Customer value evaluation method, customer level identification method, device, equipment and medium

Abstract

The invention provides a customer value evaluation method, a customer grade identification method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of value evaluation and grading. The evaluation method comprises the following steps: acquiring multi-source portrait data of a customer; value evaluation indexes of the customer are evaluated according to the multi-source portrait data, and the value evaluation indexes comprise one or more of the following: a business penetration type, an income scale, future income contribution, a business opportunity conversion amount, loyalty, credit, operation safety and an importance category; according to the value evaluation index, the score of the customer in the value dimension is determined, and the value dimension comprises one or more of the following dimensions: the current contribution dimension, the development potential dimension, the cooperation stability dimension, the performance credit dimension, the operation health degree dimension and the strategic importance dimension. The problems that in the prior art, grading dimensions are not comprehensive, and grading accuracy and practical operability are insufficient are at least solved. The method is suitable for value evaluation and grading scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of value assessment and grading, and particularly relates to a customer value assessment method, a customer grade identification method, a device, electronic equipment and a computer readable storage medium. BACKGROUND

[0002] In the field of enterprise customer management, customer value grading is a key means to realize precise operation and optimize resource allocation. Through a systematic grading system, enterprises can clearly identify customers at different value levels and develop differentiated service strategies and marketing plans, thereby improving customer satisfaction, loyalty and overall enterprise revenue.

[0003] Traditional customer value grading methods focus on a single dimension of customer income, resulting in grading results that cannot truly reflect the comprehensive value of customers to the enterprise and are difficult to support differentiated services and marketing decisions.

[0004] Moreover, existing technologies rely on manual scoring or basic statistical methods. Simply relying on manual scoring is susceptible to subjective factors, and relying solely on basic statistics is difficult to handle complex customer data correlation, resulting in low accuracy of grading results, which is difficult to land in business scenarios and cannot balance scientificity and operability.

[0005] In summary, related technologies have incomplete scoring dimensions that are not consistent with actual business needs, and single technical paths have insufficient grading accuracy and operability. SUMMARY

[0006] The technical problem to be solved by the present application is to overcome the above-mentioned deficiencies of the prior art, and to provide a customer value assessment method, a customer grade identification method, a device, electronic equipment and a computer readable storage medium, which can realize comprehensive and accurate customer value assessment and customer grade identification.

[0007] In a first aspect, the present application provides a customer value assessment method, comprising: obtaining multi-source portrait data of a customer, wherein the multi-source portrait data refers to a set of information related to the customer obtained from multiple data sources; evaluating a value evaluation index of the customer according to the multi-source portrait data, wherein the value evaluation index includes one or more of the following: business penetration type, income scale, future income contribution, opportunity conversion amount, loyalty, credit, business safety, importance category; determining the score of the customer in the value dimension according to the value evaluation index, wherein the value dimension includes one or more of the following: current contribution dimension, development potential dimension, cooperation stability dimension, credit compliance dimension, business health dimension, strategic importance dimension.

[0008] Preferably, the multi-source portrait data includes business data, overdue payment data, income data, business opportunity data, business data, and account data, and the value evaluation index of the customer is evaluated according to the multi-source portrait data, specifically including: identifying the business penetration type, the contribution type, the attribute, and the importance category of the customer according to the multi-source portrait data; evaluating the income scale, the future income contribution, the business opportunity conversion amount, and the loyalty of the customer according to the income data, the account data, and the business opportunity data; evaluating the credit degree of the customer according to the contribution type and the overdue payment data; and evaluating the business safety of the customer according to the contribution type, the attribute, and the business data.

[0009] Preferably, the contribution type includes one of high-income contribution and small-and-medium-income contribution, the overdue payment data includes one or more of the current overdue ratio, the maximum overdue ratio, the long account age accounts receivable proportion, the threshold value cumulative month number, the continuous overdue times, the overdue payment times, and the short account age accounts receivable proportion, and the credit degree of the customer is evaluated according to the contribution type and the overdue payment data, specifically including: judging the contribution type of the customer; in response to the contribution type being high-income contribution, evaluating the credit degree of the customer according to the current overdue ratio, the maximum overdue ratio, the long account age accounts receivable proportion, and the threshold value cumulative month number; and in response to the contribution type being small-and-medium-income contribution, evaluating the credit degree of the customer according to the current overdue ratio, the threshold value cumulative month number, the continuous overdue times, the overdue payment times, and the short account age accounts receivable proportion.

[0010] Preferably, the attribute includes one of enterprise type and non-enterprise type, the business data includes one or more of the total number of historical stock rights being frozen, the annual average number of administrative penalties, the annual average number of business scope changes, the annual average number of cases under investigation, the registered capital of the enterprise, the establishment length of the enterprise, the total number of historical non-investment shareholder changes, the percentage of the stock rights of the investment shareholders, and the maximum account age of the online user, and the business safety of the customer is evaluated according to the contribution type, the attribute, and the business data, specifically including: judging the attribute of the customer; in response to the attribute being non-enterprise type, determining the business safety of the customer as a first preset value; in response to the attribute being enterprise type, judging the contribution type of the customer; in response to the contribution type being high-income contribution, evaluating the business safety of the customer according to the total number of historical stock rights being frozen, the annual average number of administrative penalties, the annual average number of business scope changes, the annual average number of cases under investigation, the registered capital of the enterprise, the establishment length of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the stock rights of the investment shareholders; and in response to the contribution type being small-and-medium-income contribution, evaluating the business safety of the customer according to the annual average number of administrative penalties, the annual average number of business scope changes, the registered capital of the enterprise, the establishment length of the enterprise, and the maximum account age of the online user.

[0011] Preferably, the score of the customer in the value dimension is determined according to the value evaluation index, and specifically includes: matching the scores corresponding to the business penetration type, the income scale, the future income prediction value and the importance category from a preset mapping table, wherein the future income prediction value is a weighted sum result of the future income contribution and the opportunity conversion amount, and the preset mapping table includes a mapping relationship between the scores and the business penetration type, the income scale, the future income prediction value and the importance category; performing weighted sum on the scores corresponding to the business penetration type and the income scale to obtain the score of the customer in the current contribution dimension; determining the loyalty, the credit and the business safety as the scores of the customer in the cooperation stability dimension, the performance credit dimension and the business health dimension respectively; and determining the scores corresponding to the future income prediction value and the importance category as the scores of the customer in the development potential dimension and the strategic importance dimension.

[0012] In a second aspect, the present application further provides a method for identifying the grades of customers, which includes: obtaining the scores of a plurality of customers in the value dimension, wherein the scores are obtained by the method for evaluating the value of customers provided in the first aspect; performing weighted sum on the scores to obtain the comprehensive value scores of the plurality of customers; and identifying the grades of the plurality of customers based on the clustering algorithm and the comprehensive value scores.

