Business processing method and apparatus, computer device, and storage medium

Abstract

The application relates to a business processing method and device, computer equipment, a storage medium and a computer program product, and relates to the technical field of cloud computing. The method comprises the following steps: determining a target group according to attribute data of a target object; obtaining group correlation degrees of each control group and the target group from a group correlation graph; determining the correlation degrees of each second historical business and the target object according to the group correlation degrees of the target group and the control group and the business correlation degrees of each second historical business and each first historical business; and determining a target business according to the correlation degrees of each second historical business and the target object in each control group. By using the method, the control groups having the correlation with the target object and the historical business data of the control groups having the correlation with the historical business data of the target object are fully referenced, so that the target object can be recommended with the business having a stronger correlation with the historical business, and the accuracy and reliability of business recommendation are improved.

Description

Technical Field

[0001] This application relates to the field of cloud computing technology, and in particular to a business processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] As the types of services continue to increase, in order to improve the service experience for users, it is necessary to recommend new services that are compatible with the users.

[0003] In related technologies, the cloud platform often obtains the historical business data of the target object, performs data analysis on the historical business information of the target object, and identifies new businesses related to the historical business of the target object.

[0004] However, current methods of recommending new services to target audiences rely on data analysis of the target audience's historical business information through cloud platforms. This analysis is based on the target audience's historical business data to identify new products that interest them. Because the factors analyzed are relatively limited, the accuracy and reliability of these service recommendations are low. Summary of the Invention

[0005] Therefore, it is necessary to provide a business processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy and reliability of business recommendations, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a business processing method. The method includes:

[0007] Obtain the attribute data and first historical business data of the target object, wherein the first historical business data includes at least one first historical business that has interacted with the target object;

[0008] Based on the attribute data of the target object, determine the target group corresponding to the target object;

[0009] The group association degree between each control group and the target group is obtained from the group association graph, which is used to record the group association degree between each pair of groups;

[0010] For any of the aforementioned control groups, the second historical business data of each control object in the control group is obtained, and the business correlation degree between any second historical business and any first historical business is obtained from the business correlation graph. The second historical business data includes at least one second historical business that has interacted with the control object. The business correlation graph is used to record the business correlation degree between each pair of businesses.

[0011] For any of the control groups, the correlation degree between each second historical service and the target object is determined based on the group correlation degree between the target group and the control group, and the service correlation degree between each second historical service and each first historical service.

[0012] Based on the correlation between each of the second historical services in each of the aforementioned comparison groups and the target object, the target service is determined, and the target object is pushed services based on the target service.

[0013] In one embodiment, the method further includes:

[0014] Obtain attribute data of multiple objects, perform cluster analysis on the attribute data of the multiple objects, and obtain multiple groups;

[0015] For the first group and the second group, the group correlation degree between the first group and the second group is determined based on the historical business data of the first group and the historical business data of the second group. The first group and the second group are any two groups among the multiple groups.

[0016] A group association graph is constructed based on the group association degree between every two groups in the multiple groups.

[0017] In one embodiment, determining the group correlation degree between the first group and the second group based on the historical business data of the first group and the historical business data of the second group includes:

[0018] Based on the historical business data in the first group and the historical business data in the second group, the number of first objects in the first object group and the number of second objects in the second object group are determined. The first object group includes a first object and a second object. The first object and the second object have interacted with the same first target business. The first target business is any of the businesses in the business association diagram. The second object group includes a third object and a fourth object. Neither the third object nor the fourth object has interacted with the second target business. The second target business is any of the businesses in the business association diagram. The first object and the third object belong to the first group, and the second object and the fourth object belong to the second group.

[0019] Based on the historical business data in the first group and the historical business data in the second group, the number of third objects in the third object group and the number of fourth objects in the fourth object group are determined. The third object group includes a fifth object belonging to the first group and a sixth object belonging to the second group. The sixth object has not interacted with the third target business that the fifth object has interacted with. The fourth object group includes a seventh object belonging to the first group and an eighth object belonging to the second group. The seventh object has not interacted with the fourth target business that the eighth object has interacted with.

[0020] The group correlation degree of the first group and the second group is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object. The group correlation degree is positively correlated with the number of the first object and the number of the second object, and negatively correlated with the number of the third object and the number of the fourth object.

[0021] In one embodiment, determining the group association degree between the first group and the second group based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object includes:

[0022] The first group parameter is determined based on the number of the first object and the number of the second object;

[0023] The second group parameter is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object;

[0024] Based on the first group parameter and the second group parameter, the group correlation degree of the first group and the second group is determined. The group correlation degree is positively correlated with the first group parameter and negatively correlated with the second group parameter.

[0025] In one embodiment, the method further includes:

[0026] Based on all historical business data corresponding to each object, determine the total number of interactions for each business.

[0027] For the first service and the second service, the degree of business correlation between the first service and the second service is determined based on the total number of interactions of the first service and the total number of interactions of the second service, wherein the first service and the second service are any two services among the services.

[0028] A business association graph is constructed based on the degree of business association between every two of the aforementioned businesses.

[0029] In one embodiment, determining the business correlation between the first service and the second service based on the total number of interactions of the first service and the total number of interactions of the second service includes:

[0030] Based on the total number of interactions of the first service and the total number of interactions of the second service, a target number of interactions is calculated, which is the number of times the first service and the second service have interacted with the same object.

[0031] Based on the total number of interactions of the first service, the total number of interactions of the second service, and the target number of interactions, a target service parameter is determined. The target service parameter is positively correlated with the total number of interactions of the first service and the total number of interactions of the second service, and negatively correlated with the target number of interactions.

[0032] Based on the target business parameters and the target number of interactions, the business correlation degree between the first business and the second business is determined. The business correlation degree is positively correlated with the target number of interactions and negatively correlated with the target business parameters.

[0033] In one embodiment, determining the target service based on the correlation between each of the second historical services in each of the comparison groups and the target object includes:

[0034] The second historical services in each of the aforementioned control groups are filtered according to a preset filtering strategy to obtain the target second historical services;

[0035] According to the order of relevance from high to low, the target second historical services are sorted to obtain a service sequence;

[0036] The target service is determined from the service sequence based on the service sequence and the service selection rules.

[0037] Secondly, this application also provides a business processing apparatus. The apparatus includes:

[0038] The first acquisition module is used to acquire attribute data and first historical business data of the target object, wherein the first historical business data includes at least one first historical business that has interacted with the target object.

[0039] The first determining module is used to determine the target group corresponding to the target object based on the attribute data of the target object;

[0040] The second acquisition module is used to acquire the group association degree between each reference group and the target group from the group association graph, wherein the group association graph is used to record the group association degree between each pair of groups;

[0041] The third acquisition module is used to acquire the second historical business data of each reference object in any of the reference groups, and to acquire the business correlation degree between any second historical business and any first historical business from the business correlation graph. The second historical business data includes at least one second historical business that has interacted with the reference object. The business correlation graph is used to record the business correlation degree between each pair of businesses.

