CN118735225A

CN118735225A - A collaborative cloud system for intelligent scheduling of product resources based on multi-scenario visualization

Info

Publication number: CN118735225A
Application number: CN202411223012.0A
Authority: CN
Inventors: 陈文芳; 黄玉明; 董义中; 李伟青; 王靖靖; 白艳琴; 李思蕃
Original assignee: Qingdao Jushanghui Network Technology Co ltd
Current assignee: Qingdao Jushanghui Network Technology Co ltd
Priority date: 2024-09-03
Filing date: 2024-09-03
Publication date: 2024-10-01

Abstract

The invention relates to an intelligent scheduling collaboration cloud system based on multi-scene visual product resources, which relates to the technical field of information transmission, and comprises the following components: the data acquisition module is used for acquiring various scene data of the product; the model construction module is used for constructing a dynamic resource scheduling model for resource optimization scheduling; the multi-scene visualization module is used for displaying dynamic changes of resource scheduling to a user in the dynamic resource scheduling model; the abnormality detection module is used for intelligently adjusting the resource scheduling state; the model optimization module is used for acquiring feedback information of a user, optimizing a dynamic resource scheduling model based on the feedback information and historical data of resource scheduling, and obtaining an optimized dynamic resource scheduling model; and the resource scheduling module is used for generating and executing a product resource intelligent scheduling cooperation strategy aiming at the product according to the optimized dynamic resource scheduling model. The cloud system can improve accuracy and efficiency of product resource scheduling cooperation.

Description

Intelligent scheduling collaboration cloud system based on multi-scene visual product resources

Technical Field

The invention relates to the technical field of information transmission, in particular to an intelligent scheduling collaboration cloud system based on multi-scene visual product resources.

Background

Today, in current product development and operation processes, scheduling and collaboration of resources often rely on traditional project management tools and cloud systems. The tools generally comprise basic functions of task allocation, progress tracking, document sharing and the like, and help teams complete resource allocation and management under different scenes. Meanwhile, many enterprises also adopt customized ERP (Enterprise resource planning) cloud systems, and cross-department and cross-project resource scheduling is realized by integrating various modules. However, most of these cloud systems are static, rely on manual inputs and adjustments, and are difficult to cope with complex and dynamically changing multi-scenario demands.

However, existing resource scheduling and collaboration cloud systems and methods lack real-time response capability to multiple scene changes and cannot be intelligently adjusted according to the dynamic requirements and resource states of the project. Secondly, the tools are often complicated in operation, rely on manual work to carry out a large amount of manual management, error easily appears, and cooperation efficiency is affected. In addition, the existing cloud system has limited visualization capability, and cannot intuitively present dynamic changes of resources in different scenes, so that information is not transferred timely and comprehensively in the decision process.

Disclosure of Invention

Aiming at the technical problems in the prior art, the invention provides a multi-scene visual product resource intelligent scheduling collaboration cloud-based system, a method, electronic equipment and a non-transitory computer readable storage medium, which can improve the accuracy and efficiency of resource scheduling collaboration.

The technical scheme for solving the technical problems is as follows:

the invention provides an intelligent scheduling collaboration cloud system based on multi-scene visual product resources, which comprises:

The data acquisition module is used for acquiring various scene data related in the current development and operation process of the product;

the model construction module is used for constructing a dynamic resource scheduling model for resource optimization scheduling according to the scene data;

The multi-scene visualization module is used for displaying dynamic changes of resource scheduling to a user in the form of a graph and a graph in the dynamic resource scheduling model;

The abnormality detection module is used for monitoring abnormal conditions in the resource scheduling and using process, and intelligently adjusting the resource scheduling state when abnormality occurs;

The model optimization module is used for acquiring feedback information of the user for resource scheduling and resource scheduling state adjustment, optimizing the dynamic resource scheduling model based on the feedback information and historical data of resource scheduling, and obtaining an optimized dynamic resource scheduling model;

and the resource scheduling module is used for generating and executing the intelligent product resource scheduling cooperation strategy aiming at the product according to the optimized dynamic resource scheduling model.

Optionally, the model building module is specifically configured to:

Acquiring a scheduling state of each resource at the time t;

constructing a cost function, a resource utilization efficiency function, an availability fluctuation function of the resources and a priority function of each resource in various scenes according to the scheduling state of each resource at the moment t;

And constructing the dynamic resource scheduling model according to the cost function, the resource utilization efficiency function, the availability fluctuation function and the priority function.

Optionally, the dynamic resource scheduling model is expressed as:

；

wherein, Is the resource scheduling scheme output by the dynamic resource scheduling model,AndAll are the number values of the two-way code,Is the firstIndividual resources are atThe scheduling state of the moment of time,Is the firstThe number of resources to be allocated to each resource,Is the firstThe number of the scenes in which the video is displayed,Is a cost function of the scheduling of the resources,Is a function of the efficiency of the utilization of the resources,Is a fluctuating function of the availability of resources,、、The first weight, the second weight and the third weight respectively,Is a resourceIn a sceneIn the above, the priority function of the set,Is the total number of resources that are to be allocated,Is the lagrange multiplier and is a function of the lagrange,Is the total number of resources or scenes, and the number of resources is consistent with the number of scenes.

Optionally, the model building module is further configured to:

constructing resource constraint of resource scheduling according to the upper limit of the available resources of the product;

Constructing time constraint of resource scheduling according to the starting time and the ending time of the resource scheduling;

Constructing a multi-objective optimization function of resource scheduling according to the cost function and the resource utilization efficiency function of resource scheduling;

and constructing the dynamic resource scheduling model according to the resource constraint, the time constraint and the multi-objective optimization function.

Optionally, the resource constraint is expressed as:

；

wherein, Is the upper limit of available resources;

Wherein the time constraint is expressed as:

；

Is the start time of the scheduling of the resources, Is the end time of resource scheduling;

the multi-objective optimization is expressed as:

；

wherein, It is an optimization objective to have a high degree of accuracy,Is the lagrange multiplier and is a function of the lagrange,、The first weight and the second weight are respectively,Is the firstIndividual resources are atThe scheduling state of the moment of time,Is a cost function of the scheduling of the resources,Is a function of the efficiency of the utilization of the resources,Is the total number of resources.

