CN115034685A

CN115034685A - Customer value evaluation method, customer value evaluation device and computer-readable storage medium

Info

Publication number: CN115034685A
Application number: CN202210938814.4A
Authority: CN
Inventors: 叶鹏
Original assignee: Ping An Bank Co Ltd
Current assignee: Ping An Bank Co Ltd
Priority date: 2022-08-05
Filing date: 2022-08-05
Publication date: 2022-09-09

Abstract

The embodiment of the application discloses a customer value evaluation method, a customer value evaluation device and a computer-readable storage medium, wherein historical product transaction data of a customer to be evaluated in a first organization are obtained, wherein the first organization and at least one second organization belong to a group of organizations; extracting historical transaction amount of each historical transaction product of a customer to be evaluated from the product historical transaction data; according to the product importance of each historical transaction product, weighting the historical transaction amount of each historical transaction product to obtain the weighted transaction amount of each historical transaction product; determining the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products aiming at the historical transaction products issued by the second organization; and evaluating the customer value of the customer to be evaluated based on the weighted transaction amount and the distribution amount corresponding to the historical transaction product issued by the first organization. Therefore, the accuracy of the customer value evaluation result is improved.

Description

Customer value evaluation method, customer value evaluation device and computer-readable storage medium

Technical Field

The application relates to the technical field of internet, in particular to a method and a device for evaluating customer value and a computer-readable storage medium.

Background

In recent years, with the development of internet technology, in order to help organizations such as banks and the like to more accurately provide matched business services for their customers, in the prior art, the value of the customers in enterprise organizations is often evaluated according to historical transaction data of the customers, so that business services matched with the value stage of the customer value are formulated for the customers according to the value stage of the customer value, and thus the business service efficiency of enterprises is improved.

In the research and practice process of the prior art, the existing method for evaluating the customer value of a customer according to the historical transaction data of the customer is found to have the defects that the existing customer value evaluation system cannot accurately evaluate the customer value of the customer due to the difference between products and the complexity of business, and further the evaluation result of the customer value is poor in accuracy.

Disclosure of Invention

The embodiment of the application provides a method and a device for evaluating customer value and a computer-readable storage medium, which can improve the accuracy of evaluation results of customer value.

The embodiment of the application provides a customer value evaluation method, which comprises the following steps:

obtaining product historical transaction data of a customer to be evaluated in a first organization, wherein the first organization and at least one second organization belong to the same group of organizations, and financial products sold by the first organization can be configured to comprise financial products issued by the first organization and the second organization;

extracting the historical transaction amount of each historical transaction product of the customer to be evaluated from the product historical transaction data;

according to the product importance of each historical transaction product, weighting the historical transaction amount of each historical transaction product to obtain the weighted transaction amount of each historical transaction product;

determining an allocation amount allocated to the first organization in the weighted transaction amounts of the historical transaction products issued by the second organization;

and evaluating the customer value of the customer to be evaluated based on the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the distribution amount.

Correspondingly, the embodiment of the present application provides a customer value evaluation device, including:

the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring product historical transaction data of a customer to be evaluated in a first organization, the first organization and at least one second organization belong to the same group of organizations, and financial products sold by the first organization can be configured to include financial products issued by the first organization and the second organization;

the extraction unit is used for extracting the historical transaction amount of each historical transaction product of the customer to be evaluated from the product historical transaction data;

the weighting unit is used for weighting the historical transaction amount of each historical transaction product according to the product importance of each historical transaction product to obtain the weighted transaction amount of each historical transaction product;

a determination unit, configured to determine, for a historical transaction product issued by the second organization, an allocation amount allocated to the first organization in a weighted transaction amount of the historical transaction product;

and the evaluation unit is used for evaluating the customer value of the customer to be evaluated based on the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the distribution amount.

In one embodiment, the determining unit includes:

a product income distribution information acquisition subunit, configured to acquire product income distribution information corresponding to the historical transaction product issued by the second organization;

a proportion distribution identification subunit, configured to identify, based on the product revenue distribution information, a money distribution proportion corresponding to a historical transaction product issued by the second organization;

and the distribution amount calculation subunit is used for calculating the distribution amount distributed to the first organization in the weighted transaction amounts of the historical transaction products issued by the second organization according to the amount distribution proportion.

In one embodiment, the weighting unit includes:

the product value information acquisition subunit is used for acquiring the product value information of each historical transaction product;

the weight determining subunit is used for determining the money adjusting weight corresponding to each historical transaction product according to the product value information;

and the weighting subunit is used for carrying out weighting processing on the historical transaction amount corresponding to each historical transaction product based on the amount adjustment weight to obtain the weighted transaction amount of each historical transaction product.

In one embodiment, the weight determining subunit includes:

the extraction module is used for extracting the historical transaction unit price of each historical transaction product and the total transaction amount of each historical transaction product in the organization from the product value information;

the transaction amount calculation module is used for calculating the historical transaction amount corresponding to each historical transaction product and the ratio of the historical transaction unit price to obtain the historical transaction amount corresponding to each historical transaction product;

and the weight determining module is used for determining the money adjusting weight corresponding to each historical transaction product according to the historical transaction amount corresponding to each historical transaction product and the total transaction money.

In one embodiment, the evaluation unit includes:

the accumulation subunit is used for accumulating the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the distribution amount to obtain a target transaction amount of the customer to be evaluated in the first organization;

the updating subunit is used for updating the historical product transaction data based on the target transaction amount to obtain target product transaction data;

and the evaluation subunit is used for evaluating the client value of the client to be evaluated according to the target product transaction data.