[0013] In a third aspect, the present application further provides a device for evaluating the value of customers, which includes a first obtaining module, an evaluating module and a determining module. The first obtaining module is used to obtain the multi-source portrait data of a customer, wherein the multi-source portrait data refers to a set of information related to the customer obtained from a plurality of data sources. The evaluating module is used to evaluate the value evaluation index of the customer according to the multi-source portrait data, wherein the value evaluation index includes one or more of the following: the business penetration type, the income scale, the future income contribution, the opportunity conversion amount, the loyalty, the credit, the business safety and the importance category. The determining module is used to determine the score of the customer in the value dimension according to the value evaluation index, wherein the value dimension includes one or more of the following: the current contribution dimension, the development potential dimension, the cooperation stability dimension, the performance credit dimension, the business health dimension and the strategic importance dimension.

[0014] In a fourth aspect, the present application further provides a device for identifying the grades of customers, which includes a second obtaining module, a weighted sum module and an identifying module. The second obtaining module is used to obtain the scores of a plurality of customers in the value dimension, wherein the scores are obtained by the device for evaluating the value of customers provided in the third aspect. The weighted sum module is used to perform weighted sum on the scores to obtain the comprehensive value scores of the plurality of customers. The identifying module is used to identify the grades of the plurality of customers based on the clustering algorithm and the comprehensive value scores.

[0015] In a fifth aspect, the present application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the customer value evaluation method of the first aspect or the customer level identification method of the second aspect.

[0016] In a sixth aspect, the present application further provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the customer value evaluation method of the first aspect or the customer level identification method of the second aspect.

[0017] The customer value evaluation method, the customer level identification method, the device, the electronic device and the computer readable storage medium provided by the present application can improve the accuracy and comprehensiveness of customer value evaluation by constructing a six-dimensional value evaluation system comprising current contribution (revenue scale, business penetration type), development potential (future revenue, opportunity conversion), cooperation stability (loyalty), performance credit (credit), and strategic importance (importance category of customer relationship), covering the whole life cycle of a customer. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of the customer value evaluation method of the first embodiment of the present application; Figure 2 A flowchart of the customer level identification method of the second embodiment of the present application; Figure 3 A structural schematic diagram of the customer value evaluation device of the third embodiment of the present application; Figure 4 A structural schematic diagram of the customer level identification device of the fourth embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the technical solution of the present application better understood by those skilled in the art, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0020] It can be understood that the specific embodiments and drawings described herein are only used to explain the present application, but not to limit the present application.

[0021] It can be understood that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0022] It can be understood that, for the purpose of description, only the parts related to the present application are shown in the drawings of the present application, and the parts unrelated to the present application are not shown in the drawings.

[0023] It is understood that each unit or module involved in the embodiments of the present invention may correspond to only one entity structure, or may be composed of multiple entity structures, or multiple units or modules may be integrated into one entity structure.

[0024] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of this invention may occur in a different order than that marked in the accompanying drawings.

[0025] It is understood that the flowcharts and block diagrams of this invention illustrate the possible architecture, functions, and operations of systems, apparatuses, devices, and methods according to various embodiments of this invention. Each block in the flowchart or block diagram may represent a unit, module, program segment, or code, containing executable instructions for implementing the specified function. Furthermore, each block or combination of blocks in the block diagram and flowchart can be implemented using a hardware-based system to achieve the specified function, or using a combination of hardware and computer instructions.

[0026] It is understood that the units and modules involved in the embodiments of the present invention can be implemented by software or by hardware. For example, the units and modules can be located in a processor.

[0027] Example 1: like Figure 1 As shown, this embodiment provides a method for evaluating customer value. The method for evaluating customer value includes: S101, Obtain multi-source profile data of customers, where multi-source profile data refers to a collection of customer-related information obtained from multiple data sources.

[0028] In this embodiment, the multi-source profiling data mainly comes from the data platform. The data platform clarifies the screening criteria for modeling samples, focusing on effective customer groups such as "natural customers who have had billing or overdue payments in the past two years up to the latest billing period". Raw customer-related data is obtained by subscribing to datasets from multiple data sources, reducing the inclusion of invalid samples without actual business dealings. Data sources include, but are not limited to: government platforms, third-party commercial databases, industry associations or public disclosures, financial institutions, credit reporting systems, third-party collection agencies, tax and social security systems, enterprise data, internal systems, market data, enterprise operation systems, customer interaction channels, financial systems, payment platforms, and electronic invoice systems. At the same time, through unified data categories and cleaning standards, the raw data obtained from multiple data sources is clearly integrated and preprocessed to obtain a set of customer-related information, improving data quality and further enhancing the reliability of the classification results.

[0029] Specifically, multi-source profiling data includes business registration data, overdue payment data, revenue data, business opportunity data, business data, and billing data.

[0030] It should be noted that multi-source profiling data also includes contract data.

[0031] Specifically, overdue payment data includes one or more of the following: current overdue ratio, maximum overdue ratio, proportion of long-aged accounts receivable, cumulative number of months exceeding the threshold, number of consecutive overdue payments, number of overdue payments, and proportion of short-aged accounts receivable. Business registration data includes one or more of the following: total number of times equity has been frozen in history, average number of administrative penalties per year, average number of changes in business scope per year, average number of cases filed per year, registered capital of the enterprise, length of time the enterprise has been established, total number of changes in non-investment shareholders in history, percentage of equity held by investment shareholders, and maximum online tenure of online users.

[0032] In this embodiment, revenue data includes one or more of the following: average monthly revenue from monthly rental services, average monthly revenue from project-based services, gross profit margin of project-based services, total revenue, and average revenue. Billing data includes one or more of the following: average monthly revenue growth rate, online duration, insurance coverage rate, number of years of project-based billing, growth rate of project-based billing amount, and annual billing. Business registration data also includes registration information and business licenses. Business opportunity data includes one or more of the following: business opportunity reserve amount and conversion rate in the region. Business data includes, but is not limited to: types of products or services used and frequency of use.

