Business object pushing method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a business object pushing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to a current operation behavior of a user account in a service system, obtaining target object correlation information associated with the current operation behavior; the target object correlation information is used for recording association strength between a current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the target dimension; the target dimension is a feature dimension used for performing feature analysis on the current operation behavior; screening out a target business object from the candidate business objects according to the target object correlation information; and pushing the target business object to the user account. By adopting the method, the intelligence of business object pushing can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for pushing a business object. Background Art

[0002] In recent years, with the rapid development of Internet technology, recommendation technology has gradually emerged. In business recommendation technology, due to the emergence of more and more business objects in the business system, it is impossible to match business objects to users one by one. How to recommend business objects to users has become a problem.

[0003] In the related art, due to the large number of business objects, it is difficult for users to quickly find the business objects they are interested in. Often, administrators actively assign roles to users or users manually configure and subscribe to related information, which requires more configurations before users can see some business objects they need to pay attention to.

[0004] Therefore, there is a problem in the related art that the intelligence of business object push is low. Summary of the invention

[0005] Based on this, it is necessary to provide a business object push method, apparatus, computer device, computer-readable storage medium and computer program product that can improve the intelligence of business object push in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for pushing a business object, including:

[0007] In response to a current operation behavior of a user account in a business system, target object correlation information associated with the current operation behavior is obtained; the target object correlation information is used to record, under a target dimension, the correlation strength between a current business object associated with the current operation behavior in the business system and each candidate business object in the business system; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior;

[0008] According to the target object relevance information, a target business object is screened out from each of the candidate business objects; under the target dimension, the strength of association between the target business object and the current business object meets a preset condition;

[0009] The target business object is pushed to the user account.

[0010] In a second aspect, the present application also provides a device for pushing a business object, including:

[0011] an acquisition module, configured to acquire target object relevance information associated with the current operation behavior in the business system in response to the current operation behavior of the user account; the target object relevance information is used to record, under a target dimension, the strength of association between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior;

[0012] A screening module, configured to screen out a target business object from each of the candidate business objects according to the target object relevance information; under the target dimension, the strength of association between the target business object and the current business object meets a preset condition;

[0013] A push module is used to push the target business object to the user account.

[0014] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the above method are implemented.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0016] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0017] The above-mentioned business object push method, device, computer equipment, computer-readable storage medium and computer program product obtain target object correlation information associated with the current operation behavior in response to the current operation behavior of the user account in the business system; the target object correlation information is used to record the correlation strength between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the target dimension; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior; according to the target object correlation information, the target business object is screened out from each candidate business object; under the target dimension, the correlation strength between the target business object and the current business object meets the preset conditions; and the target business object is pushed to the user account.

[0018] In this way, according to the operation behavior of the user account in the business system, the relevance information of the target object associated with the current operation can be obtained, and the strength of the association between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the feature dimension used to perform feature analysis on the current operation behavior recorded in the target object relevance information can be obtained, so that the target business object whose association strength with the current business object meets the preset conditions can be screened out and pushed to the user account, so as to realize the priority push of business objects of different feature dimensions according to the different operation behaviors of the user account in the business system, and the real-time push of related business objects according to the real-time operation behavior of the user account, so that the user account can more easily find the business object that meets its needs and preferences for operation, thereby effectively improving the push accuracy of the business object. This method of making intelligent recommendations for business objects based on the operation behavior of the user account effectively improves the intelligence of the business object push. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic diagram of a process for pushing a business object in one embodiment;

[0021] Figure 2 A schematic diagram of a flow chart of a step of obtaining target object relevance information associated with a current operation behavior in one embodiment;

[0022] Figure 3 A schematic diagram of a process flow of a method for pushing a business object in another embodiment;

[0023] Figure 4 is a schematic diagram of interaction between an ERP system and a recommendation system in another embodiment;

[0024] Figure 5 It is a structural block diagram of a device for pushing a business object in one embodiment;

[0025] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0028] In one embodiment, Figure 1 As shown, a method for pushing a business object is provided, and a method for pushing a business object is provided. This embodiment uses the method applied to a computer device as an example. It can be understood that the computer device can be a server or a terminal. The method can be implemented by the server or the terminal alone, or through the interaction between the server and the terminal. The embodiment of the present application provides a method for pushing a business object, which is used to improve the push intelligence of business objects in a business system. It can be applied to various business systems, such as enterprise resource planning systems (Enterprise Resource Planning, ERP), enterprise management systems, financial systems, human resources systems, supply chain systems, etc. In this embodiment, the method includes but is not limited to the following steps:

[0029] Step S110 , in response to the current operation behavior of the user account in the business system, obtaining target object relevance information associated with the current operation behavior.

[0030] Among them, the structure of the business system can be divided into business areas, subsystems, and business objects.

[0031] Among them, the business domain is the highest-level concept of the business system, defining the boundaries and goals of the business system.

[0032] Among them, the subsystem is a further subdivision of the business field, breaking down the business system into multiple large manageable modules.

[0033] Among them, each large domain contains M subsystems, a subsystem contains N business objects, and the functional modules in a subsystem are composed of N business objects.

[0034] Among them, the business object is the specific entity processed in the subsystem, which is the basis for realizing business logic and can be understood as a certain functional module. For example, if the business system is an ERP system, a business object in the ERP system can be understood as a certain functional module in the ERP system, such as the procurement module, production management module, financial management module, etc.

[0035] Among them, the current operation behavior refers to the current operation behavior of the user account in the business system, such as searching for a business object in the business system, accessing a business object in the business system, closing the tab window corresponding to a business object in the business system, and opening the tab window corresponding to a business object in the business system.

[0036] The current business object refers to the business object associated with the current operation behavior, specifically the specific entity pointed to by the current operation behavior.

[0037] For example, if the current operation behavior is to search for business object A in the business system, then the current business object associated with the current operation behavior is business object A; if the current operation behavior is to close the tab window corresponding to business object B in the business system, then the current business object is business object B.