In one embodiment, the evaluation subunit includes:

the statistic module is used for carrying out statistics on the target product transaction data to obtain a multi-dimensional transaction index;

the clustering module is used for clustering the to-be-evaluated customers based on the transaction indexes to obtain at least one category set and category labels corresponding to the category sets;

and the evaluation module is used for evaluating the customer value of the customer to be evaluated based on the transaction index and the category label to obtain a customer value evaluation result corresponding to the customer to be evaluated.

In one embodiment, the evaluation module includes:

the construction submodule is used for constructing a scoring card model based on the transaction indexes and taking the category labels as dependent variables corresponding to the scoring card model;

the scoring submodule is used for scoring the to-be-assessed client according to the scoring card model to obtain an assessment score corresponding to the to-be-assessed client;

and the evaluation result determining submodule is used for determining a customer value evaluation result corresponding to the customer to be evaluated based on the evaluation score.

In addition, a computer-readable storage medium is provided, where the computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to perform the steps in any one of the customer value evaluation methods provided in the embodiments of the present application.

In addition, the embodiment of the present application further provides a computer device, which includes a processor and a memory, where the memory stores an application program, and the processor is configured to run the application program in the memory to implement the customer value evaluation method provided in the embodiment of the present application.

Embodiments of the present application also provide a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the steps in the customer value evaluation method provided by the embodiment of the application.

According to the method, by acquiring product historical transaction data of a customer to be evaluated in a first organization, wherein the first organization and at least one second organization belong to the same group of organizations, financial products sold by the first organization can be configured to include financial products issued by the first organization and the second organization; extracting historical transaction amount of each historical transaction product of a customer to be evaluated from the product historical transaction data; according to the product importance of each historical transaction product, weighting the historical transaction amount of each historical transaction product to obtain the weighted transaction amount of each historical transaction product; determining the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products aiming at the historical transaction products issued by the second organization; and evaluating the customer value of the customer to be evaluated based on the weighted transaction amount and the distribution amount corresponding to the historical transaction product issued by the first organization. Thus, the historical transaction amount of each historical transaction product is weighted according to the product importance of the historical transaction product, so that the difference between different products is pulled through, and meanwhile, distributing the weighted transaction amount corresponding to the historical transaction product issued by the second organization according to the issuing source of the historical transaction product, thereby realizing the quantitative integration of the product historical transaction data of the evaluation customers in the first organization based on the integral proportion of the organization, therefore, the client value evaluation is carried out on the client to be evaluated based on the weighted transaction amount and the distribution amount corresponding to each organization, the scale statistical mode of the transaction behavior among different organizations in the organization under the condition that the product type and the transaction mode are different is standardized, therefore, an index system for evaluating the value of the client by each organization in an organization is unified, and the accuracy of the value evaluation result of the client is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic view of an implementation scenario of a customer value assessment method provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart diagram illustrating a customer value assessment method according to an embodiment of the present disclosure;

FIG. 3 is another schematic flow chart diagram of a customer value assessment method according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a customer value evaluation device provided in an embodiment of the present application;

fig. 5 is a schematic structural diagram of a computer device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides a customer value evaluation method and device and a computer readable storage medium. The client value evaluation device can be integrated in a computer device, and the computer device can be a server or a terminal or other devices.

The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Network acceleration service (CDN), big data and an artificial intelligence platform. The terminal may be, but is not limited to, a smart television, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart phone, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

Referring to fig. 1, taking an example that a customer value evaluation device is integrated in a computer device, fig. 1 is a schematic view of an implementation scenario of a customer value evaluation method provided in an embodiment of the present application, where the computer device may obtain product historical transaction data of a customer to be evaluated in a first organization, the first organization and at least one second organization belong to a same organization, and a financial product sold by the first organization may be configured to include financial products issued by the first organization and the second organization; extracting historical transaction amount of each historical transaction product of a customer to be evaluated from the historical transaction data of the product; according to the product importance of each historical transaction product, weighting the historical transaction amount of each historical transaction product to obtain the weighted transaction amount of each historical transaction product; determining the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products issued by the second organization; and evaluating the customer value of the customer to be evaluated based on the weighted transaction amount and the distribution amount corresponding to the historical transaction product issued by the first organization.

It should be noted that the schematic diagram of the implementation environment scenario of the customer value evaluation method shown in fig. 1 is only an example, and the implementation environment scenario of the customer value evaluation method described in the embodiment of the present application is for more clearly explaining the technical solution of the embodiment of the present application, and does not constitute a limitation to the technical solution provided by the embodiment of the present application. As can be appreciated by those skilled in the art, with the evolution of customer value assessment and the emergence of new business scenarios, the technical solution provided by the present application is also applicable to similar technical problems.

The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.

The present embodiment will be described from the perspective of a customer value evaluation device, which may be specifically integrated in a computer device, which may be a server, and the present application is not limited thereto.

Referring to fig. 2, fig. 2 is a schematic flow chart illustrating a customer value evaluation method according to an embodiment of the present application. The customer value evaluation method comprises the following steps:

in step 101, historical product transaction data of a customer to be evaluated in a first organization is obtained.

