User portrait generation method and device and related product

Abstract

The invention discloses a user portrait generation method and device and a related product. Performing retrieval processing on the received target name information of the target user in an information database through the portrait generation agent to obtain an information retrieval result; if the information retrieval result indicates that other user information related to the target name information does not exist in the information database, other guiding questions are generated through a portrait generation agent, the other guiding questions are used for guiding collection of the other user information, and the other user information comprises information of the user in the current stage; receiving user rest information fed back by the target user based on the rest guiding questions through the portrait generation agent; and if the received information category set corresponding to the rest information of the user satisfies a preset category set, generating a target user portrait corresponding to the target user based on the target name information and the rest information of the user through a portrait generation agent. Therefore, compared with a related technical scheme, the user portrait can be better generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of insurance, in particular to a user portrait generation method and device and related products. BACKGROUND

[0002] The user portrait in the related technical solution is usually obtained based on user historical data. As the insurance and financial industry develops rapidly, user demand is increasingly personalized. Therefore, when analyzing the real demand and potential intention of the user based on the user portrait, many limitations occur, such as deviation between the analyzed user demand and the actual user demand.

[0003] Therefore, how to better generate a user portrait is an important issue for those skilled in the art. SUMMARY

[0004] To better generate a user portrait, the present application provides a user portrait generation method and device and related products based on the above problems.

[0005] The embodiments of the present application disclose the following technical solutions:

[0006] The first aspect of the present application provides a user portrait generation method. The user portrait generation method comprises:

[0007] The portrait generation agent performs retrieval processing on the target name information of the target user received in the information database to obtain an information retrieval result, wherein the information database comprises user information corresponding to a plurality of users;

[0008] If the information retrieval result indicates that there is no user rest information related to the target name information in the information database, the portrait generation agent generates rest guiding questions, wherein the rest guiding questions are used to guide the collection of user rest information, and the user rest information comprises information of the user in the current period stage.

[0009] The portrait generation agent receives user rest information fed back by the target user based on the rest guiding questions;

[0010] If the information category set corresponding to the received user rest information satisfies a preset category set, the portrait generation agent generates a target user portrait corresponding to the target user based on the target name information and the user rest information, wherein the target user portrait indicates an insurance service to be provided to the target user, and one information category corresponds to one preset category.

[0011] In an implementable embodiment, the remaining guiding questions include a first guiding question, a second guiding question, and a third guiding question, wherein the first guiding question indicates guiding collection of user family information, the second guiding question indicates guiding collection of user occupation information, and the third guiding question indicates guiding collection of user existing insurance products.

[0012] The receiving, by the portrait generation agent, of the user remaining information fed back by the target user based on the remaining guiding questions includes:

[0013] The receiving, by the portrait generation agent, of the user family information fed back by the target user based on the first guiding question;

[0014] The receiving, by the portrait generation agent, of the user occupation information fed back by the target user based on the second guiding question;

[0015] The receiving, by the portrait generation agent, of the user existing insurance products fed back by the target user based on the third guiding question.

[0016] In an implementable embodiment, before the generating, by the portrait generation agent, of the target user portrait corresponding to the target user based on the target name information and the user remaining information, the method further includes:

[0017] Obtaining a first generation prompt and a second generation prompt, wherein the first generation prompt indicates analysis of the user family information and the user occupation information, and the second generation prompt indicates analysis of the user existing insurance products;

[0018] The generating, by the portrait generation agent, of the target user portrait corresponding to the target user based on the target name information and the user remaining information includes:

[0019] The generating, by the portrait generation agent, of the target user portrait corresponding to the target user based on the first generation prompt and the second generation prompt includes:

[0020] In an implementable embodiment, the generating, by the portrait generation agent, of the target user portrait corresponding to the target user based on the first generation prompt and the second generation prompt includes:

[0021] The portrait generation agent analyzes and processes the user family information and the user occupation information based on the first generation prompt word, to obtain a life cycle stage and a user value level corresponding to the target user;

[0022] The portrait generation agent analyzes and processes the existing insurance product of the user based on the second generation prompt word, to obtain an insurance risk awareness level corresponding to the target user;

[0023] The portrait generation agent generates a target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level.

[0024] In an implementable embodiment, before the portrait generation agent generates a target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level, the method further includes:

[0025] Obtaining a product information library, wherein the product information library is used in combination with generating a user portrait;

[0026] The portrait generation agent generates a target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level, including:

[0027] The portrait generation agent generates an initial user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level;

[0028] The portrait generation agent generates a target user portrait corresponding to the target user based on the product information library and the initial user portrait.

[0029] In an implementable embodiment, the life cycle stage includes a first cycle stage, a second cycle stage, or a third cycle stage, the user value level includes a first value level, a second value level, or a third value level, and the insurance risk awareness level includes a first awareness level or a second awareness level, wherein the utilization rate of the first cycle stage is greater than that of the second cycle stage, the utilization rate of the second cycle stage is greater than that of the third cycle stage, the first value level is greater than the second value level, the second value level is greater than the third value level, and the first awareness level is greater than the second awareness level.