[0033] It should be noted that the average monthly revenue growth rate refers to the proportion of the difference between the average monthly revenue of the most recent X months and the average monthly revenue of the previous 12 months to the total average monthly revenue of the previous 12 months. On-line duration refers to the product of the on-line duration of a single customer service transaction and the average monthly billing adjustment factor for that transaction. The average monthly billing adjustment factor is calculated using the formula... Calculations show that For business The monthly average expense adjustment factor, For business The average of all bills issued. The median of total billing amount. Retention rate refers to the proportion of billing users during the reporting period to the total number of users with access to the service and billing at the end of the previous year. Project revenue growth rate refers to the proportion of the difference between the total project revenue in the past 12 months and the total project revenue in the previous 24 to 13 months to the total project revenue in the previous 24 to 13 months. Opportunity reserve amount refers to the amount of effective opportunities within a preset period (e.g., the past 12 months) after excluding unapproved, draft, abandoned, and unconverted opportunities from the opportunity data. Conversion rates for each region are shown in Table 1.

[0034] Table 1 Conversion rates in different regions

[0035] S102, evaluating a value evaluation index of the customer according to the multi-source portrait data, wherein the value evaluation index comprises one or more of the following: a business penetration type, a revenue scale, a future revenue contribution, an opportunity conversion amount, a loyalty, a credit, an operation safety, and an importance category.

[0036] In this embodiment, the value evaluation index refers to a quantitative index for measuring the value contribution of the customer to the enterprise. The business penetration type refers to the participation degree of the customer in different business fields of the enterprise. The revenue scale refers to the total revenue brought by the customer to the enterprise, which can reflect the purchasing power and importance of the customer to the enterprise. The future revenue contribution refers to the possible revenue brought by the customer to the enterprise in the future period of time, which is usually obtained based on historical data, market trends and customer behavior analysis. The opportunity conversion amount refers to the amount of the customer converted from a potential opportunity to an actual transaction, which reflects the response degree and conversion efficiency of the customer to the marketing activities of the enterprise. The loyalty refers to the loyalty degree of the customer to the enterprise and its products. The credit refers to the performance of the customer in credit behaviors such as contract compliance and timely repayment during the transaction process. The customer with high credit usually has low default risk. The operation safety refers to the risk that the customer may bring to the enterprise during the operation process, such as financial risk and legal risk. The customer with high operation safety usually has low risk. The importance category is used to represent the importance of the customer to the overall business of the company.

[0037] Optionally, S102: evaluating the value evaluation index of the customer according to the multi-source portrait data comprises steps S1021-S1024. S1021, identifying the business penetration type, the contribution type, the attribute and the importance category of the customer according to the multi-source portrait data.

[0038] Specifically, the contribution type comprises one of the following: high-income contribution, small-and-medium-income contribution, and the attribute comprises one of the following: enterprise type and non-enterprise type.

[0039] In this embodiment, the business penetration type comprises one of the following: single business penetration, networking double business penetration, algorithm networking double business penetration, networking algorithm networking double business penetration, networking multi-business penetration, algorithm networking multi-business penetration, and networking algorithm networking multi-business penetration. The importance type comprises one of the following: group-level G (Government) type, province-level G type, city-level G type, district-level G type, group-level B (Business) type, province-level B type, city-level B type, and district-level B type.

[0040] Single service penetration refers to the type of product or service used by a customer, for example, a customer only uses mobile communication services without involving other services (such as broadband or television services). Networked dual service penetration refers to a customer using two products or services simultaneously, and the two products or services are connected through a network, for example, fixed telephone and broadband services. Computing dual service penetration refers to a customer using two products or services simultaneously, and the two services are combined through computing and network technologies, for example, cloud computing services and data storage services. Networked computing dual service penetration refers to a customer using two products or services simultaneously, and the two services rely on both network connection and computing technology, for example, online games and cloud computing services. Networked multi-service penetration refers to a customer using multiple products or services simultaneously, and these services are connected through a network, for example, mobile communication, broadband, television, and cloud services. Computing networked multi-service penetration refers to a customer using multiple products or services simultaneously, and these services rely on the combination of computing and network technologies, for example, online education, cloud computing, and big data analysis services. Networked computing multi-service penetration refers to a customer using multiple products or services simultaneously, and these services rely on both network connection and the combination of computing technologies, for example, smart home, Internet of Things solutions, and cloud services.

[0041] According to multi-source portrait data, the business penetration type, contribution type, attribute, and importance category of the customer are identified, specifically including: clustering the type of product or service used and the frequency of use in the business data, and calculating the participation degree of the customer in each business field (including but not limited to: networking, computing network) according to the clustering results, and / or, association rule mining on the type of product or service used in the business data to identify the business combination participated by the customer, wherein the clustering includes but is not limited to K-means, hierarchical clustering, and the association rule mining includes but is not limited to Apriori; according to the participation degree and / or business combination, the customer is divided into different business penetration types. According to the preset threshold values corresponding to high-income contribution and small-income contribution, and the total income and average income in the income data, the contribution type of the customer is identified, for example: high-income contribution: annual income > X (the specific value is set according to the business situation); small-income contribution: annual income ≤ X. According to the classification algorithm and the registration information and business license in the business data, it is judged whether the customer is an enterprise, wherein the classification algorithm includes but is not limited to logistic regression classification algorithm and decision tree classification algorithm. Features related to the importance category of the customer are extracted from the multi-source portrait data (including but not limited to registration information and business license in the business data), and then the importance category of the customer is identified according to the features related to the importance category of the customer, wherein the features related to the importance category of the customer include but are not limited to administrative level and equity background, the administrative level includes but is not limited to group level, provincial level, city level, and county level, and the equity background includes but is not limited to G class and B class.

[0042] S1022 assesses a customer's revenue scale, future revenue contribution, opportunity conversion amount, and loyalty based on revenue data, billing data, and opportunity data.

[0043] In this embodiment, the customer's revenue coefficient is determined based on the gross profit margin of project-based businesses in the revenue data and the first mapping relationship shown in Table 2. The first mapping relationship refers to the mapping relationship between the gross profit margin of project-based businesses and the revenue coefficient. The customer's revenue coefficient, the monthly average revenue of monthly rental businesses, and the monthly average revenue of project-based businesses in the revenue data are input into the formula: Revenue Scale = Monthly Average Revenue of Monthly Rental Businesses + Monthly Average Revenue of Project-based Businesses × k, to calculate the customer's revenue scale, where k represents the revenue coefficient.

[0044] Table 2 First Mapping Relationship

[0045] Enter the annual expense data into the formula. Output the annual growth rate, where, Indicates the first Annual growth rate , They represent the first Year, Annual billing; if the annual billing data only includes annual billing... When billing, the moving average growth rate If the billing data contains If the billing data includes at least two years of billing, then according to Calculate the moving average growth rate , This represents the latest year in the billing data. It also represents the billing data for the initial year. Input formula for moving average growth rate Assess the client's future revenue contribution. Input the opportunity reserve amount and opportunity conversion rate from the opportunity data into the formula: Opportunity conversion amount = Opportunity reserve amount × Opportunity conversion rate, to evaluate the customer's opportunity conversion amount.

