User insurance demand evaluation method and device, computer equipment and storage medium

Abstract

The invention discloses a user insurance demand evaluation method and device, computer equipment and a storage medium, belongs to the technical field of artificial intelligence, and is applied to an application scene of an insurance online system. According to the method, a user demand keyword scoring system and a timestamp scoring system are constructed, firstly, user demand keywords are extracted and quantified from historical data, the importance of the user demand keywords is evaluated in combination with the keyword scoring system, and meanwhile, the importance of time characteristics is evaluated by utilizing the timestamp scoring system based on the time characteristics of user dialogue logs; and then through multi-dimensional fusion analysis, a comprehensive user insurance demand score is calculated, and a suitable insurance product is accurately matched. According to the method and the device, the user insurance demand comprehensive evaluation is carried out by combining the keyword score and the time dimension score, the appropriate insurance product can be accurately matched, the seat is assisted to obtain the user demand insight in real time in the communication process, the marketing efficiency and the insurance policy transaction rate are improved, and thus the more intelligent and more efficient insurance telephone service is realized.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a method, apparatus, computer equipment and storage medium for evaluating user insurance needs. Background Art

[0002] In insurance phone service scenarios, fully understanding customer needs and providing real-time feedback to agents helps improve their policy closing rates. Generally, agents identify customer insurance needs in two ways. One is through the insurance company's big data statistical analysis capabilities. After an insurance company launches a new product, its demand assessment system identifies potential customers based on product characteristics. This list is then distributed to agents via the backend system, who then promote the product during the communication process. The other approach is to leverage the agent's business experience to gradually clarify customer needs for insurance products through conversations and provide targeted sales pitches.

[0003] However, both approaches have their own drawbacks. For example, leveraging insurance companies' big data statistical analysis capabilities relies heavily on the company's data and technical reserves, resulting in high costs and poor results. Furthermore, most big data statistical analysis solutions only consider a customer's single or localized insurance needs, failing to gain a holistic understanding of customer needs across various products, making it difficult to accurately understand user needs. Evaluation solutions that rely on agent experience are significantly impacted by the agent's professional skills. These skills vary widely across the agent community, with a shortage of excellent agents and high employee turnover, leading to a high number of inexperienced agents. Furthermore, given the large number of individual commercial insurance products and the rapid pace of updates, relying solely on manual experience can also lead to insufficient exploration of customer needs. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to propose a user insurance needs assessment method, device, computer equipment and storage medium to solve the technical problems existing in the above-mentioned existing insurance needs assessment solutions.

[0005] To solve the above technical problems, the present invention provides a method for assessing user insurance needs, which adopts the following technical solutions:

[0006] A method for assessing user insurance needs, comprising:

[0007] Obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system;

[0008] Obtain a preset timestamp sequence table, and construct a scoring system corresponding to the timestamp sequence table to obtain a second scoring system;

[0009] Receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library;

[0010] Identify user keywords in user conversation logs and obtain target keywords;

[0011] Scoring the target keywords based on the first scoring system to obtain a first demand score;

[0012] Identify the log segment where the target keyword is located, obtain the timestamp corresponding to the log segment, and obtain the target timestamp;

[0013] Scoring the target timestamp based on the second scoring system to obtain a second demand score;

[0014] A user insurance demand score is calculated based on the first demand score and the second demand score, and an insurance product suitable for the user is determined based on the user insurance demand score.

[0015] In order to solve the above technical problems, the embodiment of the present application further provides a user insurance demand assessment device, which adopts the following technical solution:

[0016] A user insurance demand assessment device, comprising:

[0017] The first system module is used to obtain pre-collected user demand keywords and construct a scoring system corresponding to the user demand keywords to obtain a first scoring system;

[0018] The second system module is used to obtain a preset timestamp sequence table and construct a scoring system corresponding to the timestamp sequence table to obtain a second scoring system;

[0019] The log acquisition module is used to receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library;

[0020] Keyword module, used to identify user keywords in user conversation logs and obtain target keywords;

[0021] A first scoring module, configured to score the target keyword based on a first scoring system to obtain a first demand score;

[0022] The timestamp module is used to identify the log segment where the target keyword is located, obtain the timestamp corresponding to the log segment, and obtain the target timestamp;

[0023] A second scoring module is used to score the target timestamp based on a second scoring system to obtain a second demand score;

[0024] The demand scoring module is used to calculate the user's insurance demand score based on the first demand score and the second demand score, and determine the insurance product suitable for the user based on the user's insurance demand score.