[0030] In an implementable embodiment, before the portrait generation agent performs retrieval processing on the target name information of the target user received in the information database to obtain an information retrieval result, the method further comprises:

[0031] generating, by the portrait generation agent, a target guiding question, wherein the target guiding question is used to guide collection of the target name information;

[0032] receiving, by the portrait generation agent, target name information fed back by the target user based on the target guiding question.

[0033] The second aspect of the present application provides a user portrait generation device. The user portrait generation device comprises:

[0034] a retrieval result obtaining unit configured to perform retrieval processing on target name information of a target user received in an information database by a portrait generation agent to obtain an information retrieval result, wherein the information database comprises user information corresponding to a plurality of users respectively;

[0035] a guiding question generating unit configured to generate, by the portrait generation agent, remaining guiding questions if the information retrieval result indicates that there is no remaining information of a user related to the target name information in the information database, wherein the remaining guiding questions are used to guide collection of user remaining information, and the user remaining information comprises information of a user in a current cycle stage;

[0036] a remaining information receiving unit configured to receive, by the portrait generation agent, user remaining information fed back by the target user based on the remaining guiding questions;

[0037] a user portrait generating unit configured to generate, by the portrait generation agent, a target user portrait corresponding to the target user based on the target name information and the user remaining information if an information category set corresponding to the received user remaining information satisfies a preset category set, wherein the target user portrait indicates an insurance service to be provided to the target user, and one information category corresponds to one preset category.

[0038] In an implementable embodiment, the remaining guiding questions comprise a first guiding question, a second guiding question and a third guiding question, wherein the first guiding question indicates guiding collection of user family information, the second guiding question indicates guiding collection of user occupation information, and the third guiding question indicates guiding collection of user existing insurance products.

[0039] The remaining information receiving unit is specifically configured to:

[0040] receiving, by the portrait generation agent, user family information fed back by the target user based on the first guiding question;

[0041] receiving, by the portrait generation agent, user career information fed back by the target user based on the second guiding question;

[0042] receiving, by the portrait generation agent, user existing insurance product fed back by the target user based on the third guiding question.

[0043] In an implementable embodiment, the apparatus further comprises:

[0044] a prompt word obtaining unit, configured to obtain a first generation prompt word and a second generation prompt word, wherein the first generation prompt word indicates to analyze the user family information and the user career information, and the second generation prompt word indicates to analyze the user existing insurance product;

[0045] the user portrait generation unit comprises:

[0046] a target user portrait generation unit, configured to analyze and process, by the portrait generation agent, the target name information, the user family information, the user career information and the user existing insurance product based on the first generation prompt word and the second generation prompt word, to generate a target user portrait corresponding to the target user.

[0047] In an implementable embodiment, the target user portrait generation unit comprises:

[0048] a life cycle stage obtaining unit, configured to analyze and process, by the portrait generation agent, the user family information and the user career information based on the first generation prompt word, to obtain a life cycle stage and a user value level corresponding to the target user;

[0049] a consciousness level obtaining unit, configured to analyze and process, by the portrait generation agent, the user existing insurance product based on the second generation prompt word, to obtain an insurance risk consciousness level corresponding to the target user;

[0050] a user portrait obtaining unit, configured to generate, by the portrait generation agent, a target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level and the insurance risk consciousness level.

[0051] In an implementable embodiment, the apparatus further comprises:

[0052] an information base obtaining unit, configured to obtain a product information base, wherein the product information base is used in combination with generating a user portrait;

[0053] The user portrait obtaining unit is specifically configured to:

[0054] The portrait generation agent generates an initial user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level.

[0055] The portrait generation agent generates a target user portrait corresponding to the target user based on the product information library and the initial user portrait.

[0056] In an implementable embodiment, the life cycle stage includes a first cycle stage, a second cycle stage, or a third cycle stage, the user value level includes a first value level, a second value level, or a third value level, and the insurance risk awareness level includes a first awareness level or a second awareness level, wherein the utilization rate of the first cycle stage is greater than that of the second cycle stage, the utilization rate of the second cycle stage is greater than that of the third cycle stage, the first value level is greater than the second value level, the second value level is greater than the third value level, and the first awareness level is greater than the second awareness level.

[0057] In an implementable embodiment, the device further includes:

[0058] A target guiding question generating unit is configured to generate a target guiding question by the portrait generation agent, wherein the target guiding question is used to guide the collection of target name information.

[0059] A target name information receiving unit is configured to receive target name information fed back by a target user based on the target guiding question by the portrait generation agent.

[0060] The third aspect of the present application provides a computer device. The computer device includes:

[0061] A memory having a computer program stored thereon;

[0062] A processor configured to execute the computer program in the memory to implement the steps of the user portrait generation method provided in the first aspect.

[0063] The fourth aspect of the present application provides a computer readable storage medium having a computer program stored thereon. The program, when executed by a processor, implements the steps of the user portrait generation method provided in the first aspect.

