CN116385042A

CN116385042A - Information output method and device, electronic equipment and computer readable storage medium

Info

Publication number: CN116385042A
Application number: CN202310356251.2A
Authority: CN
Inventors: 张娇; 范鑫禹; 吉帅
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-04-04
Filing date: 2023-04-04
Publication date: 2023-07-04

Abstract

The disclosure provides an information output method and device, electronic equipment and a computer readable storage medium, which can be applied to the technical field of big data, the technical field of artificial intelligence and the technical field of finance. The information output method comprises the following steps: constructing a cooperative client global feature matrix and an uncooperative client basic feature matrix; inputting the global feature matrix of the cooperated clients into a first preset classification model, outputting the probability that each cooperated client belongs to a plurality of different tracks, and outputting first track information for representing each first target track to which each cooperated client belongs; inputting the basic feature matrix of the uncooperative clients into a second preset classification model, outputting the probability that each uncooperative client belongs to a plurality of different tracks, and outputting second track information for representing each second target track to which each uncooperative client belongs; a potential customer is determined from the at least one uncooperative customer based on the first track information and the second track information, and potential customer information is output.

Description

Information output method and device, electronic equipment and computer readable storage medium

Technical Field

The present disclosure relates to the field of big data technology and the field of artificial intelligence technology, and in particular, to an information output method, apparatus, device, medium, and program product.

Background

At present, the development and the promotion of digital economy become the key content of more and more enterprises, the development trend of the science and technology in the financial industry can be more effectively responded, and the comprehensive digital transformation developed by the integration of the emerging technology and the business is an important driving force for developing the industrial digitization.

Under the conditions of potential customer mining and product recommendation, the data resource is used as a key element, so that assistance can be provided for service popularization. In the product popularization process, at present, business personnel still mainly adopt an empirical method, and certain aggregation is presented on the selection of products for certain clients, such as medium-sized public clients, and the difficulty in the aspects of discovery of potential clients and potential requirement mining of cooperative clients is high through a traditional method, so that the efficiency is low and the referenceability of recommended results is low.

Disclosure of Invention

In view of the foregoing, the present disclosure provides an information output method, apparatus, device, medium, and program product.

In one aspect of the present disclosure, there is provided an information output method including:

Constructing a cooperative client global feature matrix and an uncooperative client basic feature matrix, wherein the cooperative client global feature matrix is used for representing first basic information, first risk information and signing conditions of at least one cooperative client aiming at target class products of at least one cooperative client, and the uncooperative client basic feature matrix is used for representing second basic information and second risk information of at least one uncooperative client;

inputting the global feature matrix of the cooperated clients into a first preset classification model, outputting the probability that each cooperated client belongs to a plurality of different tracks, so that according to the probability that each cooperated client belongs to a plurality of different tracks, outputting first track information for representing each first target track to which each cooperated client belongs;

inputting the basic feature matrix of the uncooperative clients into a second preset classification model, outputting the probability that each uncooperative client belongs to a plurality of different tracks, so that according to the probability that each uncooperative client belongs to a plurality of different tracks, outputting second track information for representing each second target track to which each uncooperative client belongs;

a potential customer is determined from the at least one uncooperative customer based on the first track information and the second track information, and potential customer information is output.

According to an embodiment of the present disclosure, determining potential customers from at least one uncooperative customer based on the first track information and the second track information includes:

determining a plurality of candidate tracks according to the probability that each cooperated client belongs to the first target track;

non-cooperative clients belonging to the candidate track are determined as potential clients based on the second track information.

According to an embodiment of the present disclosure, the above method further includes:

determining a second target track to which potential clients in the uncooperative clients belong as an associated track according to the second track information, and outputting the associated track information;

associating the associated track information with the first track information, determining the affiliated clients affiliated with the associated track as affiliated associated clients;

and determining the products signed by the cooperated associated clients as target recommended products to be recommended to the non-cooperated clients.

According to an embodiment of the present disclosure, wherein constructing the collaborative client global feature matrix and the non-collaborative client basic feature matrix includes:

acquiring cooperative client reference information, non-cooperative client reference information and basic product information of a plurality of products, wherein the cooperative client reference information comprises first basic information, first risk information, contracted product identifiers and contracted product quantity of at least one cooperative client, the non-cooperative client reference information comprises second basic information and second risk information of at least one non-cooperative client, and the basic product information at least comprises product categories;

Constructing a basic feature matrix of the uncooperative client according to the second basic information and the second risk information of at least one uncooperative client;

and constructing a cooperative client global feature matrix according to the first basic information, the first risk information, the contracted product identification, the contracted product quantity and the product categories of the products of at least one cooperative client.

According to an embodiment of the present disclosure, constructing a collaborative customer global feature matrix according to first basic information, first risk information, contracted product identification, contracted product quantity, product categories of a plurality of products of at least one collaborative customer includes:

constructing a cooperative client basic feature matrix according to the first basic information and the first risk information of at least one cooperative client;

determining a target product identifier corresponding to a target category product according to the contracted product identifier of at least one cooperated customer and the product categories of the plurality of products;

determining the contracted number of at least one cooperated customer aiming at the target class product according to the target product identifier corresponding to the target class product and the contracted product identifier and the contracted product number of at least one cooperated customer;

And constructing a cooperative client global feature matrix according to the cooperative client basic feature matrix and the subscription quantity of at least one cooperative client aiming at the target class product.

