System for establishing customer recruitment and customer asset evaluation analysis data model

Abstract

The invention relates to the field of system development, data processing, data modeling and algorithm models, in particular to a system for establishing a data model for carrying out data analysis and evaluation judgment on customer recruitment and customer assets, which comprises a customer data platform for obtaining, storing and processing customer-related data; the customer recruitment model is connected with the customer data platform and is used for evaluating a customer recruitment effect; the customer asset model is connected with the customer data platform and is used for evaluating the value of customer assets; by integrating the customer data platform, the customer recruitment model and the customer asset model, comprehensive and accurate customer value evaluation is realized. According to the customer recruitment model, the recruitment process is innovatively decomposed into four dimensions of exposure drainage, the number of obtained customers, the quality of obtained customers and the potential of obtained customers, the recruitment strategy is optimized, and the efficiency and the quality of obtained customers are improved. The customer asset model comprehensively evaluates the customer group through dimensions such as the number of people portraits, the activeness, the contribution value, the satisfaction degree and the dissatisfaction degree.

Description

Technical Field

[0001] The present invention relates to the fields of system development, data processing, data modeling, algorithm models, etc. More specifically, the present invention is a system for establishing a data model for data analysis and evaluation and judgment of customer recruitment and customer assets. Background Art

[0002] In recent years, as various consumer-oriented businesses have gradually transformed to a customer-centric operating model, the objective evaluation and analysis of the quality of customer recruitment and customer asset value of the enterprise can help enterprises more accurately evaluate the effectiveness of customer recruitment and customer operation. However, because the customers of consumer-oriented enterprises are not only numerous, but also have high consumption frequency and fast-changing consumption behavior, the relevant evaluation and judgment work faces the following difficulties: 1. The customer recruitment work lacks information evaluation on the quality and potential of the recruited customers. Currently, the analysis and evaluation of the recruitment work effect can only be based on the number of registered customers and single consumption. It lacks more critical customer value analysis and evaluation such as the long-term consumption behavior and consumption potential of the recruited customers.

[0003] 2. The customer asset value assessment lacks key information data. The company's customer asset value assessment work is currently only based on basic data such as customer quantity, consumption orders, and order amounts. It lacks evaluation and analysis of more critical customer behavior data such as customer consumption behavior, product preferences, marketing preferences, and satisfaction.

[0004] 3. The standards for customer recruitment and customer assets analysis and evaluation are inconsistent. Customer work involves multiple departments and multiple links within the company, from publicity, marketing, product design, product production, product quality, customer service and other departments. Customer recruitment also involves multiple online channels and offline stores. Therefore, it is necessary to formulate unified evaluation and analysis standards for customer analysis and evaluation work in order to achieve objective analysis and evaluation of customer work.

[0005] 4. Customized development of data models is not only costly but also inflexible. If consumer-oriented enterprises customize and develop relevant data models on their own, it will not only be costly and difficult, but also the calculation algorithms of relevant data models are fixed and if they need to be changed, they need to be redeveloped from the bottom up, which lacks flexibility. Once the market and business needs of the enterprise change, the customized data model will not be effective.

[0006] Therefore, based on the above problems, a system for establishing customer recruitment and customer asset data models is provided for consumer-oriented enterprises to help enterprises establish data models for customer recruitment and customer asset evaluation and analysis, unify customer recruitment and customer asset evaluation and analysis work standards, and the relevant system can also flexibly adjust the model based on changes in market demand to adapt to new needs. This is a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0007] Based on the problems raised in the above background technology, the present invention is a system for helping consumer-oriented enterprises to establish a data model for evaluating and analyzing customer recruitment and customer assets.

[0008] The present invention provides a system for establishing a customer recruitment and customer asset evaluation analysis data model, comprising: Customer data platform, used to obtain, store and process customer-related data; A customer recruitment model, connected to the customer data platform, for evaluating the effectiveness of customer recruitment; A customer asset model, connected to the customer data platform, for assessing the value of customer assets; The customer data platform includes a data storage module, a data cleaning module, a customer labeling module, a customer group selection module and a customer group optimization module; The customer recruitment model and the customer asset model both include an evaluation rule module, a calculation model module and a data report module; The system further comprises an access layer for obtaining the customer-related data from a plurality of data sources; The system also includes an application layer for providing analysis functions based on the customer recruitment model and the customer asset model.

[0009] Preferably, the data cleaning module of the customer data platform is used to: Cleaning the customer-related data into unified standard data; The customer label module is used to: A multi-dimensional label is generated for the customer based on the unified standard data, wherein the multi-dimensional label includes a behavior label, a preference label, a value label and a potential label.

[0010] Preferably, the customer group selection module is used to: Selecting target customers based on the combination of the multi-dimensional labels; The customer group optimization module is used to: The target customer group is optimized, including adding new tags, pre-generating new customer groups, calculating new reports, comparing data gaps between new and old reports, and / or generating new customer groups based on optimized tag combinations.

[0011] Preferably, the evaluation rule module of the customer recruitment model is used to: Configure scoring rules for recruitment-related indicators, including exposure and traffic indicators, customer acquisition quantity indicators, customer acquisition quality indicators, and customer acquisition potential indicators; The computational model module is used for: The evaluation score of each indicator and the total evaluation score are calculated based on the scoring rules and the customer-related data.

