CN118195702A

CN118195702A - Financial service popularization method and device, storage medium and electronic equipment

Info

Publication number: CN118195702A
Application number: CN202410369393.7A
Authority: CN
Inventors: 郭玉伟
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2024-03-28
Filing date: 2024-03-28
Publication date: 2024-06-14

Abstract

The application discloses a popularization method and device of financial services, a storage medium and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the following steps: acquiring target portrait data of a customer in a financial institution, and screening N target data affecting the density between the customer and the financial institution from the target portrait data, wherein N is a positive integer; inputting N kinds of target data into a target model to obtain the affinity between a client and a financial institution; determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table; and popularizing the target financial service to the client according to the target popularizing mode. The application solves the problem of low popularization efficiency of financial services caused by that a proper financial service popularization mode is not selected based on the intimacy between the client and the financial institution in the related technology.

Description

Financial service popularization method and device, storage medium and electronic equipment

Technical Field

The application relates to the field of artificial intelligence, in particular to a financial service popularization method, a financial service popularization device, a financial service storage medium and an electronic device.

Background

With the rapid development of internet finance, the number of customers from a website of a financial institution to a shop is gradually reduced, and the distance between the financial institution and the customers is gradually pulled. To draw in distance from the customer, attracting the customer to the store, it is necessary to promote financial services to the customer in various ways. However, the popularization method of the financial service in the related art still adopts a large-area invitation information coverage, and no targeted popularization is performed on different client groups.

Aiming at the problem that in the related art, due to the fact that a proper financial service popularization mode is not selected based on the intimacy between a client and a financial institution, the popularization efficiency of financial service is low, no effective solution is proposed at present.

Disclosure of Invention

The application mainly aims to provide a financial service popularization method, a financial service popularization device, a financial service storage medium and electronic equipment, and aims to solve the problem that in the related art, the financial service popularization efficiency is low because a proper financial service popularization mode is not selected based on the intimacy between a client and a financial institution.

In order to achieve the above object, according to one aspect of the present application, there is provided a method of promoting a financial service. The method comprises the following steps: acquiring target portrait data of a customer in a financial institution, and screening N target data affecting the density between the customer and the financial institution from the target portrait data, wherein N is a positive integer; inputting N kinds of target data into a target model to obtain the affinity between a client and a financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one client and the historical affinity; determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode; and popularizing the target financial service to the client according to the target popularizing mode.

Optionally, selecting N types of target data from the target representation data that affect the affinity between the customer and the financial institution includes: determining a sample customer group which receives target financial services, and acquiring portrait data of each sample customer in the sample customer group to obtain a portrait data set; performing factor analysis operation on the portrait data set to obtain at least one common factor, wherein each common factor is used for representing a plurality of kinds of data indexes in portrait data, and different common factors are not related to each other; target data is determined from the target representation data based on the common factor.

Optionally, determining the target data from the target portrait data based on the common factor includes: for each common factor, determining a data value corresponding to each data index in target portrait data represented by the common factor, and obtaining a group of data values; and calculating the concentrated trend data of a group of data values to obtain target data corresponding to the common factors.

Alternatively, the object model is obtained by: acquiring historical affinities of a plurality of clients, and historical portrait data of each client; n kinds of target data are extracted from the historical portrait data of each client, N kinds of target data and the historical affinities of the client are determined to be a group of training samples, and a plurality of groups of training samples are obtained; and training the support vector machine model based on a plurality of groups of training samples to obtain a target model.

Optionally, the method further comprises: collecting popularization results of target financial services of each client in the target client group, wherein the popularization results comprise receiving the target financial services and not receiving the target financial services; determining the popularization result as the target number of clients which do not accept the target financial service, and calculating the ratio of the target number to the number of clients in the target client group to obtain a popularization evaluation value; and updating the target model under the condition that the popularization evaluation value is larger than or equal to the popularization evaluation value threshold value.

Optionally, before updating the target model, the method further comprises: determining a test client group, wherein the test client group is a client of which the affinity belongs to a target affinity range; popularizing target financial service for each client in the test client group according to a target popularization mode, and collecting test popularization results of the test client group; calculating a confidence interval of the test client group based on the test popularization result of the test client group; in the case where the confidence level evaluation value of the confidence interval is smaller than the confidence level evaluation threshold value, the step of updating the target model is performed.