[0042] The second determining module is used to determine the correlation degree between each of the second historical services and the target object for any of the control groups, based on the group correlation degree between the target group and the control group, and the service correlation degree between each of the second historical services and each of the first historical services;

[0043] The third determining module is used to determine the target service based on the correlation between each of the second historical services in each of the comparison groups and the target object, and to push services to the target object based on the target service.

[0044] In one embodiment, the device further includes:

[0045] The fourth acquisition module is used to acquire attribute data of multiple objects, perform cluster analysis on the attribute data of the multiple objects, and obtain multiple groups;

[0046] The fourth determining module is used to determine the group correlation degree between the first group and the second group based on the historical business data of the first group and the historical business data of the second group, wherein the first group and the second group are any two groups among the plurality of groups;

[0047] The first construction module is used to construct a group association graph based on the group association degree between every two groups in multiple groups.

[0048] In one embodiment, the fourth determining module is specifically used for:

[0049] Based on the historical business data in the first group and the historical business data in the second group, the number of first objects in the first object group and the number of second objects in the second object group are determined. The first object group includes a first object and a second object. The first object and the second object have interacted with the same first target business. The first target business is any of the businesses in the business association diagram. The second object group includes a third object and a fourth object. Neither the third object nor the fourth object has interacted with the second target business. The second target business is any of the businesses in the business association diagram. The first object and the third object belong to the first group, and the second object and the fourth object belong to the second group.

[0050] Based on the historical business data in the first group and the historical business data in the second group, the number of third objects in the third object group and the number of fourth objects in the fourth object group are determined. The third object group includes a fifth object belonging to the first group and a sixth object belonging to the second group. The sixth object has not interacted with the third target business that the fifth object has interacted with. The fourth object group includes a seventh object belonging to the first group and an eighth object belonging to the second group. The seventh object has not interacted with the fourth target business that the eighth object has interacted with.

[0051] The group correlation degree of the first group and the second group is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object. The group correlation degree is positively correlated with the number of the first object and the number of the second object, and negatively correlated with the number of the third object and the number of the fourth object.

[0052] In one embodiment, the fourth determining module is specifically used for:

[0053] The first group parameter is determined based on the number of the first object and the number of the second object;

[0054] The second group parameter is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object;

[0055] Based on the first group parameter and the second group parameter, the group correlation degree of the first group and the second group is determined. The group correlation degree is positively correlated with the first group parameter and negatively correlated with the second group parameter.

[0056] In one embodiment, the device further includes:

[0057] The fifth determination module is used to determine the total number of interactions for each business based on all historical business data corresponding to each object.

[0058] The sixth determining module is used to determine the business correlation degree between the first business and the second business based on the total number of interactions of the first business and the total number of interactions of the second business, wherein the first business and the second business are any two businesses among the aforementioned businesses;

[0059] The second construction module is used to construct a business association graph based on the business association degree between every two businesses in the multiple businesses.

[0060] In one embodiment, the sixth determining module is specifically used for:

[0061] Based on the total number of interactions of the first service and the total number of interactions of the second service, a target number of interactions is calculated, which is the number of times the first service and the second service have interacted with the same object.

[0062] Based on the total number of interactions of the first service, the total number of interactions of the second service, and the target number of interactions, a target service parameter is determined. The target service parameter is positively correlated with the total number of interactions of the first service and the total number of interactions of the second service, and negatively correlated with the target number of interactions.

[0063] Based on the target business parameters and the target number of interactions, the business correlation degree between the first business and the second business is determined. The business correlation degree is positively correlated with the target number of interactions and negatively correlated with the target business parameters.

[0064] In one embodiment, the third determining module is specifically used for:

[0065] The second historical services in each of the aforementioned control groups are filtered according to a preset filtering strategy to obtain the target second historical services;

[0066] According to the order of relevance from high to low, the target second historical services are sorted to obtain a service sequence;

[0067] The target service is determined from the service sequence based on the service sequence and the service selection rules.

[0068] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the various business processing methods described in the first aspect above.

[0069] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the business processing methods described in the first aspect above.

[0070] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the business processing methods described in the first aspect above.

[0071] The aforementioned business processing method, apparatus, computer equipment, storage medium, and computer program product acquire attribute data and first historical business data of a target object, wherein the first historical business data includes at least one first historical business that has interacted with the target object; determine a target group corresponding to the target object based on the attribute data of the target object; obtain the group association degree between each reference group and the target group from a group association graph, wherein the group association graph is used to record the group association degree between each pair of object groups; for any reference group, acquire second historical business data of each reference object in the reference group, and obtain the business association degree between any second historical business and any first historical business from a business association graph, wherein the second historical business data includes at least one second historical business that has interacted with the reference object, wherein the business association graph is used to record the business association degree between each pair of businesses; for any reference group, determine the association degree between each second historical business and the target object based on the group association degree between the target group and the reference group, and the business association degree between each second historical business and each first historical business; determine a target business based on the association degree between each second historical business in each reference group and the target object, and push the business to the target object based on the target business. This case makes business recommendations based on the group correlation between groups and the business correlation between businesses, that is, it makes business recommendations from two dimensions. Because it fully considers the reference groups that are related to the target object and the historical business data of the reference groups that are related to the historical business data of the target object, it can recommend businesses that are more related to the historical business to the target object, thus improving the accuracy and reliability of business recommendations. Attached Figure Description

[0072] Figure 1 This is a flowchart illustrating a business processing method in one embodiment;

[0073] Figure 2 This is a flowchart illustrating the process of constructing a group association graph in one embodiment;

[0074] Figure 3This is a flowchart illustrating the process of determining the group association degree of the first group and the second group in one embodiment;

[0075] Figure 4 This is a flowchart illustrating the process of determining the group association degree of the first group and the second group in another embodiment;

[0076] Figure 5 This is a flowchart illustrating the process of determining the business correlation between a first service and a second service in one embodiment.

[0077] Figure 6 This is a flowchart illustrating the process of determining the business correlation between a first service and a second service in one embodiment.

[0078] Figure 7 This is a flowchart illustrating the process of determining target business data in one embodiment;

[0079] Figure 8 This is a flowchart illustrating a processing example of a business processing method in one embodiment;

[0080] Figure 9 This is a structural block diagram of a service processing device in one embodiment;

[0081] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0082] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0083] In one embodiment, such as Figure 1 As shown, a business processing method is provided. This embodiment illustrates the method applied to a server. It is understood that this method can also be applied to a terminal, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0084] Step 102: Obtain the attribute data and first historical business data of the target object.

[0085] The first historical business data includes at least one first historical business that has interacted with the target object.

[0086] In this embodiment, the server obtains attribute data of the target object and first historical business data of the target object. For example, the server obtains the attribute data of the target object and multiple first historical business transactions that have been interacted with the target object, based on a data table pre-stored in a database.