[0012] Preferably, the exposure and traffic indicators include exposure number, collection number, usage number and / or corresponding ratio; The customer acquisition quantity indicators include the number of users, the number of registered members, the number of repeat purchasing members and / or the corresponding ratios; The customer acquisition quality indicators include the number of high-quality customers, the number of orders from high-quality customers, the amount of orders from high-quality customers and / or the corresponding ratios; The customer acquisition potential indicators include the number of high-potential customers, the number of orders from high-potential customers, the amount of orders from high-potential customers and / or corresponding ratios.

[0013] Preferably, the evaluation rule module of the customer asset model is used to: Configure scoring rules for asset value-related indicators, including population portrait indicators, activity indicators, contribution value indicators, satisfaction indicators, and dissatisfaction indicators; The computational model module is used for: The evaluation score of each indicator and the total evaluation score are calculated based on the scoring rules and the customer-related data.

[0014] Preferably, the population portrait indicators include customer population change trends, regional distribution, product preference distribution and / or activity preference distribution; The activity indicators include the number of orders, number of deposits, number of deposits consumed, number of activity collections, number of activity usages and / or number of own program logins; The contribution value indicators include order amount, order gross profit, stored value amount and / or stored value balance; The satisfaction index includes the total number of favorable comments, the number of people who have given favorable comments, and / or the number of people who have given favorable comments multiple times; The dissatisfaction indicators include the number of negative reviews, the number of people who reviewed negative reviews, the number of complaints, the number of complaints and / or the number of dish returns.

[0015] Preferably, the access layer includes a WebAPI module, a database change capture module and a message queue module, which are used to obtain the customer-related data from multiple data sources; The customer-related data includes basic information, membership data, consumption data, evaluation data, behavior data, operation data, product data, promotional data and activity data.

[0016] Preferably, the application layer includes a tag plaza module, a customer group selection module, a customer group optimization module, a customer recruitment module and a customer asset analysis module; The client recruitment module is used to generate a data report including the total evaluation score of recruitment work effects of different recruitment channels, the evaluation score by scenario and the evaluation score of recruitment activities; The customer asset analysis module is used to generate data reports including asset value information of different customer groups, detailed data by scenario and customer group comparison data.

[0017] Preferably, it also includes a general function module, which includes a user authentication module, a rights management module, an operation log module, a system monitoring module and a continuous integration / continuous deployment module; Wherein, the authority management module is used to control the access and operation authority of different users to the customer recruitment model and the customer asset model; The operation log module is used to record the user's modification operations on the evaluation rules to support flexible adjustment and version management of the evaluation model.

[0018] The present invention has the following beneficial effects: The customer recruitment and asset evaluation analysis data model system provided by the present invention realizes a comprehensive and accurate customer value evaluation by integrating the customer data platform, customer recruitment model and customer asset model. The core advantages of the system are: uniform evaluation criteria, multi-dimensional comprehensive analysis capabilities and high flexibility.

[0019] As the foundation of the system, the customer data platform transforms raw data into actionable information assets through the collaboration of modules such as data storage, cleaning, customer labeling, customer group selection and optimization. In particular, the customer labeling module can extract customer behavior characteristics from massive data, providing key support for precision marketing. The customer group selection and optimization functions achieve accurate positioning of target customers and significantly improve the utilization efficiency of marketing resources.

[0020] The customer recruitment model innovatively breaks down the recruitment process into four dimensions: exposure and traffic, customer acquisition quantity, customer acquisition quality, and customer acquisition potential. This multi-dimensional evaluation method enables companies to fully understand the effects of each recruitment channel, thereby optimizing recruitment strategies and improving customer acquisition efficiency and quality. For example, based on the model analysis results, companies can focus resources on high-quality customer acquisition channels to improve return on investment.

[0021] The customer asset model comprehensively evaluates customer groups through dimensions such as population profile, activity, contribution value, satisfaction and dissatisfaction. This multi-angle analysis not only evaluates the current value of customers, but also predicts potential value, providing a basis for the company's long-term strategic decision-making. In particular, the separate evaluation of satisfaction and dissatisfaction provides more detailed insights for customer relationship management.

[0022] The hierarchical design of the system (access layer, storage layer, computing layer and application layer) ensures high scalability and maintainability. The access layer supports multiple data collection methods to ensure the comprehensiveness and real-time nature of the data. The storage layer adopts a combination of relational and non-relational storage, taking into account the structured management and flexible storage of data. The computing layer converts raw data into business insights through complex algorithm models, while the application layer presents the analysis results through an intuitive interface, which is easy for decision makers to understand and apply.

[0023] This fully integrated system design greatly improves the customer relationship management capabilities of enterprises. It not only helps enterprises locate and serve customers more accurately, but also provides data support for strategic decision-making, thereby gaining significant advantages in a highly competitive market environment. The high configurability of the system also ensures that it can adapt to the needs of enterprises of different sizes and types, and has a wide range of application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a business process diagram of the present invention.