[0046] According to the second mapping relationship as shown in Table 3, the third mapping relationship as shown in Table 4, the fourth mapping relationship as shown in Table 5, and the fifth mapping relationship as shown in Table 6, the monthly income growth rate, the online time length, the insurance use rate, the number of project collection years, and the project collection amount growth rate are matched with the corresponding scores; the scores corresponding to the monthly income growth rate, the online time length, and the insurance use rate are weighted and summed to obtain the monthly rental business loyalty score of the customer, for example: the monthly rental business loyalty score = the score corresponding to the monthly income growth rate x 33.33% + the score corresponding to the online time length x 33.33% + the score corresponding to the insurance use rate x 33.33%; the scores corresponding to the number of project collection years and the project collection amount growth rate are weighted and summed to obtain the project business loyalty score of the customer, for example: the project business loyalty score = the score corresponding to the number of project collection years x 50% + the score corresponding to the project collection amount growth rate x 50%; the monthly rental business loyalty score and the project business loyalty score are weighted and summed to obtain the loyalty of the customer, for example: the loyalty = the monthly rental business loyalty score x 80% + the project business loyalty score x 20%.

[0047] Table 3: Second mapping relationship

[0048] Table 4: Third mapping relationship

[0049] Table 5: Fourth mapping relationship

[0050] Table 6: Fifth mapping relationship

[0051] S1023, according to the contribution type and the overdue arrears data, the credit of the customer is evaluated.

[0052] Specifically, S1023: according to the contribution type and the overdue arrears data, the credit of the customer is evaluated, including: judging the contribution type of the customer; in response to the contribution type being high-income contribution, according to the current overdue rate, the maximum overdue rate, the long account receivable proportion, and the cumulative month number exceeding the threshold, the credit of the customer is evaluated; in response to the contribution type being low-income contribution, according to the current overdue rate, the cumulative month number exceeding the threshold, the continuous overdue times, the overdue arrears times, and the short account receivable proportion, the credit of the customer is evaluated.

[0053] In this embodiment, in response to the contribution type being high-income contribution, according to a sixth mapping relationship as shown in Table 7, the scores corresponding to the current overdue ratio (i.e. the ratio of the current overdue amount to the total billing amount in the last 12 months in Table 7), the maximum overdue ratio (i.e. the ratio of the maximum overdue amount in the last 12 months to the billing amount in the last 12 months in Table 7), the long account receivable proportion (i.e. the proportion of the receivables overdue for more than 3 months to all receivables in Table 7), and the threshold-exceeding cumulative month number (i.e. the cumulative month number of the overdue amount exceeding 30% of the annual billing amount) are matched, and the scores corresponding to the current overdue ratio, the maximum overdue ratio, the long account receivable proportion, and the threshold-exceeding cumulative month number are weighted and summed to obtain the credit degree of the customer. In response to the contribution type being low-income contribution, according to a seventh mapping relationship as shown in Table 8, the scores corresponding to the current overdue ratio (i.e. the ratio of the current overdue amount to the total billing amount in the last 12 months in Table 8), the threshold-exceeding cumulative month number (i.e. the cumulative month number of the overdue amount exceeding 30% of the annual billing amount in Table 8), the continuous overdue times (i.e. the continuous overdue times in the last 6 months and the highest continuous overdue times in the last 6 months in Table 8), the overdue times (i.e. the overdue times in the last 12 months in Table 8), and the short account receivable proportion (i.e. the proportion of the receivables overdue for more than 1 month to all receivables in Table 8) are matched, and the scores corresponding to the current overdue ratio, the threshold-exceeding cumulative month number, the continuous overdue times, the overdue times, and the short account receivable proportion are weighted and summed to obtain the credit degree of the customer.

[0054] Table 7 Sixth mapping relationship

[0055] Table 8 Seventh mapping relationship

[0056] S1024, according to the contribution type, the attribute, and the business data, the operating safety of the customer is evaluated.

[0057] Specifically, S1024: according to the contribution type, the attribute and the business data, the business safety of the customer is evaluated, including: judging the attribute of the customer; in response to the attribute being a non-enterprise type, determining the business safety of the customer as a first preset value; in response to the attribute being an enterprise type, judging the contribution type of the customer; in response to the contribution type being high-income contribution, according to the total number of historical equity freezing, the average number of annual administrative penalties, the average number of annual business scope changes, the average number of annual cases, the registered capital of the enterprise, the establishment time of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the investment shareholder, the business safety of the customer is evaluated; in response to the contribution type being low-income contribution, according to the average number of annual administrative penalties, the average number of annual business scope changes, the registered capital of the enterprise, the establishment time of the enterprise, and the maximum online age of the online user, the business safety of the customer is evaluated.

[0058] In this embodiment, the first preset value is taken as 100, in response to the attribute being a non-enterprise type, the business safety of the customer is determined as 100. In response to the attribute being an enterprise type and the contribution type being high-income contribution, according to the eighth mapping relationship shown in Table 9, the scores corresponding to the total number of historical equity freezing, the average number of annual administrative penalties, the average number of annual business scope changes, the average number of annual cases, the registered capital of the enterprise, the establishment time of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the investment shareholder are matched, and the scores corresponding to the total number of historical equity freezing, the average number of annual administrative penalties, the average number of annual business scope changes, the average number of annual cases, the registered capital of the enterprise, the establishment time of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the investment shareholder are weighted and summed to obtain the business safety of the customer. In response to the attribute being an enterprise type and the contribution type being low-income contribution, according to the ninth mapping relationship shown in Table 10, the scores corresponding to the average number of annual administrative penalties, the average number of annual business scope changes, the registered capital of the enterprise, the establishment time of the enterprise, and the maximum online age of the online user are matched, and the scores corresponding to the average number of annual administrative penalties, the average number of annual business scope changes, the registered capital of the enterprise, the establishment time of the enterprise, and the maximum online age of the online user are weighted and summed to obtain the business safety of the customer.

[0059] Table 9 Eighth mapping relationship

[0060] Table 10 Ninth mapping relationship

[0061] S103, according to the value evaluation index, the score of the customer in the value dimension is determined, wherein the value dimension includes one or more of the following: current contribution dimension, development potential dimension, cooperation stability dimension, performance credit dimension, business health degree dimension, and strategic importance dimension.