[0087] The target object is the entity to be recommended services, such as a user, location, or enterprise. Attribute data can include information inherent to the target object itself. For example, if the target object is a user, the attribute data could be basic information such as age, gender, and occupation. This application does not specifically limit the attribute data of the target object. The first historical business data is data generated and recorded when the target object interacted with services in the past; that is, it can include at least one first historical business transaction that has interacted with the target object. Interactions can include actions such as processing or consultation.

[0088] Step 104: Determine the target group corresponding to the target object based on the attribute data of the target object.

[0089] In this embodiment of the application, the server calls a clustering analysis algorithm to perform clustering analysis on the attribute data of the target object and the attribute data of each object, so as to obtain the target group corresponding to the target object.

[0090] Optionally, the server can perform clustering analysis based on the attribute data of each object to obtain multiple groups. Then, the server determines the group to which the target object belongs based on the attribute data of the target object, and uses the group to which the target object belongs as the target group. For the clustering analysis algorithm, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm can be adopted. The advantage of the DBSCAN algorithm is that it does not require specifying the number of clusters and can cluster dense datasets with specific task shapes. Any algorithm capable of performing clustering analysis can be applied in this application, and the embodiments of this application do not limit this application.

[0091] Step 106: Obtain the group association degree between each control group and the target group from the group association diagram.

[0092] Among them, the group association graph is used to record the group association degree between each pair of groups.

[0093] In this embodiment, the server can pre-divide the groups and pre-calculate the group association degree corresponding to each group, and record the group association degree between each pair of groups through a group association graph. The server takes the group to which the target object belongs as the target group and other groups in the group association graph as reference groups. Then, the server obtains the group association degree between each reference group and the target group in the group association graph.

[0094] Step 108: For any control group, obtain the second historical business data of each control object in the control group, and obtain the business correlation degree between any second historical business and any first historical business from the business correlation diagram.

[0095] The second historical business data includes at least one second historical business that has interacted with the comparison object, and the business relationship diagram is used to record the business relationship between each pair of businesses.

[0096] In this embodiment, for any control group, the server obtains the second historical service data of each control object in the control group. The server obtains a service association graph and retrieves the service association degree between any second historical service and any first historical service from the service association graph. For example, for any control group, the server retrieves each second historical service corresponding to each control object in the control group through a data table pre-stored in a database. Then, the server retrieves the service association degree between any second historical service and any first historical service from the pre-calculated service association graph.

[0097] Step 110: For any control group, determine the correlation between each second historical service and the target object based on the group correlation between the target group and the control group, and the business correlation between each second historical service and each first historical service.

[0098] In this embodiment of the application, for any control group, the server calculates the geometric mean of the group association degree between the target group and the control group, and the service association degree between each second historical service and each first historical service, to determine the association degree between each second historical service and the target object. The calculation process of the association degree between each second historical service and the target object can refer to formula (1), and the specific calculation process is as follows:

[0099]

[0100] Where R represents the correlation between any second historical service in the control group and the target object, v1 represents the group correlation between the target group and the control group, and v2 represents the business correlation between any second historical service and any first historical service.

[0101] For example, the reference groups include reference group A and reference group B. The server obtains the group association degree between the target group and reference group A for reference group A. The server obtains each second historical service corresponding to each reference object in reference group A. For each second historical service, the server obtains the service association degree between that second historical service and each first historical service in the target group. Then, based on the group association degree between the target group and reference group A, and the service association degree between each second historical service and each first historical service in the target group, the server determines the association degree between each second historical service in reference group A and the target object.

[0102] Step 112: Determine the target business based on the correlation between each second historical business in each comparison group and the target object, and push the business to the target object based on the target business.

[0103] In this embodiment of the application, the server determines the target service in each second historical service based on the correlation between each second historical service and the target object in each comparison group, and pushes the service to the target object based on the target service.

[0104] For example, the server can send business information containing the target service to the terminal of the recommender, who can then explain and recommend the target service to the target user; the server can also send business information containing the target service to the user's terminal, where the target service is displayed on an application pre-installed on the user's terminal.

[0105] In the above business processing method, the following steps are taken: First, the target object's attribute data and first historical business data are obtained. The first historical business data includes at least one first historical business that has interacted with the target object. Based on the target object's attribute data, the target group corresponding to the target object is determined. The group association degree between each reference group and the target group is obtained from a group association graph, which records the group association degree between each pair of object groups. For any reference group, the second historical business data of each reference object in the reference group is obtained, and the business association degree between any second historical business and any first historical business is obtained from a business association graph. The second historical business data includes at least one second historical business that has interacted with the reference object, and the business association graph records the business association degree between each pair of businesses. For any reference group, based on the group association degree between the target group and the reference group, and the business association degree between each second historical business and each first historical business, the association degree between each second historical business and the target object is determined. Based on the association degree between each second historical business and the target object in each reference group, the target business is determined, and business is pushed to the target object based on the target business. This case recommends services based on the correlation between groups and the correlation between services, that is, it recommends services from two dimensions. Because it fully considers the historical business data of the comparison groups that are related to the target object and the historical business data of the comparison groups that are related to the target object, it can recommend services with stronger historical business correlation to the target object, thus improving the accuracy and reliability of service recommendations.

[0106] In one embodiment, such as Figure 2 As shown, the above method also includes:

[0107] Step 202: Obtain attribute data of multiple objects, perform cluster analysis on the attribute data of multiple objects, and obtain multiple groups.

[0108] The attribute data can be basic information about the object, such as its age, gender, occupation, etc. This application does not specifically limit the attribute data of the object.

[0109] In this embodiment, the server retrieves attribute data of multiple objects based on a data table pre-stored in a database. Then, the server invokes a clustering analysis algorithm to perform clustering analysis on the attribute data of the multiple objects, resulting in multiple groups.

[0110] For example, the server invokes the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to perform clustering analysis on the attribute data of the target object and the attribute data of each object, resulting in multiple groups, such as group A, group B, group C, etc. The server can then assign group identifiers to each group; for example, assigning a first group identifier, a second group identifier, and a third group identifier to groups A, B, and C, respectively.

[0111] The clustering analysis algorithm and group identifier can be set by technicians in actual applications, and this application does not impose specific limitations on them.

[0112] Step 204: For the first group and the second group, determine the group correlation degree between the first group and the second group based on the historical business data of the first group and the historical business data of the second group.

[0113] Among them, the first group and the second group are any two groups from multiple groups.

[0114] In this embodiment of the application, for the first group and the second group, the server calculates the group correlation degree between the first group and the second group based on the historical business data corresponding to each object in the first group and the historical business data corresponding to each object in the second group, using a clustering evaluation index calculation method.

[0115] Step 206: Construct a group association graph based on the group association degree between every two groups in the multiple groups.

[0116] In this embodiment of the application, the server constructs a group association graph by calculating the group association degree between every two groups in multiple groups.

