Intelligent seller matching method and device for orphan insurance policy and computer equipment

Abstract

The invention relates to an orphan insurance policy salesman intelligent matching method and device and computer equipment. The method comprises the following steps: acquiring salesperson information of salesperson in each region, insurance policy information and user information of each orphan insurance policy and orphan insurance policy matching logic, and identifying salesperson characteristics of each salesperson, insurance policy characteristics of each orphan insurance policy and user characteristics for each region; identifying an orphan insurance policy matching strategy of the region based on the orphan insurance policy matching logic of the region, and training an initial orphan insurance policy matching model based on the orphan insurance policy matching strategy of the region to obtain an orphan insurance policy matching model; and matching a salesman recommendation list corresponding to each orphan insurance policy and each salesman recommendation reason through an orphan insurance policy matching model corresponding to the region, and screening a target salesman corresponding to each orphan insurance policy in response to a salesman screening operation of a user corresponding to each orphan insurance policy. By adopting the method, the intelligent matching efficiency of salespersons of the orphan insurance policy can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of financial insurance services, and in particular to a method, device and computer equipment for intelligent matching of salespersons for orphan insurance policies. Background Art

[0002] When selling insurance, each policy corresponds to a salesperson who is responsible for the policy. However, after the salesperson leaves the company, the policies of the users under the salesperson's name become orphan policies, making it necessary to reassign the corresponding salesperson to each orphan policy. However, when assigning salespersons to orphan policies, it is necessary to comprehensively consider the compatibility between the salesperson and the user corresponding to the policy. Therefore, how to improve the accuracy of salesperson matching for orphan policies is the current research focus.

[0003] In the existing technical solution, salesmen are manually assigned to orphan policies. However, this allocation method is affected by subjective factors and the principles of manual allocation are relatively one-sided, resulting in a poor user experience for the salesmen assigned to the users' orphan policies. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for intelligent matching of salesmen for orphan insurance policies in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a salesperson intelligent matching method for orphan insurance policies, comprising:

[0006] Obtain salesperson information of salespersons in each region, policy information of orphan policies in each region, user information corresponding to each orphan policy, and orphan policy matching logic in each region, and for each region, identify salesperson characteristics of each salesperson, policy characteristics of each orphan policy, and user characteristics corresponding to each orphan policy based on the salesperson information in the region, policy information in the region, and user information corresponding to the region;

[0007] Based on the orphan policy matching logic of the region, the orphan policy matching strategy of the region is identified, and based on the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the region;

[0008] Based on the salesperson characteristics of each of the salespersons, the policy characteristics of each of the orphan policies, and the user characteristics corresponding to each of the orphan policies, the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons for each salesperson in each salesperson recommendation list are matched through the orphan policy matching model corresponding to the region, and in response to the salesperson screening operation of the user corresponding to each of the orphan policies, the target salesperson corresponding to each of the orphan policies is screened in the salesperson recommendation list.

[0009] Optionally, the identifying, based on the salesperson information of the region, the policy information of the region, and the user information corresponding to the region, the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy includes:

[0010] Based on the information of each salesperson in the area, extract the salesperson feature information of each salesperson through a salesperson feature extraction strategy, and based on the feature type to which each salesperson feature information belongs, query the salesperson feature value corresponding to each salesperson feature information in a salesperson feature database;

[0011] The salesperson feature value of each feature type of each salesperson is used as the salesperson feature of each salesperson, and for each orphan policy in the area, the policy information of the orphan policy is split into the policy data of each policy identifier;

[0012] Based on the policy data of each of the policy identifiers, identifying each of the policy feature values ​​of the orphan policy through a policy feature matching strategy, and using the policy feature values ​​of each of the policy identifiers as policy features of the orphan policy;

[0013] Based on the user information of the orphan insurance policy, the key feature information of each user in the user information is extracted through a text extraction network, and the feature semantics corresponding to each user key feature information is identified through a semantic recognition network;

[0014] In the user database, the feature type corresponding to each feature semantics is queried, and the feature semantics of all feature types are used as the user features corresponding to the orphan insurance policy.

[0015] Optionally, the orphan policy matching logic based on the region and identifying the orphan policy matching strategy for the region include:

[0016] Based on the orphan policy matching logic, identifying orphan policy matching demand information corresponding to the orphan policy matching logic through a logic analysis network, and based on the orphan policy matching demand information, identifying each demand range of each orphan policy demand type in the region and each demand range of each salesperson demand type;

[0017] The demand ranges of each orphan policy demand type and the demand ranges of each salesperson demand type are used as orphan policy matching strategies for the region.

[0018] Optionally, the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region are used to train an initial orphan policy matching model to obtain an orphan policy matching model corresponding to the region, including:

[0019] Obtaining each initial historical orphan insurance policy matching record information of the region, and identifying the historical insurance policy information corresponding to each initial historical orphan insurance policy matching record information, and the historical salesperson information corresponding to each initial historical orphan insurance policy matching record information;

[0020] Based on each demand range of each orphan policy demand type, in each historical policy information, each target historical policy information of each orphan policy demand type is screened, and based on each demand range of each salesperson demand type, in each historical salesperson information, each target historical salesperson information of each salesperson demand type is screened;

[0021] Based on the target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, the target historical salesperson information of each salesperson demand type, and the first historical policy information corresponding to each target historical salesperson information, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the area.

[0022] Optionally, before matching the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list by using the orphan policy matching model corresponding to the region based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, the method further includes:

[0023] Based on the salesperson characteristics of each salesperson and the user characteristics corresponding to each orphan policy, the salesperson advantage identification strategy is used to identify the advantageous sales characteristics of each salesperson for each orphan policy;

[0024] Based on the policy characteristics of each orphan policy, the advantage characteristics of each policy advantage type of each orphan policy are identified through a policy advantage identification strategy.

[0025] Optionally, the matching of the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list by the orphan policy matching model corresponding to the region based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy includes:

[0026] For each orphan policy, based on the advantage characteristics of each policy advantage type of the orphan policy and the advantage sales characteristics of each salesperson for each orphan policy, the orphan policy matching model corresponding to the region is used to generate each recommended salesperson corresponding to each orphan policy;

[0027] Based on the advantageous sales characteristics of each recommended salesperson for the orphan insurance policy and the advantageous characteristics of the policy advantage type, the advantage matching degree between each recommended salesperson and the orphan insurance policy is evaluated through an advantage evaluation strategy, and each recommended salesperson is sorted in descending order of advantage matching degree to obtain a recommended list of salespersons corresponding to the orphan insurance policy;

[0028] Based on the advantageous sales features of each recommended salesperson for the orphan insurance policy, a salesperson recommendation reason for each recommended salesperson is generated through a text compilation network.

