Group insurance salesman portrait construction method and device and computer equipment

Abstract

The invention relates to the technical field of insurance business management, in particular to a group insurance salesman portrait construction method and device and computer equipment, and the method comprises the steps: firstly constructing a salesman portrait standard database, receiving and verifying a salesman information data template file, and obtaining salesman information data passing verification; then performing multi-dimensional feature extraction and comprehensive analysis on the salesman information data to obtain a salesman portrait comprehensive feature score, and generating a salesman portrait construction result according to the salesman portrait comprehensive feature score; and finally, monitoring through a system monitoring technology and a salesman portrait comprehensive feature score, and triggering an update feedback mechanism according to a monitoring result. Through a feature extraction technology, multi-dimensional feature extraction is carried out on received and verified salesman information data, an accurate and comprehensive salesman portrait is constructed, and an insurance company is helped to deeply understand the features and advantages of salesmen.

Description

Technical Field

[0001] The present invention relates to the technical field of insurance business management, and in particular to a method, device and computer equipment for constructing a salesperson portrait for group insurance. Background Art

[0002] Group insurance is an insurance policy that takes a group as the insured object, and is insured in the name of the group and a general insurance contract is issued by the insurer. The insurer provides protection to the members of the group in accordance with the provisions of the contract. In the process of carrying out group insurance business, customers are an important resource for group insurance agencies. Salesmen are often used in the industry to refer to them. Accurately understanding the characteristics of salesmen's portraits is crucial for formulating marketing strategies and optimizing product services.

[0003] At present, customer information collection lacks systematicity and standardization: on the one hand, customer information collection lacks systematicity. Under traditional methods, salesperson information is recorded through offline communication or simple spreadsheets. The information is scattered and the format is not uniform. For example, some are measured by the number of employees, and some are measured by annual turnover, which makes the data unable to be directly used for comprehensive analysis; on the other hand, in terms of customer portrait construction, existing methods often only focus on data of a single dimension, such as portraying salespersons only based on the type of insurance products purchased by the salesperson, so as to achieve the purpose of salesperson portrait analysis.

[0004] However, in actual application, the existing group insurance agent analysis method has some shortcomings. For example, recording agent information through simple tables may make information integration difficult, making it difficult to form a comprehensive and accurate agent portrait; only focusing on single-dimensional data ignores the agent's characteristics in other aspects, such as regional characteristics, communication methods, risk preferences, etc. This one-sided portrait cannot fully present the customer's true needs and potential value, resulting in insurance companies lacking sufficient basis when formulating targeted marketing strategies and service plans; the existing group insurance customer analysis method can no longer meet the increasingly complex and changing market demands, and there is an urgent need for a method that can comprehensively and accurately construct a group insurance agent portrait. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method, device and computer equipment for constructing a salesperson portrait for group insurance, so as to solve the problems raised in the above-mentioned background technology, such as the difficulty in integrating salesperson information and the one-sided construction of portraits.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for constructing a salesperson portrait for group insurance, comprising:

[0007] S1: Based on the information required by the insurance industry's product recommendation regulations, using big data technology, we will store and update standardized salesperson information templates in real time, including salesperson basic information data templates, historical group insurance data templates, and occupational risk level standard databases, to build a salesperson portrait standard database;

[0008] S2: Based on the standardized salesperson information template obtained in S1, receive and verify the salesperson information data, and obtain the verified salesperson information data;

[0009] S3: Using feature extraction technology, perform multi-dimensional feature extraction on the verified salesperson information data obtained in S2 to construct a multi-dimensional feature profile of the salesperson, including features of the salesperson's basic information profile, salesperson's behavior profile, salesperson's contribution value profile, and salesperson's insurance risk profile.

[0010] S4: Using big data analysis technology, comprehensively analyze the multi-dimensional features of the salesperson portrait obtained in S3 to obtain a comprehensive feature score for the salesperson portrait. Based on the comprehensive feature score, the salesperson portrait construction result is generated.