The first organization and the at least one second organization belong to a same organization, the organization can be a whole body formed by the at least one organization, and the first organization and the second organization can be social entities which are composed of a plurality of individuals or groups and have common targets and certain boundaries. For example, the organization may be an enterprise organization, e.g., a corporate group, and the first organization and the second organization may be subsidiaries in the organization. The financial products sold by the first organization may be configured to include financial products issued by the first organization and the second organization, and in particular, the financial products sold by the first organization may include products issued by the first organization and products issued by the second organization, for example, assuming that a certain organization is a group a, which has a flag of the first organization (subsidiary a) and the second organization (subsidiary b, third, etc.), for the first organization, the first organization may sell the products of the subsidiary a itself, and may also sell the products of the subsidiary b or c. The customer to be evaluated may be a customer of the first organization, and may also be a customer of the organization, and the value of the customer to be evaluated in the organization may be evaluated, and the financial product may be various carriers of a fund financing process, for example, various broad categories of products such as investments (investment, financing), insurance, bankers (bank deposit, etc.), leases, and the like, where the customer to be evaluated performs a transaction such as deposit or borrow in the first organization, and may also be regarded as purchasing a financial product of the first organization. The product historical transaction data may be transaction data generated by the to-be-evaluated customer historical to perform transaction actions on the first organization, for example, transaction data generated by the to-be-evaluated customer to purchase a product sold by the first organization, and the transaction data may include transaction information such as transaction time, transaction amount, transaction mode, and the like.

In step 102, historical transaction amounts of each historical transaction product of the customer to be evaluated are extracted from the product historical transaction data.

The historical transaction product may be a financial product corresponding to a transaction action of the customer to be evaluated in the first organization, the historical transaction amount may be a transaction amount of each historical transaction product transacted by the customer to be evaluated in the product historical transaction data, and the transaction amount may be an amount spent transacting a certain product.

In step 103, according to the product importance of each historical transaction product, the historical transaction amount of each historical transaction product is weighted to obtain the weighted transaction amount of each historical transaction product.

The product importance may be a degree of importance of the historical transaction product to the first organization or an organization corresponding to the first organization, and the weighted transaction amount may be a result of weighting the historical transaction amount of each historical transaction product based on the product importance of each historical transaction product.

For example, the product importance of each historical transaction product can be determined based on the positioning of the historical transaction product in the organizational development strategy established by the organization, for example, for an organizational structure of a bank enterprise, the importance of the product such as a bank deposit, a trade, and the like is greater than that of the product of an insurance class. The product importance of each historical transaction product may also be determined based on the profit generated by each historical transaction product, e.g., a high profit product importance is greater than a low profit product. The product importance of each historical trading product can also be determined according to the trading scale of each historical trading product, for example, the product with larger trading scale is more important than the product with smaller trading scale, and the like.

The problems that a set of large and complete service standard cannot be provided in the existing client value evaluation method to evaluate the client value of a client, so that the client cannot have a transversely pulled real and objective evaluation index system on the organizational level, and further cannot screen out measures for enabling the client with the same value to perform product coordination recommendation, client unified management and the like to improve the client value. Therefore, according to the product importance of each historical transaction product, the historical transaction amount of each historical transaction product can be weighted to obtain the weighted transaction amount of each historical transaction product, so that the evaluation standards among different products are unified. For example, the amount adjustment weight corresponding to each historical transaction product can be determined according to the product importance of each historical transaction product, so that the historical transaction amount of each historical transaction product can be weighted according to the amount adjustment weight corresponding to each historical transaction product, and the weighted transaction amount of each historical transaction product can be obtained.

Wherein the amount adjustment weight may be a weight for adjusting the historical transaction amount for each historical transaction product based on the product importance of each historical transaction product.

For example, the related service personnel can determine the money adjusting weight corresponding to each historical transaction product according to the set service rule and the product importance of each historical transaction product. Each historical transaction product can also be scored according to each factor influencing the product importance of the historical transaction product, and the historical transaction products are sorted according to the score of each historical transaction product, so that the corresponding money adjusting weight and the like can be set according to the ranking of each historical transaction product.

In step 104, an allocation amount allocated to the first organization in the weighted transaction amounts of the historical transaction products is determined for the historical transaction products issued by the second organization.

The allocated amount can be the amount allocated to the first organization in the weighted transaction amount corresponding to the historical transaction products issued by the second organization.

The financial products provided by the first organization comprise products issued by the second organization, and the historical transaction amount generated by the historical transaction products issued by the second organization does not belong to the first organization, the first organization is used as a channel seller, the second organization is used as a product issuer, and the historical transaction amount generated by the historical transaction products issued by the second organization is shared by different shares, so that the transaction data of the customer to be evaluated in each organization can be further refined by distributing the historical transaction amount generated by the historical transaction products issued by the second organization in the first organization and the second organization, and the customer value of the customer to be evaluated in each organization can be more accurately evaluated.

For example, product income distribution information corresponding to the historical transaction products issued by the second organization may be acquired, an amount distribution proportion corresponding to the historical transaction products issued by the second organization is identified based on the product income distribution information, and the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products issued by the second organization is calculated according to the amount distribution proportion.

The product profit allocation information may include information for allocating profits of products, and the product profit allocation information corresponding to each historical transaction product may be configured by related business personnel, that is, the profit allocation rule of each product may be determined according to a specific business rule. The amount distribution proportion may be a proportion of the historical transaction amount corresponding to the historical transaction product issued by the second organization, which is determined based on the distribution rule indicated in the product profit distribution information. For example, the money allocation ratio may be (first organization: second organization) = 4: and 6, four tenths of the historical transaction amount can be distributed to the first organization as the distribution amount.

For example, suppose that the organization comprises a first organization a and a second organization b, wherein the first organization a sells the product c of the second organization b, and according to the business rule set by the business personnel, the transaction amount generated after the first organization sells the product c is according to 3: 7 to the first organization and to the second organization. Meanwhile, assuming that a customer to be evaluated purchases a product c, a historical transaction amount D is generated and weighted to obtain a weighted transaction amount E, so that an amount distribution ratio of 3 can be obtained according to product income distribution information corresponding to the product c: 7, it can thus be determined from the amount allocation ratio that the allocated amount of the weighted transaction amount E allocated to the first organization is E × 3/(3 + 7) = E × 3/10.