According to an embodiment of the present disclosure, wherein:

the second predetermined classification model is trained using target training sample data comprising a matrix of cooperative customer base characteristics and probabilities that each of the cooperative customers belong to a plurality of different tracks.

According to an embodiment of the present disclosure, wherein:

the first predetermined classification model and the second predetermined classification model employ a multi-classification model.

Another aspect of the present disclosure provides an information output apparatus including:

the construction module is used for constructing a cooperative client global feature matrix and an uncooperative client basic feature matrix, wherein the cooperative client global feature matrix is used for representing first basic information, first risk information and signing conditions of at least one cooperative client aiming at a target class product, and the uncooperative client basic feature matrix is used for representing second basic information and second risk information of at least one uncooperative client;

the first classification module is used for inputting the global feature matrix of the cooperated clients into a first preset classification model, outputting the probability that each cooperated client belongs to a plurality of different tracks, so that according to the probability that each cooperated client belongs to a plurality of different tracks, outputting first track information for representing each first target track to which each cooperated client belongs;

The second classification module is used for inputting the basic feature matrix of the non-cooperative clients into a second preset classification model, outputting the probability that each non-cooperative client belongs to a plurality of different tracks, so that according to the probability that each non-cooperative client belongs to a plurality of different tracks, outputting second track information for representing each non-cooperative client belongs to a second target track;

and the output module is used for determining potential clients from at least one uncooperative client according to the first track information and the second track information and outputting the potential client information.

Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the information output method described above.

Another aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described information output method.

Another aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above-described information output method.

According to the embodiment of the disclosure, the method for outputting information automatically performs operations of data processing and information outputting through a computer, and specifically comprises the steps of constructing a global feature matrix of a cooperated client and a basic feature matrix of an uncooked client, classifying the cooperated client and the uncooked client through a classification model, and determining potential clients through associating track information between the two types of clients, so that the potential clients are determined by mining internal relations between data information of the cooperated client and data information of the uncooked client, labor is relieved, working efficiency is improved, and workflow of manually screening the potential clients is simplified to a certain extent. Meanwhile, the cooperative customer global feature matrix and the non-cooperative customer basic feature matrix constructed by the method integrate multidimensional data information, improve the multiplexing value of historical service data and reduce service risks caused by incomplete information. And the model outputs a classification result based on the objective characteristics of the data through the classification information of the cooperated clients and the non-cooperated clients output by the model, and the classification result is more objective and accurate compared with manual classification. Further, through the association classification of the first track information and the second track information, the internal connection between the data information of the cooperated clients and the data information of the non-cooperated clients is mined, so that potential clients are determined, the purpose of recommending the potential clients is achieved, the generated recommending result is more objective, the accuracy and the referenceability are better, the difficulty that the clients cannot be efficiently and accurately mined manually is overcome, the accuracy of business operation is improved, and potential clients and potential demands of the cooperated clients can be effectively mined.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of an information output method, apparatus, device, medium and program product according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a method of information output according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of an information output method according to another embodiment of the present disclosure;

fig. 4 schematically shows a block diagram of a structure of an information output apparatus according to an embodiment of the present disclosure;

fig. 5 schematically shows a block diagram of an information output apparatus according to another embodiment of the present disclosure;

fig. 6 schematically shows a block diagram of an electronic device adapted to implement the information output method according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc., of the data involved (including, but not limited to, user personal information) all comply with relevant legal regulations, are used for legal purposes, and do not violate well-known. In particular, necessary measures are taken for personal information of the user, illegal access to personal information data of the user is prevented, and personal information security, network security and national security of the user are maintained.

In embodiments of the present disclosure, the user's authorization or consent is obtained before the user's personal information is obtained or collected.

It should be noted that the information output method and apparatus, the electronic device and the computer readable storage medium according to the embodiments of the present disclosure may be applied to the big data technical field, the artificial intelligence technical field, and the financial technical field, and may also be applied to any field other than the big data technical field, the artificial intelligence technical field, and the financial technical field, and the application fields of the information output method and apparatus, the electronic device and the computer readable storage medium according to the embodiments of the present disclosure are not limited.

The embodiment of the disclosure provides an information output method, which comprises the following steps:

constructing a cooperative client global feature matrix and an uncooperative client basic feature matrix, wherein the cooperative client global feature matrix is used for representing first basic information, first risk information and signing conditions of at least one cooperative client aiming at target class products of at least one cooperative client, and the uncooperative client basic feature matrix is used for representing second basic information and second risk information of at least one uncooperative client; inputting the global feature matrix of the cooperated clients into a first preset classification model, outputting the probability that each cooperated client belongs to a plurality of different tracks, so that according to the probability that each cooperated client belongs to a plurality of different tracks, outputting first track information for representing each first target track to which each cooperated client belongs; inputting the basic feature matrix of the uncooperative clients into a second preset classification model, outputting the probability that each uncooperative client belongs to a plurality of different tracks, so that according to the probability that each uncooperative client belongs to a plurality of different tracks, outputting second track information for representing each second target track to which each uncooperative client belongs; a potential customer is determined from the at least one uncooperative customer based on the first track information and the second track information, and potential customer information is output.

