Insurance product recommendation method and device, computer equipment and readable storage medium

Abstract

The invention relates to the field of data processing, and provides an insurance product recommendation method and device, computer equipment and a computer readable storage medium, and the method comprises the steps: obtaining an occupational classification standard file and internal occupational information, and generating an oral title of an occupational language and an oral title of an industry according to the occupational classification standard file; supplementing the internal occupational information according to the oral title of the occupational and the oral title of the industry to obtain an internal occupational standard file; dialogue information between the user and the claim settlement personnel is acquired, and the occupation of the user is identified from the dialogue information according to the internal occupation standard file; and according to the occupation of the user, recommending an insurance product to the user. By adopting the embodiment of the invention, the occupation and industry information of the user can be accurately acquired on the premise of ensuring the data security, so that a more accurate insurance product recommendation service is provided.

Description

Technical Field

[0001] The present application relates to the fields of data processing and financial technology, and in particular to an insurance product recommendation method, apparatus, computer equipment and computer-readable storage medium. Background Art

[0002] When recommending insurance products, insurance companies need to obtain the precise occupation and industry type of individual users to determine insurance risks and subsequent insurance pricing. For the sub-field of "user occupations used for insurance risk judgment", the current open source model is generally lacking in response capabilities in vertical fields, and the output content is often not in the "Occupational Classification Dictionary" table.

[0003] As for occupational data, different insurance companies will have different and personalized interpretations of policy documents. Due to its privacy, corporate data cannot be sent to external large models for corpus generation. If open source models are used on the intranet to reversely generate questions and answers, the data quality will be somewhat different from the top external large models.

[0004] Therefore, how to accurately obtain users' occupational and industry information while ensuring data security, so as to provide more accurate insurance product recommendation services, has become a technical problem that needs to be urgently solved in the current insurance industry. Summary of the invention

[0005] The main purpose of this application is to provide an insurance product recommendation method, device, computer equipment and computer-readable storage medium, aiming to accurately obtain the user's occupation and industry information while ensuring data security, so as to provide more accurate insurance product recommendation services.

[0006] To achieve the above objectives, the present application provides an insurance product recommendation method, which includes the following steps:

[0007] Obtaining occupational classification standard documents and internal occupational information, and generating spoken titles of occupations and spoken titles of industries based on the occupational classification standard documents;

[0008] Supplement the internal occupation information according to the colloquial title of the occupation and the colloquial title of the industry to obtain an internal occupation standard document;

[0009] Acquiring conversation information between the user and the claims adjuster, and identifying the user's occupation from the conversation information according to the internal occupation standard file;

[0010] Recommend insurance products to the user based on the user's occupation.

[0011] In addition, to achieve the above-mentioned purpose, the present application also provides an insurance product recommendation device, the insurance product recommendation device comprising:

[0012] A spoken title generation unit, used for obtaining occupation classification standard files and internal occupation information, and generating spoken titles of occupations and spoken titles of industries according to the occupation classification standard files;

[0013] An occupation information supplement unit, used to supplement the internal occupation information according to the oral title of the occupation and the oral title of the industry to obtain an internal occupation standard document;

[0014] A user occupation identification unit, used to obtain the conversation information between the user and the claims adjuster, and to identify the user's occupation from the conversation information according to the internal occupation standard file;

[0015] An insurance product recommendation unit is used to recommend insurance products to the user according to the user's occupation. In addition, to achieve the above purpose, the present application also provides a computer device, the computer device includes a processor, a memory, and an insurance product recommendation program stored in the memory and executable by the processor, wherein when the insurance product recommendation program is executed by the processor, the steps of the above-mentioned insurance product recommendation method are implemented.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which an insurance product recommendation program is stored, wherein when the insurance product recommendation program is executed by a processor, the steps of the insurance product recommendation method as described above are implemented.

[0017] The present application provides an insurance product recommendation method, apparatus, computer equipment and computer-readable storage medium. The method includes obtaining an occupation classification standard file and internal occupation information, and generating a spoken title of an occupation and a spoken title of an industry according to the occupation classification standard file; supplementing the internal occupation information according to the spoken title of the occupation and the spoken title of the industry to obtain an internal occupation standard file; then obtaining conversation information between a user and a claims adjuster, and identifying the user's occupation from the conversation information according to the internal occupation standard file; and then recommending insurance products to the user according to the user's occupation.

