Product science popularization introduction and recommendation method and device based on large model technology

Abstract

The invention relates to the technical field of product recommendation, and discloses a product science popularization introduction and recommendation method based on a large model technology. Comprising the steps of obtaining product related information and salesman related information of an insurance product; importing user historical consultation information, and generating a product recommendation model according to the user historical consultation information, the product related information and the salesman related information; user information is obtained, the user information comprises user text information and user voice information, and keyword information in the user information is extracted; according to the keyword information, utilizing a product recommendation model to generate a product introduction, and sending the product introduction to the client; acquiring purchase intention information, generating order signing information according to the purchase intention information and the related information of the salesman, and sending the order signing information to the client; the method has the advantages of high recommendation accuracy and reduced labor cost.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a method and device for popularizing and recommending products based on large model technology. Background Art

[0002] The traditional insurance sales model relies on the salesperson’s professional knowledge and sales skills, but there are the following problems:

[0003] The insurance knowledge and abilities of salesmen vary widely, making it difficult to meet the diverse needs of customers.

[0004] Customers do not have enough knowledge about insurance products and find it difficult to make wise purchasing decisions.

[0005] The sales process is inefficient and cannot meet customers' needs for quick access to information.

[0006] With the rapid development of Internet technology and artificial intelligence technology, insurance companies urgently need to innovate sales models and improve customer service experience and sales efficiency.

[0007] Therefore, a method and device for popularizing and recommending products based on large model technology is provided to solve the above problems. Summary of the invention

[0008] The main purpose of the present invention is to solve the problems in the traditional insurance sales model, such as the uneven insurance knowledge and abilities of salesmen, which make it difficult to meet the diverse needs of customers; customers do not have enough understanding of insurance products and find it difficult to make wise purchasing decisions; the sales process is inefficient and makes it difficult to meet customers' needs for quick access to information.

[0009] A first aspect of the present invention provides a product science popularization and recommendation method based on large model technology, and the product science popularization and recommendation method based on large model technology includes:

[0010] Obtain product-related information and salesperson-related information of insurance products;

[0011] Import user historical consultation information, and generate a product recommendation model based on user historical consultation information, product related information, and salesperson related information;

[0012] Acquire user information, the user information including user text information and user voice information, and extract keyword information from the user information;

[0013] Generate product introductions using product recommendation models based on keyword information and send the product introductions to the client;

[0014] Obtain purchase intention information, generate order information based on the purchase intention information and salesperson-related information, and send the order information to the client.

[0015] Furthermore, the obtaining of product-related information and salesperson-related information of the insurance product includes:

[0016] Obtain product-related information of insurance products, including product terms information, coverage information, price information, and insurance process information;

[0017] The salesperson-related information is obtained, including contact information, service area information, and expertise information.

[0018] Furthermore, the importing of user historical consultation information and generating a product recommendation model according to the user historical consultation information, product related information and salesperson related information includes:

[0019] Import user consultation history information, extract consultation keywords and user key information from the user consultation history information, the consultation keywords include insurance type keywords, insurance name keywords and coverage keywords; the user key information includes age, gender, income and risk preference;

[0020] Match consulting keywords with insurance products, associate user keyword information with insurance products to generate relevance information, arrange insurance products according to the relevant information, and generate a product recommendation model.

[0021] Furthermore, the acquiring of user information includes user text information and user voice information, and extracting keyword information from the user information includes:

[0022] Obtain user text information and extract keyword information from the user text information;

[0023] Acquire user voice information, convert the user voice information into text information, and extract keyword information from the text information.

[0024] Further, the acquiring of purchase intention information, generating order information according to the purchase intention information and salesperson-related information, and sending the order information to the client includes:

[0025] Acquire purchase intention information, and generate order information based on the purchase intention information and relevant information of the salesperson, wherein the purchase intention information includes: information on intended purchase products and scheduled visit time information;

[0026] Send the signing information to the client.

[0027] The second aspect of the present invention provides a device for profiling the ability characteristics of insurance salespersons based on a neural network algorithm, comprising:

[0028] A data acquisition module is used to obtain product-related information and salesperson-related information of insurance products;

[0029] The product recommendation model generation module is used to import the user's historical consultation information and generate a product recommendation model based on the user's historical consultation information, product-related information and salesperson-related information;

[0030] A user information acquisition module, used to acquire user information, the user information includes user text information and user voice information, and extract keyword information from the user information;

[0031] The product recommendation module is used to generate product introductions based on keyword information using a product recommendation model and send the product introductions to the client;

[0032] The purchase intention visit module is used to obtain purchase intention information, generate signing information based on the purchase intention information and salesperson-related information, and send the signing information to the client.

[0033] A third aspect of the present invention provides an electronic device, the electronic device comprising a memory and at least one processor, the memory storing instructions;

[0034] The at least one processor calls the instructions in the memory so that the electronic device executes the various steps of the product popular science introduction and recommendation method based on large model technology as described above.

[0035] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the various steps of the product popular science introduction and recommendation method based on large model technology as described above.

