CRM-based information data analysis method and system

Abstract

The invention relates to the technical field of customer relationship management, and discloses an information data analysis method and system based on CRM. An information data analysis method based on CRM comprises the following steps: S1, collecting user original information data based on CRM, and screening out target users with loss risks according to the user original information data; s2, extracting customer loss risk features from the original information data of the target users, importing the customer loss risk features into the trained risk assessment calculation model, and outputting results to indicate loss risk levels of the target users; and S3, generating a reservation scheme according to the loss risk level of the target user and the corresponding original information data, and outputting the reservation scheme to the corresponding target user. According to the invention, grading intervention is carried out on the target users based on different risk grades, a uniform retention strategy is prevented from being adopted for all users, and the retention rate of clients is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of customer relationship management, and in particular to an information data analysis method based on CRM. Background Art

[0002] Customer churn refers to the behavior of existing customers ceasing to purchase or use a company's products or services for various reasons, typically manifesting as contract termination, non-renewal, or switching to competitors. Churn can be caused by factors such as price sensitivity, poor service experience, changing demand, or market competition, directly impacting a company's revenue and market share while increasing customer acquisition costs. High churn rates often reveal weaknesses in customer satisfaction, product value, or loyalty management. Implementing effective retention strategies to address customer churn is key to reducing churn and increasing customer lifetime value.

[0003] Existing CRM systems typically rely on static rules to determine customer churn risk. Intervention strategies lack a grading mechanism and are unable to differentiate treatments for users with different churn risk levels. Unified retention plans (such as increasing the amount of advertising push) often not only fail to retain customers but also easily lead to customer resistance. Furthermore, failure to dynamically screen out high-churn-prone customers based on user feedback can also lead to a waste of marketing resources. Summary of the Invention

[0004] The purpose of the present invention is to provide a CRM-based information data analysis method to solve the above technical problems;

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A CRM-based information data analysis method, comprising the following steps:

[0007] S1. Collect user original information data based on CRM and screen out target users with churn risk based on the user original information data;

[0008] S2. Extract customer churn risk features from the original information data of target users, import the customer churn risk features into the trained risk assessment calculation model, and output the results indicating the churn risk level of each target user;

[0009] S3. Generate a retention plan based on the target user's churn risk level and the corresponding original information data and output it to the corresponding target user;

[0010] S4. Collect and analyze the target users’ feedback on the retention plan, and screen out completely lost customers based on the analysis results.

[0011] As a further technical solution, the user-related raw information data includes:

[0012] User basic information data, including identity information and occupation information;

[0013] Interaction information data, including customer service records and platform interaction records;

[0014] Behavioral information data; including login behavior data and transaction behavior data;

[0015] Contract information data, including contract terms and renewal dynamics.

[0016] As a further technical solution, the process of screening out target users at risk of churn includes:

[0017] Based on the user's basic information data, exclude blacklisted users and test accounts;

[0018] Filter out the user set C from the remaining users whose login time exceeds the first preset time. a The user set C whose contract expires and is not renewed for more than the second preset time b ;

[0019] By C target =C a ∪C b Get user set C a and user set C b The union C of target , and marked as the target user set;

[0020] If the target user set C target If the number of users included exceeds the preset value, step S2 is continued to be executed; otherwise, steps S2 to S4 are not executed.

[0021] As a further technical solution, the process of extracting customer churn risk features from the original information data of the target user is to clean the original information data of the target user and then extract the following customer churn risk features:

[0022] Time series features, including the target user's login times and login duration within a unit time period;

[0023] Transaction characteristics, including historical transaction times and total spending amount;

[0024] Sentimental characteristics, including user satisfaction with historical transactions;

[0025] Characteristics of the agreement conditions, including the validity period and effective date of the contract reached between the user and the platform.

[0026] As a further technical solution, the process of importing customer churn risk characteristics into the trained risk assessment calculation model and outputting the results indicating the churn risk level of each target user is as follows:

[0027] Import the parameters corresponding to the target user's customer churn risk characteristics into the calculation model:

[0028]

[0029] Output the customer churn risk value R, and then based on the preset threshold rules, map the customer churn risk value R to discrete risk level intervals through linear segmentation method, including: high risk level interval, medium risk level interval and low risk level interval;

[0030] Among them, n is the number of logins per unit time of the target user in the current stage; n last is the average number of logins in all unit time periods in the historical stage; d is the duration parameter from the target user’s most recent contract validity date to the present; d sum is the target user’s most recent contract validity period; E is the target user’s total consumption amount in all historical transactions; m is the target user’s number of historical transactions; μ is the target user’s satisfaction parameter with historical transactions; ω1~ω3 are preset weights; ε1~ε3 are preset normalization coefficients.