[0018] It can be seen that in the embodiment of the present application, the spoken titles of occupations and the spoken titles of industries can be generated by an external large model according to the occupational classification standard file, and the data quality is higher than that generated by an internal open source model; then the internal occupational information is supplemented according to the spoken titles of the occupation and the industry, so that the internal occupational standard file obtained is richer and more complete; therefore, the user's occupation can be more accurately identified from the conversation information according to the internal occupational standard file, and thus the insurance products recommended to the user according to the user's occupation are also more accurate; in addition, the internal occupational information is not used as a prediction to train the external large model, which also ensures the security of the internal data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of an insurance product recommendation method provided for this application;

[0020] Figure 2 A flowchart of another insurance product recommendation method provided for this application;

[0021] Figure 3 A flowchart of another insurance product recommendation method provided for this application;

[0022] Figure 4 A schematic diagram of the functional modules of an insurance product recommendation device provided in this application;

[0023] Figure 5 A schematic block diagram of the structure of a computer device provided in this application.

[0024] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0027] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0028] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] The insurance product recommendation method involved in the embodiment of the present application is mainly applied to a computer device, which may be a PC, a portable computer, a mobile terminal, or other device with display and processing functions.

[0030] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0031] Reference Figure 1 , Figure 1 A flowchart of an insurance product recommendation method provided for this application.

[0032] like Figure 1 As shown, an embodiment of the present application provides an insurance product recommendation method, which includes steps S101 to S104.

[0033] In this embodiment, the insurance product recommendation method includes the following steps:

[0034] Step S101, obtaining occupation classification standard files and internal occupation information, and generating spoken titles of occupations and spoken titles of industries according to the occupation classification standard files.

[0035] Among them, occupational classification standard documents refer to standard documents formulated by national or international organizations to standardize and unify occupational classification. These documents are of great significance to human resource management, education planning, vocational training, statistical analysis and other aspects. In China, the most commonly used occupational classification standard document is the "Occupational Classification Dictionary of the People's Republic of China" (abbreviated as "Occupational Classification Dictionary"). Internal occupational information refers to information generated by personalized interpretation of occupational classification standard documents. Colloquial titles refer to some words or expressions used to address in daily communication. Different cultural backgrounds and social environments may have different naming habits. The colloquial title of an occupation refers to some words or expressions used to address the occupation in daily communication, and the colloquial title of an industry refers to some words or expressions used to address the industry in daily communication.

[0036] Specifically, generating the spoken titles of occupations and the spoken titles of industries according to the occupation classification standard file includes:

[0037] Extracting occupation descriptions from the occupation classification standard file;

[0038] The occupation description is used as a prompt word of a deep learning generative model, and the spoken name of the occupation and the spoken name of the industry are generated according to the deep learning generative model.

[0039] For example, the occupational description in the occupational classification standard file may be, for example, "Landscaping worker: responsible for the maintenance of greenery within the property", "Website editor: editing and processing website articles and other content", etc. The occupational description is extracted and then used as a prompt word for the deep learning generative model.

[0040] Exemplarily, the prompt words of the deep learning generative model may be:

[0041] 1. "Based on the description of the following work tasks, list some titles of people who are engaged in this kind of work content in daily life. {The work content of a certain occupation from the Occupational Classification Dictionary}".

[0042] 2. "Below is the scope description of the "xxx" occupation. For a list of colloquial sub-occupations, please refer to the format of "Landscaping worker: responsible for the maintenance of greenery within the property", "Website editor: editing and processing website articles and other content". Please come in to cover all sub-occupations."

[0043] For example, Chinese chef, head chef, cook, dim sum chef, and head cook are all colloquial titles for Chinese chefs; the industries to which restaurants, dining halls, dining rooms, snack bars, etc. belong are accommodation and catering industry - catering industry - full meal services.

[0044] Exemplarily, the deep learning generative model may be, for example, GPT (Generative Pre-trained Transformer), Wenxin Yiyan, Tongyi Qianwen, Claude, NewBing, etc., which are not limited here.

[0045] It should be noted that the step of "obtaining the occupational classification standard file" and the step of "obtaining internal occupational information" can be obtained synchronously or asynchronously, and the execution order of the two is not limited.

[0046] Step S102: supplement the internal occupation information according to the spoken title of the occupation and the spoken title of the industry to obtain an internal occupation standard document.