[0036] The present invention can provide personalized insurance product introductions and recommendations based on user needs, thereby improving customer service experience; users can quickly learn about insurance product information and obtain personalized recommendations, saving time and energy; by providing accurate insurance product recommendations and efficient service processes, customer conversion rates can be effectively improved; the work of some salesmen can be replaced, labor costs can be reduced, and operational efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of the product science popularization introduction and recommendation method based on the large model technology provided by the present invention;

[0038] Figure 2 A schematic diagram of the structure of a product science popularization introduction and recommendation device based on large model technology provided by an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The embodiment of the present invention provides a product popular science introduction and recommendation method based on big model technology, including obtaining product-related information and salesperson-related information of insurance products; importing user historical consultation information, and generating a product recommendation model based on the user's historical consultation information, product-related information and salesperson-related information; obtaining user information, the user information including user text information and user voice information, and extracting keyword information in the user information; generating a product introduction using the product recommendation model based on the keyword information, and sending the product introduction to a client; obtaining purchase intention information, generating signing information based on the purchase intention information and salesperson-related information, and sending the signing information to a client. The present invention solves the problems in the prior art that in the traditional insurance sales model, the insurance knowledge and abilities of salespersons are uneven, making it difficult to meet the diverse needs of customers; customers do not have sufficient understanding of insurance products and find it difficult to make wise purchasing decisions; the sales process is inefficient and it is difficult to meet customers' needs for quick information acquisition, and the like.

[0041] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the product popular science introduction and recommendation method based on the large model technology in the embodiment of the present invention includes:

[0043] Obtain product-related information and salesperson-related information of insurance products;

[0044] Specifically, they include:

[0045] Obtain product-related information of insurance products, including product terms information, coverage information, price information, and insurance process information;

[0046] The salesperson-related information is obtained, including contact information, service area information, and expertise information.

[0047] Import user historical consultation information, and generate a product recommendation model based on user historical consultation information, product related information, and salesperson related information;

[0048] Acquire user information, the user information including user text information and user voice information, and extract keyword information from the user information;

[0049] Generate product introductions using product recommendation models based on keyword information and send the product introductions to the client;

[0050] Obtain purchase intention information, generate order information based on the purchase intention information and salesperson-related information, and send the order information to the client.

[0051] See also Figure 1 The second embodiment of the product popular science introduction and recommendation method based on the large model technology in the embodiment of the present invention includes:

[0052] Obtain product-related information and salesperson-related information of insurance products;

[0053] Specifically, they include:

[0054] Obtain product-related information of insurance products, including product terms information, coverage information, price information, and insurance process information;

[0055] The salesperson-related information is obtained, including contact information, service area information, and expertise information.

[0056] Import user historical consultation information, and generate a product recommendation model based on user historical consultation information, product related information, and salesperson related information;

[0057] Specifically, they include:

[0058] Import user consultation history information, extract consultation keywords and user key information from the user consultation history information, the consultation keywords include insurance type keywords, insurance name keywords and coverage keywords; the user key information includes age, gender, income and risk preference;

[0059] Match consulting keywords with insurance products, associate user keyword information with insurance products to generate relevance information, arrange insurance products according to the relevant information, and generate a product recommendation model.

[0060] Acquire user information, the user information including user text information and user voice information, and extract keyword information from the user information;

[0061] Generate product introductions using product recommendation models based on keyword information and send the product introductions to the client;

[0062] Obtain purchase intention information, generate order information based on the purchase intention information and salesperson-related information, and send the order information to the client.

[0063] See also Figure 1 The third embodiment of the insurance salesperson capability feature graph profiling method based on the neural network algorithm in the embodiment of the present invention includes:

[0064] Obtain product-related information and salesperson-related information of insurance products;

[0065] Specifically, they include:

[0066] Obtain product-related information of insurance products, including product terms information, coverage information, price information, and insurance process information;

[0067] The salesperson-related information is obtained, including contact information, service area information, and expertise information.

[0068] Import user historical consultation information, and generate a product recommendation model based on user historical consultation information, product related information, and salesperson related information;

[0069] Specifically, they include:

[0070] Import user consultation history information, extract consultation keywords and user key information from the user consultation history information, the consultation keywords include insurance type keywords, insurance name keywords and coverage keywords; the user key information includes age, gender, income and risk preference;

[0071] Matching consulting keywords with insurance products. Correlating user keyword information with insurance products to generate relevance information. Arranging insurance products according to the relevance information. Insurance products ranked before the preset ranking are recommended products, and a product recommendation model is generated.

[0072] In addition, keywords correspond to insurance products, and an example of the process of associating user keyword information with insurance products is: extracting the keyword pension, the customer's keyword information is age 30-40, gender male, stable monthly income of 8K, and stable risk preference. Among them, pension corresponds to several insurance products, age 30-40 corresponds to several insurance types, and so on. Each customer's keyword information corresponds to several insurance types. The final relevance is the intersection of the insurance products corresponding to these keywords, which is a product with high relevance. The subsequent arrangement order is arranged according to the order of the customer's questions.

[0073] Acquire user information, the user information including user text information and user voice information, and extract keyword information from the user information; specifically including: acquire user text information, extract keyword information from the user text information; acquire user voice information, convert the user voice information into text information, and extract keyword information from the text information.