[0038] The object correlation information refers to information recording the correlation strength between each business object in the business system. The correlation strength between each business object may specifically include the correlation strength between each two business objects in each business object.

[0039] The association strength may refer to the degree of correlation between business objects.

[0040] Among them, the target object relevance information is the object relevance information associated with the current operation behavior, which is used to record the strength of the association between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the target dimension.

[0041] Among them, the target dimension is a feature dimension used to perform feature analysis on the current operation behavior.

[0042] The association strength between business objects is obtained by analyzing the correlation between business objects according to different feature dimensions.

[0043] The characteristic dimension may refer to a dimension for performing characteristic analysis on the operation behavior of the user account. Related characteristic dimensions may be pre-set for different operation behaviors.

[0044] In some embodiments, the associated feature dimensions can be preset according to the behavior types. Among them, the behavior types are used to classify the operation behaviors in the business system. For example, if the operation behaviors are to search for business object A in the business system and search for business object B in the business system, the corresponding behavior type is the search type; if the operation behaviors are to close the tab window corresponding to business object C in the business system and close the tab window corresponding to business object D in the business system, the corresponding behavior type is the close type; if the operation behaviors are to use the corresponding business function in the tab window corresponding to business object D and use the corresponding business function in the tab window corresponding to business object E, the corresponding behavior type is the use type.

[0045] In this way, the computer device can determine the feature dimension used for feature analysis of the current operation behavior according to the behavior type corresponding to the current operation behavior, and use it as the target dimension.

[0046] Among them, each candidate business object in the business system can refer to each business object in the business system except the current business object. For example, the business system includes 4 business objects, namely business object A, business object B, business object C, and business object D; when the current business object is business object A, each candidate business object includes business object B, business object C, and business object D; then the target object correlation information associated with the current operation behavior records the association strengths between business object A and business object B, business object C, and business object D respectively under the target dimension.

[0047] In specific implementation, the user account can perform corresponding operations in the business system according to business needs. In this way, the computer device can determine the target dimension used for feature analysis of the current operation behavior in response to the current operation behavior of the user account in the business system, so as to obtain the target object correlation information associated with the current operation behavior. The target object correlation information is used to record the association strengths between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the target dimension.

[0048] Step S120, screen out the target business object from each candidate business object according to the target object correlation information.

[0049] Among them, under the target dimension, the association strength between the target business object and the current business object meets the preset conditions.

[0050] Among them, the preset condition can be that the ranking of the association strength between the target business object and the current business object is among the top X (X < N, X is a positive integer). In some other embodiments, the preset condition can also be that the association strength between the target business object and the current business object is greater than or equal to the preset strength threshold.

[0051] In a specific implementation, the computer device can screen out candidate business objects whose association strength with the current business object meets preset conditions as target business objects based on the association strength between the current business object and each candidate business object under the target dimension recorded in the target object relevance information.

[0052] In some embodiments, the data form of the association strength may be a quantifiable value such as a specific numerical value, level, or gear. The embodiments of the present application do not impose too many limitations on the data form of the association strength.

[0053] For example, taking the data form of the association strength as an association strength value, the computer device may sort the candidate business objects in descending order according to the association strength values ​​between the candidate business objects and the current business object, and take out the first X candidate business objects with the highest association strength values ​​as the target business objects. It is also possible to screen out the candidate business objects whose association strength values ​​with the current business object are greater than or equal to a preset strength threshold from the target object relevance information, and take them as the target business objects.

[0054] Taking the data form of association strength as association strength level as an example, the computer device can sort the association strength levels between the current business object and the candidate business objects in the target object relevance information in descending order, and take out the first X candidate business objects with the highest association strength levels as the target business objects.

[0055] Step S130: Push the target business object to the user account.

[0056] In a specific implementation, the computer device may push the target business object to the user account. Specifically, the computer device may form a push result list according to the object identifier (such as module number or name) of the target business object, and return it to the business system to display the push result to the user account. The push result list indicates the business objects most relevant to the current business object under the target dimension.

[0057] In the case where there are at least two target business objects, the computer device may sort the object identifiers corresponding to the target business objects from high to low according to the association strength between the corresponding target business objects and the current business object to form a push result list.

[0058] In the above-mentioned business object push method, by responding to the current operation behavior of the user account in the business system, the target object correlation information associated with the current operation behavior is obtained; the target object correlation information is used to record the correlation strength between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the target dimension; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior; according to the target object correlation information, the target business object is screened out from each candidate business object; under the target dimension, the correlation strength between the target business object and the current business object meets the preset conditions; and the target business object is pushed to the user account.

[0059] In this way, according to the operation behavior of the user account in the business system, the relevance information of the target object associated with the current operation can be obtained, and the strength of the association between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system under the feature dimension used to perform feature analysis on the current operation behavior recorded in the target object relevance information can be obtained, so that the target business object whose association strength with the current business object meets the preset conditions can be screened out and pushed to the user account, so as to realize the priority push of business objects of different feature dimensions according to the different operation behaviors of the user account in the business system, and the real-time push of related business objects according to the real-time operation behavior of the user account, so that the user account can more easily find the business object that meets its needs and preferences for operation, thereby effectively improving the push accuracy of the business object. This method of making intelligent recommendations for business objects based on the operation behavior of the user account effectively improves the intelligence of the business object push.

[0060] In one embodiment, Figure 2 As shown, step S110, obtaining target object correlation information associated with the current operation behavior, includes the following steps:

[0061] Step S210: query the object correlation information corresponding to the target dimension in the pre-built relational database.

[0062] Among them, under different feature dimensions, the association strength between business objects is different. Therefore, object correlation information under different feature dimensions can be pre-constructed and stored in a relational database.

[0063] In a specific implementation, the computer device can query the object correlation information corresponding to the target dimension in the pre-built relational database, and the object correlation information corresponding to the target dimension is used to record the correlation strength between each business object in the business system under the target dimension. Each business object includes the current business object and each candidate business object.

