CN116843913A - A method, device, computer equipment and storage medium for processing commodity characteristics - Google Patents
A method, device, computer equipment and storage medium for processing commodity characteristics Download PDFInfo
- Publication number
- CN116843913A CN116843913A CN202310827173.XA CN202310827173A CN116843913A CN 116843913 A CN116843913 A CN 116843913A CN 202310827173 A CN202310827173 A CN 202310827173A CN 116843913 A CN116843913 A CN 116843913A
- Authority
- CN
- China
- Prior art keywords
- operator
- commodity
- data
- target
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本公开涉及一种商品特征的处理方法、装置、计算机设备及存储介质，包括：获取商品特征计算任务；从预先生成的算子关系结构中获取与目标参数相匹配的起始算子；将目标参数作为算子关系结构的输入数据，通过起始算子对目标参数进行特征计算，得到初始特征数据，通过中间算子对初始特征数据进行特征计算，得到中间特征数据，直至终止算子对中间特征数据进行处理得到最终特征数据；基于初始特征数据，中间特征数据以及最终特征数据构建目标商品的特征数据序列。本申请提供的方法相比现有技术更具有灵活性，有效提高了商品特征的处理效率，同时也兼顾了特征数据的一致性。
The present disclosure relates to a product feature processing method, device, computer equipment and storage medium, including: obtaining a product feature calculation task; obtaining a starting operator matching a target parameter from a pre-generated operator relationship structure; Parameters serve as the input data of the operator relationship structure. The starting operator is used to perform feature calculation on the target parameters to obtain the initial feature data. The intermediate operator is used to perform feature calculation on the initial feature data to obtain the intermediate feature data. Until the termination operator is used to calculate the intermediate feature data. The feature data is processed to obtain the final feature data; the feature data sequence of the target product is constructed based on the initial feature data, intermediate feature data and final feature data. The method provided by this application is more flexible than the existing technology, effectively improves the processing efficiency of product features, and also takes into account the consistency of feature data.
Description
Technical Field
The present application relates to the field of feature processing, and in particular, to a method and apparatus for processing commodity features, a computer device, and a storage medium.
Background
The current commodity feature processing is to extract commodity basic attributes by calling commodity basic information service, quickly and effectively perform feature reasoning based on basic attributes such as commodity text, images and the like to obtain high-quality single-mode features, and simultaneously can combine multiple heterogeneous mode data collaborative reasoning of commodities to obtain multi-mode features, and support feature production and storage integration.
However, in the current feature processing process, the operator is manually arranged first, and then the feature processing is performed. The whole process has longer processing time and complicated flow, so that the commodity characteristic can not be flexibly and efficiently processed.
Disclosure of Invention
In view of this, the embodiments of the present invention provide a method, an apparatus, a computer device, and a storage medium for processing commodity features, so as to solve the problem that commodity feature processing cannot be flexibly and efficiently completed.
In a first aspect, an embodiment of the present invention provides a method for processing a commodity feature, where the method includes:
acquiring a commodity characteristic calculation task, wherein the commodity characteristic calculation task comprises a target commodity and target parameters corresponding to the target commodity and used for carrying out commodity characteristic calculation;
Acquiring an initial operator matched with the target parameter from a pre-generated operator relation structure, wherein the operator relation structure comprises a plurality of operators and transmission directions among different operators, and the transmission directions are determined according to operator input and operator output of the operators;
taking the target parameter as input data of the operator relation structure, carrying out feature calculation on the target parameter through the initial operator to obtain initial feature data, carrying out feature calculation on the initial feature data through an intermediate operator to obtain intermediate feature data, and processing the intermediate feature data through a termination operator to obtain final feature data, wherein the intermediate operator comprises operators except the termination operator and the initial operator in the operator relation structure;
and constructing a characteristic data sequence of the target commodity based on the initial characteristic data, the intermediate characteristic data and the final characteristic data.
In a second aspect, an embodiment of the present invention provides a processing apparatus for commodity features, where the apparatus includes:
the acquisition module is used for acquiring commodity characteristic calculation tasks, wherein the commodity characteristic calculation tasks comprise target commodities and target parameters corresponding to the target commodities and used for commodity characteristic calculation;
The query module is used for acquiring an initial operator matched with the target parameter from a pre-generated operator relation structure, wherein the operator relation structure comprises a plurality of operators and transmission directions among different operators, and the transmission directions are determined according to operator input and operator output of the operators;
the processing module is used for taking the target parameter as input data of the operator relation structure, carrying out feature calculation on the target parameter through the initial operator to obtain initial feature data, carrying out feature calculation on the initial feature data through an intermediate operator to obtain intermediate feature data, and processing the intermediate feature data through a termination operator to obtain final feature data, wherein the intermediate operator comprises operators except the termination operator and the initial operator in the operator relation structure;
and the generation module is used for constructing a characteristic data sequence of the target commodity based on the initial characteristic data, the intermediate characteristic data and the final characteristic data.
In a third aspect, an embodiment of the present invention provides a computer apparatus, including: the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions to perform the method of the first aspect or any implementation manner corresponding to the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of the first aspect or any of its corresponding embodiments.