[0064] Compared with the prior art, the present application has the following beneficial effects:

[0065] In the present application, first, the portrait generation agent performs retrieval processing on the target name information of the target user received in the information database, obtains an information retrieval result, and thereafter, if the information retrieval result indicates that the remaining information of the user related to the target name information does not exist in the information database, generates the remaining guiding question through the portrait generation agent. Next, the portrait generation agent receives the user remaining information fed back by the target user based on the remaining guiding question, and finally, if the information category set corresponding to the received user remaining information satisfies the preset category set, the portrait generation agent generates the target user portrait corresponding to the target user based on the target name information and the user remaining information. It should be noted that the information database includes user information corresponding to a plurality of users respectively, the remaining guiding question is used to guide the collection of user remaining information, the user remaining information includes the information of the user in the current period stage, the target user portrait indicates the insurance service to be provided to the target user, and one information category corresponds to one preset category.

[0066] It can be seen that, in the present application, the user information of the target user in the current period stage is collected through the way of asking questions, that is, when the user remaining information of the target user does not exist in the information database, the remaining guiding question can be generated by the portrait generation agent to guide the collection of the user remaining information of the target user in the current period stage, so as to realize that the target user portrait can be constructed based on the real-time obtained user remaining information, and then the corresponding insurance service can be provided to the target user based on the generated target user portrait in the subsequent process. In this way, compared with the related technical solution, the user portrait can be better generated in the present application, so that the real demand and potential intention of the user at present can be better analyzed. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0068] Figure 1 A flowchart of a user portrait generation method provided by an embodiment of the present application;

[0069] Figure 2 A flowchart of generating a user portrait in a user portrait generation method provided by an embodiment of the present application;

[0070] Figure 3 A structural schematic diagram of a user portrait generation device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0071] As described above, the user portrait in the related technical solution is usually obtained based on user historical data. With the rapid development of the insurance and financial industry, user demand is increasingly personalized. Therefore, if the current real demand and potential intention of the user are analyzed based on the historical user portrait, many limitations will occur, such as deviation between the analyzed user demand and the actual user demand, thereby affecting the subsequent communication efficiency. Therefore, how to better generate a user portrait is an important issue for those skilled in the art.

[0072] In combination with the above problems, a solution is provided in the embodiments of the present application, and a user portrait generation method and device and related products are provided, aiming to better generate a user portrait. In the technical solution of the present application, first, the portrait generation agent is used to search and process the target name information of the target user received in the information database, to obtain an information search result. Then, if the information search result indicates that there is no user remaining information related to the target name information in the information database, the portrait generation agent generates remaining guiding questions. Next, the portrait generation agent receives the user remaining information fed back by the target user based on the remaining guiding questions. Finally, if the information category set corresponding to the received user remaining information satisfies the preset category set, the portrait generation agent generates a target user portrait corresponding to the target user based on the target name information and the user remaining information. The information database includes user information corresponding to a plurality of users, the remaining guiding questions are used to guide the collection of user remaining information, the user remaining information includes information of the user in the current cycle stage, the target user portrait indicates an insurance service to be provided to the target user, and one information category corresponds to one preset category.

[0073] It can be seen that, in the present application, the user information of the target user in the current cycle stage is collected through questioning, that is, when there is no user remaining information of the target user in the information database, the portrait generation agent generates remaining guiding questions to guide the collection of the user remaining information of the target user in the current cycle stage, so that the target user portrait can be constructed based on the real-time obtained user remaining information, and the corresponding insurance service can be provided to the target user based on the generated target user portrait in the subsequent process. Therefore, compared with the related technical solution, the present application can better generate a user portrait, so that the current real demand and potential intention of the user can be better analyzed.

[0074] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0075] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0076] Referring to Figure 1 , the figure is a flowchart of a user portrait generation method provided by an embodiment of the present application. As shown in Figure 1 , the user portrait generation method comprises the following steps:

[0077] S101: Retrieving the target name information of the target user received in the information database by the portrait generation agent to obtain an information retrieval result.

[0078] In this step, the portrait generation agent at least has the functions of information retrieval processing, generating guiding questions, receiving user information and generating user portraits, and the portrait generation agent is obtained based on fine-tuning of a large language model (LLM). The information database includes user information corresponding to a plurality of users, and the user information at least includes user name information.

[0079] It should be noted that before performing the operation of retrieving the target name information of the target user received in the information database by the portrait generation agent to obtain an information retrieval result, the portrait generation agent can also generate a target guiding question, wherein the target guiding question is used to guide the collection of the target name information, and thereafter the portrait generation agent can receive the target name information fed back by the target user based on the target guiding question. In this way, the present application improves the accurate collection of user information through the way of asking questions.

[0080] In some examples (it should be noted that the examples are only part of the examples), the process of collecting the target name information based on the target guiding question in the present application is embodied as follows:

[0081] Portrait generation agent: Hello. X is very happy to help you. In order to give you more suitable suggestions, I need to understand some basic information of the user. Please tell me: user name.