[0064] Step S220 : extracting information recording the association strength between the current business object and each candidate business object from the object correlation information as target object correlation information.

[0065] In this way, the computer device can extract the information recording the strength of association between the current business object and each candidate business object from the object correlation information recording the strength of association between each business object under the target dimension, as the target object correlation information associated with the current operation behavior.

[0066] For example, the business objects in the business system include business object A, business object B, business object C, and business object D. The object correlation information corresponding to the target dimension records the association strength between business object A and business object B, the association strength between business object A and business object C, the association strength between business object A and business object D, the association strength between business object B and business object C, the association strength between business object B and business object D, and the association strength between business object C and business object D. If the current business object is business object A, the computer device can extract information recording the association strength between business object A and business object B, the association strength between business object A and business object C, and the association strength between business object A and business object D from the object correlation information corresponding to the target dimension as the target object correlation information.

[0067] The technical solution of this embodiment can efficiently and accurately query the object correlation information corresponding to the target dimension through a pre-built relational database, so that according to the object correlation information recording the correlation strength between each business object in the business system under the target dimension, the information recording the correlation strength between the current business object and each candidate business object can be efficiently and accurately extracted. This realizes obtaining the target object correlation information recording the correlation strength between the current business object and each candidate business object through the target dimension corresponding to the current operation behavior and the associated current business object based on the pre-built relational database, thereby improving the reliability of the target object correlation information acquisition method.

[0068] In one embodiment, step S210, in a pre-built relational database, querying the object correlation information corresponding to the target dimension, includes: querying the object correlation matrix corresponding to the target dimension in the relational database; the object correlation matrix is ​​used to record the correlation values ​​between each business object under the target dimension; the correlation value is used to characterize the association strength; and obtaining the object correlation information corresponding to the target dimension according to the object correlation matrix.

[0069] The object correlation information corresponding to each feature dimension may be recorded in the form of a correlation matrix. Accordingly, the correlation matrix used to record the object correlation information may be named an object correlation matrix.

[0070] As mentioned above, the functional modules in a subsystem are composed of N business objects. Thus, they can be combined into a two-dimensional matrix relationship through functional grouping to construct a matrix diagram of all functional modules of the entire business system. The matrix diagram can be a two-dimensional or three-dimensional structure.

[0071] Specifically, the object correlation matrix in this embodiment is a two-dimensional matrix used to represent the co-occurrence frequency or mutual relationship between business objects (functional modules). Assuming that there are N business objects in the business system, the correlation matrix is ​​an N×N matrix.

[0072] Matrix definition: Let the elements in matrix R be Represents a functional module With function modules The correlation value between them is used to characterize the strength of association. The matrix form is as follows:

[0073]

[0074] In this way, the computer device can query the object correlation matrix corresponding to the target dimension in the relational database. The object correlation matrix corresponding to the target dimension is used to record the correlation values ​​between each business object under the target dimension, so that the object correlation information corresponding to the target dimension can be obtained according to the object correlation matrix corresponding to the target dimension.

[0075] Further, step S220, in the object correlation information, information recording the strength of association between the current business object and each candidate business object is extracted as the target object correlation information, including: in the object correlation matrix, matrix data matching the current business object is extracted; wherein the matrix data is used to record the correlation value between the current business object and each candidate business object under the target dimension; and the target object correlation information is obtained based on the matrix data.

[0076] Specifically, according to the form of the above object correlation matrix, it can be seen that each row of data in the matrix represents the correlation value between a certain functional module and all functional modules (including itself). In this way, the computer device can extract the matrix data matching the current business object from the object correlation matrix corresponding to the target dimension, that is, the matrix data recording the correlation value between the current business object and each candidate business object, so that the target object correlation information associated with the current operation behavior can be obtained according to the matrix data matching the current business object.

[0077] In actual applications, the current business object corresponds to a row in the object correlation matrix corresponding to the target dimension, and the computer device can extract the matrix data of this row as the matrix data matching the current business object. Furthermore, the matrix data of this row also contains the correlation value between the current business object and itself, which is usually 1, and can be excluded. All correlation values ​​except the correlation value with itself in the matrix data of this row are extracted to obtain the matrix data matching the current business object.

[0078] Take the current business object as function module A as an example for explanation: In the object correlation matrix corresponding to the target dimension, function module A corresponds to a row in the matrix. For example, if module A is the i-th row in the matrix, all elements in this row represent the correlation values ​​between function module A and other function modules.

[0079] Assume that the object correlation matrix corresponding to the target dimension is R (referred to as matrix R), and the functional module A (specifically functional module ) In the i-th row, the element in the matrix R Indicates functional module A ( ) and functional modules The correlation value between .

[0080] Extract the data of the i-th row in the matrix R, which represents the correlation value between function module A and all other function modules: ,in is the correlation between function module A and itself, which is usually 1 and can be ignored. The row of data after is the matrix data matching the functional module A.

[0081] In this way, when the computer device selects the target business object from the candidate business objects according to the target object relevance information, the computer device can sort the relevance values ​​in this row of matrix data from high to low, and extract the first X (for example, 10, or other values, the specific value is set according to actual needs) function modules with the highest relevance values ​​according to the sorting result. Assume that the sorted relevance value list is: , then the functional modules corresponding to the top 10 highest correlation values ​​are the 10 functional modules with the strongest association strength with functional module A.

[0082] Thus, when the computer device pushes the target business object to the user account, the computer device can return the module number or name corresponding to the filtered function module to form a push result list, indicating the 10 most relevant function modules of function module A. For example: .