[0074] Generate product introductions using product recommendation models based on keyword information and send the product introductions to the client;

[0075] Acquire purchase intention information, generate signing information based on the purchase intention information and salesperson-related information, and send the signing information to the client; specifically include: acquire purchase intention information, generate signing information based on the purchase intention information and salesperson-related information, the purchase intention information includes: intended purchase product information and appointment visit time information; send the signing information to the client.

[0076] The above describes the product science popularization introduction and recommendation method based on the large model technology in the embodiment of the present invention. The following describes the product science popularization introduction and recommendation device based on the large model technology in the embodiment of the present invention. Please refer to Figure 2 The product popular science introduction and recommendation device based on the large model technology in the embodiment of the present invention includes:

[0077] Data acquisition module 201, used to acquire product-related information and salesperson-related information of insurance products;

[0078] The product recommendation model generation module 202 is used to import the user's historical consultation information and generate a product recommendation model based on the user's historical consultation information, product related information and salesperson related information;

[0079] A user information acquisition module 203 is used to acquire user information, which includes user text information and user voice information, and extract keyword information from the user information;

[0080] The product recommendation module 204 is used to generate a product introduction based on the keyword information using the product recommendation model and send the product introduction to the client;

[0081] The purchase intention visit module 205 is used to obtain purchase intention information, generate signing information based on the purchase intention information and salesperson-related information, and send the signing information to the client.

[0082] above Figure 2 The product popularization introduction and recommendation device based on the big model technology in the embodiment of the present invention are described in detail from the perspective of modular functional entities. The electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0083] Figure 3 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing unit, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 (for example, one or more mass storage devices) storing application programs 733 or data 732. Among them, the memory 720 and the storage medium 730 can be temporary storage or permanent storage. The program stored in the storage medium 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of instruction operations in the storage medium 730 on the electronic device 700.

[0084] The electronic device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input / output interfaces 750, and / or one or more operating systems 731, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3 The structure of the electronic device shown does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0085] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of a product popular science introduction and recommendation method based on large model technology.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0087] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0088] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A product science popularization and recommendation method based on large model technology, characterized in that: The product science introduction and recommendation method based on large model technology include: Obtain product-related information and salesperson-related information of insurance products; Import user historical consultation information, and generate a product recommendation model based on user historical consultation information, product related information, and salesperson related information; Acquire user information, the user information including user text information and user voice information, and extract keyword information from the user information; Generate product introductions using product recommendation models based on keyword information and send the product introductions to the client; Obtain purchase intention information, generate order information based on the purchase intention information and salesperson-related information, and send the order information to the client.

2. The product science popularization and recommendation method based on large model technology according to claim 1 is characterized in that: The obtaining of product-related information and salesperson-related information of insurance products includes: Obtain product-related information of insurance products, including product terms information, coverage information, price information, and insurance process information; The salesperson-related information is obtained, including contact information, service area information, and expertise information.

3. The product science popularization and recommendation method based on large model technology according to claim 2 is characterized in that: The importing of user historical consultation information and generating a product recommendation model according to the user historical consultation information, product related information and salesperson related information includes: Import user consultation history information, extract consultation keywords and user key information from the user consultation history information, the consultation keywords include insurance type keywords, insurance name keywords and coverage keywords; the user key information includes age, gender, income and risk preference; Match consulting keywords with insurance products, associate user keyword information with insurance products to generate relevance information, arrange insurance products according to the relevant information, and generate a product recommendation model.

4. The product science popularization and recommendation method based on large model technology according to claim 3 is characterized in that: The acquiring of user information, wherein the user information includes user text information and user voice information, and the extracting of keyword information from the user information includes: Obtain user text information and extract keyword information from the user text information; Acquire user voice information, convert the user voice information into text information, and extract keyword information from the text information.

5. The product science popularization and recommendation method based on large model technology according to claim 4 is characterized in that: The obtaining of purchase intention information, generating order information according to the purchase intention information and relevant information of the salesperson, and sending the order information to the client comprises: Acquire purchase intention information, and generate order information based on the purchase intention information and relevant information of the salesperson, wherein the purchase intention information includes: information on intended purchase products and scheduled visit time information; Send the signing information to the client.

6. A product science popularization and recommendation device based on large model technology, characterized in that: include: A data acquisition module is used to obtain product-related information and salesperson-related information of insurance products; The product recommendation model generation module is used to import the user's historical consultation information and generate a product recommendation model based on the user's historical consultation information, product-related information and salesperson-related information; A user information acquisition module, used to acquire user information, the user information includes user text information and user voice information, and extract keyword information from the user information; The product recommendation module is used to generate product introductions based on keyword information using a product recommendation model and send the product introductions to the client; The purchase intention visit module is used to obtain purchase intention information, generate signing information based on the purchase intention information and salesperson-related information, and send the signing information to the client.

7. An electronic device, comprising a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory so that the electronic device executes each step of the product popular science introduction and recommendation method based on large model technology as described in any one of claims 1-7.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the product popular science introduction and recommendation method based on large model technology as described in any one of claims 1 to 7 are implemented.

Images