CN120822927A - A collaborative monitoring method and system for capital projects based on typical construction periods - Google Patents

Abstract

The present application relates to the field of data processing technology, and discloses a collaborative monitoring method and system for capital projects based on typical construction periods. The method comprises: performing indicator correlation analysis and processing on a multi-dimensional collaborative planning system to obtain a collaborative monitoring indicator system and a data collection scheme with a hierarchical structure; based on the data collection scheme, performing data collection according to the collaborative monitoring indicator system to obtain target collection data, and dynamically analyzing and processing the target collection data to obtain a project monitoring data set; performing multi-level response strategy analysis and processing on the project monitoring data set through a decision tree algorithm to obtain a collaborative response mechanism; performing effect evaluation and processing on the execution results of the collaborative response mechanism through an iterative optimization algorithm to obtain a construction period benchmark parameter set and monitoring and early warning rules. The present application improves the efficiency and accuracy of collaborative monitoring of capital projects based on typical construction periods.

Description

Capital project collaborative monitoring method and system based on typical construction period

Technical Field

The application relates to the field of data processing, in particular to a method and a system for collaborative monitoring of capital projects based on typical construction periods.

Background

As capital projects continue to scale up and complexity continues to rise, project management faces many challenges such as multiparty collaboration, resource allocation and progress control. At present, informatization means are widely adopted in the industry for project monitoring, including project management software planning, field data acquisition by using the Internet of things technology, progress evaluation by applying a data analysis method and the like. The technical means improves the project management level to a certain extent and provides data support for project decision.

However, the existing project monitoring method has the defects that firstly project monitoring is often dependent on experience judgment, deep mining and analysis on historical data are lacked, scientific construction period reference parameters are difficult to establish, secondly the cooperative efficiency of all participants is low, information sharing is not timely, problem discovery is delayed, response is not quick, a monitoring index system is not perfect enough, multi-dimensional comprehensive evaluation is difficult to achieve, an early warning mechanism is simple, accurate prediction cannot be carried out, and finally a resource allocation scheme is lack of an optimization mechanism, so that the situation of unbalanced resource allocation is often caused.

Disclosure of Invention

The application provides a method and a system for collaborative monitoring of capital items based on typical construction period, which are used for improving the accuracy of collaborative monitoring of the capital items based on typical construction period.

The application provides a typical construction period-based capital project collaborative monitoring method, which comprises the steps of carrying out feature extraction and cluster analysis processing on historical project data to obtain project typical construction period benchmark parameters, carrying out multidimensional plan decomposition processing on the project typical construction period benchmark parameters to obtain a multidimensional collaborative plan system, carrying out index relevance analysis processing on the multidimensional collaborative plan system to obtain a collaborative monitoring index system with a hierarchical structure and a data acquisition scheme, carrying out data acquisition according to the collaborative monitoring index system based on the data acquisition scheme to obtain target acquisition data, carrying out dynamic analysis processing on the target acquisition data to obtain a project monitoring data set, carrying out multi-level response strategy analysis processing on the project monitoring data set through a decision tree algorithm to obtain a collaborative response mechanism, and carrying out effect evaluation processing on an execution result of the collaborative response mechanism through an iterative optimization algorithm to obtain a construction period benchmark parameter set and a monitoring early warning rule.

In a second aspect, the present application provides a typical construction period based capital project collaborative monitoring system comprising:

The extraction module is used for carrying out feature extraction and cluster analysis processing on the historical project data to obtain project typical construction period benchmark parameters;

the decomposition module is used for carrying out multi-dimensional plan decomposition processing on the project typical construction period reference parameters to obtain a multi-dimensional collaborative planning system;

The analysis module is used for carrying out index correlation analysis processing on the multi-dimensional collaborative planning system to obtain a collaborative monitoring index system with a hierarchical structure and a data acquisition scheme;

The acquisition module is used for acquiring data according to the collaborative monitoring index system based on the data acquisition scheme to obtain target acquisition data, and dynamically analyzing and processing the target acquisition data to obtain a project monitoring data set;

The processing module is used for carrying out multi-level response strategy analysis processing on the project monitoring data set through a decision tree algorithm to obtain a cooperative response mechanism;

And the evaluation module is used for performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm to obtain a construction period reference parameter set and a monitoring and early warning rule.

According to the technical scheme provided by the application, the characteristic extraction and the cluster analysis processing are carried out on the historical project data to obtain the scientific and reasonable project typical construction period benchmark parameter, a reliable reference basis is provided for construction period control, and the multidimensional collaborative planning system comprising progress, resources and interface relations is formed by carrying out the multidimensional planning decomposition processing on the project typical construction period benchmark parameter, so that systematic decomposition and collaborative management of the project plan are realized. On the basis, through index relevance analysis processing on the multi-dimensional collaborative planning system, a collaborative monitoring index system with distinct hierarchy and a data acquisition scheme are constructed, and the comprehensiveness and accuracy of monitoring data are ensured. The target data acquired based on the data acquisition scheme is dynamically analyzed and processed to obtain a monitoring data set reflecting the running state of the project, and data support is provided for abnormality identification and early warning. And a decision tree algorithm is adopted to carry out multi-level response strategy analysis on the project monitoring data set, a scientific cooperative response mechanism is established, and timeliness and effectiveness of problem processing are improved. And finally, performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm, so that the dynamic update of the construction period reference parameters and the monitoring and early warning rules is realized, and the continuous improvement of a monitoring system is ensured. The method organically combines the technologies of data analysis, early warning prediction, cooperative response and the like, forms a closed-loop monitoring management system, and remarkably improves the construction period control level and the cooperative management efficiency of capital items.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained based on these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of one embodiment of a method for collaborative monitoring of capital projects based on typical construction periods in accordance with an embodiment of the application;

FIG. 2 is a schematic diagram of one embodiment of a typical construction period based capital project collaborative monitoring system in accordance with an embodiment of the application.

Detailed Description

The embodiment of the application provides a capital project collaborative monitoring method and system based on a typical construction period. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, a detailed flow of an embodiment of the present application is described below with reference to fig. 1, and one embodiment of a method for collaborative monitoring of capital items based on typical construction periods in an embodiment of the present application includes:

Step S101, carrying out feature extraction and cluster analysis processing on historical project data to obtain project typical construction period benchmark parameters;

Step S102, carrying out multi-dimensional plan decomposition processing on project typical construction period reference parameters to obtain a multi-dimensional collaborative planning system;

step S103, carrying out index correlation analysis processing on the multi-dimensional collaborative planning system to obtain a collaborative monitoring index system with a hierarchical structure and a data acquisition scheme;

step S104, based on a data acquisition scheme, carrying out data acquisition according to a collaborative monitoring index system to obtain target acquisition data, and carrying out dynamic analysis processing on the target acquisition data to obtain a project monitoring data set;

Step S105, carrying out multi-level response strategy analysis processing on the project monitoring data set through a decision tree algorithm to obtain a cooperative response mechanism;

and S106, performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm to obtain a construction period reference parameter set and a monitoring and early warning rule.