[0011] S5: Through system monitoring technology, the comprehensive feature scores of the salesperson portrait obtained in S4 are monitored, and the update feedback mechanism is triggered according to the monitoring results. The feedback results are transmitted to the front-end and back-end administrators of the system for human-computer interaction.

[0012] Preferably, a device for constructing a salesperson portrait for group insurance includes:

[0013] Build a standard salesperson profile database: Based on the information required by the insurance industry's product recommendation regulations, using big data technology, we store and update standardized salesperson information templates in real time, including salesperson basic information data templates, group insurance product preference data templates, and historical group insurance underwriting data templates, to build a standard salesperson profile database;

[0014] Salesperson portrait data collection and verification module: Based on the standardized salesperson information template, it receives and verifies salesperson information data, and transmits the verified salesperson information data to the salesperson portrait multi-dimensional feature construction module;

[0015] Salesperson portrait multi-dimensional feature construction module: Through feature extraction technology, multi-dimensional feature extraction is performed on the verified salesperson information data, and the multi-dimensional features of the salesperson portrait are constructed and transmitted to the salesperson portrait construction generation module;

[0016] Salesperson portrait construction and generation module: This module uses big data analysis technology to comprehensively analyze the multi-dimensional features of salesperson portraits to obtain a comprehensive feature score for the salesperson portraits. This score is then used to generate salesperson portrait construction results and transmitted to the salesperson portrait construction feedback module.

[0017] Salesperson portrait construction feedback module: Through system monitoring technology, the comprehensive feature score of the salesperson portrait is monitored, the update feedback mechanism is triggered according to the monitoring results, and the feedback results are transmitted to the front-end administrator for human-computer interaction.

[0018] Preferably, a computer device is characterized in that it includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the processor executes the program in the memory to implement the method for constructing a salesperson portrait for group insurance.

[0019] Technical effects and advantages of the present invention:

[0020] 1. The present invention is based on building a salesperson portrait standard database, receiving the salesperson's basic information data file and historical group insurance data, and generating a salesperson information verification result report through three-level verification, ensuring that the basic data format complies with the insurance industry data standards and insurance business common sense, providing an accurate data benchmark for the subsequent construction of group insurance salesperson portraits;

[0021] 2. This invention uses feature extraction technology to extract multi-dimensional features from received and verified salesperson information data, constructing accurate and comprehensive salesperson portraits. This avoids the problem of one-sided portrait construction, helps insurance companies gain a deeper understanding of the characteristics and advantages of salespeople, and provides strong data support for salesperson management.

[0022] 3. The present invention monitors the comprehensive feature scores of salesperson portraits through system monitoring technology, triggers an update feedback mechanism based on the monitoring results, and transmits the feedback results to the front-end administrator for human-computer interaction. It can timely detect changes in salesperson portraits, provide decision support for insurance companies, and ensure stable business operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall process of the present invention.

[0024] Figure 2 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0025] 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1 As shown, the present invention provides a salesperson portrait construction device for group insurance, including: constructing a salesperson portrait standard database, a salesperson portrait data collection and verification module, a salesperson portrait multi-dimensional feature construction module, a salesperson portrait construction generation module and a salesperson portrait construction feedback module.

[0027] The salesperson portrait standard database is connected to the salesperson portrait data collection and verification module and the salesperson portrait multi-dimensional feature construction module, the salesperson portrait data collection and verification module is connected to the salesperson portrait multi-dimensional feature construction module, and the salesperson portrait construction generation module is respectively connected to the salesperson portrait multi-dimensional feature construction module and the salesperson portrait construction feedback module.