[0047] Specifically, the internal occupation information is supplemented according to the oral title of the occupation and the oral title of the industry to obtain an internal occupation standard document, including:

[0048] The name of the occupation for which the internal occupation information is obtained;

[0049] Establishing a mapping relationship between the occupation name and the colloquial name of the occupation and the colloquial name of the industry;

[0050] The internal occupation information is supplemented according to the mapping relationship to obtain an internal occupation standard document.

[0051] Exemplarily, the occupational classification standard file stores relevant content in a table form, for example, the table includes the following four columns: occupation code, occupation name, occupation category, occupation description. By extracting information such as the occupation description or occupation name as prompt words for the external large model, the spoken name of the occupation and the spoken name of the industry can be obtained. Then the above table adds two columns to become 6 columns, namely: occupation code, occupation name, occupation category, occupation description, spoken name of the occupation, and spoken name of the industry.

[0052] Exemplarily, the internal occupational information is also stored in the form of a table, which includes the following five columns: occupation code, occupation name, occupation category, occupation description, and risk level.

[0053] Then, the occupation names in the table are identified, and the mapping relationship between the occupation names and the spoken titles of the occupations and the spoken titles of the industries is established. Then, the internal occupation information can be supplemented according to the mapping relationship to obtain the internal occupation standard file. After merging the above two tables, the internal occupation standard file includes 7 columns: occupation code, occupation name, occupation category, occupation description, spoken title of occupation, spoken title of industry, and risk level.

[0054] For example, industry types can be stored in a multi-level classification manner, for example: agriculture, forestry, animal husbandry, fishery -> agriculture -> planting of grains and other crops, and companies that may work under the planting type of grains and other crops may include: agriculture, farm plantations, greenhouse vegetable suppliers, fruit seedling cultivation companies, grain field planting companies, grain planting farms, fruit and vegetable planting companies, seed breeding companies, agricultural product research and development companies, crop seed companies, agricultural cooperatives, agricultural technology companies, agricultural biotechnology companies, agricultural supply chain management companies, etc. Then, the above content can be used as prompt words to generate the colloquial name of the industry.

[0055] Step S103: obtaining the conversation information between the user and the claims adjuster, and identifying the user's occupation from the conversation information according to the internal occupation standard file.

[0056] In a specific embodiment of the present application, the step of identifying the user's occupation from the conversation information according to the internal occupation standard file includes:

[0057] Converting the dialogue information into dialogue information text;

[0058] Performing word segmentation processing on the dialogue information text to obtain at least one text keyword;

[0059] Extracting a plurality of candidate occupations from the internal occupation standard file according to at least one of the text keywords;

[0060] Calculating the similarity between each candidate occupation and at least one of the text keywords;

[0061] Calculating scores of the plurality of candidate occupations according to the similarities;

[0062] The user's occupation is determined according to the scores of the plurality of candidate occupations.

[0063] Exemplarily, the dialogue information may include the communication dialogue between the user and the insurance salesperson, and may also include emotional information during the communication dialogue, and may also include environmental information during the communication dialogue.

[0064] Exemplarily, if the communication dialogue can be in text form, the dialogue information text can be directly obtained; if the communication dialogue is in voice form, the voice can be converted into the dialogue information text through voice-to-text technology.

[0065] If the conversation information includes emotional information during the conversation, then the emotional information can be used to assist in recommending insurance products to the user based on the emotional information of the current user. For example, if the emotional information is negative, it is judged that the risk of default in the future is high, so the user's risk level can be increased, and the second method described below is used to recommend insurance products to the user; if the emotional information is positive, it is judged that the risk of default in the future is low, so the user's risk level is reduced, and the first method described below is used to recommend insurance products to the user.

[0066] Exemplarily, if the dialogue information includes environmental information during the communication dialogue, the environmental information can assist in the judgment of the user's occupation and industry. For example, the keywords involved in the current communication dialogue are related to fruit and vegetable planting, so the user's occupation may be a farmer or an agricultural researcher, and the environmental information during the communication dialogue can be used to further assist in the judgment. If the noise confirmed in the environmental information during the communication dialogue is large, it is judged that his occupation is a farmer who works in the field to plant; if the noise confirmed in the environmental information during the communication dialogue is small, it is judged that his occupation is an agricultural researcher who cultivates in a laboratory through utensils; the two occupations are quite different, so the judged risk levels are also very different, so the recommended insurance products are also very different. Furthermore, the noise level can be judged according to the set decibel threshold.