Optionally, the abnormality detection module is further configured to:

Acquiring a historical dataset of information for scheduling or using the resource;

constructing a prediction function for predicting future resource scheduling requirements according to the historical data set;

Acquiring a scheduling adjustment amount, an adjustment coefficient and a fourth weight of resource scheduling;

And constructing an intelligent adjustment algorithm according to the prediction function, the scheduling adjustment amount, the adjustment coefficient and the fourth weight, and intelligently adjusting the resource scheduling scheme based on the intelligent adjustment algorithm to obtain an adjusted resource scheduling state.

Optionally, the intelligent adjustment algorithm represents:

；

wherein, Is the adjusted resource scheduling state of the resource,Is the amount of scheduling adjustment that is made,Is the adjustment coefficient of the light source,Is a function of the prediction and,Is the fourth weight to be applied to the first and second substrates,Is a set of historical data that is to be used,For the number value of the code,Is the total number of prediction functions, each of which corresponds to a fourth weight and a historical dataset.

Optionally, the abnormality detection module is further configured to:

Constructing an adjustment amplitude constraint of resource scheduling state adjustment according to the upper limit of the available resources;

Constructing a prediction precision constraint of resource scheduling state adjustment according to a preset maximum prediction error;

And adjusting the resource scheduling state according to the scheduling amplitude constraint and the prediction precision constraint.

Optionally, the adjustment amplitude constraint is expressed as:

；

wherein, Is the maximum value of the adjustment amplitude;

wherein the prediction accuracy constraint is expressed as:

；

wherein, Is the actual resource requirement of the system,Is a predicted need for resources that will be available,Is the maximum prediction error that can be used to determine,Is the total number of times t used to calculate the maximum prediction error.

The invention also provides a method for intelligently scheduling the collaborative cloud based on the multi-scene visual product resources, which comprises the following steps:

acquiring various scene data related to the current development and operation process of the product;

Constructing a dynamic resource scheduling model for resource optimization scheduling according to the scene data;

The dynamic change of resource scheduling is displayed to the user in the form of a graph and a graph in the dynamic resource scheduling model;

monitoring abnormal conditions in the resource scheduling and using processes, and intelligently adjusting the resource scheduling state when the abnormal conditions occur;

Acquiring feedback information of the user for resource scheduling and resource scheduling state adjustment, and optimizing the dynamic resource scheduling model based on the feedback information and historical data of resource scheduling to obtain an optimized dynamic resource scheduling model;

And generating and executing a product resource intelligent scheduling cooperation strategy aiming at the product according to the optimized dynamic resource scheduling model.

In addition, to achieve the above object, the present invention also proposes an electronic device including: a memory for storing a computer software program; and the processor is used for reading and executing the computer software program, so as to realize the intelligent scheduling collaboration cloud method based on the multi-scene visual product resources.

In addition, in order to achieve the above objective, the present invention further provides a non-transitory computer readable storage medium, in which a computer software program is stored, the computer software program, when executed by a processor, implements a multi-scenario visualization product resource-based intelligent scheduling collaboration cloud method as described above.

The beneficial effects of the invention are as follows:

(1) According to the invention, by establishing the dynamic resource scheduling model and introducing a plurality of optimization targets and constraint conditions, the intellectualization and automation of resource scheduling can be realized, and by considering multiple factors such as cost, resource utilization rate, resource volatility, scene priority and the like, the cloud system can generate an optimal resource scheduling scheme, so that manual intervention is effectively reduced, and the rationality and efficiency of resource allocation are improved. Particularly in multiple scenes, the cloud system can dynamically adjust the scheduling scheme according to the real-time data, and ensure the optimal allocation of resources in different projects and tasks.

(2) The invention accurately predicts future resource demands by using the prediction model based on the historical data and the intelligent adjustment mechanism of the real-time state, and dynamically adjusts according to the actual situation, so that the cloud system can quickly respond to the change of the resource demands, and the possibility of resource conflict and resource waste is reduced. By introducing adjustment amplitude constraint and prediction error control, the cloud system keeps flexibility, avoids instability of the cloud system caused by excessive adjustment, and further improves accuracy and reliability of scheduling.

(3) According to the invention, a three-dimensional visualization technology is adopted, and dynamic display of time dimension is combined, so that a user can intuitively observe state changes of resources at different time points, and 3D visualization can display not only the current state of the resources, but also historical data and future prediction results, thereby helping the user to better understand and analyze resource scheduling conditions in a complex scene. The visual display mode is beneficial to improving the decision efficiency of the user and reducing the misjudgment risk caused by the asymmetry of the information.

In conclusion, the cloud system can realize the omnibearing improvement of the traditional resource management cloud system through the innovation of multiple dimensions such as intelligent scheduling, dynamic adjustment, three-dimensional visualization, collaborative efficiency improvement, decision support, self-adaptive optimization and the like. Not only can the resource utilization efficiency and the scheduling precision be improved, but also a sustainable intelligent resource management platform is provided for enterprises, and a solid foundation is laid for future digital and intelligent operation.

Drawings

FIG. 1 is a scene graph of a multi-scene visual product resource intelligent scheduling collaboration cloud-based method provided by the invention;

FIG. 2 is a flow chart of a method for intelligently scheduling collaborative clouds based on multi-scenario visualization product resources;

Fig. 3 is a schematic structural diagram of an intelligent scheduling collaboration cloud system based on multi-scenario visual product resources;

fig. 4 is a schematic hardware structure of one possible electronic device according to the present invention;

fig. 5 is a schematic hardware structure of a possible computer readable storage medium according to the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

In the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

In the description of the present invention, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

Referring to fig. 1, fig. 1 is a scene diagram of a method for intelligently scheduling collaboration cloud based on multi-scene visual product resources. As shown in fig. 1, the terminal and the server are connected through a network, for example, a wired or wireless network connection. The terminal may include, but is not limited to, mobile terminals such as mobile phones and tablets, and fixed terminals such as computers, inquiry machines and advertising machines, where applications of various network platforms are installed. The server provides various business services for the user, including a service push server, a user recommendation server and the like.

It should be noted that, the scenario diagram of the intelligent scheduling collaboration cloud method based on multi-scenario visualization product resources shown in fig. 1 is only an example, and the terminal, the server and the application scenario described in the embodiments of the present invention are for more clearly describing the technical solution of the embodiments of the present invention, and do not generate the limitation of the technical solution provided by the embodiments of the present invention, and as a person of ordinary skill in the art can know that, with the evolution of the cloud system and the appearance of a new service scenario, the technical solution provided by the embodiments of the present invention is applicable to similar technical problems.