According to the method provided by the embodiment of the application, the target parameters are utilized to automatically match the initiation operator from the operator relation structure, the initiation operator can automatically deduce the intermediate operator and the termination operator based on the transmission direction in the operator relation structure, and the intermediate operator and the termination operator are utilized to perform characteristic calculation. Compared with the prior art, the method has the advantages that the flexibility is higher, the processing efficiency of commodity characteristics is effectively improved, and meanwhile, the consistency of characteristic data is also considered.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow diagram of a method of processing merchandise features according to some embodiments of the invention;
FIG. 2 is a schematic diagram of an operator structure relationship according to some embodiments of the invention;
FIG. 3 is a flow chart of a method of processing merchandise features according to some embodiments of the invention;
FIG. 4 is a schematic diagram of an operator structure relationship according to some embodiments of the invention;
FIG. 5 is a block diagram of a processing device for commodity features according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. 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.
According to embodiments of the present invention, there is provided a method, apparatus, computer device and storage medium for processing commodity features, it being noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system, such as a set of computer executable instructions, and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.
In this embodiment, a method for processing commodity features is provided, which may be used in the mobile terminal, such as a mobile phone, a tablet computer, etc., fig. 1 is a flowchart of a method for processing commodity features according to an embodiment of the present application, and as shown in fig. 1, the flowchart includes the following steps:
step S11, acquiring a commodity feature calculation task, wherein the commodity feature calculation task comprises a target commodity and target parameters corresponding to the target commodity and used for calculating commodity features.
In the embodiment of the application, the commodity characteristic calculation task can be triggered according to the updating frequency of the commodity, or the commodity characteristic calculation task can be triggered according to the pre-generated time period, the changed commodity is pulled through the commodity characteristic calculation task, and the characteristic calculation is carried out on the basic information or commodity transaction data after the commodity is changed, so that the characteristic data of the commodity after the commodity is changed can be quickly obtained.
Specifically, the commodity characteristic calculation task is obtained, and the commodity characteristic calculation task comprises the following steps of A1-A5:
and A1, acquiring a commodity change message queue, wherein the commodity change message queue carries change time and change basic information of at least one first candidate commodity.
In the embodiment of the application, the server can monitor whether the commodity basic information of the online commodity is changed in real time, and the commodity basic information can comprise: commodity title, commodity attributes, commodity pictures, and the like. When the basic information of the online commodity is monitored to be changed, the change time of the basic information of the commodity is read, the change basic information of the commodity is read, the commodity is taken as a candidate commodity, the commodity ID of the candidate commodity, the change time and the change basic information are sent to a commodity message change queue.
As one example, the merchandise message change queue includes the following messages:
message 1: candidate commodity ID 1-change time T1, change basic information M1.
Message 2: candidate commodity ID 2-change time T2, change base information M2.
Message 3: candidate commodity ID 2-change time T3, change base information M3.
And A2, acquiring a commodity data table, wherein the commodity data table comprises commodity transaction data of at least one second candidate commodity in unit time.
In the embodiment of the application, the server can monitor commodity transaction data of online commodities in real time, wherein the commodity transaction data can comprise: browsing volume, transaction volume, collection volume, etc., the server may update commodity transaction data of the commodity in the commodity data table in real time using the commodity transaction data.
As one example, the data of the commodity data table is as follows:
commodity 1: day 1-browsing amount x11, amount of deals y11, amount of collection z11, day 2-browsing amount x12, amount of deals y12, amount of collection z12.
Commodity 2: day 2-view amount x21, volume y21, collection z21, day 2-view amount x22, volume y22, collection z22.
Commodity 3: day 3-view volume x31, volume y31, collection z32, day 2-view volume x32, volume y32, collection z32.
And A3, determining a first candidate commodity with the change time falling into a preset time period in the commodity change message queue as a target commodity, or determining a second candidate commodity with the unit time falling into the preset time period in the commodity data table as a target commodity.
Step A4, obtaining target parameters corresponding to target commodities, wherein the target parameters comprise: and changing basic information, commodity transaction data or preset characteristic fields.
In the embodiment of the application, the target parameter is determined according to the characteristic requirement of the current commodity, and can also be preset. Specifically, if the current target commodity is determined based on the commodity change message queue, the target parameter at this time may be change base information of the commodity. If the current target commodity is determined based on the commodity data table, the target parameter at this time may be commodity transaction data. If processing is required for a certain commodity feature or commodity features, a feature field may be preset, and the preset feature field may be a tag feature, an image feature, or the like.
And step A5, generating commodity characteristic calculation tasks based on the target commodity and the target parameters.
In the embodiment of the present application, after determining the target commodity and the target parameter, a commodity feature calculation task Q1 of a preset time period may be generated, and the commodity feature calculation task is added to a task queue, and the state of the commodity feature calculation task is updated to an execution state, where the task queue includes: and calculating tasks corresponding to the commodity characteristics in each time period and corresponding task processing results.
Step S12, an initial operator matched with the target parameter is obtained from a pre-generated operator relation structure, wherein the operator relation structure comprises a plurality of operators and transfer directions among different operators, and the transfer directions are determined according to operator input and operator output of the operators.
In the embodiment of the application, the construction process of the operator relation structure comprises the following steps of B1-B3:
and step B1, obtaining interface description files of all operators.