[0029] In a second aspect, the present application also provides an intelligent matching device for salespersons of orphan insurance policies, comprising:

[0030] An acquisition module, used to acquire salesperson information of salespersons in each region, policy information of orphan policies in each region, user information corresponding to each orphan policy, and orphan policy matching logic in each region, and for each region, based on the salesperson information in the region, policy information in the region, and user information corresponding to the region, identify salesperson characteristics of each salesperson, policy characteristics of each orphan policy, and user characteristics corresponding to each orphan policy;

[0031] A training module, for identifying an orphan policy matching strategy for the region based on the orphan policy matching logic for the region, and training an initial orphan policy matching model based on the orphan policy matching strategy for the region and historical orphan policy matching record information for the region, to obtain an orphan policy matching model corresponding to the region;

[0032] A screening module is used to match the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons for each salesperson in each salesperson recommendation list based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy through an orphan policy matching model corresponding to the region, and in response to the screening operation of the user corresponding to each orphan policy on the salesperson, screen the target salesperson corresponding to each orphan policy in the salesperson recommendation list.

[0033] Optionally, the acquisition module is specifically used to:

[0034] Based on the information of each salesperson in the area, extract the salesperson feature information of each salesperson through a salesperson feature extraction strategy, and based on the feature type to which each salesperson feature information belongs, query the salesperson feature value corresponding to each salesperson feature information in a salesperson feature database;

[0035] The salesperson feature value of each feature type of each salesperson is used as the salesperson feature of each salesperson, and for each orphan policy in the area, the policy information of the orphan policy is split into the policy data of each policy identifier;

[0036] Based on the policy data of each of the policy identifiers, identifying each of the policy feature values ​​of the orphan policy through a policy feature matching strategy, and using the policy feature values ​​of each of the policy identifiers as policy features of the orphan policy;

[0037] Based on the user information of the orphan insurance policy, the key feature information of each user in the user information is extracted through a text extraction network, and the feature semantics corresponding to each user key feature information is identified through a semantic recognition network;

[0038] In the user database, the feature type corresponding to each feature semantics is queried, and the feature semantics of all feature types are used as the user features corresponding to the orphan insurance policy.

[0039] Optionally, the training module is specifically used for:

[0040] Based on the orphan policy matching logic, identifying orphan policy matching demand information corresponding to the orphan policy matching logic through a logic analysis network, and based on the orphan policy matching demand information, identifying each demand range of each orphan policy demand type in the region and each demand range of each salesperson demand type;

[0041] The demand ranges of each orphan policy demand type and the demand ranges of each salesperson demand type are used as orphan policy matching strategies for the region.

[0042] Optionally, the training module is specifically used for:

[0043] Obtaining each initial historical orphan insurance policy matching record information of the region, and identifying the historical insurance policy information corresponding to each initial historical orphan insurance policy matching record information, and the historical salesperson information corresponding to each initial historical orphan insurance policy matching record information;

[0044] Based on each demand range of each orphan policy demand type, in each historical policy information, each target historical policy information of each orphan policy demand type is screened, and based on each demand range of each salesperson demand type, in each historical salesperson information, each target historical salesperson information of each salesperson demand type is screened;

[0045] Based on the target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, the target historical salesperson information of each salesperson demand type, and the first historical policy information corresponding to each target historical salesperson information, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the area.

[0046] Optionally, the device further comprises:

[0047] A first identification module is used to identify the advantageous sales characteristics of each salesperson for each orphan insurance policy through a salesperson advantage identification strategy based on the salesperson characteristics of each salesperson and the user characteristics corresponding to each orphan insurance policy;

[0048] The second identification module is used to identify the advantage characteristics of each policy advantage type of each orphan policy based on the policy characteristics of each orphan policy through a policy advantage identification strategy.

[0049] Optionally, the screening module is specifically used to:

[0050] For each orphan policy, based on the advantage characteristics of each policy advantage type of the orphan policy and the advantage sales characteristics of each salesperson for each orphan policy, the orphan policy matching model corresponding to the region is used to generate each recommended salesperson corresponding to each orphan policy;

[0051] Based on the advantageous sales characteristics of each recommended salesperson for the orphan insurance policy and the advantageous characteristics of the policy advantage type, the advantage matching degree between each recommended salesperson and the orphan insurance policy is evaluated through an advantage evaluation strategy, and each recommended salesperson is sorted in descending order of advantage matching degree to obtain a recommended list of salespersons corresponding to the orphan insurance policy;

[0052] Based on the advantageous sales features of each recommended salesperson for the orphan insurance policy, a salesperson recommendation reason for each recommended salesperson is generated through a text compilation network.

[0053] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0055] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0056] The above-mentioned salesperson intelligent matching method, device and computer equipment for orphan insurance policies obtain the salesperson information of the salespersons in each area, the policy information of the orphan insurance policies in each area, the user information corresponding to each orphan insurance policy, and the orphan insurance policy matching logic in each area, and for each area, based on the salesperson information of the area, the policy information of the area, and the user information corresponding to the area, identify the salesperson characteristics of each salesperson, the policy characteristics of each orphan insurance policy, and the user characteristics corresponding to each orphan insurance policy; based on the orphan insurance policy matching logic of the area, identify the orphan insurance policy matching strategy of the area, and based on the orphan insurance policy matching logic of the area The orphan policy matching strategy of the domain and the historical orphan policy matching record information of the region are used to train the initial orphan policy matching model to obtain the orphan policy matching model corresponding to the region; based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list are matched through the orphan policy matching model corresponding to the region, and in response to the screening operation of the user corresponding to each orphan policy on the salesperson, the target salesperson corresponding to each orphan policy is screened in the salesperson recommendation list. This solution analyzes the characteristics of orphan policies, salespersons, and users corresponding to the orphan policies in different regions, and then optimizes and trains orphan policy matching models in different regions according to the orphan policy matching logic of each region, thereby improving the recommendation accuracy of orphan policies in different regions. Then, this solution generates a salesperson recommendation list of orphan policies in different regions and the recommendation reasons of each salesperson according to the orphan policy matching model corresponding to each region through user characteristics, salesperson characteristics, and policy characteristics, thereby improving the orphan policy users' understanding of each recommender in the salesperson recommendation list and efficiently identifying the reasons for the adaptation of each recommender to the orphan policy. Finally, the user screening is performed in response to the user to whom the orphan policy belongs, and the target salesperson corresponding to different orphan policies is obtained. This ensures that the salesperson of the selected orphan policy not only meets the user recognition of the user to whom the orphan policy belongs, but also ensures the accuracy of the salesperson assigned to the unchanged policy, thereby comprehensively improving the user experience of the salesperson assigned to the user's orphan policy. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A flowchart of a salesperson intelligent matching method for orphan insurance policies in one embodiment;