[0025] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0026] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the user insurance demand assessment method as described in any one of the above are implemented.

[0027] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0028] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the user insurance demand assessment method as described in any one of the above.

[0029] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0030] The present application discloses a method, device, computer equipment and storage medium for evaluating user insurance needs, which belongs to the field of artificial intelligence technology and is applied to the application scenario of insurance online systems. By constructing a user demand keyword scoring system and a timestamp scoring system, the present application can efficiently extract target keywords in the process of parsing user conversation logs, and conduct a comprehensive evaluation of user insurance needs in combination with the time dimension. Compared with the traditional method based on big data statistical analysis, the present application not only reduces the dependence on huge data reserves, but also analyzes user needs from a global level, improves accuracy, and avoids the limitation of focusing only on single points or local needs. At the same time, compared with the method that relies on the business experience of agents, the present application can provide standardized and automated demand assessments, reducing the problem of transaction rate fluctuations caused by uneven agent business levels. By comprehensively calculating the user insurance demand score, the present application can accurately match suitable insurance products, help agents obtain real-time insights into user needs during the communication process, improve marketing efficiency and policy transaction rates, and thus achieve more intelligent and efficient insurance telephone services. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] Figure 1 shows an exemplary system architecture diagram in which the present application can be applied;

[0033] Figure 2 A flowchart of an embodiment of a method for assessing user insurance needs according to the present application is shown;

[0034] Figure 3 A schematic structural diagram of an embodiment of a user insurance demand assessment device according to the present application is shown;

[0035] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0037] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0039] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0040] The user can use the terminal device 101 to interact with the server 103 via the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0041] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0042] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0043] It should be noted that the user insurance demand assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the user insurance demand assessment device is generally set in the server / terminal device.

[0044] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0045] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for assessing user insurance needs according to the present application. The method for assessing user insurance needs comprises the following steps:

[0046] S201, obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system;

[0047] Specifically, the collection of user demand keywords is based on a large number of historical user insurance-related conversations, insurance industry expert knowledge bases, and analysis of insurance product characteristics. User demand keywords include "medical insurance," "accident insurance," "pension protection," etc., and combined with user concerns, user demand keywords also include "insurance amount," "compensation ratio," "premium," etc. When constructing a scoring system, it is also necessary to consider the importance of keywords, the frequency of occurrence, and the emotional weight expressed by users. For example, if a user actively mentions words such as "purchase," "urgent need," and "high compensation," it may indicate a strong demand, and the score should be higher accordingly. The scoring system can adopt a weighted average, a machine learning model, or a scoring mechanism based on expert experience to ensure the rationality and accuracy of the evaluation system.

[0048] S202, obtaining a preset timestamp sequence table, and constructing a scoring system corresponding to the timestamp sequence table to obtain a second scoring system;

[0049] Specifically, the timestamp sequence table is established based on the user's historical interaction time points, which can reflect the changing trend of user needs over time. Different time periods may represent different stages of user insurance needs. For example, users may pay attention to accident insurance before and after major holidays, and pay attention to medical insurance after a health check-up. The construction of the scoring system needs to model the impact of time factors on user needs. For example, users who have frequently inquired about relevant insurance information recently may have more urgent needs and corresponding time weight scores are higher; while users with longer time spans and intermittent inquiries may have relatively low needs and lower scores. In addition, the timestamp scoring system can be combined with user behavior patterns. For example, more consultations at night may represent temporary needs, while continuous attention to the same type of insurance for several months may represent deep needs, thereby improving the accuracy of the assessment.

[0050] S203, receiving a user's insurance demand assessment instruction and obtaining the user's conversation log from a preset conversation log library;

[0051] Specifically, when the system receives a user's insurance needs assessment instruction, it extracts historical conversation records related to the user from the conversation log library. The conversation log library contains the user's interactions with customer service, intelligent assistants, insurance agents, etc., and records information such as the user's consultation content, number of questions asked, and concerns about insurance plans. These logs can be stored in a structured manner, such as a database table, or in an unstructured manner, such as text files or voice transcriptions. During the data extraction process, natural language processing (NLP) technology can be used to perform word segmentation, keyword extraction, and sentiment analysis on the conversation content to subsequently identify the user's true needs. Conversation logs can be obtained through full extraction or optimized through methods such as keyword matching and time range filtering to ensure the efficiency and accuracy of data extraction.