[0082] Dialoger: XYY.

[0083] It can be understood that in the above example, XYY represents the target name information, and the dialoger can be the target user, and the dialoger can also be a business personnel.

[0084] It should be noted that for each user, the user information corresponding to the user further includes user remaining information related to the user name information, and the user remaining information related to the user name information is divided into period stages. It can be understood that the user remaining information related to the user name information at this time includes user remaining information divided into a first period stage and user remaining information divided into a second period stage, wherein the first period stage is different from the second period stage. For example, the first period stage is from January 2, 2022 to January 1, 2023, and the second period stage is from January 2, 2023 to January 1, 2024.

[0085] In the present application, the portrait generation agent can be used to search the target name information of the target user received in the information database to determine whether there is user remaining information related to the target name information in the information database, and at the same time, to determine whether the first period stage or the second period stage corresponding to the user remaining information is in the current period stage, thereby generating an information search result.

[0086] S102: If the information search result indicates that there is no user remaining information related to the target name information in the information database, a remaining guiding question is generated by the portrait generation agent.

[0087] In this step, if the information search result indicates that there is no user remaining information related to the target name information in the information database, a remaining guiding question is generated by the portrait generation agent. Alternatively, if the information search result indicates that there is user remaining information related to the target name information in the information database, and the first period stage or the second period stage corresponding to the user remaining information is not in the current period stage, a remaining guiding question is generated by the portrait generation agent. For example, the current period stage is from January 2, 2024 to January 1, 2025, and at this time, the first period stage or the second period stage is in the current period stage.

[0088] Among them, the remaining guiding question is used to guide the collection of user remaining information, and the user remaining information at this time includes information of the user in the current period stage. It can be understood that in the present application, if there is no information of the user in the current period stage in the information database, the information of the user in the current period stage is collected through the remaining guiding question, which facilitates the generation of the user portrait subsequently.

[0089] In an implementable embodiment, if the information retrieval result indicates that there is user remaining information related to the target name information in the information database, and the first periodic stage or the second periodic stage corresponding to the user remaining information is the current periodic stage, the user remaining information corresponding to the first periodic stage or the second periodic stage in the current periodic stage is extracted from the information database. Then, the target user portrait corresponding to the target user can be generated by the portrait generation agent based on the target name information and the user remaining information.

[0090] It should be noted that the remaining guiding questions include the first guiding question, the second guiding question and the third guiding question, wherein the first guiding question indicates guiding to collect user family information, the second guiding question indicates guiding to collect user occupation information, and the third guiding question indicates guiding to collect user existing insurance products. It can be understood that the user family information includes target gender information, target age information and target family structure of the target user, and the user occupation information includes target occupation information and annual income range of the target user.

[0091] In some examples (it should be noted that the examples are only part of the examples), the process of collecting user remaining information based on the remaining guiding questions in the present application is embodied as follows:

[0092] Portrait generation agent: Hello. Little X is very happy to help you. In order to give you more suitable suggestions, I need to understand some basic information of the user. Can you tell me: user gender and user age, and family structure, such as marital status and child status?

[0093] Portrait generation agent: Thank you for your cooperation. What is your current occupation? What is your annual income range? Do you have existing insurance products, such as existing critical illness protection?

[0094] S103: receiving the user remaining information of the target user based on the remaining guiding questions by the portrait generation agent.

[0095] Specifically, in the present application, the user family information of the target user based on the first guiding question can be received by the portrait generation agent, the user occupation information of the target user based on the second guiding question can be received by the portrait generation agent, and the user existing insurance products of the target user based on the third guiding question can be received by the portrait generation agent. In this way, in the present application, the information of the user in the current periodic stage can be simply and accurately collected through multiple rounds of question asking, which improves the possibility of optimizing insurance services and more accurately grasps the actual needs of the user.

[0096] S104: If the information category set corresponding to the received user remaining information satisfies the preset category set, generate the target user portrait corresponding to the target user based on the target name information and the user remaining information by the portrait generation agent.

[0097] In the present application, since the received user remaining information includes different information categories, the different information categories can be compared with the preset categories in the preset category set at this time, wherein one information category corresponds to one preset category, and the preset category set includes gender category, age category, family structure category, occupation category, annual income category and existing guarantee category. That is, when the information category set corresponding to the received user remaining information satisfies the preset category set, it indicates that the required user remaining information is complete, and then the user portrait can be generated.

[0098] It should be noted that, before the operation of generating the target user portrait corresponding to the target user based on the target name information and the user remaining information by the portrait generation agent is performed, the first generation prompt word and the second generation prompt word can also be obtained, wherein the first generation prompt word indicates analyzing the user family information and the user occupation information, and the second generation prompt word indicates analyzing the user existing insurance product.

