CN112750043A

CN112750043A - Business data pushing method and device and server

Info

Publication number: CN112750043A
Application number: CN202110047200.2A
Authority: CN
Inventors: 陈珊珊; 郭宏
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-01-14
Filing date: 2021-01-14
Publication date: 2021-05-04
Anticipated expiration: 2041-01-14
Also published as: CN112750043B

Abstract

The specification provides a service data pushing method, a service data pushing device and a service data pushing server. Based on the method, in the field of artificial intelligence, when a server pushes business data to a user object, the client group type of the user object is determined, and then a prediction sub-model matched with the client group type in a preset target user prediction model is called to determine whether the user object is a potential target user capable of receiving the business data; the preset target user prediction model comprises a first prediction submodel which is established based on horizontal federal learning according to first sample data of a first data party and second sample data of a second data party, and a second prediction submodel which is established based on federal transfer learning according to the first sample data, the second sample data and the first prediction submodel; and under the condition that the user object is determined to be the target user, appropriate target service data is pushed to the user object, so that a better pushing effect can be obtained, and the pushing success rate is improved.

Description

Business data pushing method and device and server

Technical Field

The specification belongs to the technical field of artificial intelligence, and particularly relates to a service data pushing method, a service data pushing device and a service server.

Background

In many business data pushing scenarios (for example, a recommendation scenario of a financial business, etc.), it is often difficult to accurately predict whether a user object to be pushed business data is a potential target user that will receive the business data due to the model precision of the used prediction model. The technical problems of inaccurate pushing, poor business data pushing effect and the like often exist when business data are pushed to a user object based on the existing method.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The specification provides a business data pushing method, a business data pushing device and a business data pushing server, so that whether a user object is a target user can be accurately determined by using a preset target user prediction model established based on horizontal federal learning and federal transfer learning; and under the condition that the user object is determined to be the target user, corresponding target service data is pushed to the user object, so that a good pushing effect can be obtained, and the pushing success rate is improved.

The method for pushing the service data provided by the present specification includes:

acquiring identification information of a user object and characteristic data of the user object; wherein the feature data at least comprises non-traffic class feature data;

determining the guest group type of the user object according to the identification information of the user object;

calling a prediction sub-model matched with the guest group type of the user object in a preset target user prediction model to process the characteristic data of the user object so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning;

and under the condition that the user object is determined to be the target user, pushing appropriate target business data to the user object.

In one embodiment, the guest group type includes: a first fully featured guest group type and a second poorly featured guest group type.

In one embodiment, the first predictor model matches a first guest group type and the second predictor model matches a second guest group type.

In one embodiment, the preset target user prediction model is established as follows:

the method comprises the steps that a first server responds to a first training request about a preset target user prediction model, and performs sample data fusion with a second server in a cooperative mode according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in sample users of a first passenger group type and a second positive sample user and a second negative sample user in sample users of a second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user;

acquiring non-service characteristic data of a first positive sample user and non-service characteristic data of a first negative sample user from the first sample data to serve as first grouping sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data;

training to obtain a first predictor model according to the first grouping sample data;

obtaining a second predictor model through federal transfer learning training according to the second group of sample data and the first predictor model;

and combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model.

In one embodiment, training to obtain a first predictor model according to the first packet of sample data includes:

extracting a plurality of data from the non-business characteristic data of a first positive sample user in the first grouping sample data, and marking the data as first positive sample training data; extracting a plurality of data from the non-business class characteristic data of a first negative sample user in the first grouping sample data, and marking the data as first negative sample training data;

combining the first positive sample training data and the first negative sample training data to obtain first class training data;

and training by using the first type of training data to obtain a first predictor model.

In one embodiment, the obtaining a second predictor model through federated migration learning training according to the second packet of sample data and the first predictor model comprises:

extracting a plurality of data from the non-business class characteristic data of a second positive sample user in the second grouping sample data, and marking the data as second positive sample training data; extracting a plurality of data from the non-business class characteristic data of the second negative sample user in the second grouping sample data, and marking the data as second negative sample training data;

combining the second positive sample training data and the second negative sample training data to obtain second type training data;

calling a preset first predictor model to process the second type of training data to obtain a corresponding predicted value;

combining the second type of training data with the corresponding predicted value to obtain combined second type of training data;

and training by using the combined second type of training data to obtain a second predictor model.

In one embodiment, the first guest group type comprises a bank-originating payroll group and the second guest group type comprises a non-bank-originating payroll group.

In one embodiment, in case it is determined that the user object is a target user, the method further comprises:

acquiring and determining a portrait label of a user object according to service class characteristic data of the user object;

generating a target pushing rule matched with the user object according to the portrait label of the user object;

and pushing appropriate target business data to the user object according to the target pushing rule.

In one embodiment, determining a portrait label for a user object based on business class characterization data for the user object comprises:

calling a preset user portrait prediction model to process the service class characteristic data of the user object to obtain a corresponding processing result; the preset user portrait prediction model is established in advance according to first sample data and second sample data based on longitudinal federal learning;

and determining the portrait label of the user object according to the processing result.

In one embodiment, the target business data includes insurance business products and/or insurance business services that fit the user object; correspondingly, the target pushing rule comprises an insurance business marketing scheme.

In one embodiment, the non-traffic class characteristic data comprises at least one of: monthly income, monthly consumption amount, deposit balance; the service class characteristic data comprises at least one of: gift identification, premium, and premium.

The present specification further provides a method for training a model, which is applied to a first server deployed on a first data side, and includes:

responding to a first training request about a preset target user prediction model, and performing sample data fusion in cooperation with a second server according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in the sample users of the first passenger group type and a second positive sample user and a second negative sample user in the sample users of the second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user;

This specification also provides a service data pushing device, including:

the acquisition module is used for acquiring the identification information of the user object and the characteristic data of the user object; wherein the feature data at least comprises non-traffic class feature data;

the determining module is used for determining the guest group type of the user object according to the identification information of the user object;

the calling module is used for calling a prediction sub-model matched with the user object passenger group type in a preset target user prediction model to process the characteristic data of the user object so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning;

and the pushing module is used for pushing appropriate target business data to the user object under the condition that the user object is determined to be the target user.

The present specification further provides a training apparatus for a model, which is applied to a first server deployed on a first data side, and includes:

the fusion module is used for responding to a first training request about a preset target user prediction model, and performing sample data fusion with the second server in a cooperative mode according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in the sample users of the first passenger group type and a second positive sample user and a second negative sample user in the sample users of the second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user;

the acquisition module is used for acquiring the non-service characteristic data of a first positive sample user and the non-service characteristic data of a first negative sample user from the first sample data as first grouping sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data;

the first training module is used for training to obtain a first predictor model according to the first grouping sample data;

the second training module is used for obtaining a second predictor model through federal transfer learning training according to the second grouping of sample data and the first predictor model;

and the combination module is used for combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model.

The present specification also provides a server, which includes a processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement the relevant steps of the pushing method of the business data.

According to the pushing method, the pushing device and the pushing server for the business data, when the server pushes the business data to the user object, the client type of the user object can be determined firstly, and then a prediction sub-model matched with the client type in a preset target user prediction model can be called to determine whether the user object is a potential target user who can receive the pushed business data or not according to the characteristic data of the user object; the preset target user prediction model comprises a first prediction submodel which is established based on horizontal federal learning according to first sample data of a first data party and second sample data of a second data party, and a second prediction submodel which is established based on federal transfer learning according to the first sample data, the second sample data and the first prediction submodel; and under the condition that the user object is determined to be the target user, appropriate target service data is pushed to the user object, so that a better pushing effect can be obtained, and the pushing success rate is improved.