[0025] Figure 2 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0026] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects thereof are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0027] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0028] Please refer to Figure 1-2 First, the present invention provides a system for establishing a customer recruitment and customer asset evaluation and analysis data model, which includes a customer data platform, a customer recruitment model and a customer asset model. The customer data platform is used to obtain, store and process customer-related data; the customer recruitment model is connected to the customer data platform to evaluate the customer recruitment effect; the customer asset model is also connected to the customer data platform to evaluate the customer asset value.

[0029] Specifically, the customer data platform includes a data storage module, a data cleaning module, a customer tag module, a customer group selection module, and a customer group optimization module. These modules work together to ensure that the system can efficiently process and analyze customer data. For example, in an actual application scenario, when a chain restaurant company uses this system, the data storage module can store customer consumption records, member information, and other data from various stores. The data cleaning module is responsible for unifying the format of these data from different channels, removing duplicate and erroneous information, and laying the foundation for subsequent analysis.

[0030] Secondly, both the customer recruitment model and the customer asset model include an evaluation rule module, a calculation model module, and a data report module. This structural design enables the system to flexibly adapt to the needs of different enterprises. For example, for the aforementioned chain restaurant enterprises, specific customer recruitment effect evaluation criteria can be set in the evaluation rule module according to their own business characteristics, such as the repurchase rate of new customers, the member conversion rate, etc.

[0031] Thirdly, the system also includes an access layer and an application layer. The access layer is used to obtain customer-related data from multiple data sources, while the application layer provides analysis functions based on customer recruitment models and customer asset models. This design enables the system to collect data comprehensively and present the analysis results intuitively to users.

[0032] Furthermore, the data cleaning module in the customer data platform of the present invention plays a key role. It cleans customer-related data into unified standard data, providing a reliable data basis for subsequent analysis. For example, for customer birthday information recorded in different formats in different stores, the data cleaning module can unify it into the YYYY-MM-DD format, which is convenient for subsequent customer portrait analysis.

[0033] Next, the customer tag module generates multi-dimensional tags for customers based on the cleaned unified standard data, including behavior tags, preference tags, value tags, and potential tags. These tags provide a basis for precision marketing and personalized services. For example, high-value customer tags can be generated based on the customer's consumption frequency and amount, and spicy preference tags can be generated based on the dishes that the customer frequently orders.

[0034] In addition, the customer group selection module and the customer group optimization module work together to achieve accurate positioning and continuous optimization of the target customer group. The customer group selection module selects the target customer group based on a combination of multi-dimensional tags, while the customer group optimization module continuously optimizes the customer group definition by adding new tags, pre-generating new customer groups, calculating new reports, and comparing the data gap between old and new reports. This process is crucial to improving marketing effectiveness. For example, a catering company can select female customers with high consumption frequency and large single consumption amount within 30 days as the target customer group, and then optimize by adding tags that are interested in new products to select the most suitable target audience for new product promotion activities.

[0035] Subsequently, the evaluation rule module in the customer recruitment model of the present invention configures the scoring rules for recruitment-related indicators, including exposure and traffic indicators, customer acquisition quantity indicators, customer acquisition quality indicators, and customer acquisition potential indicators. The calculation model module calculates the evaluation score of each indicator and the total evaluation score based on these scoring rules and customer-related data. This design enables enterprises to comprehensively evaluate the effectiveness of customer recruitment activities.

[0036] Specifically, exposure and traffic indicators may include the number of ad exposures, the number of coupons received, the number of coupons used, etc. Customer acquisition quantity indicators may include the number of newly registered members, the number of first-time customers, etc. Customer acquisition quality indicators may include the average spending amount of new customers, the repurchase rate, etc. Customer acquisition potential indicators may include the consumption growth rate of new customers, the breadth of product trials, etc. Through the comprehensive scoring of these indicators, companies can clearly understand the effects of different recruitment channels and activities, thereby optimizing resource allocation.

[0037] For example, a catering company may find that although the number of customers obtained through social media advertising is large, the average spending amount is low; while the number of customers obtained through high-end food forum promotion is small, but they have strong spending power and a high willingness to repurchase. This insight can help companies better formulate precise customer recruitment strategies.

[0038] At the same time, the evaluation rule module of the customer asset model is configured with scoring rules for asset value-related indicators, including population portrait indicators, activity indicators, contribution value indicators, satisfaction indicators, and dissatisfaction indicators. The calculation model module also calculates the evaluation score and total evaluation score of each indicator based on these scoring rules and customer-related data. This comprehensive evaluation system enables enterprises to gain a deep understanding of the true value of customer assets.

[0039] In actual applications, demographic indicators may include trends in customer size, age distribution, occupational distribution, etc. Activity indicators may include average consumption frequency, time of last consumption, etc. Contribution value indicators may include customer lifetime value (LTV), total annual consumption, etc. Satisfaction indicators may include favorable ratings, willingness to recommend, etc. Dissatisfaction indicators may include complaint rates, dish return rates, etc.

[0040] Through comprehensive analysis of these indicators, companies can comprehensively evaluate the value of customer assets. For example, a catering company may find that although a certain customer group has a small number of people, they have a high consumption frequency, a high average customer spending, and often bring in new customers, so they have a high asset value. This insight can help companies better allocate resources and develop differentiated customer retention strategies.