[0059] Figure 2 It is a system architecture diagram of a feature system in an embodiment;

[0060] Figure 3 A flowchart of an example of intelligent matching of salespersons for orphan insurance policies in one embodiment;

[0061] Figure 4 It is a structural block diagram of a salesperson intelligent matching device for orphan insurance policies in one embodiment;

[0062] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] The method for intelligent matching of salespersons for orphan insurance policies provided in the embodiment of the present application can be applied in the application environment of intelligent matching of salespersons for orphan insurance policies. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, mid-size computers, etc. The terminal performs feature analysis on orphan insurance policies, salespersons, and users corresponding to the orphan insurance policies in different regions, and then optimizes and trains orphan insurance policy matching models in different regions according to the orphan insurance policy matching logic of each region, thereby improving the accuracy of recommendation for orphan insurance policies in different regions. Then, this solution generates a salesperson recommendation list of orphan policies in different regions and the recommendation reasons of each salesperson according to the orphan policy matching model corresponding to each region through user characteristics, salesperson characteristics, and policy characteristics, thereby improving the orphan policy users' understanding of each recommender in the salesperson recommendation list and efficiently identifying the reasons for the adaptation of each recommender to the orphan policy. Finally, the user screening is performed in response to the user to whom the orphan policy belongs, and the target salesperson corresponding to different orphan policies is obtained. This ensures that the salesperson of the selected orphan policy not only meets the user recognition of the user to whom the orphan policy belongs, but also ensures the accuracy of the salesperson assigned to the unchanged policy, thereby comprehensively improving the user experience of the salesperson assigned to the user's orphan policy.

[0065] In an exemplary embodiment, Figure 1 As shown, a salesperson intelligent matching method for orphan insurance policies is provided, and the method is applied to a terminal as an example for explanation, including the following steps S101 to S103. Among them:

[0066] Step S101, obtain the salesperson information of the salespersons in each area, the policy information of the orphan policies in each area, the user information corresponding to each orphan policy, and the orphan policy matching logic in each area, and for each area, identify the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy based on the salesperson information of the area, the policy information of the area, and the user information corresponding to the area.

[0067] In this embodiment, the terminal obtains the salesperson information of the salesperson in each region, the policy information of the orphan insurance policy in each region, and the user information corresponding to each orphan insurance policy, wherein each region may be each province, each sub-district, or each artificially divided region. The salesperson information of the salesperson is the information stored in the salesperson database, therefore, the terminal directly performs information query in the salesperson database of each region, and can obtain the salesperson information of the salesperson, and the orphan insurance policy information of each region is the policy sales record information of each orphan insurance policy recorded in the insurance policy database, then the terminal performs information query from each insurance policy database, and can obtain the insurance policy information of each orphan insurance policy. The user information corresponding to each orphan insurance policy may have incomplete user information in the database, or the user information change cannot be adjusted in time, therefore, the terminal sends a user information collection template to the user end corresponding to each orphan insurance policy, wherein the user information collection template is a form of user information that the user needs to fill in, and / or the profile information of the user information that the user needs to fill in, and the user can obtain the corresponding user information of each orphan insurance policy by checking in the form, and / or the user feedback a text containing user information. Then, for each region, the terminal identifies the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy based on the salesperson information of the region, the policy information of the region, and the user information corresponding to the region. Figure 2As shown, the salesperson characteristics (AMIS) include but are not limited to salesperson ID, age, gender, education, marital status, political affiliation, current rank, contract duration, tenure, number of visits, etc., where the characteristic meaning of each feature is as follows: salesperson ID, salesperson ID is the unique identifier of the salesperson in the salesperson management system of the individual insurance channel; age, salespeople of different age groups are good at operating different groups of users; gender, salespeople of different genders are good at operating different groups of users; education, salespeople of different education levels have great differences in their ability to operate users; marital status, marital status, number of children, etc., affect the salesperson's ability to operate users; political affiliation, salespeople of different political affiliations have great differences in their ability to operate users; current rank, reflects the salesperson's marketing ability; contract duration, reflects the salesperson's industry experience; tenure, reflects the salesperson's work experience; number of visits, reflects the salesperson's attitude towards operating users. User characteristics (CMDS) include but are not limited to user ID, age, gender, user rating, income level, marital status, occupation category, due diligence mark, business type, etc. Among them, the characteristic meaning of each feature is: user ID, user ID is the unique identifier of the user in the user master data management system; age, users of different age groups have different needs for insurance products; gender, users of different genders have different needs for insurance products; user rating value, the rating value can well reflect the user's purchasing power and loyalty; income level, the user's ability to pay determines the type and amount of insurance products they can buy; marital status, marital status, number of children, etc., affect the demand for family insurance; occupational category, the user's occupational type, reflects the user's job stability; due diligence identification, whether the user has completed due diligence, reflects the user's risk level of purchasing products; business type, the business category of the user's source. The policy characteristics (DWD public service data) include but are not limited to the total / average premium of the previous year, long / short insurance user identification, new / old user identification, and valid policies / fees. The meaning of each feature is as follows: the total / average premium of the previous year reflects the salesperson's operating ability and the user's consumption level in the previous year; the long / short insurance user identification reflects the user's demand for long-term / short-term insurance products; the new / old user identification reflects the user's demand for repurchasing insurance products; the valid insurance policy / premium reflects the number of valid insurance policies held by the user, reflecting the user's protection level. The specific identification process will be explained in detail later.

[0068] Step S102, based on the orphan policy matching logic of the region, identify the orphan policy matching strategy of the region, and based on the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region, train the initial orphan policy matching model to obtain the orphan policy matching model corresponding to the region.