Optionally, updating the target model includes: n kinds of target data and the affinity of each client in the test client group are determined as a group of newly added training samples, and a plurality of groups of newly added training samples are obtained; combining a plurality of groups of newly added training samples with a plurality of groups of training samples to obtain a training sample set; and training the support vector machine model based on the training sample set to obtain an updated target model.

In order to achieve the above object, according to another aspect of the present application, there is provided a promotion device of a financial service. The device comprises: an acquisition unit for acquiring target portrait data of a customer at a financial institution, and screening N target data affecting the affinity between the customer and the financial institution from the target portrait data, wherein N is a positive integer; the input unit is used for inputting N kinds of target data into the target model to obtain the affinity between the client and the financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one client and the historical affinity; the system comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode; and the promotion unit is used for promoting the target financial service to the client according to the target promotion mode.

According to the application, the following steps are adopted: acquiring target portrait data of a customer in a financial institution, and screening N target data affecting the density between the customer and the financial institution from the target portrait data, wherein N is a positive integer; inputting N kinds of target data into a target model to obtain the affinity between a client and a financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one client and the historical affinity; determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode; according to the target promotion mode, target financial services are promoted to customers, and the problem that in the related art, due to the fact that proper financial service promotion modes are not selected based on the intimacy between the customers and financial institutions, promotion efficiency of the financial services is low is solved. The target data influencing the affinity is screened from the target portrait data, the target data is input into the target model to predict the affinity of the client, and the matched target popularization mode is determined according to the affinity, so that the target financial service is promoted to the client according to the target popularization mode, and the effect of improving the popularization efficiency of the financial service is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

FIG. 1 is a flow chart of a method of promoting financial services provided in accordance with an embodiment of the present application;

FIG. 2 is a schematic diagram of an activity deployment method provided in accordance with an embodiment of the present application;

FIG. 3 is a schematic diagram of a promotional device for financial services provided in accordance with an embodiment of the present application;

Fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party.

It should be noted that the collected information is information and data authorized by the user or fully authorized by each party, and the related data is collected, stored, used, processed, transmitted, provided, disclosed, applied and the like, all comply with related laws and regulations and standards of related areas, necessary security measures are taken, no prejudice is made to the public order, and corresponding operation entrance is provided for the user to select authorization or rejection.

The present application will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a method for promoting financial services provided according to an embodiment of the present application, as shown in fig. 1, and the method includes the following steps:

Step S101, target portrait data of a customer in a financial institution is obtained, and N target data affecting the intimacy between the customer and the financial institution are screened from the target portrait data, wherein N is a positive integer.

Specifically, the target portrayal data may be an information profile established for the customer at a financial institution. Such as customer age, occupation, sex, regular deposit total equity, fund total equity, financing total equity, insurance total equity, precious metal total equity, loan total liability, service agreement endorsement amount, customer star rating, customer risk rating index, etc. In order to predict the affinity between the customer and the financial institution, N kinds of target data affecting the affinity are screened out from the target portrait data by factor analysis. The target data may be several kinds of data in the target portrait data or may be a comprehensive representation of a plurality of kinds of data.

Step S102, inputting N kinds of target data into a target model to obtain the affinity between the client and the financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one client and the historical affinity.

Specifically, the target model may be a support vector machine model, and the support vector machine is trained by a training sample with a label added in advance to obtain the target model, so as to predict the affinity between the client and the financial institution based on the target model and the N kinds of target data.

Step S103, determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode.

Specifically, the popularization mode can be sending a short message or a mobile phone bank popup window, calling out a phone, sending related product information according to an activity theme, and the like, and different popularization modes are set for different intimacy ranges, for example, the short message or the mobile phone bank popup window is not sent any more for clients with intimacy belonging to the first intimacy range; aiming at the continuous tracking of clients with the affinity belonging to the second affinity range, the clients continue to send short messages or mobile phone bank popup windows to recommend, and the recommendation can be properly performed through telephone outbound; and for clients with the affinity belonging to the third affinity range, bringing the clients into a special list management library, and sending relevant product information according to the activity theme.