[0083] The technical solution of this embodiment is to query the object correlation matrix corresponding to the target dimension in the relational database; the object correlation matrix is ​​used to record the correlation values ​​between each business object under the target dimension; the correlation value is used to characterize the strength of association; in the object correlation matrix, the matrix data matching the current business object is extracted; the matrix data is used to record the correlation values ​​between the current business object and each candidate business object under the target dimension; according to the matrix data, the target object correlation information is obtained. In this way, the object correlation matrix corresponding to the target dimension can be efficiently and accurately queried through the relational database, and the correlation values ​​between each business object under the target dimension can be accurately characterized through the object correlation matrix corresponding to the target dimension, so that the matrix data used to record the correlation values ​​between the current business object and each candidate business object under the target dimension can be efficiently and accurately extracted from the object correlation matrix corresponding to the target dimension, so as to more reliably obtain the target object correlation information associated with the current operation behavior based on the extracted matrix data.

[0084] In one embodiment, the relational database includes an account relational database. When the user account is a historical user account, object correlation information corresponding to the target dimension is queried in the pre-built relational database, including: querying the account correlation information associated with the historical user account in the account relational database; and extracting the object correlation information corresponding to the target dimension from the account correlation information.

[0085] Among them, the historical user account is a user account that has corresponding historical operation behavior data in the business system, or a user account whose amount of corresponding historical operation behavior data meets a preset quantity condition.

[0086] The historical operation behavior data is data used to record the historical operation behavior of a user account.

[0087] The account relevance information is determined based on the historical operation behaviors of historical user accounts in the business system.

[0088] The account relevance information includes object relevance information corresponding to feature dimensions assigned to different historical operation behaviors of historical user accounts.

[0089] In actual applications, different feature dimensions can be assigned to different historical user accounts according to the usage habits determined by the historical operation behaviors of the historical user accounts, so as to further realize personalized push of business objects for different user accounts and diversification of push behaviors for different user accounts.

[0090] The account relationship database may record the account correlation information associated with each historical user account, and different account correlation information may be recorded for different historical user accounts.

[0091] In a specific implementation, a computer device can query the account correlation information associated with a historical user account currently operating in the business system from the account correlation information associated with multiple historical user accounts recorded in the account relationship database, where the account correlation information associated with the historical user account is determined based on the historical operation behavior of the historical user account in the business system; the account correlation information associated with the historical user account includes object correlation information corresponding to the feature dimensions assigned to the historical user account for different historical operation behaviors of the historical user account.

[0092] In this way, the computer device can extract the object correlation information corresponding to the target dimension from the account correlation information associated with the historical user accounts.

[0093] In the technical solution of this embodiment, the relational database includes an account relational database. When the user account is a historical user account, the account correlation information associated with the historical user account is queried in the account relational database; the account correlation information is determined based on the historical operation behavior of the historical user account in the business system; the account correlation information includes object correlation information corresponding to the feature dimensions assigned to different historical operation behaviors of the historical user account; in the account correlation information, the object correlation information corresponding to the target dimension is extracted.

[0094] In this way, the account correlation information associated with different historical user accounts is recorded in the account relationship database, and the account correlation information associated with the historical user accounts currently operating in the business system is queried from the account relationship database. These account correlation information are determined based on the historical operation behaviors of the historical user accounts in the business system, including the object correlation information corresponding to the feature dimensions assigned to the different historical operation behaviors of the historical user accounts. Therefore, the object correlation information corresponding to the target dimension can be extracted from the account correlation information, and based on the object correlation information corresponding to the target dimension, the business objects that meet the usage habits are pushed to the historical user accounts according to the current operation behaviors of the historical user accounts currently operating in the business system. This realizes pushing business objects that better meet the usage needs to the historical user accounts according to the usage habits of different historical user accounts, thereby improving the personalization and push accuracy of business object push.

[0095] In one embodiment, the relational database includes a general relational database, and the general relational database includes general object correlation information corresponding to each feature dimension.

[0096] The general object relevance information is object relevance information determined based on historical operation behaviors of multiple historical user accounts in the business system.

[0097] When the user account is a new user account, the object correlation information corresponding to the target dimension is queried in a pre-built relational database, including: querying the general object correlation information corresponding to the target dimension in a general relational database; and using the general object correlation information corresponding to the target dimension as the object correlation information corresponding to the target dimension.

[0098] Among them, the new user account is a user account for which there is no historical operation behavior data in the business system, or the corresponding historical operation behavior data does not meet the preset quantity conditions.

[0099] In a specific implementation, when the user account currently operating in the business system is a new user account, since the historical operation behavior data of the new user account is too little, the computer device can query the general object correlation information corresponding to the target dimension in the general relational database; and use the general object correlation information corresponding to the target dimension as the object correlation information corresponding to the target dimension.

[0100] In the technical solution of this embodiment, the relational database includes a universal relational database, and the universal relational database includes universal object relevance information corresponding to each characteristic dimension; the universal object relevance information is object relevance information determined based on historical operation behaviors of multiple historical user accounts in the business system; when the user account is a new user account, the universal object relevance information corresponding to the target dimension is queried in the universal relational database; the universal object relevance information corresponding to the target dimension is used as the object relevance information corresponding to the target dimension.

[0101] In this way, even if the user account currently operating in the business system is a new user account, it is still possible to filter out the common object relevance information corresponding to the target dimension based on the historical operation behaviors of a large number of historical user accounts, and perform preliminary business object push to the new user account. This can achieve adaptive recommendations for the current operation behaviors of the new user account and improve the push accuracy for new user accounts with sparse data.

[0102] In one embodiment, before the step of querying the object correlation information corresponding to the target dimension in the pre-built relational database, the method also includes: obtaining historical operation behavior data of historical user accounts in the business system; performing calculations on the historical operation behavior data according to the data calculation rules corresponding to the correlation indicators matched by each feature dimension, so as to obtain the correlation strength between each pair of business objects in each business object under each feature dimension.

[0103] Among them, historical operation behavior data is data used to record the historical operation behaviors of historical user accounts in the business system.

[0104] Among them, historical operation behavior data may include operation logs, embedded point data and usage habit data of historical user accounts.

[0105] Among them, the operation log is a log that records the relevant operations performed by the user account in the business system (view, add, delete, modify, etc.).

[0106] Among them, the tracking data is the statistical data made to count the functions of the business system used by user accounts.