[0028] Build a standard salesperson profile database: Based on the information required by the insurance industry's product recommendation regulations, using big data technology, we store and update standardized salesperson information templates in real time, including salesperson basic information data templates, group insurance product preference data templates, and historical group insurance underwriting data templates, to build a standard salesperson profile database;

[0029] Salesperson portrait data collection and verification module: Based on the standardized salesperson information template, it receives and verifies salesperson information data, and transmits the verified salesperson information data to the salesperson portrait multi-dimensional feature construction module;

[0030] Salesperson portrait multi-dimensional feature construction module: Through feature extraction technology, multi-dimensional feature extraction is performed on the verified salesperson information data, and the multi-dimensional features of the salesperson portrait are constructed and transmitted to the salesperson portrait construction generation module;

[0031] What needs to be specifically explained in this embodiment is that the salesperson portrait multi-dimensional feature construction module includes a salesperson basic information portrait construction unit, a salesperson behavior portrait construction unit, a salesperson contribution value portrait construction unit and a salesperson insurance risk portrait construction unit.

[0032] Salesperson portrait construction and generation module: This module uses big data analysis technology to comprehensively analyze the multi-dimensional features of salesperson portraits to obtain a comprehensive feature score for the salesperson portraits. This score is then used to generate salesperson portrait construction results and transmitted to the salesperson portrait construction feedback module.

[0033] Salesperson portrait construction feedback module: Through system monitoring technology, the comprehensive feature score of the salesperson portrait is monitored, the update feedback mechanism is triggered according to the monitoring results, and the feedback results are transmitted to the front-end administrator for human-computer interaction.

[0034] See also Figure 2 As shown, a method for constructing a salesperson portrait for group insurance includes the following steps: S1: Based on the information required by the insurance industry product recommendation regulations, using big data technology, real-time storage and update of standardized salesperson information templates, including salesperson basic information data templates, historical group insurance underwriting data templates and occupational risk level standard databases, to construct a salesperson portrait standard database; S2: Based on the standardized salesperson information templates obtained in S1, receiving and verifying the salesperson information data to obtain verified salesperson information data; S3: Using feature extraction technology, multi-dimensional feature extraction is performed on the verified salesperson information data obtained in S2. Extract and construct multi-dimensional features of the salesperson portrait, including the salesperson's basic information portrait features, salesperson's behavior portrait features, salesperson's contribution value portrait features, and salesperson's insurance risk portrait features. S4: Through big data analysis technology, comprehensively analyze the multi-dimensional features of the salesperson portrait obtained in S3 to obtain the comprehensive feature score of the salesperson portrait, and generate the salesperson portrait construction result based on the comprehensive feature score of the salesperson portrait. S5: Through system monitoring technology, monitor the comprehensive feature score of the salesperson portrait obtained in S4, trigger the update feedback mechanism according to the monitoring results, and transmit the feedback results to the front-end and back-end administrators of the system for human-computer interaction.

[0035] S1: Based on the information required by the insurance industry's product recommendation regulations, using big data technology, we will store and update standardized salesperson information templates in real time, including salesperson basic information data templates, historical group insurance data templates, and occupational risk level standard databases, to build a salesperson portrait standard database;

[0036] What needs to be specifically explained in this embodiment is that the basic information module includes basic information such as the salesperson's name, group name, unified social credit code, establishment time, registered address, etc.; the cooperation history module saves past cooperation records with customers, including the start time and end time of the cooperation, the list of purchased insurance products, claims records, etc. These two data templates can ensure the comprehensiveness and standardization of customer information collection; the occupational risk level standard database can be obtained through the insurance industry occupational risk level classification standards.

[0037] S2: Based on the standardized salesperson information template obtained in S1, receiving and verifying the salesperson information data, and obtaining the verified salesperson information data, including the following steps:

[0038] S2.1: Based on the standardized salesperson information template obtained in S1, receive the salesperson's basic information data file BDF and the historical group insurance data file HDF, where BDF = [bd1, bd1, ..., bd n ], bd n Indicates the nth field, where n indicates the number of basic information fields; HDF = [hd1, hd2, ..., hd m ], hd m Indicates the mth field, where m represents the number of historical group insurance fields;