Fig. 1 schematically illustrates an application scenario diagram of an information output method, apparatus, device, medium and program product according to an embodiment of the present disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 through the network 104 using at least one of the first terminal device 101, the second terminal device 102, the third terminal device 103, to receive or send messages, etc. Various communication client applications, such as a shopping class application, a web browser application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc. (by way of example only) may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

The first terminal device 101, the second terminal device 102, the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

In an application scenario of the embodiment of the present disclosure, a service person may initiate a request for acquiring potential customer information to the server 105 through the first terminal device 101, the second terminal device 102, and the third terminal device 103, and in response to a user request, the server 105 may execute an information output method of the embodiment of the present disclosure, construct a global feature matrix of a cooperated customer and a basic feature matrix of an uncooperative customer, and output, through different classification models, first track information for characterizing a first target track to which each of the cooperated customers belongs and second track information for characterizing a second target track to which each of the uncooperative customers belongs, respectively, and then determine, according to the first track information and the second track information, a potential customer from at least one uncooperative customer, and return the potential customer information to the service person through the first terminal device 101, the second terminal device 102, and the third terminal device 103.

It should be noted that, the information output method provided by the embodiment of the present disclosure may be generally performed by the server 105. Accordingly, the information output apparatus provided by the embodiments of the present disclosure may be generally provided in the server 105. The information output method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105. Accordingly, the information output apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The information output method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 6 based on the scenario described in fig. 1.

Fig. 2 schematically illustrates a flowchart of an information output method according to an embodiment of the present disclosure.

As shown in fig. 2, the information output method of this embodiment includes operations S201 to S204.

In operation S201, a cooperative customer global feature matrix for characterizing first basic information, first risk information, and subscription conditions of at least one cooperative customer for a target class product, and an uncooperative customer basic feature matrix for characterizing second basic information and second risk information of at least one uncooperative customer are constructed.

The present disclosure is directed to a method of an embodiment for determining potential customers by mining intrinsic relations between data information of collaborated customers and non-collaborated customers. Therefore, preprocessing of the client data information is needed in advance, and a cooperative client global feature matrix and an uncooperative client basic feature matrix are constructed.

The construction of the global feature matrix of the cooperated clients and the basic feature matrix of the non-cooperated clients can be to preliminarily collect related information, obtain cooperated client information, non-cooperated client information, product information of a plurality of products and the like. Then, through natural language processing, machine learning and other technologies, word segmentation, keyword feature recognition, data standardization and other processes are carried out, and a cooperative customer global feature matrix and an uncooperative customer basic feature matrix are constructed.

Wherein the information of the cooperated clients and the non-cooperated clients can include, but is not limited to, first basic information such as client name, registration time, registered capital, company development, etc., first risk information such as illegal event, etc. In addition, the cooperated customer information also includes contracted product information such as contracted product names, quantity, and the like. The product information can include, but is not limited to, product names, product categories, applicable scenes, business processes, cooperative clients and the like, ensure full coverage of client information and marketing product information, and periodically update related information to ensure timeliness of marketing progress.

In embodiments of the present disclosure, consent or authorization of the customer may be obtained prior to obtaining the customer's information. For example, before operation S201, a request to acquire user information may be issued to a client. In case that the client agrees or authorizes that the client information can be acquired, operation S201 is performed.

In operation S202, the global feature matrix of the cooperated clients is input into the first predetermined classification model, and probabilities that the respective cooperated clients belong to a plurality of different tracks are output, so that first track information for characterizing the respective first target tracks to which the respective cooperated clients belong is output according to the probabilities that the respective cooperated clients belong to the plurality of different tracks.

For example, the single collaborative client global feature vector Tspn1 may be summarized to generate the collaborative client global feature matrix TSP1, and the probabilities that each collaborative client belongs to a plurality of different tracks (categories) may be output as the model input through the first predetermined classification model. Probability vectors for each co-operating client belonging to a different track: ks= { (K1: probability (K1)), K2: probability (K2)), …, KS: probability (KS)). The most probable track K of the K-class tracks to which the individual cooperated clients belong may be denoted as TSPK1 as the first target track to which the cooperated clients belong and arranged in descending order.

The first predetermined classification model may be a pre-trained decision tree model, or may be a multi-classification model of other types. By classification of the first predetermined classification model, clients belonging to the same track have similar characteristics, basic information and risk information are similar, and subscription conditions for target class products are similar.

According to an embodiment of the disclosure, the first predetermined classification model may also be a clustering algorithm model, and may be a clustering algorithm that performs cluster classification on the plurality of collaborative clients global feature matrices by setting a maximum iteration number or adjusting an amplitude threshold, and performs iterative convergence through the algorithm, that is, classifies the collaborative clients into K categories, and belongs to K tracks respectively.

In operation S203, the non-cooperative customer basic feature matrix is input into a second predetermined classification model, and probabilities that each non-cooperative customer belongs to a plurality of different tracks are output, so that second track information for characterizing each non-cooperative customer belongs to a respective second target track is output according to the probabilities that each non-cooperative customer belongs to a plurality of different tracks.