[0107] Among them, the correlation index corresponds to the feature dimension one by one. For example, if the feature dimension is the switching frequency dimension, then the corresponding correlation index is the switching frequency index; if the feature dimension is the co-occurrence frequency dimension, then the corresponding correlation index is the co-occurrence frequency index.

[0108] In a specific implementation, before the computer device queries the object correlation information corresponding to the target dimension in the pre-built relational database, it can first construct a mapping relationship between the feature dimension and the object correlation information. Specifically, the computer device can obtain the historical operation behavior data of the historical user account in the business system, and the historical operation behavior data is data used to record the historical operation behavior of the historical user account in the business system.

[0109] The computer device can perform calculations and processing on the historical operation behavior data according to the data calculation rules corresponding to the correlation indicators matching each feature dimension, and obtain the correlation strength between each business object in the business system under the feature dimension, thereby obtaining the object correlation information corresponding to each feature dimension of the historical user account.

[0110] Among them, the historical operation behavior data is recorded by the business system. After obtaining the historical operation behavior data, the business system can first pre-process the historical operation behavior data, and then perform feature extraction on the pre-processed historical operation behavior data under different feature dimensions, and extract the feature information of different feature dimensions of historical user accounts using various business objects as user behavior feature data, so that the computer device can calculate and process the user behavior feature data according to the data calculation rules corresponding to each correlation indicator, and obtain the correlation strength between each business object in the business system under each feature dimension.

[0111] Among them, different feature dimensions may include co-occurrence frequency dimension, switching frequency dimension, residence time correlation dimension, mutual influence degree dimension, etc. The feature dimensions correspond to correlation indicators one by one, so the correlation indicators may include co-occurrence frequency indicator, switching frequency indicator, residence time indicator, mutual influence degree indicator, etc.

[0112] Take the elements in matrix R Represents a functional module With function modules For the convenience of understanding by those skilled in the art, the following describes each feature dimension:

[0113] Co-occurrence frequency: the frequency with which a user account uses these two functional modules at the same time.

[0114] Switching frequency: User account from function module Switch to the function module The number of times.

[0115] Dwell time correlation: the similarity or correlation of the dwell time of user accounts in these two functional modules.

[0116] Mutual influence: functional modules With function modules Whether the operation of one functional module triggers the use of another module.

[0117] In this way, in the process of extracting features from the preprocessed historical operation behavior data in different feature dimensions, the computer device can extract features such as the usage frequency, residence time, path analysis (switching behavior between different business objects) of the business objects, so as to obtain feature information of different feature dimensions of the historical user accounts using each business object.

[0118] Among them, the data calculation rules corresponding to each correlation indicator are as follows:

[0119] Co-occurrence frequency index: Calculates the number of function modules used by a user account during one operation or one visit. and function modules The frequency of is usually expressed as:

[0120]

[0121] in, Represents the correlation value under the co-occurrence frequency indicator.

[0122] Switching frequency index: Calculates the number of times users switch from a functional module Switch to the function module The frequency is:

[0123]

[0124] in, Indicates the correlation value under the switching frequency indicator.

[0125] Stay time correlation index: If the stay time of a user account in two functional modules is close (for example, the two functional modules are opened at the same time on the business system), it can be considered that there is a certain correlation between the two functional modules. The calculation formula is:

[0126]

[0127] in, Indicates the correlation value under the residence time correlation indicator.

[0128] in, Indicates that the user account is in the function module The average dwell time on Indicates that the user account is in the function module The average dwell time on is the maximum value of the residence time; Specifically, it refers to the time from when a single user account logs into a business system to when it logs out of the business system, that is, the total time the user account uses the business system at one time.

[0129] For example, after a user account logs into a business system, it usually operates a certain business, but this business may involve multiple function modules, so the user account will open the tab windows of multiple function modules. For example, after opening the tab window of function module A, the tab window of function module B is opened, and then the tab window of function module C is opened. However, after using it for a period of time, the user account closes the tab window of function module C, and only retains the tab windows of function modules A and B. This means that the user account needs to use function modules A and B back and forth more closely. Then the stay time of function modules A and B is relatively close, and the stay time correlation between function modules A and B is higher.

[0130] Mutual influence: Analyze the dependency between functional modules to determine whether the use of a certain functional module will significantly increase the use probability of other functional modules. This can be calculated using statistical probability or causal analysis models.

[0131] In this way, by performing operations on user behavior feature data according to the data operation rules corresponding to different correlation indicators, the correlation value between each business object in each business object under each feature dimension can be calculated. The correlation value can characterize the association strength between each business object in each business object under the corresponding feature dimension. Therefore, according to the association strength between each business object in each business object under each feature dimension, the object correlation information corresponding to each feature dimension can be obtained and stored in the relational database.

[0132] For example, if the characteristic dimension is the switching frequency dimension, the user behavior characteristic data can be processed according to the data operation rules corresponding to the switching frequency indicator to obtain the correlation value between two business objects under the switching frequency dimension. For another example, if the characteristic dimension is the co-occurrence frequency dimension, the user behavior characteristic data can be processed according to the data operation rules corresponding to the co-occurrence frequency dimension to obtain the correlation value between two business objects under the switching frequency dimension.

[0133] The technical solution of this embodiment is to obtain historical operation behavior data of historical user accounts in the business system before querying the object correlation information corresponding to the target dimension in the pre-built relational database; the historical operation behavior data is data used to record the historical operation behavior of historical user accounts in the business system; the historical operation behavior data is processed according to the data operation rules corresponding to the correlation indicators matched by each feature dimension, so as to obtain the correlation strength between each business object under each feature dimension; according to the correlation strength between each business object under each feature dimension, the object correlation information corresponding to each feature dimension is obtained, and stored in the relational database.