Drawings

In order to more clearly illustrate the embodiments of the present specification, the drawings needed to be used in the embodiments will be briefly described below, and the drawings in the following description are only some of the embodiments described in the present specification, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic diagram of an embodiment of a structural composition of a data processing system to which a pushing method of service data provided by an embodiment of the present specification is applied;

fig. 2 is a flowchart illustrating a pushing method of service data according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram illustrating an embodiment of a pushing method for service data provided by an embodiment of the present specification, in a scenario example;

FIG. 4 is a schematic flow chart diagram of a model training method provided by one embodiment of the present description;

FIG. 5 is a schematic diagram of a server according to an embodiment of the present disclosure;

fig. 6 is a schematic structural composition diagram of a service data pushing device provided in an embodiment of the present specification;

FIG. 7 is a schematic structural component diagram of a model training apparatus provided in an embodiment of the present disclosure;

fig. 8 is a schematic diagram of an embodiment of a pushing method for service data provided by an embodiment of the present specification, in a scenario example;

fig. 9 is a schematic diagram of an embodiment of a pushing method for service data provided by an embodiment of the present specification, in a scenario example;

fig. 10 is a schematic diagram of an embodiment of a pushing method for service data provided by an embodiment of the present specification, in an example scenario.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

In consideration of the existing pushing method based on the business data, under the condition of data isolation, sample data in a single data party is often used for training a prediction model for predicting a potential target user which can receive the pushed business data, then the prediction model is used for predicting a user object to be pushed with the business data so as to determine whether the user object is a potential target user, and then the business data is pushed to the user object according to the prediction result.

Firstly, the sample data used by the method in the process of training the prediction model is often only the sample data in a single data party, and the sample data used is relatively limited, so that the model precision of the prediction model obtained by training is relatively poor.

Secondly, there is a large difference in the data quality of the characteristic data of different sample users in the held sample data. For example, for a part of sample users, the collected features are complete, the sample data contains 30 different features of the sample user, and the data quality of the feature data is high. For another part of sample users, the acquired feature loss is serious, the sample data only contains 5 different features of the sample user, and the data quality of the feature data is low. At this time, if the feature data of the sample user with serious feature loss and poor data quality is directly used to participate in model training, the accuracy of the model is obviously affected.

For the root cause of the above problems, the present specification first considers that the first sample data in the first data party and the second sample data in the second data party can be comprehensively utilized through the protocol rules based on horizontal federal learning to expand the sample data for model training.

When specifically utilizing the first sample data in the first data party and the second sample data in the second data party, further finding out: different data parties have different data channels and data isolation, so that the different data parties often have great difference in marking sample data and even have the problem of disordered data labels; further, it is difficult to directly collaborate with sample data held by different data parties, subject to data isolation.

For example, the head office, although not exclusively responsible for pushing business data, may hold non-business class feature data for a full number of sample users. And the subsidiary company which is specially responsible for business data pushing generally performs business data pushing aiming at the existing sample users of the main company. When business data is pushed specifically, a main company often pushes the business data of a subsidiary company only through a shared channel shared with the subsidiary company. On the subsidiary side, besides using the shared channel, the business data can be pushed through the own channel which the main company does not have. For example, on the head office side, the record data based on the common channel for sample user a is marked as negative sample user. On the subsidiary side, the user a is marked as a positive sample for the same sample based on the recorded data of the own channel.

In some cases, the subsidiary company records only the business class feature data of the user who has successfully pushed the data (corresponding to the positive sample user), and does not record the relevant data of the user who has failed to push the data (corresponding to the negative sample user).

Therefore, the head office often holds the non-business class feature data (which can be recorded as the first sample data) of the full sample users, and the subsidiary often holds the business class feature data (which can be recorded as the second sample data) of the full positive sample users (i.e. users whose business data push is successful).

Further, under the constraint of the relevant regulations, the head office and the subsidiary companies generally cannot directly transfer the data held by each other, and it is difficult to directly use the data held by both parties in combination to train the model.

In view of the above, the present specification further combines specific features in a data processing scenario and the correlation between the first sample data and the second sample data, before the specific implementation, the first server having the first sample data is deployed on the first data side for the influence of sample data with incomplete features on model training, and a second server deployed in a second data party and holding second sample data can distinguish sample users of a first passenger group type with complete characteristics and sample users of a second passenger group type with incomplete characteristics in the sample users, and then according to a protocol rule based on horizontal federal learning, performing data fusion by cooperation to obtain first class training data for training a first predictor model corresponding to the first guest group type, and second class training data for training a second predictor model corresponding to the second guest group type. Further, a first predictor model with higher precision can be obtained by training by utilizing first type training data with higher data quality; and then, second training data are utilized, the first prediction submodel obtained by previous training is combined, data knowledge of the first prediction submodel is introduced through federal transfer learning, the influence of the second training data characteristic irregularity on model training is weakened, the second prediction submodel with relatively high precision is obtained through training, and therefore the preset target user prediction model with relatively high precision and relatively good effect on the two passenger group types can be obtained.

In this way, in specific implementation, after accessing the feature data of the user object of the service data to be pushed, the server may determine the guest group type of the user object, and may further invoke a prediction sub-model in the preset target user prediction model, which is matched with the guest group type of the user object, to process the feature data of the user object, so as to accurately identify whether the user object belongs to a potential target user who will accept the pushed service data. And under the condition that the user object is determined to be the target user, pushing appropriate service data to the user object. Therefore, a better pushing effect can be obtained, the pushing success rate is improved, and the accurate pushing of the service data of the user object is realized.

The embodiment of the present specification provides a method for pushing service data, which may be specifically applied to a data processing system including a first server and a second server. As can be seen in fig. 1. The first server and the second server can be connected in a wired or wireless mode to perform corresponding data interaction.

In this embodiment, the first server may be specifically understood as a server deployed on a side of a first data party (or referred to as a first data domain, for example, a head office). The first server may hold first sample data in a first data party. The first sample data may be specifically understood as sample data obtained from the first data party. Each piece of sample data in the first sample data may specifically include two pieces of data, namely, identification information of the user object (for example, an identity ID of the user a, a mobile phone number of the user a, a name of the user a, and the like) and non-business feature data (for example, occupation of the user a, monthly income of the user a, number of default times of the user a, and the like) corresponding to the identification information and not directly related to business data. The non-traffic class feature data may further comprise a plurality of different non-traffic class features.

In this embodiment, the second server may be specifically understood as a server deployed on the side of the second data party (or referred to as the second data domain, e.g., a subsidiary company). The second server may hold second sample data in the second data party. The second sample data may be sample data obtained from a second data party. Each sample data in the second sample data may specifically include two parts of data, i.e., identification information of the user object and service class feature data directly related to the service data corresponding to the identification information. The service class feature data may further comprise a plurality of different service class features.

The identification information of the user object in the second sample data is included in the identification information of the user object in the first sample data.

In addition, because there is data isolation between the first data party and the second data party, the first server cannot directly transmit the held first sample data to the second server. Accordingly, the second server cannot directly transmit the held second sample data to the first server.

In this embodiment, before the implementation (modeling stage), referring to fig. 1, the first server and the second server may cooperate to perform data fusion according to a protocol rule based on horizontal federal learning, and determine a full positive sample user from the full sample users according to first sample data and second sample data respectively held by the first server and the second server; and by distinguishing a first passenger group type and a second passenger group type in the full-amount sample users, first class training data (corresponding to a first positive sample user and a first negative sample user in the first passenger group type) with complete characteristics and high data quality and second class training data (corresponding to a second positive sample user and a second negative sample user in the second passenger group type) with incomplete characteristics and poor data quality are separated.

Then, the first class of training data can be used to train to obtain a first predictor model corresponding to the first guest group type with higher precision. And then, the second type of training data is utilized, and meanwhile, the first predictor model obtained by previous training is combined, the data knowledge of the first type of training data is introduced through federal transfer learning to reduce the influence of the characteristic loss of the second type of training data on model training, and the second predictor model with relatively high precision is obtained. And finally, combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model. Therefore, the preset target user prediction model with higher precision aiming at the first passenger group type and the second passenger group type can be obtained.

According to the mode, the first server and the second server can obtain the preset target user prediction model with high precision and good effect through cooperation training.

The first server and/or the second server can hold and call the trained prediction model, and the prediction model can be provided for a third server of a third party to use according to a cooperation protocol.

In specific implementation (a pushing stage), a server (which may be a first server, a second server, or a third server) accessing a data object of service data to be pushed may determine a guest group type of a user object according to identification information of the user object; the feature data of the user object can be processed by calling a prediction sub-model matched with the guest group type of the user object in a preset target user prediction model, so that whether the user object belongs to a potential target user capable of receiving the pushed business data or not can be accurately identified; and under the condition that the user object is determined to be the target user, pushing the appropriate target business data to the user object.