[0117] Specifically, the server can summarize the group association degree between each pair of groups in multiple groups into a group association degree data table, and use this data table as a group association graph; the server can also generate a tree structure graph based on the group association degree between each pair of groups in multiple groups.

[0118] Optionally, the server can provide the target object with a data table or tree structure diagram corresponding to the group association graph, so that the target object can know the association relationship between any two groups.

[0119] In this embodiment, the server can obtain multiple groups related to the object attributes based on the attribute data of multiple objects. Based on the historical business data of each object within each pair of groups, the group association degree between the two groups is obtained, thus generating a group association graph. The server can also provide the target object with the data table or tree structure diagram corresponding to the group association graph, enabling the target object to understand the association relationship between any two groups. Because the calculation of the group association graph fully considers the attribute data and historical business data of each object, and adopts multiple calculation factors, the accuracy and reliability of calculating the group association degree between two groups are improved.

[0120] In one embodiment, such as Figure 3 As shown, step 204 includes:

[0121] Step 302: Determine the number of first objects in the first object group and the number of second objects in the second object group based on the historical business data in the first group and the historical business data in the second group.

[0122] The first object group includes a first object and a second object. The first object and the second object have interacted with the same first target business. The first target business is any business in the business association diagram. The second object group includes a third object and a fourth object. Neither the third object nor the fourth object has interacted with the second target business. The second target business is any business in the business association diagram. The first object and the third object belong to the first group, and the second object and the fourth object belong to the second group.

[0123] In this embodiment of the application, for the first group and the second group, the server obtains multiple objects in the first group and their corresponding historical services, and multiple objects in the second group and their corresponding historical services.

[0124] For each object in the first group, the server checks if there are any identical historical transactions in the historical transactions corresponding to each object in the second group. If any historical transaction corresponding to any object in the second group is the same as any historical transaction corresponding to any object in the first group, the server takes that historical transaction as the first target transaction, and takes the corresponding objects in the first group and the corresponding objects in the second group as the first object and the second object, respectively, to form a first object group.

[0125] Similarly, the server obtains multiple first object groups from the first group and the second group, and then determines the number of first objects in the first object group based on the number of first object groups.

[0126] The server can retrieve all business data from a pre-stored data table. For any object in the first group, the server compares the historical business corresponding to that object with all business data to obtain a second target business that the object has not interacted with. The server then uses that object as the third object.

[0127] For each third object and the second target service corresponding to that third object, the server determines whether the second target service is not included in the historical services corresponding to each object in the second group. If the second target service is not included in the historical services corresponding to any object in the second group, the object in the second group is regarded as the fourth object, and a second object group is formed based on each third object and the corresponding fourth object.

[0128] Similarly, the server retrieves multiple second object groups from the first group and the second group, and then determines the number of second objects in each second object group based on the number of second object groups.

[0129] Each first object group includes a first object and a second object, and each second object group includes a third object and a fourth object.

[0130] Step 304: Based on the historical business data in the first group and the historical business data in the second group, determine the number of third objects in the third object group and the number of fourth objects in the fourth object group.

[0131] The third object group includes the fifth object belonging to the first group and the sixth object belonging to the second group. The sixth object has not interacted with the third target business that the fifth object has interacted with. The fourth object group includes the seventh object belonging to the first group and the eighth object belonging to the second group. The seventh object has not interacted with the fourth target business that the eighth object has interacted with.

[0132] In this embodiment of the application, for the first group and the second group, the server obtains multiple objects in the first group and their corresponding historical services, and multiple objects in the second group and their corresponding historical services.

[0133] The server designates each object in the first group as the fifth object. For any historical service that each fifth object has interacted with, the server determines in the second group whether there is an object that has not interacted with that historical service, and designates that historical service as the third target service. The server designates the objects in the second group that have not interacted with the third target service as the sixth object, forming a third object group based on each fifth object and its corresponding sixth object.

[0134] Similarly, the server retrieves multiple third object groups from the first and second groups. Then, the server determines the number of third objects in each third object group based on the number of third object groups.

[0135] Then, the server designates each object in the second group as the eighth object. For any historical service that each eighth object has interacted with, the server determines in the first group whether there is an object that has not interacted with that historical service. The server designates that historical service as the fourth target service, and the objects in the first group that have not interacted with the fourth target service as the seventh objects, forming a fourth object group based on each eighth object and its corresponding seventh object.

[0136] Similarly, the server retrieves multiple fourth object groups from the first and second groups. Then, the server determines the number of fourth objects in each fourth object group based on the total number of fourth object groups.

[0137] Step 306: Determine the group association degree of the first group and the second group based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object.

[0138] Among them, the group correlation degree is positively correlated with the number of first objects and the number of second objects, and negatively correlated with the number of third objects and the number of fourth objects. The number of first objects is used to represent the number of objects in the first group and the second group that have interacted with the same business. The number of second objects is used to represent the number of objects in the first group and the second group that have not interacted with the same business. The number of third objects is used to represent the number of objects in the first group that have interacted with a certain business, while an object in the second group has not interacted with that business. The number of fourth objects is used to represent the number of objects in the second group that have interacted with a certain business, while an object in the first group has not interacted with that business.

[0139] In this embodiment, the server can accurately calculate the group association degree of each first group and second group by using the following methods: representing the number of objects in the first group and second group that have interacted with the same service; representing the number of objects in the first group and second group that have not interacted with the same service; representing the number of objects in the first group that have interacted with a certain service while an object in the second group has not interacted with that service; and representing the number of objects in the second group that have interacted with a certain service while an object in the first group has not interacted with that service.

[0140] In one embodiment, such as Figure 4 As shown, step 306 includes:

[0141] Step 402: Determine the first group parameter based on the number of the first object and the number of the second object.

[0142] In this embodiment of the application, the server sums the number of the first object and the number of the second object to obtain the first group parameter.

[0143] Step 404: Determine the second group parameter based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object.

[0144] In this embodiment of the application, the server sums the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object to obtain the second group parameter.

[0145] Step 406: Determine the group association degree of the first group and the second group based on the parameters of the first group and the second group.

[0146] Among them, the group correlation degree is positively correlated with the first group parameter and negatively correlated with the second group parameter.

[0147] In this embodiment, the server divides the first group parameter and the second group parameter to obtain the group association degree of the first group and the second group. Specifically, the calculation method for the group association degree of the first group and the second group can refer to the following formula, and the specific calculation process is as follows:

[0148]

[0149] Wherein, Rand Index represents the group association degree between the first group and the second group, TP represents the number of first objects, TN represents the number of second objects, TP+TN represents the parameters of the first group, FP represents the number of third objects, FN represents the number of fourth objects, and TP+FP+TN+FN represents the parameters of the second group.

[0150] For ease of understanding, for example, in order to obtain the group association degree between group A and group B, the server obtains all objects in group A, namely object A1 and object A2, and obtains all objects in group B, namely object B1, object B2 and object B3.