[0067] Among them, word segmentation is an important step in natural language processing, which divides a continuous text into independent vocabulary units, which are usually called "words" or "word units". Exemplarily, word segmentation can be a rule-based method, a statistical method, or a deep learning method. The rule-based method for word segmentation refers to segmenting text through predefined dictionaries and rules; the statistical method for word segmentation refers to using a large corpus training model to determine the boundaries of words through statistical probability; the deep learning method for word segmentation refers to using neural network models, such as recurrent neural networks (RNN), long short-term memory networks (LSTM) and Transformers, to perform word segmentation.

[0068] Specifically, a plurality of candidate occupations are extracted from the internal occupation standard file according to at least one of the text keywords. For example, the at least one text keyword is retrieved from the internal occupation standard file, and then the occupations associated with the retrieved keywords are taken as candidate occupations.

[0069] Among them, similarity is used to measure the similarity between two texts. Exemplarily, the similarity in this application includes at least one of the following: cosine similarity, Jaccard similarity, edit distance (Levenshtein distance), word embedding similarity. Cosine similarity measures the similarity of two vectors by calculating the cosine value of the angle between them. Jaccard similarity measures their similarity by calculating the ratio of the intersection and union of two sets. Edit distance measures their similarity by calculating the minimum number of editing operations (insertion, deletion, substitution) required to convert one string into another. Word embedding (such as Word2Vec, GloVe, BERT, etc.) can map words into a high-dimensional vector space, and measure the similarity of words or sentences by calculating the distance between vectors (such as Euclidean distance or cosine similarity).

[0070] Exemplarily, the score may be expressed by similarity, for example, if the similarity is 98%, the score is 98; if the similarity is 80%, the score is 80; if the similarity is 34%, the score is 34.

[0071] Specifically, the internal occupation standard file includes the spoken occupation name of each occupation, the standard occupation name corresponding to the spoken occupation name, and the industry to which it belongs; the calculating the similarity between each candidate occupation and the keyword includes:

[0072] Perform word segmentation processing on each candidate occupation to obtain a first spoken occupation name keyword and a first industry keyword;

[0073] Determining a second spoken occupation name keyword and a second industry keyword from at least one text keyword;

[0074] Calculating the name similarity between the first spoken occupation name keyword and the second spoken occupation name keyword, and calculating the industry similarity between the first industry keyword and the second industry keyword;

[0075] The similarity between each of the candidate occupations and the keyword is determined according to the name similarity and the industry similarity.

[0076] Exemplarily, the similarity between each candidate occupation and the keyword is determined based on the name similarity and the industry similarity, and corresponding weights are set for the name similarity and the industry similarity, and then a first product of the name similarity and its weight, and a second product of the industry similarity and its weight are calculated, and then the sum of the first product and the second product is used as the similarity between each candidate occupation and the keyword. Furthermore, since the similarity between each candidate occupation and the keyword is determined, the weight of the name similarity can be set to be greater than the weight of the industry similarity, but the sum of the two is guaranteed to be 1.

[0077] Step S104: recommending insurance products to the user based on the user's occupation.

[0078] In a specific embodiment of the present application, recommending an insurance product to the user according to the user's occupation includes:

[0079] Determine a target risk level corresponding to the user's occupation, and recommend an insurance product with a risk level higher than or equal to the target risk level to the user.

[0080] Exemplarily, after merging the above two tables, the internal occupational standard file includes 7 columns: occupation code, occupation name, occupation category, occupation description, occupational colloquial title, industry colloquial title, and risk level. After identifying the user's occupation, search the occupation column in the internal occupational standard file to find the risk level corresponding to the user's occupation as the target risk level, and then recommend insurance products with risk levels higher than or equal to the target risk level to the user. For example, the candidate occupations are A, B, and C, and the risk levels are 1, 2, and 3, and the risk level is 1<2<3; the determined occupation is B, and the recommended product is 2 or 3.

[0081] It can be seen that the embodiment of the present application can recommend more insurance products for users to choose from while reducing the risk of insurance companies. However, it first needs to determine the occupation from multiple candidate occupations, so it needs to calculate multiple similarities, and the recommendation speed is relatively slow.

[0082] Furthermore, the internal occupation standard file includes a risk level for each occupation, and before determining the target risk level corresponding to the user's occupation, determining the user's occupation according to the scores of the plurality of candidate occupations includes:

[0083] Determine the candidate occupation with the highest score as the user's occupation;

[0084] In another specific embodiment of the present application, the insurance product recommendation method further includes:

[0085] Determine a target risk level corresponding to each of the candidate occupations to obtain a plurality of target risk levels;

[0086] Recommending to the user an insurance product whose risk level is higher than or equal to the highest target risk level.