Therefore, the user object is more willing to accept the pushed service data, a better pushing effect is obtained, the pushing success rate is improved, and the accurate pushing of the service data of the user object is realized.

In this embodiment, the first server and the second server may specifically include a background server that is applied to a service data processing platform side and is capable of implementing functions such as data transmission and data processing. Specifically, the first server and the second server may be, for example, an electronic device having data operation, storage functions and network interaction functions. Alternatively, the first server and the second server may also be software programs running in the electronic device and providing support for data processing, storage and network interaction. In this embodiment, the number of servers included in the first server and the second server is not specifically limited. The first server and the second server may be specifically one server, or several servers, or a server cluster formed by several servers.

Referring to fig. 2, an embodiment of the present disclosure provides a method for pushing service data. When the method is implemented, the following contents may be included.

S201: acquiring identification information of a user object and characteristic data of the user object; wherein the feature data at least comprises non-traffic class feature data;

s202: determining the guest group type of the user object according to the identification information of the user object;

s203: calling a prediction sub-model matched with the guest group type of the user object in a preset target user prediction model to process the characteristic data of the user object so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning;

s204: and under the condition that the user object is determined to be the target user, pushing appropriate target business data to the user object.

Through the embodiment, the server can accurately identify and determine whether the user object of the business data to be pushed is a potential target user who can receive the business data or not based on the preset target user prediction model which is established jointly by the horizontal federal learning and the federal transfer learning according to sample data held by multiple parties respectively in advance; and under the condition that the user object is determined to be the target user, pushing appropriate target service data to the user object. Therefore, the user object is more willing to accept the pushed service data, a better pushing effect is obtained, and the pushing success rate is improved; meanwhile, the user object can obtain better pushing experience.

In one embodiment, the method may be applied specifically on the server side. The server may be a first server deployed on a side of a first data party, a second server deployed on a side of a second data party, or a third server deployed on a side of a third party different from the first data party and the second data party.

The first data party may be a data party holding the first sample data. The first sample data may specifically include non-traffic class feature data of a full number of sample users. The second data party may specifically be a data party holding second sample data. The first sample data may specifically include service class feature data of a full number of positive sample users. The full positive sample users are a subset of full sample users. The third data party may be specifically different from the first data party and the second data party, and is not a third party holding sample data.

In an embodiment, the service class feature data may be specifically understood as feature data directly associated with service data to be pushed, and the non-service class feature data may be specifically understood as feature data indirectly associated with the service data to be pushed. The service data may specifically include: insurance business products, insurance business services, financing business products, financing business services, and the like. Of course, the above listed service data is only a schematic illustration. In specific implementation, the service data may also include other types of service data according to specific application scenarios and processing requirements. The present specification is not limited to these.

In an embodiment, the service class feature data and the non-service class feature data may specifically include different types of features respectively according to different service data, the first data party and the second data party.

The following description will specifically take the business data as an insurance business product, the first data party as a bank head office, and the second data party as an insurance business sub-company subordinate to the bank head office.

In this embodiment, the non-service feature data may specifically include one or more of the following features: monthly income, monthly consumption amount, inventory amount, occupation, etc. Correspondingly, the service class feature data may specifically include one or more of the following listed features: gift identification, historical premium, historical purchased risk category, and the like.

In this embodiment, the first server deployed on the first data side may hold non-business class feature data of a full number of sample users as the first sample data. The first data party is not mainly responsible for pushing the business data, but assists the second data party in pushing the business data through a shared channel (for example, bank insurance and the like) shared by the second data party. Therefore, the positive sample users (i.e., users that receive the pushed traffic data) that are marked out of the total number of sample users in the first sample data held by the first data party are often not complete.

The second server deployed on the second data side is mainly responsible for pushing the service data. Moreover, due to the association relationship between the second data party and the first data party, the second data party often mainly pushes related service data for the full number of sample users held by the first data party, and records the sample user (marked as a positive sample user) that is successfully pushed and the service class feature data of the positive sample user that is successfully pushed.

In addition, the second data party pushes the business data by using a shared channel shared by the first data party and also pushes the business data by using a self-owned channel (such as a self-selling channel of an insurance company) which is not possessed by other first data parties, and records the positive sample user and the business class feature data of the positive sample user. For such positive sample users, the first data party is not known or marked on the side of the first data party due to data isolation between the first data party and the second data party.

Thus, the second server may hold the traffic class feature data of the full number of positive sample users as the second sample data. And the above-mentioned full positive sample users are often also a subset of full sample users.

In an embodiment, when preparing to push service data to a user object, the server may first obtain identification information of the user object and feature data of the user object.

The identification information may specifically include identification information such as a name, an identity ID, a mobile phone number, and an account name for indicating the user object. The feature data of the user object may specifically be non-business feature data of the user object. Of course, the feature data of the user object may also be a combination of non-service class feature data and service class feature data of the user object.

In an embodiment, the server may determine, according to the identification information of the user object, a type of the guest group to which the user object belongs by data query, for example, by querying a preset guest group list.

In one embodiment, the guest group type may specifically include: a first fully featured guest group type and a second poorly featured guest group type.

In this embodiment, the user object is divided into the guest group types according to the first guest group type with complete features and the second guest group type with incomplete features based on whether the features of the user object are complete, so that a prediction sub-model matched with the user object in a preset target user prediction model can be called subsequently, and whether the user object is a target user or not is accurately determined.

In one embodiment, the first customer group type is specifically understood as a complete and complete customer group type with the characteristics held by the first data party. The above features may specifically refer to features in non-service feature data. Specifically, for example, the first guest group type may be a bank sponsor payroll group. For this type of customer base, the non-business type feature data (including asset features, transaction features, etc.) that the first data party (i.e., the bank) often holds are complete and complete, including, for example, the user's credit balance, the user's credit card water, the user's monthly income, and so forth.

In one embodiment, the second guest group type may be specifically understood as a guest group type with incomplete features and missing features held by the first data party. The above features may specifically refer to features in non-service feature data. Specifically, for example, the second guest group type may be a non-bank sponsor payroll group. For this type of customer group, the non-business class feature data that the first data party (i.e., bank) often holds is missing feature, incomplete.

Accordingly, the full number of sample users in the first sample data held by the first server may also include: sample users of a first guest group type with complete features, and sample users of a second guest group type with incomplete features. In the first sample data, the characteristics contained in the non-service characteristic data of the first passenger group type sample user are complete, and the data quality is relatively high; the non-business feature data of the sample users of the second customer group type comprise incomplete features and lack, and the data quality is relatively poor.

In one embodiment, when the server is implemented, a prediction sub-model matched with a guest group type can be determined from prediction sub-models contained in a preset target user prediction model according to the guest group type of a user object; and then, the matched predictor model can be called to process the characteristic data of the user object, and whether the user object is a target user or not is determined according to a processing result output by the model.

In one embodiment, the target user may be specifically understood as a potential customer group user with a relatively high probability of accepting the pushed service data.

In an embodiment, the preset target user prediction model may be specifically understood as a prediction model which is obtained by the first server and the second server in advance through cooperation and based on horizontal federal learning and federal transfer learning training by using the first sample data and the second sample data held by the first server and the second server, and can predict the probability value of the user object belonging to the target user based on the feature data of the user object. The training mode of the preset target user prediction model will be further described later.

In one embodiment, in particular, the guest group types include: under the condition of the first guest group type and the second guest group type, the preset target user prediction model specifically may include two different prediction submodels, namely a first prediction submodel and a second prediction submodel. The first predictor model is matched with a first passenger group type, and the second predictor model is matched with a second passenger group type.

In this embodiment, the first predictor model may be specifically obtained by training in advance using non-service characteristic data (denoted as first-class training data) of a sample user of the first guest group type, and it can be determined more accurately whether the user object is a predictor model of the target user for the first guest group type. The second predictor model may be obtained by training the first predictor model in combination with non-service characteristic data (recorded as second-class training data) of a sample user of the second guest group type in advance, and may be capable of determining whether the user object is the predictor model of the target user more accurately for the second guest group type.

By establishing and utilizing the preset target user prediction model which comprises the first prediction submodel corresponding to the first customer group type and the second prediction submodel corresponding to the second customer group type, whether the user object is a potential target user for receiving the service data can be determined more finely.