[0062] Specifically, S103: determining the score of the customer on the value dimension according to the value evaluation index, including steps S1031-S1034: S1031, from the preset mapping table, matching out the scores corresponding to the business penetration type, the income scale, the future income prediction value and the importance category respectively, wherein the future income prediction value refers to the weighted sum result of the future income contribution and the opportunity conversion amount, and the preset mapping table includes the mapping relationship between the scores and the business penetration type, the income scale, the future income prediction value and the importance category.

[0063] In this embodiment, the preset mapping table includes but is not limited to: the tenth mapping relationship as shown in Table 11, the eleventh mapping relationship as shown in Table 12, the twelfth mapping relationship as shown in Table 13, and the thirteenth mapping relationship as shown in Table 14, wherein the scores are segmented according to different customer income scales, and the logarithmic interpolation method is used to assign different scores according to different customer income scales, wherein the future income prediction value = future income contribution + opportunity conversion amount, the median of all income scales, the geometric mean of the top 2% of the income scale, the geometric mean of the last 1% of the income scale, the median of all future income prediction values, the geometric mean of the top 2% of the future income prediction value, the geometric mean of the last 1% of the future income prediction value, and the logarithmic interpolation method is used to determine the scores corresponding to the income scale and the future income prediction value from the score interval.

[0064] Table 11: Tenth mapping relationship

[0065] Table 12: Eleventh mapping relationship

[0066] Table 13: Twelfth mapping relationship

[0067] Table 14: Thirteenth mapping relationship

[0068] S1032, the scores corresponding to the business penetration type and the income scale are weighted and summed to obtain the score of the customer on the current contribution dimension.

[0069] In this embodiment, the score of the customer on the current contribution dimension = the score corresponding to the income scale × 70% + the score corresponding to the business penetration type × 30%.

[0070] S1033, the loyalty, credit, and business safety are determined as the scores of the customer on the cooperation stability dimension, the credit compliance dimension, and the business health dimension, respectively.

[0071] S1034, the future income prediction value and the importance category are determined as the scores of the customer on the development potential dimension and the strategic importance dimension, respectively.

[0072] It should be noted that after determining the score of the customer on the value dimension according to the value evaluation index, the embodiment further determines the score weight of the customer on the value dimension according to the fourteenth mapping relationship shown in Table 15, and performs weighted summation on the score of the customer on the value dimension and the score weight to obtain the comprehensive value score corresponding to the customer, that is: the comprehensive value score corresponding to the customer = the score of the customer on the current contribution dimension x 35% + the score of the customer on the development potential dimension x 15% + the score of the customer on the cooperation stability dimension x 15% + the score of the customer on the credit compliance dimension x 25% + the score of the customer on the business health dimension x 10% + the score of the customer on the strategic importance dimension.

[0073] Table 15 Fourteenth mapping relationship

[0074] The comprehensive value scores corresponding to all customers are obtained to form a clustering data set, 6 clustering centers are initialized by a clustering algorithm, the Euclidean distance between each sample in the clustering data set and the clustering center is calculated, and finally 6 stable clustering centers are obtained by iteration to meet the distance convergence threshold, and the 6 stable clustering centers are sorted from low to high according to the comprehensive value scores. The minimum score and the maximum score of each cluster are extracted to form an initial adaptive grading interval, wherein the clustering algorithm includes but is not limited to the K-means algorithm. Through the three-step closed loop of accurate comprehensive score calculation, clustering adaptive interval division, and multi-dimensional business calibration, a scientific and reasonable six-level customer grading result is formed, which not only relies on the clustering algorithm to guarantee the objectivity and scientificity of the grading, but also ensures that the result has strong landing operability through business rule calibration, and perfectly connects the front-line marketing and service work.

[0075] The embodiment can also fine-tune the initial adaptive grading interval according to the business habits and management needs of the operator to ensure that the interval boundaries are integers and continuous and non-overlapping, and form the target adaptive grading interval as shown in Table 16.

[0076] Table 16 Adaptive grading interval

[0077] This embodiment provides a customer value assessment method that constructs a six-dimensional value evaluation system, including current contribution (revenue scale, business penetration type), development potential (future revenue, business opportunity conversion), cooperation stability (loyalty), performance credit (creditworthiness), and strategic importance (importance category of customer relationship), covering the entire customer lifecycle, improving the accuracy and comprehensiveness of customer value assessment, and achieving a comprehensive and accurate customer value assessment.

[0078] Example 2: like Figure 2 As shown, this embodiment provides a method for identifying customer levels. The method for identifying customer levels includes: S201, obtain ratings for several customers on different value dimensions.

[0079] In this embodiment, customer business penetration type, contribution type, attributes, and importance category are identified based on multi-source profile data. Specifically, this includes: clustering the types and frequencies of products or services used in the business data, calculating the customer's participation in various business areas (including but not limited to: networking, computing), and / or performing association rule mining on the types of products or services used in the business data to identify the business combinations the customer participates in. Clustering includes, but is not limited to, K-means and hierarchical clustering, and association rule mining includes, but is not limited to, Apriori. Based on participation and / or business combinations, customers are categorized into different business penetration types. Based on preset thresholds corresponding to high-income contribution and low-to-medium-income contribution, as well as total income and average income in the income data, the customer's contribution type is identified. For example: high-income contribution: annual income > X (specific value set according to business situation); low-to-medium-income contribution: annual income ≤ X. Based on classification algorithms and registration information and business licenses in the business registration data, it is determined whether the customer is a company. Classification algorithms include, but are not limited to, logistic regression classification algorithms and decision tree classification algorithms. Features related to customer importance categories are extracted from multi-source profiling data (including but not limited to registration information and business licenses in business registration data). Then, the importance category of the customer is identified based on the features related to the customer importance category. The features related to the customer importance category include but are not limited to: administrative level and equity background. The administrative level includes but is not limited to: group level, provincial level, prefecture-level city level, and district / county level. The equity background includes but is not limited to: G category and B category.

[0080] Based on the gross profit margin of project-based businesses in the revenue data and the first mapping relationship shown in Table 2, the customer's revenue coefficient is determined. The first mapping relationship refers to the mapping relationship between the gross profit margin of project-based businesses and the revenue coefficient. The customer's revenue coefficient, the monthly average revenue of monthly rental businesses, and the monthly average revenue of project-based businesses in the revenue data are entered into the formula: Revenue Scale = Monthly Average Revenue of Monthly Rental Businesses + Monthly Average Revenue of Project-based Businesses × k, to calculate the customer's revenue scale, where k represents the revenue coefficient.