[0087] For example, the candidate occupations are A, B, and C, and the risk levels are 1, 2, and 3; the highest level is 3, and in order to reduce the risk of the insurance company, the recommended product is 3. It can be seen that in the embodiment of the present application, the highest risk level is directly determined based on multiple candidate occupations, and then products with a risk level higher than or equal to the highest risk level are recommended. This method may recommend fewer insurance products to users, but it does not need to calculate multiple similarities, so the calculation speed is relatively fast.

[0088] It can be seen that in the embodiment of the present application, the spoken titles of occupations and the spoken titles of industries can be generated by an external large model according to the occupational classification standard file, and the data quality is higher than that generated by an internal open source model; then the internal occupational information is supplemented according to the spoken titles of the occupation and the industry, so that the internal occupational standard file obtained is richer and more complete; therefore, the user's occupation can be more accurately identified from the conversation information according to the internal occupational standard file, and thus the insurance products recommended to the user according to the user's occupation are also more accurate; in addition, the internal occupational information is not used as a prediction to train the external large model, which also ensures the security of the internal data.

[0089] Reference Figure 2 , Figure 2 A flowchart of another insurance product recommendation method provided for this application.

[0090] like Figure 2 As shown, an embodiment of the present application provides an insurance product recommendation method, and the five-level loan classification method includes steps S201 to S217.

[0091] In this embodiment, the insurance product recommendation method includes the following steps:

[0092] Step S201, obtaining occupational classification standard files and internal occupational information.

[0093] Step S202: extracting the occupation description in the occupation classification standard file.

[0094] Step S203: using the occupation description as a prompt word for a deep learning generative model, and generating a spoken title for the occupation and a spoken title for the industry based on the deep learning generative model.

[0095] Step S204: Obtain the occupation name of the internal occupation information.

[0096] Step S205: Establish a mapping relationship between the occupation name and the spoken name of the occupation and the spoken name of the industry.

[0097] Step S206: supplement the internal occupation information according to the mapping relationship to obtain an internal occupation standard file, wherein the internal occupation standard file includes the spoken occupation name of each occupation, the standard occupation name corresponding to the spoken occupation name, the industry to which it belongs, and the risk level.

[0098] Step S207: Obtaining conversation information between the user and the claims adjuster.

[0099] Step S208: converting the dialogue information into dialogue information text.

[0100] Step S209: performing word segmentation processing on the dialogue information text to obtain at least one text keyword.

[0101] Step S210: extract multiple candidate occupations from the internal occupation standard file according to at least one of the text keywords.

[0102] Step S211, perform word segmentation processing on each candidate occupation to obtain a first spoken occupation name keyword and a first industry keyword.

[0103] Step S212: Determine a second spoken occupation name keyword and a second industry keyword from at least one text keyword.

[0104] Step S213, calculating the name similarity between the first spoken occupation name keyword and the second spoken occupation name keyword, and calculating the industry similarity between the first belonging industry keyword and the second belonging industry keyword.

[0105] Step S214: Determine the similarity between each of the candidate occupations and the keyword based on the name similarity and the industry similarity.

[0106] Step S215: Calculate scores of the plurality of candidate occupations according to the similarities.

[0107] Step S216: Determine the candidate occupation with the highest score as the user's occupation.

[0108] Step S217: determine the target risk level corresponding to the user's occupation, and recommend to the user an insurance product with a risk level higher than or equal to the target risk level.

[0109] The specific implementation methods of each step in the embodiments of the present application refer to the specific implementation methods of each step in the above embodiments, which will not be repeated here.

[0110] Reference Figure 3 , Figure 3 A flowchart of another insurance product recommendation method provided in this application.

[0111] like Figure 3 As shown, an embodiment of the present application provides an insurance product recommendation method, and the five-level loan classification method includes steps S301 to S312.

[0112] In this embodiment, the insurance product recommendation method includes the following steps:

[0113] Step S301, obtaining occupational classification standard files and internal occupational information.

[0114] Step S302: extracting the occupation description in the occupation classification standard file.

[0115] Step S303: using the occupation description as a prompt word for a deep learning generative model, and generating a spoken title for the occupation and a spoken title for the industry based on the deep learning generative model.

[0116] Step S304: Obtain the occupation name of the internal occupation information.