In an embodiment of the present application, an interface description (interface definition language, abbreviated IDL) file of the operator may be preconfigured, and the configured interface description file is stored in the zookeeper. Based on the above, when the operator relation structure is built, the interface description file of the operator can be directly pulled from the zookeeper. It should be noted that, the purpose of the interface description file through the configuration operator is to facilitate the subsequent quick access of the heterogeneous operator.
And B2, accessing an operator by using the interface description file, and acquiring operator configuration information corresponding to the operator, wherein the operator configuration information comprises operator input and operator output.
In the embodiment of the application, after the interface description file of the operator is pulled from the zookeeper, the operator access is realized by utilizing the interface description file, and meanwhile, the operator configuration information of the currently accessed operator is obtained, and the configuration information is as follows:
operator 1:
service:kitex.test.server1
input:
a.b:f1
output:
f2:c.d
f3:e
operator 2:
service:kitex.test.server2
input:
g:f2
output:
f4:h
f5:j
the operator configuration information configures the input and the output of each operator, for example: the operator input for operator 1 is a.b: f1, the operator output of the operator 1 is f2: c.d, f3:e. The operator input of the operator 2 is g to f2, and the operator output of the operator 2 is f4 to h and f5 to j.
And B3, determining the transmission directions among the operators according to the operator input and the operator output carried by the configuration information, and constructing an operator relation structure based on the operators and the transmission directions among the operators.
In the embodiment of the present application, the transfer direction of each operator time is determined according to the operator input and the operator output configured by each operator in the configuration information, for example: the operator output of the operator 1 is f2: c.d, f3:e, and the operator input of the operator 2 is g:f2, so that the operator output of the operator 1 can be determined to be the operator input of the operator 2, and the transfer direction is operator 1- & gt operator 2. Finally, an operator relation structure is built based on each operator and the transmission direction among the operators, and the operator relation structure of the embodiment of the application can be a directed acyclic (Directed Acyclic Graph, abbreviated DAG) graph.
In addition, whether the interface description file is changed or not can be monitored through the zookeeper, and if the interface description file is changed, the operator relation structure is updated according to the updated interface description file.
According to the method provided by the embodiment of the application, the interface description file of the operators is pre-configured, so that the quick access of each operator can be realized, and after the operator is accessed, the operator input and the operator output of each operator configured in the operator configuration information are utilized to determine the transfer direction between the operators, so that an operator relation structure is automatically built, the relation between the operators is not required to be manually arranged, and the efficiency of feature calculation is improved.
In the embodiment of the application, acquiring the initial operator matched with the target parameter from the pre-generated operator relation structure comprises the following steps: traversing operator inputs of all operators in the operator relation structure, and determining an operator with the operator inputs matched with the target parameters as an initial operator. Or traversing the operator output of each operator in the operator relation structure, determining the operator with the operator output matched with the target parameter as a reference operator, and determining the operator associated with the operator output of the reference operator in the operator relation structure as a starting operator.
As an example, when the target parameter is change basic information (commodity title, commodity attribute, etc.) of the target commodity, as shown in fig. 2, an operator 1 matching the commodity title or an operator 2 matching the commodity attribute may be obtained from the operator relationship structure, and the operator 1, the operator 2 may be finally determined as an initial operator.
Or when the target parameter is a preset feature field (title feature, attribute feature, etc.) of the target commodity, as shown in fig. 2, an operator 1 with an operator output matched with the title feature or an operator 2 with an operator output matched with the attribute feature can be obtained from the operator relation structure, and finally the operator 1 and the operator 2 are determined as reference operators, and the operator output of the operator 1 is taken as the input of an operator 3, and then the operator 3 is taken as an initial operator. Meanwhile, the operator output of the operator 2 is the input of the operator 4, and the operator 4 is taken as an initial operator at the moment.
It should be noted that, through the flexible configuration of the target parameter, on the one hand, the automatic matching of the initiator under the scene of changing the basic information can be realized through the input of the target parameter matching operator. On the other hand, the automatic matching of the initial operator under the scene of the preset characteristic field can be realized through the output of the target parameter matching operator. The method comprises the steps that a target parameter is input to an initiator, the initiator can be processed based on the target parameter, meanwhile, the initiator can automatically deduce an intermediate operator and a termination operator based on the transmission direction in an operator relation structure, and the intermediate operator and the termination operator finish characteristic data obtained by sequential characteristic calculation in the deduction process. Based on the method, the operator is automatically deduced according to the transfer relation of the operator relation structure, and the characteristic calculation is carried out through the operator, so that the consistency of characteristic data is improved.
And S13, taking the target parameters as input data of an operator relation structure, carrying out feature calculation on the target parameters through an initial operator to obtain initial feature data, carrying out feature calculation on the initial feature data through an intermediate operator to obtain intermediate feature data, and processing the intermediate feature data through a termination operator to obtain final feature data, wherein the intermediate operator comprises operators except the termination operator and the initial operator in the operator relation structure.