[0031] As a further technical solution, the process of generating a retention plan based on the target user's churn risk level and the corresponding original information data includes:

[0032] Input conditions include the target user's churn risk level corresponding to the risk level range, user basic information data, and interaction information data;

[0033] Adopt a graded intervention strategy and match differentiated solutions based on the target user's churn risk level;

[0034] According to the basic information data and interactive information data of the target user, the push text of the differentiated solution is output and sent to the client.

[0035] As a further technical solution, the process of collecting and analyzing target users' feedback on the retention solution includes:

[0036] After the push text of the differentiation plan is sent, feedback information is obtained through the dialogue window monitoring;

[0037] Extract characteristic parameters from feedback information, including response delay and conversation turns;

[0038] After normalizing the characteristic parameters in the feedback information and the target user's churn risk level parameters, they are imported into the weighted calculation model, and the output result is the churn propensity score;

[0039] The screening threshold is obtained by using the churn propensity scores of historical completely churned users. The churn propensity score of the current target user is compared with the screening threshold. If the churn propensity score of the target user exceeds the screening threshold, the corresponding target user is marked as a completely churned customer and screened out; otherwise, the target user is retained.

[0040] A CRM-based information data analysis system, comprising:

[0041] Information collection module, which collects user-related original information data based on CRM;

[0042] Feature extraction module, used to extract customer churn risk features from user-related raw information data;

[0043] The risk analysis module imports customer churn risk characteristics into the trained calculation model and obtains the customer churn risk level through calculation;

[0044] Dynamic intervention strategy generation module, used to output retention plans based on risk levels and original information data;

[0045] Feedback analysis module, used to collect and analyze target users' feedback on the retention plan;

[0046] The churn determination module determines and screens out completely lost customers based on the analysis results.

[0047] Beneficial effects of the present invention:

[0048] This method reduces data processing by screening target users, focusing on customers with a high likelihood of churn, quickly narrowing the monitoring scope, and then accurately quantifying the degree of customer churn risk by calculating the customer churn risk level. This method implements graded intervention for target users based on different risk levels, avoiding the use of a uniform retention strategy for all users and improving customer retention rates. Screening out completely churned customers based on user feedback avoids excessive disruption to customers, improves the customer experience, and reduces the waste of marketing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below with reference to the accompanying drawings.

[0050] Figure 1 Flowchart of the CRM-based information data analysis method of the present invention;

[0051] Figure 2 Framework diagram of the CRM-based information data analysis system in the present invention; DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] See also Figure 1 As shown, a CRM-based information data analysis method includes the following steps:

[0054] S1. Collect user original information data based on CRM. Based on the user original information data, which includes transaction records, service interaction records, user login or usage frequency, etc., screen out target users with churn risk. The above preliminary screening can reduce the amount of data processing, focus on customers with high churn potential, and improve the efficiency of subsequent analysis. In addition, blacklisted users and test accounts can also be screened out.

[0055] S2. Extracting customer churn risk characteristics from the target user's original information data. Customer churn risk characteristics specifically include transaction characteristics, interaction characteristics, user behavior characteristics, etc., then importing the customer churn risk characteristics into a trained risk assessment calculation model. The output indicates the churn risk level of each target user. Specifically, using a trained machine learning model, such as a random forest or deep learning model, the churn probability is calculated and the risk level is classified.

[0056] S3. Generate a retention plan based on the target user's churn risk level and the corresponding raw information data and output it to the corresponding target user. Differentiated plans are developed based on different risk levels. For example, for low-risk users, optimized recommendations and satisfaction surveys may be sent; for medium-risk users, coupons may be issued; and for high-risk customers, account manager follow-up services may be provided. Furthermore, the push text within the differentiated plan can be automatically generated based on the user's raw information, such as address and recommended product types.