Wherein the terminal may be configured to:

Referring to fig. 2, fig. 2 is a schematic structural diagram of a multi-scenario-based intelligent scheduling collaboration cloud system for visualized product resources.

As shown in fig. 2, the intelligent scheduling collaborative cloud system based on multi-scenario visualization product resources provided by the embodiment of the invention comprises:

the data acquisition module 201 is configured to acquire various types of scene data related to the current development and operation process of the product.

Cloud systems, among other things, refer to a mode of providing computing services over the internet, allowing users to access storage, computing power and applications remotely over a network without requiring extensive computation or storage on local devices.

The scene data refers to various information related to resource scheduling generated in the process of product development and operation. Such information includes, but is not limited to, status of use of the resource, progress of the task, time node, resource demand change, etc. The data reflect the actual running states of the cloud system under different conditions, and are the necessary basis for resource optimization scheduling.

In some embodiments, scenario identification refers to the cloud system automatically identifying different contexts involved in the current product development and operation process. These scenarios include development tasks, project management nodes, operational events, and the like. Each scenario may create specific demands on the resource or affect the manner in which the resource is used. For example, in a software development project, a scenario may include a code development phase, a test phase, a deployment phase, and so on. The different stages have different demands on resources (e.g., developers, testers, servers, etc.).

In some embodiments, the resource status data may include availability, occupancy, idle time, etc. of the current resource. Such as the length of time the developer is working, the state of use of the hardware device, etc.

In some embodiments, the task progress data may include a start time, an expected completion time, an actual completion time, a current progress, etc. of the task. For example, the development progress of a certain functional module is currently 50% completed.

In some embodiments, the time node data may include key time nodes of the project, such as milestones, lead times, test phase start times, and the like. These time nodes have a direct impact on resource scheduling.

In some embodiments, the demand change data may include resource demand adjustments due to changes in customer demand or changes in external environments. For example, a customer suddenly requires that a function be added, which may cause additional resource requirements.

In some embodiments, scene data may be obtained by: sensors are widely used to monitor equipment status, environmental conditions, etc. in hardware equipment or production environments through sensors and monitoring cloud systems. Such as temperature sensors, pressure sensors, equipment operating status sensors, etc. These sensors can collect in real time operational data of the device such as temperature, pressure, frequency of use, etc. For example, in a manufacturing plant, temperature and vibration sensors of the equipment can provide real-time machine operating state data. These data are used to determine the operating state of the device and possible fault conditions, so that the resource scheduling adjustment is performed in time.

In some embodiments, the scenario data of the product may be monitored through a software log and cloud system. During software development and operation, cloud system logs and monitoring tools can record and analyze the operating state and performance data of the software. For example, cloud system logs may record time, progress, error information, etc. of task execution. In a continuously integrated cloud system, a build server records the time of each build, the build results, test coverage, etc. These data can be used to monitor development progress and automatically adjust resource allocation based on the progress.

In some embodiments, project management tools (e.g., JIRA, trello, asana, etc.) are typically used to manage tasks, allocate resources, track progress. By integrating with the tools, the cloud system can acquire data such as current task state, resource allocation condition, project progress and the like. For example, in a software development project, a project management tool may record the task allocation, task completion, resource usage, etc. of the developer. These data directly reflect the current state of the project and can be updated in real time, thereby providing a basis for resource scheduling.

In some embodiments, the scene data is obtained by way of user input and feedback. For example, in some cases, user input and feedback is also an important source of data. For example, project manager or team members may directly input information on current task status, resource demand changes, etc. through the cloud system. In emergency task processing, project manager can directly input current emergency demand or task priority adjustment conditions, and the cloud system can adjust the resource scheduling scheme based on the inputs.

In some embodiments, the acquired scene data will typically be stored in a database for subsequent analysis, prediction, and optimization. The data may be structured (e.g., relational databases) or unstructured (e.g., log files). For example, on a large data platform, scene data acquired in real time may be stored in a distributed database, supporting massive parallel computation and analysis.

In some embodiments, the collected data needs to be processed and analyzed in order to extract information useful for resource scheduling. Such as data cleansing, filtering, aggregation, statistical analysis, and the like. For example, in the data processing process, irrelevant data can be filtered, missing values can be processed, statistical results can be aggregated, and then the statistical results are input into a resource scheduling algorithm to generate an optimized scheduling scheme.

By the method, the acquisition of various scene data related in the current development and operation process of the product is a key step of a resource scheduling cloud system. The process comprises the links of scene recognition, data acquisition, data storage, processing and the like, and the cloud system can grasp the actual conditions of product development and operation in real time by comprehensively utilizing the means of sensors, cloud system monitoring, project management tools, user feedback and the like, so that a solid data base is provided for intelligent scheduling, real-time adjustment and accurate prediction.

The model building module 202 is configured to build a dynamic resource scheduling model for performing resource optimization scheduling according to the scenario data.

In some embodiments, the model building module 202 may be specifically configured to:

Acquiring a scheduling state of each resource at the time t;

In some embodiments, the dynamic resource scheduling model is expressed as:

；

In a specific implementation of the present invention,Is the optimal resource scheduling scheme output by the model, and is the optimal resource scheduling scheme obtained by calculation of the optimization model, namely at the time pointOn the resourceOptimal allocation status under multiple objectives (e.g., cost, utilization, volatility, priority, etc.) comprehensive consideration.

Is the firstIndividual resources are atThe scheduling state of the moment, the resources can be personnel, equipment, funds and the like, and the allocation and use states of the resources in the project or the task need to be optimized.

Is a cost function of resource scheduling, including time consumption, resource conflict, etc., is a cost function of resource scheduling, describes at timeUsing resourcesVarious costs are incurred. The cost may include the following:

time consumption: the longer the use time of the resource, the higher the cost.

Resource conflict: contention for the same resource by multiple tasks may result in scheduling conflicts, thereby increasing scheduling costs.

Direct cost: such as equipment usage fees, personnel wages, etc.

Is a resource utilization efficiency function, considers idle time, use efficiency and the like of the resource and is used for measuring the time of the resourceIs used in the case of the use of (3). Mainly consider the following factors:

Idle time: the longer the idle time of the resource between tasks, the lower the utilization efficiency.

Use efficiency: the higher the ratio of the time that the resource is effectively used to the total time, the higher the efficiency.

Is the availability fluctuation function of the resource, reflects the fluctuation degree of the resource state and describes the fluctuation degree of the resource state. The greater the volatility, the more difficult it is to predict the availability of resources, and the less stable the scheduling scheme may be. For example:

Resource state change: the device may be temporarily unavailable for failure, maintenance, etc.