[0134] In this way, by performing calculations on historical operation behavior data through data operation rules corresponding to correlation indicators matching each feature dimension, feature analysis can be performed on historical operation behavior data from different feature dimensions to obtain the strength of association between each business object in the business system under each feature dimension. Therefore, according to different operation behaviors of user accounts and based on the strength of association between each business object in the business system under the feature dimensions corresponding to each operation behavior, the push strategy for the user account can be automatically adjusted, thereby improving the intelligence of the push.

[0135] In one embodiment, when the target dimension includes at least two characteristic dimensions, the method also includes: obtaining weight information corresponding to each characteristic dimension of the target dimension, and the correlation strength between two business objects under the correlation indicators corresponding to each characteristic dimension of the target dimension; obtaining object correlation information corresponding to the target dimension according to weighted information between the weight information corresponding to each characteristic dimension in the target dimension and the corresponding correlation strength; and storing the object correlation information corresponding to the target dimension in a relational database.

[0136] Among them, for some operation behaviors, multiple feature dimensions can be used for analysis. For example, for function module search behavior, multiple feature dimensions can be used for object correlation analysis. For example, for function module search behavior, co-occurrence frequency dimension and switching frequency dimension can be used for object correlation analysis; or, co-occurrence frequency dimension and dwell time correlation dimension can be used for object correlation analysis; or, co-occurrence frequency dimension, dwell time correlation dimension, switching frequency dimension and mutual influence dimension can be used for object correlation analysis.

[0137] In a specific implementation, when the target dimension includes at least two characteristic dimensions, the computer device can obtain the weight information corresponding to each characteristic dimension of the target dimension, as well as the correlation strength between two business objects under the correlation indicators corresponding to each characteristic dimension of the target dimension; obtain the object correlation information corresponding to the target dimension according to the weighted information between the weight information corresponding to each characteristic dimension in the target dimension and the corresponding correlation strength; and store the object correlation information corresponding to the target dimension in a relational database.

[0138] Specifically, the computer device can obtain the target correlation value between each pair of business objects under the target dimension based on the weighted information between the weight coefficients corresponding to each feature dimension and the corresponding correlation values ​​in the target dimension, and obtain the object correlation information corresponding to the target dimension based on the target correlation value between each pair of business objects under the target dimension.

[0139] For example, when the target dimension includes multiple feature dimensions, the object correlation matrix corresponding to the target dimension is taken as matrix R, and the elements of matrix R are is the target relevance value, which can be obtained by weighted summation of these relevance indicators (feature dimensions):

[0140]

[0141] Among them, w1, w2, and w3 are the weights of different correlation indicators (feature dimensions), representing the weights of the co-occurrence frequency indicator, the switching frequency indicator, and the residence time correlation indicator, respectively. They can be optimized according to the actual application scenarios and experimental results.

[0142] In this way, the relational database can not only store the object correlation information corresponding to each feature dimension, such as the object correlation matrix corresponding to the co-occurrence frequency dimension and the object correlation matrix corresponding to the switching frequency dimension; it can also store the weighted object correlation information of multiple feature dimensions, such as the weighted object correlation matrix, and there will be different matrix data for different historical user accounts, thereby improving the accuracy of data push.

[0143] The technical solution of this embodiment, when the target dimension includes at least two characteristic dimensions, obtains the weight information corresponding to each characteristic dimension of the target dimension, and the correlation strength between two business objects under the correlation index corresponding to each characteristic dimension of the target dimension; obtains the object correlation information corresponding to the target dimension according to the weight information corresponding to each characteristic dimension in the target dimension and the weighted information between the corresponding correlation strength; and stores the object correlation information corresponding to the target dimension in a relational database. In this way, by introducing multiple characteristic dimensions and corresponding weight information, the correlation strength between different business objects can be more comprehensively evaluated, and by weighted integration of this information, object correlation information that is more in line with the user account usage habits can be generated, thereby achieving more accurate push.

[0144] In another embodiment, Figure 3 As shown, a method for pushing a business object is provided, and the method is applied to a computer device as an example for explanation, and includes the following steps:

[0145] Step S302: Obtain historical operation behavior data of historical user accounts in the business system.

[0146] Step S304 , according to the data operation rules corresponding to the correlation indicators matched by each characteristic dimension, the historical operation behavior data is operated and processed to obtain the correlation strength between each business object in each characteristic dimension.

[0147] Step S306, according to the correlation strength between each business object in each business object under each characteristic dimension, obtain the object correlation information corresponding to each characteristic dimension, and store it in a relational database.

[0148] Step S308 , in response to the current operation behavior of the user account in the business system, query the object correlation matrix corresponding to the target dimension in the relational database.

[0149] Step S310: extracting matrix data matching the current business object from the object correlation matrix.

[0150] Step S312: obtaining target object correlation information associated with the current operation behavior according to the matrix data.

[0151] Step S314: Filter out the target business object from the candidate business objects according to the target object relevance information.

[0152] Step S316: Push the target business object to the user account.

[0153] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a method for pushing a business object above.

[0154] In order to facilitate the understanding of those skilled in the art, a computer device with a push system (recommendation system) is deployed, and the business system is an ERP system as an example. Figure 4 A schematic diagram of the interaction between an ERP system and a recommendation system is provided. Specifically:

[0155] On the ERP system side, the system needs to record the operational behavior data of user accounts on each terminal (mobile terminal, PC terminal), and then pre-process the operational behavior data (such as deduplication, clarification, data standardization, serialization processing and other pre-processing operations), and then perform feature extraction on the pre-processed operational behavior data under different feature dimensions to extract feature information, such as: frequency of use of functional modules, residence time, path analysis (switching behavior between different functional modules), and upload these feature information as user behavior feature data to the recommendation system.