Step S104, popularizing the target financial service to the client according to the target popularizing mode.

Specifically, after the target popularization mode corresponding to the intimacy of the customer is determined, the target financial service is promoted to the customer according to the target popularization mode, the corresponding popularization modes are selected for different types of customers in a targeted mode to promote, and the acceptance of the customer to accept the promotion of the target financial service is improved.

According to the popularization method of the financial service, provided by the embodiment of the application, the target portrait data of the customer in the financial institution is obtained, and N target data influencing the density between the customer and the financial institution are screened from the target portrait data, wherein N is a positive integer; inputting N kinds of target data into a target model to obtain the affinity between a client and a financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one client and the historical affinity; determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode; according to the target promotion mode, target financial services are promoted to customers, and the problem that in the related art, due to the fact that proper financial service promotion modes are not selected based on the intimacy between the customers and financial institutions, promotion efficiency of the financial services is low is solved. The target data influencing the affinity is screened from the target portrait data, the target data is input into the target model to predict the affinity of the client, and the matched target popularization mode is determined according to the affinity, so that the target financial service is promoted to the client according to the target popularization mode, and the effect of improving the popularization efficiency of the financial service is achieved.

Optionally, in the method for promoting a financial service provided by the embodiment of the present application, selecting N kinds of target data affecting the affinity between a client and a financial institution from the target portrait data includes: determining a sample customer group which receives target financial services, and acquiring portrait data of each sample customer in the sample customer group to obtain a portrait data set; performing factor analysis operation on the portrait data set to obtain at least one common factor, wherein each common factor is used for representing a plurality of kinds of data indexes in portrait data, and different common factors are not related to each other; target data is determined from the target representation data based on the common factor.

Specifically, the sample customer group may be a customer who receives the target financial service, that is, the customer who receives the target financial service has higher affinity to the financial institution, so that the public factors related to the affinity are screened through the image data set of the customer who is willing to receive the target financial service, the public factors affecting the affinity are obtained through factor analysis on the image data set to eliminate the co-linearity problem caused by excessive indexes, and the image data may include the age, occupation, sex, regular deposit on the total asset ratio, fund on the total asset ratio, financial on the total asset ratio, insurance on the total asset ratio, precious metal on the total asset ratio, loan on the total liability ratio, service agreement subscription number, four or more stars on the customer risk level index. At least one common factor is extracted from the set of representation data by a factor analysis operation, and target data is determined from the target representation data based on the common factor. The present embodiment uses the determined target data to predict the affinity of the customer based on the target data.

It should be noted that the basic idea of factor analysis is to use a few common factors to explain the complex relationships existing in a plurality of variables to be observed, and instead of recombining the original variables, the original variables are decomposed into two parts, namely the common factors and the special factors. And the score of the newly generated factor variable is calculated, so that the factor score can be used for replacing the original variable to further analyze, and the effect of reducing the dimension is achieved.

For example, let P (p=12) related random variables contain m (m=3) common factors independent of each other, and each of the image data may be expressed as x=af+epsilon.

Wherein ,X₁ X₂ X₃ X₄ X₅ X₆ X₇ X₈ X₉ X₁₀ X₁₁ is the index of customer age, occupation, sex, regular deposit total asset ratio, fund total asset ratio, financial total asset ratio, insurance total asset ratio, noble metal total asset ratio, loan total liability ratio, service agreement signed number and customer risk grade, F ₁,F₂,F₃ is three common factors such as customer basic information, investment financial condition and risk bearing capacity, which are non-observable variables, and the coefficient alpha ₁₁、α₁₂ is called factor load, A is called factor load matrix. Epsilon is a special factor and is a part that cannot be included in the common factor.

It should be noted that: the common factors are uncorrelated, and the variance of each common factor is 1, namely the covariance matrix of F _i is I; the common factor and the special factor are independent of each other, i.e., cov (F _i, epsilon) =0. The specific factors are not related to each other, but the variances are not necessarily the same. Ideally, for each original variable, it is in the factor load matrix that the load is larger on one common factor and smaller on the other factors. The factor load matrix may be adjusted by a factor rotation method.