Personnel change: personnel may not be able to participate in the current task for holidays, mobilization, etc.

、、The first weight, the second weight, and the third weight, respectively.

Is a resourceIn a sceneIn consideration of suitability of resources in different scenarios, degree of urgency, etc., the function may be nonlinear, representing uncertainty of priority.

In particular, the method comprises the steps of,、、And the comprehensive objective functions of the optimization model are formed together. The influence of different targets on the final decision can be controlled by adjusting the weights. For example, if the first weight is relatively large, the cloud system may tend to reduce costs, and a low cost resource scheduling scheme may be preferred. And if the third weight is larger, the cloud system will pay more attention to the stability of the resources, avoiding selecting those resources with larger volatility.

By introducing a priority functionThe model can identify which resources should be preferentially allocated to a particular task in the current scenario. This function is particularly critical when handling multi-tasking, multi-scenario scheduling. For example, in emergency tasks, cloud systems may increase the priority of related resources, thereby ensuring that important tasks are preferentially handled.

Wherein, Representing solving for R values that minimize the objective function, i.e., finding the optimal resource scheduling scheme. This process is usually implemented by optimization techniques such as iterative algorithms or linear programming, in order to find an optimal solution from among all possible resource allocation solutions, taking into account cost, efficiency, volatility and priority.

By way of example only, assume that one software development project involves multiple development tasks, each of which requires allocation of different resources (e.g., developers, testers, hardware devices, etc.) that have different availability and priorities at different points in time. Will be calculated by the following steps. Wherein, Is the developer a who has developed the product,Is the developer B who has the ability to perform,Is the developer C who has developed the product,Is a hardware device D.

Accordingly, each function may have a different valueCorresponding function values, e.g.、、、500, 450, 300 And 200, respectively (cost units are yuan per hour). And so on, other functions also have a different meaningThe corresponding function value.

Hypothesis is directed toTo the point ofCalculated outThe values are 503, 452, 303 and 201, respectively, and the composite scores of the resources are compared, and the combination with the lowest score is selected. Assuming that the task allocation requires one developer and one tester, the following combinations may be selected:

development task 1 uses developer B and tester C, and development task 2 uses developer a and hardware device D. Thus, in this example, the result is A scheduling scheme for the following resource combinations is possible:

To the point of For the purpose of task 1,To the point ofFor task 2.

By the above method, specifically solveIs a scheduling combination including respective resource allocation states, which is an optimal resource allocation scheme obtained by minimizing total cost, maximizing resource utilization efficiency, and considering resource volatility and priority. The scheme ultimately determines which resources are used to perform which tasks at a particular point in time and can be dynamically adjusted to account for real-time changes.

In summary, the invention provides a mathematical method for solving an optimal resource scheduling scheme by comprehensively considering a plurality of key factors. The method is suitable for complex multi-task and multi-resource scheduling scenes, and can automatically generate an optimal scheduling scheme under various constraint conditions, so that the efficiency and accuracy of resource management are improved, and the method is particularly suitable for complex project environments requiring dynamic scheduling and real-time response.

In some embodiments, the model building module 202 is further to:

In some embodiments, the resource constraint is expressed as:

；

wherein, Is the upper limit of available resources;

Wherein the time constraint is expressed as:

；

the multi-objective optimization is expressed as:

；

In particular to the specific implementation of the method,Is the upper limit of available resources. The formula represents at any point in timeAll resourcesCannot exceed the upper limit of available resources。Refers to an upper limit on the total amount of resources that can be scheduled in a cloud system, such as developers, hardware devices, or budgets available in a project. The process of resource scheduling needs to ensure that the total amount of allocated resources does not exceed the upper limit at any time, which may otherwise lead to resource conflicts, overloads or project failures.

Assuming that there are 5 developers in a project, then5. At a certain point in timeAbove, if 3 developers are required to process task a and 2 developers are required to process task B, then the allocation satisfies the condition 3+2=5.ltoreq.5. However, if one task requires 4 developers and another task requires 2 developers, the total demand is 6, which exceedsThis constraint cannot be satisfied.

The time constraint is expressed as:

；

To the point of Is the scheduling time range. The formula prescribes a scheduling time rangeRequiring that all scheduling activities must be inAndAnd between.、Indicating the time points at which the scheduling starts and ends, respectively. This constraint ensures that all resource allocation and task scheduling are completed within a predetermined time frame, thereby avoiding task delays or resource idleness.

If the development period of a project is from 2024, 1/12/31, thenFor 1 month and 1 day of 2024,2024, 12/31. All resource scheduling must be done during this time, and tasks outside this time range cannot be scheduled or executed.

The multi-objective optimization is expressed as:

；

the formula represents a multi-objective optimized Lagrangian function for optimizing resource scheduling on the premise of meeting resource and time constraints. The optimization objective mainly comprises two parts:

Cost and utilization targets: function of Represents an integrated goal for resource scheduling, wherein:

Is a cost function for calculating the time Upper use of resourcesCosts (e.g., wages, equipment usage fees, etc.).Is a resource utilization efficiency function for calculating the utilization efficiency of a resource (such as the utilization rate of a device or the workload of a person, etc.).、The first weight and the second weight are used for balancing the influence between the two.

In some embodiments, the functionIs a punishment term in whichAnd the Lagrangian multiplier is used for punishing resource overrun. The function of this term is to ensure that the total resource usage does not exceedIf so, the value of the overall objective function is increased, thereby reducing its optimality.

It will be appreciated that the goal of multi-objective optimization is to minimize the cost of resource usage and maximize the utilization of resources without exceeding resource and time constraints. Lagrange multiplierThe introduction of (2) is that if the resource usage exceeds the upper limit in the optimization process, the penalty is automatically increased, so that the optimization result is guided to be within a reasonable range.

By way of example only, assuming two tasks in a project, 3 developers and 2 developers are required, respectively, at costs of 500 and 450 yuan per hour, respectively, with availability of 0.8 and 0.7, respectively. The total developer upper limit for this project is 4. In the optimization process, if the total number of developers allocated to the two tasks exceeds 4, lagrangian multiplierPenalty is added to avoid exceeding the resource limit and find the optimal resource allocation mode, such as allocating 4 developers, reducing the total cost and maximizing the resource utilization.

