CN-116756424-B - Insurance service recommendation method, apparatus, server and storage medium

CN116756424BCN 116756424 BCN116756424 BCN 116756424BCN-116756424-B

Abstract

The embodiment of the application relates to the field of financial science and technology, and discloses an insurance service recommendation method, device, server and storage medium, wherein the method comprises the steps of obtaining basic information of a user, extracting characteristic data corresponding to the user according to the basic information, classifying the user to obtain category labels of the user, determining a target service strategy adapted to the user according to the category labels, sending an insurance service questionnaire to terminal equipment according to the target service strategy, obtaining questionnaire feedback, determining insurance service keywords and insurance service topics according to the questionnaire feedback, generating a plurality of topic cover diagrams according to the insurance service keywords by utilizing an image generation model, generating target insurance service contents according to the topic cover diagrams and the insurance service topics, and sending the target insurance service contents to the terminal equipment. The insurance service recommendation method realizes insurance service pushing based on the user category, improves the customer service quality of the insurance service, and further improves the success rate of the insurance service.

Inventors

YAN YANGYANG

Assignees

中国平安财产保险股份有限公司

Dates

Publication Date: 20260508
Application Date: 20230620

Claims (9)

1. An insurance service recommendation method based on user category, the method comprising: When receiving an insurance service information request sent by a terminal device logged in by a user account corresponding to a user, responding to the insurance service request to acquire basic information of the user, and extracting feature data corresponding to the user according to the basic information; Classifying the users by using a preset classification model and the characteristic data to obtain class labels of the users, and determining target service strategies adapted to the users according to the class labels; sending an insurance service questionnaire to the terminal equipment according to the target service strategy, and acquiring questionnaire feedback sent by the terminal equipment in response to the insurance service questionnaire; Determining an insurance service keyword and an insurance service theme according to the questionnaire feedback, and generating a plurality of theme cover diagrams according to the insurance service keyword by utilizing an image generation model; Generating target insurance service content according to the theme cover diagram and the insurance service theme, and sending the target insurance service content to the terminal equipment so that the terminal equipment displays the target insurance service content; The image generation model comprises a text analysis network, an image generation network and an image enhancement network, wherein the image generation model is used for generating a plurality of theme cover images according to the insurance service keywords, the image generation model comprises the steps of carrying out semantic analysis on the insurance service keywords by using the text analysis network to obtain semantic analysis characteristic vectors, outputting a plurality of initial cover images by using the image generation network according to the semantic analysis characteristic vectors, and carrying out image enhancement processing on the plurality of initial cover images by using the image enhancement network to obtain a plurality of theme cover images.
2. The method according to claim 1, wherein the classification model includes a vector conversion network, a first classification network, and a second classification network, the classifying the user using a preset classification model and the feature data to obtain a class label of the user, including: converting the characteristic data into corresponding characteristic vectors by using the vector conversion network, and respectively inputting the characteristic vectors into the first classification network and the second classification network; acquiring a first classification predicted value of the user output by the first classification network, and acquiring a second classification predicted value of the user output by a second classification network; a category label of the user is determined based on the first category prediction value and the second category prediction value.
3. The method of claim 1, wherein the sending an insurance service questionnaire to the terminal device according to the target service policy comprises: determining an insurance service questionnaire for information acquisition according to the target service strategy, and downloading questionnaire resources corresponding to the insurance service questionnaire from a resource server; and in the questionnaire resource downloading process, transmitting the questionnaire resource to the terminal equipment so that the terminal equipment displays the corresponding insurance service questionnaire according to the questionnaire resource.
4. The method of claim 1, wherein said determining insurance service keywords and insurance service topics from the questionnaire feedback comprises: determining insurance service items interested by the user according to the questionnaire feedback; and determining the insurance service keywords and the insurance service theme adapted by the user according to the insurance service items.
5. The method of claim 1, wherein prior to generating a plurality of topic cover maps from the insurance service keywords using an image generation model, the method further comprises: Outputting a first image set by using an initial image generation model to be trained; acquiring the image similarity of each first image in the first image set; calculating a loss value of a loss function of the initial image generation model according to the image similarity; and updating the model parameters of the initial image generation model according to the loss value until the image generation model is obtained.
6. The method of claim 5, wherein the image similarity includes at least gray level similarity, contour similarity, and spatial location similarity, and the first image set includes a plurality of sub-images, the acquiring the image similarity of each first image in the first image set comprising: performing gray comparison operation on an image comparison group in the first image set to perform gray comparison on sub-images in the image comparison group to obtain gray similarity of the image comparison group, wherein the image comparison group is formed by any two sub-images in the first image set; Performing contour extraction operation on the image comparison group to compare the contours of the sub-images in the image comparison group to obtain the contour similarity of the image comparison group; performing spatial position comparison operation on the image comparison group so as to perform spatial position comparison on target objects in sub-images in the image comparison group, thereby obtaining spatial position similarity of the image comparison group; and acquiring the gray level similarity, the contour similarity and the spatial position similarity for multiple times, and determining the image similarity corresponding to the first image set according to the gray level similarity, the contour similarity and the spatial position similarity acquired for multiple times.
7. An insurance service recommendation device based on user category, comprising: the information acquisition module is used for responding to the insurance service request to acquire the basic information of the user when receiving the insurance service information request sent by the terminal equipment logged in by the user account corresponding to the user, and extracting the characteristic data corresponding to the user according to the basic information; The policy configuration module is used for classifying the users by utilizing a preset classification model and the characteristic data to obtain class labels of the users, and determining target service policies adapted to the users according to the class labels; The insurance questionnaire module is used for sending an insurance service questionnaire to the terminal equipment according to the target service strategy and acquiring questionnaire feedback sent by the terminal equipment in response to the insurance service questionnaire; the cover generation module is used for determining insurance service keywords and insurance service topics according to the questionnaire feedback, and generating a plurality of topic cover diagrams according to the insurance service keywords by utilizing an image generation model; The service pushing module is used for generating target insurance service content according to the theme cover diagram and the insurance service theme and sending the target insurance service content to the terminal equipment so that the terminal equipment displays the target insurance service content; The image generation model comprises a text analysis network, an image generation network and an image enhancement network, wherein the image generation model is used for generating a plurality of theme cover images according to the insurance service keywords, the image generation model comprises the steps of carrying out semantic analysis on the insurance service keywords by using the text analysis network to obtain semantic analysis characteristic vectors, outputting a plurality of initial cover images by using the image generation network according to the semantic analysis characteristic vectors, and carrying out image enhancement processing on the plurality of initial cover images by using the image enhancement network to obtain a plurality of theme cover images.
8. A server, wherein the server comprises a processor and a memory; the memory is used for storing a computer program; the processor is configured to execute the computer program and to implement the user category based insurance service recommendation method as claimed in any of claims 1 to 6 when the computer program is executed.
9. A computer-readable storage medium, which when executed by one or more processors causes the one or more processors to perform the steps of the user category-based insurance service recommendation method of any of claims 1 to 6.