[0039] S2.2: First, perform a first-level field check. Build a regular expression rule library based on insurance industry standards to match fields in real time. Dynamically update field rule parameters through the configuration center (such as Nacos, Apollo), such as the year range of ID card numbers and mobile phone number segments. When operators add new number segments (such as 198, 166), there is no need to modify the code to obtain the first-level field check results, including pass and fail. If the check fails, a corresponding field error prompt will be given, and the subsequent process will be terminated until it passes. If the check passes, the second-level field logic check will be performed to ensure that the basic data format complies with the insurance industry data standards. Then, a second-level logic check will be performed. Based on the insurance industry logic standards, the Drools rule engine will be used to perform pattern matching on the field logic (such as the correlation between the insured age and the date of birth on the ID card). To the logical verification result, if the match fails, the corresponding field logic error prompt is issued, and the subsequent process is terminated until it passes. If the match passes, the third-level group insurance product rule verification is entered. A decision tree model is used, with the group insurance product type (such as group accident insurance, employer liability insurance renewal, etc.) as the root node, cross-field logical constraints as intermediate nodes (such as "insured age ≥18 years old and ≤65 years old", "correlation verification of insurance amount and occupational risk", etc.), and group insurance product verification results as leaf nodes (such as passing verification, triggering manual review, etc.). A group insurance product rule verification model is constructed. If the verification fails, the corresponding group insurance product rule error prompt is issued, and the subsequent process is terminated until it passes. If the verification passes, a salesperson information verification result report is generated, including passed fields, abnormal fields, and handling suggestions;

[0040] What needs to be specifically explained in this embodiment is that regular expression is a text pattern matching tool that implements functions such as text retrieval, replacement, and verification through a regular string composed of specific character combinations. It is widely used in programming, data processing, form validation and other fields, and is efficient and flexible. For example, the insured's ID number must be 18 digits + X (the last digit), and the policy effective date must be in the YYYY-MM-DD format; the configuration center is the core component for dynamic configuration and service governance in the microservice architecture. Nacos and Apollo, as mainstream open source solutions in China, have significant differences in functional positioning, technical architecture, and applicable scenarios; the Drools rule engine refers to the distribution of rule calculation tasks to multiple nodes (such as concurrent processing of insurance underwriting rules), and all nodes in the cluster synchronize the latest rules (to avoid inconsistent rule versions on different nodes).

[0041] S3: Using feature extraction technology, perform multi-dimensional feature extraction on the verified salesperson information data obtained in S2 to construct a multi-dimensional feature profile of the salesperson, including the salesperson's basic information profile features, salesperson's behavior profile features, salesperson's contribution value profile features, and salesperson's insurance risk profile features. The following steps are included:

[0042] S3.1: Salesperson basic information portrait features: Extract the group name from the verified salesperson information data, obtain the corresponding number of employees emp, and use the piecewise linear interpolation method to calculate the human scale score emp_sco. If emp<50, then emp_sco=0.2. If 50≤emp<200, then If 200≤emp<500, then If 500≤emp<1000, then If emp ≥ 1000, then emp_sco = 1. Then, based on the group's region, identify the level label value GL of the group's city (for example, a first-tier city has a numerical label of 1, a second-tier city has a numerical label of 2, and so on). Finally, through big data analysis technology, obtain the salesperson's basic information profile score BD_sco, BD_sco = emp_sco × (1 + 1 / GL).

[0043] S3.2: Salesperson behavior profile features: Extract the historical group insurance list from the verified salesperson information data, and perform frequency statistics to obtain the number of group insurance data sets pro_cou, pro_cou = [pro_id1:n1, pro_id1:n2,..., pro_id k :nk], pro_id k :nk represents the number of historical insurance purchases for the kth group insurance, k represents the number of group insurance types, and the group insurance product preference score pre_sco is obtained. The larger the value, the more concentrated the customer's preference for group insurance products. At the same time, a list of communication records is obtained from the system communication log. Each record in the list contains the initiation timestamp i_t I and reply timestamp r_t I , in hours, to get the communication response timeliness score res_sco, m represents the total number of communication records, and t0 represents the insurance industry's response time delay benchmark, such as 48 hours. Finally, through big data analysis technology, the salesperson behavior profile score BP_sco is obtained: BP_sco = a1 × [pre_sco / max(pre_sco)] + a2 × [res_sco / max(res_sco)], where a1 and a2 represent the corresponding weights, a1 = 2 × a2, and max() represents the historical maximum value.