In the embodiment of the application, the target parameter is used as the input data of the operator relation structure, namely, the target parameter is used as the operator input of the initiator, and the initiator is called to perform characteristic calculation on the target parameter, so that the initial characteristic data is obtained. The feature computation may be a feature computation, for example: the target parameter is a commodity title, which is understood to be a title field. The initiator may be to identify the commodity title, and obtain the text feature (i.e. initial feature data) corresponding to the commodity title.
After the initial feature data is obtained, the initial operator determines the transmission direction of operator output based on the operator relation structure, so that an intermediate operator is determined, the initial feature data is transmitted to a first intermediate operator, and the first intermediate operator processes the initial feature data to obtain first intermediate feature data. For example: when the initial feature data is text features, the first intermediate operator performs word segmentation on the text features to obtain text word segmentation features (namely first intermediate feature data).
After the first intermediate feature data is obtained, the first intermediate operator determines the transmission direction of the operator output based on the operator relation structure, so that the next operator is determined, if the next operator does not belong to the termination operator, the first intermediate feature data is transmitted to the second intermediate operator (namely, the next operator of the first intermediate operator), and the second intermediate operator processes the first intermediate feature data to obtain second intermediate feature data.
After the second intermediate feature data is obtained, the second intermediate operator determines the transmission direction of the operator output based on the operator relation structure, so that the next operator is determined, if the next operator belongs to the termination operator, the second intermediate feature data is transmitted to the termination operator (namely, the next operator of the second intermediate operator), and the termination operator processes the second intermediate feature data to obtain final feature data.
Step S14, constructing a characteristic data sequence of the target commodity based on the initial characteristic data, the intermediate characteristic data and the final characteristic data.
As an example, description will be given of the title and picture change of the target commodity, and as shown in fig. 3, the changed commodity title and commodity picture are first acquired. And secondly, an operator input operator matched with the commodity title and the picture, namely an operator 1 (starting operator), is obtained from the operator relation structure. At this time, the changed commodity title is input as an operator of the operator 1, and the operator 1 predicts the category of the changed commodity title to obtain a predicted category characteristic, wherein the predicted category characteristic may be a food category ID (identifier), a clothing category ID (identifier), or the like. Then determining which operator is the operator input of operator 1 from the operator relation structure shown in fig. 3, thereby determining the next operator of operator 1, operator 2 (intermediate operator), taking the prediction category and commodity picture as the operator input of operator 2, obtaining the picture feature of commodity picture, determining the next operator of operator 2, operator 3 (termination operator) based on the operator relation structure, obtaining the multi-mode vector feature by model reasoning of operator 3 on the prediction category and picture feature, wherein the multi-mode vector feature can be: merchandise tag features, merchandise description features, and the like. The final prediction category (initial feature data), the picture features of the commodity picture (intermediate feature data), and the multi-modal features (final feature data) are combined into one feature data sequence.
According to the method provided by the embodiment of the application, the target parameters are utilized to automatically match the initiation operator from the operator relation structure, the initiation operator can automatically deduce the intermediate operator and the termination operator based on the transmission direction in the operator relation structure, and the intermediate operator and the termination operator are utilized to perform characteristic calculation. Compared with the prior art, the method has the advantages that the flexibility is higher, the processing efficiency of commodity characteristics is effectively improved, and meanwhile, the consistency of characteristic data is also considered.
Fig. 3 is a flowchart of a method for processing commodity features according to an embodiment of the present application, as shown in fig. 3, the flowchart including the steps of:
step S21, acquiring a commodity feature calculation task, wherein the commodity feature calculation task comprises a target commodity and target parameters corresponding to the target commodity and used for calculating commodity features. The detailed description refers to the corresponding related descriptions of the above embodiments, and will not be repeated here.
Step S22, an initial operator matched with the target parameter is obtained from a pre-generated operator relation structure, wherein the operator relation structure comprises a plurality of operators and transfer directions among different operators, and the transfer directions are determined according to operator input and operator output of the operators. The detailed description refers to the corresponding related descriptions of the above embodiments, and will not be repeated here.
Step S23, taking the target parameters as input data of an operator relation structure, carrying out feature calculation on the target parameters through an initial operator to obtain initial feature data, carrying out feature calculation on the initial feature data through an intermediate operator to obtain intermediate feature data, and processing the intermediate feature data through a termination operator to obtain final feature data, wherein the intermediate operator comprises operators except the termination operator and the initial operator in the operator relation structure.
In the embodiment of the application, the initial characteristic data is obtained by carrying out characteristic calculation on the target parameters through an initiation operator, and the method comprises the following steps of C1-C3:
and C1, obtaining cache configuration information, wherein the cache configuration information comprises operator identifications corresponding to each operator and calculation results, and the calculation results are obtained by performing characteristic calculation on the operators in advance.
In the embodiment of the application, in order to reduce the time of feature transfer between operators in the feature calculation process, the cache configuration information is increased, any operator can firstly inquire the cache configuration information in the subsequent feature calculation process, and if the cache configuration information carries the calculation result of the operator, the operator does not need to calculate any more, and the calculation result in the cache configuration information is directly transferred to the next operator. The method solves the problem of repeated calculation of operators, and reduces the time of feature transfer between operators by improving the calculation efficiency of single operators.