In one embodiment, in the case that the guest group type of the user object is determined to be the first guest group type, a first prediction submodel in a preset target user prediction model may be determined to be a matched prediction submodel; the first predictor model may then be invoked to process the feature data of the user object to determine whether the user object is a target user.

Under the condition that the guest group type of the user object is determined to be the second guest group mental core, a second prediction sub-model in a preset target user prediction model can be determined to be a matched prediction sub-model; a second predictor model may then be invoked to process the feature data for the user object to determine whether the user object is a target user.

In one embodiment, in the case that the user object is determined to be a target user, appropriate target business data can be pushed to the user object.

In an embodiment, under the condition that the user object is determined to be the target user, service class feature data of the user object or other associated background data can be further acquired; according to the personalized requirements and the personal preferences of the user object, the appropriate target service data can be pushed to the user object more accurately, the pushing success rate is further improved, and the user object can obtain better pushing experience.

In an embodiment, when the method is implemented in a specific manner in a case where the user object is determined to be a target user, the method may further include the following steps:

s1: acquiring and determining a portrait label of a user object according to service class characteristic data of the user object;

s2: generating a target pushing rule matched with the user object according to the portrait label of the user object;

s3: and pushing appropriate target business data to the user object according to the target pushing rule.

Through the embodiment, the server can more finely and accurately determine and utilize the portrait label of the user object to analyze the demand tendency and the personal preference of the user object, and further more effectively pushes appropriate target business data to the user object.

In one embodiment, the portrait tag may be specifically understood as tag data reflecting a requirement or preference of a user object for an attribute dimension of the service data that is prone to be accepted.

In an embodiment, in the case that the service data is insurance service product or insurance service, and the application scenario is insurance service marketing scenario, the portrait label may specifically include one or more of the following listed portrait labels: payment terms propensity label, premium propensity label, and the like. Of course, the above-mentioned image labels are only illustrative.

In specific implementation, the portrait label may also include other types of portrait labels according to specific service data and specific application scenarios. For example, in the case where the business data is a financial product and the application scenario is a marketing scenario of the financial product, the portrait label may be an annual profit margin tendency label, a fixed holding duration tendency label, a financial risk level tendency label, or the like.

In an embodiment, the determining the portrait label of the user object according to the service class feature data of the user object may include the following steps: calling a preset user portrait prediction model to process the service class characteristic data of the user object to obtain a corresponding processing result; the preset user portrait prediction model is established in advance according to first sample data and second sample data based on longitudinal federal learning; and determining the portrait label of the user object according to the processing result.

Through the embodiment, the portrait label of the user object can be determined more accurately and efficiently, and further, appropriate business data can be pushed to the user object more accurately.

In an embodiment, the preset user portrait prediction model may be specifically understood as a prediction model that the first server and the second server cooperate in advance to use the first sample data and the second sample data held by the first server and the second server to predict a portrait label, which is matched with the user object and relates to business data, based on feature data of the user object, based on vertical federal learning training.

In one embodiment, the predetermined user portrait prediction model may specifically include a plurality of portrait prediction submodels. Wherein each of the plurality of image predictor models corresponds to one image label.

Correspondingly, the server can call a plurality of portrait prediction submodels contained in the preset portrait prediction model of the user to respectively process the characteristic data of the user object to obtain a plurality of different portrait labels corresponding to the user object, and further can utilize the different portrait labels to more finely and comprehensively depict the personalized demand tendency or preference of the user object.

In one embodiment, matching target push rules can be customized for a user object in a targeted manner according to portrait labels of the user object; and further, according to the target pushing rule, appropriate target business data can be pushed to the user object.

In an embodiment, the target pushing rule may specifically be a construction manner of business data matched with the user object and applicable to the user object, a marketing scheme of the business data, or a recommendation policy of the business data. The target push rule may also be rule data of other contents corresponding to different service data and application scenarios. The present specification is not limited to these.

In one embodiment, specifically, the server may determine a target push rule suitable for the user object in a targeted manner according to the portrait label of the user object; further, target business data with high matching degree with the user object and high user object receiving probability can be configured according to a target pushing rule; and then, according to a target pushing rule, selecting a pushing mode which is preferred by the user object and can be reached in time, and pushing the target service data to the user object.

When the user object receives the target service data pushed according to the target pushing rule, relatively, the user object has a higher probability of being willing to accept the target service data. Therefore, the pushing success rate can be effectively improved, and a better pushing effect is obtained.

As can be seen from the above, based on the method for pushing service data provided in this specification, when the server pushes service data to the user object, the client class type of the user object may be determined first, and then a prediction sub-model matching the client class type in a preset target user prediction model may be invoked to determine whether the user object is a target user who potentially receives the pushed service data according to the feature data of the user object; the preset target user prediction model comprises a first prediction submodel which is established based on horizontal federal learning according to first sample data of a first data party and second sample data of a second data party, and a second prediction submodel which is established based on federal transfer learning according to the first sample data, the second sample data and the first prediction submodel; and under the condition that the user object is determined to be the target user, appropriate target service data is pushed to the user object, so that a better pushing effect can be obtained, and the pushing success rate is improved.

In an embodiment, the preset target user prediction model (which may be denoted as model a) called by the server may be specifically established by the first server and the second server in advance according to first sample data in the first data party and second sample data in the second data party respectively held by the first server and the second server, based on the horizontal federal learning and the federal migration.

In an embodiment, in implementation, for the first server side, the preset target user prediction model may be specifically trained in the following manner.

S1: the method comprises the steps that a first server responds to a first training request about a preset target user prediction model, and performs sample data fusion with a second server in a cooperative mode according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in sample users of a first passenger group type and a second positive sample user and a second negative sample user in sample users of a second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user;

s2: acquiring non-service characteristic data of a first positive sample user and non-service characteristic data of a first negative sample user from the first sample data to serve as first grouping sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data;

s3: training to obtain a first predictor model according to the first grouping sample data;

s4: obtaining a second predictor model (which can be marked as a model A2) through federal transfer learning training according to the second grouping of sample data and the first predictor model (which can be marked as a model A1);

s5: and combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model.

Through the embodiment, the first server can cooperate with the second server through the horizontal federal learning framework according to the protocol rule based on horizontal federal learning, and on the premise that the sample data held by the first server cannot be out of range, the full positive sample users are determined and marked from the full sample users held by one side of the first server; and dividing the full amount of sample users into sample users of a first passenger group type with complete characteristics and sample users of a second passenger group type with incomplete characteristics based on the passenger group types. Then, non-business characteristic data of a first passenger group type sample user with higher data quality can be obtained from the first sample data as first type training data; and training by using the first type of training data with higher data quality to obtain a first predictor model with higher precision corresponding to the first passenger group type. Meanwhile, non-business characteristic data of a second passenger group type sample user with poor data quality can be obtained from the first sample data and used as second training data; and the second type of training data with poor data quality is utilized, and the first predictor model with higher precision obtained by previous training is combined and used to introduce the data knowledge of the first type of training data, so that the influence of the characteristic irregularity in the second type of training data on model training is reduced, and the second predictor model with relatively higher precision is obtained. Therefore, the prediction model which has higher precision and better effect on the user objects of the first guest group type and the second guest group type at the same time can be obtained by training.

In an embodiment, the first training request may be specifically initiated by a first server, or may be initiated by a second server. The present specification is not limited to these.

In one embodiment, it is considered that in some cases, there may be data isolation between the first server and the second server, and the two parties cannot directly interact with each other to respectively hold the first sample data and the second sample data. Therefore, the horizontal federal learning framework can be utilized to perform safe sample data fusion according to the cooperation of the protocol rules based on the horizontal federal learning so as to break the limitation of data isolation and not to directly reveal the sample data held by the own party to the other party.

Through the data fusion, the first server can determine and mark a full number of positive sample users in the first sample data held by the own party (for example, preset marking information for indicating the positive sample users is set in the positive sample users); meanwhile, the first server can also divide the full sample data into two groups, namely a sample user of a first guest group type and a sample user of a second guest group type.