[0069] In this embodiment, the terminal identifies the orphan policy matching strategy of the region based on the orphan policy matching logic of the region, and trains the initial orphan policy matching model based on the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region to obtain the orphan policy matching model corresponding to the region. Among them, the orphan policy matching logic of different regions is different, because the policy data of different regions have different characteristics. For example, Province A adopts a higher circulation number for orphan policy allocation, while Province B has many salesmen and users, so the circulation number is small and the circulation efficiency is low. The terminal summarizes and divides the orphan policy matching logic of each region to obtain the demand ranges of each orphan policy demand type and the demand ranges of each salesperson demand type. Among them, the demand range is the range of orphan policies of different policy types obtained after classifying each orphan policy, and each salesperson demand type is the type of each salesperson who allocates orphan policies. Specifically, the identification process of the policy matching strategy will be described in detail later. The initial orphan policy matching model is an Xgboost model. The terminal trains the initial orphan policy matching model through the policy matching strategies of different regions and the historical orphan policy matching record information, thereby ensuring that the obtained initial orphan policy matching model can adapt to the orphan policy matching logic of different regions, thereby improving the accuracy and rationality of orphan policy matching in different regions.

[0070] Step S103, based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons for each salesperson in each salesperson recommendation list are matched through the orphan policy matching model corresponding to the region, and in response to the salesperson screening operation of the user corresponding to each orphan policy, the target salesperson corresponding to each orphan policy is screened in the salesperson recommendation list.

[0071] In this embodiment, the terminal matches the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy through the orphan policy matching model corresponding to the region. The specific matching process will be described in detail later. Then, the terminal sends the salesperson recommendation list of each orphan policy and the recommendation reasons of each salesperson to the user terminal of the user corresponding to each orphan policy, and after each user has screened the salesperson, the terminal responds to the screening operation of the user corresponding to each orphan policy on the salesperson, and screens the target salesperson corresponding to each orphan policy in the salesperson recommendation list.

[0072] Based on the above scheme, by analyzing the characteristics of orphan insurance policies, salespersons, and users corresponding to the orphan insurance policies in different regions, and then optimizing and training the orphan insurance policy matching models in different regions according to the orphan insurance policy matching logic of each region, the accuracy of recommendation for orphan insurance policies in different regions is improved. Then, this scheme generates a salesperson recommendation list of orphan insurance policies in different regions and the recommendation reasons of each salesperson according to the orphan insurance policy matching model corresponding to each region through user characteristics, salesperson characteristics, and insurance policy characteristics, thereby improving the orphan insurance policy users' understanding of each recommender in the salesperson recommendation list, and efficiently identifying the reasons for the adaptation of each recommender to the orphan insurance policy. Finally, in response to the user to whom the orphan insurance policy belongs, user screening is performed to obtain the target salesperson corresponding to different orphan insurance policies. This ensures that the salesperson of the selected orphan insurance policy not only meets the user recognition of the user to whom the orphan insurance policy belongs, but also ensures the accuracy of the salesperson assigned to the unchanged insurance policy, thereby comprehensively improving the user experience of the salesperson assigned to the user's orphan insurance policy.

[0073] Optionally, based on the salesperson information of the region, the insurance policy information of the region, and the user information corresponding to the region, the salesperson characteristics of each salesperson, the policy characteristics of each orphan insurance policy, and the user characteristics corresponding to each orphan insurance policy are identified, including: based on the salesperson information of the region, extracting the salesperson characteristic information of each salesperson through a salesperson characteristic extraction strategy, and based on the characteristic type of each salesperson characteristic information, querying the salesperson characteristic value corresponding to each salesperson characteristic information in the salesperson characteristic database; using the salesperson characteristic value of each characteristic type of each salesperson as the salesperson characteristic of each salesperson, and for each orphan insurance policy in the region, Insurance policy, split the policy information of the orphan policy into the policy data of each policy identifier; based on the policy data of each policy identifier, identify the policy feature values ​​of the orphan policy through the policy feature matching strategy, and use the policy feature values ​​of each policy identifier as the policy features of the orphan policy; based on the user information of the orphan policy, extract the key feature information of each user in the user information through the text extraction network, and identify the feature semantics corresponding to the key feature information of each user through the semantic recognition network; in the user database, query the feature type corresponding to each feature semantic, and use the feature semantics of all feature types as the user features corresponding to the orphan policy.

[0074] In this embodiment, the terminal extracts the salesperson feature information of each salesperson based on the salesperson information of the area through the salesperson feature extraction strategy, and queries the salesperson feature value corresponding to each salesperson feature information in the salesperson feature database based on the feature type to which each salesperson feature information belongs. Among them, the salesperson feature extraction strategy is to query the content corresponding to each feature information identification information in the salesperson information database based on each feature information identification information to obtain the salesperson feature information of each salesperson. The salesperson feature database includes the correspondence between the feature data and the feature value of each salesperson feature information, and the terminal identifies the salesperson feature value corresponding to each salesperson feature information based on the correspondence. Finally, the terminal uses the salesperson feature value of each feature type of each salesperson as the salesperson feature of each salesperson.

[0075] For each orphan policy in the region, the terminal splits the policy information of the orphan policy into the policy data of each policy identifier. Among them, the policy information database includes the policy data of each policy in different forms. Then, based on the policy identifiers of the orphan policies, the terminal directly queries the policy data of each policy identifier in the policy information database. The policy feature matching strategy includes the correspondence between different policy feature values ​​and policy data ranges, and the terminal identifies each policy feature value of each orphan policy based on the policy data range to which the policy data of each orphan policy belongs. Finally, the terminal uses the policy feature value of each policy identifier as the policy feature of the orphan policy.

[0076] Based on the user information of the orphan insurance policy, the terminal extracts the key feature information of each user in the user information through the text extraction network, and identifies the feature semantics corresponding to each user's key feature information through the semantic recognition network. Among them, the text extraction network and the semantic recognition network are both large language models. Finally, the terminal queries the feature type corresponding to each feature semantic in the user database, and uses the feature semantics of all feature types as the user features corresponding to the orphan insurance policy. Among them, each feature type includes but is not limited to age type, gender type, user rating value type, income level type, marital status type, occupation category type, due diligence identification type, and business type.

[0077] Based on the above solution, different feature recognition methods are used to identify salesperson features, policy features, and user features, respectively, thereby improving the accuracy and comprehensiveness of identifying each feature.