[0044] S3.3: Salesperson contribution value profile features: Extract the average annual premium AAP, the total claim amount paid to the target group Tca, the insurance company's actual historical premium income Gpi, the number of group insurance products that have been renewed rp, the historical cumulative number of group insurance products ep, and the customer's first insurance year fy from the verified salesperson information data, and obtain the basic renewal rate br, renewal attenuation factor dr, and salesperson profile behavior risk adjustment coefficient RAC, br = rp / ep, dr = 0.9. cy-fy , cy represents the current year, RAC=1-[Tca / (Gpi×RAC0)], RAC0 represents the benchmark claim ratio, and the comprehensive renewal rate err is obtained by the basic renewal rate br and the renewal attenuation factor dr. r i The weight of the i-th group insurance product is determined according to the Insurance Product Classification Guidelines. k represents the number of group insurance types. For example, the weight of health insurance is 1.2, the weight of life insurance is 1, and the weight of accident insurance is 0.8. i represents the basic renewal rate of the i-th group insurance product; finally, the salesperson contribution value portrait score LTV_sco is obtained by big data analysis technology. ∑(AAP) represents the cumulative value of historical average annual premiums;

[0045] S3.4: Salesperson insurance risk profile characteristics: Extract the target group occupation from the verified salesperson information data, match the occupational risks in the target group occupational risk level standard database, and obtain the risk level label value R0 of the target group occupation. For example, office clerk R0 = 1, construction worker R0 = 2, firefighter R0 = 5; then, based on the target group occupational baseline accident rate, obtain the comprehensive risk correction coefficient C, C = C0 × [1-0.1 × (1-tcr)], tcr represents the safety training coverage rate, which is the ratio of the number of employees in the group who actually receive safety training to the total number of employees who should participate in the training; finally, through big data analysis technology, obtain the salesperson insurance risk profile score RP_sco, RAC represents the risk adjustment coefficient of salesperson profile behavior;

[0046] S4. Using big data analysis technology, comprehensively analyze the multi-dimensional features of the salesperson portrait obtained in S3 to obtain a comprehensive feature score for the salesperson portrait. Based on the comprehensive feature score, generate the salesperson portrait construction result, where the comprehensive feature score CF_sco is obtained, CF_sco = (b1×BD_sco+b2×BP_sco+b3×LTV_sco) / b4×RP_sco, where b1, b2, b3, and b4 represent the corresponding weights, BD_sco represents the salesperson's basic information portrait score, BP_sco represents the salesperson's behavior portrait score, and LTV_sco represents the salesperson's contribution value portrait. Score, RP_sco represents the insurance risk profile score of the salesperson. The entropy weight method weight calculation function is used to obtain the corresponding weights based on the historical group insurance feature samples under the occupational risk level of the target group in the same city, such as b1=0.2, b2=0.2, b3=0.3, and b4=0.3. Then, the comprehensive feature score CF_sco of the salesperson portrait is compared with the corresponding threshold. If the comparison result is greater than 50% of the threshold, it is considered a high-value customer. If the comparison result is greater than the threshold range [0,50%], it is a potential customer. If the comparison result is less than the threshold, it is a general customer. The salesperson portrait construction result is obtained, including high-value customers, potential customers, and general customers.

[0047] S5. Through system monitoring technology, the comprehensive feature score of the salesperson portrait obtained in S4 is monitored, and the update feedback mechanism is triggered according to the monitoring results. The feedback results are transmitted to the front-end and back-end administrators of the system for human-computer interaction. Through system monitoring technology, the comprehensive feature score threshold of the salesperson portrait is compared. Within the preset update cycle, if the comparison result is still in the original salesperson portrait construction result, there is no update operation. Otherwise, the update feedback mechanism is triggered to perform an update operation, such as updating a high-value customer to a potential customer.