Optionally, in the method for promoting a financial service provided by the embodiment of the present application, determining, based on the common factor, target data from target portrait data includes: for each common factor, determining a data value corresponding to each data index in target portrait data represented by the common factor, and obtaining a group of data values; and calculating the concentrated trend data of a group of data values to obtain target data corresponding to the common factors.

Specifically, after determining the common factor, determining a data value corresponding to each data index in target portrait data represented by the common factor from target portrait data of the client, for example, the client basic information common factor represents data indexes such as client age, occupation, sex and the like, determining data values such as client age, occupation, sex and the like from target portrait data, and calculating central tendency data of a group of data values as target data of the common factor, wherein the central tendency data can be mean value, variance and the like of a group of data values. According to the embodiment, the target data corresponding to each public factor of the client is determined, and the intimacy of the client is calculated based on the target data.

Optionally, in the method for promoting a financial service provided by the embodiment of the present application, the target model is obtained by: acquiring historical affinities of a plurality of clients, and historical portrait data of each client; n kinds of target data are extracted from the historical portrait data of each client, N kinds of target data and the historical affinities of the client are determined to be a group of training samples, and a plurality of groups of training samples are obtained; and training the support vector machine model based on a plurality of groups of training samples to obtain a target model.

Specifically, the clients used as training samples are randomly selected clients, the historical affinity of each client is determined based on the service records of the clients and expert experience, the historical affinities of all clients are divided into three types of tagged client groups, such as non-preference clients (0 representation), experience preference clients (1 representation) and strong preference clients (2 representation). N kinds of target data and historical affinities of each customer are used as a training sample, each sample corresponds to a point in a vector space, and samples representing the same class are enabled to fall into the same coordinate area through linearization division of the vector space. Since in most cases these data are linearly inseparable in vector space. Therefore, the adopted multi-layer support vector product model obtains a target model for predicting the affinity through a plurality of groups of training sample pairs and a support vector machine model.

For example, N kinds of target data are selected as three factors of the features that most contribute to the difference. Sample data of a plurality of groups of training samples, especially abnormal values and missing values, can be removed or adopt a mean value filling mode and the like. Training samples are classified into three categories using a support vector machine model, no preference type client (e.g., client tag may be represented by 0), experience preference type client (e.g., client tag may be represented by 1), and strong preference type client (e.g., client tag may be represented by 2). And (3) checking the model again by verifying the sample, and correcting the target model when the model prediction affinity is low in accuracy.

Optionally, in the method for promoting the financial service provided by the embodiment of the present application, the method further includes: collecting popularization results of target financial services of each client in the target client group, wherein the popularization results comprise receiving the target financial services and not receiving the target financial services; determining the popularization result as the target number of clients which do not accept the target financial service, and calculating the ratio of the target number to the number of clients in the target client group to obtain a popularization evaluation value; and updating the target model under the condition that the popularization evaluation value is larger than or equal to the popularization evaluation value threshold value.

Specifically, in order to further improve the accuracy of the predicted affinity of the target model, the popularization results of the target customer group within a period of time are collected. That is, after popularizing the target financial service to each client in the target client group according to the target popularizing mode, determining the target number of clients which do not accept the target financial service, calculating the ratio of the target number to the total number of clients in the target client group as a popularizing evaluation value, if the popularizing evaluation value is greater than or equal to a threshold value of the popularizing evaluation value, the popularizing effect of the target financial service is poor, the predicted client affinity is inaccurate, and the model needs to be updated. According to the embodiment, whether the target model prediction intimacy is accurate or not is evaluated by calculating the popularization evaluation value of the target financial service, and whether the target model needs to be updated or not is evaluated.

Optionally, in the method for promoting a financial service provided by the embodiment of the present application, before updating the target model, the method further includes: determining a test client group, wherein the test client group is a client of which the affinity belongs to a target affinity range; popularizing target financial service for each client in the test client group according to a target popularization mode, and collecting test popularization results of the test client group; calculating a confidence interval of the test client group based on the test popularization result of the test client group; in the case where the confidence level evaluation value of the confidence interval is smaller than the confidence level evaluation threshold value, the step of updating the target model is performed.