[0052] S204, identifying user keywords in the user conversation log to obtain target keywords;

[0053] Specifically, NLP (natural language processing) technology is usually used to extract keywords related to insurance needs from the user's historical conversation records. For example, the user may mention "medical insurance coverage" and "pension insurance collection method" in the conversation. The system needs to extract target keywords such as "medical insurance", "coverage", "pension insurance", and "collection method". Keyword extraction methods can include TF-IDF (term frequency-inverse document frequency) algorithm, BERT pre-training model or LSTM and other deep learning methods to ensure the accuracy of keyword extraction. In addition, for user conversations expressed in colloquial language, semantic analysis technology can be used to identify the user's true intention. For example, if a user asks "If I get sick, can the insurance compensate me?", he may actually be concerned about the scope of medical insurance compensation rather than the type of insurance. Through keyword extraction, the target keyword obtained should be "compensation".

[0054] S205, scoring the target keyword based on the first scoring system to obtain a first demand score;

[0055] Specifically, after obtaining the target keywords, the system will score these keywords according to the first scoring system to measure the user's insurance demand. The first scoring basis mainly includes the importance of the keywords, the frequency of user mentions, contextual relevance, and emotional tendencies. For example, words such as "urgent", "immediately", and "high amount" may indicate the urgency of the user's needs and should be given a higher score; while "think about it" and "talk about it later" may represent weaker needs and correspond to lower scores. In addition, the scoring process can also be combined with the user's past behavior data, such as whether the user has consulted the same insurance product multiple times, or whether the user has browsed, compared, and performed other operations on the insurance platform. If the user mentions keywords such as "accident insurance" and "high amount protection" multiple times, and frequently pays attention to related products in the historical records, the first demand score will be increased accordingly to ensure that the system can accurately assess the intensity of the user's insurance needs.

[0056] S206, identifying the log segment where the target keyword is located, and obtaining the timestamp corresponding to the log segment to obtain the target timestamp;

[0057] Specifically, the system determines the specific time points at which target keywords appear, allowing for further time-sensitive evaluation of user needs. First, the system searches the user's conversation logs, locates the complete conversation segments containing the target keywords, and records the timestamps of these conversations. For example, if a user inquires about "critical illness insurance" and "insurance claims process" on March 1 and March 10, 2024, respectively, the system extracts the specific time information for these conversations and forms a time series. Log segments with time nodes closer to the current system time are given a higher weight when scoring. Timestamps are typically obtained using the time field in system logs or based on conversation time annotations from speech-to-text conversion. Once timestamps are obtained, the system can also analyze user behavior patterns, such as whether the user frequently inquires about the same question within a short period of time or whether interest in a particular type of insurance suddenly emerges after a specific event (such as a health checkup, marriage, or childbirth), to more accurately analyze the time sensitivity of user needs.

[0058] S207, scoring the target timestamp based on the second scoring system to obtain a second demand score;

[0059] Specifically, after obtaining the target timestamp, the system will score it according to the second scoring system to measure the time urgency and duration of the user's needs. The main basis for the time score includes the time interval and frequency of user consultations, the time of the most recent consultation, etc. For example, if a user mentions the same type of insurance (such as medical insurance) multiple times in a short period of time, it means that the need is more urgent, and the corresponding time score is higher; on the other hand, if the user only consulted once by chance a long time ago, the time score is lower. The scoring model can use a linear decay function, that is, the score gradually decreases as the time interval increases. In addition, it can also be weighted in combination with the user's life cycle events. For example, users who consult about insurance at key time points such as marriage, childbirth, and home purchase may have more practical needs, and the time score should be increased accordingly. Combining these factors, the second demand score can more accurately reflect the actual urgency of the user's need for insurance.

[0060] S208 , calculating the user's insurance demand score based on the first demand score and the second demand score, and determining an insurance product suitable for the user based on the user's insurance demand score.

[0061] Specifically, the final user insurance demand score is calculated comprehensively based on the first demand score (keyword score) and the second demand score (time score). The calculation method can adopt weighted average, logistic regression, decision tree and other models to ensure the scientific nature of the scoring results. For example, if the user frequently mentions keywords such as "high insurance amount" and "accident insurance" in the conversation (the first score is high), and has consulted related questions many times in a short period of time recently (the second score is high), the comprehensive demand score will be higher. Based on this score, the system can match insurance products that best meet the user's needs, such as high-insurance accident insurance, short-term health insurance, etc. In addition, the user's historical purchasing behavior, financial status, health status and other factors can be combined to further optimize the insurance recommendation plan and improve the accuracy of the match, thereby improving the user experience and insurance conversion rate.