In step 105, the customer value of the customer to be assessed is assessed based on the weighted transaction amount and the allocated amount corresponding to the historical transaction product issued by the first organization.

In terms of an enterprise organization, the customer value may be enterprise income realized by the organization from the purchasing behavior of the customer, and the customer value may be value which can be created for the enterprise by the customer measured according to variables such as the transaction behavior and the consumption characteristics of the customer in the organization.

For example, the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the allocation amount may be accumulated to obtain a target transaction amount of the customer to be evaluated in the first organization, the product historical transaction data may be updated based on the target transaction amount to obtain target product transaction data, and the customer value of the customer to be evaluated may be evaluated according to the target product transaction data.

The target transaction amount is the result of accumulating the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the allocation amount, namely the amount allocated to the first organization in the weighted transaction amount generated in the historical transaction behavior of the customer to be evaluated in the first organization. The target product transaction data may be product historical transaction data in which a corresponding historical transaction amount in the product historical transaction data is replaced based on a target transaction amount.

For example, suppose that an organization includes a first organization a and a second organization b, wherein the products sold by the first organization a include a product d, a product e and a product c provided by the first organization, and according to the business rules set by the business personnel, the transaction amount generated after the first organization sells the product c is according to 3: 7 to the first organization and to the second organization. Meanwhile, assuming that a customer F to be evaluated purchases a product c and a product d, the purchase of the product c generates a historical transaction amount G, and the weighted transaction amount G is obtained after weighting, so that an amount distribution ratio of 3 can be obtained according to product income distribution information corresponding to the product c: 7, according to the amount distribution ratio, the distribution amount distributed to the first organization in the weighted transaction amount G is determined to be gx 3/(3 + 7) = gx 3/10, and the historical transaction amount H generated by purchasing the product d is weighted to obtain the weighted transaction amount H, so that the weighted transaction amount H corresponding to the product d and the distribution amount corresponding to the product c can be accumulated to obtain the target transaction amount (H + gx 3/10) of the customer to be evaluated in the first organization.

For example, the target product transaction data may be counted to obtain a multidimensional transaction index, the to-be-evaluated customers are clustered based on the transaction index to obtain at least one category set and category labels corresponding to the category set, and the customer value of the to-be-evaluated customer is evaluated based on the transaction index and the category labels to obtain a customer value evaluation result corresponding to the to-be-evaluated customer.

Wherein, the multi-dimensional transaction index can be a statistical index in the target product transaction data in multiple dimensions, the index which can be used for evaluating the transaction behavior of the customer to be evaluated can include, for example, the indexes of cooperation duration, transaction frequency, transaction scale and the time interval of the last transaction, the category set can be a plurality of category sets obtained by clustering the clients to be evaluated according to the transaction index, each category set can be an integer formed by at least one client to be evaluated, the category label may be a label corresponding to the category set, and may be used to characterize common transaction characteristics of each customer to be evaluated in the category set, after the customers to be evaluated are classified, the customers can be assigned with values integrally according to the customer characteristics of each category set, for example, automatic batch marking can be adopted to label each category set. The customer value evaluation result may be a result obtained by evaluating the customer value corresponding to each customer to be evaluated.

For example, a customer relationship management model (RFM, a customer value evaluation analysis model) may be adopted, and according to three dimensions, namely a time interval (Recency) of the last transaction of a customer to be evaluated in a first organization, a customer transaction Frequency (Frequency), and a customer transaction scale (Monetary), of the customer to be evaluated in the first organization, and according to the organization plus the customer as a granularity, various transaction indexes of each customer to be evaluated are counted in the target product transaction data.

After the transaction data of the target product is counted, clustering processing can be performed on the customer to be evaluated based on the transaction index, so as to obtain at least one category set and category labels corresponding to the category set. The method for clustering the customers to be evaluated based on the transaction index may be various, for example, an unsupervised clustering algorithm (e.g., K-Means algorithm) may be used to cluster the customers to be evaluated based on the transaction index, and optionally, objective and effective classification evaluation may be performed on the customer group corresponding to the customers to be evaluated by calculating the profile coefficient.

After clustering processing is performed on the customer to be evaluated based on the transaction index, the customer value of the customer to be evaluated can be evaluated based on the transaction index and the category label. For example, a scoring card model may be constructed based on the transaction index, the category label is used as a dependent variable corresponding to the scoring card model, the customer to be evaluated is scored according to the scoring card model to obtain an evaluation score corresponding to the customer to be evaluated, and a customer value evaluation result corresponding to the customer to be evaluated is determined based on the evaluation score.

The category label can be used as a dependent variable (Y value) corresponding to the scoring card model, so that the scoring card model can be constructed based on the transaction index, at the moment, the scoring card model can adopt some scoring models, scoring is performed on each transaction index corresponding to the customer according to transaction behavior data such as the transaction index of the customer and the category label, and accordingly the customer value and the like of the customer to be assessed are determined according to the assessment score.

From the above, by acquiring historical product transaction data of a customer to be evaluated in a first organization, the first organization and at least one second organization belong to the same group of organizations, and financial products sold by the first organization can be configured to include financial products issued by the first organization and the second organization; extracting historical transaction amount of each historical transaction product of a customer to be evaluated from the product historical transaction data; according to the product importance of each historical transaction product, weighting the historical transaction amount of each historical transaction product to obtain the weighted transaction amount of each historical transaction product; determining the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products issued by the second organization; and evaluating the customer value of the customer to be evaluated based on the weighted transaction amount and the distribution amount corresponding to the historical transaction product issued by the first organization. Thus, the historical transaction amount of each historical transaction product is weighted according to the product importance of the historical transaction product, so that the difference between different products is pulled through, and meanwhile, distributing the weighted transaction amount corresponding to the historical transaction product issued by the second organization according to the issuing source of the historical transaction product, thereby realizing the quantitative integration of the product historical transaction data of the evaluation customers in the first organization based on the integral proportion of the organization, therefore, the client value evaluation is carried out on the client to be evaluated based on the weighted transaction amount and the distribution amount corresponding to each organization, the scale statistical mode of the transaction behavior among different organizations in the organization under the condition that the product type and the transaction mode are different is standardized, therefore, an index system for evaluating the value of the client by each organization in an organization is unified, and the accuracy of the value evaluation result of the client is improved.

The method described in the above examples is further illustrated in detail below by way of example.

In this embodiment, a specific description will be given by taking an example in which the customer value evaluation device is specifically integrated in a server.

For a better description of the embodiments of the present application, please refer to fig. 3. As shown in fig. 3, fig. 3 is another schematic flow chart of a customer value evaluation method provided in the embodiment of the present application. The specific process is as follows:

in step 201, the server obtains historical transaction data of a customer to be evaluated in a first organization, and extracts a historical transaction amount of each historical transaction product of the customer to be evaluated from the historical transaction data of the product.

The first organization may be a professional sub-company in an organization such as a group, the organization may further include at least one second organization, the financial products sold by the first organization may include products issued by the first organization and products issued by the second organization, for example, assuming that a certain organization is a group a and a group a has a first organization (a sub-company a) and a second organization (a sub-company b, a sub-company c, etc.), for the first organization, the first organization may sell products of the sub-company a itself, and may also sell products of the sub-companies b or c. The historical transaction products may include various broad categories of financial products for financing (investment, financing), insurance, banking (bank deposit, etc.), leasing, etc. The product historical transaction data may be transaction data generated by the to-be-evaluated customer historical to perform transaction actions on the first organization, for example, transaction data generated by the to-be-evaluated customer to purchase a product sold by the first organization, and the transaction data may include transaction information such as transaction time, transaction amount, transaction mode, and the like. The historical transaction amount may be a transaction amount of each historical transaction product to be traded by the customer to be evaluated in the product historical transaction data, and the transaction amount may be an amount spent trading a certain product.

In step 202, the server obtains product value information of each historical transaction product, determines an amount adjustment weight corresponding to each historical transaction product according to the product value information, and performs weighting processing on the historical transaction amount corresponding to each historical transaction product based on the amount adjustment weight to obtain a weighted transaction amount of each historical transaction product.

The product value information may be information representing the value of the historical transaction product, and may include information such as transaction unit price, sales volume, etc. of the historical transaction product.

For example, the historical transaction unit price of each historical transaction product and the total transaction amount of each historical transaction product in the organization can be extracted from the product value information, the ratio of the historical transaction amount corresponding to each historical transaction product to the historical transaction unit price is calculated to obtain the historical transaction amount corresponding to each historical transaction product, and the amount adjusting weight corresponding to each historical transaction product is determined according to the historical transaction amount corresponding to each historical transaction product and the total transaction amount.

The historical transaction unit price may be a sale unit price corresponding to a historical transaction product in the historical transaction behavior of the first organization of the customer to be evaluated, the total transaction amount may be a transaction amount resulting from a transaction behavior of the historical transaction product in an organization corresponding to the first organization, and the total transaction amount may be a transaction amount resulting from a transaction behavior of the historical transaction product in an organization corresponding to the first organization within a certain period of time. The historical transaction amount may be a ratio of the historical transaction amount to the historical transaction unit price. For example, assuming that a customer z purchases a product c provided by a first organization and pays 5000 dollars, the selling unit price of the product c is 1000 dollars, and the product c generates 50 ten thousand of transaction amounts in the organization corresponding to the first organization, the historical transaction unit price of the product c is 1000 dollars, the historical transaction amount of the product c purchased by the customer z is 5000/1000=5, and the total transaction amount is 50 ten thousand.

For example, a ratio of the historical transaction amount corresponding to each historical transaction product to the total transaction amount corresponding thereto may be calculated, and the amount adjustment weight corresponding to each historical transaction product is obtained according to the ratio, for example, for the customer z, the amount adjustment weight corresponding to the historical transaction amount corresponding to the product c may be 5/50 ten thousands.

In one embodiment, the monetary adjustment weight for each historical transaction product may be determined by the associated business person based on business rules.

In step 203, the server obtains the distribution information of the product income corresponding to the historical transaction products issued by the second organization, identifies the allocation proportion of the money amount corresponding to the historical transaction products issued by the second organization based on the distribution information of the product income, and calculates the distribution money amount allocated to the first organization in the weighted transaction money amount of the historical transaction products issued by the second organization according to the allocation proportion of the money amount.

The product profit allocation information may include information for allocating profits of products, and the product profit allocation information corresponding to each historical transaction product may be configured by related business personnel, that is, the profit allocation rule of each product may be determined according to a specific business rule. The amount distribution proportion may be a proportion of the historical transaction amount corresponding to the historical transaction product issued by the second organization, which is determined based on the distribution rule indicated in the product profit distribution information.