[0057] S4. Collect and analyze target user feedback regarding the retention plan and, based on the analysis, screen out any customers who have completely churned. Monitor user responses to the retention plan. If a user doesn't respond or explicitly terminates service, halt marketing investment to avoid wasted marketing costs.

[0058] Through the above technical solution, this embodiment provides a CRM-based information data analysis method. By screening target users, data processing can be reduced, focusing on customers with a high churn potential and quickly narrowing the monitoring scope. Then, by calculating customer churn risk levels, the degree of churn risk can be accurately quantified. Then, targeted users can be intervened in a graded manner based on different risk levels, avoiding the need to apply a uniform retention strategy to all users and improving customer retention rates. Furthermore, by screening out completely churned customers based on user feedback, excessive disruption to customers can be avoided, improving the customer experience and reducing the waste of marketing resources.

[0059] User-related raw information data includes:

[0060] Basic user information includes identity information such as age, gender, and region, and occupational information such as industry, position, and income level. This information is collected to inform intervention strategies and facilitate the generation of push notifications. For example, high-income professionals may be less sensitive to price but have higher service requirements.

[0061] Interaction information data, including customer service records and platform interaction records, customer service such as complaints, inquiries, resolution time, etc., and platform interaction records such as positive and negative reviews.

[0062] Behavioral information data; including login behavior data and transaction behavior data. Login behavior data includes login frequency and duration, and transaction services include transaction number and amount.

[0063] Contract information data, including contract terms and renewal dynamics.

[0064] Through the above technical solution, this embodiment provides the specific content of the original information data related to the user.

[0065] The process of screening out target users at risk of churn includes:

[0066] Based on the user's basic information data, first exclude blacklisted users and test accounts to ensure that the analysis targets are valid customers;

[0067] Filter out the user set C whose login time exceeds the first preset time (such as 20 days) from the remaining users a The set C of users whose contracts have expired and not been renewed for more than a second preset period (e.g., 15 days) b ;

[0068] By C target =C a ∪C b Get user set C a and user set C b The union C of target, and marked as the target user set;

[0069] If the target user set C target If the number of users included exceeds the preset value, step S2 is continued; otherwise, steps S2 to S4 are not performed. Only when the number of target users reaches the preset threshold (e.g., 100 people) is the subsequent in-depth analysis and intervention triggered to avoid wasting resources.

[0070] Through the above technical solution, this embodiment quickly locates high-risk users through initial screening, combines scale verification to control analysis costs, and ensures that subsequent steps are only effective for a sufficient number of potential churn customers, taking into account both efficiency and accuracy.

[0071] The process of extracting customer churn risk features from the target user's original information data is to clean the target user's original information data and then extract the following customer churn risk features:

[0072] Time series features are used to identify activity decay trends, including the number of logins and login duration of target users within a unit time period;

[0073] Transaction characteristics, including historical transaction times and total consumption amount; statistics on consumption frequency and total amount to determine changes in user value and consumption willingness.

[0074] Emotional characteristics, including user satisfaction with historical transactions. Satisfaction can be measured by quantifying the star rating (1 to 5 stars) submitted by users after completing transactions.

[0075] Characteristics of the agreement conditions, including the validity period and effective date of the contract reached between the user and the platform.

[0076] Through the above technical solution, this embodiment provides a process for extracting customer churn risk characteristics from the original information data of target users. This process extracts four types of characteristics from the cleaned data: behavior, transaction, emotion, and contract. By quantifying user activity, spending power, satisfaction, and agreement constraints, a multi-dimensional churn risk assessment system is constructed to provide structured input for subsequent model analysis.

[0077] The process of importing customer churn risk characteristics into the trained risk assessment calculation model and outputting the results indicating the churn risk level of each target user is as follows:

[0078] Import the parameters corresponding to the target user's customer churn risk characteristics into the calculation model:

[0079]

[0080] Output the customer churn risk value R, and then based on the preset threshold rules, map the customer churn risk value R to discrete risk level intervals through linear segmentation method, including: high risk level interval, medium risk level interval and low risk level interval; in the formula, Reflects the contract status. If If is a positive value, it indicates that the contract is not renewed and the corresponding loss risk is high. If it is a negative value, it means that the customer is currently within the contract period and the corresponding loss risk is relatively small.