[0062] In the above embodiment, this application, by constructing a user demand keyword scoring system and a timestamp scoring system, can efficiently extract target keywords in the process of parsing user conversation logs, and conduct a comprehensive assessment of user insurance needs in combination with the time dimension. Compared with the traditional method based on big data statistical analysis, this application not only reduces the dependence on huge data reserves, but also analyzes user needs from a global level, improves accuracy, and avoids the limitation of focusing only on single points or local needs. At the same time, compared with the method that relies on the business experience of agents, this application can provide standardized and automated demand assessments, reducing the problem of transaction rate fluctuations caused by uneven agent business levels. This application can accurately match suitable insurance products by comprehensively calculating user insurance demand scores, helping agents to obtain real-time insights into user needs during the communication process, improve marketing efficiency and policy transaction rates, and thus achieve more intelligent and efficient insurance telephone services.

[0063] Furthermore, the steps of obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system specifically include:

[0064] Obtain historical user conversation data, and identify user keywords from the historical user conversation data to obtain historical keywords;

[0065] Performing semantic recognition on historical keywords and classifying the historical keywords based on the semantic recognition results, wherein the categories of historical keywords include demand keywords and non-demand keywords;

[0066] The classified historical keywords are divided into levels to obtain the hierarchical sequence of demand keywords and the hierarchical sequence of non-demand keywords;

[0067] According to a preset first scoring criterion, the demand keyword hierarchical sequence and the non-demand keyword hierarchical sequence are scored and divided to generate a first scoring system.

[0068] In this embodiment, the process of obtaining pre-collected user demand keywords and constructing the first scoring system first requires extracting user keywords from historical user conversation data. This process typically relies on natural language processing (NLP) techniques, including text segmentation, part-of-speech tagging, and entity recognition, to ensure the accuracy of keyword extraction. Extracted keywords include keywords related to insurance business entities, such as "health insurance," "high compensation," and "short-term protection." These keywords represent user concerns regarding insurance needs. Next, the system performs semantic recognition on these keywords, analyzing their contextual relationships using deep learning models (such as BERT and Word2Vec) to distinguish demand keywords (such as "medical insurance" and "insurance claims") from non-demand keywords (such as "thank you," "goodbye," and "no need"). The classified historical keywords are further hierarchically divided, primarily based on the conceptual hierarchy of the terms and industry knowledge base. For example, "health insurance" belongs to the broad category of "medical insurance," while "cancer insurance" is a subcategory of "health insurance." Finally, based on the preset first scoring criteria, demand keywords and non-demand keywords at different levels are scored. For example, keywords that appear frequently and are strongly related to insurance needs are given higher scores, while keywords that are mentioned occasionally or have ambiguous semantics are given lower scores. Ultimately, the first scoring system for evaluating user needs is generated.

[0069] Through these steps, the system can accurately identify users' insurance needs and establish a scientific scoring system to improve the accuracy of needs assessment. Furthermore, based on hierarchical scoring criteria, the system can provide personalized insurance recommendations, enhance user experience, and strengthen the compatibility of insurance products.

[0070] Furthermore, the step of scoring and dividing the demand keyword hierarchy sequence and the non-demand keyword hierarchy sequence according to the preset first scoring criterion to generate a first scoring system specifically includes:

[0071] Configure the word frequency weight standard, semantic weight standard, user behavior weight standard, and level weight standard to obtain the first scoring criterion;

[0072] Based on the first scoring criterion, the word frequency weight, semantic weight, user behavior weight and hierarchical weight of the demand keywords and non-demand keywords in the historical keywords are calculated respectively;

[0073] The calculated word frequency weight, semantic weight, user behavior weight and hierarchical weight are scored and normalized to obtain the first scoring system.