[0151] Then, the server retrieves the historical business data of each object in group A and group B. Specifically, the historical business data of object A1 in group A consists of business a and business b, the historical business data of object A2 in group A consists of business a, business b and business c, the historical business data of object B1 in group B consists of business a, business c and business d, the historical business data of object B2 in group B consists of business a, business d and business e, and the historical business data of object B3 in group B consists of business b, business c and business d.

[0152] Regarding the number of first objects (i.e., the number of objects in the first and second groups that have interacted with the same business), the server checks whether business a is included in the historical business records of objects B1, B2, and B3 for object A1. It can be concluded that business a is included in the historical business records of objects B1 and B2. Therefore, objects A1 and B1, and objects A1 and B2, are each a pair of first and second objects. Similarly, regarding business b of object A1, the server checks whether business b is included in the historical business records of objects B1, B2, and B3. It can be concluded that business b is included in the historical business records of object B3. Therefore, objects A1 and B3 are a pair of first and second objects, forming a first object group. Thus, with A1 as the first object, there are three second objects. In other words, for object A1 in group A, there are three pairs of first and second objects, forming three first object groups.

[0153] Similarly, for business a, business b, and business c of object A2, we calculate whether business a, business b, and business c are included in the historical business of objects B1, B2, and B3, respectively. We can conclude that when object A2 is the first object, there are a total of five second objects. That is, for object A2 in group A, there are a total of five pairs of first objects and second objects, that is, there are a total of five first object groups.

[0154] Then the number of the first object group in both group A and group B is eight, that is, the number of the first object is eight.

[0155] For the second number of objects (i.e., the number of objects in the first group and the second group that have not interacted with the same business), the server obtains all business names and obtains all businesses as business a, business b, business c, business d, business e and business f.

[0156] For object A1, the server compares the historical business of object A1 with all historical business to obtain the business that has not interacted with object A1, namely business c, business d, business e and business f.

[0157] Based on the services c, d, e, and f that have not interacted with object A1, the server determines from the historical services of object B1 that B1 has also not interacted with, namely services e and f. Since objects A1 and B1 have two services that they have not interacted with, objects A1 and B1 are considered two pairs of third and fourth objects, i.e., two second object groups. Similarly, from the historical services of object B2, the server determines that B2 has also not interacted with, namely services c and f. Since objects A1 and B2 also have two services that they have not interacted with, objects A1 and B2 are also considered two pairs of third and fourth objects, i.e., two second object groups. Furthermore, from the historical services of object B3, the server determines that B3 has also not interacted with, namely services e and f. Since objects A1 and B3 also have two services that they have not interacted with, objects A1 and B3 are also considered two pairs of third and fourth objects, i.e., two second object groups.

[0158] That is, for object A1 in group A, there are six second object groups.

[0159] Similarly, for object A2 in group A, identify the services that object A2 has not interacted with, namely services d, e, and f. For services d, e, and f, identify the services that the corresponding objects in group B1, B2, and B3 have not processed in their historical transactions. This leads to the conclusion that, with object A2 as a third object, there are five fourth objects; that is, for object A2 in group A, there are five pairs of third and fourth objects, or five groups of second objects.

[0160] The number of the second object group in both group A and group B is eleven, meaning the number of the second object is eleven.

[0161] Regarding the number of third objects (i.e., the number of objects in the first group that have interacted with a certain business, while an object in the second group has not interacted with that business), for business a of object A1, we check whether business a is not included in the historical business records of objects B1, B2, and B3. We can conclude that business a is not included in the historical business records of object B3. Therefore, objects A1 and B3 are a pair of fifth and sixth objects, i.e., a third object group. For business b of object A1, we check whether business b is not included in the historical business records of objects B1, B2, and B3. We can conclude that business b is not included in the historical business records of objects B1 and B2. Therefore, objects A1 and B1, and objects A1 and B2 are two pairs of fifth and sixth objects, i.e., two third object groups.

[0162] That is, for object A1 in group A, there are three third object groups.

[0163] Similarly, for business a, business b, and business c of object A2, we can confirm whether business a, business b, and business c are not included in the historical business of objects B1, B2, and B3. We can conclude that when object A2 is the fifth object, there are four sixth objects. That is, for object A2 in group A, there are four pairs of fifth and sixth objects, which means there are four third object groups.

[0164] Therefore, the number of third objects in both group A and group B is seven, meaning the number of third objects is seven.

[0165] Regarding the number of fourth objects (i.e., the number of objects in the second group that have interacted with a certain business, while an object in the first group has not interacted with that business), for business a of object B1, by checking whether business a is not included in the historical business records of objects A1 and A2, it can be concluded that business a is included in all historical business records of object B3. Therefore, objects A1, A2, and B1 are not a pair of seventh and eighth objects, i.e., zero fourth object groups. For business c of object B1, by checking whether business c is not included in the historical business records of objects A1 and A2, it can be concluded that business c is not included in the historical business records of object A1. Therefore, objects A1 and B1 are a pair of seventh and eighth objects, i.e., one fourth object group. For business d of object B1, by checking whether business d is not included in the historical business records of objects A1 and A2, it can be concluded that business c is not included in the historical business records of objects A1 and A2. Therefore, objects A1 and B1, and objects A2 and B1 are two pairs of seventh and eighth objects, i.e., two fourth object groups.

[0166] That is, for object B1 in group B, there are three fourth object groups.

[0167] Similarly, for business a, business d, and business e of object B2, by checking whether business a, business d, and business e are not included in the historical business records of objects A1 and A2, it can be concluded that when object B2 is the eighth object, there are four pairs of seventh objects. That is, for object B2 in group B, there are four pairs of seventh and eighth objects, i.e., four groups of fourth objects. For business b, business c, and business d of object B3, by checking whether business b, business c, and business d are not included in the historical business records of objects A1 and A2, it can be concluded that when object B3 is the eighth object, there are three pairs of seventh objects, i.e., three groups of fourth objects.

[0168] Then the number of fourth objects in group A and group B is ten, that is, the number of fourth objects is ten.

[0169] In this embodiment, by combining the first clustering evaluation index with the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object, the interaction between each object in the first group and the historical business is fully taken into account, and the interaction between each object in the second group and the historical business is fully taken into account. This achieves the effect of accurately calculating the group association degree of the first group and the second group, thus improving the accuracy of calculating the group association degree.

[0170] In one embodiment, such as Figure 5 As shown, the above method also includes:

[0171] Step 502: Determine the total number of interactions for each business based on all historical business data corresponding to each object.

[0172] In this embodiment of the application, the server calculates the total number of interactions for each business based on all historical business data corresponding to each object.

[0173] Step 504: For the first business and the second business, determine the business correlation between the first business and the second business based on the total number of interactions in the first business and the total number of interactions in the second business.

[0174] Among them, the first business and the second business are any two businesses in each business.