[0081] Among them, n is the number of logins per unit time of the target user in the current stage; n last is the average number of logins in all unit time periods in the historical stage; d is the duration parameter from the target user’s most recent contract validity date to the present; d sum is the target user's most recent contract validity period; E is the target user's total spending in all historical transactions; m is the target user's number of historical transactions; μ is the target user's satisfaction with historical transactions, which can be the average star rating of all historical transactions; ω1-ω3 are preset weights; and ε1-ε3 are preset normalization coefficients. Through the above technical solution, this embodiment provides a process for calculating the user churn risk level.

[0082] The process of generating a retention plan based on the target user's churn risk level and the corresponding original information data includes:

[0083] Input conditions include the target user's churn risk level corresponding to the risk level range, user basic information data, and interaction information data;

[0084] Adopt a graded intervention strategy and match differentiated solutions based on the target user's churn risk level; for example:

[0085] For low-risk users, implement mild reminders, such as satisfaction surveys;

[0086] Implement proactive care for users at medium risk levels, such as issuing coupons;

[0087] Implement strong retention strategies for high-risk users, such as free value-added services.

[0088] Based on the target user's basic information and interactive data, a push notification message with differentiated solutions is generated. This push notification message clarifies the solution and includes a link to the corresponding activity, which is then sent to the client. The user's basic information is used as a reference for addressing the user when editing the notification message, while the interactive data is used to define the product category in the notification message.

[0089] Through the above technical solution, this embodiment provides a process for generating a retention plan based on the target user's churn risk level and the corresponding original information data.

[0090] The process of collecting and analyzing target users' feedback on the retention plan includes:

[0091] After the push text of the differentiation plan is sent, feedback information is obtained through the dialogue window monitoring;

[0092] Extract characteristic parameters from the feedback information, including response delay and conversation rounds (the number of times the customer actively initiates a conversation after receiving the push text). After normalizing the characteristic parameters in the feedback information and the target user's churn risk level parameters, they are imported into a weighted calculation model, and the output is a churn propensity score.

[0093] For example, let the loss risk level be The response delay is x2;

[0094] Normalization processing: is the mean of x1 to x3, and σ is the standard deviation of x1 to x3;

[0095] By formula Calculate the churn propensity score S

[0096] The screening threshold is obtained by using the churn propensity scores of historical completely churned users. For example, the average churn propensity scores of all completely churned users are taken as the screening threshold. The churn propensity score of the current target user is compared with the screening threshold. If the churn propensity score of the target user exceeds the screening threshold, the corresponding target user is marked as a completely churned customer and screened out; otherwise, the target user is retained.

[0097] Through the above technical solution, this embodiment provides a process for collecting and analyzing the feedback information of the target user regarding the retention solution.

[0098] See also Figure 2 As shown, a CRM-based information data analysis system includes:

[0099] The information collection module collects user-related raw information data based on CRM, obtains users' basic data, transaction records, interaction behaviors and other raw information from the CRM system, and provides a data basis for subsequent analysis;

[0100] The feature extraction module is used to extract customer churn risk features from user-related raw information data; and extract key features from the raw data for evaluating churn risk.

[0101] The risk analysis module imports customer churn risk characteristics into the trained calculation model, obtains the customer churn risk level through calculation; calculates the customer churn probability and divides the risk level into low, medium and high levels.

[0102] The dynamic intervention strategy generation module is used to output retention plans based on risk levels and original information data; based on risk levels and user original information data, it automatically generates personalized retention plans, such as coupons, exclusive services, etc.

[0103] The feedback analysis module is used to collect and analyze the feedback information of target users on the retention plan; monitor the user's response to the intervention measures and evaluate the effectiveness of the strategy.

[0104] The churn determination module uses analysis results to identify and remove completely churned customers. Based on feedback data, completely churned customers are identified and removed from the active recovery list to optimize resource allocation.

[0105] Through the above technical solution, the system provided in this embodiment can implement graded intervention on target users based on different risk levels, avoiding the use of a uniform retention strategy for all users and improving customer retention. Furthermore, by screening out completely churned customers based on user feedback, it can avoid excessive disruption to customers, improve the customer experience, and reduce the waste of marketing resources.