[0074] In this embodiment, to ensure a more accurate scoring system for user demand keywords, a first scoring criterion must be configured. This criterion includes four key weighting criteria: word frequency weighting, semantic weighting, user behavior weighting, and hierarchical weighting. The word frequency weighting measures the frequency of a keyword's appearance in historical conversation data. A higher frequency indicates greater importance and is assigned a higher weight. The semantic weighting uses natural language processing techniques (such as BERT and Word2Vec) to analyze the contextual relevance of keywords to ensure that the keywords' actual meanings are consistent with the scope of insurance needs. The user behavior weighting combines user interaction behaviors, such as clicks, dwell time, and number of inquiries, to determine the user's actual interest in the keyword. The hierarchical weighting, based on the hierarchical structure of keywords, ensures that core categories (such as "medical insurance") are given more appropriate weights than specific subcategories (such as "cancer insurance"). The system then calculates the weights for demand keywords and non-demand keywords based on the first scoring criterion and normalizes the results. This allows weight scores from different sources to be compared and weighted within the same scoring system, ultimately forming a scientific and reasonable first scoring system.

[0075] For example, a user mentioned keywords such as "critical illness insurance," "high compensation," and "cancer protection" repeatedly in their conversation logs over the past month. They also inquired about topics like "insurance claims process" and "purchase channels." The system first analyzes these keywords and calculates frequency weights. For example, "critical illness insurance" appears five times in the user's conversations and is therefore assigned a higher frequency weight, while "purchase channels" appears only once and has a lower frequency weight. Next, the semantic weighting criterion analyzes the context of these keywords. For example, "high compensation" is closely related to insurance product protection and therefore has a higher semantic weight, while "purchase channels," while related to insurance, is not a core need and therefore has a lower semantic weight. The system then considers user behavior weighting. If the user repeatedly browses the critical illness insurance page on the insurance platform or repeatedly confirms relevant information during conversations, "critical illness insurance" will be assigned a higher user behavior weight. Finally, based on hierarchical weighting, "critical illness insurance" falls under the "health insurance" category and therefore has a higher hierarchical weight, while "claims process" is considered additional information and has a lower hierarchical weight. Finally, the system normalizes the weights of each item, so that "critical illness insurance" obtains a higher demand score, thereby improving the effect of accurate insurance recommendations.

[0076] Through the above steps, the system can comprehensively evaluate user keywords based on multi-dimensional factors, thereby more comprehensively reflecting the user's insurance needs, optimizing the demand scoring system, and improving the accuracy of recommendations for personalized insurance products.

[0077] Furthermore, the steps of obtaining a preset timestamp sequence table and constructing a scoring system corresponding to the timestamp sequence table to obtain a second scoring system specifically include:

[0078] Arrange the timestamp sequence according to the preset time interval to obtain a timestamp sequence table;

[0079] According to the preset second scoring criteria, each time stamp in the time stamp sequence table is scored and divided to generate a second scoring system.

[0080] In this embodiment, to more accurately assess the changing trends in a user's insurance needs, the system first arranges a timestamp sequence according to preset time intervals to form a timestamp sequence table. The time intervals can be set based on different business needs, such as by day, week, or month, to capture how user needs change over time. For example, if a user has inquired about health insurance multiple times in the past week, the system can organize these timestamps by day or hour to more clearly demonstrate the evolution of the user's needs. The system then scores each timestamp in the timestamp sequence table based on a second scoring criterion. Key scoring criteria include temporal proximity (inquiries closer to the current time receive a higher weight), query frequency (higher frequency in a short period of time receives a higher score), and persistence (long-term, stable attention receives a higher score). For example, a user who inquired about critical illness insurance three times in the last three days should receive a higher time score than a user who only inquired once three months ago. Finally, by normalizing the scores of all timestamps, the system generates a second scoring system to more accurately measure the urgency and persistence of a user's insurance needs.

[0081] Through the above steps, the system can integrate the user's time behavior characteristics, accurately judge the immediacy and long-term nature of needs, improve the accuracy of insurance demand assessment, and thus optimize personalized insurance product recommendations.

[0082] Furthermore, the steps of scoring and dividing each time stamp in the time stamp sequence table according to a preset second scoring criterion to generate a second scoring system specifically include:

[0083] Configure the time distribution weight standard, activity weight standard, and time decay weight standard to obtain the second scoring criterion;

[0084] Calculate the time distribution weight, activity weight and time decay weight of each timestamp in the timestamp sequence table based on the second scoring criterion;

[0085] The calculated time distribution weight, activity weight, and time decay weight are scored and normalized to obtain the second scoring system.