It will be appreciated that the subject of the present application may be a capital project collaborative monitoring system based on typical construction periods, or may be a terminal or server, and is not limited in this regard. The embodiment of the application is described by taking a server as an execution main body as an example.

Specifically, the historical project data is processed through data cleaning, and a standardized historical data set is obtained through the modes of eliminating abnormal values, supplementing missing values and the like according to project scale (building area, equipment number and the like), investment limit (total investment amount, sub-project investment and the like) and construction period (start date, finish date and the like) data. And carrying out time sequence segmentation on the standardized historical data set, dividing the project into a preparation stage, a construction stage and a ending stage, setting key nodes in each stage, and recording time points to form time sequence data. And aiming at project key node time sequence data, carrying out classification statistics according to project types (such as industrial buildings, civil buildings and the like), and calculating characteristic values such as average construction period, construction period variance and the like of various projects at different stages to form construction period distribution characteristics. And adopting a principal component analysis algorithm to reduce the dimension of the construction period distribution characteristics, and extracting core factors influencing the construction period. For example, in an industrial building project, the main component analysis finds that the equipment purchase period, the base construction time and the equipment installation and debugging time are main factors influencing the total construction period, and the contribution rates are 35%, 28% and 22% respectively.

And performing correlation calculation on the core construction period influence factors, establishing a correlation matrix among the factors, and determining the weight coefficient of each factor through parameter calibration. Classifying the items through a hierarchical clustering algorithm to obtain an item type feature library. For example, industrial buildings with investment limit of more than 10 hundred million yuan and building area of more than 5 ten thousand square meters are divided into large-scale industrial building categories, and typical construction period reference parameters comprise equipment purchasing period of 12-15 months, basic construction time of 6-8 months and equipment installation and debugging time of 4-6 months. And carrying out multidimensional plan decomposition according to project typical construction period reference parameters, firstly constructing a project overall plan framework, determining working contents and time nodes of each stage, and forming a key node plan table. And (3) analyzing the resource demand, calculating the quantity of resources such as manpower, equipment, materials and the like required by each stage, compiling a resource allocation list, balancing time sequence and generating a resource allocation scheme. And identifying a cooperative interface in the plan, determining the cooperative relationship of each participant, forming a plan cooperative node table, and finally obtaining a multidimensional cooperative plan system.

And carrying out index relevance analysis on the multi-dimensional collaborative planning system, dividing monitoring dimensions such as progress, quality, cost and safety, and setting specific index parameters of each dimension. The indexes are divided into primary indexes, secondary indexes and the like through hierarchical classification, the association degree among the indexes is calculated, and an index influence relation matrix is established. And determining data sources and acquisition frequencies according to the index characteristics, and formulating data acquisition standards to form a collaborative monitoring index system and a data acquisition scheme. And collecting project operation data based on a data acquisition scheme, and preprocessing and standardizing the acquired data to obtain a standardized data stream. Extracting time sequence features, performing data training by using a neural network algorithm, setting an early warning threshold value, and predicting project states. The neural network adopts a three-layer structure, the input layer contains monitoring index data, the hidden layer carries out feature learning, and the output layer predicts the project state. And identifying an abnormal mode, establishing an early warning judging rule, and finally forming a project monitoring data set.

And analyzing the project monitoring data set by using a decision tree algorithm to construct a multi-level response strategy. Each node of the decision tree represents a judgment condition, such as a progress delay exceeding 5%, a cost hyperbranched exceeding 3%, and the like, and the branch nodes correspond to different response measures. And analyzing the resource demand according to the response decision path, formulating a deployment strategy and priority, forming a resource allocation scheme, and establishing a cooperative response mechanism. And evaluating the execution effect of the cooperative response mechanism, collecting the item data after response, and calculating the deviation from the target to obtain an effect evaluation index. Parameters are continuously adjusted through an iterative optimization algorithm, and the construction period reference parameters and the early warning rules are updated. The iterative optimization algorithm adopts a gradient descent method, and an optimization objective function is F=w1× (actual construction period-planned construction period) 2+w2× (actual cost-planned cost) 2+w3× (quality standard-reaching rate-target standard-reaching rate) 2, wherein w1, w2 and w3 are weight coefficients.

Taking a certain large industrial building project as an example, obtaining the construction period standard parameters of 14 months of equipment purchasing period, 7 months of foundation construction and 5 months of equipment installation based on historical data analysis. In the project execution process, the purchase progress of the equipment is found to be delayed for 15 days through cooperative monitoring, and the cost is 2%. The decision tree analysis gives a response scheme for adjusting the purchasing strategy and increasing the construction team. After the response measures are executed, the progress delay is shortened to 7 days, and the cost is controlled within 1%. Through iterative optimization, the updated equipment purchasing period reference parameter is adjusted to 14.5 months, and the progress delay threshold in the early warning rule is adjusted to 7 days from 10 days.

In the embodiment of the application, the characteristic extraction and the cluster analysis processing are carried out on the historical project data to obtain the scientific and reasonable project typical construction period benchmark parameter, a reliable reference basis is provided for construction period control, and the multidimensional collaborative planning system comprising progress, resources and interface relations is formed by carrying out the multidimensional planning decomposition processing on the project typical construction period benchmark parameter, so that systematic decomposition and collaborative management of the project plan are realized. On the basis, through index relevance analysis processing on the multi-dimensional collaborative planning system, a collaborative monitoring index system with distinct hierarchy and a data acquisition scheme are constructed, and the comprehensiveness and accuracy of monitoring data are ensured. The target data acquired based on the data acquisition scheme is dynamically analyzed and processed to obtain a monitoring data set reflecting the running state of the project, and data support is provided for abnormality identification and early warning. And a decision tree algorithm is adopted to carry out multi-level response strategy analysis on the project monitoring data set, a scientific cooperative response mechanism is established, and timeliness and effectiveness of problem processing are improved. And finally, performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm, so that the dynamic update of the construction period reference parameters and the monitoring and early warning rules is realized, and the continuous improvement of a monitoring system is ensured. The method organically combines the technologies of data analysis, early warning prediction, cooperative response and the like, forms a closed-loop monitoring management system, and remarkably improves the construction period control level and the cooperative management efficiency of capital items.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Carrying out data cleaning treatment on project scale, investment limit and construction period in the historical project data to obtain a standardized historical data set, and carrying out time sequence segmentation treatment on the standardized historical data set to obtain project key node time sequence data;