Further, for the sample users of the first guest group type, the first server may first determine a positive sample user from the sample users of the first guest group type by retrieving the tag information of the sample users of the first guest group type, and mark the positive sample user as the first positive sample user. And determining the rest sample users except the first positive sample user in the sample users of the first passenger group type as negative sample users, and recording as first negative sample users.

For the sample users of the second guest group type, the first server may first determine a positive sample user from the sample users of the second guest group type by retrieving the tag information of the sample users of the second guest group type, and record the positive sample user as a second positive sample user. And determining the rest sample users except the second positive sample user in the sample users of the second passenger group type as negative sample users, and recording as second negative sample users.

With the above embodiment, the first server and the second server may cooperate through a protocol rule based on horizontal federal learning to determine and identify a first positive sample user and a first negative sample user among sample users of a first guest group type among a total number of sample users held by the first server; meanwhile, a second positive sample user and a second negative sample user are determined and identified among the sample users of the second guest group type.

In one embodiment, for a sample user of a first guest group type, the first server may obtain, from the held first sample data, non-traffic class characteristic data of a first positive sample user and non-traffic class characteristic data of a first negative sample user as first packet sample data. Therefore, sample data with complete characteristics and high data quality can be screened out.

Meanwhile, for the sample users of the second guest group type, the first server may obtain, from the held first sample data, non-traffic class feature data of a second positive sample user and non-traffic class feature data of a second negative sample user as second packet sample data. Therefore, sample data with missing features and poor data quality can be stripped.

Therefore, the first server can accurately split the first component sample data and the second component sample data which are used for training different prediction submodels aiming at different customer group types from the held first sample data.

In an embodiment, the training to obtain the first predictor model according to the first packet of sample data may include the following steps.

S1: extracting a plurality of data from the non-business characteristic data of a first positive sample user in the first grouping sample data, and marking the data as first positive sample training data; extracting a plurality of data from the non-business class characteristic data of a first negative sample user in the first grouping sample data, and marking the data as first negative sample training data;

s2: combining the first positive sample training data and the first negative sample training data to obtain first class training data;

s3: and training by using the first type of training data to obtain a first predictor model.

Through the embodiment, the first server can independently use the first type of training data with complete split characteristics and high data quality from the first sample data to train to obtain the first predictor model with high precision.

In one embodiment, when the first server is specifically trained, an initial model based on logistic regression may be constructed first; and continuously training and adjusting the initial model by utilizing the first type of training data to obtain a first predictor model meeting the requirement.

In one embodiment, referring to fig. 3, the second predictor model obtained by the federal shift learning training according to the second packet sample data and the first predictor model may be implemented as follows.

S1: extracting a plurality of data from the non-business class characteristic data of a second positive sample user in the second grouping sample data, and marking the data as second positive sample training data; extracting a plurality of data from the non-business class characteristic data of the second negative sample user in the second grouping sample data, and marking the data as second negative sample training data;

s2: combining the second positive sample training data and the second negative sample training data to obtain second type training data;

s3: calling a preset first predictor model to process the second type of training data to obtain a corresponding predicted value;

s4: combining the second type of training data with the corresponding predicted value to obtain combined second type of training data;

s5: and training by using the combined second type of training data to obtain a second predictor model.

By the embodiment, when the first server trains the second predictor model, the first predictor model with higher precision obtained by previous training is used for processing second training data with incomplete characteristics and poor data quality to obtain a corresponding predicted value; combining the second type of training data with the corresponding predicted values to introduce the data knowledge of the first type of training data with higher data quality to obtain the combined second type of training data with better training effect; and then the combined second type training data can be used for replacing the original second type training data with poor data quality to carry out model training, so that the influence of the second type training data with incomplete characteristics and poor data quality on model training on model precision can be effectively reduced, and a second predictor model with relatively high precision is obtained.

In one embodiment, specifically, as shown in fig. 3, the second type of training data is input into the trained first predictor model, and the first predictor model is operated to output the corresponding predicted value.

In one embodiment, the second type of training data originally contains missing and irregular features, and the first predictor model is trained by using training data with complete features, so the first predictor model cannot directly process the second type of training data. Before calling a preset first predictor model to process the second class of training data, the method further comprises the following steps: and preprocessing the second class of training data.

In specific implementation, the first type of training data and the second type of training data can be compared in characteristics, and the missing characteristics of the second type of training data relative to the first type of training data are determined; and adding data bits with missing features in the second type of training data, and setting the numerical values of the data bits with the missing features to zero to obtain the preprocessed second type of training data. And then, a preset first predictor model can be called to process the preprocessed second-class training data to obtain a corresponding predicted value.

In one embodiment, in the specific combination, the obtained predicted value may be used as a new feature to be combined with the original feature in the second type of training data, so as to expand the original feature space with missing and incomplete features in the second type of training data, and obtain the combined second type of training data with relatively richer features and relatively better training effect.

Specifically, for example, taking a certain piece of training data Xi in the second class of training data as an example, the training data originally includes only 3 features, which are respectively marked as a first feature, a second feature, and a fourth feature, and the corresponding data values are x1, x2, and x4, respectively. Accordingly, Xi may be represented as [ x1, x2, x4 ]. And comparing the second type of training data with the first type of training data with complete characteristics to determine the missing characteristics in the second type of training data as a third characteristic and a fifth characteristic. In this case, the training data Xi may be preprocessed to obtain preprocessed training data, which is denoted as Xi' as [ x1, x2,0, x4,0 ]. And inputting the preprocessed training data Xi' into a first predictor model, and calling the first predictor model to process the data to obtain a corresponding predicted value, which is marked as Px. And combining the predicted values with the original second class training data Xi to obtain combined second class training data, wherein the combined second class training data is marked as Xi and is represented as [ x1, x2, x4 and Px ]. Therefore, data knowledge of the first class of training data is introduced by using the first predictor model, and combined second class of training data with better training effect is obtained.

In an embodiment, when the second type of training data is combined with the corresponding predicted value, the association weight related to the predicted value may also be determined according to the degree of feature loss of the second type of training data and the degree of influence of the original feature in the second type of training data on the service data received by the user. And combining the original features in the second type of training data with the product of the associated weight and the predicted value, thereby obtaining the second type of training data with better training effect.

When the association weight of the predicted value is specifically determined, if the feature missing degree of the second type of training data is more serious and the influence degree of the original features in the second type of training data on the service data received by the user is smaller, the value of the association weight of the predicted value can be set to be relatively larger. Conversely, if the degree of feature missing of the second type of training data is more slight, and the degree of influence of the original features in the second type of training data on the service data received by the user is larger, the value of the association weight of the predicted value may be set to be relatively smaller.

In an embodiment, the preset user portrait prediction model (which may be denoted as model B) invoked by the server may be specifically established by the first server and the second server in advance based on the vertical federal learning according to first sample data in the first data party and second sample data in the second data party respectively held by the first server and the second server.

In one embodiment, the predetermined user profile prediction model may be trained on the first server side in the following manner.

S1: the first server responds to a second training request about a preset user portrait prediction model, and cooperates with the second server to perform sample data fusion according to a protocol rule based on longitudinal federal learning to obtain third training data carrying a preset portrait label; wherein the third training data comprises non-traffic class feature data of the positive sample user; the preset portrait label is determined according to the business class characteristic data of the user who just samples;

s2: and training to obtain a preset user portrait prediction model by using the third training data carrying the preset portrait label.

Through the embodiment, the first server can cooperate with the second server by utilizing a longitudinal federal learning frame according to protocol rules based on longitudinal federal learning, the second server determines the preset portrait label of the positive sample user by utilizing the held business characteristic data, and then the portrait label is fused with the non-business characteristic data of the positive sample user held by the first server to obtain third training data of the preset portrait label carrying data knowledge containing the business characteristic data; and then, a preset user portrait prediction model which can predict and determine portrait labels of users about business data more accurately is obtained through training by using the third training data.

In an embodiment, the second training request may be specifically initiated by the first server, or may be initiated by the second server. The present specification is not limited to these.

In one embodiment, in consideration of the possible data isolation between the first server and the second server in some scenarios, two parties cannot directly interact with each other to respectively hold the first sample data and the second sample data. Therefore, the longitudinal federal learning framework can be utilized to perform safe sample data fusion according to the cooperation of the protocol rules based on the longitudinal federal learning so as to break the limitation of data isolation and not directly reveal the data held by the own party to the other party.