For example, suppose that the organization comprises a first organization a and a second organization b, wherein the first organization a sells the product c of the second organization b, and according to the business rule set by the business personnel, the transaction amount generated after the first organization sells the product c is according to 3: 7 to the first organization and to the second organization. Meanwhile, assuming that a customer to be evaluated purchases a product c, a historical transaction amount D is generated and weighted to obtain a weighted transaction amount E, so that the server can obtain an amount distribution ratio of 3 according to product income distribution information corresponding to the product c: the server may thus determine that the allocation amount allocated to the first organization in the weighted transaction amount E is E × 3/(3 + 7) = E × 3/10 according to the amount allocation ratio.

In step 204, the server accumulates the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the allocated amount to obtain a target transaction amount of the customer to be evaluated in the first organization, and updates the historical transaction data of the product based on the target transaction amount to obtain the transaction data of the target product.

The target transaction amount is the result of accumulating the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the distribution amount, namely the amount distributed to the first organization in the weighted transaction amount generated in the historical transaction behavior of the customer to be evaluated in the first organization. The target product transaction data may be product historical transaction data in which a corresponding historical transaction amount in the product historical transaction data is replaced based on a target transaction amount.

For example, suppose that an organization includes a first organization a and a second organization b, wherein the products sold by the first organization a include a product d, a product e and a product c provided by the first organization, and according to the business rules set by the business personnel, the transaction amount generated after the first organization sells the product c is according to 3: 7 to the first organization and to the second organization. Meanwhile, assuming that a customer F to be evaluated purchases a product c and a product d, the purchase of the product c generates a historical transaction amount G, and the weighted transaction amount G is obtained after weighting, so that the server can obtain an amount distribution ratio of 3 according to product income distribution information corresponding to the product c: and 7, the server can determine that the distribution amount allocated to the first organization in the weighted transaction amount G is gx 3/(3 + 7) = gx 3/10 according to the amount distribution ratio, and the purchase product d generates a historical transaction amount H and obtains a weighted transaction amount H after weighting, so that the weighted transaction amount H corresponding to the product d and the distribution amount corresponding to the product c can be accumulated to obtain the target transaction amount (H + gx 3/10) of the customer to be evaluated in the first organization.

In step 205, the server performs statistics on the transaction data of the target product to obtain a multidimensional transaction index, and performs clustering processing on the customer to be evaluated based on the transaction index to obtain at least one category set and a category label corresponding to the category set.

For example, the server may adopt a customer relationship management model (RFM, a customer value evaluation analysis model), and respectively count various transaction indexes of each customer to be evaluated in the target product transaction data according to three dimensions, namely a time interval of the last transaction of the customer to be evaluated in the first organization, a customer transaction frequency and a customer transaction scale, and the organization plus the customer as a granularity.

After the server counts the transaction data of the target product, the server can perform clustering processing on the customer to be evaluated based on the transaction index to obtain at least one category set and a category label corresponding to the category set. The server may perform clustering processing on the to-be-evaluated customer based on the transaction index, for example, the server may perform clustering processing on the to-be-evaluated customer based on the transaction index by using an unsupervised clustering algorithm (e.g., a K-Means algorithm), and optionally, may perform objective and effective classification evaluation on a customer group corresponding to the to-be-evaluated customer by calculating a contour coefficient.

In step 206, the server constructs a rating card model based on the transaction index, takes the category label as a dependent variable corresponding to the rating card model, scores the customer to be evaluated according to the rating card model to obtain an evaluation score corresponding to the customer to be evaluated, and determines a customer value evaluation result corresponding to the customer to be evaluated based on the evaluation score.

The server can use the category label as a dependent variable (Y value) corresponding to the scoring card model, so that the scoring card model can be constructed based on the transaction index, at the moment, the scoring card model can adopt some scoring models, scoring is performed on each transaction index corresponding to the client according to transaction behavior data such as the transaction index of the client and the category label, and accordingly the client value of the client to be assessed is determined according to the assessment score.

As can be seen from the above, in the embodiment of the application, the server obtains the historical transaction data of the to-be-evaluated customer in the first organization, and the historical transaction amount of each historical transaction product of the to-be-evaluated customer is extracted from the historical transaction data of the product; the server acquires product value information of each historical transaction product, determines a money amount adjusting weight corresponding to each historical transaction product according to the product value information, and performs weighting processing on the historical transaction money amount corresponding to each historical transaction product based on the money amount adjusting weight to obtain a weighted transaction money amount of each historical transaction product; the server acquires product income distribution information corresponding to the historical transaction products issued by the second organization, identifies the money distribution proportion corresponding to the historical transaction products issued by the second organization based on the product income distribution information, and calculates the distribution money distributed to the first organization in the weighted transaction money of the historical transaction products issued by the second organization according to the money distribution proportion; the server accumulates the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the allocated amount to obtain a target transaction amount of the customer to be evaluated in the first organization, and updates the historical transaction data of the product based on the target transaction amount to obtain target product transaction data; the server counts the transaction data of the target product to obtain a multi-dimensional transaction index, and performs clustering processing on the customer to be evaluated based on the transaction index to obtain at least one category set and a category label corresponding to the category set; the server constructs a scoring card model based on the transaction index, takes the category label as a dependent variable corresponding to the scoring card model, scores the client to be evaluated according to the scoring card model to obtain an evaluation score corresponding to the client to be evaluated, and determines a client value evaluation result corresponding to the client to be evaluated based on the evaluation score. Therefore, the adjustment weight of the amount corresponding to each historical transaction product is determined according to the product value information of the historical transaction products, the historical transaction amount of each historical transaction product is weighted, the difference among different products is pulled through, meanwhile, the weighted transaction amount corresponding to the historical transaction product issued by the second organization is distributed according to the issuing source of the historical transaction product, the fine-grained quantitative integration of the product historical transaction data of the evaluation client in the first organization based on the integral proportion of the organization is realized, the product historical transaction data is updated based on the weighted transaction amount and the distributed amount corresponding to each organization, the target product transaction data is obtained, the multi-dimensional transaction indexes are counted in the target product transaction data, and the clustering processing is carried out on the client to be evaluated based on the transaction indexes, the method comprises the steps of obtaining at least one category set and category labels corresponding to the category sets, constructing a scoring card model to score a customer to be assessed, determining a customer value assessment result corresponding to the customer to be assessed based on assessment scores, standardizing a scale statistical mode of transaction behaviors among different organizations in an organization under the condition that product types and transaction modes are different, further unifying an index system of the customer value assessment of each organization in the organization, accurately assessing the customer value of the customer in the organization, and further improving the accuracy of the customer value assessment result.

In order to better implement the above method, the embodiment of the present invention further provides a client value evaluation device, which may be integrated in a server.

For example, as shown in fig. 4, for a schematic structural diagram of a customer value evaluation device provided in an embodiment of the present application, the customer value evaluation device may include an obtaining unit 301, an extracting unit 302, a weighting unit 303, a determining unit 304, and an evaluating unit 305, as follows:

an obtaining unit 301, configured to obtain product historical transaction data of a customer to be evaluated in a first organization, wherein the first organization and at least one second organization belong to the same group of organizations, and financial products sold by the first organization can be configured to include financial products issued by the first organization and the second organization;

an extracting unit 302, configured to extract a historical transaction amount of each historical transaction product of the customer to be evaluated from the product historical transaction data;

the weighting unit 303 is configured to perform weighting processing on the historical transaction amount of each historical transaction product according to the product importance of each historical transaction product, so as to obtain a weighted transaction amount of each historical transaction product;

a determining unit 304, configured to determine, for historical transaction products issued by the second organization, an allocation amount allocated to the first organization in the weighted transaction amounts of the historical transaction products;

the evaluation unit 305 is configured to evaluate the customer value of the customer to be evaluated based on the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the allocation amount.

In one embodiment, the determining unit 304 includes:

a product profit allocation information obtaining subunit, configured to obtain product profit allocation information corresponding to the historical transaction product issued by the second organization;

the proportion distribution identification subunit is used for identifying the amount distribution proportion corresponding to the historical transaction product issued by the second organization based on the product income distribution information;

and the distribution amount calculation subunit is used for calculating the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products issued by the second organization according to the amount distribution proportion.

In one embodiment, the weighting unit 303 includes:

In one embodiment, the weight determining subunit includes:

In one embodiment, the evaluation unit 305 includes:

the updating subunit is used for updating the historical transaction data of the product based on the target transaction amount to obtain the transaction data of the target product;

In one embodiment, the evaluation subunit includes:

the statistic module is used for carrying out statistics on the transaction data of the target product to obtain a multi-dimensional transaction index;

the clustering module is used for clustering the to-be-evaluated customers based on the transaction index to obtain at least one category set and category labels corresponding to the category set;

In one embodiment, the evaluation module includes:

the construction submodule is used for constructing a scoring card model based on the transaction index and taking the category label as a dependent variable corresponding to the scoring card model;

the scoring submodule is used for scoring the customer to be assessed according to the scoring card model to obtain an assessment score corresponding to the customer to be assessed;

In specific implementation, the above units may be implemented as independent entities, or may be combined arbitrarily, and implemented as the same or several entities, and specific implementations of the above units may refer to the foregoing method embodiment, which is not described herein again.

As can be seen from the above, in the embodiment of the present application, the obtaining unit 301 obtains the product historical transaction data of the customer to be evaluated in the first organization, where the first organization and at least one second organization belong to the same group of organizations, and the financial products sold by the first organization may be configured to include financial products issued by the first organization and the second organization; the extracting unit 302 extracts the historical transaction amount of each historical transaction product of the customer to be evaluated from the product historical transaction data; the weighting unit 303 weights the historical transaction amount of each historical transaction product according to the product importance of each historical transaction product to obtain the weighted transaction amount of each historical transaction product; the determination unit 304 determines, for the historical transaction products issued by the second organization, an allocation amount allocated to the first organization from among weighted transaction amounts of the historical transaction products; the evaluation unit 305 evaluates the customer value of the customer to be evaluated based on the weighted transaction amount and the allocation amount corresponding to the historical transaction product issued by the first organization. Thus, the historical transaction amount of each historical transaction product is weighted according to the product importance of the historical transaction product, so that the difference between different products is pulled through, and meanwhile, distributing the weighted transaction amount corresponding to the historical transaction product issued by the second organization according to the issuing source of the historical transaction product, thereby realizing the quantitative integration of the product historical transaction data of the evaluation customers in the first organization based on the integral proportion of the organization, therefore, the client value evaluation is carried out on the client to be evaluated based on the weighted transaction amount and the distribution amount corresponding to each organization, the scale statistical mode of the transaction behavior among different organizations in the organization under the condition that the product type and the transaction mode are different is standardized, therefore, an index system for evaluating the value of the client by each organization in an organization is unified, and the accuracy of the value evaluation result of the client is improved.

An embodiment of the present application further provides a computer device, as shown in fig. 5, which shows a schematic structural diagram of a computer device according to an embodiment of the present application, where the computer device may be a server, and specifically:

the computer device may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 5 does not constitute a limitation of computer devices, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. Wherein:

the processor 401 is a control center of the computer device, connects various parts of the entire computer device using various interfaces and lines, and performs various functions of the computer device and processes data by running or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby performing overall detection of the computer device. Alternatively, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.

The memory 402 may be used to store software programs and modules that the processor 401 executes to perform various functional applications and customer value evaluations by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.