Specifically, in order to determine that poor popularization of the target financial service is caused by the problem of prediction accuracy of the target model, confidence levels of different customer groups are calculated by testing the customer groups, and then whether the target model needs to be updated is determined. If the confidence level evaluation value is smaller than the confidence level evaluation threshold value, the result of the intimacy prediction of the client group of the type is inaccurate, and the target model needs to be updated.

For example, three classes of non-preference clients, experience preference clients and strong preference clients are obtained according to the target model, test client groups of three classes of samples are obtained, and target financial service popularization and deployment are carried out. The clients are not interested in target financial service popularization, experience preference type clients which are experienced by clients clicking short messages or mobile banking but not actually in the website, and strong preference type clients which are experienced by clients clicking short messages or mobile banking in the store. And sending an offer application to clients in the three different test client groups, reaching the clients through a plurality of channels of a short message or a mobile phone APP, calculating the experience probability of the three types of clients, further calculating the confidence interval of the test client groups based on the experience probability, and determining a confidence level evaluation value. And further determining whether the target model needs to be updated based on the confidence level assessment value.

Optionally, in the method for promoting a financial service provided by the embodiment of the present application, updating the target model includes: n kinds of target data and the affinity of each client in the test client group are determined as a group of newly added training samples, and a plurality of groups of newly added training samples are obtained; combining a plurality of groups of newly added training samples with a plurality of groups of training samples to obtain a training sample set; and training the support vector machine model based on the training sample set to obtain an updated target model.

Specifically, if the target model needs to be updated, the data of the test client group can be used as a new training sample, and then the target model is updated by expanding the training sample set.

According to another embodiment of the present application, there is further provided an activity deployment method, and fig. 2 is a schematic diagram of the activity deployment method according to the embodiment of the present application. As shown in fig. 2, the method includes: and analyzing the influence factors of the client affinity, selecting clients with client grades of four stars and more in a certain area as samples, and dividing the samples into a training set, a testing set and a verification set. The sample data is subjected to data processing such as removal or alignment of outliers and missing values. And establishing an affinity recognition model by adopting a support vector set, correcting and perfecting the model precision of the recognition model, and calculating the affinity confidence interval of the client based on the perfected recognition model. And deploying activities to the clients according to the confidence intervals in different modes, wherein the deploying activities mainly comprise short messages and mobile phone application programs.

According to the embodiment, the affinity influence factors are analyzed, the affinity type of the client is judged according to the support vector machine model, and finally the affinity confidence interval is obtained according to the probability of experience prediction of different affinity types, so that corresponding marketing strategies are set for different types of clients. By establishing a customer affinity recognition model, classifying the sample population, setting different service strategies for different types of customers, the customer needs can be known more accurately, the thousands of service modes are achieved, the traditional business handling mode is changed, and the customer experiences full-scene, one-stop and higher-end atmospheric service experience.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides a financial service promotion device, and the financial service promotion device can be used for executing the financial service promotion method provided by the embodiment of the application. The following describes a popularization device of financial services provided by the embodiment of the application.

Fig. 3 is a schematic diagram of a promotion device of a financial service provided according to an embodiment of the present application. As shown in fig. 3, the apparatus includes:

an acquisition unit 301 for acquiring target portrait data of a customer at a financial institution, and selecting N kinds of target data affecting the affinity between the customer and the financial institution from the target portrait data, wherein N is a positive integer;

The input unit 302 is configured to input N kinds of target data into a target model to obtain an affinity between a customer and a financial institution, where the target model is obtained by training multiple sets of training samples, and each set of training samples includes N kinds of target data and a historical affinity of a customer;

a first determining unit 303, configured to determine a target affinity range to which affinity belongs, and determine at least one target popularization style matching with the target affinity range from a service popularization style matching table, where the service popularization style matching table includes a plurality of matching relations, and each matching relation includes one affinity range and at least one popularization style;

and the promotion unit 304 is configured to promote the target financial service to the client according to the target promotion mode.