Description

Insurance service recommendation method, apparatus, server and storage medium Technical Field The application relates to the field of personal finance technology, in particular to an insurance service recommendation method, device, server and storage medium based on user categories. Background With the rapid development and wide use of information technology, users have more and more demanded insurance services, and financial enterprises providing insurance services have more and more. Therefore, customer quality of service is central to insurance service enterprises attracting and enhancing customer loyalty. Based on the different requirements of different users on insurance services, how to provide the most needed high-quality services for the users in a huge insurance system is a dilemma faced by each insurance service enterprise. In the existing insurance service, service personnel generally recommend the insurance service for different users according to a unified recommendation mode, so that the users cannot experience good customer service quality, and the success rate of the insurance service is low. Therefore, how to improve the customer service quality of insurance service, and thus the yield of insurance service, is of great importance to those skilled in the art. Disclosure of Invention The embodiment of the application mainly aims to provide an insurance service recommending method, device, server and storage medium based on user category, aiming at realizing personalized recommendation based on users so as to improve the customer service quality of insurance service and further improve the yield of the insurance service. In a first aspect, an embodiment of the present application provides a method for recommending insurance services based on a user category, where the method includes: When receiving an insurance service information request sent by a terminal device logged in by a user account corresponding to a user, responding to the insurance service request to obtain basic information of the user, and extracting feature data corresponding to the user according to the basic information; sending an insurance service questionnaire to the terminal equipment according to the target service strategy, and acquiring questionnaire feedback sent by the terminal equipment in response to the insurance service questionnaire; Determining an insurance service keyword and an insurance service theme according to the questionnaire feedback, and generating a plurality of theme cover diagrams according to the insurance service keyword by utilizing an image generation model; And generating target insurance service content according to the theme cover diagram and the insurance service theme, and sending the target insurance service content to the terminal equipment so that the terminal equipment displays the target insurance service content. In a second aspect, an embodiment of the present application further provides an insurance service recommendation device based on a user category, including: the information acquisition module is used for responding to the insurance service request to acquire the basic information of the user when receiving the insurance service information request sent by the terminal equipment logged in by the user account corresponding to the user, and extracting the characteristic data corresponding to the user according to the basic information; The policy configuration module is used for classifying the users by utilizing a preset classification model and the characteristic data to obtain class labels of the users, and determining target service policies adapted to the users according to the class labels; The insurance questionnaire module is used for sending an insurance service questionnaire to the terminal equipment according to the target service strategy and acquiring questionnaire feedback sent by the terminal equipment in response to the insurance service questionnaire; the cover generation module is used for determining insurance service keywords and insurance service topics according to the questionnaire feedback, and generating a plurality of topic cover diagrams according to the insurance service keywords by utilizing an image generation model; And the service pushing module is used for generating target insurance service content according to the theme cover diagram and the insurance service theme, and sending the target insurance service content to the terminal equipment so that the terminal equipment displays the target insurance service content. In a third aspect, embodiments of the present application further provide a server comprising a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for enabling a connection communication between the processor and the memory, wherein the computer program, when executed by the processor, implements the steps of the user class based insurance service recommendation method as p