[0078] Optionally, based on the orphan policy matching logic of the region, an orphan policy matching strategy of the region is identified, including: based on the orphan policy matching logic, identifying orphan policy matching demand information corresponding to the orphan policy matching logic through a logic analysis network, and based on the orphan policy matching demand information, identifying each demand range of each orphan policy demand type in the region and each demand range of each salesperson demand type; using each demand range of each orphan policy demand type and each demand range of each salesperson demand type as the orphan policy matching strategy of the region.

[0079] In this embodiment, the terminal identifies the orphan policy matching requirement information corresponding to the orphan policy matching logic through a logic analysis network based on the orphan policy matching logic, wherein the logic analysis network is a neural network based on reinforcement learning.

[0080] Then, based on the orphan policy matching demand information, the terminal identifies the demand ranges of each orphan policy demand type in the region and the demand ranges of each salesperson demand type. The demand ranges of each orphan policy demand type are the characteristic data ranges of each policy feature of different orphan policy types, and the demand ranges of each salesperson demand type are the characteristic data ranges of different salesperson levels of the salespersons that can be transferred in the region. The salesperson level is the data range of each salesperson information preset by the staff in the salesperson database.

[0081] Finally, the terminal uses the demand ranges of each orphan policy demand type and the demand ranges of each salesperson demand type as the orphan policy matching strategy for the region.

[0082] Based on the above solution, by splitting the orphan policy demand type and the salesperson demand type, the orphan policy matching strategy for each region is identified separately, thereby improving the recognition accuracy and efficiency of the orphan policy matching strategy.

[0083] Optionally, based on the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the region, including: obtaining each initial historical orphan policy matching record information of the region, and identifying the historical policy information corresponding to each initial historical orphan policy matching record information, and the historical salesperson information corresponding to each initial historical orphan policy matching record information; based on each demand range of each orphan policy demand type, in each historical policy information, screening each target historical policy information of each orphan policy demand type, and based on each demand range of each salesperson demand type, in each historical salesperson information, screening each target historical salesperson information of each salesperson demand type; based on each target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, each target historical salesperson information of each salesperson demand type, and the first historical policy information corresponding to each target historical salesperson information, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the region.

[0084] In this embodiment, the terminal obtains each initial historical orphan policy matching record information of the region, and identifies the historical policy information corresponding to each initial historical orphan policy matching record information, and the historical salesperson information corresponding to each initial historical orphan policy matching record information. Then, based on each demand range of each orphan policy demand type, the terminal screens each target historical policy information of each orphan policy demand type in each historical policy information, and based on each demand range of each salesperson demand type, screens each target historical salesperson information of each salesperson demand type in each historical salesperson information. Then, based on each target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, each target historical salesperson information of each salesperson demand type (i.e., each salesperson level), and the first historical policy information corresponding to each target historical salesperson information, the terminal trains the initial orphan policy matching model to obtain the orphan policy matching model corresponding to the region.

[0085] Based on the above scheme, the initial orphan policy matching model is trained by type through historical policy information and salesperson information of different orphan policy demand types and salesperson demand types. This can ensure that the obtained orphan policy matching model can adapt to the orphan policy adaptation logic of the region, and can also ensure the adaptation accuracy of different types of orphan policy demand types and different types of salesperson demand types.

[0086] Optionally, based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, before matching the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list through the orphan policy matching model corresponding to the region, it also includes: based on the salesperson characteristics of each salesperson and the user characteristics corresponding to each orphan policy, identifying the advantageous sales characteristics of each salesperson for each orphan policy through the salesperson advantage identification strategy; based on the policy characteristics of each orphan policy, identifying the advantageous characteristics of each policy advantage type of each orphan policy through the policy advantage identification strategy.

[0087] In this embodiment, the terminal identifies the advantageous sales features of each salesperson for each orphan insurance policy through the salesperson advantage identification strategy based on the salesperson features of each salesperson and the user features corresponding to each orphan insurance policy. Among them, the salesperson advantage identification strategy is a matching degree identification strategy between each salesperson feature and the user feature. Based on the matching degree identification strategy between each salesperson feature and the user feature, the terminal calculates the matching degree between each salesperson feature and the user feature, and selects the salesperson features corresponding to the matching degree greater than the matching degree threshold as the advantageous sales features of the salesperson for the orphan insurance policy.

[0088] Then, based on the policy features of each orphan policy, the terminal identifies the advantageous features of each policy advantage type of each orphan policy through a policy advantage identification strategy. Among them, the policy advantage identification strategy includes the policy feature value range corresponding to each feature advantage of each policy identifier. For each orphan policy, the terminal uses the feature advantage corresponding to the policy feature value range to which the policy feature value of each policy identifier belongs as the feature advantage of each policy identifier of the orphan policy. Finally, the terminal selects the policy identifier to which the feature advantage is greater than the feature advantage threshold preset in the terminal as the advantageous features of each policy advantage type of the orphan policy. Among them, each policy identifier corresponds to a policy feature type, and the terminal uses each policy feature type corresponding to the selected policy identifier as the policy advantage type.

[0089] Based on the above scheme, through the salesperson advantage identification strategy and the policy advantage identification strategy, the advantageous sales characteristics of each salesperson for each orphan policy and the advantageous characteristics of each policy advantage type of each orphan policy are identified, thereby improving the sales characteristics of the salesperson and the policy feature types, thereby limiting the range of consideration parameters for redistributing the salesperson for each orphan policy, and improving the screening efficiency and accuracy of the salesperson.

[0090] Optionally, based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, the orphan policy matching model corresponding to the region is used to match the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list, including: for each orphan policy, based on the advantage characteristics of each policy advantage type of the orphan policy and the advantageous sales characteristics of each salesperson for each orphan policy, the orphan policy matching model corresponding to the region is used to generate each recommended salesperson corresponding to each orphan policy; based on the advantageous sales characteristics of each recommended salesperson for the orphan policy and the advantageous characteristics of the policy advantage type, the advantage matching degree of each recommended salesperson with the orphan policy is evaluated through an advantage evaluation strategy, and each recommended salesperson is sorted in order of advantage matching degree from large to small to obtain a salesperson recommendation list corresponding to the orphan policy; based on the advantageous sales characteristics of each recommended salesperson for the orphan policy, the salesperson recommendation reason of each recommended salesperson is generated through a text compilation network.