In the embodiment of the application, the operator identification and the calculation result in the cache configuration information are stored in the form of key value pairs. The operator is identified as Key, the calculation result is value, according to the spliced character string of the corresponding buffer configuration of the operator, the character string is calculated by using a Message-Digest Algorithm (MD 5) to obtain a hash value, and the hash value is used as the operator identifier (namely, the Key of the buffer configuration information).
In the embodiment of the application, the operator cache key configuration format: input1, input2, input3, version, wherein input1 is an operator identifier corresponding to operator 1, input2 is an operator identifier corresponding to operator 2, input3 is an operator identifier corresponding to operator 3, wherein [. Times ] is used for marking whether the operator identifier needs to be broken up to serve as a key of a cache, version represents a current version number, the cache can be refreshed when the operator iterates, and the version number also changes at the moment.
When a commodity contains a plurality of images, the operator input into the image can perform feature calculation on each image corresponding to the commodity, and then the calculated features of each image are combined through a list < any > structure to be stored as a complete feature. Therefore, when the image features of the commodity are stored, the operator identification of the operator is scattered to serve as a cached key. After the image of the commodity is changed, the image features of the unchanged image can be obtained directly through the cache key, meanwhile, the changed image is calculated to obtain new image features, and finally, the new image features and the image features of the unchanged image are combined into new complete features through a list < any > structure.
And step C2, inquiring whether a first operator identifier corresponding to the starting operator exists in the cache configuration information.
And step C3, under the condition that the first operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the first operator identifier from the cache configuration information, and taking the calculation result corresponding to the first operator identifier as initial characteristic data.
In the embodiment of the application, after the cache configuration information is determined, whether a first operator identifier corresponding to an initiator exists is inquired from the cache configuration information, if so, the initiator does not need to calculate target parameters, a corresponding calculation result is directly obtained from the cache configuration, the calculation result is used as initial feature data, and the initial feature data is transmitted to an intermediate operator according to the transmission direction in an operator relation structure.
In the embodiment of the application, the method further comprises the following steps: and under the condition that the first operator identifier does not exist in the cache configuration information, calling an initiator to calculate the target parameter to obtain initial characteristic data, and storing the initial characteristic data as a calculation result of the first operator identifier into the cache configuration information.
When the first operator identifier does not exist in the cache configuration information, the characteristic calculation is not performed before the start operator is described, the start operator is called to calculate the target parameters at the moment, initial characteristic data are obtained, and the initial characteristic data are stored into the cache configuration information as a calculation result of the first operator identifier. Therefore, when the subsequent operator executes calculation again, the corresponding calculation result can be directly extracted from the cache configuration information.
In the embodiment of the application, the initial characteristic data is subjected to characteristic calculation through an intermediate operator to obtain intermediate characteristic data until the intermediate characteristic data is processed by a termination operator to obtain final characteristic data, and the method comprises the following steps of D1-D4:
and D1, determining at least one operator associated with the operator output of the starting operator in the operator relation structure as an intermediate operator, and taking the initial characteristic data as the operator input of the intermediate operator.
Step D2, under the condition that a second operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the second operator identifier from the cache configuration information, and taking the calculation result corresponding to the second operator identifier as intermediate characteristic data, wherein the second operator identifier is an operator identifier corresponding to a target operator.
And D3, acquiring a termination operator associated with the intermediate operator from the operator relation structure, and taking the intermediate characteristic data as operator input of the termination operator.
In an embodiment of the present application, an operator associated with an operator output of an intermediate operator is obtained from an operator relationship structure, and there is no operator of a downstream operator, and the operator is determined to be a termination operator. It should be noted that, the operator output that is the operator without the downstream operator is not used as the operator input of other operators.
And D4, under the condition that a third operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the third operator identifier from the cache configuration information, and taking the calculation result corresponding to the third operator identifier as final characteristic data, wherein the third operator identifier is an operator identifier corresponding to a target operator.
As an example, as shown in fig. 4, operator 1 is an initiator operator, and operator 1 transfers initial feature data to operator 2 (intermediate operator) in the transfer direction in the operator relationship structure.
The operator 2 queries the cache configuration information, if the cache configuration information comprises an operator identifier of the operator 2 and a calculation result, the operator 2 directly pulls the calculation result, takes the calculation result as first intermediate feature data, and then transfers the initial feature data to the operator 2 to the operator 3 (intermediate operator) according to a transfer direction in an operator relation structure.
The operator 3 queries the cache configuration information, if the cache configuration information comprises an operator identifier of the operator 3 and a calculation result, the operator 3 directly pulls the calculation result, takes the calculation result as second intermediate feature data, and then transfers the initial feature data to the operator 3 to the operator 4 according to a transfer direction in an operator relation structure (terminates the operator).
The operator 4 queries the cache configuration information, if the cache configuration information comprises the operator identification of the operator 3 and the calculation result, the operator 4 directly pulls the calculation result, and the calculation result is used as final feature data.
In the embodiment of the application, if the operator identification of the intermediate operator does not exist in the cache configuration information, the intermediate operator is called to calculate the initial feature data to obtain the intermediate feature data, and the intermediate feature data is used as a calculation result of the operator identification and is stored in the cache configuration information. And similarly, if the operator identification of the final operator does not exist in the cache configuration information, calling the final operator to calculate the intermediate feature data to obtain final feature data, and storing the final feature data as a calculation result of the operator identification of the final feature data to the cache configuration information. Based on the above, the calculation efficiency of the subsequent operators can be effectively improved through continuously updating the cache configuration information.