[0086] In this embodiment, to more accurately assess the urgency of a user's insurance needs, the system first configures a second scoring criterion, which includes a time distribution weighting criterion, an activity weighting criterion, and a time decay weighting criterion. The time distribution weighting criterion is used to measure the distribution of user query behavior along the time axis, such as whether there are periodic peaks (such as inquiring about insurance after monthly salary payment) or concentrated inquiries (such as users repeatedly inquiring about insurance within a short period of time). The activity weighting criterion mainly analyzes the frequency of user interactions within a certain time range. Users who frequently inquire about insurance receive higher scores, indicating a stronger need. The time decay weighting criterion is used to control the impact of time on the need score. Typically, an exponential decay function is used, which makes more recent inquiries more influential and reduces the influence of more recent inquiries. For example, if a user inquires about health insurance multiple times in the past three days, their time decay weight is higher than that of a user who only inquired once six months ago. Next, based on these weighting criteria, the system calculates the corresponding weights for each timestamp in the timestamp sequence table and performs normalization processing to ensure that data from different sources can be compared under a unified scoring system. The resulting second scoring system can effectively quantify the time sensitivity of user needs and assist in insurance product recommendations.

[0087] Through the above steps, the system can comprehensively analyze the user's query time characteristics, accurately identify the urgency of the needs, ensure that insurance recommendations are more personalized, and improve user experience and product matching.

[0088] Furthermore, the step of scoring the target keyword based on the first scoring system to obtain a first demand score specifically includes:

[0089] Obtain the user's initial demand rating;

[0090] Identify demand keywords and non-demand keywords among target keywords;

[0091] Scoring the demand keywords in the target keywords based on the first scoring system to obtain a first score, wherein the first score is a positive score;

[0092] Scoring the non-demand keywords in the target keywords based on the first scoring system to obtain a second score, wherein the second score is a positive score;

[0093] The sum of the initial demand score, the first score, and the second score is calculated to obtain the first demand score.

[0094] In this embodiment, to accurately assess the strength of a user's insurance need, the system first obtains the user's initial need score. This score can be determined based on the user's historical interactions, consultation history, and past insurance purchases, serving as the basis for need assessment. Next, the system analyzes target keywords in the user's conversation log to identify need keywords and non-need keywords. For example, in the sentence "I was in a car accident," "I want to learn about the specific coverage of critical illness insurance," "critical illness insurance" and "want to learn" are need keywords, while "car accident" is a non-need keyword. The system then scores the need keywords based on a first scoring system, generating a first score. Need keywords typically receive higher scores because the first score directly reflects the user's insurance need. Simultaneously, the system also scores non-need keywords, generating a second score. While non-need keywords don't directly express need, they can provide semantic context. For example, words like "compare" and "recommend" may reflect a user's purchase intention. Finally, the system calculates the sum of the initial need score, the first score, and the second score to obtain the first need score, which provides a more comprehensive measure of the user's insurance need.

[0095] Through the above steps, the system can effectively integrate users' historical demand scores with real-time conversation analysis to ensure more accurate demand assessment, while reducing the interference of semantic noise and improving the accuracy of insurance product matching and user satisfaction.

[0096] Furthermore, after the step of calculating the user's insurance demand score based on the first demand score and the second demand score, the method further includes:

[0097] Obtain the user's initial insurance demand type to obtain the first insurance demand type;

[0098] Determining the insurance demand type corresponding to the user's insurance demand score based on a preset demand type benchmark to obtain a second insurance demand type;

[0099] Determining whether the first insurance demand type and the second insurance demand type are the same;

[0100] If the first insurance requirement type is different from the second insurance requirement type, the user's insurance requirement type is updated to the second insurance requirement type.

[0101] In this embodiment, to ensure more accurate classification of a user's insurance needs, the system further analyzes the user's insurance need type after calculating the user's insurance need score. First, the system obtains the user's initial insurance need type (first insurance need type). This type can be derived from the user's historical purchase history, past inquiries, or proactively selected insurance preferences. For example, if a user has primarily focused on health insurance in the past, the system might set their initial insurance need type to "health insurance." Then, based on a preset need type benchmark, the system maps the calculated user's insurance need score to the corresponding insurance need type (second insurance need type). This process typically relies on machine learning or rule-matching algorithms. For example, if a user has recently frequently inquired about topics such as "life insurance" and "coverage period" and has a high need score, the system might identify their current need type as "life insurance." Next, the system determines whether the first and second insurance need types are consistent. If they are different, this indicates that the user's insurance needs have changed, such as from health insurance to life insurance. At this point, the system automatically updates the user's insurance need type to reflect the latest demand trends. This dynamic adjustment mechanism helps ensure the accuracy of insurance recommendations and prevents users from receiving inappropriate insurance product recommendations even after their needs have changed.