[0081] Enter the annual expense data into the formula. Output the annual growth rate, where, Indicates the first Annual growth rate , They represent the first Year, Annual billing; if the annual billing data only includes annual billing... When billing, the moving average growth rate If the billing data contains If the billing data includes at least two years of billing, then according to Calculate the moving average growth rate , This represents the latest year in the billing data. It also represents the billing data for the initial year. Input formula for moving average growth rate Assess the client's future revenue contribution. Input the opportunity reserve amount and opportunity conversion rate from the opportunity data into the formula: Opportunity conversion amount = Opportunity reserve amount × Opportunity conversion rate, to evaluate the customer's opportunity conversion amount.

[0082] According to the second mapping relationship shown in Table 3, the third mapping relationship shown in Table 4, the fourth mapping relationship shown in Table 5 and the fifth mapping relationship shown in Table 6, the scores corresponding to the monthly average income growth rate, the online time length, the insurance use rate, the number of project collection years and the project collection amount growth rate are matched respectively; the scores corresponding to the monthly average income growth rate, the online time length and the insurance use rate are weighted and summed to obtain the monthly rental business loyalty score of the customer, for example: the monthly rental business loyalty score = the score corresponding to the monthly average income growth rate x 33.33% + the score corresponding to the online time length x 33.33% + the score corresponding to the insurance use rate x 33.33%; the scores corresponding to the number of project collection years and the project collection amount growth rate are weighted and summed to obtain the project business loyalty score of the customer, for example: the project business loyalty score = the score corresponding to the number of project collection years x 50% + the score corresponding to the project collection amount growth rate x 50%; the monthly rental business loyalty score and the project business loyalty score are weighted and summed to obtain the loyalty of the customer, for example: the loyalty = the monthly rental business loyalty score x 80% + the project business loyalty score x 20%.

[0083] In response to the contribution type being high-income contribution, according to the sixth mapping relationship shown in Table 7, the scores corresponding to the current overdue ratio (i.e. the ratio of the current overdue amount to the total billing amount in the last 12 months in Table 7), the maximum overdue ratio (i.e. the ratio of the maximum overdue amount in the last 12 months to the billing amount in the last 12 months in Table 7), the long account age proportion (i.e. the proportion of the accounts receivable overdue for more than 3 months to all accounts receivable in Table 7), and the threshold exceeding cumulative month number (i.e. the cumulative month number of the overdue amount exceeding 30% of the annual billing in Table 7) are matched respectively, and the scores corresponding to the current overdue ratio, the maximum overdue ratio, the long account age proportion and the threshold exceeding cumulative month number are weighted and summed to obtain the credit of the customer. In response to the contribution type being low-income contribution, according to the seventh mapping relationship shown in Table 8, the scores corresponding to the current overdue ratio (i.e. the ratio of the current overdue amount to the total billing amount in the last 12 months in Table 8), the threshold exceeding cumulative month number (i.e. the cumulative month number of the overdue amount exceeding 30% of the annual billing in Table 8), the continuous overdue times (i.e. the continuous overdue times in the last 6 months and the highest continuous overdue times in the last 6 months in Table 8), the overdue times (i.e. the overdue times in the last 12 months in Table 8), and the short account age proportion (i.e. the proportion of the accounts receivable overdue for more than 1 month to all accounts receivable in Table 8) are matched respectively, and the scores corresponding to the current overdue ratio, the threshold exceeding cumulative month number, the continuous overdue times, the overdue times and the short account age proportion are weighted and summed to obtain the credit of the customer.

[0084] Taking the first preset value 100 as an example, in response to the attribute being a non-enterprise type, the business safety of the customer is determined as 100. In response to the attribute being an enterprise type and the contribution type being high-income contribution, according to an eighth mapping relationship as shown in Table 9, the scores corresponding to the total number of historical equity freezes, the annual average number of administrative penalties, the annual average number of business scope changes, the annual average number of cases, the registered capital of the enterprise, the establishment time of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the equity of the investment shareholder are matched, and the scores corresponding to the total number of historical equity freezes, the annual average number of administrative penalties, the annual average number of business scope changes, the annual average number of cases, the registered capital of the enterprise, the establishment time of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the equity of the investment shareholder are weighted and summed to obtain the business safety of the customer. In response to the attribute being an enterprise type and the contribution type being medium-low income contribution, according to a ninth mapping relationship as shown in Table 10, the scores corresponding to the annual average number of administrative penalties, the annual average number of business scope changes, the registered capital of the enterprise, the establishment time of the enterprise, and the maximum online age of the online user are matched, and the scores corresponding to the annual average number of administrative penalties, the annual average number of business scope changes, the registered capital of the enterprise, the establishment time of the enterprise, and the maximum online age of the online user are weighted and summed to obtain the business safety of the customer.

[0085] The preset mapping table includes but is not limited to: a tenth mapping relationship as shown in Table 11, an eleventh mapping relationship as shown in Table 12, a twelfth mapping relationship as shown in Table 13, and a thirteenth mapping relationship as shown in Table 14. Different scores are given to different income scales of the customer according to a logarithmic interpolation method, where the future income prediction value = future income contribution + opportunity conversion amount, is the median of all income scales, is the geometric mean of the top 2% of income scales, is the geometric mean of the last 1% of income scales, is the median of all future income prediction values, is the geometric mean of the top 2% of future income prediction values, is the geometric mean of the last 1% of future income prediction values, and the scores corresponding to the income scale and the future income prediction value are determined from the scoring interval by using the logarithmic interpolation method.

[0086] The score of the customer in the current contribution dimension = the score corresponding to the income scale × 70% + the score corresponding to the business penetration type × 30%. The loyalty, the credit, and the business safety are respectively determined as the scores of the customer in the cooperation stability dimension, the credit compliance dimension, and the business health dimension. The scores corresponding to the future income prediction value and the importance category are respectively determined as the scores of the customer in the development potential dimension and the strategic importance dimension.

[0087] S202, the scores are weighted and summed to obtain a comprehensive value score corresponding to each customer.

[0088] In this embodiment, according to the fourteenth mapping relationship shown in Table 15, the score weight of the customer in the value dimension is determined, and the score of the customer in the value dimension and the score weight are weighted and summed to obtain a comprehensive value score corresponding to the customer, that is, the comprehensive value score corresponding to the customer = the score of the customer in the current contribution dimension x 35% + the score of the customer in the development potential dimension x 15% + the score of the customer in the cooperation stability dimension x 15% + the score of the customer in the performance credit dimension x 25% + the score of the customer in the business health degree dimension x 10% + the score of the customer in the strategic importance dimension.

[0089] S202, based on the clustering algorithm and the comprehensive value score, a grade corresponding to each of the customers is identified.