The computer device further comprises a power supply 403 for supplying power to the various components, and preferably, the power supply 403 is logically connected to the processor 401 via a power management system, so that functions of managing charging, discharging, and power consumption are implemented via the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

The computer device may also include an input unit 404, the input unit 404 being operable to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the computer device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 401 in the computer device loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application programs stored in the memory 402, thereby implementing various functions as follows:

acquiring historical product transaction data of a customer to be evaluated in a first organization, wherein the first organization and at least one second organization belong to the same group of organization, and financial products sold by the first organization can be configured to comprise financial products issued by the first organization and the second organization; extracting historical transaction amount of each historical transaction product of a customer to be evaluated from the product historical transaction data; according to the product importance of each historical transaction product, weighting the historical transaction amount of each historical transaction product to obtain the weighted transaction amount of each historical transaction product; determining the distribution amount distributed to the first organization in the weighted transaction amount of the historical transaction products issued by the second organization; and evaluating the customer value of the customer to be evaluated based on the weighted transaction amount and the distribution amount corresponding to the historical transaction product issued by the first organization.

The above operations can be implemented in the foregoing embodiments, and are not described in detail herein. It should be noted that the computer device provided in the embodiment of the present application and the method for evaluating a customer value in the foregoing embodiment belong to the same concept, and specific implementation processes thereof are described in the foregoing method embodiment, and are not described herein again.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, embodiments of the present application provide a computer-readable storage medium having stored therein a plurality of instructions, which can be loaded by a processor to perform the steps of any of the customer value assessment methods provided by embodiments of the present application. For example, the instructions may perform the steps of:

Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the instructions stored in the computer-readable storage medium can execute the steps in any of the customer value evaluation methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the customer value evaluation methods provided in the embodiments of the present application can be achieved, which are detailed in the foregoing embodiments and will not be described again here.

According to an aspect of the application, there is provided, among other things, a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations provided by the embodiments described above.

The above detailed description is provided for a method, an apparatus, and a computer-readable storage medium for evaluating a customer value provided in the embodiments of the present application, and specific examples are applied herein to illustrate the principles and implementations of the present application, and the descriptions of the above embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A customer value assessment method, comprising:

2. The customer value evaluation method of claim 1, wherein determining an allocated amount of the weighted transaction amounts of the historical transaction products for historical transaction products issued by the second organization that is allocated to the first organization comprises:

acquiring product income distribution information corresponding to historical trading products issued by the second organization;

identifying a money allocation proportion corresponding to the historical transaction product issued by the second organization based on the product income allocation information;

and calculating the distribution amount distributed to the first organization in the weighted transaction amounts of the historical transaction products issued by the second organization according to the amount distribution proportion.

3. The method for assessing customer value according to claim 1, wherein said weighting the historical transaction amount of each historical transaction product according to the product importance of each historical transaction product to obtain a weighted transaction amount of each historical transaction product comprises:

acquiring product value information of each historical transaction product;

determining the corresponding money adjusting weight of each historical transaction product according to the product value information;

and carrying out weighting processing on the historical transaction amount corresponding to each historical transaction product based on the amount adjusting weight to obtain the weighted transaction amount of each historical transaction product.

4. The customer value assessment method of claim 3, wherein said determining a monetary adjustment weight for each historical transaction product based on said product value information comprises:

extracting the historical trading unit price of each historical trading product and the total trading amount of each historical trading product in the organization from the product value information;

calculating the historical transaction amount corresponding to each historical transaction product and the ratio of the historical transaction unit price to obtain the historical transaction amount corresponding to each historical transaction product;

and determining the money regulating weight corresponding to each historical transaction product according to the historical transaction amount corresponding to each historical transaction product and the total transaction money.

5. The method of assessing customer value of claim 1, wherein said assessing customer value of said customer to be assessed based on said weighted transaction amount and said allocated amount corresponding to historical transaction products issued by said first organization comprises:

accumulating the weighted transaction amount corresponding to the historical transaction product issued by the first organization and the distribution amount to obtain a target transaction amount of the customer to be evaluated in the first organization;

updating the historical product transaction data based on the target transaction amount to obtain target product transaction data;

and evaluating the customer value of the customer to be evaluated according to the target product transaction data.

6. The method of assessing customer value according to claim 5, wherein said assessing the customer value of said customer to be assessed based on said target product transaction data comprises:

counting the target product transaction data to obtain a multi-dimensional transaction index;

clustering the to-be-evaluated customers based on the transaction indexes to obtain at least one category set and category labels corresponding to the category sets;

and evaluating the customer value of the customer to be evaluated based on the transaction index and the category label to obtain a customer value evaluation result corresponding to the customer to be evaluated.

7. The method for evaluating customer value according to claim 6, wherein the evaluating the customer value of the customer to be evaluated based on the transaction index and the category label to obtain a customer value evaluation result corresponding to the customer to be evaluated comprises:

constructing a scoring card model based on the transaction indexes, and taking the category label as a dependent variable corresponding to the scoring card model;

grading the customer to be evaluated according to the grading card model to obtain an evaluation score corresponding to the customer to be evaluated;

and determining a customer value evaluation result corresponding to the customer to be evaluated based on the evaluation score.

8. A customer value evaluation apparatus, comprising:

the extracting unit is used for extracting the historical transaction amount of each historical transaction product of the customer to be evaluated from the product historical transaction data;

9. A computer readable storage medium storing instructions adapted to be loaded by a processor to perform the steps of the customer value assessment method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor; the memory stores an application program, and the processor is configured to execute the application program in the memory to perform the steps of the customer value evaluation method according to any one of claims 1 to 7.