[0048] What needs to be specifically explained in this implementation is that the comprehensive feature score of the salesperson portrait can comprehensively reflect the customer's performance in multiple dimensions such as basic characteristics, behavioral characteristics, value characteristics and risk characteristics, thereby providing a quantitative customer value assessment indicator; through comprehensive scoring, enterprises can quickly identify high-value customers and low-value customers, providing a basis for subsequent customer management and marketing strategy formulation; the system front-end administrator connects with subordinate salespeople, and the system can manage salespeople; the system back-end administrator cooperates with salespeople to select products and place orders, organize ledgers, and the system can match products, generate quotations, maintain salespeople, and import daily reports.

[0049] What needs to be specifically explained in this embodiment is that the present invention also provides a computer device, characterized in that it includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the processor executes the program in the memory to implement the method for constructing a salesperson portrait of a group insurance.

[0050] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0051] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

Claims

1. A method for constructing a salesperson portrait for group insurance, characterized in that: include: S1: Based on the information required by the insurance industry's product recommendation regulations, using big data technology, we will store and update standardized salesperson information templates in real time, including salesperson basic information data templates, historical group insurance data templates, and occupational risk level standard databases, to build a salesperson portrait standard database; S2: Based on the standardized salesperson information template obtained in S1, receive and verify the salesperson information data, and obtain the verified salesperson information data; S3: Using feature extraction technology, perform multi-dimensional feature extraction on the verified salesperson information data obtained in S2 to construct a multi-dimensional feature profile of the salesperson, including features of the salesperson's basic information profile, salesperson's behavior profile, salesperson's contribution value profile, and salesperson's insurance risk profile. S4: Using big data analysis technology, comprehensively analyze the multi-dimensional features of the salesperson portrait obtained in S3 to obtain a comprehensive feature score for the salesperson portrait. Based on the comprehensive feature score, the salesperson portrait construction result is generated. S5: Through system monitoring technology, the comprehensive feature scores of the salesperson portrait obtained in S4 are monitored, and the update feedback mechanism is triggered according to the monitoring results. The feedback results are transmitted to the front-end and back-end administrators of the system for human-computer interaction.

2. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: The multi-dimensional features of the salesperson portrait are constructed in S3, including the salesperson basic information portrait features: the group name is extracted from the verified salesperson information data, the corresponding number of employees emp is obtained, and the human scale score emp_sco is calculated using the piecewise linear interpolation method. If emp < 50, then emp_sco = 0.2, if 50 ≤ emp < 200, then If 200≤emp<500, then If 500≤emp<1000, then If emp ≥ 1000, then emp_sco = 1; then, based on the group's region, identify the level label value GL of the city where the group is located; finally, through big data analysis technology, obtain the salesperson's basic information portrait score BD_sco, BD_sco = emp_sco × (1 + 1 / GL).

3. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: The multi-dimensional features of the salesperson portrait are constructed in S3, including the salesperson behavior portrait features: the historical insurance group insurance list is extracted from the verified salesperson information data, and the frequency statistics are performed to obtain the insurance frequency dataset pro_cou for each group insurance, pro_cou = [pro_id1:n1, pro_id1:n2,..., pro_id k :nk], pro_id k :nk represents the number of historical insurance applications for the kth group insurance, k represents the number of group insurance types, and the group insurance product preference score pre_sco is obtained; at the same time, a list of communication records is obtained from the system communication log, and each record in the list contains the initiation timestamp i_t I and reply timestamp r_t I , in hours, to obtain the communication response timeliness score res_sco; finally, through big data analysis technology, the salesperson behavior profile score BP_sco is obtained.

4. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: In S3, multi-dimensional features of the salesperson profile are constructed, including the salesperson contribution value profile features: the average annual premium AAP, the total claim amount paid to the target group Tca, the insurance company's actual historical premium income Gpi, the number of group insurance products renewed rp, the historical cumulative number of group insurance products ep, and the customer's first insurance year fy are extracted from the verified salesperson information data. The basic renewal rate br, the renewal attenuation factor dr, and the salesperson profile behavior risk adjustment coefficient RAC are obtained respectively, br = rp / ep, dr = 0.