[0090] In this embodiment, the comprehensive value scores corresponding to all the customers are obtained to form a clustering data set, 6 clustering centers are initialized through a clustering algorithm, the Euclidean distance between each sample in the clustering data set and the clustering center is calculated, finally the distance convergence threshold is satisfied through iteration, 6 stable clustering centers are obtained, and the clustering centers are sorted from low to high according to the comprehensive value scores, the minimum score and the maximum score of each cluster are extracted to form an initial adaptive grading interval, wherein the clustering algorithm includes but is not limited to the K-means algorithm. Through the three-step closed loop of accurate comprehensive score calculation, clustering adaptive interval division, and multi-dimensional business calibration, a scientific and reasonable six-level customer grading result is formed, which not only relies on the clustering algorithm to guarantee the objectivity and scientificity of the grading, but also ensures that the result has strong landing operability through business rule calibration, and perfectly connects the front-line marketing and service work. The initial adaptive grading interval can also be fine-tuned according to the business habits and management needs of the operator to ensure that the interval boundary is an integer and continuous and non-overlapping, and the target adaptive grading interval shown in Table 16 is formed.

[0091] The customer grade identification method provided in this embodiment realizes comprehensive and accurate customer grade identification through the scores accurately and comprehensively evaluated, that is, the scores of the customer in the current contribution dimension, the development potential dimension, the cooperation stability dimension, the performance credit dimension, the business health degree dimension, and the strategic importance dimension.

[0092] Embodiment 3: As Figure 3As shown, the embodiment also provides an evaluation device for customer value, comprising a first acquisition module 31, an evaluation module 32 and a determination module 33. The first acquisition module 31 is configured to acquire multi-source portrait data of the customer, wherein the multi-source portrait data refers to a set of information related to the customer obtained from multiple data sources. The evaluation module 32 is configured to evaluate a value evaluation index of the customer according to the multi-source portrait data, wherein the value evaluation index comprises one or more of the following: business penetration type, income scale, future income contribution, opportunity conversion amount, loyalty, credit, business safety, importance category. The determination module 33 is configured to determine a score of the customer in a value dimension according to the value evaluation index, wherein the value dimension comprises one or more of the following: current contribution dimension, development potential dimension, cooperation stability dimension, credit performance credit dimension, business health degree dimension, strategic importance dimension.

[0093] Specifically, the evaluation module 32 comprises an identification unit 321, a first evaluation unit 322, a second evaluation unit 323 and a third evaluation unit 324. The identification unit 321 is configured to identify the business penetration type, contribution type, attribute and importance category of the customer according to the multi-source portrait data. The first evaluation unit 322 is configured to evaluate the income scale, future income contribution, opportunity conversion amount and loyalty of the customer according to the income data, account data and opportunity data. The second evaluation unit 323 is configured to evaluate the credit of the customer according to the contribution type and overdue arrears data. The third evaluation unit 324 is configured to evaluate the business safety of the customer according to the contribution type, attribute and business data.

[0094] Specifically, the second evaluation unit 323 comprises a first judgment subunit, a first evaluation subunit and a second evaluation subunit. The first judgment subunit is configured to judge the contribution type of the customer. The first evaluation subunit is configured to evaluate the credit of the customer according to the current overdue ratio, maximum overdue ratio, long account receivable proportion and threshold-exceeding cumulative month number in response to the contribution type being high-income contribution. The second evaluation subunit is configured to evaluate the credit of the customer according to the current overdue ratio, threshold-exceeding cumulative month number, continuous overdue times, overdue arrears times and short account receivable proportion in response to the contribution type being low-income contribution.

[0095] Specifically, the third evaluation unit 324 comprises a second judgment subunit, a determination subunit, a third judgment subunit, a third evaluation subunit and a fourth evaluation subunit, the second judgment subunit is configured to judge the attribute of the customer, the determination subunit is configured to determine the business safety of the customer as a first preset value in response to the attribute being a non-enterprise type, the third judgment subunit is configured to judge the contribution type of the customer in response to the attribute being an enterprise type, the third evaluation subunit is configured to evaluate the business safety of the customer according to the total number of historical equity freezes, the annual average number of administrative penalties, the annual average number of business scope changes, the annual average number of cases on file, the registered capital of the enterprise, the establishment time of the enterprise, the total number of historical non-investment shareholder changes, and the percentage of the investment shareholder's equity in response to the contribution type being high-income contribution, and the fourth evaluation subunit is configured to evaluate the business safety of the customer according to the annual average number of administrative penalties, the annual average number of business scope changes, the registered capital of the enterprise, the establishment time of the enterprise, and the maximum online age of the online user in response to the contribution type being medium or low-income contribution.

[0096] Specifically, the determination module 33 comprises a matching unit 331, a weighted summation unit 332, a first determination unit 333 and a second determination unit 334, the matching unit 331 is configured to match the scores corresponding to the business penetration type, the income scale, the future income prediction value and the importance category respectively from a preset mapping table, wherein the future income prediction value refers to the weighted summation result of the future income contribution and the opportunity conversion amount, the preset mapping table comprises the mapping relationship between the scores and the business penetration type, the income scale, the future income prediction value and the importance category, the weighted summation unit 332 is configured to perform weighted summation on the scores corresponding to the business penetration type and the income scale respectively to obtain the score of the customer in the current contribution dimension, the first determination unit 333 is configured to determine the loyalty, the credit and the business safety as the scores of the customer in the cooperation stability dimension, the performance credit dimension and the business health dimension respectively, and the second determination unit 334 is configured to determine the scores corresponding to the future income prediction value and the importance category respectively as the scores of the customer in the development potential dimension and the strategic importance dimension.

[0097] It can be understood that the above-mentioned customer value evaluation device executes the customer value evaluation method corresponding to the above-mentioned embodiment 1, and thus the beneficial effects that can be achieved can refer to the beneficial effects of the schemes corresponding to the customer value evaluation method of the above-mentioned embodiment 1, which will not be described here.

[0098] Embodiment 4: As Figure 4As shown, the embodiment further provides a customer level identification device, comprising a second acquisition module 41, a weighted summation module 42 and an identification module 43. The second acquisition module 41 is configured to acquire scores of a plurality of customers in a value dimension. The weighted summation module 42 is configured to perform weighted summation on the scores to obtain comprehensive value scores of the plurality of customers. The identification module 43 is configured to identify levels of the plurality of customers based on a clustering algorithm and the comprehensive value scores.

[0099] It can be understood that the above-mentioned customer level identification device performs the customer level identification method of the above-mentioned embodiment 2, and thus the beneficial effects achieved thereby can refer to the beneficial effects of the above-mentioned customer level identification method of the embodiment 2, which will not be described herein again.