[0175] In this embodiment, the server selects any two services from among the various services as the first service and the second service. For the first service and the second service, the server determines the service correlation degree between the first service and the second service based on the total number of interactions between the first service and the second service. This process is repeated until the service correlation degree between any two services is obtained.

[0176] Step 506: Construct a business relationship graph based on the business relationship between every two businesses in the multiple businesses.

[0177] In this embodiment, the server constructs a business relationship graph based on the business correlation between every two services among multiple services. The business relationship graph can be constructed using the business relationship matrix in formula (3), as follows:

[0178]

[0179] Among them, P XY P represents the probability of simultaneously interacting with both service X and service Y. Specifically, P 11 This represents the probability of simultaneously interacting with both Service 1 and Service 2, i.e., P. 11 P is 1. 1NP represents the probability of simultaneously interacting with both service number 1 and service number N. N1 P represents the probability of simultaneously interacting with both service N and service 1. NN The probability of simultaneously interacting with service number N, i.e., P NN The value is 1.

[0180] Specifically, the server can summarize the business relationship data between each pair of services in multiple services based on the business relationship between each pair of services, and use this data table as a business relationship graph; the server can also generate a tree structure graph based on the business relationship between each pair of services in multiple services.

[0181] Optionally, the server can provide the target object with the data table or tree structure diagram corresponding to the business relationship diagram, so that the target object can know the relationship between any two businesses.

[0182] In this embodiment, the server can determine the total number of interactions for each business based on all historical business data corresponding to each object. Based on the total number of interactions between the first and second businesses in any two businesses, the server can determine the business correlation degree between the first and second businesses, thereby obtaining a business correlation graph. The server can also provide the target object with the data table or tree structure diagram corresponding to the business correlation graph, enabling the target object to understand the correlation between any two businesses.

[0183] In one embodiment, such as Figure 6 As shown, step 504 includes:

[0184] Step 602: Calculate the target number of interactions based on the total number of interactions in the first business and the total number of interactions in the second business.

[0185] The target number of interactions refers to the number of times that the first and second business processes have interacted with the same object.

[0186] In this embodiment, the server obtains the total number of interactions between the first service and each object, and the total number of interactions between the second service and each object, based on data tables pre-stored in the database. Then, the server determines the number of objects with which the first and second services have interacted with the same object, based on the total number of interactions between the first and second services. The server uses this number as the target number of interactions.

[0187] Step 604: Determine the target business parameters based on the total number of interactions for the first business, the total number of interactions for the second business, and the target number of interactions.

[0188] Among them, the target business parameters are positively correlated with the total number of interactions of the first business and the total number of interactions of the second business, and negatively correlated with the target number of interactions.

[0189] In this embodiment, the server determines the target service parameters based on the total number of interactions for the first service, the total number of interactions for the second service, and the target number of interactions. The calculation method for the target service parameters can refer to formula (4), and the specific calculation process is as follows:

[0190] N2 = Nnm a +Num b -Num ab Formula (4)

[0191] Where N2 represents the target service parameter, Nnm ab Nnm represents the target number of interactions. a Num represents the total number of interactions for the first business a. b This represents the total number of interactions for the second business function b.

[0192] Step 606: Determine the business correlation between the first business and the second business based on the target business parameters and the target number of interactions.

[0193] Among them, the business relevance is positively correlated with the number of target interactions and negatively correlated with the target business parameters.

[0194] In this embodiment, the server determines the degree of business correlation between the first business and the second business based on the target business parameters and the target number of interactions.

[0195] The calculation method for the business correlation between the first business and the second business can refer to formula (5), and the specific calculation process is as follows:

[0196]

[0197] Among them, P ab and P ba Both represent the degree of business correlation between the first business a and the second business b, Nnm ab Indicates the target number of interactions.

[0198] In this embodiment, the target number of interactions is obtained by statistically analyzing the total number of interactions between the first and second services. The correlation between the two services is then obtained, along with the total number of interactions for each service and the number of objects that each service has interacted with. Multiple calculation factors are adopted to improve the accuracy and reliability of calculating the correlation between the two services.

[0199] In one embodiment, such as Figure 7 As shown, step 112 includes:

[0200] Step 702: Filter the second historical business in each control group according to the preset filtering strategy to obtain the target second historical business.

[0201] In this embodiment of the application, the server performs filtering processing on the second historical services in each comparison group according to a preset filtering strategy to obtain the target second historical service.

[0202] Specifically, the server can pre-store a preset filtering strategy. Based on the preset filtering strategy and the first historical services of the target object, the server can filter out services that are different from the first historical services in the second historical services of each comparison group and use them as the target second historical services.

[0203] The preset filtering strategy is used to select the desired target second historical business from each second historical business.

[0204] Step 704: Sort the second historical business of each target according to the order of relevance from high to low to obtain the business sequence.

[0205] In this embodiment of the application, the server sorts the target second historical services in each comparison group according to the order of their correlation with the target object from high to low, and obtains a service sequence with high to low correlation with the target object.

[0206] Step 706: Determine the target business from the business sequence based on the business sequence and business selection rules.

[0207] This application's embodiments enable in-depth mining of large amounts of repetitive historical business data and attribute data. Through a business processing method based on label correlation, the degree of association between various groups can be inferred, allowing for more diverse and suitable business recommendations to be made for each group. This effectively uncovers new targets for business, and the degree of association between different groups can be displayed on the application or recommended to target objects by business personnel, effectively enhancing the trust of target objects and thus improving the efficiency and number of business recommendations.

[0208] The business selection rule is used to select a preset number of businesses based on the business sequence.

[0209] In this embodiment of the application, the server determines a preset number of services as target services from the service sequence according to the service selection rules.

[0210] For example, the server may pre-store service selection rules, and select a preset number of services from the service sequence according to the service selection rules as the target services corresponding to the target object. Optionally, the server may also select all services as the target services corresponding to the target object.

[0211] The selection rules and preset number of services can be determined by technical personnel in actual application, and this application embodiment does not limit this.

[0212] In this embodiment, the server can, based on a preset filtering strategy, filter new services that differ from the first historical services from multiple second historical services, and then select a preset number of services from the new services as the target services corresponding to the target object. This achieves the effect of recommending a preset number of new services to the target object.

[0213] Furthermore, this embodiment enhances the interactive experience of the target audience in a more direct and diverse manner during the various business recommendation processes. Through this business processing method, it can increase the target audience's trust while providing them with more diverse services, ultimately completing the business recommendation process. This solution incorporates the currently emerging crowdsourced tag inference algorithm to present marketing product information to customers in a more trustworthy and diverse way, providing them with a superior interactive experience.

[0214] In one embodiment, such as Figure 8 As shown, a processing example of a business processing method is provided, including the following steps:

[0215] Step 801: Obtain the attribute data of the target object.

[0216] Step 802: Provide a clustering analysis algorithm to perform clustering analysis on the attribute data of the target object.

[0217] In this embodiment of the application, the server calls a clustering analysis algorithm to perform clustering analysis on the attribute data of the target object and the attribute data of each object, so as to obtain the target group corresponding to the target object and the control groups corresponding to other objects.

[0218] Step 803: Determine the group association degree between the target group and the control group.

[0219] In this embodiment of the application, the server obtains the group association degree between each reference group and the target group in the group association graph.

[0220] Step 804: Obtain the first historical business data of the target object.

[0221] Step 805: Obtain the second historical business data for each comparison group.

[0222] In this embodiment of the application, the server obtains the second historical business data of each control object in the control group based on the data table pre-stored in the database.

[0223] Step 806: Determine the business correlation between each first historical business and each second historical business.

[0224] In this embodiment of the application, the server obtains a business association graph and obtains the business association degree between any second historical business and any first historical business from the business association graph.

[0225] Step 807: Calculate the correlation between each second historical business and the target object.

[0226] In this embodiment of the application, the server determines the correlation between each second historical service and the target object based on the group correlation between the target group and the control group, and the service correlation between each second historical service and each first historical service.

[0227] Step 808: Filter the second historical business in each control group according to the preset filtering strategy to obtain the target second historical business.

[0228] In this embodiment of the application, the server, based on a preset filtering strategy and the first historical services of the target object, filters out services that are different from the first historical services in the second historical services of each comparison group, and uses them as the target second historical services.

[0229] Step 809: Sort the second historical business of each target according to the order of relevance from high to low to obtain the business sequence.

[0230] Step 810: Determine the target business data from the business sequence based on the business sequence and business selection rules.

[0231] In this embodiment of the application, the server determines a preset number of services as target services from the service sequence according to the service selection rules.

[0232] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0233] Based on the same inventive concept, this application also provides a business processing apparatus for implementing the business processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more business processing apparatus embodiments provided below can be found in the limitations of the business processing method described above, and will not be repeated here.

[0234] In one embodiment, such as Figure 9 As shown, a service processing device 900 is provided, including: a first acquisition module 902, a first determination module 904, a second acquisition module 906, a third acquisition module 908, a second determination module 910, and a third determination module 912, wherein:

[0235] The first acquisition module 902 is used to acquire attribute data of the target object and first historical business data, wherein the first historical business data includes at least one first historical business that has interacted with the target object.

[0236] The first determining module 904 is used to determine the target group corresponding to the target object based on the attribute data of the target object;

[0237] The second acquisition module 906 is used to acquire the group association degree between each reference group and the target group from the group association graph, wherein the group association graph is used to record the group association degree between each pair of groups;

[0238] The third acquisition module 908 is used to acquire the second historical business data of each reference object in any of the reference groups, and to acquire the business correlation degree between any second historical business and any first historical business from the business correlation diagram. The second historical business data includes at least one second historical business that has interacted with the reference object. The business correlation diagram is used to record the business correlation degree between each pair of businesses.

[0239] The second determining module 910 is used to determine the correlation degree between each second historical service and the target object for any of the control groups, based on the group correlation degree between the target group and the control group, and the service correlation degree between each second historical service and each first historical service.

[0240] The third determining module 912 is used to determine the target service based on the correlation between each of the second historical services in each of the comparison groups and the target object, and to push services to the target object based on the target service.

[0241] The business processing apparatus provided in this disclosure makes business recommendations based on the group correlation between groups and the business correlation between businesses, that is, it makes business recommendations from two dimensions. Since it fully considers the reference groups that are related to the target object and the historical business data that have been interacted with by the reference groups that are related to the historical business data of the target object, it can recommend businesses that are more related to historical businesses for the target object, thereby improving the accuracy and reliability of business recommendations.

[0242] In one embodiment, the apparatus further includes:

[0243] The fourth acquisition module is used to acquire attribute data of multiple objects, perform cluster analysis on the attribute data of the multiple objects, and obtain multiple groups;

[0244] The fourth determining module is used to determine the group correlation degree between the first group and the second group based on the historical business data of the first group and the historical business data of the second group, wherein the first group and the second group are any two groups among the plurality of groups;

[0245] The first construction module is used to construct a group association graph based on the group association degree between every two groups in multiple groups.

[0246] In one embodiment, the fourth determining module is specifically used for:

[0247] Based on the historical business data in the first group and the historical business data in the second group, the number of first objects in the first object group and the number of second objects in the second object group are determined. The first object group includes a first object and a second object. The first object and the second object have interacted with the same first target business. The first target business is any of the businesses in the business association diagram. The second object group includes a third object and a fourth object. Neither the third object nor the fourth object has interacted with the second target business. The second target business is any of the businesses in the business association diagram. The first object and the third object belong to the first group, and the second object and the fourth object belong to the second group.

[0248] Based on the historical business data in the first group and the historical business data in the second group, the number of third objects in the third object group and the number of fourth objects in the fourth object group are determined. The third object group includes a fifth object belonging to the first group and a sixth object belonging to the second group. The sixth object has not interacted with the third target business that the fifth object has interacted with. The fourth object group includes a seventh object belonging to the first group and an eighth object belonging to the second group. The seventh object has not interacted with the fourth target business that the eighth object has interacted with.

[0249] The group correlation degree of the first group and the second group is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object. The group correlation degree is positively correlated with the number of the first object and the number of the second object, and negatively correlated with the number of the third object and the number of the fourth object.

[0250] In one embodiment, the fourth determining module is specifically used for:

[0251] The first group parameter is determined based on the number of the first object and the number of the second object;

[0252] The second group parameter is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object;

[0253] Based on the first group parameter and the second group parameter, the group correlation degree of the first group and the second group is determined. The group correlation degree is positively correlated with the first group parameter and negatively correlated with the second group parameter.

[0254] In one embodiment, the device further includes:

[0255] The fifth determination module is used to determine the total number of interactions for each business based on all historical business data corresponding to each object.

[0256] The sixth determining module is used to determine the business correlation degree between the first business and the second business based on the total number of interactions of the first business and the total number of interactions of the second business, wherein the first business and the second business are any two businesses among the aforementioned businesses;

[0257] The second construction module is used to construct a business association graph based on the business association degree between every two businesses in the multiple businesses.

[0258] In one embodiment, the sixth determining module is specifically used for:

[0259] Based on the total number of interactions of the first service and the total number of interactions of the second service, a target number of interactions is calculated, which is the number of times the first service and the second service have interacted with the same object.

[0260] Based on the total number of interactions of the first service, the total number of interactions of the second service, and the target number of interactions, a target service parameter is determined. The target service parameter is positively correlated with the total number of interactions of the first service and the total number of interactions of the second service, and negatively correlated with the target number of interactions.

[0261] Based on the target business parameters and the target number of interactions, the business correlation degree between the first business and the second business is determined. The business correlation degree is positively correlated with the target number of interactions and negatively correlated with the target business parameters.