[0102] Through the above steps, the system can intelligently identify changes in users' insurance needs, ensure dynamic updates of users' insurance demand types, and make recommended insurance products more in line with users' current needs, thereby improving user experience and purchase conversion rates.

[0103] In the above embodiment, the present application discloses a method for evaluating user insurance needs, which belongs to the field of artificial intelligence technology and is applied to the application scenario of insurance online systems. By constructing a user demand keyword scoring system and a timestamp scoring system, the present application can efficiently extract target keywords in the process of parsing user conversation logs, and conduct a comprehensive evaluation of user insurance needs in combination with the time dimension. Compared with the traditional method based on big data statistical analysis, the present application not only reduces the dependence on huge data reserves, but also analyzes user needs from a global level, improves accuracy, and avoids the limitation of focusing only on single points or local needs. At the same time, compared with the method that relies on the business experience of agents, the present application can provide standardized and automated demand assessments, reducing the problem of transaction rate fluctuations caused by uneven agent business levels. By comprehensively calculating the user's insurance demand score, the present application can accurately match suitable insurance products, help agents obtain real-time insights into user needs during the communication process, improve marketing efficiency and policy transaction rates, and thus achieve more intelligent and efficient insurance telephone services.

[0104] In this embodiment, the electronic device (eg Figure 1The server shown in FIG. 1 may receive instructions or obtain data via a wired connection or a wireless connection. It should be noted that the wireless connection may include, but is not limited to, 3G / 4G connection, Wi-Fi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (Ultra Wide Band) connection, and other wireless connection methods currently known or to be developed in the future.

[0105] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned user demand keyword information, the above-mentioned user demand keyword information can also be stored in a node of a blockchain.

[0106] The blockchain referred to in this application refers to a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (to prevent counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0107] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0108] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0109] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0110] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0111] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a user insurance demand assessment device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0112] like Figure 3 As shown, the user insurance demand assessment device 300 of this embodiment includes:

[0113] The first system module 301 is used to obtain pre-collected user demand keywords and construct a scoring system corresponding to the user demand keywords to obtain a first scoring system;

[0114] The second system module 302 is used to obtain a preset timestamp sequence table and construct a scoring system corresponding to the timestamp sequence table to obtain a second scoring system;

[0115] The log acquisition module 303 is used to receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library;

[0116] Keyword module 304, used to identify user keywords in user conversation logs and obtain target keywords;

[0117] A first scoring module 305 is configured to score the target keyword based on a first scoring system to obtain a first demand score;

[0118] The timestamp module 306 is used to identify the log segment where the target keyword is located and obtain the timestamp corresponding to the log segment to obtain the target timestamp;

[0119] A second scoring module 307 is configured to score the target timestamp based on a second scoring system to obtain a second demand score;

[0120] The demand scoring module 308 is used to calculate the user's insurance demand score based on the first demand score and the second demand score, and determine an insurance product suitable for the user based on the user's insurance demand score.

[0121] Furthermore, the first system module 301 specifically includes:

[0122] A keyword recognition unit is used to obtain historical user conversation data and identify user keywords from the historical user conversation data to obtain historical keywords;

[0123] a semantic recognition unit, configured to perform semantic recognition on historical keywords and classify the historical keywords based on the semantic recognition results, wherein the categories of historical keywords include demand keywords and non-demand keywords;

[0124] A hierarchical division unit is used to perform hierarchical division on the classified historical keywords to obtain a hierarchical sequence of demand keywords and a hierarchical sequence of non-demand keywords;

[0125] The first scoring division unit is used to score and divide the demand keyword hierarchical sequence and the non-demand keyword hierarchical sequence according to a preset first scoring criterion to generate a first scoring system.

[0126] Furthermore, the first scoring division unit specifically includes:

[0127] The first standard configuration subunit is used to configure the word frequency weight standard, the semantic weight standard, the user behavior weight standard and the level weight standard to obtain the first scoring criterion;

[0128] A first weight calculation subunit is used to calculate the word frequency weight, semantic weight, user behavior weight and hierarchical weight of the demand keywords and non-demand keywords in the historical user demand keywords based on the first scoring criterion;

[0129] The first score normalization subunit is used to perform score normalization on the calculated word frequency weight, semantic weight, user behavior weight and hierarchical weight to obtain a first score system.