[0100] Embodiment 5 The embodiment further provides an electronic device, comprising a memory and a processor. The memory stores a computer program. The processor is configured to execute the computer program to implement the customer value evaluation method of the above-mentioned embodiment 1 or the customer level identification method of the above-mentioned embodiment 2.

[0101] Embodiment 6 The embodiment further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the customer value evaluation method of the above-mentioned embodiment 1 or the customer level identification method of the above-mentioned embodiment 2.

[0102] It can be understood that the above-mentioned embodiments are only exemplary embodiments for illustrating the principles of the present application, and the present application is not limited thereto. Various modifications and improvements can be made by those skilled in the art without departing from the spirit and essence of the present application, and these modifications and improvements are also considered to be within the protection scope of the present application.

Claims

1. A method of evaluating customer value, characterized by, The method comprises the following steps: acquiring multi-source portrait data of a customer, wherein the multi-source portrait data refers to a set of information related to the customer obtained from multiple data sources; evaluating a value evaluation index of the customer according to the multi-source portrait data, wherein the value evaluation index comprises one or more of the following: business penetration type, income scale, future income contribution, opportunity conversion amount, loyalty, credit, business safety, importance category; determining a score of the customer on a value dimension according to the value evaluation index, wherein the value dimension comprises one or more of the following: current contribution dimension, development potential dimension, cooperation stability dimension, credit fulfillment dimension, business health dimension, strategic importance dimension.

2. The method of evaluating customer value according to claim 1, wherein, The multi-source portrait data comprises business data, overdue payment data, income data, opportunity data, business data, and account data, The evaluating the value evaluation index of the customer according to the multi-source portrait data specifically comprises: identifying the business penetration type, contribution type, attribute, and importance category of the customer according to the multi-source portrait data; evaluating the income scale, future income contribution, opportunity conversion amount, and loyalty of the customer according to the income data, account data, and opportunity data; evaluating the credit of the customer according to the contribution type and overdue payment data; evaluating the business safety of the customer according to the contribution type, attribute, and business data.

3. The method of evaluating customer value according to claim 2, wherein, The contribution type comprises one of the following: high-income contribution, small-and-medium-income contribution, The overdue payment data comprises one or more of the following: current overdue ratio, maximum overdue ratio, long account age receivable proportion, threshold-exceeding cumulative month number, continuous overdue number, overdue payment number, and short account age receivable proportion, The evaluating the credit of the customer according to the contribution type and overdue payment data specifically comprises: judging the contribution type of the customer; in response to the contribution type being high-income contribution, evaluating the credit of the customer according to the current overdue ratio, maximum overdue ratio, long account age receivable proportion, and threshold-exceeding cumulative month number; in response to the contribution type being small-and-medium-income contribution, evaluating the credit of the customer according to the current overdue ratio, threshold-exceeding cumulative month number, continuous overdue number, overdue payment number, and short account age receivable proportion.

4. The method of evaluating customer value according to claim 3, wherein, The attribute comprises one of the following: enterprise type, non-enterprise type, The business data comprises one or more of the following: total number of historical stock right freezing, annual average administrative penalty number, annual average business scope change number, annual average case number, enterprise registered capital, enterprise establishment time length, total number of historical non-investment shareholder change, investment shareholder stock right percentage, and maximum account age of online user, The evaluating the business safety of the customer according to the contribution type, attribute, and business data specifically comprises: judging the attribute of the customer; in response to the attribute being non-enterprise type, determining the business safety of the customer as a first preset value; in response to the attribute being enterprise type, judging the contribution type of the customer; in response to the contribution type being high-income contribution, evaluating the business safety of the customer according to the total number of historical stock right freezing, annual average administrative penalty number, annual average business scope change number, annual average case number, enterprise registered capital, enterprise establishment time length, total number of historical non-investment shareholder change, and investment shareholder stock right percentage. In response to the contribution type being a low-income contribution, the business safety of the customer is evaluated according to the average number of administrative penalties per year, the average number of changes in business scope per year, the registered capital of the enterprise, the length of time the enterprise has been established, and the maximum online age of the online user.

5. The method of evaluating customer value according to claim 1, wherein, The score of the customer in the value dimension is determined according to the value evaluation index, and specifically includes: From the preset mapping table, the scores corresponding to the business penetration type, the income scale, the future income prediction value, and the importance category are matched, wherein the future income prediction value is the weighted sum result of the future income contribution and the opportunity conversion amount, and the preset mapping table includes the mapping relationship between the scores and the business penetration type, the income scale, the future income prediction value, and the importance category; The scores corresponding to the business penetration type and the income scale are weighted and summed to obtain the score of the customer in the current contribution dimension; The loyalty, the credit, and the business safety are respectively determined as the scores of the customer in the cooperation stability dimension, the performance credit dimension, and the business health dimension; The scores corresponding to the future income prediction value and the importance category are determined as the scores of the customer in the development potential dimension and the strategic importance dimension.

6. A method of identifying a customer class, characterized by It includes: Obtaining scores of a plurality of customers in a value dimension, wherein the scores are evaluated by the customer value evaluation method of any one of claims 1-5; The scores are weighted and summed to obtain comprehensive value scores corresponding to the plurality of customers; Based on the clustering algorithm and the comprehensive value scores, the grades of the plurality of customers are identified.

7. A customer value assessment device, characterized in that, It includes a first obtaining module, an evaluation module, and a determination module, The first obtaining module is configured to obtain multi-source portrait data of a customer, wherein the multi-source portrait data refers to a set of information related to the customer obtained from a plurality of data sources, The evaluation module is configured to evaluate value evaluation indexes of the customer according to the multi-source portrait data, wherein the value evaluation indexes include one or more of the following: business penetration type, income scale, future income contribution, opportunity conversion amount, loyalty, credit, business safety, and importance category, The determination module is configured to determine a score of the customer in a value dimension according to the value evaluation indexes, and the value dimension includes one or more of the following: current contribution dimension, development potential dimension, cooperation stability dimension, performance credit dimension, business health dimension, and strategic importance dimension.

8. A customer class identification apparatus characterized by comprising: It includes a second obtaining module, a weighted sum module, and an identification module, The second obtaining module is configured to obtain scores of a plurality of customers in a value dimension, wherein the scores are evaluated by the customer value evaluation device of claim 6, The weighted sum module is configured to weight and sum the scores to obtain comprehensive value scores of the plurality of customers, The identification module is configured to identify the grades of the plurality of customers based on the clustering algorithm and the comprehensive value scores.

9. An electronic device, comprising: It includes a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to implement the customer value evaluation method of any one of claims 1-5 or the customer grade identification method of claim 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the method for evaluating customer value according to any one of claims 1 to 5 or the method for identifying customer grades according to claim 6.

Images