Through the formulas of resource constraint, time constraint and multi-objective optimization, the scheme can ensure that resource scheduling is optimally performed within a reasonable resource and time range, reduce cost, improve efficiency and avoid resource overload and time overrun. The formulas work together, so that the cloud system can automatically generate an optimal resource scheduling scheme in a complex multi-task environment, and the execution effect of the whole project is improved.

And the multi-scene visualization module 203 is configured to display the dynamic change of the resource scheduling performed by the dynamic resource scheduling model to the user in a form of a graph or a graph.

The dynamic resource scheduling model is a cloud system for optimally distributing and adjusting resources according to real-time data and historical data. Because resource scheduling is performed in a constantly changing dynamic environment, cloud systems need to present these changes to users in real time so that they can know the status and usage of the resources at any time.

In some embodiments, the cloud system can display the information of the current use state, availability, utilization rate and the like of each resource to the user in a graphical mode, so that the user can be helped to know the current state of each resource and the allocation situation of each resource in different tasks in time. Implementations take the form of, for example, instrument panels (dashboards), pie charts, bar charts, etc., showing the current state of each resource. The instrument panel can display key indexes such as real-time utilization rate, availability and the like of resources. Such as the current workload of a developer, the use of a server, etc. The pie chart shows the allocation ratio of resources in each task or project. For example, the proportion of developers used by different tasks, or the occupation of resources by different departments.

The resource scheduling is not only static allocation, but also a process that is continuously adjusted over time. Cloud systems need to demonstrate how resource scheduling dynamically adjusts with changes in external conditions, and the impact of these adjustments on the project as a whole.

Implementations show dynamic changes in resource scheduling, as by Gantt chart (GANTT CHART) and time series chart. The Gantt chart can show the time progress and resource allocation condition of each task. Such as the start-stop time of each task, the associated resources, and the change in scheduling. The time series diagram may show the time-varying conditions of resource utilization, task completion progress, etc. For example, a trend in workload change of a developer or a gradual increase in the task completion rate is performed during a certain period.

In multi-scenario applications, the resource requirements and allocation schemes may be different in different scenarios. The cloud system displays the resource allocation schemes under different scenes in a chart and graph form, and helps users compare and analyze the optimal scheduling schemes. The implementation modes are shown by adopting a comparison graph, a thermodynamic diagram (Heat Map) and the like. The comparison chart can show the allocation situation of the same resource under different scenes. For example, the work allocation and load conditions of the developer are compared in the development phase and the test phase. Thermodynamic diagrams may show the concentration and priority of resource usage. For example, the use of server resources over different time periods, or the strength of demand for resources by different tasks.

In some embodiments, the cloud system not only can display the current resource scheduling state, but also can display the future possible resource demand change trend based on historical data and a prediction model, so as to help a user plan resources in advance. The implementation is as shown with trend graphs and predictive model graphs. The trend graph may show a prediction curve of resource demand. For example, the expected workload of the developer, or the trend of demand for some critical resource, within a few weeks in the future. The prediction model diagram can show resource demand prediction results obtained by the cloud system according to historical data, such as task completion time prediction, project resource peak period prediction and the like.

When abnormal conditions (such as resource overload, conflict and the like) occur in the resource scheduling process or the cloud system performs intelligent adjustment, the cloud system needs to remind users of the changes in a graph or chart form and show the influence of the adjustment on the whole scheduling scheme. Implementations may be presented through alert icons and adjustment logs. Alarm icon when a resource is overloaded, unavailable or conflicted, the cloud system will be marked with an alarm icon in the chart to alert the user. The adjustment log shows the specific content of each intelligent adjustment and its impact. For example, a cloud system reallocates resources due to the urgency of a task, and the adjusted solution and its impact on other tasks are recorded and presented in a log.

In some embodiments, the user may view the latest changes to the data in real time, and the cloud system may automatically refresh the data and update the chart content, ensuring that the information presented is always up to date. The implementation may be an auto-refresh function for charts and graphs, such as refreshing data every few seconds, or updating immediately when a critical event occurs.

In some embodiments, the user may customize the display of the chart according to his or her needs, such as selecting a particular time frame, resource type, or task type for presentation. The filtering and sorting functions of the charts can be provided to allow the user to select specific data for in-depth analysis through the interactive interface.

In some embodiments, the user may review past resource scheduling history, looking at resource allocation conditions and their changes at different points in time. For example, through a time slider or playback function, the user can view the scheduling status at any point in time, knowing the context and results of the historical adjustments.

Through the mode, the dynamic change of resource scheduling is displayed through the graph and the graph, and the cloud system can visualize the complex resource scheduling process, so that a user can easily understand and manage the resource allocation condition. The visualization not only improves the decision-making efficiency of the user, but also helps the user to identify potential problems in advance and make more timely and reasonable adjustment.

The anomaly detection module 204 is configured to monitor anomalies in the resource scheduling and usage process, and intelligently adjust the resource scheduling state when anomalies occur.

In some embodiments, the anomaly detection module 204 may also be configured to:

In some embodiments, the intelligent adjustment algorithm represents:

；

In a specific implementation of the present invention,The adjusted resource scheduling state is the optimal resource scheduling scheme for the initialAnd (5) performing a corrected result. When external conditions change, such as demand fluctuation, resource state change or emergency, the originally calculated optimal scheduling schemeMay no longer be applicable. At this time, the cloud system needs to respond to the current latest information pairAdjustments are made to ensure continued availability of resource scheduling,The new scheme after adjustment is obtained.

The resource scheduling scheme obtained by optimization calculation is the optimal resource allocation state under the given constraint condition, and is the optimal scheme obtained by comprehensively considering various factors, but in the actual operation process, the scheme is possibly not optimal due to the change of external factors, so that further adjustment is needed.

Is a scheduling adjustment amount, which is calculated according to a deviation between a current resource state and an expected target. Representing current resource scheduling statusAnd ideal stateDifferences between them. This discrepancy may be due to a change in actual demand, sudden unavailability of resources, or insertion of new tasks, etc. By calculation ofThe cloud system can make necessary corrections to the current resource scheduling state.

The adjustment coefficient determines the adjustment amplitude. If it isIf the adjustment amount is larger, the cloud system has higher sensitivity to adjustment, and the adjustment amount has larger influence, so that the method is suitable for scenes with severe changes; whileSmaller indicates more careful adjustment, and is suitable for a scene with more stable change.