For example, the individual non-cooperative customer basic feature vectors Tspn2 may be summarized to generate a non-cooperative customer global feature matrix TSP2, and the probabilities that the respective non-cooperative customers belong to a plurality of different tracks (categories) may be output as model inputs through a second predetermined classification model. Probability vectors for each uncooperative client belonging to a different track: si= { (I1: probability (I1)), I2: probability (I2)), …, IK: probability (IK)). The most probable track K of the K classes of tracks to which a single non-cooperative client belongs may be denoted as TSPK2 as the second target track to which the non-cooperative client belongs and arranged in descending order.

The second predetermined classification model may be a pre-trained multi-classification model, for example, a neural network model. And classifying the non-cooperative clients through a second preset classification model, wherein clients belonging to the same category have similar characteristics, the basic information and the risk information are similar, and the subscription conditions of products aiming at the target category are similar.

In operation S204, a potential customer is determined from at least one uncooperative customer based on the first track information and the second track information, and potential customer information is output.

For example, the first track information and the second track information may be associated, and an uncooperative client belonging to the same track as the cooperative client may be used as a potential client. For example, the first course information includes: the cooperated client A belongs to the track 1; the cooperated client B belongs to the track 1; the cooperated client C belongs to the track 2; the cooperated client D belongs to the track 3. The second course information includes: the uncooperative client E belongs to the track 1; the uncooperative client F belongs to the race track 3; the uncooperative client G belongs to the track 4; the uncooperative customer H attributes the racetrack 5. The potential clients include non-cooperative clients E and non-cooperative clients F.

According to the embodiment of the disclosure, the method automatically performs the operations of data processing and information output through a computer, specifically comprises the steps of constructing a global feature matrix of a cooperated client and a basic feature matrix of an uncooked client, classifying the cooperated client and the uncooked client through a classification model, and determining potential clients through associating track information between the two types of clients, so that the potential clients are determined by mining internal connection between data information of the cooperated client and the uncooked client, labor is relieved, working efficiency is improved, and workflow of manually screening the potential clients is simplified to a certain extent. Meanwhile, the cooperative customer global feature matrix and the non-cooperative customer basic feature matrix constructed by the method integrate multidimensional data information, improve the multiplexing value of historical service data and reduce service risks caused by incomplete information. And the model outputs a classification result based on the objective characteristics of the data through the classification information of the cooperated clients and the non-cooperated clients output by the model, and the classification result is more objective and accurate compared with manual classification. Further, through the association classification of the first track information and the second track information, the internal connection between the data information of the cooperated clients and the data information of the non-cooperated clients is mined, so that potential clients are determined, the purpose of recommending the potential clients is achieved, the generated recommending result is more objective, the accuracy and the referenceability are better, the difficulty that the clients cannot be efficiently and accurately mined manually is overcome, the accuracy of business operation is improved, and potential clients and potential demands of the cooperated clients can be effectively mined.

According to the embodiment of the disclosure, it should be noted that, because the information amounts represented by the input data are different (the cooperative clients use the global feature matrix and the non-cooperative clients use the basic feature matrix), the first predetermined classification model and the second predetermined classification model may use different multi-classification models. For example, the first predetermined classification model employs a decision tree model and the second predetermined classification model employs a neural network model.

The information types represented by the global feature matrix of the cooperated clients are relatively comprehensive information, not only comprises client basic information and client feature information of risk information, but also comprises product cooperation information aiming at the signing condition of target class products, and the path classification can be carried out on the basis of the features through a multi-classification model such as a decision tree model, so that the probability that the cooperated clients belong to a plurality of different tracks is output.

The basic feature matrix of the uncooperative client has fewer information types than the global feature matrix, and the information types comprise client feature information such as client basic information and risk information, and the classification result cannot be accurately output by adopting a decision tree model. The classification prediction is thus performed using a pre-trained second predetermined classification model.

Specifically, the second predetermined classification model is trained using target training sample data comprising a matrix of cooperative customer base characteristics, and probabilities that each cooperative customer belongs to a plurality of different tracks as sample labels. The information types of the basic feature matrix characterization (prediction sample) of the cooperative clients, which are used as training sample data, are the same as those of the basic feature matrix characterization (prediction sample) of the non-cooperative clients, and the basic feature matrix characterization data comprise client basic information, risk information and other client feature information. The training method can be a supervised training method or a semi-supervised training method. Through training, the model can output the probability that the clients belong to different categories based on the basic characteristic information of the clients.

According to the embodiment of the disclosure, the probabilities that the cooperated clients belong to a plurality of different tracks are output in advance through the first preset classification model, and the track with the highest probability is used as the first target track to which the cooperated clients finally belong, so that on one hand, the prediction result of the first preset classification model is used as the classification result of the cooperated clients and is applied to the subsequent business flow. On the other hand, the prediction result of the first predetermined classification model in the first stage is used as the label of the training sample of the second predetermined classification model in the second stage, so that the automatic labeling of the training sample data of the second predetermined classification model is realized, the flow of data processing and model training is simplified on the whole, the model training efficiency is improved, and the model training accuracy is improved.

According to the embodiment of the disclosure, because the information quantity represented by the input data is different, the first preset classification model and the second preset classification model adopt different multi-classification models, so that accurate prediction for different kinds of data information is realized, and the accuracy of model prediction is improved.