Step S24, constructing a characteristic data sequence of the target commodity based on the initial characteristic data, the intermediate characteristic data and the final characteristic data.
In the embodiment of the application, after the feature data sequence of the target commodity is constructed based on the initial feature data, the intermediate feature data and the final feature data, the feature data in the obtained feature data sequence can be sent to a message queue for distribution and storage by a downstream service. The downstream service firstly reads the characteristic data from the message queue, queries the position to be stored from the storage configuration file corresponding to the characteristic data, wherein the storage comprises a forward index and an inverse index, and then performs serialization storage. For example, when the feature data sequence includes: and searching the corresponding forward index by querying the storage configuration file according to the feature data such as the prediction category, the prediction brand and the like corresponding to the target commodity, and updating the feature data to the forward index. When the characteristic data sequence includes: and searching the corresponding inverted index by inquiring the storage configuration file according to the vector characteristic data corresponding to the target commodity, and updating the characteristic data to the inverted index.
After the characteristic data sequence is obtained, the characteristic data in the characteristic data sequence can be distributed, so that forward updating and backward updating are performed, flexible storage of the characteristic data is realized, and accuracy of subsequent commodity inquiry is improved.
The embodiment also provides a processing device for commodity features, which is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides a processing apparatus for commodity features, as shown in fig. 5, including:
the acquiring module 51 is configured to acquire a commodity feature calculation task, where the commodity feature calculation task includes a target commodity and a target parameter corresponding to the target commodity and used for calculating a commodity feature;
a query module 52, configured to obtain an initiation operator matched with the target parameter from a pre-generated operator relationship structure, where the operator relationship structure includes a plurality of operators and a transfer direction between different operators, and the transfer direction is determined according to an operator input and an operator output of the operators;
The processing module 53 is configured to perform feature computation on the target parameter through an initiator to obtain initial feature data, and perform feature computation on the initial feature data through an intermediate operator to obtain intermediate feature data until the intermediate feature data is processed by a terminator to obtain final feature data, where the intermediate operator includes operators other than the terminator and the initiator in the operator relationship structure;
a generation module 54 for constructing a feature data sequence of the target commodity based on the initial feature data, the intermediate feature data, and the final feature data.
In the embodiment of the present application, the obtaining module 51 is configured to obtain a commodity change message queue, where the commodity change message queue carries at least one first candidate commodity and change basic information of the first candidate commodity; acquiring a commodity data table, wherein the commodity data table comprises at least one second candidate commodity and commodity transaction data of the second candidate commodity in unit time; determining a first candidate commodity with the change time falling into a preset time period in the commodity change message queue as a target commodity, or determining a second candidate commodity with the unit time falling into the preset time period in the commodity data table as a target commodity; obtaining target parameters corresponding to target commodities, wherein the target parameters comprise: changing basic information, commodity transaction data or preset characteristic fields; and generating commodity characteristic calculation tasks based on the target commodity and the target parameters.
In an embodiment of the present application, a processing device for commodity features further includes: the construction module is used for acquiring interface description files of all operators; accessing an operator by using an interface description file, and acquiring operator configuration information corresponding to the operator, wherein the operator configuration information comprises operator input and operator output; and determining the transfer directions among the operators according to the operator input and the operator output carried by the configuration information, and constructing an operator relation structure based on the operators and the transfer directions among the operators.
In the embodiment of the present application, the query module 52 is configured to traverse operator inputs of each operator in the operator relationship structure, and determine an operator whose operator input matches the target parameter as an initial operator; or traversing the operator output of each operator in the operator relation structure, determining the operator with the operator output matched with the target parameter as a reference operator, and determining the operator associated with the operator output of the reference operator in the operator relation structure as a starting operator.
In the embodiment of the present application, the processing module 53 is configured to obtain cache configuration information, where the cache configuration information includes an operator identifier corresponding to each operator and a calculation result, and the calculation result is obtained by performing feature calculation on the operators in advance; inquiring whether a first operator identifier corresponding to an initial operator exists in the cache configuration information; under the condition that the first operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the first operator identifier from the cache configuration information, and taking the calculation result corresponding to the first operator identifier as initial characteristic data.
In an embodiment of the present application, a processing device for commodity features further includes: and the calling module is used for calling the starting operator to calculate the target parameters under the condition that the first operator identifier does not exist in the cache configuration information, obtaining initial characteristic data, and storing the initial characteristic data as a calculation result of the first operator identifier to the cache configuration information.
In the embodiment of the present application, the processing module 53 is configured to determine at least one operator associated with the operator output of the start operator in the operator relationship structure as an intermediate operator, and use the initial feature data as an operator input of the intermediate operator; under the condition that a second operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the second operator identifier from the cache configuration information, and taking the calculation result corresponding to the second operator identifier as intermediate characteristic data, wherein the second operator identifier is an operator identifier corresponding to a target operator; acquiring a termination operator associated with an intermediate operator from an operator relation structure, and taking intermediate characteristic data as operator input of the termination operator; under the condition that a third operator identifier exists in the cache configuration information, obtaining a calculation result corresponding to the third operator identifier from the cache configuration information, and taking the calculation result corresponding to the third operator identifier as final characteristic data, wherein the third operator identifier is an operator identifier corresponding to a target operator.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 6, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system).