Is a predictive function based on historical data setsAnd the current point in timeIs a resource demand prediction function of (1). By analysing historical dataSuch as past resource usage, task completion time, seasonal fluctuations, etc., to predict future resource demands or state changes. The predicted outcome is used to adjust the current resource schedule to account for future possible changes in advance. For example, historical data may show that resource demand is increasing at some point in time, and then near these points in time, the cloud system may be pre-adjusted based on the predictions.For the number value of the code,Is the total number of prediction functions, each of which corresponds to a fourth weight and a historical dataset.

Is the fourth weight, indicating the importance of the prediction result in the adjustment process. The degree of influence of the prediction result in the overall adjustment is determined. If a certain prediction result is very reliable and important,The cloud system can greatly adjust the resource scheduling according to the prediction; conversely, if the uncertainty of the predicted outcome is higher or its impact is smaller,Will be smaller.

Is a historical data set and comprises information such as usage records, task completion records, resource state changes and the like of resources at different time points in the past. Basic data is provided for the prediction function, and actual use conditions of the resources in different scenes are reflected. The data can reveal the regularity and trend of the resource use, and help the cloud system to make reasonable adjustment in advance in future resource scheduling.

In a dynamic project environment, resource requirements and task priorities may change over time. For example, in an ongoing development project, a critical task suddenly requires priority, or a critical resource (e.g., a core developer or critical device) is suddenly unavailable. At this time, the original optimal scheduling schemeMay no longer be applicable.

In some embodiments, the cloud system first calculates the current resource status and the current resource statusThe difference between them to obtain the dispatch adjustment quantity. Next, the cloud system utilizes the historical datasetBy prediction functionPredicting the change trend of the resource demand in a future period of time. Finally, in combination with these factors, the cloud system pairAdjusting to generate a new scheduling schemeTo better address current and future needs.

Assume that in a software development project, the original scheduling schemeIs derived based on current demand. However, as the project advances, a new high priority task is suddenly inserted, and some equipment in the original plan is not available due to the failure. The cloud system will perform the following steps:

Calculation of Scheduling bias caused by new task insertion and device unavailability is identified and quantified.

Calculation ofBased on historical data, predicting may require more developer resources in the future or predicting device repair time.

Adjustment ofAccording to the calculated result, an adjustment coefficient is appliedAnd weightFinally, a new scheme is generatedEnsuring that the resource scheduling more meets the current and future actual demands.

The invention can generate a resource scheduling scheme more in accordance with the actual situation when facing the dynamically changing requirements and environment by comprehensively considering the scheduling adjustment amount, the historical data prediction and the current optimal schemeThe cloud system can respond to various emergency situations in real time, and the continuous effectiveness and flexibility of resource scheduling are maintained.

In some embodiments, the anomaly detection module 204 is further to:

In some embodiments, the adjustment amplitude constraint is expressed as:

；

wherein, Is the maximum value of the adjustment amplitude;

wherein the prediction accuracy constraint is expressed as:

；

In a specific implementation of the present invention,Is the maximum value of the adjustment amplitude.

The prediction accuracy constraint is expressed as:

：

wherein, Is the actual resource requirement, is the time point of the cloud systemAnd the amount of real resources required.

Is a predicted resource requirement, is a prediction function of a cloud system based on historical data and a prediction modelPredicted point in timeAnd the amount of resources needed.

Is the prediction error, i.e. the actual resource demandAnd (3) withAverage absolute error between. The error represents the degree of deviation between the predicted result and the actual demand.

The maximum prediction error is the allowable maximum prediction error, and represents the upper limit of the error that can be tolerated by the prediction model.Is the total number of times t for calculating the maximum prediction error, e.g10, There are 10 times t, respectively t1 to t10, correspondingly 10AndFor calculating a prediction error.

It will be appreciated that this constraint may be used to ensure the accuracy of the prediction model, preventing errors in the resource scheduling scheme due to inaccurate predictions. By limiting prediction errorsNo more thanThe cloud system can ensure that its adjustments made based on the predictions are reliable.

Cloud systems rely on predictions of future resource demands, however the accuracy of the predictions directly affects the effectiveness of the scheduling scheme. If the prediction error is too large, the cloud system may erroneously adjust the resource allocation, resulting in a waste or shortage of resources. Thus, the setting isAs an upper error limit, the cloud system is ensured to be adjusted according to the prediction result only when the prediction precision meets the requirement.

For example only, in a large project, resource requirements may fluctuate due to changes in external conditions. For example, a development task may suddenly increase or decrease resource demand due to a change in customer demand. Cloud system through historical datasetPredicting resource demand in a future period of time, and performing scheduling adjustment. If prediction errorSmaller, i.eAnd the method is smaller, the prediction result is more accurate, and the cloud system can rely on the prediction and perform corresponding scheduling adjustment. But if itExceeding the limitIt is indicated that the prediction may be unreliable enough that the cloud system needs to re-evaluate the prediction model or avoid significant adjustments based on the prediction.

It can be appreciated that the adjustment range constraint can ensure that the adjustment range of the resource scheduling is not too large, so as to maintain the stability of the cloud system and prevent the problem of new resource management caused by excessive adjustment. The prediction precision constraint can ensure the accuracy of resource demand prediction, prevent resource scheduling decision errors caused by inaccurate prediction, and ensure that the cloud system is reasonably and reliably adjusted based on the prediction result.

According to the invention, through the two constraints, the resource scheduling cloud system can maintain reasonable adjustment amplitude and higher prediction accuracy when meeting complex and changeable demands, so that efficient resource management and scheduling are realized.

The model optimization module 205 is configured to obtain feedback information of the user for resource scheduling and adjustment of the resource scheduling state, and optimize the dynamic resource scheduling model based on the feedback information and historical data of resource scheduling, so as to obtain an optimized dynamic resource scheduling model.

The user feedback information refers to comments and suggestions for adjusting the current scheduling scheme and the resource state when the user uses the resource scheduling cloud system. Feedback information may be obtained in a variety of ways, for example:

direct feedback: the user can directly input satisfaction degree of the current resource scheduling scheme, a place for suggesting improvement or a problem through a feedback interface of the cloud system. For example, a project manager may feed back that a task requires more developers when it finds that the resource allocation of the task is insufficient.

Automatic recording: the cloud system can automatically record implicit feedback of the user by monitoring the operation and adjustment behavior of the user on resource scheduling. For example, if a user frequently manually adjusts some type of resource allocation, this indicates that automatic scheduling of the cloud system may be inadequate in this regard.