[0041] In addition, the system of the present invention also includes an access layer, which includes a Web API module, a database change capture module and a message queue module, which are used to obtain customer-related data from multiple data sources. These data sources may include the company's sales system, CRM system, social media platform, etc. For example, the Web API module can obtain customers' browsing and interaction data on the company's official website or APP in real time; the database change capture module can capture new order information in the sales system in a timely manner; and the message queue module can handle high-concurrency data streams from various stores. This integration of multi-source data provides a basis for comprehensive and accurate customer analysis.

[0042] Finally, the system of the present invention also includes an application layer, which includes a tag square module, a customer group selection module, a customer group optimization module, a customer recruitment module and a customer asset analysis module. These modules work together to provide enterprises with intuitive and easy-to-use analysis tools.

[0043] For example, the customer recruitment module can generate data reports including the total evaluation score of recruitment work effects of different recruitment channels, evaluation scores by scenario, and evaluation scores of recruitment activities. Through these reports, companies can clearly see the comparison of the effects of various recruitment channels and activities, so as to make wise marketing decisions. For example, companies may find that offline activities perform well in terms of customer acquisition quality, while online advertising has more advantages in terms of customer acquisition quantity, so they can choose the appropriate channel combination according to different recruitment goals.

[0044] The customer asset analysis module can generate data reports including asset value information of different customer groups, detailed data by scenario, and customer group comparison data. These reports can help companies gain in-depth understanding of the value composition and changing trends of different customer groups. For example, a company may find that the satisfaction of a certain high-value customer group begins to decline. Through further analysis, it may be found that the newly launched dishes do not meet the taste preferences of this customer group, so the product strategy can be adjusted in a timely manner.

[0045] It is worth noting that the present invention also includes common functional modules, including user authentication module, authority management module, operation log module, system monitoring module and continuous integration / continuous deployment module. Although these modules are not directly involved in data analysis, they are crucial to the security, availability and maintainability of the system.

[0046] In particular, the permission management module is used to control the access and operation permissions of different users to the customer recruitment model and customer asset model. This ensures the security of sensitive data, while also supporting different roles (such as the marketing department and customer service department) to use the system according to their respective needs. For example, the marketing department can only access data and functions related to customer recruitment, while the customer service department can access data and functions related to customer assets.

[0047] In addition, the operation log module is used to record the user's modification operations on the evaluation rules to support the flexible adjustment and version management of the evaluation model. This function is very important for the continuous optimization of the evaluation model. For example, when an enterprise finds that a certain evaluation indicator is no longer applicable, it can view the operation log to understand the historical adjustment records and make more reasonable new adjustments.

[0048] In general, the system for establishing a customer recruitment and customer asset evaluation and analysis data model provided by the present invention realizes the whole process management from data collection, cleaning, analysis to application by integrating the customer data platform, customer recruitment model and customer asset model. It can not only help enterprises to more accurately evaluate the customer recruitment effect and customer asset value, but also support enterprises to formulate more accurate marketing strategies and customer service strategies. Through this system, enterprises can better understand customers, improve customer satisfaction, and ultimately achieve sustainable business growth.

[0049] In a preferred embodiment of the present invention, the implementation process of the customer recruitment and asset evaluation analysis data model system can be described in more detail as follows: First, the system synchronizes various customer-related data to the customer data platform through automated tasks. These data cover all aspects of customers, including but not limited to basic customer information, membership data, consumption data, evaluation data, behavior data, promotional data, and activity data. It is worth noting that the execution method of these synchronization tasks can be flexibly set according to actual needs, and you can choose offline batch synchronization or real-time streaming synchronization. For example, for basic customer information, offline batch synchronization may be performed once a day; while for consumption data with higher real-time requirements, real-time streaming synchronization may be used to ensure the timeliness and accuracy of the data.

[0050] Next, as the cornerstone of the entire system, the customer data platform undertakes multiple important tasks. The first is data storage and cleaning, the second is tracking customer consumption behavior and preferences through a tag system, and finally, it must be able to select and optimize various target customer groups required by the business. In order to achieve these functions, the customer data platform is designed to include four key sub-modules: data storage, customer tagging, customer group selection, and customer group optimization.

[0051] During the data storage phase, the system will first perform in-depth cleaning of customer-related data integrated and summarized from various channels. This process includes but is not limited to: standardization of data formats, processing of outliers, filling of missing values, removal of duplicate data, etc. For example, different systems may use different date formats (such as January 1, 2023, "2023-01-01", "01 / 01 / 2023"), and the data cleaning process will convert these different formats into a standard format predefined by the system, such as "2023-01-01". The cleaned data will be converted into a unified standard data format and then stored. This step is critical to ensuring the accuracy of subsequent analysis and model building.

[0052] Then, the customer tag module comes into play. This module automatically tags each customer with multiple dimensions through complex algorithms and rule engines. These tags may involve multiple dimensions such as consumption habits (such as high-frequency consumers, weekend consumers), product preferences (such as dessert lovers, healthy food preferrs), and activity participation (such as heavy coupon users, new tasters). For example, the system may label customers as high-value customers, medium-value customers, or low-value customers based on the frequency and amount of their consumption in the past three months; or label them with tastes such as spicy preference and light preference based on the types of products that customers frequently purchase. These tags are not static, but will be dynamically updated as customer behavior changes, thereby providing real-time and accurate customer portraits for subsequent precision marketing and personalized services.