[0091] In this embodiment, the terminal generates recommended salespersons corresponding to each orphan policy for each orphan policy based on the advantage characteristics of each policy advantage type of the orphan policy and the advantageous sales characteristics of each salesperson for each orphan policy through the orphan policy matching model corresponding to the region.

[0092] Specifically, when making predictions, the basic label table is first associated with the salesperson and user ID. After obtaining the prediction results, the model asynchronously calls the lonely system to return the results, and recommends the top K (K<=5) salespersons and the reasons for recommending each salesperson for each user for use by the lonely system in decision-making.

[0093] After obtaining the final recommendation result, strategy recommendation can also be performed. Since the number of users that each salesperson can assign in one allocation is limited, a linear programming algorithm is used to ensure that the total number of users assigned to each salesperson in one allocation is less than or equal to the maximum number of users that can be assigned. At the same time, the sum of the predicted probabilities of the salespersons recommended in the result of one allocation is maximized to obtain a better solution for one allocation, ensuring that the salesperson assigned to each user can be assigned at the time of allocation.

[0094] represents the recommendation probability of each salesperson, Indicates whether to allocate the i-th customer and the j-th salesperson. It only has the values ​​0 and 1. Representatives make allocations, represents no allocation, m represents the total number of users, n represents the number of salespeople, Indicates the maximum number of users that can be assigned to each salesperson.

[0095]

[0096]

[0097]

[0098]

[0099] Among them, the recommendation reasons of each salesperson are described by their most relevant characteristics, including similar age, long tenure, high rank, high frequency of visiting users in the previous year, and high premiums in the previous year.

[0100] Then, based on the advantageous sales features of each recommended salesperson for the orphan insurance policy and the advantageous features of the policy advantage type, the terminal evaluates the advantageous matching degree of each recommended salesperson with the orphan insurance policy through the advantage evaluation strategy, and sorts each recommended salesperson in the order of advantageous matching degree from large to small, and obtains a recommended list of salespersons corresponding to the orphan insurance policy. Among them, the advantage evaluation strategy is an evaluation strategy for each advantageous feature, wherein the evaluation strategy includes the corresponding relationship between each advantageous matching degree and the characteristic range of the advantageous sales feature. The terminal identifies the characteristic value of each recommended salesperson for the advantageous sales feature of the orphan insurance policy, and identifies the characteristic range corresponding to each advantageous sales feature. Finally, the terminal uses the average value of the advantageous matching degree corresponding to the characteristic range corresponding to each advantageous sales feature as the advantageous matching degree of each recommended salesperson with the orphan insurance policy, and then sorts them in the order of advantageous matching degree from large to small, and obtains a recommended list of salespersons corresponding to the orphan insurance policy.

[0101] Finally, the terminal generates the salesperson recommendation reason for each recommended salesperson based on the advantageous sales features of each recommended salesperson for orphan insurance policies through the text compilation network. Among them, each advantageous sales feature corresponds to a feature introduction text, and the terminal inputs each feature introduction text into the artificial intelligence recommendation network (i.e., the text compilation network) to obtain the salesperson recommendation reason for each recommended salesperson. Among them, the artificial intelligence recommendation network is the artificial neural network corresponding to the chatGPT model.

[0102] Based on the above scheme, salespersons are screened through the orphan policy matching model corresponding to the region, and then the salesperson recommendation reasons for each recommended salesperson are generated through an artificial neural network. This not only improves the user's understanding of the salesperson, but also ensures that the salesperson of the screened orphan policy not only meets the user recognition of the user to which the orphan policy belongs, but also ensures the accuracy of the salesperson assigned to the unchanged policy, thereby comprehensively improving the user experience of the salesperson assigned to the user's orphan policy.

[0103] This application also provides an example of intelligent matching of salespersons for orphan insurance policies, such as Figure 3 As shown, the specific processing process includes the following steps:

[0104] Step S301, obtaining the salesperson information of the salespersons in each region, the policy information of the orphan policies in each region, the user information corresponding to each orphan policy, and the orphan policy matching logic in each region.

[0105] Step S302, based on the salesperson information of each region, the salesperson feature information of each salesperson is extracted through the salesperson feature extraction strategy, and based on the feature type of each salesperson feature information, the salesperson feature value corresponding to each salesperson feature information is queried in the salesperson feature database.

[0106] Step S303, using the salesperson feature values ​​of each feature type of each salesperson as the salesperson feature of each salesperson, and for each orphan policy in the region, splitting the policy information of the orphan policy into policy data of each policy identifier.

[0107] Step S304, based on the policy data of each policy identifier, the policy feature values ​​of the orphan policy are identified through the policy feature matching strategy, and the policy feature values ​​of each policy identifier are used as the policy features of the orphan policy.

[0108] Step S305, based on the user information of the orphan insurance policy, the key feature information of each user in the user information is extracted through the text extraction network, and the feature semantics corresponding to each user key feature information is identified through the semantic recognition network.

[0109] Step S306, in the user database, query the feature type corresponding to each feature semantics, and use the feature semantics of all feature types as the user features corresponding to the orphan insurance policy.

[0110] Step S307, based on the orphan policy matching logic, identify the orphan policy matching demand information corresponding to the orphan policy matching logic through the logic analysis network, and based on the orphan policy matching demand information, identify the demand ranges of each orphan policy demand type in the region and the demand ranges of each salesperson demand type.

[0111] Step S308, using each demand range of each orphan insurance policy demand type and each demand range of each salesperson demand type as the orphan insurance policy matching strategy of the region.

[0112] Step S309, obtaining each initial historical orphan policy matching record information of the region, and identifying the historical policy information corresponding to each initial historical orphan policy matching record information, and the historical salesperson information corresponding to each initial historical orphan policy matching record information.

[0113] Step S310, based on the demand ranges of each orphan policy demand type, in each historical policy information, filter the target historical policy information of each orphan policy demand type, and based on the demand ranges of each salesperson demand type, in each historical salesperson information, filter the target historical salesperson information of each salesperson demand type.

[0114] Step S311, based on the target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, the target historical salesperson information of each salesperson demand type, and the first historical policy information corresponding to each target historical salesperson information, train the initial orphan policy matching model to obtain the orphan policy matching model corresponding to the region.

[0115] Step S312, based on the salesperson characteristics of each salesperson and the user characteristics corresponding to each orphan policy, the salesperson advantage identification strategy is used to identify the advantageous sales characteristics of each salesperson for each orphan policy.