[0099] Specifically, in the present application, the portrait generation agent can be used to analyze and process the target name information, user family information, user occupation information and user existing insurance product from the two dimensions of the first generation prompt word and the second generation prompt word, based on the RFM model (customer value evaluation), the STP theory (market segmentation and positioning) and the user segmentation logic (data-driven clustering), to generate the target user portrait corresponding to the target user, wherein the target user portrait indicates the insurance service to be provided to the target user. In this way, in the present application, not only can the user portrait be constructed based on the real-time obtained user remaining information, but also the user portrait can prompt the insurance service to be provided to the target user, thereby improving the user experience.

[0100] Further, in the present application, the portrait generation agent can be used to analyze and process the user family information and the user occupation information based on the first generation prompt word, to obtain the life cycle stage and the user value level corresponding to the target user. That is, the user family information can be analyzed and processed to obtain the life cycle stage corresponding to the target user, wherein the life cycle stage includes a first cycle stage, a second cycle stage or a third cycle stage, the utilization rate of the first cycle stage is greater than that of the second cycle stage, and the utilization rate of the second cycle stage is greater than that of the third cycle stage. The first cycle stage includes an old age cycle stage, the second cycle stage includes a married cycle stage, and the third cycle stage includes an unmarried cycle stage.

[0101] The user professional information can be analyzed and processed to obtain a user value level corresponding to the target user, wherein the user value level includes a first value level, a second value level, or a third value level, the first value level is greater than the second value level, the second value level is greater than the third value level, the first value level includes a high value level, the second value level includes a potential value level, and the third value level includes a normal value level. In an implementable embodiment, in the present application, the user professional information can be analyzed and processed by the portrait generation agent based on the second generated prompt word and user interaction information to obtain a user value level corresponding to the target user. The user interaction information at least includes the interaction date, interaction item, and interaction times of the target user and the business personnel.

[0102] In an implementable embodiment, in the present application, the user family information, the user professional information, and the user existing insurance product can be analyzed and processed by the portrait generation agent based on the first generated prompt word and the second generated prompt word to obtain a life cycle stage corresponding to the target user. The life cycle stage includes a first cycle stage, a second cycle stage, or a third cycle stage, the utilization rate of the first cycle stage is greater than that of the second cycle stage, and the utilization rate of the second cycle stage is greater than that of the third cycle stage. The first cycle stage includes an active cycle stage (for example, the number of user existing insurance products is greater than a preset number, the user family information meets a preset requirement, and the user professional information meets a preset requirement), the second cycle stage includes a new customer cycle stage (for example, the number of user existing insurance products is 0, the user family information meets a preset requirement, and the user professional information meets a preset requirement), and the third cycle stage includes a loss cycle stage (for example, the number of user existing insurance products is 0, the user family information does not meet a preset requirement, or / and the user professional information does not meet a preset requirement).

[0103] Then, in the present application, the user existing insurance product can be analyzed and processed by the portrait generation agent based on the second generated prompt word to obtain an insurance risk awareness level corresponding to the target user, wherein the insurance risk awareness level includes a first awareness level or a second awareness level, the first awareness level is greater than the second awareness level, the first awareness level includes a high awareness level (for example, the number of user existing insurance products is greater than 0), and the second awareness level includes a low awareness level (for example, the number of user existing insurance products is 0).

[0104] In an implementable implementation, in the present application, the existing insurance product of the user can be analyzed and processed by the portrait generation agent based on the second generation prompt word to obtain the insurance protection gap or protection gap priority corresponding to the target user, wherein the insurance protection gap indicates the insurance product to be obtained by the user, and the insurance protection priority indicates the insurance product to be upgraded by the user in order, such as: the health risk is greater than the property risk.

[0105] Finally, the target user portrait corresponding to the target user can be generated by the portrait generation agent based on the target name information, the life cycle stage, the user value level and the insurance risk awareness level. In this way, in the present application, different information of the user can be obtained under the action of the generation prompt word, so as to accurately generate the user portrait. Compared with the related technical solution, the limitation problem of service optimization brought by the historical insurance product of the user can be fully utilized, so as to realize real-time perception of user demand and improve user experience.

[0106] It should be further pointed out that, before performing the operation of generating the target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level and the insurance risk awareness level by the portrait generation agent, the product information library can also be obtained, wherein the product information library is used in combination with the generation of the user portrait. The product information library includes a plurality of different types of insurance products and a plurality of different types of insurance products respectively corresponding to product information, and the product information indicates product characteristics and product target population. The product information library is regularly updated and maintained to ensure the accuracy and timeliness of the product information.

[0107] Specifically, in the present application, the initial user portrait corresponding to the target user can be generated by the portrait generation agent based on the target name information, the life cycle stage, the user value level and the insurance risk awareness level. Thereafter, the insurance product (insurance service) to be provided to the target user can be determined based on the product information library and the initial user portrait, i.e., the initial user portrait can be used to query and process in the product information library at this time, such as determining the insurance risk field not covered by the target user, so as to generate the target user portrait corresponding to the target user. In this way, in the present application, the user can be deeply analyzed by the machine learning algorithm to generate the user portrait, accurately identify the user demand and preference, realize personalized recommendation and intelligent decision, and improve the user touch efficiency and conversion effect. And compared with the related technical solution, the same product is recommended to the user only by the historical insurance product of the user, which is difficult to accurately match the actual protection demand of the user.