In accordance with an embodiment of the present disclosure, constructing a collaborative customer global feature matrix and a non-collaborative customer basic feature matrix includes the following operations.

Operation 11, obtaining cooperative customer reference information, non-cooperative customer reference information, and basic product information of a plurality of products, wherein the cooperative customer reference information includes first basic information, first risk information, contracted product identification, and contracted product quantity of at least one cooperative customer, the non-cooperative customer reference information includes second basic information and second risk information of at least one non-cooperative customer, and the basic product information includes at least a product category.

Specifically, the basic information of the cooperated customers and the non-cooperated customers may include, for example, basic information classes such as customer names, registration times, registered capital, company development, etc., and the risk information of the cooperated customers and the non-cooperated customers may include, for example, risk class information such as credit good, liability, penalty event, etc. The contracted product information of the affiliated clients may include contracted product names, contracted product identifications, contracted product numbers, and the like. In embodiments of the present disclosure, consent or authorization of the customers is obtained prior to obtaining reference information for both the collaborated customers and the non-collaborated customers. For example, prior to operation 11 described above, a request to obtain user information may be issued to the customer. In case the client agrees or authorizes that the client information can be obtained, the above-mentioned operation 11 is performed.

The basic product information at least comprises product names, product categories (such as XX payment, XX enterprise payment, bank enterprise interconnection, legal person financial accounting and the like), product applicable scene information (such as fund receipt and payment, fund management, investment financial accounting and the like), business process information (such as good credit, admission approval, complete qualification, consignment and the like) and the like.

An operation 12 constructs a non-cooperative customer base characteristic matrix from the second base information and the second risk information of the at least one non-cooperative customer.

For example, feature word extraction is performed by establishing a keyword dictionary through natural language processing technology, requested word segmentation features are further obtained through TF-IDF algorithm calculation, and an uncooperative client basic feature matrix is established.

And an operation 13, constructing a global feature matrix of the cooperated clients according to the first basic information, the first risk information, the contracted product identification, the contracted product quantity and the product categories of the products of at least one cooperated client.

Specifically, constructing the collaborative client global feature matrix includes:

first, a cooperative client basic feature matrix is constructed according to first basic information and first risk information of at least one cooperative client. For example, through natural language processing technology, feature word extraction is performed by establishing a keyword dictionary, the requested word segmentation feature is further obtained through TF-IDF algorithm calculation, and a cooperative customer basic feature matrix is established.

And then, according to the contracted product identification of at least one cooperated customer and the product categories of the products, carrying out data matching to determine the target product identification corresponding to the target category product.

Specifically, a product classification mark matrix may be pre-established for a plurality of products. Classifying all products according to the product specification into J classes to generate a product classification marking matrix, wherein the product classification marking matrix comprises a product identification column and a product class column, and the single product class judgment standard is as follows: judging whether the product belongs to the j-class product, if so, assigning 1, and if not, assigning 0. Product identification vectors are established for signed products of individual collaborated customers. And (3) taking the product category as a key field, correlating the product identification matrix with the product classification marking matrix, screening out products belonging to the target category, determining target product identifications corresponding to the target category products, generating target product identification vectors aiming at single cooperated clients, and combining the target product identification vectors of the single cooperated clients to generate the target product identification matrix.

And then, carrying out data matching according to the target product identifier corresponding to the target class product, and the contracted product identifier and the contracted product number of at least one cooperated client, and determining the contracted number of the at least one cooperated client aiming at the target class product.

Specifically, a collaborative product information matrix can be established for the signed product identification and the signed product quantity of a single collaborative client, the collaborative product information matrix and the target product identification vector are subjected to data matching and association by taking the target product identification as a key field, the signed quantity of the single collaborative client for the target class product is determined, the signed product quantity vector for the single collaborative client is established, and the signed product quantity vectors of the single collaborative client are combined to generate at least one signed product quantity matrix of the single collaborative client for the target class product. Taking a single client Sn as an example, product labels are generated for p products cooperated with clients, and the judgment standards are as follows: judging whether the client Sn has signed up the cooperative j class products, if so, marking the client Sn as the total number Pj of the accumulated signed up cooperative j class products, and if not, assigning 0.

Wherein, for each customer Sn product label, normalization processing may be performed, and the processing rule is as follows (1):

W*＝(W-W _min )/(W _max -W _min )-----(1)

wherein, each parameter has the following meaning:

w: normalized tag values;

w: label values before normalization;

W _min : label minimum;

W _max : label maximum.

And finally, constructing a cooperative client global feature matrix according to the cooperative client basic feature matrix and the subscription quantity of at least one cooperative client aiming at the target class product. The method specifically comprises the steps of combining the basic feature matrix of the cooperated clients and the signed product quantity matrix of the cooperated clients aiming at the target class products to generate the global feature matrix of the cooperated clients.

According to the embodiment of the disclosure, the data processing method is used for processing the customer information and the product information to establish the feature matrix, abstracting the information data into the data representation, realizing the integration of the information, providing the data basis for the subsequent model processing, simultaneously overcoming the blind spot and the information deficiency in the visual field in the service process, correlating the experience of service personnel with the enterprise data information, and providing assistance for the service processing by using the data resource as a key element.

According to an embodiment of the present disclosure, the determining of the potential customer from the at least one uncooperative customer based on the first track information and the second track information may include the following operations.