[0116] Step S313, based on the policy characteristics of each orphan policy, the advantage characteristics of each policy advantage type of each orphan policy are identified through a policy advantage identification strategy.

[0117] Step S314, for each orphan policy, based on the advantage characteristics of each policy advantage type of the orphan policy and the advantageous sales characteristics of each salesperson for each orphan policy, the orphan policy matching model corresponding to the region is used to generate recommended salespersons corresponding to each orphan policy.

[0118] Step S315, based on the advantageous sales features of each recommended salesperson for the orphan policy and the advantageous features of the policy advantage type, the advantage evaluation strategy is used to evaluate the advantage matching degree between each recommended salesperson and the orphan policy, and each recommended salesperson is sorted in order of advantage matching degree from large to small to obtain a recommended list of salespersons corresponding to the orphan policy.

[0119] Step S316, based on the advantageous sales features of each recommended salesperson for orphan policies, generate salesperson recommendation reasons for each recommended salesperson through a text compilation network.

[0120] Step S317, in response to the salesperson screening operation performed by the user corresponding to each orphan insurance policy, the target salesperson corresponding to each orphan insurance policy is screened in the salesperson recommendation list.

[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0122] Based on the same inventive concept, the embodiment of the present application also provides an intelligent matching device for orphan insurance policies for implementing the intelligent matching method for orphan insurance policies involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the intelligent matching device for orphan insurance policies provided below can refer to the limitations of the intelligent matching method for orphan insurance policies above, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 4 As shown, a salesperson intelligent matching device for orphan insurance policies is provided, including: an acquisition module 410, a training module 420 and a screening module 430, wherein:

[0124] The acquisition module 410 is used to acquire the salesperson information of the salespersons in each region, the policy information of the orphan policies in each region, the user information corresponding to each orphan policy, and the orphan policy matching logic in each region, and for each region, based on the salesperson information in the region, the policy information in the region, and the user information corresponding to the region, identify the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy;

[0125] A training module 420 is used to identify the orphan policy matching strategy of the region based on the orphan policy matching logic of the region, and to train an initial orphan policy matching model based on the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region to obtain an orphan policy matching model corresponding to the region;

[0126] The screening module 430 is used to match the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons for each salesperson in each salesperson recommendation list based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy through the orphan policy matching model corresponding to the area, and in response to the screening operation of the user corresponding to each orphan policy on the salesperson, screen the target salesperson corresponding to each orphan policy in the salesperson recommendation list.

[0127] Optionally, the acquisition module 410 is specifically configured to:

[0128] Based on the information of each salesperson in the area, extract the salesperson feature information of each salesperson through a salesperson feature extraction strategy, and based on the feature type to which each salesperson feature information belongs, query the salesperson feature value corresponding to each salesperson feature information in a salesperson feature database;

[0129] The salesperson feature value of each feature type of each salesperson is used as the salesperson feature of each salesperson, and for each orphan policy in the area, the policy information of the orphan policy is split into the policy data of each policy identifier;

[0130] Based on the policy data of each of the policy identifiers, identifying each of the policy feature values ​​of the orphan policy through a policy feature matching strategy, and using the policy feature values ​​of each of the policy identifiers as policy features of the orphan policy;

[0131] Based on the user information of the orphan insurance policy, the key feature information of each user in the user information is extracted through a text extraction network, and the feature semantics corresponding to each user key feature information is identified through a semantic recognition network;

[0132] In the user database, the feature type corresponding to each feature semantics is queried, and the feature semantics of all feature types are used as the user features corresponding to the orphan insurance policy.

[0133] Optionally, the training module 420 is specifically used for:

[0134] Based on the orphan policy matching logic, identifying orphan policy matching demand information corresponding to the orphan policy matching logic through a logic analysis network, and based on the orphan policy matching demand information, identifying each demand range of each orphan policy demand type in the region and each demand range of each salesperson demand type;

[0135] The demand ranges of each orphan policy demand type and the demand ranges of each salesperson demand type are used as orphan policy matching strategies for the region.

[0136] Optionally, the training module 420 is specifically used for:

[0137] Obtaining each initial historical orphan insurance policy matching record information of the region, and identifying the historical insurance policy information corresponding to each initial historical orphan insurance policy matching record information, and the historical salesperson information corresponding to each initial historical orphan insurance policy matching record information;

[0138] Based on each demand range of each orphan policy demand type, in each historical policy information, each target historical policy information of each orphan policy demand type is screened, and based on each demand range of each salesperson demand type, in each historical salesperson information, each target historical salesperson information of each salesperson demand type is screened;

[0139] Based on the target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, the target historical salesperson information of each salesperson demand type, and the first historical policy information corresponding to each target historical salesperson information, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the area.

[0140] Optionally, the device further comprises:

[0141] A first identification module is used to identify the advantageous sales characteristics of each salesperson for each orphan insurance policy through a salesperson advantage identification strategy based on the salesperson characteristics of each salesperson and the user characteristics corresponding to each orphan insurance policy;

[0142] The second identification module is used to identify the advantage characteristics of each policy advantage type of each orphan policy based on the policy characteristics of each orphan policy through a policy advantage identification strategy.

[0143] Optionally, the screening module 430 is specifically used to:

[0144] For each orphan policy, based on the advantage characteristics of each policy advantage type of the orphan policy and the advantage sales characteristics of each salesperson for each orphan policy, the orphan policy matching model corresponding to the region is used to generate each recommended salesperson corresponding to each orphan policy;

[0145] Based on the advantageous sales characteristics of each recommended salesperson for the orphan insurance policy and the advantageous characteristics of the policy advantage type, the advantage matching degree between each recommended salesperson and the orphan insurance policy is evaluated through an advantage evaluation strategy, and each recommended salesperson is sorted in descending order of advantage matching degree to obtain a recommended list of salespersons corresponding to the orphan insurance policy;

[0146] Based on the advantageous sales features of each recommended salesperson for the orphan insurance policy, a salesperson recommendation reason for each recommended salesperson is generated through a text compilation network.

[0147] Each module in the above-mentioned salesperson intelligent matching device for orphan insurance policies can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0148] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a salesperson intelligent matching method for orphan insurance policies is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0149] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0150] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, steps of a method for intelligent matching of salespersons for orphan insurance policies are implemented.

[0151] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the salesperson intelligent matching method for orphan insurance policies are implemented.