Questionnaires and surveys: and periodically sending questionnaires or surveys to users, and collecting the comments of the users on the aspects of overall performance, scheduling effect, response speed and the like of the cloud system.

In some embodiments, the user feedback information may be divided into multiple dimensions, which will be used for different optimization objectives, such as:

Satisfaction of resource allocation: and (5) whether the user is satisfied with the current resource allocation scheme or not, and whether the resource allocation is reasonable and sufficient or not is considered.

Scheduling response speed: and evaluating the response speed of the cloud system by a user, and judging whether the cloud system can timely adjust resources to meet the requirement change.

Task completion: and evaluating a scheduling result by a user, and judging whether resources distributed by the cloud system can effectively support the task to be completed on time.

Efficiency of resource usage: the user's perception of efficiency of resource usage, e.g., whether there is a condition of resource idling or over-utilization.

Wherein, the historical data refers to all relevant data recorded by the cloud system in the past resource scheduling process, and can include but is not limited to the following types:

Resource usage record: including usage of each resource over different time periods, workload, task allocation records, etc. For example, the task allocation and completion rate of a developer over the past several months.

Scheduling adjustment records: the method comprises all scheduling adjustment operations performed by a cloud system, and the resource state, the scheduling target, the adjustment reason and the like before and after adjustment.

Task completion data: including information on the actual completion time of the task, resource consumption, obstructions encountered, etc. For example, if a project task is scheduled to be completed, if a resource shortage or overstock condition occurs.

User feedback record: information fed back by each user and its corresponding scheduling decisions, and whether or not these feedback is taken.

In some embodiments, the historical data provides a large amount of reference information for the optimization model, enabling the cloud system to adjust according to past experience, such as:

identifying patterns and trends: by analyzing the historical data, the cloud system can identify patterns and trends in resource usage, such as which time periods have higher resource demands and which tasks often have insufficient resources.

Correcting the prediction model: the historical data may be used to verify and correct the accuracy of the predictive model. For example, if past scheduling predictions deviate significantly from actual demand, the cloud system may readjust parameters of the prediction model based on historical data.

Optimizing a scheduling strategy: by reviewing the effects of historical scheduling, the cloud system can identify which scheduling policies are good and which need improvement, thereby optimizing future scheduling policies.

In some embodiments, the process of optimizing the dynamic resource scheduling model may include the following steps:

Collecting feedback and historical data: the cloud system firstly collects feedback information and historical resource scheduling data of the user, and the comprehensiveness and accuracy of the data are ensured.

Data analysis and processing: and cleaning and sorting the collected feedback information and history data, and analyzing to extract key information. For example, statistics are made of which feedback is most concentrated and which historical scheduling schemes are most effective.

Adjusting parameters of a scheduling model: and adjusting parameters in the dynamic resource scheduling model according to the analysis result. For example, the scheduling priority of certain resources is raised based on feedback, or the weight factor of the scheduling algorithm is adjusted.

Simulation and verification: after adjusting the model parameters, the cloud system can verify whether the adjusted model is more efficient by simulating future scheduling scenarios. The simulation results are compared with the historical data to evaluate the optimization effect.

Model update and application: if the optimization effect is remarkable, the cloud system can apply the optimized model to actual resource scheduling and continuously monitor the effect.

In some embodiments, key objectives of the model may include:

And (3) improving the scheduling precision: by combining feedback and historical data, the model can more accurately predict resource demands, optimize resource allocation and reduce resource waste and task delay.

And the adaptability is enhanced: by constantly learning user feedback and historical data, the model can better adapt to different scheduling scenes and demand changes, providing a more flexible resource scheduling scheme.

The manual intervention is reduced: along with the optimization of the model, the cloud system can automatically complete resource scheduling to a greater extent, manual adjustment operation of a user is reduced, and resource management is more efficient.

By way of example only, assume that in a project management cloud system, the user feedback is often inadequate for the allocation of resources for certain tasks, and that historical data also shows that the completion time for these tasks is generally long and times out multiple times. Based on these feedback and historical data, the cloud system may adjust parameters of the scheduling model, such as increasing the priority of these tasks or increasing the amount of resources allocated. Simulation tests show that the task completion efficiency is remarkably improved after the adjusted model is subjected to simulation tests. Therefore, the cloud system applies the updated model to actual resource scheduling, so that project requirements are better met.

In summary, the cloud system can continuously optimize the dynamic resource scheduling model by acquiring the feedback information of the user for the resource scheduling and the resource scheduling state adjustment and combining the historical data of the resource scheduling, and the process ensures that the cloud system not only can adapt to the current scheduling requirement, but also can improve the efficiency and the accuracy of future scheduling through learning and adjustment. The finally obtained optimization model can manage resources more flexibly and efficiently, reduce manual intervention and improve the overall project management effect.

And the resource scheduling module 206 is configured to generate and execute a product resource intelligent scheduling collaboration policy for the product according to the optimized dynamic resource scheduling model.

In some embodiments, the optimized dynamic resource scheduling model may be obtained by continuously collecting user feedback information, analyzing historical scheduling data, and continuously adjusting model parameters. The optimized model can more accurately predict future resource demands and generate a more reasonable resource allocation scheme.

It can be appreciated that the model has a high degree of dynamics and adaptivity, and can automatically adjust the scheduling policy according to the scene and the demand which change in real time. It not only takes into account current resource status and task requirements, but also integrates the ability to predict future trends and process uncertainty factors.

Through the optimized model, the cloud system can more accurately allocate resources, reduce resource waste and ensure that the resource requirements of key tasks are preferentially met. The optimized model can respond to external changes in real time in the execution process, and dynamically adjust the resource allocation strategy according to the latest data.

In some embodiments, generating the product resource intelligent scheduling collaboration policy is converting the optimized scheduling model into a specific action scheme. The process may include the steps of:

Inputting the current state and the requirements: the cloud system firstly collects current state data in product development and operation, including current resource availability, task progress, time nodes, emergencies and the like.

Model calculation and analysis: and calculating an optimal resource allocation scheme according to the cloud system according to the optimized dynamic resource scheduling model. The calculation process integrates real-time data, historical trend and user feedback, and ensures the rationality and effectiveness of the scheme.

Generating a scheduling scheme: the cloud system generates a detailed resource scheduling collaboration policy. This policy includes specific resource allocation details such as the kind and amount of resources required for each task, the point in time of resource allocation, priority settings, etc.