[0156] The recommendation system will build an association matrix model of the functional modules according to the preset functional module tree structure. At the same time, based on user behavior feature data or external data (such as product-related information involved in the functional modules), it will extract feature information of different feature dimensions of the user account using each functional module (such as co-occurrence frequency, switching frequency, residence time, mutual influence, etc.), and by assigning weights to feature information of different feature dimensions, it will debug association matrix models under different weight combinations (including multiple correlation matrices) and determine the optimal weight value for each feature dimension (for example, if the recommendation system hopes to better reflect the functions recently used by the user account, it is necessary to increase the weights of the co-occurrence frequency dimension and the residence time correlation dimension, and reduce the weights of other feature dimensions). At the same time, the user behavior feature data of the user account each time it is used will affect the correlation data of this model, thereby dynamically updating the data of this model. In other words, through the allocation and debugging of user behavior feature data and feature weights of different feature dimensions, multiple weighted correlation matrices for different feature dimensions and different feature dimension combinations of user accounts can be formed. When a user account uses a certain functional module of the business system, the recommendation system can identify a list of strong and weak combinations of correlations with this functional module (i.e., a push result list) to push related functions. Each time the user behavior feature data of a user account is uploaded, the association matrix model of the user account will be dynamically adjusted.

[0157] After receiving the push result list pushed by this recommendation system on the ERP side, you can make personalized display or configuration for this push result list (such as function recommendation, permission pre-allocation, push of hot function information, etc.).

[0158] As can be seen from the analysis in the above embodiment, there are 1 to N functional modules in the business system, the object correlation matrix is ​​R, and the functional module and function modules The correlation value between , and the correlation value has relevant feature dimensions and weight information, such as: the co-occurrence frequency dimension can be expressed as , and its weight coefficient is , the switching frequency dimension can be expressed as , and its weight coefficient is 2. Under the weighting of multiple feature dimensions, the functional module and function modules The final correlation value is In this way, the present application can make priority recommendations for different feature dimensions according to different operation behaviors of user accounts, and can also make weighted priority recommendations for multiple feature dimensions.

[0159] For example:

[0160] There are four function modules, ABCD, in the business system. When a user account uses the business system 50 times in total, AB / AC / AD modules are used together 6 / 18 / 10 times, which means that the co-occurrence frequency of function modules A and C is higher than that of other function modules. After using function module A, the total number of switches to other function modules is 100, and the number of switches to B / C / D is 50 / 30 / 20, which means that the switching frequency from function module A to function module B is the highest.

[0161] Then the recommendation system can give priority to recommending function module B and function module C when the user account uses function module A. The function module recommendation operation can be performed based on the operation behavior related to the user account and function module A.

[0162] For example, in the help center of function module A, you can make guidance recommendations for related function modules, using the co-occurrence frequency feature, and the recommendation priority is C > D > B;

[0163] For example, after function module A is used up, that is, after closing the tab window corresponding to function module A, a priority recommendation for the next function module can be made. Using the switching frequency feature, the recommended priorities are B > C > D;

[0164] For example, when searching for functional module A, the results can be weighted according to the relevance values ​​of multiple different feature dimensions. The numerical value of will be used to make the sorting priority recommendation. Different combinations of recommendation results will be generated according to different weights.

[0165] In some embodiments, different feature dimensions and feature weights may be flexibly introduced into the recommendation system to update the correlation matrix of user accounts, and different feature dimensions and weights may be assigned to different user accounts to achieve diversification of recommendation behaviors of different user accounts.

[0166] It is also possible to preset or adjust the feature dimensions of different operation behaviors of the user account in the recommendation system to obtain a correlation matrix associated with the feature dimensions of the user account.

[0167] In summary, this solution can reduce excessive configurations of roles, permissions, functions, etc. in large-scale system software, and reduce the cost of implementation delivery and user use. It can quickly locate the corresponding functions for user accounts with similar characteristics, and is easy to use. It can also make intelligent recommendations and quick use of related and commonly used functions. At the same time, it can also accurately push messages for hot information that user accounts are concerned about.

[0168] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0169] Based on the same inventive concept, the embodiment of the present application also provides a business object push device for implementing the business object push method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the push device for one or more business objects provided below can refer to the limitations on the business object push method above, and will not be repeated here.

[0170] In an exemplary embodiment, Figure 5 As shown, a device for pushing a business object is provided, including: an acquisition module 510, a screening module 520 and a pushing module 530, wherein:

[0171] Acquisition module 510 is used to obtain target object correlation information associated with the current operation behavior of the user account in the business system in response to the current operation behavior of the user account in the business system; the target object correlation information is used to record, under the target dimension, the strength of correlation between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior.

[0172] The screening module 520 is used to screen out a target business object from the candidate business objects according to the target object relevance information; under the target dimension, the correlation strength between the target business object and the current business object meets a preset condition.

[0173] The push module 530 is used to push the target business object to the user account.

[0174] In one of the embodiments, the acquisition module 510 is specifically used to query the object correlation information corresponding to the target dimension in a pre-built relational database; the object correlation information is used to record the correlation strength between each business object in the business system under the target dimension; each business object includes the current business object and each candidate business object; in the object correlation information, the information recording the correlation strength between the current business object and each candidate business object is extracted as the target object correlation information.

[0175] In one of the embodiments, the acquisition module 510 is specifically used to query the object correlation matrix corresponding to the target dimension in the relational database; the object correlation matrix is ​​used to record the correlation values ​​between each of the business objects under the target dimension; the correlation values ​​are used to characterize the association strength; the object correlation information is obtained according to the object correlation matrix; in the object correlation matrix, matrix data matching the current business object is extracted; the matrix data is used to record the correlation values ​​between the current business object and each of the candidate business objects under the target dimension; and the target object correlation information is obtained according to the matrix data.

[0176] In one embodiment, the relational database includes an account relational database. When the user account is a historical user account, the acquisition module 510 is specifically used to query the account correlation information associated with the historical user account in the account relational database; the account correlation information is determined based on the historical operation behavior of the historical user account in the business system; the account correlation information includes object correlation information corresponding to the feature dimensions assigned to different historical operation behaviors of the historical user account; and in the account correlation information, the object correlation information corresponding to the target dimension is extracted.