[0108] In some examples, in the present application, corresponding insurance services can be generated for users in different life cycle stages, such as pension planning insurance services, critical illness insurance services and life insurance services for users in the old age cycle stage, and children's education insurance services for users in the married cycle stage. It can be seen that in the present application, the real needs and potential needs of users can be analyzed according to the basic information of users (such as family information, etc.) and the knowledge of user protection gap (such as no insurance products), combined with machine learning algorithms, to better depict the user portrait and improve the user experience.

[0109] In an implementable embodiment, the core idea of the portrait generation agent in the present application is embodied as follows:

[0110] In combination with the RFM model (customer value evaluation), the STP theory (market segmentation and positioning), and the user segmentation logic (data-driven group division), the following two dimensions are cut in:

[0111] Basic information (i.e., the first generation prompt word)

[0112] Protection situation (i.e., the second generation prompt word)

[0113] Analysis target (i.e., the analysis target of generating the user portrait):

[0114] Identify the life cycle stage (first cycle stage / second cycle stage / third cycle stage)

[0115] Divide the value level (first value level / second value level / third value level)

[0116] Identify the protection gap priority (first awareness level / second awareness level, such as high health risk)

[0117] Among them, the RFM model can be embodied as: recent interaction score: 5 points (such as the target user interacting with the business personnel 6 days ago), interaction frequency score: 1 point (such as the target user interacting with the business personnel 2 times in the past 6 months), value contribution score: 5 points (such as the premium of the existing insurance product is greater than the preset premium), total score: 11 points, user value level: first value level. The STP theory and the user segmentation logic can be embodied as: demographics: middle-aged, business owner, core family; behavioral characteristics: prefer high-end insurance products, high offline activity participation; life cycle stage: second cycle stage; insurance risk awareness level: first awareness level.

[0118] In some examples, the target user portrait corresponding to the generated target user can be embodied as follows:

[0119] User information of the target user: target name information, user family information and user occupation information;

[0120] The target user's insurance coverage: The user already has insurance products;

[0121] Target user interaction information: user interaction date, user interaction item, and number of user interactions;

[0122] Target user value level: First value level;

[0123] Target user lifecycle stages: First stage;

[0124] Target users' insurance risk awareness level: Level 1;

[0125] Insurance services to be provided to target users: Insurance Service A;

[0126] Insurance product to be offered to target users: Insurance product A.

[0127] like Figure 2 As shown, Figure 2 This is a flowchart illustrating the user profile generation method provided in an embodiment of this application. Figure 2 The system first receives user information input by a profiling agent. This information supports voice input, which is then converted into text. The user information can include the user's name. If a user profile needs to be generated, the profiling agent searches the information database for the received user name information to obtain the retrieval results. If no user profile is needed, the process ends. If the retrieval results indicate that no other user information related to the user's name exists in the information database, the profiling agent generates additional guiding questions to receive the remaining user information until it is complete. This remaining information is then analyzed to generate the user profile. Alternatively, if the retrieval results indicate that other user information related to the user's name exists in the information database, but the received information is incomplete, the profiling agent generates additional guiding questions to receive the remaining user information until it is complete. This remaining information is then analyzed to generate the user profile. This generated user profile can be displayed on the front-end page or used in downstream applications to analyze insurance products to be recommended to users.

[0128] To sum up, in the embodiment, the user information of the target user in the current cycle stage is collected by means of questioning, that is, when the remaining information of the target user does not exist in the information database, the remaining guiding questions can be generated by the portrait generation agent to guide the collection of the remaining information of the target user in the current cycle stage, so as to realize the construction of the target user portrait based on the real-time obtained remaining information of the user, and then the corresponding insurance service can be provided for the target user based on the generated target user portrait in the subsequent process. In this way, compared with the related technical solution, the user portrait can be better generated, so that the real demand and potential intention of the user can be better analyzed.

[0129] Based on the user portrait generation method provided in the foregoing embodiments, the application also correspondingly provides a user portrait generation device. Figure 3 A structural schematic diagram of a user portrait generation device provided for an embodiment of the application is shown in FIG. 1. As shown in the figure, the user portrait generation device includes: Figure 3

[0130] A retrieval result obtaining unit 301 is configured to perform retrieval processing on the target name information of a target user received by a portrait generation agent in an information database to obtain an information retrieval result, wherein the information database includes user information corresponding to a plurality of users respectively;

[0131] A guiding question generating unit 302 is configured to generate remaining guiding questions by the portrait generation agent if the information retrieval result indicates that the remaining information of the user related to the target name information does not exist in the information database, wherein the remaining guiding questions are used to guide the collection of the remaining information of the user, and the remaining information of the user includes information of the user in the current cycle stage;

[0132] A remaining information receiving unit 303 is configured to receive the remaining information of the user fed back by the target user based on the remaining guiding questions by the portrait generation agent;

[0133] A user portrait generating unit 304 is configured to generate a target user portrait corresponding to the target user based on the target name information and the remaining information of the user by the portrait generation agent if an information category set corresponding to the received remaining information of the user satisfies a preset category set, wherein the target user portrait indicates an insurance service to be provided for the target user, and one information category corresponds to one preset category.