According to the popularization device of the financial service, provided by the embodiment of the application, the target portrait data of the client in the financial institution is obtained through the obtaining unit 301, and N target data affecting the density between the client and the financial institution are screened from the target portrait data, wherein N is a positive integer; the input unit 302 inputs N kinds of target data into a target model to obtain the affinity between the customer and the financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one customer and the historical affinity; a first determining unit 303, configured to determine a target affinity range to which affinity belongs, and determine at least one target popularization style matching with the target affinity range from a service popularization style matching table, where the service popularization style matching table includes a plurality of matching relations, and each matching relation includes one affinity range and at least one popularization style; the promotion unit 304 promotes the target financial service to the customer according to the target promotion mode, solves the problem of low promotion efficiency of the financial service because a proper financial service promotion mode is not selected based on the intimacy between the customer and the financial institution in the related technology, and further inputs the target data into the target model to predict the intimacy of the customer, and determines a matched target promotion mode according to the intimacy, thereby promoting the target financial service to the customer according to the target promotion mode, and further achieving the effect of improving the promotion efficiency of the financial service.

Optionally, in the promotion device of financial service provided in the embodiment of the present application, the obtaining unit 301 includes: the first determining module is used for determining a sample customer group which receives the target financial service, and obtaining the portrait data of each sample customer in the sample customer group to obtain a portrait data set; the execution module is used for executing factor analysis operation on the portrait data set to obtain at least one common factor, wherein each common factor is used for representing a plurality of kinds of data indexes in the portrait data, and different common factors are not related to each other; and the second determining module is used for determining target data from the target portrait data based on the common factors.

Optionally, in the promotion device for financial services provided by the embodiment of the present application, the second determining module includes: the determining submodule is used for determining data values corresponding to each data index in the target portrait data represented by the common factors for each common factor to obtain a group of data values; and the calculation sub-module is used for calculating the concentrated trend data of a group of data values to obtain target data corresponding to the common factors.

Optionally, in the promotion device for financial services provided by the embodiment of the present application, the target model is obtained by: acquiring historical affinities of a plurality of clients, and historical portrait data of each client; n kinds of target data are extracted from the historical portrait data of each client, N kinds of target data and the historical affinities of the client are determined to be a group of training samples, and a plurality of groups of training samples are obtained; and training the support vector machine model based on a plurality of groups of training samples to obtain a target model.

Optionally, in the promotion device of financial service provided by the embodiment of the present application, the device further includes: the first acquisition unit is used for acquiring popularization results of target financial services of each client in the target client group, wherein the popularization results comprise receiving the target financial services and not receiving the target financial services; the first calculation unit is used for determining the popularization result as the target number of the clients which do not receive the target financial service, and calculating the ratio of the target number to the number of the clients in the target client group to obtain a popularization evaluation value; and the updating unit is used for updating the target model under the condition that the popularization evaluation value is larger than or equal to the popularization evaluation value threshold value.

Optionally, in the promotion device of financial service provided by the embodiment of the present application, the device further includes: the second determining unit is used for determining a test client group, wherein the test client group is a client of which the intimacy belongs to the target intimacy range; the second acquisition unit is used for popularizing target financial services for each client in the test client group according to a target popularizing mode and acquiring test popularizing results of the test client group; the second calculation unit is used for calculating the confidence interval of the test client group based on the test popularization result of the test client group; and an execution unit configured to execute the step of updating the target model in a case where the confidence level evaluation value of the confidence interval is smaller than the confidence level evaluation threshold value.

Optionally, in the promotion device for financial services provided by the embodiment of the present application, the update unit includes: the third determining module is used for determining N kinds of target data and affinities of each client in the test client group as a group of newly added training samples to obtain a plurality of groups of newly added training samples; the combination module is used for combining a plurality of groups of newly added training samples with a plurality of groups of training samples to obtain a training sample set; and the training module is used for training the support vector machine model based on the training sample set to obtain an updated target model.

The popularization device of the financial service includes a processor and a memory, the above-mentioned acquisition unit 301, input unit 302, first determination unit 303, popularization unit 304, and the like are stored as program units in the memory, and the above-mentioned program units stored in the memory are executed by the processor to realize the corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more, and the promotion efficiency of the financial service is improved by adjusting the kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the invention provides a computer readable storage medium, on which a program is stored, which when executed by a processor, implements a method of promoting financial services.