Through the data fusion, the second server can determine preset portrait tags (such as payment deadline tendency tags, premium tendency tags and the like) of the positive sample user by using service class feature data in second sample data held by the own party; meanwhile, the first server can obtain the non-business characteristic data of the positive sample user from the held first sample data; and then the first server and the second server can combine the preset portrait label and the non-business characteristic data corresponding to the same positive sample user through cooperation to obtain the third training data carrying the preset portrait label.

In one embodiment, in the concrete integration, the first server and the second server can also combine three data, namely a preset portrait label corresponding to the same positive sample user, non-business characteristic data and business characteristic data, through cooperation to obtain relatively more complete and rich third training data carrying the preset portrait label, so that a more accurate preset user portrait prediction model can be trained.

In an embodiment, when the preset user portrait prediction model is specifically trained, the initial model may be learned and trained by using the third training data carrying the preset portrait label, so as to obtain the preset user portrait prediction model.

In one embodiment, the positive sample user training the preset user portrait prediction model may be a sample user that is determined in advance by using the preset target user prediction model and marked as a target user. Therefore, the trained preset target user prediction model and the preset user portrait prediction model have stronger associativity.

In one embodiment, the predetermined user portrait prediction model may specifically include one portrait prediction submodel, or may include a plurality of portrait prediction submodels, where different portrait prediction submodels are used to predict different portrait tags.

By the embodiment, a plurality of different portrait labels of the user object can be predicted simultaneously by using the preset user portrait prediction model; furthermore, according to the different portrait labels, the requirement tendency and the personal preference of the user object can be more finely depicted, so that a target pushing rule with higher matching degree and better effect can be generated for the user object.

In one embodiment, in the case that the preset user portrait prediction model includes a plurality of portrait prediction submodels, the second server and the first server may generate a plurality of different preset portrait labels according to different business class feature data of the held positive sample user during data fusion according to a protocol rule based on longitudinal federal learning. Thus, the third training data obtained through data fusion finally can contain multiple groups of third training data. Wherein, the third training data of the same group carries the same kind of preset portrait label.

Correspondingly, during training, a plurality of initial models can be trained by utilizing the plurality of groups of third training data respectively to obtain a plurality of portrait prediction submodels respectively corresponding to different portrait labels; and combining the plurality of portrait prediction submodels to obtain a preset user portrait prediction model.

In one embodiment, taking an insurance business marketing scenario as an example, the target business data may specifically include insurance business products and/or insurance business services suitable for the user object; correspondingly, the target pushing rule may specifically include an insurance business marketing scheme.

In the insurance business marketing scene, whether the current user object to be marketed belongs to a potential target user who can accept the marketed insurance business can be determined by using a preset target user prediction model; under the condition that the current user object belongs to the target user, predicting a portrait label of the user object related to the insurance business by using a preset user portrait prediction model, and further determining the demand tendency and personal preference of the current user object for the insurance business according to the portrait label; further, an insurance business marketing scheme which is matched with the current user object and has higher acceptance of the current user object can be generated by combining the personalized demand tendency and the personal preference; and further, according to the insurance business marketing scheme, the appropriate marketing treatment of insurance business products and/or insurance business services can be accurately carried out on the current user object. Therefore, the marketing success rate can be effectively improved, meanwhile, the appropriate insurance business can be recommended to the user accurately according to the individual demand tendency and preference of the user, and the service experience of the user is improved.

In an embodiment, taking an insurance business marketing scenario as an example, the non-business class feature data may specifically include at least one of the following: monthly income, monthly consumption amount, deposit balance, etc.; the service class feature data may specifically include at least one of the following: gift identification, premium, etc. Of course, the above listed non-service class feature data and service class feature data are only schematic illustrations. In specific implementation, the non-service characteristic data and the service characteristic data may further include other types of data according to a specific application scenario and a processing requirement. The present specification is not limited to these.

By acquiring and utilizing the diversified business characteristic data and the non-business characteristic data, a preset target user prediction model and a preset user portrait prediction model which have higher precision and better effect and aim at an insurance business marketing scene can be trained.

In one embodiment, in the insurance business marketing scenario, the first data party may be a bank or a bank head office. Accordingly, the second data party may specifically be an associated insurance carrier.

In one embodiment, the first guest group type may include a bank-originating payroll group, and the second guest group type may include a non-bank-originating payroll group.

Through this embodiment, distinguish the guest group according to whether for bank's proxy payroll guest group to can accurately follow the full sample user who holds in bank or bank split out the sample user of the complete first guest group type of characteristic, and the sample user of the incomplete second guest group type of characteristic.

In an embodiment, taking an insurance business marketing scenario as an example, the portrait label may specifically include at least one of the following: payment due trend labels, premium trend labels, and the like. Of course, the above-listed image labels are merely illustrative. In particular, the portrait tags may also include other types of tag data, depending on the particular application scenario and processing requirements. The present specification is not limited to these.

By utilizing the diversified portrait label, the individualized demand tendency and the individual preference of the user object about the insurance business can be more finely and comprehensively depicted in the insurance business marketing scene, so that the user object can be more accurately and properly marketed for the insurance business.

As can be seen from the above, in the method for pushing service data provided in this specification, when pushing service data to a user object, a guest group type of the user object may be determined first, and then a prediction sub-model matching the guest group type in a preset target user prediction model may be invoked to determine whether the user object is a target user who potentially receives the pushed service data according to feature data of the user object; the preset target user prediction model comprises a first prediction submodel which is established based on horizontal federal learning according to first sample data of a first data party and second sample data of a second data party, and a second prediction submodel which is established based on federal transfer learning according to the first sample data, the second sample data and the first prediction submodel; and under the condition that the user object is determined to be the target user, appropriate target service data is pushed to the user object, so that a better pushing effect can be obtained, and the pushing success rate is improved. When a preset target user prediction model is trained, distinguishing a first passenger group type with complete characteristics and a second passenger group type with incomplete characteristics, enabling a first server holding first sample data in a first data party and a second server holding second sample data in a second data party to perform data fusion through cooperation according to a protocol rule based on horizontal federal learning, and separating to obtain first training data with complete characteristics and second training data with incomplete characteristics; further, a first predictor model with higher precision can be obtained by training with first type of training data with complete characteristics; and according to the second type of training data, the influence of the characteristic irregularity in the second type of training data on model training is reduced by combining the first predictor model and federal transfer learning, and the second predictor model with relatively high precision is obtained, so that the prediction model with relatively high precision and relatively good effect on the user objects of the first passenger group type and the second passenger group type can be obtained through training. Further acquiring and determining an image label of the user object according to the service class characteristic data of the user object under the condition that the user object is determined to be a target user which can receive the pushed service data; analyzing the personalized demand tendency and personal preference of the user object according to the portrait label of the user object, and generating a target pushing rule suitable for the user object; and according to the target pushing rule, the appropriate target service data is accurately pushed to the user object, so that the pushing success rate can be further improved.

Referring to fig. 4, an embodiment of the present disclosure further provides a method for training a model to obtain a predetermined target user prediction model meeting requirements. The method can be applied to a first server deployed on the first data side. When implemented, the following may be included.

S401: responding to a first training request about a preset target user prediction model, and performing sample data fusion in cooperation with a second server according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in the sample users of the first passenger group type and a second positive sample user and a second negative sample user in the sample users of the second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user;

s402: acquiring non-service characteristic data of a first positive sample user and non-service characteristic data of a first negative sample user from the first sample data to serve as first grouping sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data;

s403: training to obtain a first predictor model according to the first grouping sample data;

s404: obtaining a second predictor model through federal transfer learning training according to the second group of sample data and the first predictor model;

s405: and combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model.

In this embodiment, when a preset target user prediction model is trained, a first passenger group type with complete features and a second passenger group type with incomplete features are distinguished, so that a first server holding first sample data in a first data party and a second server holding second sample data in a second data party perform data fusion through cooperation according to a protocol rule based on horizontal federal learning, and first training data with complete features and second training data with incomplete features are obtained through separation; further, a first predictor model with higher precision can be obtained by training with first type of training data with complete characteristics; and according to the second type of training data, the influence of the characteristic irregularity in the second type of training data on model training is reduced by combining the first predictor model and federal transfer learning, and the second predictor model with relatively high precision is obtained, so that the prediction model with relatively high precision and relatively good effect on the user objects of the first passenger group type and the second passenger group type can be obtained through training.