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods shown in implementing the above embodiments.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created from the use of the computer device of the presentation of a sort of applet landing page, and the like. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The input device 30 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointer stick, one or more mouse buttons, a trackball, a joystick, and the like. The output means 40 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. Such display devices include, but are not limited to, liquid crystal displays, light emitting diodes, displays and plasma displays. In some alternative implementations, the display device may be a touch screen.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (10)
1. A method of processing a commodity feature, the method comprising:
acquiring a commodity characteristic calculation task, wherein the commodity characteristic calculation task comprises a target commodity and target parameters corresponding to the target commodity and used for carrying out commodity characteristic calculation;
acquiring an initial operator matched with the target parameter from a pre-generated operator relation structure, wherein the operator relation structure comprises a plurality of operators and transmission directions among different operators, and the transmission directions are determined according to operator input and operator output of the operators;
taking the target parameter as input data of the operator relation structure, carrying out feature calculation on the target parameter through the initial operator to obtain initial feature data, carrying out feature calculation on the initial feature data through an intermediate operator to obtain intermediate feature data, and processing the intermediate feature data through a termination operator to obtain final feature data, wherein the intermediate operator comprises operators except the termination operator and the initial operator in the operator relation structure;
And constructing a characteristic data sequence of the target commodity based on the initial characteristic data, the intermediate characteristic data and the final characteristic data.
2. The method of claim 1, wherein the acquiring commodity feature calculation task comprises:
acquiring a commodity change message queue, wherein the commodity change message queue carries change time and change basic information of at least one first candidate commodity;
acquiring a commodity data table, wherein the commodity data table comprises commodity transaction data of at least one second candidate commodity in unit time;
determining a first candidate commodity with the change time falling into a preset time period in the commodity change message queue as the target commodity, or determining a second candidate commodity with the unit time falling into the preset time period in the commodity data table as the target commodity;
obtaining target parameters corresponding to the target commodity, wherein the target parameters comprise: changing basic information, commodity transaction data or preset characteristic fields;
and generating the commodity feature calculation task based on the target commodity and the target parameter.
3. The method of claim 1, wherein prior to retrieving an initiation operator matching the target parameter from a pre-generated operator relationship structure, the method further comprises:
Acquiring interface description files of all operators;
accessing the operator by using the interface description file, and acquiring operator configuration information corresponding to the operator, wherein the operator configuration information comprises operator input and operator output;
determining the transfer direction between operators according to the operator input and the operator output carried by the configuration information, and constructing the operator relation structure based on each operator and the transfer direction between operators.
4. A method according to claim 3, wherein said obtaining an initiation operator matching said target parameter from a pre-generated operator relationship structure comprises:
traversing operator inputs of all operators in the operator relation structure, and determining an operator matched with the operator inputs and the target parameters as the starting operator; or alternatively, the first and second heat exchangers may be,
traversing the operator output of each operator in the operator relation structure, determining the operator with the operator output matched with the target parameter as a reference operator, and determining the operator associated with the operator output of the reference operator in the operator relation structure as the starting operator.
5. The method according to claim 1, wherein the performing feature calculation on the target parameter by the initiation operator to obtain initial feature data includes:
Obtaining cache configuration information, wherein the cache configuration information comprises operator identifications corresponding to operators and calculation results, and the calculation results are obtained by performing feature calculation on the operators in advance;
inquiring whether a first operator identifier corresponding to the starting operator exists or not from the cache configuration information;
under the condition that the first operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the first operator identifier from the cache configuration information, and taking the calculation result corresponding to the first operator identifier as the initial characteristic data.
6. The method of claim 5, wherein the method further comprises:
and under the condition that the first operator identifier does not exist in the cache configuration information, calling the starting operator to calculate the target parameter to obtain the initial characteristic data, and storing the initial characteristic data to the cache configuration information as a calculation result of the first operator identifier.
7. The method according to claim 5, wherein the performing feature computation on the initial feature data by an intermediate operator to obtain intermediate feature data until a final feature data is obtained by processing the intermediate feature data by a termination operator, includes:
Determining at least one operator associated with the operator output of the initiation operator in the operator relationship structure as the intermediate operator, and taking the initial feature data as the operator input of the intermediate operator;
under the condition that a second operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the second operator identifier from the cache configuration information, and taking the calculation result corresponding to the second operator identifier as the intermediate characteristic data, wherein the second operator identifier is an operator identifier corresponding to the target operator;
acquiring the termination operator associated with the intermediate operator from the operator relation structure, and taking the intermediate feature data as operator input of the termination operator;
under the condition that a third operator identifier exists in the cache configuration information, acquiring a calculation result corresponding to the third operator identifier from the cache configuration information, and taking the calculation result corresponding to the third operator identifier as the final characteristic data, wherein the third operator identifier is the operator identifier corresponding to the target operator.