9. cy-fy , cy represents the current year, RAC = 1-[Tca / (Gpi×RAC0)], RAC0 represents the benchmark claims ratio, and the comprehensive renewal rate err is obtained by the basic renewal rate br and the renewal attenuation factor dr; finally, big data analysis technology is used to obtain the salesperson contribution value portrait score LTV_sco.

5. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: The multi-dimensional features of the salesperson's profile are constructed in S3, including the salesperson's insurance risk profile features: The target group occupation is extracted from the verified salesperson information data, and the occupational risks in the target group occupational risk level standard database are matched to obtain the risk level label value R0 of the target group occupation; then, based on the target group occupational baseline accident rate, the comprehensive risk correction coefficient C is obtained, C = C0 × [1-0.1 × (1-tcr)], where tcr represents the safety training coverage rate, which is the ratio of the number of employees in the group who actually receive safety training to the total number of employees who should participate in the training; finally, the salesperson insurance risk profile score RP_sco is obtained through big data analysis technology. RAC represents the risk adjustment coefficient of salesperson profile behavior.

6. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: The S4 includes obtaining the comprehensive feature score CF_sco of the salesperson portrait, CF_sco = (b1×BD_sco+b2×BP_sco+b3×LTV_sco) / b4×RP_sco, b1, b2, b3 and b4 respectively represent the corresponding weights, BD_sco represents the salesperson's basic information portrait score, BP_sco represents the salesperson's behavior portrait score, LTV_sco represents the salesperson's contribution value portrait score, and RP_sco represents the salesperson's insurance risk portrait score.

7. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: The S4 also includes generating the salesperson portrait construction results: comparing the comprehensive feature score CF_sco of the salesperson portrait with the corresponding threshold. If the comparison result is greater than the threshold by 50%, it is considered a high-value customer; if the comparison result is greater than the threshold range [0,50%], it is a potential customer; if the comparison result is less than the threshold, it is a general customer. The salesperson portrait construction results are obtained, including high-value customers, potential customers and general customers.

8. The method for constructing a salesperson portrait for group insurance according to claim 1, characterized in that: In S5, an update feedback mechanism is triggered according to the monitoring results: through system monitoring technology, the comprehensive feature score threshold of the salesperson portrait is compared. Within the preset update cycle, if the comparison result is still in the original salesperson portrait construction result, there is no update operation; otherwise, the update feedback mechanism is triggered to perform the update operation.

9. A digital advertising device based on big data analysis, for use with the group insurance salesperson portrait construction method described in any one of claims 1 to 8, comprising: Build a standard salesperson profile database: Based on the information required by the insurance industry's product recommendation regulations, using big data technology, we store and update standardized salesperson information templates in real time, including salesperson basic information data templates, group insurance product preference data templates, and historical group insurance underwriting data templates, to build a standard salesperson profile database; Salesperson portrait data collection and verification module: Based on the standardized salesperson information template, it receives and verifies salesperson information data, and transmits the verified salesperson information data to the salesperson portrait multi-dimensional feature construction module; Salesperson portrait multi-dimensional feature construction module: Through feature extraction technology, multi-dimensional feature extraction is performed on the verified salesperson information data, and the multi-dimensional features of the salesperson portrait are constructed and transmitted to the salesperson portrait construction generation module; Salesperson portrait construction and generation module: This module uses big data analysis technology to comprehensively analyze the multi-dimensional features of salesperson portraits to obtain a comprehensive feature score for the salesperson portraits. This score is then used to generate salesperson portrait construction results and transmitted to the salesperson portrait construction feedback module. Salesperson portrait construction feedback module: Through system monitoring technology, the comprehensive feature score of the salesperson portrait is monitored, the update feedback mechanism is triggered according to the monitoring results, and the feedback results are transmitted to the front-end administrator for human-computer interaction.

10. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program in the memory to implement a method for constructing a salesperson portrait for group insurance as described in any one of claims 1 to 8.

Images