(2) Carrying out classified statistical treatment on the project key node time sequence data according to the project types to obtain project type construction period distribution characteristics, and carrying out characteristic dimension reduction treatment on the project type construction period distribution characteristics through a principal component analysis algorithm to obtain core construction period influence factors;

(3) Performing correlation calculation processing on the core construction period influence factors to obtain construction period influence factor weight matrixes, and performing parameter calibration processing on the construction period influence factor weight matrixes to obtain construction period reference parameter tables;

(4) Carrying out item classification processing on the project standard parameter table through a hierarchical clustering algorithm to obtain a project type feature library, and carrying out standard parameter extraction processing according to the project type feature library to obtain a standard project parameter set;

(5) And carrying out statistical analysis processing on the standard construction period parameter set to obtain construction period influence key factors, and carrying out weight calculation processing on the construction period influence key factors to obtain project typical construction period benchmark parameters and project typical construction period benchmark parameters.

Specifically, the data cleaning process is performed on the historical project data, and the historical project data comprises three major types of data, namely project scale (such as building area, equipment number, device scale and the like), investment limit (project total investment, sub-project investment, equipment investment and the like), and construction period (start date, finish date, construction period of each stage and the like). The data cleaning comprises the steps of removing abnormal values (values exceeding a normal interval), supplementing missing values (filled by similar item average values), and unifying data formats (unifying time formats, unit conversion and the like) to obtain a standardized historical data set which is standardized and can be directly used. And carrying out time sequence segmentation processing on the standardized historical data set, dividing the whole project period into three main stages of project preparation stage (including early batch reporting, design and the like), construction implementation stage (including civil engineering, installation and the like) and completion acceptance stage, setting key nodes in each stage, such as a design completion time point, a main structure completion time point, a device installation completion time point and the like, and recording the time sequence data of key nodes formed by the time nodes.

And classifying and counting the time sequence data of the project key nodes according to project types (such as petrochemical projects, metallurgical projects, electric projects and the like), calculating the average construction period, construction period standard deviation, construction period distribution interval and other statistical characteristics of various projects at different stages, and forming project type construction period distribution characteristics. And performing dimension reduction treatment on the construction period distribution characteristics by adopting a principal component analysis algorithm, wherein the principal component analysis firstly calculates characteristic values and characteristic vectors, and selects the characteristic vector corresponding to the characteristic values with the accumulated contribution rate reaching more than 85% as the principal component, so as to finally obtain core factors influencing the construction period, such as equipment purchasing period, construction difficulty coefficients, climate influence coefficients and the like. And performing correlation calculation on the core construction period influence factors, calculating the correlation degree among the factors by adopting a Pearson correlation coefficient method, establishing a factor correlation matrix, determining the initial weight of each factor by adopting an expert scoring method, and correcting the weight by combining a correlation analysis result to finally obtain a construction period influence factor weight matrix. Calibrating parameters in the construction period influence factor weight matrix, determining influence degree of each factor on the construction period through regression analysis, and establishing a construction period prediction equation to form a construction period reference parameter table.

Classifying items in a construction period reference parameter table by adopting a hierarchical clustering algorithm, firstly calculating Euclidean distance between the items by hierarchical clustering, and then gradually merging the categories closest to the items by adopting a shortest distance method until the number of the categories reaches a preset number, so as to obtain an item type feature library. And extracting construction period characteristic parameters of various projects based on the project type characteristic library, such as standard construction period of each stage, construction period floating range and the like, and forming a standard construction period parameter set. And carrying out statistical analysis on the standard construction period parameter set, calculating statistics such as mean value, variance, distribution characteristics and the like of each parameter, and identifying key factors which have obvious influence on the construction period. And calculating weights of key factors influencing the construction period by adopting an analytic hierarchy process, firstly constructing a judgment matrix, carrying out consistency test to obtain weight values of the factors, and finally forming project typical construction period reference parameters.

Taking a certain large petrochemical project as an example, 100 pieces of standardized data of historical projects are obtained through data cleaning processing. After the time sequence is segmented, 8 key nodes such as design completion, civil engineering completion, equipment installation and the like are determined. The principal component analysis found that the cumulative contribution rate of the three factors of the equipment arrival period, the foundation construction period and the equipment installation period reached 87%, and the cumulative contribution rate was determined as the core construction period influencing factor. The correlation analysis showed that the correlation coefficient of the equipment arrival period and the total construction period was 0.82, the correlation coefficient of the base construction period and the total construction period was 0.75, and the correlation coefficient of the equipment installation period and the total construction period was 0.68. The project is divided into three types of large (more than 50 hundred million investment), medium (10-50 hundred million investment) and small (less than 10 hundred million investment) by hierarchical clustering, and the project period parameters of various projects are extracted. Typical construction period standard parameters of the finally obtained large petrochemical project are 12 months of design period (floating range + -1.5 months), 18 months of civil construction period (floating range + -2 months), 15 months of equipment installation period (floating range + -2 months) and 45 months of total construction period.

In a specific embodiment, the process of executing step S102 may specifically include the following steps:

(1) Carrying out planning level construction processing on the typical construction period reference parameters and the project typical construction period reference parameters to obtain a project overall plan frame, and carrying out milestone node decomposition processing on the project overall plan frame to obtain a key node plan table;

(2) Performing resource demand analysis processing on the key node schedule to obtain a resource allocation list, and performing time sequence balance processing on the resource allocation list to obtain a resource allocation scheme;

(3) And carrying out interface identification processing on the resource allocation scheme to obtain a planning cooperative node table, and carrying out dependency analysis processing on the planning cooperative node table to obtain a multi-dimensional cooperative planning system.