Embodiments of the present specification further provide a server, including a processor and a memory for storing processor-executable instructions, where the processor, when implemented, may perform the following steps according to the instructions: acquiring identification information of a user object and characteristic data of the user object; wherein the feature data at least comprises non-traffic class feature data; determining the guest group type of the user object according to the identification information of the user object; calling a prediction sub-model matched with the guest group type of the user object in a preset target user prediction model to process the characteristic data of the user object so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning; and under the condition that the user object is determined to be the target user, pushing appropriate target business data to the user object.

In order to more accurately complete the above instructions, referring to fig. 5, another specific server is provided in the embodiments of the present specification, wherein the server includes a network communication port 501, a processor 502 and a memory 503, and the above structures are connected by an internal cable, so that the structures can perform specific data interaction.

The network communication port 501 may be specifically configured to obtain identification information of a user object and feature data of the user object; wherein the feature data at least comprises non-traffic class feature data.

The processor 502 may be specifically configured to determine a guest group type of the user object according to the identification information of the user object; calling a prediction sub-model matched with the guest group type of the user object in a preset target user prediction model to process the characteristic data of the user object so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning; and under the condition that the user object is determined to be the target user, pushing appropriate target business data to the user object.

The memory 503 may be specifically configured to store a corresponding instruction program.

In this embodiment, the network communication port 501 may be a virtual port that is bound to different communication protocols, so that different data can be sent or received. For example, the network communication port may be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for mail data communication. In addition, the network communication port can also be a communication interface or a communication chip of an entity. For example, it may be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it may also be a bluetooth chip.

In this embodiment, the processor 502 may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The description is not intended to be limiting.

In this embodiment, the memory 503 may include multiple layers, and in a digital system, the memory may be any memory as long as binary data can be stored; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

Embodiments of the present specification further provide a server, including a processor and a memory for storing processor-executable instructions, where the processor, when implemented, may perform the following steps according to the instructions: responding to a first training request about a preset target user prediction model, and performing sample data fusion in cooperation with a second server according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in the sample users of the first passenger group type and a second positive sample user and a second negative sample user in the sample users of the second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user; acquiring non-service characteristic data of a first positive sample user and non-service characteristic data of a first negative sample user from the first sample data to serve as first grouping sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data; training to obtain a first predictor model according to the first grouping sample data; obtaining a second predictor model through federal transfer learning training according to the second group of sample data and the first predictor model; and combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model.

An embodiment of the present specification further provides a computer storage medium based on the above service data pushing method, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium implements: acquiring identification information of a user object and characteristic data of the user object; wherein the feature data at least comprises non-traffic class feature data; determining the guest group type of the user object according to the identification information of the user object; calling a prediction sub-model matched with the guest group type of the user object in a preset target user prediction model to process the characteristic data of the user object so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning; and under the condition that the user object is determined to be the target user, pushing appropriate target business data to the user object.

In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

The present specification further provides a computer storage medium based on the training method of the model, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer program instructions implement: responding to a first training request about a preset target user prediction model, and performing sample data fusion in cooperation with a second server according to a protocol rule based on horizontal federal learning so as to determine a first positive sample user and a first negative sample user in the sample users of the first passenger group type and a second positive sample user and a second negative sample user in the sample users of the second passenger group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user; acquiring non-service characteristic data of a first positive sample user and non-service characteristic data of a first negative sample user from the first sample data to serve as first grouping sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data; training to obtain a first predictor model according to the first grouping sample data; obtaining a second predictor model through federal transfer learning training according to the second group of sample data and the first predictor model; and combining the first prediction submodel and the second prediction submodel to obtain a preset target user prediction model.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.

Referring to fig. 6, in a software level, an embodiment of the present specification further provides a service data pushing device, which may specifically include the following structural modules.

The obtaining module 601 may be specifically configured to obtain identification information of a user object and feature data of the user object; wherein the feature data at least comprises non-traffic class feature data;

the determining module 602 may be specifically configured to determine, according to the identification information of the user object, a guest group type of the user object;

the invoking module 603 may be specifically configured to invoke a prediction sub-model, which is matched with the guest group type of the user object, in a preset target user prediction model to process feature data of the user object, so as to determine whether the user object is a target user; the preset target user prediction model at least comprises a first prediction submodel and a second prediction submodel; the first prediction submodel is established in advance based on transverse federal learning according to first sample data in a first data party and second sample data in a second data party; the second predictor model is established in advance according to the first sample data and the second sample data and combined with the data knowledge of the first predictor model based on federal transfer learning;

the pushing module 604 may be specifically configured to, in a case that it is determined that the user object is a target user, push appropriate target service data to the user object.

It should be noted that, the units, devices, modules, etc. illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. It is to be understood that, in implementing the present specification, functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules or sub-units, or the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Therefore, the service data pushing device provided by the embodiment of the present specification can accurately determine whether the user object is the target user, and push appropriate target service data to the user object under the condition that the user object is determined to be the target user, so that a better pushing effect can be obtained, and the pushing success rate is improved.

Referring to fig. 7, on a software level, an embodiment of the present specification further provides a model training apparatus, which may specifically include the following structural modules.

The fusion module 701 may be specifically configured to respond to a first training request regarding a preset target user prediction model, and perform sample data fusion in cooperation with a second server according to a protocol rule based on horizontal federal learning, so as to determine a first positive sample user and a first negative sample user among sample users of a first guest group type, and a second positive sample user and a second negative sample user among sample users of a second guest group type; the first server is deployed at one side of a first data party, the held first sample data at least comprises non-business characteristic data of a full amount of sample users, and the full amount of sample users comprise sample users of a first customer group type and sample users of a second customer group type; the second server is a server deployed at one side of a second data party, and second sample data held by the second server at least comprises service class characteristic data of a full positive sample user;

an obtaining module 702, configured to obtain, from the first sample data, non-service characteristic data of a first positive sample user and non-service characteristic data of a first negative sample user as first packet sample data; acquiring non-service characteristic data of a second positive sample user and non-service characteristic data of a second negative sample user from the first sample data to serve as second grouping sample data;

the first training module 703 may be specifically configured to train to obtain a first predictor model according to the first packet of sample data;

a second training module 704, which may be specifically configured to obtain a second predictor model through federal transfer learning training according to the second packet of sample data and the first predictor model;

the combining module 705 may be specifically configured to combine the first predictor model and the second predictor model to obtain a preset target user prediction model.

As can be seen from the above, the training device based on the model provided in the embodiment of the present specification can train to obtain a prediction model having higher precision and better effect on both the user objects of the first guest group type and the second guest group type.

In a specific scenario example, the above method provided in this specification may be applied to assist an insurance subsidiary under a bank in accurate marketing of insurance business. For a specific implementation process, the following can be referred to.

In the present scenario example, it is noted that insurance marketing is an important part of the banking marketing business. The insurance is of various types, and may include risk-transferred insurance and wealth-added insurance. Further, the risk-transferring insurance may include life insurance, health insurance, accident insurance, and the like. And each type of branch may in turn contain numerous sub-branches. Therefore, the insurance marketing difficulty is high, and an intelligent model is needed to assist insurance agents to accurately mine potential insurance purchasing customers.

Many banks will generally set up related insurance companies, and the insurance marketing data of the banks has the following problems: 1. and (5) isolating data. Due to the limitation of the supervision policy, the data of the insurance subsidiary company and the bank are not circulated, so that the insurance marketing modeling sample is separated and can be modeled only based on the data of each party. 2. The images of the non-generation wage client group (corresponding to the second client group type) are imperfect, the proportion of the images in the total client group is large, and the marketing model effect on the client group is poor. The non-client payroll group has a difference in feature distribution compared with the client payroll group (corresponding to the first client group type), and the feature missing data ratio is high. Generally, the images of the client groups of the agency wages held by the bank are perfect, and the marketing model effect of the client groups is good.

In this scenario example, before implementation, the training method of the model provided in this specification may be applied to joint modeling by using data held by banks and insurance companies through federal learning (including horizontal federal learning and federal migration learning).