[0134] ​In an implementable embodiment, the remaining guiding questions include a first guiding question, a second guiding question, and a third guiding question, wherein the first guiding question indicates guiding collection of user family information, the second guiding question indicates guiding collection of user occupation information, and the third guiding question indicates guiding collection of user existing insurance products.

[0135] The remaining information receiving unit 303 is specifically configured to:

[0136] receive, by the portrait generation agent, user family information fed back by the target user based on the first guiding question;

[0137] receive, by the portrait generation agent, user occupation information fed back by the target user based on the second guiding question;

[0138] receive, by the portrait generation agent, user existing insurance products fed back by the target user based on the third guiding question.

[0139] In an implementable embodiment, the device further includes:

[0140] a prompt word obtaining unit configured to obtain a first generation prompt word and a second generation prompt word, wherein the first generation prompt word indicates analysis of the user family information and the user occupation information, and the second generation prompt word indicates analysis of the user existing insurance products;

[0141] The user portrait generation unit 304 includes:

[0142] a target user portrait generation unit configured to analyze and process, by the portrait generation agent, the target name information, the user family information, the user occupation information, and the user existing insurance products based on the first generation prompt word and the second generation prompt word, to generate a target user portrait corresponding to the target user.

[0143] In an implementable embodiment, the target user portrait generation unit includes:

[0144] a life cycle stage obtaining unit configured to analyze and process, by the portrait generation agent, the user family information and the user occupation information based on the first generation prompt word, to obtain a life cycle stage and a user value level corresponding to the target user;

[0145] a consciousness level obtaining unit configured to analyze and process, by the portrait generation agent, the user existing insurance products based on the second generation prompt word, to obtain an insurance risk consciousness level corresponding to the target user;

[0146] The user portrait obtaining unit is configured to generate, by the portrait generation agent, an initial user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level.

[0147] In an implementable embodiment, the apparatus further comprises:

[0148] The information base obtaining unit is configured to obtain a product information base, wherein the product information base is used in combination with generating the user portrait.

[0149] The user portrait obtaining unit is specifically configured to:

[0150] The user portrait obtaining unit is specifically configured to:

[0151] The user portrait obtaining unit is specifically configured to:

[0152] In an implementable embodiment, the life cycle stage comprises a first cycle stage, a second cycle stage, or a third cycle stage, the user value level comprises a first value level, a second value level, or a third value level, and the insurance risk awareness level comprises a first awareness level or a second awareness level, wherein the utilization rate of the first cycle stage is greater than that of the second cycle stage, the utilization rate of the second cycle stage is greater than that of the third cycle stage, the first value level is greater than the second value level, the second value level is greater than the third value level, and the first awareness level is greater than the second awareness level.

[0153] In an implementable embodiment, the apparatus further comprises:

[0154] The target guiding question generating unit is configured to generate, by the portrait generation agent, a target guiding question, wherein the target guiding question is used to guide the collection of the target name information.

[0155] The target name information receiving unit is configured to receive, by the portrait generation agent, target name information fed back by the target user based on the target guiding question.

[0156] The user portrait generation apparatus provided in the embodiments of the present application has the same beneficial effects as the user portrait generation method provided in the above embodiments, and can better generate a user portrait, which will not be described herein again.

[0157] The present application further provides a computer device. The computer device comprises:

[0158] a memory having a computer program stored thereon.

[0159] a processor configured to execute the computer program in the memory to implement some or all steps of the method for generating user portrait according to the foregoing embodiments.

[0160] The application further provides a computer readable storage medium having a computer program stored thereon. The program, when executed by a processor, implements some or all steps of the method for generating user portrait according to the foregoing embodiments.

[0161] It should be noted that the "first", "second" (if any) in the names mentioned in the embodiments of the present application are only used for name identification, and do not represent the first and second in order.

[0162] It should also be noted that each of the embodiments in the specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, the device and equipment embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment. The device and equipment embodiments described above are only illustrative, and the units described as separate components can be or can not be physically separated, and the components indicated as units can be or can not be physical units, that is, they can be located in one place or distributed on multiple network units. According to the actual needs, some or all modules can be selected to achieve the purpose of the embodiments. Those skilled in the art can understand and implement it without creative labor.