[0152] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of a salesperson intelligent matching method for orphan insurance policies.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0155] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A salesperson intelligent matching method for orphan insurance policies, characterized in that: The method comprises: Obtain salesperson information of salespersons in each region, policy information of orphan policies in each region, user information corresponding to each orphan policy, and orphan policy matching logic in each region, and for each region, identify salesperson characteristics of each salesperson, policy characteristics of each orphan policy, and user characteristics corresponding to each orphan policy based on the salesperson information in the region, policy information in the region, and user information corresponding to the region; Based on the orphan policy matching logic of the region, the orphan policy matching strategy of the region is identified, and based on the orphan policy matching strategy of the region and the historical orphan policy matching record information of the region, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the region; Based on the salesperson characteristics of each of the salespersons, the policy characteristics of each of the orphan policies, and the user characteristics corresponding to each of the orphan policies, the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons for each salesperson in each salesperson recommendation list are matched through the orphan policy matching model corresponding to the region, and in response to the salesperson screening operation of the user corresponding to each of the orphan policies, the target salesperson corresponding to each of the orphan policies is screened in the salesperson recommendation list.

2. The method according to claim 1, characterized in that The identifying, based on the salesperson information of the region, the policy information of the region, and the user information corresponding to the region, the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, includes: Based on the information of each salesperson in the area, extract the salesperson feature information of each salesperson through a salesperson feature extraction strategy, and based on the feature type to which each salesperson feature information belongs, query the salesperson feature value corresponding to each salesperson feature information in a salesperson feature database; The salesperson feature value of each feature type of each salesperson is used as the salesperson feature of each salesperson, and for each orphan policy in the area, the policy information of the orphan policy is split into the policy data of each policy identifier; Based on the policy data of each of the policy identifiers, identifying each of the policy feature values ​​of the orphan policy through a policy feature matching strategy, and using the policy feature values ​​of each of the policy identifiers as policy features of the orphan policy; Based on the user information of the orphan insurance policy, the key feature information of each user in the user information is extracted through a text extraction network, and the feature semantics corresponding to each user key feature information is identified through a semantic recognition network; In the user database, the feature type corresponding to each feature semantics is queried, and the feature semantics of all feature types are used as the user features corresponding to the orphan insurance policy.

3. The method according to claim 1, characterized in that The orphan policy matching logic based on the region, identifying the orphan policy matching strategy of the region, includes: Based on the orphan policy matching logic, identifying orphan policy matching demand information corresponding to the orphan policy matching logic through a logic analysis network, and based on the orphan policy matching demand information, identifying each demand range of each orphan policy demand type in the region and each demand range of each salesperson demand type; The demand ranges of each orphan policy demand type and the demand ranges of each salesperson demand type are used as orphan policy matching strategies for the region.

4. The method according to claim 3, characterized in that The orphan insurance policy matching strategy based on the region and the historical orphan insurance policy matching record information of the region are used to train the initial orphan insurance policy matching model to obtain the orphan insurance policy matching model corresponding to the region, including: Obtaining each initial historical orphan insurance policy matching record information of the region, and identifying the historical insurance policy information corresponding to each initial historical orphan insurance policy matching record information, and the historical salesperson information corresponding to each initial historical orphan insurance policy matching record information; Based on each demand range of each orphan policy demand type, in each historical policy information, each target historical policy information of each orphan policy demand type is screened, and based on each demand range of each salesperson demand type, in each historical salesperson information, each target historical salesperson information of each salesperson demand type is screened; Based on the target historical policy information of each orphan policy demand type, the first historical salesperson information corresponding to each target historical policy information, the target historical salesperson information of each salesperson demand type, and the first historical policy information corresponding to each target historical salesperson information, an initial orphan policy matching model is trained to obtain an orphan policy matching model corresponding to the area.

5. The method according to claim 1, characterized in that Before matching the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list by using the orphan policy matching model corresponding to the region based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy, the method further includes: Based on the salesperson characteristics of each salesperson and the user characteristics corresponding to each orphan policy, the salesperson advantage identification strategy is used to identify the advantageous sales characteristics of each salesperson for each orphan policy; Based on the policy characteristics of each orphan policy, the advantage characteristics of each policy advantage type of each orphan policy are identified through a policy advantage identification strategy.

6. The method according to claim 5, characterized in that Based on the salesperson characteristics of each of the salespersons, the policy characteristics of each of the orphan policies, and the user characteristics corresponding to each of the orphan policies, the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons of each salesperson in each salesperson recommendation list are matched through the orphan policy matching model corresponding to the region, including: For each orphan policy, based on the advantage characteristics of each policy advantage type of the orphan policy and the advantage sales characteristics of each salesperson for each orphan policy, the orphan policy matching model corresponding to the region is used to generate each recommended salesperson corresponding to each orphan policy; Based on the advantageous sales characteristics of each recommended salesperson for the orphan insurance policy and the advantageous characteristics of the policy advantage type, the advantage matching degree between each recommended salesperson and the orphan insurance policy is evaluated through an advantage evaluation strategy, and each recommended salesperson is sorted in descending order of advantage matching degree to obtain a recommended list of salespersons corresponding to the orphan insurance policy; Based on the advantageous sales features of each recommended salesperson for the orphan insurance policy, a salesperson recommendation reason for each recommended salesperson is generated through a text compilation network.

7. An intelligent matching device for salespersons of orphan insurance policies, characterized in that: The device comprises: An acquisition module, used to acquire salesperson information of salespersons in each region, policy information of orphan policies in each region, user information corresponding to each orphan policy, and orphan policy matching logic in each region, and for each region, based on the salesperson information in the region, policy information in the region, and user information corresponding to the region, identify salesperson characteristics of each salesperson, policy characteristics of each orphan policy, and user characteristics corresponding to each orphan policy; A training module, for identifying an orphan policy matching strategy for the region based on the orphan policy matching logic for the region, and training an initial orphan policy matching model based on the orphan policy matching strategy for the region and historical orphan policy matching record information for the region, to obtain an orphan policy matching model corresponding to the region; A screening module is used to match the salesperson recommendation list corresponding to each orphan policy and the recommendation reasons for each salesperson in each salesperson recommendation list based on the salesperson characteristics of each salesperson, the policy characteristics of each orphan policy, and the user characteristics corresponding to each orphan policy through an orphan policy matching model corresponding to the region, and in response to the screening operation of the user corresponding to each orphan policy on the salesperson, screen the target salesperson corresponding to each orphan policy in the salesperson recommendation list.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images