[0053] Then, the system enters the customer group selection stage. In this stage, the customer group selection module will use the previously generated customer tags to select customers with specific tag combinations as target customers based on business needs. This process first requires the establishment of different customer group types, such as basic customer groups, high-spending customer groups, and highly active customer groups. This classification management method enables companies to more efficiently formulate corresponding marketing strategies for customer groups with different characteristics. For example, a high-value potential customer group may be selected by combining the tags of medium consumption level, increasing consumption frequency, and interest in new products.

[0054] Based on customer group selection, the customer group optimization module further plays a role by adding more tags to provide more refined target customer groups for the business. This optimization process usually includes the following detailed steps: First, create a customer segment report. This step requires selecting the target customer segment to be optimized and setting the time range for analysis. For example, you may select high-value potential customers in the past 30 days as the optimization target, and set the time range to the last 90 days.

[0055] Secondly, the system will automatically analyze the customer group report. This analysis process will focus on multiple key indicators, including but not limited to the number of customers, number of orders, actual orders received, order gross profit, average order value, product sales, etc. In addition, based on specific business needs and data conditions, other relevant analysis indicators can be further added, such as activity participation, stored value amount, etc. For example, the system may find that the average average order value of this high-value potential customer group in the past 90 days is 20% higher than that of all customers, but the activity participation is lower than the average level.

[0056] Third, the system will try to pre-generate a new customer group by adding new tags. For example, it may try to add the tag "sensitive to discounts" to generate a new customer group, and then calculate various indicators of this new customer group to form a new report.

[0057] Next, the system automatically compares the data gap between the new and old reports. In this example, the system may find that after adding the discount-sensitive label, the activity participation of the new customer group has increased significantly, and the average order value has not decreased significantly.

[0058] Finally, based on these analysis results, the system will filter out customer group tag combinations that can meet business expectations. Users can choose to add new tags to the original customer group tags to cover the original customer group information, or directly generate a new customer group based on the new tag combination. In this example, it may be decided to add the label of sensitive to discounts to the original high-value potential customer group definition to form a more accurate target customer group.

[0059] It is worth noting that although the above steps can well solve the problem of understanding, grouping and optimizing the company's existing customers and provide target customer groups for the company's precise business, with the continuous development of the company, it is still necessary to continuously recruit new customers through various means. Therefore, the present invention also provides a special customer recruitment model to help the company objectively and comprehensively judge the value of newly recruited customers, and then accurately evaluate the effects of different recruitment channels.

[0060] In the customer recruitment model, based on the business needs of consumer companies, the entire recruitment work is divided into four main business scenarios: exposure and traffic, customer acquisition quantity, customer acquisition quality and customer acquisition potential. This classification method enables companies to comprehensively evaluate all aspects of customer recruitment.

[0061] Among them, the exposure and traffic flow scenario is mainly responsible for judging the exposure, collection, and use of the recruitment activities of the corresponding recruitment channels. For example, for an online coupon distribution activity, the system will record and analyze indicators such as the number of coupon displays, collections, and uses.

[0062] The customer acquisition scenario focuses on the number of customers obtained through different recruitment channels, the number of registered members, the number of repeat customers, and other information. These indicators directly reflect the quantitative effect of recruitment activities. For example, the system will count the number of new registered users brought in through specific channels (such as social media advertising), as well as how many of these users completed their first purchase and how many became repeat customers.

[0063] The customer acquisition quality scenario is used to evaluate the situation and proportion of high-quality customers (i.e. customers with high consumption contribution) in the newly acquired customer base. This may include indicators such as the average consumption amount of new customers and the proportion of high-spending customers (such as those in the top 20% in terms of consumption amount).

[0064] The customer acquisition potential scenario focuses on determining the situation and proportion of high-potential customers in the newly acquired customer base that meet the business characteristics of the enterprise. This may involve indicators such as the growth trend of new customers' consumption frequency, the breadth of product types tried, and the acceptance of new products.

[0065] Next, the system will configure specific evaluation rules for each business scenario, including scoring rules for detailed indicator data values, percentage calculation formulas and scoring rules, weighting rules for summary indicators, and calculation rules for average indicators, etc. These rules are very flexible and can be customized according to the specific needs of the enterprise.

[0066] For example, in the exposure and traffic diversion scenario, the following rules may be set: Exposure number: 1 point for every 1,000 exposures; Number of collections: 1 point for every 100 collections; Number of uses: 1 point for every 10 uses; Receive rate (number of receives / number of exposures): 10 points for every 1 percentage point increase; Utilization rate (number of uses / number of receipts): 20 points for every 1 percentage point increase; You can then set weights for these metrics, for example: Exposure and traffic evaluation score = exposure score*0.1+receipt score*0.3+usage score*0.4+receipt rate score*0.1+usage rate score*0.1.

[0067] Similarly, the number of customers, customer quality and customer potential scenarios will also have corresponding scoring rules and weights. These rules can be adjusted according to the actual situation and phased goals of the enterprise to ensure that the evaluation results can accurately reflect the core demands of the enterprise.