The federal learning specifically means that each participant can perform joint modeling by means of data of other parties in the process of performing machine learning. All parties do not need to share original data, namely under the condition that the data are not local, data combined training is carried out, and a shared machine learning model is established.

Federated transfer learning may specifically refer to a joint modeling technique that combines federated learning and transfer learning techniques with less overlap of both users and features.

The horizontal federal learning specifically means that under the condition that sample features of a data set are overlapped more and sample IDs are overlapped less, the data are aligned according to feature dimensions by adopting the horizontal federal, and the data with the same sample features and not identical users are taken out for training.

In the scenario example, the above problems of the insurance precision marketing modeling in the bank + insurance mode are solved based on the federal migration learning technology. The bank and the insurance subsidiary company which limit data isolation due to the supervision policy realize the safe fusion of data, and the effect of optimizing the whole marketing model by utilizing the bank development payroll group model with perfect insurance image is achieved. In addition, the insurance sample size and feature dimension are also expanded. The client mining accuracy of the insurance marketing model of the large bank non-issuing client group is obviously improved.

In specific implementation, the data isolation exists in consideration of the fact that insurance marketing data of both the bank and the insurance company are not circulated. The machine learning model training has the first premise that the sample data is sufficient and subject to independent equal distribution. For sample data, the more core features are generally required, the more complete the portrait, and the better the modeling effect. The high-value user can be effectively mined by the method that the generation wage client group with better modeling effect accounts for a smaller proportion of the total bank client group, but the portrait features are more comprehensive and comprise the core features of purchasing personal portrait, such as wage, income, academic calendar, professional information and the like (for example, more complete non-business feature data). The non-generation wage group has extremely high feature missing ratio, and particularly has larger missing ratio of key features of purchase insurance.

Specific data cases can be seen in fig. 8. Therefore, when two types of passenger groups are mixed for modeling, the sample distribution is deviated, and the model effect of modeling based on the data is greatly influenced.

In the example of the scenario, during the concrete modeling, the data of the bank and the insurance sub-company may be safely fused through the federal learning technology, an insurance client mining model (corresponding to the first prediction sub-model) of the sponsor generation group is trained, and an insurance hidden client list of the sponsor generation group is obtained by using the model.

And then training an insurance client mining model (corresponding to a second prediction submodel) of the non-generation client group by using the non-generation payroll client group based on the federal migration technology, and obtaining an insurance latent client list of the client group by using the model, so that the knowledge of the generation payroll client group can be migrated to the non-generation payroll client group.

A specific training process can be seen in fig. 9. The training process comprises 1, respectively carrying out data preparation work by a bank (or a head office) and an insurance subsidiary company; 2. the method comprises the steps of implementing safety fusion on sample data of banks and insurance companies based on a federal learning technology, and training a federal model of an agency payroll group, namely an 'insurance client mining model A1'; 3. training a federal model of a non-generational payroll group based on federal transfer learning, namely an 'insurance customer mining model A2'; 4. and generating a list of the hidden passengers. When the specific model is applied, the insurance agent can distinguish the types of the client groups, separately use the model, use A1 for the client group of the agent payroll and use A2 for the client group of the agent payroll to predict. Specifically, the following steps may be included.

Step 1: the work and insurance subsidiary perform data preparation work, respectively.

Step 2: and (3) performing safe fusion on sample data of the head office and the insurance subsidiary company based on a federal learning technology, training a federal model of an agent payroll group, namely an 'insurance client mining model A1', and predicting and generating an agent payroll group insurance hidden client list by using the model.

In the step, according to the data classification condition, the flow is based on the traditional horizontal federal technology and bank characteristics, positive samples of both organizations are superposed, and samples of the sponsor and sponsor groups are selected for modeling.

And step 3: and training a federal model of a non-generation wage passenger group, namely an 'insurance customer mining model A2', by using federal transfer learning based on the model in the second step, and predicting and generating an insurance hidden passenger list by using the model.

Referring to fig. 8, after data preparation, the data distribution difference between the bank and its insurance company is still large. The total number of customers held by the bank is divided into a sponsor payroll group and a non-sponsor payroll group. In addition, the method has the following characteristics: the insurance purchase channel is divided into a self-selling channel (e.g., self-owned channel) and a banking channel (e.g., shared channel). The insurance sub-company holds the full insurance purchase positive sample, including the self-marketing positive sample and the silver insurance sample. The customers of the insurance carrier are typically customers of a bank, i.e. the customers of the insurance carrier typically use the bank account. But subject to regulatory policy, banks have no positive sample of insurance carrier's self-selling channels. Specifically, as shown in fig. 8, the guest group (i) represents a customer who purchases insurance of the subsidiary company in the head office, and the guest group (i) corresponds to the guest group (ii) of the subsidiary insurance company. Both the guest group i and the guest group ii are positive samples. The client group c represents the insurance purchasing client of the insurance company from the channel-selling company, and is a positive sample on the insurance company side. The guest group (r) corresponds to the guest group (r) at the head office, and the bank does not know the purchase condition of the guest group (r), so the guest group (r) is regarded as a negative sample at the bank side. The bank also contains other massive users, namely a guest group. The guest group (r) is contained in the guest group (c).

Specifically, when the non-issuing-customer-group insurance customer mining model a2 is constructed, as shown in fig. 10, the method includes the following steps:

step S01: acquiring non-proxy wage sample data;

step S02: acquiring a surreptitious payroll group insurance marketing model A1;

step S03: predicting a non-generation passenger group by using the model A1 to obtain a passenger probability Y (for example, a predicted value);

step S04: adding the above passenger probability Y as a new feature into a non-generative payroll model feature space to obtain a combined feature (for example, combined second-class training data), wherein the data processing logic is the same as that of the generative payroll model A1, and a federal transfer learning technology is applied and realized;

step S05: based on the features merged as above, the non-surrogate model a2 was trained using non-surrogate guest population samples.

Through the scene example, the insurance precision marketing modeling under the bank and insurance mode based on the federal transfer learning is realized. The method realizes federal transfer learning in the field of insurance marketing, so that joint modeling of banks and insurance companies which cannot be realized due to data supervision authority limit becomes possible; and the high-value portrait information of the bank development wage client group is migrated to the large-cardinal-number bank client group, so that the accuracy of the overall marketing of the bank insurance is effectively improved, the marketing cost of insurance agents is saved, and a marketing model with a better effect is obtained.

Although the present specification provides method steps as described in the examples or flowcharts, additional or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. The terms first, second, etc. are used to denote names, but not any particular order.

Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

From the above description of the embodiments, it is clear to those skilled in the art that the present specification can be implemented by software plus necessary general hardware platform. With this understanding, the technical solutions in the present specification may be essentially embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments in the present specification.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.

Claims

1. A method for pushing service data is characterized by comprising the following steps:

2. The method of claim 1, wherein the guest group type comprises: a first fully featured guest group type and a second poorly featured guest group type.

3. The method of claim 2, wherein the first predictor model matches a first guest group type and the second predictor model matches a second guest group type.

4. The method of claim 3, wherein the predetermined target user prediction model is established as follows:

5. The method of claim 4, wherein training a first predictor model based on the first packet of sample data comprises:

6. The method of claim 4, wherein deriving a second predictor model from the second packet of sample data and the first predictor model through federated migration learning training comprises:

7. The method of claim 2, wherein the first guest group type comprises a bank-originating payroll group and the second guest group type comprises a non-bank-originating payroll group.

8. The method of claim 1, wherein in the case that the user object is determined to be a target user, the method further comprises:

9. The method of claim 8, wherein determining a portrait label for a user object based on business class characterization data for the user object comprises:

10. The method according to claim 8, wherein the target business data comprises insurance business products and/or insurance business services suitable for the user object; correspondingly, the target pushing rule comprises an insurance business marketing scheme.

11. The method of claim 8, wherein the non-traffic class characteristic data comprises at least one of: monthly income, monthly consumption amount, deposit balance; the service class characteristic data comprises at least one of: gift identification, premium, and premium.

12. A method for training a model, applied to a first server deployed on a first data side, includes:

13. A device for pushing service data, comprising:

14. A training device of a model, applied to a first server deployed on a first data side, comprises:

15. A server comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 11.