[0117] Step S305: Establish a mapping relationship between the occupation name and the spoken name of the occupation and the spoken name of the industry.

[0118] Step S306: supplement the internal occupation information according to the mapping relationship to obtain an internal occupation standard file, wherein the internal occupation standard file includes the spoken occupation name of each occupation, the standard occupation name corresponding to the spoken occupation name, the industry to which it belongs, and the risk level.

[0119] Step S307: Obtaining the conversation information between the user and the claims adjuster.

[0120] Step S308: convert the dialogue information into dialogue information text.

[0121] Step S309: perform word segmentation processing on the dialogue information text to obtain at least one text keyword.

[0122] Step S310: extract multiple candidate occupations from the internal occupation standard file according to at least one of the text keywords.

[0123] Step S311, determining the target risk level corresponding to each of the candidate occupations, and obtaining multiple target risk levels.

[0124] Step S312: recommending to the user an insurance product whose risk level is higher than or equal to the highest target risk level.

[0125] The specific implementation methods of each step in the embodiments of the present application refer to the specific implementation methods of each step in the above embodiments, which will not be repeated here.

[0126] See also Figure 4 , Figure 4 A schematic diagram of the functional modules of an insurance product recommendation device provided in this application.

[0127] like Figure 4 As shown, the insurance product recommendation device includes:

[0128] A spoken title generation unit 401 is used to obtain a professional classification standard file and internal professional information, and to generate a spoken title for a profession and a spoken title for an industry according to the professional classification standard file;

[0129] The occupation information supplement unit 402 is used to supplement the internal occupation information according to the oral title of the occupation and the oral title of the industry to obtain an internal occupation standard file;

[0130] A user occupation identification unit 403, used to obtain the conversation information between the user and the claims adjuster, and to identify the user's occupation from the conversation information according to the internal occupation standard file;

[0131] The insurance product recommendation unit 404 is used to recommend insurance products to the user according to the user's occupation.

[0132] Specifically, in the aspect of generating the spoken titles of occupations and the spoken titles of industries according to the occupation classification standard file, the spoken title generating unit 401 is specifically used for:

[0133] Extracting occupation descriptions from the occupation classification standard file;

[0134] The occupation description is used as a prompt word of a deep learning generative model, and the spoken name of the occupation and the spoken name of the industry are generated according to the deep learning generative model.

[0135] Specifically, in the aspect of supplementing the internal occupation information according to the oral title of the occupation and the oral title of the industry to obtain the internal occupation standard file, the occupation information supplementing unit 402 is specifically used to:

[0136] The name of the occupation for which the internal occupation information is obtained;

[0137] Establishing a mapping relationship between the occupation name and the colloquial name of the occupation and the colloquial name of the industry;

[0138] The internal occupation information is supplemented according to the mapping relationship to obtain an internal occupation standard document.

[0139] Specifically, in the aspect of identifying the user's occupation from the dialog information according to the internal occupation standard file, the user occupation identification unit 403 is specifically used to:

[0140] Converting the dialogue information into dialogue information text;

[0141] Performing word segmentation processing on the dialogue information text to obtain at least one text keyword;

[0142] Extracting a plurality of candidate occupations from the internal occupation standard file according to at least one of the text keywords;

[0143] Calculating the similarity between each candidate occupation and at least one of the text keywords;

[0144] Calculating scores of the plurality of candidate occupations according to the similarities;

[0145] The user's occupation is determined according to the scores of the plurality of candidate occupations.

[0146] Furthermore, the internal occupation standard file includes the spoken occupation name of each occupation, the standard occupation name corresponding to the spoken occupation name, and the industry to which it belongs; in calculating the similarity between each candidate occupation and the keyword, the user occupation identification unit 403 is specifically used to:

[0147] Perform word segmentation processing on each candidate occupation to obtain a first spoken occupation name keyword and a first industry keyword;

[0148] Determining a second spoken occupation name keyword and a second industry keyword from at least one text keyword;

[0149] Calculating the name similarity between the first spoken occupation name keyword and the second spoken occupation name keyword, and calculating the industry similarity between the first industry keyword and the second industry keyword;

[0150] The similarity between each of the candidate occupations and the keyword is determined according to the name similarity and the industry similarity.