8. A commodity feature processing apparatus, the apparatus comprising:
The acquisition module is used for acquiring commodity characteristic calculation tasks, wherein the commodity characteristic calculation tasks comprise target commodities and target parameters corresponding to the target commodities and used for commodity characteristic calculation;
the query module is used for acquiring an initial operator matched with the target parameter from a pre-generated operator relation structure, wherein the operator relation structure comprises a plurality of operators and transmission directions among different operators, and the transmission directions are determined according to operator input and operator output of the operators;
the processing module is used for taking the target parameter as input data of the operator relation structure, carrying out feature calculation on the target parameter through the initial operator to obtain initial feature data, carrying out feature calculation on the initial feature data through an intermediate operator to obtain intermediate feature data, and processing the intermediate feature data through a termination operator to obtain final feature data, wherein the intermediate operator comprises operators except the termination operator and the initial operator in the operator relation structure;
and the generation module is used for constructing a characteristic data sequence of the target commodity based on the initial characteristic data, the intermediate characteristic data and the final characteristic data.
9. A computer device, comprising:
a memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, cause the processor to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310827173.XA CN116843913A (en) | 2023-07-06 | 2023-07-06 | A method, device, computer equipment and storage medium for processing commodity characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310827173.XA CN116843913A (en) | 2023-07-06 | 2023-07-06 | A method, device, computer equipment and storage medium for processing commodity characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116843913A true CN116843913A (en) | 2023-10-03 |
Family
ID=88170353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310827173.XA Pending CN116843913A (en) | 2023-07-06 | 2023-07-06 | A method, device, computer equipment and storage medium for processing commodity characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843913A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119250370A (en) * | 2024-10-16 | 2025-01-03 | 西南财经大学 | Data processing method, system and medium based on memory rule engine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382347A (en) * | 2018-12-28 | 2020-07-07 | 广州市百果园信息技术有限公司 | Object feature processing and information pushing method, device and equipment |
| KR20210092689A (en) * | 2020-01-15 | 2021-07-26 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Method and apparatus for traversing graph database |
| CN114117206A (en) * | 2021-11-09 | 2022-03-01 | 北京达佳互联信息技术有限公司 | Recommendation model processing method and device, electronic equipment and storage medium |
| CN115878637A (en) * | 2021-09-28 | 2023-03-31 | 北京转转精神科技有限责任公司 | Object data processing method and device, electronic equipment and storage medium |
-
2023
- 2023-07-06 CN CN202310827173.XA patent/CN116843913A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382347A (en) * | 2018-12-28 | 2020-07-07 | 广州市百果园信息技术有限公司 | Object feature processing and information pushing method, device and equipment |
| KR20210092689A (en) * | 2020-01-15 | 2021-07-26 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Method and apparatus for traversing graph database |
| CN115878637A (en) * | 2021-09-28 | 2023-03-31 | 北京转转精神科技有限责任公司 | Object data processing method and device, electronic equipment and storage medium |
| CN114117206A (en) * | 2021-11-09 | 2022-03-01 | 北京达佳互联信息技术有限公司 | Recommendation model processing method and device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119250370A (en) * | 2024-10-16 | 2025-01-03 | 西南财经大学 | Data processing method, system and medium based on memory rule engine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11670288B1 (en) | Generating predicted follow-on requests to a natural language request received by a natural language processing system | |
| US11645471B1 (en) | Determining a relationship recommendation for a natural language request | |
| US11348294B2 (en) | Systems and methods for updating a third party visualization in response to a query | |
| CN111247518B (en) | Method and system for database sharding | |
| US11816140B1 (en) | Non-text machine data processing | |
| US11475053B1 (en) | Providing completion recommendations for a partial natural language request received by a natural language processing system | |
| US11789993B2 (en) | Correlating non-text machine data using event fields | |
| US11921799B1 (en) | Generating and using alert definitions | |
| US11676345B1 (en) | Automated adaptive workflows in an extended reality environment | |
| US11790649B1 (en) | External asset database management in an extended reality environment | |
| CN112084270A (en) | Data blood margin processing method and device, storage medium and equipment | |
| CN112532748B (en) | Message push method, apparatus, device, medium and computer program product | |
| CN108989397B (en) | Data recommendation method and device and storage medium | |
| CN113157947A (en) | Knowledge graph construction method, tool, device and server | |
| JP2023001336A (en) | IMAGE DISPLAY METHOD, IMAGE DISPLAY DEVICE, ELECTRONIC DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM | |
| CN109409419B (en) | Method and apparatus for processing data | |
| US20200342025A1 (en) | Interactive and non-interactive execution and rendering of templates to automate control and exploration across systems | |
| CN110110172B (en) | Information display method and device | |
| CN113655895B (en) | Information recommendation method, device and electronic device applied to input method | |
| CN116843913A (en) | A method, device, computer equipment and storage medium for processing commodity characteristics | |
| CN113076186A (en) | Task processing method and device, electronic equipment and storage medium | |
| CN119520509A (en) | System file download method, device, equipment and medium based on open Hongmeng | |
| CN110929207B (en) | Data processing method, device and computer readable storage medium | |
| CN113377378A (en) | Processing method, device and equipment for small program and storage medium | |
| CN117807188B (en) | Search information processing method, apparatus, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |