CN110781380A

CN110781380A - Information pushing method and device, computer equipment and storage medium

Info

Publication number: CN110781380A
Application number: CN201910848272.XA
Authority: CN
Inventors: 张超亚; 蔡健
Original assignee: OneConnect Smart Technology Co Ltd
Current assignee: OneConnect Smart Technology Co Ltd
Priority date: 2019-09-09
Filing date: 2019-09-09
Publication date: 2020-02-11

Abstract

The application relates to an information pushing method, an information pushing device, computer equipment and a storage medium. The method relates to big data analysis technology, comprising the following steps: acquiring user identification information of a service user, and inquiring the service user information according to the user identification information; performing data missing detection on the service user information, and determining user missing information when the missing detection result is information missing; performing prediction information completion on the user missing information to obtain user completion information; according to the user completion information and the service user information, obtaining user complete information; and carrying out information matching on the user complete information and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to a service user. By adopting the method, the information pushing effect can be improved.

Description

Information pushing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information pushing method and apparatus, a computer device, and a storage medium.

Background

With the development of computer technology, more and more business systems are realized through the internet, and various business services such as network social contact, financial services and the like are provided on line, so that people can select the business services according to actual needs, and the life of people is facilitated. In addition, each business system also provides product recommendation based on the interest characteristics and purchasing behaviors of each user, and recommends information and commodities which are interested by the user to the user.

However, in the current business system, the business personnel actively contact the users to push the product information, and the business personnel blindly push the product information for each user, so that the pertinence of the type of the product information to be pushed is poor, and the information pushing effect is limited.

Disclosure of Invention

In view of the above, it is necessary to provide an information pushing method, an information pushing apparatus, a computer device, and a storage medium capable of improving an information pushing effect.

An information pushing method, the method comprising:

acquiring user identification information of a service user, and inquiring the service user information according to the user identification information;

performing data missing detection on the service user information, and determining user missing information when the missing detection result is information missing;

performing prediction information completion on the user missing information to obtain user completion information;

according to the user completion information and the service user information, obtaining user complete information;

and carrying out information matching on the user complete information and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to a service user.

In one embodiment, performing predicted information completion on the missing user information, and obtaining user completion information includes:

performing information type matching according to the missing information of the user, and determining the information type of the missing information of the user;

acquiring a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy;

processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information;

and completing the missing information of the user according to the information prediction result to obtain user completion information.

In one embodiment, the processing the statistical completion data by using a method corresponding to an information completion policy to obtain an information prediction result corresponding to the missing information of the user includes:

analyzing the user behavior data of each service user in the statistical completion data based on similarity analysis, and classifying each service user;

acquiring service user information of a user with complete information;

counting the service user information of various information complete users to obtain the service user information with the highest frequency in the service user information of each category dimension;

the service user information with the highest frequency in the service user information of each category dimension is used as the prediction information of each category dimension;

and determining an information prediction result corresponding to the user missing information according to the prediction information corresponding to the category of the service user.

In one embodiment, before information matching is performed on the user complete information and preset product information, the method further includes:

acquiring a demand analysis result of a service user;

and when the requirement analysis result is product information pushing, executing a step of performing information matching on the user complete information and preset product information.

In one embodiment, the information matching of the user complete information and the preset product information, the determination of the information to be pushed according to the matching result, and the pushing of the information to be pushed to the terminal corresponding to the service user includes:

acquiring a user wind control parameter corresponding to a service user;

when the user wind control parameters meet the risk control conditions, information matching is carried out on the user complete information and preset product information to obtain a matching result;

and determining the information to be pushed from the matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

An information push apparatus, the apparatus comprising:

the user information acquisition module is used for acquiring user identification information of the service user and inquiring the service user information according to the user identification information;

the missing information determining module is used for carrying out data missing detection on the service user information, and determining the user missing information when the missing detection result is information missing;

the completion information acquisition module is used for performing prediction information completion on the missing information of the user to obtain user completion information;

the complete information acquisition module is used for acquiring complete user information according to the user completion information and the service user information;

and the information pushing processing module is used for carrying out information matching on the complete information of the user and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

According to the information pushing method, the information pushing device, the computer equipment and the storage medium, when the fact that the business user information corresponding to the business user is lost is detected, user missing information is completed, user complete information is obtained according to the user completing information, information matching is carried out on the basis of the user complete information and preset product information, and the corresponding information to be pushed is determined to carry out information pushing. In the information pushing process, the missing service user information is supplemented, and information matching is performed based on the supplemented user complete information, so that the accuracy of product information matching is improved, and the information pushing effect is improved.

Drawings

Fig. 1 is a diagram illustrating an application scenario of an information push method according to an embodiment;

FIG. 2 is a flowchart illustrating an information pushing method according to an embodiment;

FIG. 3 is a flow diagram illustrating missing information completion processing in one embodiment;

FIG. 4 is a block diagram of an information pushing apparatus according to an embodiment;

FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The information pushing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal device 102 communicates with the server 104 via a network. The terminal device 102 sends service user information needing information pushing processing to the server 104, the server 104 performs data missing detection on the service user information, completes the user missing information when detecting that the service user information corresponding to the service user is missing, obtains user complete information according to the user complete information, performs information matching based on the user complete information and preset product information, and determines corresponding information to be pushed to perform information pushing. The terminal device 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, an information pushing method is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:

step S201: and acquiring user identification information of the service user, and inquiring the service user information according to the user identification information.

The user identification information is an identification used for distinguishing each service user in each service system, and may be identification data capable of uniquely identifying each service user, such as name, mobile phone number, identity card number, service number, and the like of the service user. After obtaining the user identification information of the service user, querying the service user information corresponding to the user identification information, where the service user information is various data of the service user corresponding to the user identification information in the service system, such as historical service data, and the like.

Step S203: and carrying out data missing detection on the service user information, and determining the user missing information when the missing detection result is information missing.

The data missing detection is to detect the integrity of the service user information so as to determine whether the service user information obtained from the service system is complete. For example, assume that the complete service user information includes: when the service user information of the user A only contains the vehicle information and the content of the work industry and the marriage and bearing information does not exist, the missing detection result is information missing, and the user information with the missing user A information can be further determined to be the marriage and bearing information.

Step S205: and performing prediction information completion on the missing user information to obtain user completion information.

After determining the missing user information, namely the missing part in the service user information stored in the service system, performing predictive information completion on the missing user information to obtain user completion information. In specific implementation, after the user missing information is obtained, the information type of the user missing information can be judged. For example, the information types may include vehicle information, marriage and education information, work industry, and the like, and are not limited to the listed information types, and all the information for embodying the user characteristics is the service user information of the service user, and there is a corresponding information type.

After the information type of the user missing information is determined, according to a preset information completion strategy corresponding to the information type of the user missing information and statistical completion data corresponding to the information completion strategy, information completion is predicted based on the information completion strategy and the statistical completion data, and user completion information is obtained. The information completion strategy refers to a method for processing and analyzing statistical completion data to obtain a presumed result of user missing information, similarity analysis can be adopted in the information completion strategy, the information completion strategy adopting the similarity analysis is suitable for all types of user missing information, and the required statistical completion data is user behavior data of each service user. Different information completion strategies can be set according to different information types, and the statistical completion data required by the different information completion strategies are different, so that the corresponding statistical completion data are obtained based on the information completion strategies. For example, if the information type of the user missing information is marriage/education information, a specific information completion policy is created for the characteristics of the marriage/education information, and statistical completion data (i.e., the city where the user is located, the sex, the academic calendar, the age, etc.) required for the information completion policy for the marriage/education information is used. For another example, when the information type of the missing information of the user is vehicle information, a determination information completion strategy is made according to the characteristics of the vehicle information, and statistical completion data (i.e., position information and the like) required by the information completion strategy of the vehicle information is used. For another example, when the information type of the missing information of the user is the work industry, a determined information completion strategy is made according to the characteristics of the work industry, and statistical completion data (i.e., position information and the like) required by the information completion strategy of the work industry is used.

Step S207: and obtaining the complete information of the user according to the completion information of the user and the service user information.

And after the user completion information corresponding to the user missing information is obtained, obtaining the user complete information according to the user completion information and the service user information. Specifically, the obtained user completion information can be directly supplemented into the service user information to obtain the user completion information supplemented with the missing part. For example, in the user completion information obtained by deleting the marriage and education information of user a in the service system, if the marriage and education information of user a is married and educated, the information input field of the marriage and education information of user a (or the position for writing the service user information) is written into the married and educated, and the marriage and education information of user a is completed, so that the user completion information is obtained.

Step S209: and carrying out information matching on the user complete information and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to a service user.

And after the user complete information is obtained, performing information matching based on the user complete information and preset product information, determining information to be pushed according to a matching result, and finally pushing the information to be pushed to a terminal corresponding to a service user. When the requirement analysis result of the service user is product information pushing, information matching can be carried out on the user complete information and the product information, wherein the requirement analysis result can determine the requirement analysis level of the service user according to the user complete information, the service requirement type of the service user is determined when the requirement analysis level of the service user meets a preset requirement analysis level condition, the service requirement type is obtained through calculation according to a preset service requirement index corresponding to the service requirement type and an index weight corresponding to the service requirement index, and finally the information to be pushed is determined according to the requirement analysis result and the preset product information and information pushing is carried out.

According to the information pushing method, when the fact that the business user information corresponding to the business user is lost is detected, user missing information is completed, user complete information is obtained according to the user completing information, information matching is conducted on the basis of the user complete information and preset product information, and the corresponding information to be pushed is determined to be pushed to carry out information pushing. In the information pushing process, the missing service user information is supplemented, and information matching is performed based on the supplemented user complete information, so that the accuracy of product information matching is improved, and the information pushing effect is improved.

In an embodiment, as shown in fig. 3, when missing information padding processing is performed, performing predictive information padding on the user missing information, and obtaining user padding information includes:

step S301: and performing information type matching according to the missing information of the user, and determining the information type of the missing information of the user.

In this embodiment, different information completion processing methods are preset correspondingly for the missing information of the user with different information types. Specifically, after the user missing information is determined, information type matching is performed according to the user missing information, and the information type of the user missing information is determined. Different user missing information belongs to different information types, such as vehicle information, marriage and education information, work industry and the like, and the specific information type division method is flexibly set according to the requirements of each business system. When the information types are matched according to the user missing information, the user missing information and each preset information type can be matched one by one, for example, keyword matching is performed on the user missing information and the description text corresponding to each information type, and the information type of the user missing information is determined according to the information type matching result.

Step S303: and acquiring a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy.

Different completion methods are preset correspondingly for the user missing information of different information types, namely, the user missing information of each information type is subjected to completion processing according to different completion processing. Specifically, after the information type of the user missing information is obtained, a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy are obtained. The information completion strategy refers to a method for processing and analyzing statistical completion data to obtain a presumed result of user missing information, the information completion strategy can adopt similarity analysis, the information completion strategy adopting the similarity analysis is suitable for service user information of all information types, and the statistical completion data corresponding to the information completion strategy can be a statistical analysis result obtained by performing statistical analysis according to user behavior data of each service user in the service system.

Step S305: and processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information.

And after an information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy are obtained, processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information. Specifically, the information completion policy may be a similarity analysis policy, and the method corresponding to the information completion policy is to classify the service users in the statistical completion data, analyze and process the service user information of each type of service user, and perform inference according to the similarity of the service user information of each type of service user to obtain an inference result of the user missing information, that is, an information prediction result.

For example, a determined information completion strategy is formulated according to the characteristics of marriage and childbirth information, such as: acquiring the marriage and education structure characteristics of the city according to the city in the statistical completion data, and conjecturing the marriage and education information of the user according to the gender, the academic calendar and the age of the user in the statistical completion data and the marriage and education structure characteristics of the city.

Step S307: and completing the missing information of the user according to the information prediction result to obtain user completion information.

And after an information prediction result corresponding to the user missing information is obtained, completing the user missing information according to the information prediction result to obtain user completion information. In specific implementation, the information prediction result can be directly used as user completion information, and keywords can be extracted from the information prediction result and combined to obtain the user completion information. For example, if the marriage and education information of user a is missing and the obtained information prediction result indicates that the marriage and education information of user a is married and educated, the information input field (or the position for writing the business user information) of the marriage and education information of user a is written into the married and educated, and the marriage and education information of user a is completed, so that the user completion information is obtained.

In one embodiment, the processing the statistical completion data by using a method corresponding to an information completion policy to obtain an information prediction result corresponding to the missing information of the user includes: analyzing the user behavior data of each service user in the statistical completion data based on similarity analysis, and classifying each service user; acquiring service user information of a user with complete information; counting the service user information of various information complete users to obtain the service user information with the highest frequency in the service user information of each category dimension; the service user information with the highest frequency in the service user information of each category dimension is used as the prediction information of each category dimension; and determining an information prediction result corresponding to the user missing information according to the prediction information corresponding to the category of the service user.

In this embodiment, the statistical completion data is processed based on the information completion strategy of the similarity analysis, so as to obtain an information prediction result corresponding to the missing information of the user. Specifically, the user behavior data of each service user in the statistical completion data is analyzed based on the similarity analysis, and each service user is classified. The user behavior data of the service user refers to data generated when the service user accesses the service system, for example, when the service system is accessed through a website or an APP (Application program) or other platform. And analyzing the user behavior data of each service user in the basic data based on the similarity analysis, and classifying each service user. For example, people of the same age and sex are classified into a group, women, a group aged at 30 years, and the like.