[0262] In one embodiment, the third determining module 912 is specifically used for:

[0263] The second historical services in each of the aforementioned control groups are filtered according to a preset filtering strategy to obtain the target second historical services;

[0264] According to the order of relevance from high to low, the target second historical services are sorted to obtain a service sequence;

[0265] The target service is determined from the service sequence based on the service sequence and the service selection rules.

[0266] Each module in the aforementioned business processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0267] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores historical business data and attribute data for various objects. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a business processing method.

[0268] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0269] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0270] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0271] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0272] 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, data stored, data displayed, 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 related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0273] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0274] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 specification.

[0275] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A business processing method, characterized in that, The method includes: Obtain the attribute data and first historical business data of the target object, wherein the first historical business data includes at least one first historical business that has interacted with the target object; Based on the attribute data of the target object, determine the target group corresponding to the target object; The group association degree between each control group and the target group is obtained from the group association graph, which is used to record the group association degree between each pair of groups; For any of the aforementioned control groups, the second historical business data of each control object in the control group is obtained, and the business correlation degree between any second historical business and any first historical business is obtained from the business correlation graph. The second historical business data includes at least one second historical business that has interacted with the control object. The business correlation graph is used to record the business correlation degree between each pair of businesses. For any of the control groups, the correlation degree between each second historical service and the target object is determined based on the group correlation degree between the target group and the control group, and the service correlation degree between each second historical service and each first historical service. Based on the correlation between each of the second historical services in each of the aforementioned comparison groups and the target object, the target service is determined, and the target object is pushed services based on the target service; The method further includes: Obtain attribute data of multiple objects, perform cluster analysis on the attribute data of the multiple objects, and obtain multiple groups; For the first group and the second group, the group correlation degree between the first group and the second group is determined based on the historical business data of the first group and the historical business data of the second group. The first group and the second group are any two groups among the multiple groups. Based on the group association degree between every two groups in the multiple groups, a group association graph is constructed; The method further includes: Based on all historical business data corresponding to each object, determine the total number of interactions for each business. For the first service and the second service, the degree of business correlation between the first service and the second service is determined based on the total number of interactions of the first service and the total number of interactions of the second service, wherein the first service and the second service are any two services among the services. A business association graph is constructed based on the degree of business association between every two of the aforementioned businesses.

2. The method according to claim 1, characterized in that, Determining the group correlation degree between the first group and the second group based on the historical business data of the first group and the historical business data of the second group includes: Based on the historical business data in the first group and the historical business data in the second group, the number of first objects in the first object group and the number of second objects in the second object group are determined. The first object group includes a first object and a second object. The first object and the second object have interacted with the same first target business. The first target business is any of the businesses in the business association diagram. The second object group includes a third object and a fourth object. Neither the third object nor the fourth object has interacted with the second target business. The second target business is any of the businesses in the business association diagram. The first object and the third object belong to the first group, and the second object and the fourth object belong to the second group. Based on the historical business data in the first group and the historical business data in the second group, the number of third objects in the third object group and the number of fourth objects in the fourth object group are determined. The third object group includes a fifth object belonging to the first group and a sixth object belonging to the second group. The sixth object has not interacted with the third target business that the fifth object has interacted with. The fourth object group includes a seventh object belonging to the first group and an eighth object belonging to the second group. The seventh object has not interacted with the fourth target business that the eighth object has interacted with. The group correlation degree of the first group and the second group is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object. The group correlation degree is positively correlated with the number of the first object and the number of the second object, and negatively correlated with the number of the third object and the number of the fourth object.

3. The method according to claim 2, characterized in that, Determining the group association degree between the first group and the second group based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object includes: The first group parameter is determined based on the number of the first object and the number of the second object; The second group parameter is determined based on the number of the first object, the number of the second object, the number of the third object, and the number of the fourth object; Based on the first group parameter and the second group parameter, the group correlation degree of the first group and the second group is determined. The group correlation degree is positively correlated with the first group parameter and negatively correlated with the second group parameter.

4. The method according to claim 1, characterized in that, Determining the business correlation between the first service and the second service based on the total number of interactions of the first service and the total number of interactions of the second service includes: Based on the total number of interactions of the first service and the total number of interactions of the second service, a target number of interactions is calculated, which is the number of times the first service and the second service have interacted with the same object. Based on the total number of interactions of the first service, the total number of interactions of the second service, and the target number of interactions, a target service parameter is determined. The target service parameter is positively correlated with the total number of interactions of the first service and the total number of interactions of the second service, and negatively correlated with the target number of interactions. Based on the target business parameters and the target number of interactions, the business correlation degree between the first business and the second business is determined. The business correlation degree is positively correlated with the target number of interactions and negatively correlated with the target business parameters.

5. The method according to claim 1, characterized in that, The step of determining the target service based on the correlation between each of the second historical services in each of the reference groups and the target object includes: The second historical services in each of the aforementioned control groups are filtered according to a preset filtering strategy to obtain the target second historical services; According to the order of relevance from high to low, the target second historical services are sorted to obtain a service sequence; The target service is determined from the service sequence based on the service sequence and the service selection rules.

6. A business processing apparatus, characterized in that, The device includes: The first acquisition module is used to acquire attribute data and first historical business data of the target object, wherein the first historical business data includes at least one first historical business that has interacted with the target object. The first determining module is used to determine the target group corresponding to the target object based on the attribute data of the target object; The second acquisition module is used to acquire the group association degree between each reference group and the target group from the group association graph, wherein the group association graph is used to record the group association degree between each pair of groups; The third acquisition module is used to acquire the second historical business data of each reference object in any of the reference groups, and to acquire the business correlation degree between any second historical business and any first historical business from the business correlation graph. The second historical business data includes at least one second historical business that has interacted with the reference object. The business correlation graph is used to record the business correlation degree between each pair of businesses. The second determining module is used to determine the correlation degree between each of the second historical services and the target object for any of the control groups, based on the group correlation degree between the target group and the control group, and the service correlation degree between each of the second historical services and each of the first historical services; The third determining module is used to determine the target service based on the correlation between each of the second historical services in each of the comparison groups and the target object, and to push services to the target object based on the target service; The fourth acquisition module is used to acquire attribute data of multiple objects, perform cluster analysis on the attribute data of the multiple objects, and obtain multiple groups; The fourth determining module is used to determine the group correlation degree between the first group and the second group based on the historical business data of the first group and the historical business data of the second group, wherein the first group and the second group are any two groups among the plurality of groups; The first construction module is used to construct a group association graph based on the group association degree between every two groups in the multiple groups; The fifth determination module is used to determine the total number of interactions for each business based on all historical business data corresponding to each object. The sixth determining module is used to determine the business correlation degree between the first business and the second business based on the total number of interactions of the first business and the total number of interactions of the second business, wherein the first business and the second business are any two businesses among the aforementioned businesses; The second construction module is used to construct a business association graph based on the business association degree between every two businesses in the multiple businesses.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images