Specifically, the typical construction period reference parameters (including standard construction period values such as design period, purchasing period and construction period) and project typical construction period reference parameters (including specific construction period parameters of various projects) are compared and analyzed, and a project plan hierarchical structure is established. The planning hierarchy includes an overall planning layer (project overall construction period plan), a professional planning layer (professional planning for design, purchase, construction, etc.), and a control planning layer (concrete implementation planning for month, zhou Du, etc.), forming a project overall planning framework. And (3) performing milestone node decomposition on the project overall plan framework, and dividing the project overall construction period into a plurality of work packages according to the key nodes. The milestone nodes comprise design completion nodes, equipment ordering nodes, main structure capping nodes, single machine test nodes, linkage test nodes and the like, and each node is provided with control elements such as scheduling completion time, delivery results and the like. By analyzing the time sequence relation of the milestone nodes, a key node schedule is compiled, and the factors such as the scheduled starting time, the scheduled finishing time, the duration time and the like of each node are defined.

And (3) carrying out resource demand analysis based on a key node schedule, and calculating the quantity and the service time of human resources (such as designers, constructors and the like), equipment resources (such as gantry cranes, crawler cranes and the like) and material resources (such as steel materials, concrete and the like) required by each work package. The resource demand data is derived from technical files such as engineering quantity lists, construction schemes and the like, and is calculated by combining construction process requirements and production rate standards to form a resource allocation list. And (3) carrying out time sequence balance processing on the resource allocation list, firstly identifying peak periods and valley periods of resource use, and calculating the resource utilization rate. When the excessive concentration of the resources or the idle of the resources occurs, the balanced use of the resources is realized by adjusting the working sequence, optimizing the construction process, reasonably arranging the working time and the like. And forming a resource allocation scheme after time sequence balance, wherein the resource allocation scheme comprises a detailed use plan and allocation strategy of various resources.

Interface identification is carried out aiming at a resource allocation scheme, and working interfaces among all participants (such as owners, design units, construction units, suppliers and the like) are combed. The interface types include a time interface (work handover time point), a technology interface (technology document delivery), a management interface (communication coordination mode), and the like. And the identified interface information is arranged into a planned cooperative node table, and factors such as a responsibility main body, cooperative content, time requirement and the like of each interface are defined. And carrying out dependency analysis on the plan collaboration node table, and determining the logical relationship between works by adopting a network planning technology. The dependency types include a completion-start type (a next job can be started after a previous job is completed), a start-start type (both jobs start at the same time), a completion-completion type (both jobs complete at the same time), and the like. And identifying a critical path through analyzing the dependency relationship, determining a construction period control key point, and finally forming a multi-dimensional collaborative planning system.

Taking a certain large-scale electric power project as an example, a three-layer planning system is constructed through a planning hierarchy, wherein the overall plan comprises a project total construction period of 36 months, the professional plan comprises 12 months of design, 18 months of purchase and 24 months of construction, and the control plan is refined into a month and Zhou Du plan. The milestone node decomposition determines 15 key nodes including preliminary design completion (4 months), construction map design completion (12 months), master order (6 months), master arrival (18 months), civil construction completion (20 months), equipment installation completion (30 months), commissioning completion (36 months), etc. The analysis result of the resource demand shows that 25 large-scale mechanical equipment is needed by 80 designers, 600 constructors and the like in the peak period. The peak value of the demand of constructors is reduced from 600 to 450 through time sequence balance, and the peak value of the demand of mechanical equipment is reduced from 25 to 18. The interface identification discovers 54 cooperative nodes, including 20 interfaces for design and construction, 15 interfaces for construction and debugging, and the like. The dependency analysis determines three critical paths throughout the project, namely a design critical path (12 months), a device critical path (18 months) and a construction critical path (24 months), and corresponding control measures and a cooperative mechanism are formulated according to the three critical paths.

In a specific embodiment, the process of executing step S103 may specifically include the following steps:

(1) Performing monitoring dimension division processing on the multi-dimension collaborative planning system to obtain a monitoring index parameter set, and performing hierarchical classification processing on the monitoring index parameter set to obtain an index classification table;

(2) Performing inter-index association degree calculation processing on the index classification table to obtain an index influence relation matrix, and performing data source identification processing on the index influence relation matrix to obtain a data acquisition element table;

(3) And carrying out acquisition frequency setting processing on the data acquisition element table to obtain a data acquisition standard, and carrying out data format standardization processing on the data acquisition standard to obtain a collaborative monitoring index system and a data acquisition scheme.

Specifically, the multidimensional collaborative planning system is subjected to monitoring dimension division, and monitoring indexes are divided into five categories of progress dimension (construction period progress, workload completion and the like), quality dimension (construction quality, material quality and the like), cost dimension (investment control, expense and the like), safety dimension (safety accidents, hidden trouble correction and the like) and resource dimension (manpower configuration, equipment utilization and the like). Setting specific monitoring parameters under each dimension, wherein the progress dimension comprises parameters such as a planned completion rate, a construction period deviation rate, a milestone completion rate and the like, and the quality dimension comprises parameters such as a primary acceptance rate, a quality defect number, a rework rate and the like, so that a monitoring index parameter set is formed. And carrying out level classification on the monitoring index parameter set, and dividing the indexes into a first-level index, a second-level index and a third-level index. The primary index is a five-dimensional overall index, such as overall progress completion rate, the secondary index is a main control index in each dimension, such as design progress completion rate and construction progress completion rate, and the tertiary index is a specific assessment index, such as construction drawing design completion rate and main structure completion rate. And (3) defining the calculation method, the assessment standard and the control requirement of each level index through level classification to form an index classification table. And carrying out association degree calculation on each index in the index grading table, and determining the degree of interaction between the indexes by adopting a gray association analysis method. Firstly, a reference number sequence and a comparison number sequence are determined, the historical data of each index is normalized, then the correlation coefficient is calculated, and the correlation value is obtained. The higher the correlation value is, the stronger the correlation between indexes is, and the obvious correlation exists between indexes with the correlation degree larger than 0.8. And (3) arranging the calculation results into an index influence relation matrix, wherein each element in the matrix represents the association strength between two indexes.

And carrying out data source identification on the index influence relation matrix, and combing the data acquisition path of each index. The data sources comprise channels such as project management platforms, field acquisition equipment, manual filling and the like. And determining a main data source and a standby data source according to each index, and defining the responsibility unit, the acquisition mode and the data format requirement of data acquisition to form a data acquisition element table. The data acquisition element table records the information of data items, data types, value ranges, measurement units and the like of each index in detail. And setting the acquisition frequency of each index based on the data acquisition element table, and determining different acquisition periods according to the index importance degree, the change speed and the control requirement. The real-time acquisition index (such as safety monitoring data) is acquired once every minute, the high-frequency acquisition index (such as construction progress) is acquired once every day, and the conventional acquisition index (such as cost data) is acquired once every week, so that the data acquisition standard is formed. The acquisition specification clearly defines the contents of time nodes, acquisition modes, quality requirements and the like of data acquisition.