[0068] After completing the configuration of the evaluation rules for each scenario, the system will automatically perform the calculation task to obtain the evaluation scores of each recruitment channel in different scenarios. This process is automated and can be set to execute regularly (such as daily updates) or triggered in real time according to needs.

[0069] These evaluation results will eventually be presented to users in the form of data reports, including overall summary reports and detailed reports for each scenario. In the summary report, users can see at a glance the total evaluation score of customer recruitment work results for all channels, as well as the evaluation scores for corresponding work scenarios (such as exposure and traffic, number of customers acquired, customer acquisition quality, and customer acquisition potential). Since the evaluation criteria for all channels are consistent, users can quickly find the channel that best meets the needs of corporate customer recruitment work through a simple score comparison.

[0070] In addition, users can also view detailed reports for each scenario. For example, in the exposure and traffic report, users can view the specific data values ​​and ratings of various indicators (such as exposures, usages, orders, order amounts, etc.) of different recruitment activities (such as 30% off coupons or gift coupons) in the selected recruitment channel in the exposure and traffic scenario, and even view detailed data by day. Such detailed information allows users to deeply understand the specific performance of each recruitment activity and make more accurate decisions.

[0071] Through this comprehensive and detailed evaluation system, companies can clearly understand the effects of different recruitment channels and activities, optimize resource allocation, and improve the overall efficiency and effectiveness of customer recruitment. For example, a company may find that although a certain online channel has a large number of customers, the quality of customers is low; while a certain offline activity has a small number of customers, but the quality and potential of customers are high. Based on such insights, companies can adjust their recruitment strategies accordingly, such as increasing resource investment in high-quality customer acquisition channels, or optimizing the activity design of low-quality customer acquisition channels to improve customer quality.

[0072] Finally, the present invention also includes a customer asset module for comprehensively evaluating the asset value of the customer groups owned by the enterprise. This module divides the customer asset value judgment into five main scenarios: headcount profile, activity, contribution value, satisfaction and dissatisfaction. This multi-dimensional evaluation method enables enterprises to fully understand the true value of customer assets.

[0073] In the crowd profiling scenario, the system mainly focuses on the trend of customer population changes and various distribution situations. For example, the system will analyze the monthly growth rate of customer size, the proportion of customers in different age groups, the distribution of customers in different cities, the proportion of customers with different product preferences, etc. This information helps companies understand the overall structure and changing trends of customer groups.

[0074] The activity scenario focuses on various interactive behaviors of customers, such as order frequency, stored value, activity participation, etc. The system may calculate indicators such as average consumption frequency, time of the last consumption, frequency of participation in promotional activities, etc. These indicators reflect the activeness of the interaction between customers and enterprises.

[0075] The contribution value scenario mainly evaluates the economic value of the customer base, including consumption amount, order gross profit, stored value amount, etc. The system may calculate indicators such as customer lifetime value (LTV), annual total consumption, and average customer price. These indicators directly reflect the economic contribution of customers to the company.

[0076] Satisfaction and dissatisfaction scenarios evaluate customer feedback from positive and negative perspectives respectively. Satisfaction may include indicators such as favorable ratings and willingness to recommend scores (NPS); while dissatisfaction may include indicators such as complaint rates and return rates. These indicators reflect the customer's satisfaction with the company's products and services and are important indicators for predicting customer loyalty and long-term value.

[0077] When configuring the evaluation rules for these scenarios, the system will set specific detailed indicators and their scoring rules for each scenario, as well as weighted rules for summary indicators. For example, in the crowd portrait scenario, the following rules may be set: Customer base size growth rate: 5 points for every 1 percentage point increase; The proportion of high-value customers: 10 points for every 1 percentage point increase; New customer acquisition rate: 8 points for every 1 percentage point increase; In the activity scenario, the following rules may be set: Average number of monthly consumption: 10 points each time; Number of days since the last purchase: 20 points if the purchase was made within 30 days, 10 points if the purchase was made between 30 and 60 days, 5 points if the purchase was made between 60 and 90 days, and 0 points if the purchase was made over 90 days. Percentage of stored-value customers: 15 points for every 1 percentage point increase; In the contribution value scenario, the following rules may be set: Average monthly consumption amount: 1 point for every 100 yuan; Customer Lifetime Value (LTV): 10 points for every 1,000 yuan; Gross profit margin: 20 points for every 1 percentage point increase; In the satisfaction scenario, the following rules may be set: Favorable rate: 5 points for every 1 percentage point increase; Willingness to recommend score (NPS): 10 points for every 1 point increase; Repurchase rate: 15 points for every 1 percentage point increase; In the unsatisfactory scenario, the following rules may be set: Complaint rate: 10 points for every 0.1 percentage point decrease; Return rate: 5 points for every 0.1 percentage point decrease; Churn rate: 20 points for every 0.1 percentage point decrease; It is worth noting that these rules can be flexibly adjusted according to the specific circumstances and phased goals of the enterprise. For example, if the current focus of the enterprise is to improve customer satisfaction, the weight of satisfaction-related indicators can be increased accordingly.