The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute a popularization method of financial services.

Fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present application. As shown in fig. 4, the electronic device 401 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor implements the following steps when executing the program: (method claim step, independent + dependent). The device herein may be a server, PC, PAD, cell phone, etc.

The application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: (steps of method claim, independent + dependent).

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that 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, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. A method of facilitating financial services, comprising:

Acquiring target portrait data of a customer in a financial institution, and screening N target data influencing the density between the customer and the financial institution from the target portrait data, wherein N is a positive integer;

Inputting the N kinds of target data into a target model to obtain the affinity between the client and the financial institution, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises N kinds of target data of one client and historical affinity;

Determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode;

and popularizing the target financial service to the client according to the target popularizing mode.

2. The method of claim 1, wherein screening the target representation data for N target data affecting an affinity between the customer and the financial institution comprises:

Determining a sample customer group for receiving the target financial service, and acquiring portrait data of each sample customer in the sample customer group to obtain a portrait data set;

Performing factor analysis operation on the portrait data set to obtain at least one common factor, wherein each common factor is used for representing a plurality of kinds of data indexes in the portrait data, and different common factors are not related to each other;

the target data is determined from the target portrait data based on the common factor.

3. The method of claim 2, wherein determining the target data from the target representation data based on the common factor comprises:

for each common factor, determining a data value corresponding to each data index in the target portrait data represented by the common factor, and obtaining a group of data values;

And calculating the concentrated trend data of the group of data values to obtain target data corresponding to the common factors.

4. The method of claim 1, wherein the target model is derived by:

acquiring historical affinities of a plurality of clients, and historical portrait data of each client;

n kinds of target data are extracted from the historical portrait data of each client, N kinds of target data and historical affinities of the client are determined to be a group of training samples, and a plurality of groups of training samples are obtained;

And training a support vector machine model based on the plurality of groups of training samples to obtain the target model.

5. The method according to claim 1, wherein the method further comprises:

collecting popularization results of the target financial service of each client in a target client group, wherein the popularization results comprise receiving the target financial service and not receiving the target financial service;

determining the popularization result as the target number of clients which do not accept the target financial service, and calculating the ratio of the target number to the number of clients in the target client group to obtain a popularization evaluation value;

And updating the target model under the condition that the popularization evaluation value is larger than or equal to a popularization evaluation value threshold value.

6. The method of claim 5, wherein prior to updating the target model, the method further comprises:

determining a test client group, wherein the test client group is a client of which the affinity belongs to the target affinity range;

Promoting the target financial service for each client in the test client group according to the target promotion mode, and collecting test promotion results of the test client group;

calculating a confidence interval of the test client group based on the test popularization result of the test client group;

And in the case that the confidence level evaluation value of the confidence interval is smaller than a confidence level evaluation threshold value, performing the step of updating the target model.

7. The method of claim 6, wherein updating the object model comprises:

Determining N kinds of target data and the affinity of each client in the test client group as a group of newly added training samples to obtain a plurality of groups of newly added training samples;

Combining the multiple groups of newly added training samples with the multiple groups of training samples to obtain a training sample set;

And training a support vector machine model based on the training sample set to obtain an updated target model.

8. A promotional device for financial services, comprising:

An acquisition unit, configured to acquire target portrait data of a customer at a financial institution, and screen N target data affecting an affinity between the customer and the financial institution from the target portrait data, where N is a positive integer;

The input unit is used for inputting the N target data into a target model to obtain the affinity between the client and the financial institution, wherein the target model is obtained by training a plurality of groups of training samples, and each group of training samples comprises N target data of one client and the historical affinity;

the system comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for determining a target affinity range to which the affinity belongs, and determining at least one target popularization mode matched with the target affinity range from a service popularization mode matching table, wherein the service popularization mode matching table comprises a plurality of matching relations, and each matching relation comprises an affinity range and at least one popularization mode;

And the promotion unit is used for promoting the target financial service to the client according to the target promotion mode.

9. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored program, wherein the program, when run, controls a device in which the non-volatile storage medium is located to perform the method of promoting a financial service according to any one of claims 1 to 7.

10. 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 implement the method of promotion of financial services of any one of claims 1 to 7.