And carrying out data format standardization processing on the data acquisition standard, and unifying the expression form, the measurement unit and the precision requirement of the data. For example, the time data is in a 'year-month-day: minute: second' format, the percentage data is reserved in two decimal places, and the monetary amount is used in ten thousand yuan units. Through standardized processing, the consistency and comparability of data are ensured, and finally, a complete collaborative monitoring index system and a data acquisition scheme are formed.

Taking a petrochemical project as an example, a monitoring index parameter set containing 72 specific indexes is determined through monitoring dimension division. The method comprises the steps of 20 indexes of a progress dimension, 15 indexes of a quality dimension, 12 indexes of a cost dimension, 13 indexes of a safety dimension and 12 indexes of a resource dimension. In an index classification table formed by hierarchical classification, 5 primary indexes, 18 secondary indexes and 49 tertiary indexes are used. The grey correlation analysis finds that the correlation between the equipment arrival rate and the construction progress completion rate is 0.92, the correlation between the constructor arrival rate and the construction progress is 0.88, and the correlation between the quality defect correction rate and the one-time acceptance rate is 0.85. Data source identification shows that 45% of index data comes from the project management platform, 35% comes from the on-site collection equipment, and 20% requires manual reporting. The acquisition frequency setting result is that 10 indexes need to be acquired in real time, 25 indexes are acquired once a day, and 37 indexes are acquired once a week. The standardized processing unifies 8 data formats and 12 measurement units, and a complete data acquisition standard is formed.

In a specific embodiment, the process of executing step S104 may specifically include the following steps:

(1) Based on a data acquisition scheme, carrying out data acquisition according to a collaborative monitoring index system to obtain target acquisition data;

(2) Performing data preprocessing and standardization processing on target acquisition data to obtain a standardized data stream, and performing time sequence feature extraction processing on the standardized data stream to obtain a dynamic feature sequence;

(3) Carrying out data training processing on the dynamic characteristic sequence through a neural network to obtain an early warning threshold parameter set, and carrying out index prediction calculation processing on the early warning threshold parameter set to obtain a state prediction result;

(4) And carrying out abnormal mode identification processing on the state prediction result to obtain an early warning discrimination rule, and carrying out association analysis processing on the early warning discrimination rule to obtain an item monitoring data set.

Specifically, according to the acquisition frequency and the acquisition mode determined by the data acquisition scheme, the data acquisition is carried out on the indexes in the collaborative monitoring index system. The real-time acquisition index records data once every minute through the acquisition equipment, the high-frequency acquisition index acquires data at regular time every day, and the conventional acquisition index collects data according to the period. The collected data content comprises progress data (such as construction drawing design progress, equipment purchasing progress, construction actual progress and the like), quality data (such as primary acceptance rate, quality defect number and the like), cost data (such as actual investment amount, cost expenditure and the like), safety data (such as safety accident number, hidden danger correction condition and the like), resource data (such as personnel arrival rate, equipment utilization rate and the like) and forms target collected data. The target acquisition data is subjected to data preprocessing, including data cleaning (abnormal value and error data removal), missing value processing (adjacent value filling or average value filling), data alignment (uniform sampling time) and other operations. And then carrying out standardization processing, uniformly converting the data with different dimensions into the same scale range, and mapping the data into a 0-1 interval by adopting a maximum and minimum standardization method to obtain a standardized data stream. And extracting time sequence features of the normalized data stream, calculating statistical features such as a sliding average value (reflecting data trend), a standard deviation (reflecting data fluctuation), a change rate (reflecting data change speed) and the like, and extracting time sequence mode features by combining project stage features to form a dynamic feature sequence.

And the neural network algorithm is adopted to carry out data training on the dynamic characteristic sequence, and the neural network structure comprises an input layer (each index characteristic data), a hidden layer (data characteristic learning) and an output layer (early warning state judgment). The training data set comprises normal data samples and abnormal data samples in the history item, and the network weight is adjusted through a back propagation algorithm, so that the network has early warning judging capability. And after training is finished, an early warning threshold parameter set of each index is obtained, wherein the early warning threshold parameter set comprises a primary early warning threshold (attention is prompted), a secondary early warning threshold (intervention is needed), a tertiary early warning threshold (processing is needed) and the like. And carrying out index prediction calculation on the early warning threshold parameter set, and predicting index change conditions in a future period of time based on the current data and the historical trend to obtain a state prediction result. And carrying out abnormal mode identification on the state prediction result, comparing the prediction value with an early warning threshold value, and identifying abnormal conditions beyond the threshold value range. The abnormality modes include types of abrupt abnormality (abrupt change of the index in a short period), gradual abnormality (continuous deviation of the index from the target value), periodic abnormality (abnormal fluctuation of the index), and the like. And according to the characteristics and the influence degree of the abnormal mode, a corresponding early warning judgment rule is formulated. And carrying out association analysis on the early warning discrimination rules, researching early warning association relations among different indexes, establishing an early warning conduction mechanism, and finally forming a complete project monitoring data set.

Taking a nuclear power station construction project as an example, 72 monitoring index data including 35 progress indexes, 15 quality indexes, 12 cost indexes and 10 safety indexes are acquired every day according to a data acquisition scheme. Outliers accounting for 3% of the total data amount were removed by data preprocessing, and missing values of 1.5% were filled. After the normalization treatment, the characteristics of the 10-day sliding average value, standard deviation, change rate and the like of each index are calculated. Training is carried out by adopting a three-layer neural network, 72 nodes (corresponding to 72 indexes) of an input layer, 120 nodes of a hidden layer and 3 nodes (corresponding to three early warning levels) of an output layer are arranged. Training was performed using 1000 historical data samples, including 850 normal samples and 150 abnormal samples, with network convergence after 200 rounds of training. The early warning threshold values of the construction progress indexes of the main structure are set to be primary early warning (the progress deviation is 5% -10%), secondary early warning (the progress deviation is 10% -15%) and tertiary early warning (the progress deviation is more than 15%). Predictive calculation shows that the progress deviation of a certain construction section reaches 12% within 15 days in the future, and secondary early warning is triggered. The abnormal pattern recognition finds that the method belongs to gradual change abnormality, has obvious relevance with insufficient labor force and low equipment in-place rate, has relevance coefficients of 0.85 and 0.82 respectively, and needs to adjust a resource allocation scheme in time.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Performing early warning grade division processing on the project monitoring data set to obtain a grading response strategy table, and performing decision rule extraction processing on the grading response strategy table to obtain a response decision path;

(2) Performing resource demand analysis processing on the response decision path to obtain a resource allocation strategy, and performing priority calculation processing on the resource allocation strategy to obtain a resource allocation scheme;

(3) And carrying out cooperative mechanism construction processing on the resource allocation scheme to obtain a cooperative response mechanism.

Specifically, the project monitoring data sets are divided into three levels, namely, primary early warning (with slight abnormality of the index and attention), secondary early warning (with obvious abnormality of the index and intervention), and tertiary early warning (with serious abnormality of the index and treatment). Setting response strategies for different early warning grades, wherein the response strategies comprise response time limit requirements (response within 24 hours of primary early warning, response within 12 hours of secondary early warning and response within 4 hours of tertiary early warning), response measure requirements (monitoring enhancement is adopted for primary early warning, adjustment and optimization are implemented for secondary early warning, emergency plan is started for tertiary early warning), and response responsibility person requirements (primary early warning project manager is responsible, secondary early warning branch leader is responsible and tertiary early warning total manager is responsible) to form a hierarchical response strategy table. And applying a decision tree algorithm to the hierarchical response strategy table to extract decision rules, wherein nodes of the decision tree comprise judging conditions (such as more than 10% of progress delay, more than 5% of cost hyperbranched, more than 3 quality defects and the like), and branch paths correspond to different processing measures. And extracting effective decision rules by analyzing the processing experience in the historical cases, and classifying and sorting according to the early warning level, the response type, the processing measures and other factors to obtain a response decision path. The response decision path defines the complete process flow from early warning triggering to problem solving.

And analyzing the resource demand aiming at the response decision path, and calculating the quantity of various resources required by the processing measure. The resource types include human resources (e.g., technicians, construction personnel, etc.), equipment resources (e.g., construction machinery, inspection equipment, etc.), material resources (e.g., building materials, spare parts, etc.), capital resources, etc. And according to the workload and implementation period of the treatment measures, the production efficiency and the use efficiency of the resources are combined, the resource demand is calculated, and a resource allocation strategy is formed. The resource allocation policy includes an allocation scheme, a usage plan, and an exit schedule for the resource. And (3) carrying out priority calculation on the resource allocation strategy, and setting priority evaluation indexes including a construction period influence degree (construction period delay days), a cost influence degree (cost hyperbranched amount), a quality influence degree (quality defect grade), a safety influence degree (safety risk grade) and the like. And determining the weight of each index by adopting an analytic hierarchy process, calculating the comprehensive scores of different allocation schemes, and sorting according to the scores to obtain a resource allocation scheme. The resource allocation scheme specifies the specific allocation quantity, the use time and the input sequence of various resources.

And constructing a cooperative mechanism based on a resource allocation scheme, setting a cooperative organization architecture (comprising a decision layer, a management layer and an execution layer), establishing a communication cooperative mechanism (comprising an example meeting system, a reporting system and a contact system), and formulating an assessment reward and punishment mechanism (comprising performance assessment standards and reward and punishment measures) to form a complete cooperative response mechanism. The cooperative response mechanism ensures the effective cooperation of all the participants in the early warning process.

Taking a construction project of a chemical device as an example, a project monitoring data set displays that the installation progress of main equipment is abnormal. Through the early warning grade division, the progress is delayed for 15 days, and the construction period deviation rate is 12%, and the method belongs to secondary early warning. The decision rule extraction shows that when the equipment installation progress is delayed for more than 10 days and the deviation rate is more than 10%, construction teams are required to be added and the construction process is required to be adjusted. The resource demand analysis shows that 30 welders, 2 lifting equipment and 5 tool clamps are added in the treatment measures, and the construction period is 20 days. And the priority calculation results comprise the problem construction period influence degree 0.8 (weight 0.4), the cost influence degree 0.6 (weight 0.3), the quality influence degree 0.7 (weight 0.2), the safety influence degree 0.5 (weight 0.1), the comprehensive score 0.69 and the second ranking among all the problems to be processed. And finally, determining to allocate a welder team from other projects, temporarily renting hoisting equipment from an equipment renting company, and calling a fixture from a spare part library. And establishing a three-level coordination mechanism, namely, a project manager hosts a coordination meeting every day, an electromechanical construction manager reports the progress every 4 hours, and a field manager checks the construction condition every 2 hours. After 10 days of implementation, the progress delay is shortened to 5 days, the deviation rate is reduced to 4%, and the early warning is released.

In a specific embodiment, the process of executing step S106 may specifically include the following steps:

(1) Performing effect data acquisition processing on the processing result of the cooperative response mechanism to obtain a response effect data set, and performing deviation analysis processing on the response effect data set to obtain an effect evaluation index;

(2) Performing target comparison processing on the effect evaluation index to obtain an improved direction parameter, and performing reference parameter updating processing on the improved direction parameter to obtain a candidate reference parameter;

(3) And carrying out rule extraction processing on the candidate reference parameters to obtain an early warning rule set, and carrying out verification processing on the early warning rule set to obtain the construction period reference parameters and the monitoring early warning rules.

Specifically, the effect data collection is performed on the processing result of the cooperative response mechanism, including collecting various index data before and after the implementation of the response measure, such as progress index (construction period deviation, completion rate, etc.), quality index (one-time acceptance qualification rate, defect number, etc.), cost index (investment deviation, expense, etc.), resource index (personnel utilization rate, equipment utilization rate, etc.). The collected data are sorted according to a time sequence, and index change conditions of each time point are recorded to form a response effect data set. And carrying out deviation analysis on the response effect data set, and calculating the change quantity and the change rate of the indexes before and after the implementation of the response measures. And obtaining the absolute deviation value by calculating the difference between the actual value and the target value, and obtaining the relative deviation rate by calculating the ratio of the deviation value to the target value. And carrying out statistical analysis on the deviation data, calculating statistics such as average deviation, maximum deviation, accumulated deviation and the like, and analyzing the variation trend of the deviation to obtain an effect evaluation index. The effect evaluation index reflects the processing effect and implementation efficiency of the response measures.

And comparing and analyzing the effect evaluation index with project targets, wherein the targets comprise control requirements such as a planned construction period, a quality standard, a cost limit and the like. And identifying index items with obvious differences from the target through comparative analysis, and analyzing reasons generated by the differences, such as unreasonable setting of construction period reference parameters, loose early warning threshold, unsatisfactory response measure effects and the like. And determining the direction and content to be improved according to the analysis result, and forming an improved direction parameter. The improved direction parameters define the concrete contents to be adjusted, such as construction period reference parameters, early warning rules and the like. And carrying out reference parameter updating processing on the improved direction parameters, and correcting the original parameters according to the response effect data. The reference parameter updating adopts a sliding weighted average method, and comprehensively considers the historical reference value and the current response result to determine a new parameter value. And obtaining a group of candidate reference parameters including construction period parameters, quality control parameters, cost management parameters and the like of each stage through iterative calculation.