The method comprises the steps of obtaining service user information of an information-complete user, wherein the information-complete user means that all service user information of a service user has corresponding information content, namely the service user information has integrity requirements and the missing completion of the service user is not needed. For example, if the information types of the service user information owned by the service user include vehicle information, marriage and education information, and a work industry, the vehicle information of the user C is a vehicle, the marriage and education information is married and educated, the work industry is a medical worker, the vehicle information of the user D is a vehicle, the position corresponding to the marriage and education information has no data or data, and the work industry is an education industry, the user C is a user with complete information, and the user D is a user with missing information. Acquiring user information of a user with complete information, such as: take women, age 30 as an example: the user sex is female, the age is 30 years old, and the information is complete service user information of the user.

Further, the service user information of various information complete users is counted to obtain the service user information with the highest frequency in the service user information of each category dimension, such as: take women, age 30 as an example: the business user information of women and users aged 30 years is counted, and the highest frequency of vehicle information in the counting result is that vehicles exist, the highest frequency of marriage and childbearing information is that married and educated, the highest frequency of childbearing information is that educated, and the like. After the prediction information is obtained, according to the prediction information corresponding to the category to which the service user belongs, determining an information prediction result corresponding to the user missing information, and taking the service user information with the highest frequency in the service user information of each category dimension as a result of estimating the service user information of the information missing user of each category dimension. For example, if the information-missing user D belongs to a female and is aged 30 years, the user D is missing business user information with the dimension of marriage and education information, and the female and aged 30 years, whose marriage and education information has the highest frequency of marriage and education information, is married and educated, it can be estimated that the marriage and education information of the user D is married and educated. By estimating the missing service user information based on similarity analysis, all information prediction results requiring information supplementation can be estimated.

In one embodiment, before the information matching is performed on the user complete information and the preset product information, the method further includes: acquiring a demand analysis result of a service user; and when the requirement analysis result is product information pushing, executing a step of performing information matching on the user complete information and preset product information.

In this embodiment, before information matching is performed on the complete user information and the product information, it is determined whether the service user needs to perform information pushing according to a requirement analysis result of the service user, and information matching is performed when the requirement analysis result meets an information pushing condition.

Specifically, a requirement analysis result of the service user is obtained, and the requirement analysis result can be obtained by performing requirement analysis in advance based on the user complete information, which reflects the requirement degree of each service user. After the requirement analysis result is obtained, the requirement analysis result is judged, if the requirement analysis result is product information pushing, the fact that information pushing needs to be carried out on the service user is indicated, and the step of carrying out information matching on the complete information of the user and preset product information is executed, so that the requirement analysis results of all service users are utilized to carry out screening, information pushing processing is carried out on the service user needing information pushing in a targeted mode, the pertinence of information pushing is guaranteed, and the information pushing effect is improved.

In one embodiment, the information matching of the user complete information and the preset product information, the determination of the information to be pushed according to the matching result, and the pushing of the information to be pushed to the terminal corresponding to the service user includes: acquiring a user wind control parameter corresponding to a service user; when the user wind control parameters meet the risk control conditions, information matching is carried out on the user complete information and preset product information to obtain a matching result; and determining the information to be pushed from the matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

In this embodiment, according to the user wind control parameter of the service user, information matching is performed with preset product information, and information to be pushed is determined to be pushed based on a matching result to perform information pushing. Specifically, when the information to be pushed is determined according to the matching result, the user wind control parameter corresponding to the service user is obtained, the user wind control parameter reflects the risk degree of the service user, and the service user with the excessively high risk does not need to perform demand analysis, so that preliminary risk control is realized, and resource waste is avoided. And when the user wind control parameters meet the risk control conditions, for example, the user wind control parameters are smaller than a preset wind control threshold value, performing information matching on the user complete information and preset product information to obtain a matching result. When the user complete information is matched with the preset product information, whether each item of data in the user complete information meets the preset product information or not can be judged, and for example, matching results with different similarity ranks can be obtained based on similarity matching. And then determining the information to be pushed from the matching result, and pushing the information to be pushed to a terminal corresponding to the service user. For example, a plurality of matching results with the highest matching degree in the matching results may be used as information to be pushed, and the pushed information may be pushed to a terminal corresponding to the service user.

In one embodiment, the result of analyzing the requirement of the service user can be obtained by the following steps: determining the requirement analysis level of a service user; when the requirement analysis level meets a preset requirement analysis level condition, determining the service requirement type of a service user; acquiring a preset service demand index corresponding to the service demand type and an index weight corresponding to the service demand index; and calculating to obtain a demand analysis result of the service user according to the service demand index and the index weight.

The requirement analysis levels reflect the requirement degrees of the service user for service requirement analysis, different requirement analysis levels have different requirement analysis degrees, and whether the service user needs to be subjected to requirement analysis and subsequent product information pushing can be judged according to the requirement analysis levels. The requirement analysis level can be determined according to user service data of the service user and a corresponding requirement analysis rule, for example, for the service user with the wind control not meeting the minimum requirement or the product information pushing frequency being too high, the requirement analysis degree is low, the corresponding requirement analysis level can be low, the requirement analysis can be temporarily not carried out, the appropriate potential user is mined by concentrated resources, the service user is filtered according to the requirement analysis level, the pertinence of the requirement analysis and the product information pushing is ensured, and the information pushing effect is improved.

In specific implementation, the requirement analysis level of each service user can be recorded by maintaining a requirement analysis level table, and when the requirement analysis and judgment of the service user is required, the corresponding requirement analysis level can be determined from the requirement analysis level table according to the user identification information of the service user.

The requirement analysis level conditions can be set individually according to actual business rules, different business systems can set different requirement analysis level conditions, and whether the requirement analysis and the product information pushing of the business user are needed or not is judged by comparing the requirement analysis level of the business user with the requirement analysis level conditions. The service requirement type is a service type which needs to perform requirement analysis and product information pushing on service users and can be obtained through a requirement type model obtained based on historical service data training of each service system. For example, in the financial business, the business types of various loan services including credit card service, credit extension service, consumption credit service, business credit service, car purchase credit service and the like, and various insurance services including accident insurance, car insurance, property insurance, human life insurance and the like are different, and the business users have different demands for various business types. For different service users, the service users have different service type requirements, that is, the service users correspond to different service requirement types. The method has the advantages that the requirement type judgment is carried out on each service user, so that various service types of the service user needing further service requirement analysis are preliminarily determined, the blind requirement analysis on each service user can be effectively avoided, the service requirement analysis efficiency can be improved, and meanwhile, the accurate and effective requirement analysis and the product information pushing are carried out.

Specifically, when the requirement analysis level of the service user meets a preset requirement analysis level condition, that is, the service user needs to be subjected to requirement analysis and product information push processing, the service requirement type of the service user is further determined. The service requirement type can be processed by combining the user complete information of the service user through a preset requirement type model, such as a Bayesian probability model, a decision tree model, a neural network model and the like, so as to obtain the service requirement type corresponding to the service user and needing service requirement analysis, such as the service types of credit card requirements, small credit requirements, consumption credit requirements and the like. The demand type model can be obtained by training based on historical service data of each service user in each service system.

After the service requirement type of the service user is determined, a preset service requirement index corresponding to the service requirement type and an index weight corresponding to the service requirement index are obtained. The service demand indexes are various indexes such as age segmentation, academic history, industry and gender when demand analysis is carried out on the service demand type, and can be obtained based on a big data analysis result of historical service data; the index weight and the service demand index are correspondingly arranged, the importance degree of each service demand index is reflected, different index weights are arranged for each service demand index in different service demand types when demand analysis is carried out, and the index weights can be determined through an index weight model obtained based on historical service data training. Specifically, the index weight corresponding to the service demand index can be obtained by inputting the service demand index of the service demand type into a preset index weight model, and the index weight model can be obtained by training based on historical service data of each service user in the service system, such as a bayesian probability model, a decision tree model, a neural network model, and the like.

After a preset service demand index corresponding to the service demand type and an index weight corresponding to the service demand index are obtained, a demand analysis result of a service user is obtained through calculation according to the service demand index and the index weight, the demand analysis result reflects the demand degree of the service user on the service demand type, and when the demand degree meets a push condition, product information push can be performed on a service product of the service demand type, so that an information push effect is improved.

Specifically, according to the obtained service requirement index, user index information for service requirement analysis can be extracted from the user complete information of the service user. And scoring the obtained user index information according to a preset index scoring rule to obtain a requirement index score of each service requirement index corresponding to the user index information. And calculating to obtain a demand analysis result of the service user for the service demand type by combining the index weight corresponding to the service demand index and the demand index score, wherein the demand analysis result effectively reflects the demand degree of the service user for the service, and after the demand analysis result is obtained, determining information to be pushed according to the demand analysis result and pushing the information.

In one embodiment, determining the demand analysis level of the business user comprises: inquiring a preset requirement analysis level table; and inquiring the requirement analysis level corresponding to the user identification information from the requirement analysis level table.

In this embodiment, after the service user performing the requirement analysis determination is determined, the requirement analysis level of each service user is determined through the requirement analysis level table maintained in advance. Specifically, a preset requirement analysis level table is inquired, and the requirement analysis level table is constructed according to user complete information of each service user and requirement analysis levels determined by corresponding requirement analysis rules. The requirement analysis level table records requirement analysis levels of all service users, and the requirement analysis levels are determined according to user complete information of the service users and corresponding requirement analysis rules. And after the requirement analysis level table is obtained, inquiring the requirement analysis level corresponding to the user identification information from the requirement analysis level table to obtain the requirement analysis level of the service user.

In one embodiment, determining the service demand type of the service user comprises: inquiring a preset demand type model, wherein the demand type model is obtained by training according to historical service data of each service system; and inputting the complete information of the user into the requirement type model to obtain the service requirement type of the service user.

After the requirement analysis level of the service user is obtained, comparing the requirement analysis level with a preset requirement analysis level condition to judge whether the requirement analysis and product information pushing are needed to be carried out on the service user, and when the requirement analysis level of the service user meets the preset requirement analysis level condition, carrying out requirement analysis on the service user to obtain a requirement analysis result. The requirement analysis level conditions can be set individually according to actual business rules, and different service systems can set different requirement analysis level conditions. In this embodiment, when the requirement analysis level of the service user meets the preset requirement analysis level condition, the service requirement type of the service user is determined by combining the user integrity information of the service user through a preset requirement type model, such as a bayesian probability model, a decision tree model, a neural network model, and the like.

Specifically, when the requirement analysis level of the service user meets a preset requirement analysis level condition, a preset requirement type model is inquired, and the requirement type model is obtained by training according to historical service data of each service system. For example, the demand type model can be a Bayesian probability model, a decision tree model, a neural network model, and the like. When the demand type model is trained, historical service data of each service user can be inquired from each service system, user complete information of the service user in the historical service data is used as model input, the service type in the historical service data is used as model output, and the historical service data is trained to obtain the demand type model. The demand type model can output the service demand type of the service user corresponding to the user complete information according to the input user complete information. The obtained demand type model can be a Bayesian probability model, a decision tree model, a neural network model and the like, and the specific type is determined according to a training algorithm selected by actual demands.

And after the requirement type model is obtained, inputting the obtained user complete information into the requirement type model to obtain the service requirement type of the service user, wherein the service requirement type is the service type which needs to carry out requirement analysis and product information push on the service user.

In one embodiment, the calculating the requirement analysis result of the service user according to the service requirement index and the index weight includes: extracting user index information from the user complete information according to the service demand index; scoring the user index information according to a preset index scoring condition to obtain a demand index score corresponding to the service demand index; and calculating to obtain a demand analysis score of the service user according to the demand index score and the index weight, wherein the demand analysis result comprises the demand analysis score.

In this embodiment, after obtaining the preset service demand index corresponding to the service demand type and the index weight corresponding to the service demand index, the demand analysis score of the service user is calculated according to the service demand index, the user integrity information, the index scoring condition, and the index weight, and the demand analysis result includes the demand analysis score.

Specifically, when a demand analysis result of a service user is calculated, user index information is extracted from user complete information according to a service demand index. The service demand indexes are various types of indexes when demand analysis is carried out on service demand types, and the user index information is user complete information corresponding to the service demand indexes. After the user index information is obtained, a preset index scoring condition is obtained, wherein the index scoring condition can be an index scoring rule for scoring the user index information by combining with a service system, and different index scoring conditions can be set by different service systems. And scoring the user index information according to the obtained index scoring condition to obtain a demand index score corresponding to the service demand index, wherein the demand index score reflects the demand degree of the service user for each service demand index. And after the demand index score is obtained, calculating to obtain a demand analysis score of the service user according to the demand index score and the index weight, wherein the demand analysis result comprises the demand analysis score. The requirement analysis result reflects the requirement degree of the service user on the service requirement type, and when the requirement degree meets the pushing condition, product information pushing can be performed on the service product information of the service requirement type, so that the product information pushing effect is improved.

In one embodiment, the obtaining of the preset service requirement index corresponding to the service requirement type and the index weight corresponding to the service requirement index includes: inquiring a service demand index corresponding to the service demand type from a preset service demand index table; inquiring a preset index weight model, wherein the index weight model is obtained by training according to historical service data; and inputting the service demand indexes into the index weight model to obtain the index weights corresponding to the service demand indexes.

In this embodiment, after the service demand type of the service user is determined, the service demand index corresponding to the service demand type when the demand analysis is performed on the service demand type is determined according to the preset service demand index table, and the index weight corresponding to the service demand index is determined according to the preset index weight model.

Specifically, after the service requirement type of the service user is determined, a preset service requirement index table is queried, the service requirement index table records service requirement indexes corresponding to each service requirement type, and the service requirement indexes are set according to specific service rules or rules of each service system. And inquiring the service requirement index corresponding to the service requirement type from the service requirement index table. And inquiring a preset index weight model, wherein the index weight model is obtained by training according to historical service data, such as a Bayesian probability model, a decision tree model, a neural network model and the like. For example, for the business of business loan, historical business data related to the business of business loan is obtained from a business system, and business loan historical index data corresponding to a demand index of the business of loan is extracted from the business system, based on supervised learning, the business loan historical index data is divided into a training set and a test set, a model to be tested is obtained through training of the training set, and the test set is used for testing to obtain an index weight model meeting the demand, such as a bayesian probability model, a decision tree model, a neural network model and the like. The index weight model may output an index weight corresponding to each service demand index after inputting the service demand index corresponding to the service demand type.

In specific application, the index weight model may also be set corresponding to each service requirement type, that is, different service requirement types, and different index weight models are set. For example, for both credit card demand and accident demand, an "industry" index may be included in the business demand index, however, for business users in different industries, the index affects differently in the credit card demand analysis and accident demand analysis. For example, for high-risk industries, the influence degree of the credit card demand is general, the index weight corresponding to the 'industry' index is lower during the credit card demand analysis, the influence on the accident demand is larger, and the index weight corresponding to the 'industry' index is higher during the credit card demand analysis. In addition, the index weight corresponding to each service requirement type can also be maintained through an index weight table, and the index weight corresponding to the service requirement index of each service requirement type can be obtained through the table query.

After the service demand indexes and the index weight models corresponding to the service demand types are obtained, the service demand indexes corresponding to the service demand types are input into the index weight models to obtain the index weights corresponding to the service demand indexes, the index weights are set corresponding to the service demand indexes, and the importance degrees of the service demand indexes are reflected.

In one embodiment, as shown in fig. 4, there is provided an information pushing apparatus including: a user information obtaining module 401, a missing information determining module 403, a completion information obtaining module 405, a complete information obtaining module 407, and an information pushing processing module 409, where:

a user information obtaining module 401, configured to obtain user identification information of a service user, and query service user information according to the user identification information;

a missing information determining module 403, configured to perform data missing detection on the service user information, and determine user missing information when a missing detection result is information missing;

a completion information obtaining module 405, configured to perform prediction information completion on the missing user information to obtain user completion information;

a complete information obtaining module 407, configured to obtain complete user information according to the user completion information and the service user information;

the information pushing processing module 409 is configured to perform information matching on the complete user information and preset product information, determine information to be pushed according to a matching result, and push the information to be pushed to a terminal corresponding to a service user.

In one embodiment, the completion information obtaining module 405 includes: the information type determining unit is used for performing information type matching according to the missing information of the user and determining the information type of the missing information of the user; the completion strategy acquisition unit is used for acquiring a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy; the information prediction processing unit is used for processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information; and the completion information acquisition unit is used for completing the missing user information according to the information prediction result to obtain user completion information.

In one embodiment, the information prediction processing unit includes a user classification subunit, a complete user information acquisition subunit, a complete user information statistics subunit, a prediction information subunit, and a prediction result subunit; wherein: the user classification subunit is used for analyzing the user behavior data of each service user in the statistical completion data based on the similarity analysis and classifying each service user; the complete user information acquisition subunit is used for acquiring the service user information of the information complete user; the complete user information counting subunit is used for counting the service user information of various information complete users and acquiring the service user information with the highest frequency in the service user information of each category dimension; the prediction information subunit is used for taking the service user information with the highest frequency in the service user information of each category dimension as the prediction information of each category dimension; and the prediction result subunit is used for determining an information prediction result corresponding to the user missing information according to the prediction information corresponding to the category to which the service user belongs.

In one embodiment, the system further comprises a requirement analysis obtaining module, configured to obtain a requirement analysis result of the service user; and the demand pushing processing module is used for executing the step of performing information matching on the user complete information and preset product information when the demand analysis result is product information pushing.

In one embodiment, the information pushing processing module 409 includes a wind control parameter unit, a matching unit and an information pushing unit; wherein: the system comprises a wind control parameter unit, a service user management unit and a service user management unit, wherein the wind control parameter unit is used for acquiring user wind control parameters corresponding to service users; the matching unit is used for performing information matching on the complete information of the user and preset product information to obtain a matching result when the wind control parameters of the user meet the risk control conditions; and the information pushing unit is used for determining the information to be pushed from the matching result and pushing the information to be pushed to the terminal corresponding to the service user.

For specific limitations of the information pushing apparatus, reference may be made to the above limitations of the information pushing method, which is not described herein again. All or part of the modules in the information pushing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an information push method.

Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:

In one embodiment, the processor, when executing the computer program, further performs the steps of: performing information type matching according to the missing information of the user, and determining the information type of the missing information of the user; acquiring a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy; processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information; and completing the missing information of the user according to the information prediction result to obtain user completion information.

In one embodiment, the processor, when executing the computer program, further performs the steps of: analyzing the user behavior data of each service user in the statistical completion data based on similarity analysis, and classifying each service user; acquiring service user information of a user with complete information; counting the service user information of various information complete users to obtain the service user information with the highest frequency in the service user information of each category dimension; the service user information with the highest frequency in the service user information of each category dimension is used as the prediction information of each category dimension; and determining an information prediction result corresponding to the user missing information according to the prediction information corresponding to the category of the service user.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a demand analysis result of a service user; and when the requirement analysis result is product information pushing, executing a step of performing information matching on the user complete information and preset product information.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a user wind control parameter corresponding to a service user; when the user wind control parameters meet the risk control conditions, information matching is carried out on the user complete information and preset product information to obtain a matching result; and determining the information to be pushed from the matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of: performing information type matching according to the missing information of the user, and determining the information type of the missing information of the user; acquiring a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy; processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information; and completing the missing information of the user according to the information prediction result to obtain user completion information.

In one embodiment, the computer program when executed by the processor further performs the steps of: analyzing the user behavior data of each service user in the statistical completion data based on similarity analysis, and classifying each service user; acquiring service user information of a user with complete information; counting the service user information of various information complete users to obtain the service user information with the highest frequency in the service user information of each category dimension; the service user information with the highest frequency in the service user information of each category dimension is used as the prediction information of each category dimension; and determining an information prediction result corresponding to the user missing information according to the prediction information corresponding to the category of the service user.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a demand analysis result of a service user; and when the requirement analysis result is product information pushing, executing a step of performing information matching on the user complete information and preset product information.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a user wind control parameter corresponding to a service user; when the user wind control parameters meet the risk control conditions, information matching is carried out on the user complete information and preset product information to obtain a matching result; and determining the information to be pushed from the matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. An information pushing method, the method comprising:

acquiring user identification information of a service user, and inquiring service user information according to the user identification information;

obtaining user complete information according to the user completion information and the service user information;

and performing information matching on the user complete information and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

2. The method of claim 1, wherein the performing predictive information completion on the missing user information to obtain user completion information comprises:

performing information type matching according to the user missing information, and determining the information type of the user missing information;

3. The method according to claim 2, wherein the processing the statistical completion data by using the method corresponding to the information completion policy to obtain the information prediction result corresponding to the missing information of the user comprises:

acquiring service user information of a user with complete information;

4. The method according to claim 1, further comprising, before said information matching the user integrity information with preset product information:

acquiring a demand analysis result of the service user;

5. The method according to any one of claims 1 to 4, wherein the performing information matching on the user complete information and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to the service user comprises:

acquiring a user wind control parameter corresponding to the service user;

when the user wind control parameters meet risk control conditions, information matching is carried out on the user complete information and preset product information to obtain a matching result;

and determining information to be pushed from the matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

6. An information pushing apparatus, characterized in that the apparatus comprises:

the user information acquisition module is used for acquiring user identification information of a service user and inquiring the service user information according to the user identification information;

a missing information determining module, configured to perform data missing detection on the service user information, and determine user missing information when a missing detection result indicates that information is missing;

the completion information acquisition module is used for performing prediction information completion on the user missing information to obtain user completion information;

and the information pushing processing module is used for carrying out information matching on the user complete information and preset product information, determining information to be pushed according to a matching result, and pushing the information to be pushed to a terminal corresponding to the service user.

7. The apparatus of claim 6, wherein the completion information obtaining module comprises:

the information type determining unit is used for performing information type matching according to the user missing information and determining the information type of the user missing information;

a completion strategy obtaining unit, configured to obtain a preset information completion strategy corresponding to the information type and statistical completion data corresponding to the information completion strategy;

the information prediction processing unit is used for processing the statistical completion data by using a method corresponding to the information completion strategy to obtain an information prediction result corresponding to the user missing information;

and the completion information acquisition unit is used for completing the user missing information according to the information prediction result to obtain user completion information.

8. The apparatus of claim 6, further comprising:

the demand analysis acquisition module is used for acquiring a demand analysis result of the service user;

and the demand pushing processing module is used for executing the step of performing information matching on the user complete information and preset product information when the demand analysis result is product information pushing.

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.