[0151] Furthermore, the internal occupation standard file includes the risk level of each occupation. In determining the occupation of the user according to the scores of the plurality of candidate occupations, the user occupation identification unit 403 is specifically used to:

[0152] Determine the candidate occupation with the highest score as the user's occupation;

[0153] In the aspect of recommending insurance products to the user according to the user's occupation, the insurance product recommendation unit 404 is specifically used to:

[0154] Determine a target risk level corresponding to the user's occupation, and recommend an insurance product with a risk level higher than or equal to the target risk level to the user.

[0155] Furthermore, the insurance product recommendation unit 404 is specifically used to:

[0156] Determine a target risk level corresponding to each of the candidate occupations to obtain a plurality of target risk levels;

[0157] Recommending to the user an insurance product whose risk level is higher than or equal to the highest target risk level.

[0158] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0159] The above-mentioned device can be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0160] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a computer device provided in this application. The computer device may be a server.

[0161] See also Figure 5 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0162] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any insurance product recommendation method.

[0163] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0164] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any insurance product recommendation method.

[0165] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0166] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0167] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0168] Obtaining occupational classification standard documents and internal occupational information, and generating spoken titles of occupations and spoken titles of industries based on the occupational classification standard documents;

[0169] Supplement the internal occupation information according to the colloquial title of the occupation and the colloquial title of the industry to obtain an internal occupation standard document;

[0170] Acquiring conversation information between the user and the claims adjuster, and identifying the user's occupation from the conversation information according to the internal occupation standard file;

[0171] Recommend insurance products to the user based on the user's occupation.

[0172] In one embodiment, in the aspect of generating the spoken titles of occupations and the spoken titles of industries according to the occupation classification standard file, the processor is used to run a computer program stored in a memory to implement the following steps:

[0173] Extracting occupation descriptions from the occupation classification standard file;

[0174] The occupation description is used as a prompt word of a deep learning generative model, and the spoken name of the occupation and the spoken name of the industry are generated according to the deep learning generative model.

[0175] In one embodiment, in the aspect of supplementing the internal occupation information according to the spoken title of the occupation and the spoken title of the industry to obtain the internal occupation standard file, the processor is used to run a computer program stored in the memory to implement the following steps:

[0176] The name of the occupation for which the internal occupation information is obtained;

[0177] Establishing a mapping relationship between the occupation name and the colloquial name of the occupation and the colloquial name of the industry;

[0178] The internal occupation information is supplemented according to the mapping relationship to obtain an internal occupation standard document.

[0179] In one embodiment, in the aspect of identifying the occupation of the user from the dialog information according to the internal occupation standard file, the processor is used to run a computer program stored in the memory to implement the following steps:

[0180] Converting the dialogue information into dialogue information text;

[0181] Performing word segmentation processing on the dialogue information text to obtain at least one text keyword;

[0182] Extracting a plurality of candidate occupations from the internal occupation standard file according to at least one of the text keywords;

[0183] Calculating the similarity between each candidate occupation and at least one of the text keywords;

[0184] Calculating scores of the plurality of candidate occupations according to the similarities;

[0185] The user's occupation is determined according to the scores of the plurality of candidate occupations.

[0186] In one embodiment, the internal occupation standard file includes the spoken occupation name of each occupation, the standard occupation name corresponding to the spoken occupation name, and the industry to which it belongs; in the aspect of calculating the similarity between each candidate occupation and the keyword, the processor is used to run a computer program stored in the memory to implement the following steps:

[0187] Perform word segmentation processing on each candidate occupation to obtain a first spoken occupation name keyword and a first industry keyword;

[0188] Determining a second spoken occupation name keyword and a second industry keyword from at least one text keyword;

[0189] Calculating the name similarity between the first spoken occupation name keyword and the second spoken occupation name keyword, and calculating the industry similarity between the first industry keyword and the second industry keyword;

[0190] The similarity between each of the candidate occupations and the keyword is determined according to the name similarity and the industry similarity.

[0191] In one embodiment, the internal occupation standard file includes a risk level for each occupation, and in determining the occupation of the user according to the scores of the plurality of candidate occupations, the processor is configured to run a computer program stored in the memory to implement the following steps:

[0192] Determine the candidate occupation with the highest score as the user's occupation;

[0193] The recommending an insurance product to the user according to the user's occupation includes:

[0194] Determine a target risk level corresponding to the user's occupation, and recommend an insurance product with a risk level higher than or equal to the target risk level to the user.

[0195] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0196] Determine a target risk level corresponding to each of the candidate occupations to obtain a plurality of target risk levels;

[0197] Recommending to the user an insurance product whose risk level is higher than or equal to the highest target risk level.