And carrying out rule extraction on the candidate reference parameters, and setting early warning judgment conditions based on the parameter characteristics. And establishing an early warning rule by adopting a decision tree algorithm, dividing a parameter value range into a normal interval, a concerned interval and an early warning interval, and determining processing requirements of different intervals. And forming an early warning rule set through rule induction and optimization. The early warning rule set comprises complete early warning trigger conditions and response measures. And carrying out verification processing on the early warning rule set, and selecting typical case data to carry out rule verification. And (3) evaluating the accuracy and applicability of the rule by comparing the coincidence degree of the judgment result of the analysis rule and the actual situation. And optimizing and adjusting the rule according to the verification result, and finally determining the construction period reference parameter and the monitoring and early warning rule.

Taking a certain petrochemical device construction project as an example, the effect of delay processing of the equipment installation stage progress is evaluated. The response effect data show that after the measures of adding construction groups, adjusting construction technology and the like are implemented, the 15-day progress delay is shortened to 5 days within 10 days, and the construction period deviation rate is reduced from 12% to 4%. The deviation analysis result shows that the progress recovery speed is 1 day/day (recovery is delayed for 1 day) and exceeds the original 0.8 day/day target, the resource investment is increased by 52 ten thousand yuan, the quality acceptance rate is kept at 98% within the budget range, and the requirement is met. Compared with project targets, the method has the advantages that the construction period of the equipment installation stage in the original construction period standard parameters is compact and needs to be properly adjusted, and the early warning threshold value is set too high to find problems in time. The improvement direction is determined by adjusting the construction period standard of the equipment installation stage from 60 days to 65 days, and the primary early warning threshold value is adjusted down from 10% to 8%, and the secondary early warning threshold value is adjusted down from 15% to 12%. The new construction period reference parameters, namely 65 days of construction period in the equipment installation stage and + -5 days of allowed floating range, are determined through sliding weighted average calculation. The early warning rule is set in such a way that the progress deviation is 5-8% to trigger the primary early warning, 8-12% to trigger the secondary early warning and more than 12% to trigger the tertiary early warning. And verifying the new parameters and rules, and applying the method to the equipment installation work of the following 3 sub-projects, wherein the deviation detection rate is improved to 95%, the early warning accuracy rate reaches 92%, and the verification result shows that the adjusted parameters and rules are more reasonable and effective.

The method for collaborative monitoring of a capital item based on a typical construction period in the embodiment of the present application is described above, and the system for collaborative monitoring of a capital item based on a typical construction period in the embodiment of the present application is described below, referring to fig. 2, an embodiment of the system for collaborative monitoring of a capital item based on a typical construction period in the embodiment of the present application includes:

The extraction module 201 is used for performing feature extraction and cluster analysis processing on the historical project data to obtain project typical construction period benchmark parameters;

The decomposition module 202 is configured to perform multidimensional planning decomposition processing on the project typical construction period reference parameter to obtain a multidimensional collaborative planning system;

The analysis module 203 is configured to perform index relevance analysis processing on the multi-dimensional collaborative planning system to obtain a collaborative monitoring index system with a hierarchical structure and a data acquisition scheme;

The acquisition module 204 is configured to acquire data according to the collaborative monitoring index system based on the data acquisition scheme, obtain target acquisition data, and dynamically analyze and process the target acquisition data to obtain a project monitoring data set;

The processing module 205 is configured to perform a multi-level response policy analysis processing on the item monitoring dataset through a decision tree algorithm, so as to obtain a collaborative response mechanism;

And the evaluation module 206 is configured to perform effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm, so as to obtain a construction period reference parameter set and a monitoring and early warning rule.

Through the cooperation of the components, the characteristic extraction and the cluster analysis processing are carried out on the historical project data, so that the project typical construction period benchmark parameters are obtained, a reliable reference basis is provided for construction period control, and a multi-dimensional cooperation plan system comprising progress, resources and interface relations is formed through carrying out multi-dimensional plan decomposition processing on the project typical construction period benchmark parameters, so that systematic decomposition and cooperation management of project plans are realized. On the basis, through index relevance analysis processing on the multi-dimensional collaborative planning system, a collaborative monitoring index system with distinct hierarchy and a data acquisition scheme are constructed, and the comprehensiveness and accuracy of monitoring data are ensured. The target data acquired based on the data acquisition scheme is dynamically analyzed and processed to obtain a monitoring data set reflecting the running state of the project, and data support is provided for abnormality identification and early warning. And a decision tree algorithm is adopted to carry out multi-level response strategy analysis on the project monitoring data set, a scientific cooperative response mechanism is established, and timeliness and effectiveness of problem processing are improved. And finally, performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm, so that the dynamic update of the construction period reference parameters and the monitoring and early warning rules is realized, and the continuous improvement of a monitoring system is ensured. The method organically combines the technologies of data analysis, early warning prediction, cooperative response and the like, forms a closed-loop monitoring management system, and remarkably improves the construction period control level and the cooperative management efficiency of capital items.

While the application has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that the foregoing embodiments may be modified or equivalents may be substituted for some of the features thereof, and that the modifications or substitutions do not depart from the spirit and scope of the embodiments of the application.

Claims (8)

1. A typical construction period based capital project collaborative monitoring method, characterized in that the typical construction period based capital project collaborative monitoring method comprises:

Performing feature extraction and cluster analysis processing on the historical project data to obtain project typical construction period benchmark parameters;

carrying out multi-dimensional plan decomposition processing on the project typical construction period reference parameters to obtain a multi-dimensional collaborative planning system;

performing index relevance analysis processing on the multi-dimensional collaborative planning system to obtain a collaborative monitoring index system with a hierarchical structure and a data acquisition scheme;

Based on the data acquisition scheme, carrying out data acquisition according to the collaborative monitoring index system to obtain target acquisition data, and carrying out dynamic analysis processing on the target acquisition data to obtain a project monitoring data set;

Performing multi-level response strategy analysis processing on the project monitoring data set through a decision tree algorithm to obtain a cooperative response mechanism;

and performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm to obtain a construction period reference parameter set and a monitoring and early warning rule.