[0106] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A CRM-based information data analysis method, characterized in that: The method comprises the following steps: S1. Collect user original information data based on CRM and screen out target users with churn risk based on the user original information data; S2. Extract customer churn risk features from the original information data of target users, import the customer churn risk features into the trained risk assessment calculation model, and output the results indicating the churn risk level of each target user; S3. Generate a retention plan based on the target user's churn risk level and the corresponding original information data and output it to the corresponding target user; S4. Collect and analyze the target users’ feedback on the retention plan, and screen out completely lost customers based on the analysis results.

2. The CRM-based information data analysis method according to claim 1, characterized in that: User-related raw information data includes: User basic information data, including identity information and occupation information; Interaction information data, including customer service records and platform interaction records; Behavioral information data; including login behavior data and transaction behavior data; Contract information data, including contract terms and renewal dynamics.

3. The CRM-based information data analysis method according to claim 2, characterized in that: The process of screening out target users at risk of churn includes: Based on the user's basic information data, exclude blacklisted users and test accounts; Filter out the user set C from the remaining users whose login time exceeds the first preset time. a The user set C whose contract expires and is not renewed for more than the second preset time b ; By C target =C a ∪C b Get user set C a and user set C b The union C of target , and marked as the target user set; If the target user set C target If the number of users included exceeds the preset value, step S2 is continued to be executed; otherwise, steps S2 to S4 are not executed.

4. The CRM-based information data analysis method according to claim 3, characterized in that: The process of extracting customer churn risk features from the target user's original information data is to clean the target user's original information data and then extract the following customer churn risk features: Time series features, including the target user's login times and login duration within a unit time period; Transaction characteristics, including historical transaction times and total spending amount; Sentimental characteristics, including user satisfaction with historical transactions; Characteristics of the agreement conditions, including the validity period and effective date of the contract reached between the user and the platform.

5. The CRM-based information data analysis method according to claim 4, characterized in that: The process of importing customer churn risk characteristics into the trained risk assessment calculation model and outputting the results indicating the churn risk level of each target user is as follows: Import the parameters corresponding to the target user's customer churn risk characteristics into the calculation model: Output the customer churn risk value R, and then based on the preset threshold rules, map the customer churn risk value R to discrete risk level intervals through linear segmentation method, including: high risk level interval, medium risk level interval and low risk level interval; Among them, n is the number of logins per unit time of the target user in the current stage; n last is the average number of logins in all unit time periods in the historical stage; d is the duration parameter from the target user’s most recent contract validity date to the present; d sum is the target user’s most recent contract validity period; E is the target user’s total consumption amount in all historical transactions; m is the target user’s number of historical transactions; μ is the target user’s satisfaction parameter with historical transactions; ω1~ω3 are preset weights; ε1~ε3 are preset normalization coefficients.

6. The CRM-based information data analysis method according to claim 5, characterized in that: The process of generating a retention plan based on the target user's churn risk level and the corresponding original information data includes: Input conditions include the target user's churn risk level corresponding to the risk level range, user basic information data, and interaction information data; Adopt a graded intervention strategy and match differentiated solutions based on the target user's churn risk level; According to the basic information data and interactive information data of the target user, the push text of the differentiated solution is output and sent to the client.

7. The CRM-based information data analysis method according to claim 1, characterized in that: The process of collecting and analyzing target users' feedback on the retention plan includes: After the push text of the differentiation plan is sent, feedback information is obtained through the dialogue window monitoring; Extract characteristic parameters from feedback information, including response delay and conversation turns; After normalizing the characteristic parameters in the feedback information and the target user's churn risk level parameters, they are imported into the weighted calculation model, and the output result is the churn propensity score; The screening threshold is obtained by using the churn propensity scores of historical completely churned users. The churn propensity score of the current target user is compared with the screening threshold. If the churn propensity score of the target user exceeds the screening threshold, the corresponding target user is marked as a completely churned customer and screened out; otherwise, the target user is retained.

8. A CRM-based information data analysis system, characterized in that: The system is used to execute the CRM-based information data analysis method according to any one of claims 1 to 7, and the system includes: Information collection module, which collects user-related original information data based on CRM; Feature extraction module, used to extract customer churn risk features from user-related raw information data; The risk analysis module imports customer churn risk characteristics into the trained calculation model and obtains the customer churn risk level through calculation; Dynamic intervention strategy generation module, used to output retention plans based on risk levels and original information data; Feedback analysis module, used to collect and analyze target users' feedback on the retention plan; The churn determination module determines and screens out completely lost customers based on the analysis results.

Images