Scheme verification and simulation: before actual execution, the cloud system may perform simulation test to verify the feasibility of the scheme. For example, simulating the effect of the strategy in different situations ensures that efficiency is maintained in the face of an emergency.

In some embodiments, the scheduling collaboration policy may include the following:

Resource allocation plan: the allocation situation of each resource at a specific time point is described in detail, including the kind, the number, the task allocation, the working time and the like of the resource. For example, 3 developers are assigned to a development task, and the working time is 9:00 to 18:00.

Priority setting: the priority of each task is defined, and the priority of the key task is ensured to acquire resources. For example, the cloud system may prioritize the allocation of resources for items that are about to expire, while deferring processing of secondary tasks.

Emergency plan: in the resource scheduling process, the cloud system also generates an emergency plan to cope with possible emergency events. For example, if a critical device suddenly fails, the cloud system may automatically initiate backup resources or adjust the resource allocation for other tasks.

Coordination and communication planning: and (5) formulating a coordination and communication mechanism among departments or teams to ensure the smooth progress of the resource scheduling process. For example, the project management tool automatically notifies the relevant responsible person of the change of the resource allocation, so as to ensure the cooperation of the parties.

In some embodiments, the cloud system automatically executes the scheme once the scheduling collaboration policy is generated. The execution process comprises automatic allocation of resources, scheduling of tasks, monitoring of time nodes and the like. During execution, the cloud system can monitor the use condition of resources and the progress of tasks in real time. If an abnormal use of resources (e.g., overload, idle, conflict, etc.) is detected, the cloud system automatically adjusts. For example, if the resource demand of a task suddenly increases, the cloud system may reallocate resources or adjust the resources of other tasks.

In some cases, the scheduling schemes generated by the cloud system may need to be manually reviewed and approved, particularly when significant decisions or resource conflicts are involved. The user can check the scheduling scheme suggested by the cloud system and adjust the scheduling scheme according to actual conditions. If the user finds that the scheduling policy automatically executed by the cloud system needs to be adjusted, the cloud system allows the user to perform manual intervention. For example, a project manager may temporarily change the resource allocation to prioritize certain urgent tasks.

In some embodiments, the resource scheduling cooperation strategy generated and executed by the optimized scheduling model can obviously improve the utilization efficiency of resources, ensure that each resource is reasonably and fully utilized, and reduce the phenomena of resource idling and over allocation.

In some embodiments, the optimized scheduling policy can better support on-time completion of tasks and successful delivery of items. Because the policy considers the priority and the emergency plan of the resource, the cloud system can flexibly cope with the environment with changeable conditions, and the task progress is ensured.

It can be appreciated that the scheduling strategy is automatically generated and executed by the cloud system, so that a great amount of manual operation and decision time are reduced, and the overall efficiency of project management is improved. Meanwhile, the cloud system also provides monitoring and adjusting rights for users, and effective intervention can be ensured when necessary.

Through the method, according to the optimized dynamic resource scheduling model, the cloud system can generate and execute the intelligent product resource scheduling cooperation strategy, and the method is a core step of applying the theoretical model to actual operation. The process not only realizes the optimal configuration of resources, but also ensures the smooth progress of product development and operation processes through automatic execution, real-time monitoring and flexible adjustment, and improves the efficiency of resource management and project success rate.

Referring to fig. 3, a flowchart of a method for intelligently scheduling collaboration cloud based on multi-scenario visualization product resources is provided, which comprises the following steps:

step 301, acquiring various scene data related to the current development and operation process of the product;

step 302, constructing a dynamic resource scheduling model for resource optimization scheduling according to the scene data;

Step 303, displaying the dynamic change of resource scheduling in the dynamic resource scheduling model to a user in a form of a graph and a figure;

Step 304, monitoring abnormal conditions in the resource scheduling and using processes, and intelligently adjusting the resource scheduling state when the abnormal conditions occur;

Step 305, obtaining feedback information of the user for resource scheduling and resource scheduling state adjustment, and optimizing the dynamic resource scheduling model based on the feedback information and historical data of resource scheduling to obtain an optimized dynamic resource scheduling model;

and 306, generating and executing a product resource intelligent scheduling cooperation strategy aiming at the product according to the optimized dynamic resource scheduling model.

It should be noted that, the relevant content of the above steps is already described in the foregoing part of the intelligent scheduling collaboration cloud system based on the multi-scenario visualization product resource, and will not be repeated here.

Referring to fig. 4, fig. 4 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 4, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420, wherein the processor 420 executes the computer program 411 to implement the following steps:

Referring to fig. 5, fig. 5 is a schematic diagram of an embodiment of a computer readable storage medium according to an embodiment of the invention. As shown in fig. 5, the present embodiment provides a computer-readable storage medium 500 having stored thereon a computer program 411, which computer program 411, when executed by a processor, performs the steps of:

In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a cloud system, method, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (cloud systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a cloud system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction cloud system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. The utility model provides a based on intelligent scheduling cooperation cloud system of visual product resource of many scenes which characterized in that, cloud system includes:

2. The intelligent scheduling collaboration cloud system based on multi-scenario visualization product resources of claim 1, wherein the model building module is specifically configured to:

Acquiring a scheduling state of each resource at the time t;

3. The intelligent scheduling collaboration cloud system based on multi-scenario visualization product resources of claim 2, wherein the dynamic resource scheduling model is expressed as:

；

4. The multi-scenario visualization product resource based intelligent scheduling collaboration cloud system of claim 3, wherein the model building module is further to:

5. The multi-scenario visualization product resource-based intelligent scheduling collaboration cloud system of claim 4, wherein the resource constraints are expressed as:

；

wherein, Is the upper limit of available resources;

Wherein the time constraint is expressed as:

；

the multi-objective optimization is expressed as:

；

6. The multi-scenario-based visualization product resource intelligent scheduling collaboration cloud system of claim 5, wherein the anomaly detection module is further to:

7. The multi-scenario visualization product resource-based intelligent scheduling collaboration cloud system of claim 6, wherein the intelligent adjustment algorithm represents:

；

8. The multi-scenario-based visualization product resource intelligent scheduling collaboration cloud system of claim 7, wherein the anomaly detection module is further to:

9. The intelligent scheduling collaboration cloud system based on multi-scenario visualization product resources as claimed in claim 8, wherein the adjustment magnitude constraint is expressed as:

；

wherein, Is the maximum value of the adjustment amplitude;

wherein the prediction accuracy constraint is expressed as:

；