2. The method for collaborative monitoring of a typical construction period-based capital project according to claim 1, wherein the performing feature extraction and cluster analysis processing on historical project data to obtain project typical construction period benchmark parameters comprises:

Carrying out data cleaning treatment on the project scale, investment limit and construction period in the historical project data to obtain a standardized historical data set, and carrying out time sequence segmentation treatment on the standardized historical data set to obtain project key node time sequence data;

Carrying out classified statistical treatment on the project key node time sequence data according to project types to obtain project type construction period distribution characteristics, and carrying out characteristic dimension reduction treatment on the project type construction period distribution characteristics through a principal component analysis algorithm to obtain core construction period influence factors;

Performing correlation calculation processing on the core construction period influence factors to obtain construction period influence factor weight matrixes, and performing parameter calibration processing on the construction period influence factor weight matrixes to obtain construction period reference parameter tables;

Performing item classification processing on the construction period reference parameter table through a hierarchical clustering algorithm to obtain an item type feature library, and performing reference parameter extraction processing according to the item type feature library to obtain a standard construction period parameter set;

And carrying out statistical analysis processing on the standard construction period parameter set to obtain construction period influence key factors, and carrying out weight calculation processing on the construction period influence key factors to obtain project typical construction period benchmark parameters.

3. The method for collaborative monitoring of a typical construction period-based capital project according to claim 1, wherein the performing a multi-dimensional plan decomposition process on the project typical construction period benchmark parameters to obtain a multi-dimensional collaborative planning system comprises:

Performing planning hierarchy construction processing on the typical construction period reference parameters and project typical construction period reference parameters to obtain a project overall planning frame, and performing milestone node decomposition processing on the project overall planning frame to obtain a key node planning table;

Performing resource demand analysis processing on the key node schedule to obtain a resource allocation list, and performing time sequence balancing processing on the resource allocation list to obtain a resource allocation scheme;

And carrying out interface identification processing on the resource allocation scheme to obtain a planning cooperative node table, and carrying out dependency analysis processing on the planning cooperative node table to obtain a multi-dimensional cooperative planning system.

4. The method for collaborative monitoring of a capital project based on a typical construction period according to claim 1, wherein the performing an index association analysis process on the multi-dimensional collaborative planning system to obtain a collaborative monitoring index system with a hierarchical structure and a data collection scheme comprises:

performing monitoring dimension division processing on the multi-dimensional collaborative planning system to obtain a monitoring index parameter set, and performing hierarchical classification processing on the monitoring index parameter set to obtain an index classification table;

performing inter-index association degree calculation processing on the index classification table to obtain an index influence relation matrix, and performing data source identification processing on the index influence relation matrix to obtain a data acquisition element table;

and carrying out acquisition frequency setting processing on the data acquisition element table to obtain a data acquisition standard, and carrying out data format standardization processing on the data acquisition standard to obtain a collaborative monitoring index system and a data acquisition scheme.

5. The collaborative monitoring method for capital projects based on typical construction periods according to claim 1, wherein the data acquisition based on the data acquisition scheme performs data acquisition according to the collaborative monitoring index system to obtain target acquisition data, and performs dynamic analysis processing on the target acquisition data to obtain project monitoring data sets, comprising:

Based on the data acquisition scheme, carrying out data acquisition according to the collaborative monitoring index system to obtain target acquisition data;

Performing data preprocessing and standardization processing on the target acquisition data to obtain a standardized data stream, and performing time sequence feature extraction processing on the standardized data stream to obtain a dynamic feature sequence;

performing data training processing on the dynamic feature sequence through a neural network to obtain an early warning threshold parameter set, and performing index prediction calculation processing on the early warning threshold parameter set to obtain a state prediction result;

and carrying out abnormal mode identification processing on the state prediction result to obtain an early warning judgment rule, and carrying out association analysis processing on the early warning judgment rule to obtain an item monitoring data set.

6. The method for collaborative monitoring of a capital project based on a typical construction period according to claim 1, wherein the performing a multi-level response policy analysis process on the project monitoring dataset through a decision tree algorithm to obtain a collaborative response mechanism comprises:

Performing early warning grade division processing on the project monitoring data set to obtain a grading response strategy table, and performing decision rule extraction processing on the grading response strategy table to obtain a response decision path;

Performing resource demand analysis processing on the response decision path to obtain a resource allocation strategy, and performing priority calculation processing on the resource allocation strategy to obtain a resource allocation scheme;

and carrying out cooperative mechanism construction processing on the resource allocation scheme to obtain a cooperative response mechanism.

7. The method for collaborative monitoring of a capital item based on a typical construction period according to claim 1, wherein performing effect evaluation processing on the execution result of the collaborative response mechanism by an iterative optimization algorithm to obtain a construction period benchmark parameter set and a monitoring and early warning rule comprises:

performing effect data acquisition processing on the processing result of the cooperative response mechanism to obtain a response effect data set, and performing deviation analysis processing on the response effect data set to obtain an effect evaluation index;

performing target comparison processing on the effect evaluation index to obtain an improved direction parameter, and performing reference parameter updating processing on the improved direction parameter to obtain a candidate reference parameter;

And carrying out rule extraction processing on the candidate reference parameters to obtain an early warning rule set, and carrying out verification processing on the early warning rule set to obtain a construction period reference parameter and a monitoring early warning rule.

8. A typical construction period based capital project collaborative monitoring system for implementing the typical construction period based capital project collaborative monitoring method according to any one of claims 1-7, characterized in that the typical construction period based capital project collaborative monitoring system comprises:

The extraction module is used for carrying out feature extraction and cluster analysis processing on the historical project data to obtain project typical construction period benchmark parameters;

the decomposition module is used for carrying out multi-dimensional plan decomposition processing on the project typical construction period reference parameters to obtain a multi-dimensional collaborative planning system;

The analysis module is used for carrying out index correlation analysis processing on the multi-dimensional collaborative planning system to obtain a collaborative monitoring index system with a hierarchical structure and a data acquisition scheme;

The acquisition module is used for acquiring data according to the collaborative monitoring index system based on the data acquisition scheme to obtain target acquisition data, and dynamically analyzing and processing the target acquisition data to obtain a project monitoring data set;

The processing module is used for carrying out multi-level response strategy analysis processing on the project monitoring data set through a decision tree algorithm to obtain a cooperative response mechanism;

And the evaluation module is used for performing effect evaluation processing on the execution result of the cooperative response mechanism through an iterative optimization algorithm to obtain a construction period reference parameter set and a monitoring and early warning rule.