[0163] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any changes or replacements within the technical range disclosed in the present application can be easily thought of by those skilled in the art, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of generating a user profile, characterized by, The method comprises the following steps: Retrieving target name information of a target user received by an image generation agent in an information database, wherein the information database comprises user information corresponding to a plurality of users respectively; If the information retrieval result indicates that there is no user information related to the target name information in the information database, generating a remaining guiding question by the image generation agent, wherein the remaining guiding question is used to guide the collection of user information, and the user information comprises information of the user in a current period stage; Receiving user information fed back by the target user based on the remaining guiding question by the image generation agent; If the information category set corresponding to the received user information satisfies a preset category set, generating a target user image corresponding to the target user based on the target name information and the user information by the image generation agent, wherein the target user image indicates an insurance service to be provided to the target user, and one information category corresponds to one preset category.

2. The method of claim 1, wherein, The remaining guiding question comprises a first guiding question, a second guiding question and a third guiding question, wherein the first guiding question indicates guiding the collection of user family information, the second guiding question indicates guiding the collection of user occupation information, and the third guiding question indicates guiding the collection of user existing insurance products. The receiving of the user information fed back by the target user based on the remaining guiding question by the image generation agent comprises: Receiving user family information fed back by the target user based on the first guiding question by the image generation agent; Receiving user occupation information fed back by the target user based on the second guiding question by the image generation agent; Receiving user existing insurance products fed back by the target user based on the third guiding question by the image generation agent.

3. The method of claim 2, wherein, Before the generating of the target user image corresponding to the target user based on the target name information and the user information by the image generation agent, the method further comprises: Obtaining a first generation prompt word and a second generation prompt word, wherein the first generation prompt word indicates analyzing the user family information and the user occupation information, and the second generation prompt word indicates analyzing the user existing insurance products; The generating of the target user image corresponding to the target user based on the target name information and the user information by the image generation agent comprises: Analyzing and processing the target name information, the user family information, the user occupation information and the user existing insurance products based on the first generation prompt word and the second generation prompt word by the image generation agent to generate the target user image corresponding to the target user.

4. The method of claim 3, wherein, The analyzing and processing of the target name information, the user family information, the user occupation information and the user existing insurance products based on the first generation prompt word and the second generation prompt word by the image generation agent to generate the target user image corresponding to the target user comprises: The portrait generation agent analyzes and processes the user family information and the user occupation information based on the first generation prompt word, to obtain a life cycle stage and a user value level corresponding to the target user; The portrait generation agent analyzes and processes the existing insurance product of the user based on the second generation prompt word, to obtain an insurance risk awareness level corresponding to the target user; The portrait generation agent generates a target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level.

5. The method of claim 4, wherein, Before the portrait generation agent generates the target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level, the method further includes: obtaining a product information library, wherein the product information library is used in combination with generating a user portrait; The portrait generation agent generates a target user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level, including: The portrait generation agent generates an initial user portrait corresponding to the target user based on the target name information, the life cycle stage, the user value level, and the insurance risk awareness level; The portrait generation agent generates a target user portrait corresponding to the target user based on the product information library and the initial user portrait.

6. The method of claim 4, wherein, The life cycle stage includes a first cycle stage, a second cycle stage, or a third cycle stage, the user value level includes a first value level, a second value level, or a third value level, and the insurance risk awareness level includes a first awareness level or a second awareness level, wherein the utilization rate of the first cycle stage is greater than that of the second cycle stage, the utilization rate of the second cycle stage is greater than that of the third cycle stage, the first value level is greater than the second value level, the second value level is greater than the third value level, and the first awareness level is greater than the second awareness level.

7. The method of claim 1, wherein, Before the portrait generation agent performs retrieval processing on the target name information of the target user received in the information database to obtain an information retrieval result, the method further includes: The portrait generation agent generates a target guiding question, wherein the target guiding question is used to guide the collection of target name information; The portrait generation agent receives target name information fed back by the target user based on the target guiding question.

8. An apparatus for generating a user profile, characterized by The method includes: a retrieval result obtaining unit configured to perform retrieval processing on target name information of a target user received in an information database by a portrait generation agent to obtain an information retrieval result, wherein the information database includes user information corresponding to a plurality of users; The guiding question generation unit is configured to generate, by the portrait generation agent, a remaining guiding question if the information retrieval result indicates that there is no user remaining information related to the target name information in the information database, wherein the remaining guiding question is used to guide the collection of user remaining information, and the user remaining information includes information of the user in a current period stage; The remaining information receiving unit is configured to receive, by the portrait generation agent, user remaining information fed back by the target user based on the remaining guiding question; The user portrait generation unit is configured to generate, by the portrait generation agent, a target user portrait corresponding to the target user based on the target name information and the user remaining information if a set of information categories corresponding to the received user remaining information satisfies a preset category set, wherein the target user portrait indicates an insurance service to be provided to the target user, and one information category corresponds to one preset category.

9. A computer device, comprising: The computer program is stored in the memory and includes a computer program element. The processor is configured to execute the computer program in the memory to implement the steps of the user portrait generation method in any one of claims 1-7. The computer program is stored in the memory and includes a computer program element.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images