An operation 21 determines a plurality of candidate tracks based on the probabilities that each of the collaborated clients belongs to the first target track. The first predetermined classification model may output probabilities that each of the collaborated clients belongs to a plurality of different tracks, where the probabilities that each of the collaborated clients belongs to the first target track may be output, and several tracks with a larger probability may be selected from the probabilities as candidate tracks, as a candidate track set rec= { K1, K2, K3, K4 … … }.

Operation 22, determining non-cooperative clients belonging to the candidate track as potential clients according to the second track information, and outputting a potential client result set REC 1= { I1, I2,13}. The second track information includes track information attributed to each non-cooperative client.

For example, non-cooperative client A belongs to track 1; non-cooperative clients B home track 1; the uncooperative client C belongs to track 2. Let it be assumed that the candidate track set rec= { track 1, track 3} is determined from the previous operation. The non-cooperative clients attributed to the track 1 and the track 3 may be regarded as potential clients, where the potential clients include the non-cooperative client a and the non-cooperative client B.

For another example, as shown in table 1 below, in the case of the candidate track set rec= { K1, K2, K3}, the co-track potential clients are associated, and the 9 clients { I1, 12, … … I9} corresponding to { K1, K2, K3} are finally determined and fed back as the final co-track potential client recommendation set REC 1.

TABLE 1

Candidate racetracks	Potential clients of the same race track
		K1	{I1,I2,I3}
K2	{I4,I5,I6}
		K3	{I7,I8,I9}

As an alternative embodiment, fig. 3 schematically shows a flowchart of an information output method according to another embodiment of the present disclosure.

The information output method of this embodiment includes operations S301 to 303 as shown in fig. 3, in addition to operations S201 to S204 described above with reference to fig. 2. For brevity of description, descriptions of operations S201 to S204 are omitted here.

In operation S301, determining a second target track to which a potential customer of the non-cooperative customers belongs as an associated track according to the second track information, and outputting the associated track information; the second track information includes track information attributed to each non-cooperative client, and after the foregoing operation determines the potential client from the non-cooperative clients, the track attributed to the potential client (i.e., the track with the highest probability) may be determined as the associated track.

The associated track may be the same or a different track than the candidate track in the preceding operation. For example, non-cooperative client A belongs to track 1; non-cooperative clients B home track 1; the uncooperative client C belongs to track 2. Let rec= { track 1, track 3}. The non-cooperative clients attributed to the track 1 and the track 3 may be regarded as potential clients, where the potential clients include the non-cooperative client a and the non-cooperative client B (there is no non-cooperative client attributed to the track 3). Further, the racetrack 1 to which the potential customers, non-cooperative customer a and non-cooperative customer B, belong is determined as the associated racetrack. In this case, the associated track and the candidate track are different. If there are non-cooperative clients attributed to track 3, the final determined associated track is the same as the candidate track.

In operation S302, the associated track information and the first track information are associated, and the affiliated clients affiliated with the associated track are determined as affiliated associated clients. The first track information is used to characterize the track information to which each of the collaborated clients belongs, and is further back-pushed here to determine the collaborated clients belonging to the associated tracks as collaborated associated clients.

In operation S303, a product contracted by the collaborated-associated client is determined as a target recommended product to be recommended to the non-collaborated client. For example, all products contracted by the cooperatively associated clients are taken as a to-be-recommended product list pec= { P1, P2, P3, … … }. Finally, by accumulating the times of repeatedly appearing products in the PEC, selecting several products with the largest occurrence times, namely { P1', P2', … … Pn '}, as a final product recommendation list PEC' according to descending order, and performing feedback recommendation.

According to the embodiment of the disclosure, after determining the potential client, the cooperative associated client is reversely deduced through the association relationship between the potential client (non-cooperative client) and the cooperative client, and the product subscribed by the cooperative associated client is further determined as the target recommended product to be recommended to the non-cooperative client. Therefore, on the basis of determining potential clients, products suitable for recommendation are determined through the association relationship between the potential clients and the cooperated clients, and product recommendation is further achieved. The recommended result accords with the inherent objective association relation between the two types of clients, and the result has higher referenceability.

Based on the information output method, the disclosure also provides an information output device. The device will be described in detail below in connection with fig. 4.

Fig. 4 schematically shows a block diagram of the structure of an information output apparatus according to an embodiment of the present disclosure.

As shown in fig. 4, the information output apparatus 400 of this embodiment includes a construction module 401, a first classification module 402, a second classification module 403, and an output module 404.

A building module 401, configured to build a cooperative client global feature matrix and an uncooperative client basic feature matrix, where the cooperative client global feature matrix is used to characterize first basic information, first risk information, and subscription conditions of at least one cooperative client for a target class product, and the uncooperative client basic feature matrix is used to characterize second basic information and second risk information of at least one uncooperative client;

a first classification module 402, configured to input the global feature matrix of the cooperated clients into a first predetermined classification model, output probabilities that each of the cooperated clients belongs to a plurality of different tracks, so that first track information for characterizing each of the first target tracks to which each of the cooperated clients belongs is output according to the probabilities that each of the cooperated clients belongs to the plurality of different tracks;

A second classification module 403, configured to input the basic feature matrix of the non-cooperative clients into a second predetermined classification model, and output probabilities that each non-cooperative client belongs to a plurality of different tracks, so that second track information for characterizing each non-cooperative client belongs to a respective second target track is output according to the probabilities that each non-cooperative client belongs to a plurality of different tracks;

an output module 404 for determining potential customers from the at least one uncooperative customer based on the first track information and the second track information, and outputting the potential customer information.