[0198] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the insurance product recommendation methods provided in the embodiments of the present application.

[0199] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0200] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for recommending insurance products, characterized in that: The insurance product recommendation method comprises the following steps: Obtaining occupational classification standard documents and internal occupational information, and generating spoken titles of occupations and spoken titles of industries based on the occupational classification standard documents; Supplement the internal occupation information according to the colloquial title of the occupation and the colloquial title of the industry to obtain an internal occupation standard document; Acquiring conversation information between the user and the claims adjuster, and identifying the user's occupation from the conversation information according to the internal occupation standard file; Recommend insurance products to the user based on the user's occupation.

2. The insurance product recommendation method according to claim 1, characterized in that: The generating of the spoken titles of occupations and the spoken titles of industries according to the occupation classification standard file includes: Extracting occupation descriptions from the occupation classification standard file; The occupation description is used as a prompt word of a deep learning generative model, and the spoken name of the occupation and the spoken name of the industry are generated according to the deep learning generative model.

3. The insurance product recommendation method according to claim 1, characterized in that: The internal occupation information is supplemented according to the oral title of the occupation and the oral title of the industry to obtain an internal occupation standard document, including: The name of the occupation for which the internal occupation information is obtained; Establishing a mapping relationship between the occupation name and the colloquial name of the occupation and the colloquial name of the industry; The internal occupation information is supplemented according to the mapping relationship to obtain an internal occupation standard document.

4. The insurance product recommendation method according to claim 1, characterized in that: The step of identifying the user's occupation from the conversation information according to the internal occupation standard file includes: Converting the dialogue information into dialogue information text; Performing word segmentation processing on the dialogue information text to obtain at least one text keyword; Extracting a plurality of candidate occupations from the internal occupation standard file according to at least one of the text keywords; Calculating the similarity between each candidate occupation and at least one of the text keywords; Calculating scores of the plurality of candidate occupations according to the similarities; The user's occupation is determined according to the scores of the plurality of candidate occupations.

5. The insurance product recommendation method according to claim 4, characterized in that: The internal occupational standard file includes the colloquial occupational name of each occupation, the standard occupational name corresponding to the colloquial occupational name, and the industry to which it belongs; The calculating the similarity between each candidate occupation and the keyword includes: Perform word segmentation processing on each candidate occupation to obtain a first spoken occupation name keyword and a first industry keyword; Determining a second spoken occupation name keyword and a second industry keyword from at least one text keyword; Calculating the name similarity between the first spoken occupation name keyword and the second spoken occupation name keyword, and calculating the industry similarity between the first industry keyword and the second industry keyword; The similarity between each of the candidate occupations and the keyword is determined according to the name similarity and the industry similarity.

6. The insurance product recommendation method according to claim 4, characterized in that: The internal occupation standard file includes the risk level of each occupation, and the user's occupation is determined according to the scores of the plurality of candidate occupations, including: Determine the candidate occupation with the highest score as the user's occupation; The recommending an insurance product to the user according to the user's occupation includes: Determine a target risk level corresponding to the user's occupation, and recommend an insurance product with a risk level higher than or equal to the target risk level to the user.

7. The insurance product recommendation method according to claim 4, characterized in that: The insurance product recommendation method further includes: Determine a target risk level corresponding to each of the candidate occupations to obtain a plurality of target risk levels; Recommending to the user an insurance product whose risk level is higher than or equal to the highest target risk level.

8. An insurance product recommendation device, characterized in that: The insurance product recommendation device comprises: A spoken title generation unit, used for obtaining occupation classification standard files and internal occupation information, and generating spoken titles of occupations and spoken titles of industries according to the occupation classification standard files; An occupation information supplement unit, used to supplement the internal occupation information according to the oral title of the occupation and the oral title of the industry to obtain an internal occupation standard document; A user occupation identification unit, used to obtain the conversation information between the user and the claims adjuster, and to identify the user's occupation from the conversation information according to the internal occupation standard file; The insurance product recommendation unit is used to recommend insurance products to the user according to the user's occupation.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and an insurance product recommendation program stored in the memory and executable by the processor, wherein when the insurance product recommendation program is executed by the processor, the steps of the insurance product recommendation method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an insurance product recommendation program, wherein when the insurance product recommendation program is executed by a processor, the steps of the insurance product recommendation method according to any one of claims 1 to 7 are implemented.

Images