[0078] After completing the configuration of the evaluation rules for each scenario, the system will automatically perform the calculation task and obtain the evaluation scores of different customer groups in each scenario. This process is automated and usually set to update daily to ensure that the company can keep abreast of changes in the value of customer assets.

[0079] These evaluation results will eventually be presented to users in the form of data reports. First, users can view the asset value information of all customer groups that need to be analyzed through summary reports, including the number of people, number of members, active value, average active value per person, contribution value, average contribution value per person, satisfaction value, dissatisfaction value, etc. Since the evaluation criteria for all customer groups are consistent, companies can easily determine the preliminary asset value of the target customer groups.

[0080] Secondly, users can also view detailed data of the selected customer group in the corresponding scenario through the scenario data table. For example: 1. In the population portrait report, users can view the changing trend of the customer base, as well as the distribution of customers in different active areas, different membership levels, different product preferences, and different activity preferences.

[0081] 2. In the activity report, users can view relevant data and evaluation scores related to customer activity, such as the number of orders, number of deposits, number of activity usage, number of own program logins, etc.

[0082] 3. In the contribution report, users can view relevant data and evaluation scores related to customer contribution, such as order amount, order gross profit, stored value amount, stored value balance, etc.

[0083] 4. In the satisfaction report, users can view relevant data and evaluation scores related to customer satisfaction, such as the number of positive reviews, the number of positive reviews, the number of multiple positive reviews, the number of positive reviews with pictures, etc.

[0084] 5. In the dissatisfaction report, users can view relevant data and evaluation scores related to customer dissatisfaction, such as the number of negative reviews, the number of people who gave negative reviews, the number of people who gave multiple negative reviews, the number of complaints, the number of complaints, the number of returns, the number of returns, and other related data.

[0085] In addition, the system also provides a customer group comparison function. Users can select multiple customer groups to be compared and choose one of them as the reference customer group. The system will generate a detailed comparison report, including comparison data of each customer group in terms of number of people, active value, average active value per person, contribution value, average contribution value per person, satisfaction value, dissatisfaction value, etc. This comparison function enables companies to more intuitively understand the differences between different customer groups, so as to formulate more targeted customer operation strategies.

[0086] For example, suppose a restaurant chain uses this system to evaluate customer assets. Through the customer comparison function, they may find: 1. High-frequency dine-in customers have the highest per capita contribution value, but their satisfaction is relatively low.

[0087] 2. The cost of acquiring new takeout customers is low, but the repurchase rate is not high.

[0088] 3. Member loyalty customers have the highest satisfaction, but the growth rate has begun to slow down.

[0089] Based on these insights, restaurants can develop strategies to: 1. For high-frequency dine-in customers, focus on improving service quality and dining experience to increase satisfaction.

[0090] 2. Design special promotional activities for new takeout customers to encourage secondary consumption and increase customer stickiness.

[0091] 3. Launch new benefits and reward programs for loyal members to stimulate consumption growth and attract more new customers to join the membership program.

[0092] Through this comprehensive and detailed customer asset evaluation system, companies can gain an in-depth understanding of the value composition and changing trends of different customer groups, thereby formulating more precise customer operation strategies. For example, a company may find that the satisfaction of a certain high-value customer group has begun to decline. Through further analysis, it may be found that the newly launched product does not meet the preferences of this customer group. Based on such insights, companies can adjust product strategies or customer service methods in a timely manner to maintain and improve the satisfaction of high-value customers.

[0093] In general, the system for establishing a customer recruitment and customer asset evaluation and analysis data model provided by the present invention realizes the full process management from data collection, cleaning, analysis to application by integrating the customer data platform, customer recruitment model and customer asset model. It can not only help enterprises to more accurately evaluate the customer recruitment effect and customer asset value, but also support enterprises to formulate more accurate marketing strategies and customer service strategies.

[0094] The advantage of this system lies in its comprehensiveness and flexibility. It covers all stages of the customer life cycle, from acquiring new customers to evaluating the value of existing customers to preventing customer churn. At the same time, the system's various parameters and evaluation rules can be adjusted according to the specific circumstances of the enterprise, which enables the system to adapt to the needs of enterprises of different types and at different stages of development.

[0095] In addition, the system has a high degree of automation and can continuously collect and analyze data to provide companies with real-time insights. This enables companies to quickly respond to market changes and adjust their business strategies in a timely manner.

[0096] In practical applications, this system can help enterprises solve many common business problems. For example: 1. Optimize marketing investment: Through the customer recruitment model, companies can clearly understand the effectiveness of different marketing channels, so as to allocate marketing budget more reasonably.

[0097] 2. Improve customer retention: Through the customer asset model, companies can identify high-value customers and customers at risk of churn, and take targeted retention measures.

[0098] 3. Personalized services: Based on the customer tags and customer segmentation generated by the system, companies can provide more personalized products and services for different types of customers.

[0099] 4. Product innovation: By analyzing the consumption behaviors and preferences of different customer groups, companies can gain inspiration for product innovation and better meet customer needs.

[0100] 5. Improve operational efficiency: The system's automated data collection and analysis process can greatly reduce the workload of manual data processing and improve the company's operational efficiency.

[0101] It should be emphasized that although this system provides powerful data analysis capabilities, the final decision still needs to be combined with the experience and judgment of enterprise managers. The role of the system is to provide objective and comprehensive data support for decision-making and help enterprises make more informed choices.

[0102] In the future, with the further development of artificial intelligence and machine learning technology, this system still has a lot of room for optimization. For example, more complex prediction models can be introduced to not only analyze past and current data, but also predict future trends; more data sources can be added, such as social media data, location data, etc., to obtain more comprehensive customer insights; and more intuitive data visualization interfaces can be developed to make analysis results easier to understand and apply.

[0103] In short, this customer recruitment and asset evaluation analysis data model system provides enterprises with a powerful tool to help them better understand and serve customers in the increasingly fierce market competition, thereby gaining a sustainable competitive advantage.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, replacement, and improvement made within the principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for establishing a customer recruitment and customer asset evaluation and analysis data model, characterized in that: include: Customer data platform, used to obtain, store and process customer-related data; A customer recruitment model, connected to the customer data platform, for evaluating the effectiveness of customer recruitment; A customer asset model, connected to the customer data platform, for assessing the value of customer assets; The customer data platform includes a data storage module, a data cleaning module, a customer labeling module, a customer group selection module and a customer group optimization module; The customer recruitment model and the customer asset model both include an evaluation rule module, a calculation model module and a data report module; The system further comprises an access layer for obtaining the customer-related data from a plurality of data sources; The system also includes an application layer for providing analysis functions based on the customer recruitment model and the customer asset model.

2. The system according to claim 1, characterized in that The data cleaning module of the customer data platform is used to: Cleaning the customer-related data into unified standard data; The customer label module is used to: A multi-dimensional label is generated for the customer based on the unified standard data, wherein the multi-dimensional label includes a behavior label, a preference label, a value label and a potential label.

3. The system according to claim 2, characterized in that The customer group selection module is used to select the target customer group based on the combination of the multi-dimensional tags; The customer group optimization module is used to: The target customer group is optimized, including adding new tags, pre-generating new customer groups, calculating new reports, comparing data gaps between new and old reports, and / or generating new customer groups based on optimized tag combinations.

4. The system according to claim 1, characterized in that The evaluation rule module of the customer recruitment model is used to: Configure scoring rules for recruitment-related indicators, including exposure and traffic indicators, customer acquisition quantity indicators, customer acquisition quality indicators, and customer acquisition potential indicators; The computational model module is used for: The evaluation score of each indicator and the total evaluation score are calculated based on the scoring rules and the customer-related data.

5. The system according to claim 4, characterized in that The exposure and traffic indicators include exposure number, receipt number, usage number and / or corresponding ratio; The customer acquisition quantity indicators include the number of users, the number of registered members, the number of repeat purchasing members and / or the corresponding ratios; The customer acquisition quality indicators include the number of high-quality customers, the number of orders from high-quality customers, the amount of orders from high-quality customers and / or the corresponding ratios; The customer acquisition potential indicators include the number of high-potential customers, the number of orders from high-potential customers, the amount of orders from high-potential customers and / or corresponding ratios.

6. The system according to claim 1, characterized in that The evaluation rule module of the customer asset model is used to: Configure scoring rules for asset value-related indicators, including population portrait indicators, activity indicators, contribution value indicators, satisfaction indicators, and dissatisfaction indicators; The computational model module is used for: The evaluation score of each indicator and the total evaluation score are calculated based on the scoring rules and the customer-related data.

7. The system according to claim 6, characterized in that The demographic profile indicators include customer population change trends, regional distribution, product preference distribution, and / or activity preference distribution; The activity indicators include the number of orders, number of deposits, number of deposits consumed, number of activity collections, number of activity usages and / or number of own program logins; The contribution value indicators include order amount, order gross profit, stored value amount and / or stored value balance; The satisfaction index includes the total number of favorable comments, the number of people who have given favorable comments, and / or the number of people who have given favorable comments multiple times; The dissatisfaction indicators include the number of negative reviews, the number of people who reviewed negative reviews, the number of complaints, the number of complaints and / or the number of dish returns.

8. The system according to claim 1, characterized in that The access layer includes a WebAPI module, a database change capture module and a message queue module, which are used to obtain the customer-related data from multiple data sources; The customer-related data includes basic information, membership data, consumption data, evaluation data, behavior data, operation data, product data, promotional data and activity data.

9. The system according to claim 1, characterized in that The application layer includes a tag square module, a customer group selection module, a customer group optimization module, a customer recruitment module and a customer asset analysis module; The client recruitment module is used to generate a data report including the total evaluation score of recruitment work effects of different recruitment channels, the evaluation score by scenario and the evaluation score of recruitment activities; The customer asset analysis module is used to generate data reports including asset value information of different customer groups, detailed data by scenario and customer group comparison data.

10. The system according to claim 1, characterized in that It also includes a general function module, which includes a user authentication module, a rights management module, an operation log module, a system monitoring module and a continuous integration / continuous deployment module; Wherein, the authority management module is used to control the access and operation authority of different users to the customer recruitment model and the customer asset model; The operation log module is used to record the user's modification operations on the evaluation rules to support flexible adjustment and version management of the evaluation model.

Images