According to the embodiment of the disclosure, the above information output device realizes the operations of automatically performing data processing and information output by a computer, specifically includes constructing a global feature matrix of a cooperated client and a basic feature matrix of an uncooperative client by a construction module 401, classifying the cooperated client and the uncooperative client by a first classification module 402 and a second classification module 403, associating the race track information between the two classes of clients by an output module 404, and determining the potential client. Meanwhile, the cooperative client global feature matrix and the non-cooperative client basic feature matrix constructed by the construction module 401 integrate multidimensional data information, thereby improving the multiplexing value of historical service data and reducing service risks caused by incomplete information. The classification information of the cooperated clients and the non-cooperated clients output by the first classification module 402 and the second classification module 403 is used for outputting classification results based on objective characteristics of data by the model, and the classification results are more objective and accurate compared with manual classification. Further, the output module 404 is used for associating and classifying the first track information and the second track information, and mining the internal connection between the data information of the cooperated clients and the data information of the non-cooperated clients, so that the potential clients are determined, the purpose of recommending the potential clients is achieved, the generated recommending result is more objective, the accuracy and the referenceability are better, the difficulty that the clients cannot be efficiently and accurately mined manually is overcome, the accuracy of business operation is improved, and the potential clients and the potential demands of the cooperated clients can be effectively mined.

According to an embodiment of the present disclosure, the output module 404 includes a first determination unit, a second determination unit.

Wherein the first determining unit is used for determining a plurality of candidate tracks according to the probability that each cooperated client belongs to the first target track.

And a second determining unit for determining, as potential customers, non-cooperative customers belonging to the candidate track based on the second track information.

Fig. 5 schematically shows a block diagram of an information output apparatus according to another embodiment of the present disclosure.

The information output apparatus of this embodiment includes, as shown in fig. 5, a first determination module 501, a second determination module 502, and a third determination module 503 in addition to the construction module 401, the first classification module 402, the second classification module 403, and the output module 404 described above with reference to fig. 4.

The first determining module 501 is configured to determine, according to the second track information, a second target track to which a potential client of the uncooperative clients belongs as an associated track, and output associated track information.

A second determining module 502, configured to associate the associated track information with the first track information, and determine the cooperated clients belonging to the associated track as cooperated associated clients.

A third determining module 503, configured to determine a product subscribed by the associated clients as a target recommended product to be recommended to the non-collaborating clients.

According to an embodiment of the present disclosure, the building module 401 includes an acquisition unit, a first building unit, and a second building unit.

The system comprises an acquisition unit, a comparison unit and a comparison unit, wherein the acquisition unit is used for acquiring cooperative client reference information, non-cooperative client reference information and basic product information of a plurality of products, the cooperative client reference information comprises at least one first basic information of a cooperative client, first risk information, contracted product identification and contracted product quantity, the non-cooperative client reference information comprises at least one second basic information and second risk information of the non-cooperative client, and the basic product information at least comprises a product category;

the first construction unit is used for constructing a basic feature matrix of the uncooperative client according to the second basic information and the second risk information of at least one uncooperative client;

the second construction unit is used for constructing a cooperative client global feature matrix according to the first basic information, the first risk information, the contracted product identification, the contracted product quantity and the product categories of the products of at least one cooperative client.

According to an embodiment of the disclosure, the second building unit comprises a first building subunit, a first determining subunit, a second building subunit.

A first construction subunit, configured to construct a cooperative client basic feature matrix according to the first basic information and the first risk information of at least one cooperative client;

the first determining subunit is used for determining a target product identifier corresponding to a target category product according to the contracted product identifier of at least one cooperated customer and the product categories of the products;

the second determining subunit is used for determining the contracted number of the at least one cooperated client aiming at the target category product according to the target product identifier corresponding to the target category product and the contracted product identifier and the contracted product number of the at least one cooperated client;

and the second construction subunit is used for constructing the cooperative client global feature matrix according to the cooperative client basic feature matrix and the subscription quantity of at least one cooperative client aiming at the target class product.

According to an embodiment of the present disclosure, the second predetermined classification model is trained using target training sample data comprising a matrix of cooperative customer base characteristics and probabilities that each cooperative customer belongs to a plurality of different tracks.

According to an embodiment of the present disclosure, wherein the first predetermined classification model and the second predetermined classification model employ multiple classification models.

According to an embodiment of the present disclosure, any of the building module 401, the first classification module 402, the second classification module 403, the output module 404, the first determination module 501, the second determination module 502, and the third determination module 503 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the building block 401, the first classification block 402, the second classification block 403, the output block 404, the first determination block 501, the second determination block 502, the third determination block 503 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable way of integrating or packaging a circuit, or in any one of or a suitable combination of three of software, hardware and firmware. Alternatively, at least one of the building module 401, the first classification module 402, the second classification module 403, the output module 404, the first determination module 501, the second determination module 502, and the third determination module 503 may be at least partially implemented as a computer program module, which may perform the corresponding functions when being run.