[0177] In one of the embodiments, the relational database includes a universal relational database, and the universal relational database includes universal object relevance information corresponding to each characteristic dimension; the universal object relevance information is object relevance information determined based on historical operation behaviors of multiple historical user accounts in the business system; when the user account is a new user account, the acquisition module 510 is specifically used to query the universal object relevance information corresponding to the target dimension in the universal relational database; and use the universal object relevance information corresponding to the target dimension as the object relevance information corresponding to the target dimension.

[0178] In one embodiment, the device also includes: a construction module, used to obtain historical operation behavior data of historical user accounts in the business system; the historical operation behavior data is data used to record the historical operation behavior of the historical user account in the business system; the historical operation behavior data is processed according to the data operation rules corresponding to the correlation indicators matched by each feature dimension, so as to obtain the correlation strength between each pair of business objects in each business object under each feature dimension; according to the correlation strength between each pair of business objects in each business object under each feature dimension, the object correlation information corresponding to each feature dimension is obtained, and stored in the relational database.

[0179] In one of the embodiments, when the target dimension includes at least two of the characteristic dimensions, the construction module is specifically used to obtain the weight information corresponding to each of the characteristic dimensions of the target dimension, and the correlation strength between the two business objects under the correlation index corresponding to each of the characteristic dimensions of the target dimension; obtain the object correlation information corresponding to the target dimension according to the weighted information between the weight information corresponding to each of the characteristic dimensions in the target dimension and the corresponding correlation strength; and store the object correlation information corresponding to the target dimension in the relational database.

[0180] Each module in the push device of the above business object can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0181] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store object correlation information data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for pushing a business object is implemented.

[0182] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0183] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0184] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0185] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0186] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0187] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0188] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0189] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for pushing a business object, characterized in that: The method comprises: In response to a current operation behavior of a user account in a business system, target object correlation information associated with the current operation behavior is obtained; the target object correlation information is used to record, under a target dimension, the correlation strength between a current business object associated with the current operation behavior in the business system and each candidate business object in the business system; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior; According to the target object relevance information, a target business object is screened out from each of the candidate business objects; under the target dimension, the strength of association between the target business object and the current business object meets a preset condition; The target business object is pushed to the user account.

2. The method according to claim 1, characterized in that The acquiring of target object relevance information associated with the current operation behavior includes: In a pre-built relational database, query the object correlation information corresponding to the target dimension; the object correlation information is used to record the correlation strength between each business object in the business system under the target dimension; each business object includes the current business object and each candidate business object; In the object correlation information, information recording the association strength between the current business object and each of the candidate business objects is extracted as the target object correlation information.

3. The method according to claim 2, characterized in that The querying of the object correlation information corresponding to the target dimension in the pre-built relational database includes: In the relational database, querying an object correlation matrix corresponding to the target dimension; the object correlation matrix is ​​used to record correlation values ​​between two business objects in each business object under the target dimension; the correlation value is used to characterize the association strength; Obtaining the object correlation information according to the object correlation matrix; The extracting, from the object correlation information, information recording the correlation strength between the current business object and each of the candidate business objects as the target object correlation information includes: In the object correlation matrix, matrix data matching the current business object is extracted; the matrix data is used to record the correlation value between the current business object and each of the candidate business objects under the target dimension; The target object correlation information is obtained according to the matrix data.

4. The method according to claim 2, characterized in that: The relational database includes an account relational database. When the user account is a historical user account, querying the object correlation information corresponding to the target dimension in the pre-built relational database includes: In the account relationship database, query the account correlation information associated with the historical user account; the account correlation information is determined based on the historical operation behavior of the historical user account in the business system; the account correlation information includes object correlation information corresponding to the feature dimensions assigned to different historical operation behaviors of the historical user account; From the account correlation information, the object correlation information corresponding to the target dimension is extracted.

5. The method according to claim 2, characterized in that: The relational database includes a general relational database, and the general relational database includes general object relevance information corresponding to each characteristic dimension; the general object relevance information is object relevance information determined based on historical operation behaviors of multiple historical user accounts in the business system; In the case where the user account is a new user account, querying the object correlation information corresponding to the target dimension in the pre-built relational database includes: In the general relational database, querying general object relevance information corresponding to the target dimension; The general object correlation information corresponding to the target dimension is used as the object correlation information corresponding to the target dimension.

6. The method according to claim 2, characterized in that: Before the step of querying the object correlation information corresponding to the target dimension in the pre-built relational database, the method further includes: Acquire historical operation behavior data of a historical user account in the business system; the historical operation behavior data is data used to record the historical operation behavior of the historical user account in the business system; According to the data operation rules corresponding to the correlation indicators matched by each feature dimension, the historical operation behavior data is operated and processed to obtain the correlation strength between each of the business objects under each feature dimension; According to the association strength between each of the business objects in each of the business objects under each of the feature dimensions, the object correlation information corresponding to each of the feature dimensions is obtained and stored in the relational database.

7. The method according to claim 6, characterized in that In the case where the target dimension includes at least two of the feature dimensions, the method further includes: Obtaining weight information corresponding to each of the characteristic dimensions of the target dimension, and the correlation strength between two of the business objects under the correlation index corresponding to each of the characteristic dimensions of the target dimension; Obtaining object correlation information corresponding to the target dimension according to weight information corresponding to each of the feature dimensions in the target dimension and weighted information between corresponding association strengths; The object correlation information corresponding to the target dimension is stored in the relational database.

8. A device for pushing a business object, characterized in that: The device comprises: an acquisition module, configured to acquire target object relevance information associated with the current operation behavior in the business system in response to the current operation behavior of the user account; the target object relevance information is used to record, under a target dimension, the strength of association between the current business object associated with the current operation behavior in the business system and each candidate business object in the business system; the target dimension is a feature dimension used to perform feature analysis on the current operation behavior; A screening module, configured to screen out a target business object from each of the candidate business objects according to the target object relevance information; under the target dimension, the strength of association between the target business object and the current business object meets a preset condition; A push module is used to push the target business object to the user account.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images