As shown in fig. 6, an electronic device 600 according to an embodiment of the present disclosure includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. The processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. Processor 601 may also include on-board memory for caching purposes. The processor 601 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are stored. The processor 601, the ROM602, and the RAM603 are connected to each other through a bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM602 and/or the RAM 603. Note that the program may be stored in one or more memories other than the ROM602 and the RAM 603. The processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 600 may also include an input/output (I/O) interface 605, the input/output (I/O) interface 605 also being connected to the bus 604. The electronic device 600 may also include one or more of the following components connected to an input/output (I/O) interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to an input/output (I/O) interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 602 and/or RAM 603 and/or one or more memories other than ROM 602 and RAM 603 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code means for causing a computer system to carry out the information output method provided by the embodiments of the present disclosure when the computer program product is run on the computer system.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and/or installed from the removable medium 611. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. An information output method, comprising:

constructing a cooperative client global feature matrix and an uncooperative client basic feature matrix, wherein the cooperative client global feature matrix is used for representing first basic information, first risk information and signing conditions of at least one cooperative client aiming at a target class product, and the uncooperative client basic feature matrix is used for representing second basic information and second risk information of at least one uncooperative client;

inputting the basic feature matrix of the non-cooperative clients into a second preset classification model, and outputting the probability that each non-cooperative client belongs to a plurality of different tracks, so that second track information for representing each non-cooperative client belongs to a respective second target track is output according to the probability that each non-cooperative client belongs to a plurality of different tracks;

and determining potential customers from at least one uncooperative customer according to the first track information and the second track information, and outputting potential customer information.

2. The method of claim 1, determining potential customers from at least one uncooperative customer based on the first track information and the second track information comprising:

determining a plurality of candidate tracks according to the probability that each of the collaborated clients belongs to the first target track;

And determining non-cooperative clients belonging to the candidate track as potential clients according to the second track information.

3. The method of claim 1, further comprising:

determining a second target track to which the potential client belongs in the non-cooperative clients as an associated track according to the second track information, and outputting associated track information;

associating the associated track information with the first track information, determining a cooperated client attributed to the associated track as a cooperated associated client;

4. The method of claim 1, wherein constructing a collaborative customer global feature matrix and a non-collaborative customer base feature matrix comprises:

acquiring cooperative client reference information, non-cooperative client reference information and basic product information of a plurality of products, wherein the cooperative client reference information comprises at least one first basic information of a cooperative client, first risk information, contracted product identification and contracted product quantity, the non-cooperative client reference information comprises at least one second basic information of a non-cooperative client and second risk information, and the basic product information at least comprises a product category;

Constructing a basic feature matrix of the non-cooperative clients according to the second basic information and the second risk information of the at least one non-cooperative client;

and constructing the global feature matrix of the cooperated clients according to the first basic information, the first risk information, the contracted product identification, the contracted product quantity and the product categories of the products of the at least one cooperated client.

5. The method of claim 4, wherein constructing the collaborative customer global feature matrix from the first base information, the first risk information, the contracted product identification, the contracted product quantity, the product categories of the plurality of products of the at least one collaborative customer comprises:

constructing a cooperative client basic feature matrix according to the first basic information and the first risk information of the at least one cooperative client;

determining a target product identifier corresponding to a target category product according to the contracted product identifier of the at least one cooperated client and the product categories of the plurality of products;

determining the contracted number of the at least one cooperated client aiming at the target class product according to the target product identifier corresponding to the target class product, the contracted product identifier of the at least one cooperated client and the contracted product number;

And constructing the global feature matrix of the cooperated clients according to the basic feature matrix of the cooperated clients and the contracted number of the at least one cooperated client aiming at the target class product.

6. The method according to claim 5, wherein:

the second predetermined classification model is trained using target training sample data comprising the matrix of cooperative customer base characteristics and probabilities that each of the cooperative customers belongs to a plurality of different tracks.

7. The method of any one of claims 1-6, wherein:

8. An information output apparatus, comprising:

the system comprises a construction module, a first analysis module and a second analysis module, wherein the construction module is used for constructing a cooperative client global feature matrix and an uncooperative client basic feature matrix, the cooperative client global feature matrix is used for representing first basic information, first risk information and subscription conditions of at least one cooperative client aiming at target class products of at least one cooperative client, and the uncooperative client basic feature matrix is used for representing second basic information and second risk information of at least one uncooperative client;

The first classification module is used for inputting the global feature matrix of the cooperated clients into a first preset classification model, outputting the probability that each cooperated client belongs to a plurality of different tracks, so that according to the probability that each cooperated client belongs to a plurality of different tracks, first track information for representing each first target track to which each cooperated client belongs is output;

the second classification module is used for inputting the basic feature matrix of the non-cooperative clients into a second preset classification model, outputting the probability that each non-cooperative client belongs to a plurality of different tracks, so that second track information used for representing each non-cooperative client belongs to a respective second target track is output according to the probability that each non-cooperative client belongs to a plurality of different tracks;

and the output module is used for determining potential clients from at least one uncooperative client according to the first track information and the second track information and outputting potential client information.

9. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.

10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-7.

11. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.