[0130] Furthermore, the second system module 302 specifically includes:

[0131] A timestamp arrangement unit, configured to arrange a timestamp sequence according to a preset time interval to obtain a timestamp sequence table;

[0132] The second scoring division unit is used to perform scoring division on each time stamp in the time stamp sequence table according to a preset second scoring criterion to generate a second scoring system.

[0133] Furthermore, the second scoring division unit specifically includes:

[0134] The second standard configuration subunit is used to configure the time distribution weight standard, the activity weight standard and the time decay weight standard to obtain the second scoring criterion;

[0135] A second weight calculation subunit is used to calculate the time distribution weight, activity weight and time decay weight of each time stamp in the time stamp sequence table based on the second scoring criterion;

[0136] The second scoring normalization subunit is used to normalize the calculated time distribution weight, activity weight and time decay weight to obtain a second scoring system.

[0137] Furthermore, the first scoring module 305 specifically includes:

[0138] Initial scoring unit, used to obtain the user's initial demand score;

[0139] A demand identification unit, used to identify demand keywords and non-demand keywords in target keywords;

[0140] A first scoring unit is configured to score the demand keywords in the target keywords based on a first scoring system to obtain a first score, wherein the first score is a positive score;

[0141] A second scoring unit is configured to score the non-demand keywords in the target keywords based on the first scoring system to obtain a second score, wherein the second score is a positive score;

[0142] The scoring calculation unit is used to calculate the sum of the initial demand score, the first score and the second score to obtain the first demand score.

[0143] Furthermore, the user insurance demand assessment device 300 further includes:

[0144] A first demand module, configured to obtain the user's initial insurance demand type and obtain a first insurance demand type;

[0145] A second demand module is used to determine the insurance demand type corresponding to the user's insurance demand score based on a preset demand type benchmark to obtain a second insurance demand type;

[0146] A demand determination module, configured to determine whether the first insurance demand type is the same as the second insurance demand type;

[0147] The demand type updating module is configured to update the user's insurance demand type to the second insurance demand type if the first insurance demand type is different from the second insurance demand type.

[0148] In the above embodiment, the present application discloses a user insurance demand assessment device, which belongs to the field of artificial intelligence technology and is applied to the application scenario of the insurance online system. By constructing a user demand keyword scoring system and a timestamp scoring system, the present application can efficiently extract target keywords in the process of parsing user conversation logs, and conduct a comprehensive assessment of user insurance needs in combination with the time dimension. Compared with the traditional method based on big data statistical analysis, the present application not only reduces the dependence on huge data reserves, but also analyzes user needs from a global level, improves accuracy, and avoids the limitation of focusing only on single points or local needs. At the same time, compared with the method that relies on the business experience of agents, the present application can provide standardized and automated demand assessments, reducing the problem of transaction rate fluctuations caused by uneven agent business levels. By comprehensively calculating the user's insurance demand score, the present application can accurately match suitable insurance products, help agents obtain real-time insights into user needs during the communication process, improve marketing efficiency and policy transaction rates, and thus achieve more intelligent and efficient insurance telephone services.

[0149] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0150] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0151] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0152] The memory 41 includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, an optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. Of course, the memory 41 may also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the computer-readable instructions of the method. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0153] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for executing the user insurance needs assessment method.

[0154] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0155] The present application also provides an embodiment, namely, a computer device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the above-mentioned user insurance demand assessment method are implemented, namely, the following steps are implemented:

[0156] A method for assessing user insurance needs, comprising:

[0157] Obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system;

[0158] Obtain a preset timestamp sequence table, and construct a scoring system corresponding to the timestamp sequence table to obtain a second scoring system;

[0159] Receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library;

[0160] Identify user keywords in user conversation logs and obtain target keywords;

[0161] Scoring the target keywords based on the first scoring system to obtain a first demand score;

[0162] Identify the log segment where the target keyword is located, obtain the timestamp corresponding to the log segment, and obtain the target timestamp;

[0163] Scoring the target timestamp based on the second scoring system to obtain a second demand score;

[0164] A user insurance demand score is calculated based on the first demand score and the second demand score, and an insurance product suitable for the user is determined based on the user insurance demand score.

[0165] The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions. The computer-readable instructions can be executed by at least one processor to cause the at least one processor to perform the steps of the above-mentioned user insurance needs assessment method, namely, to achieve:

[0166] A method for assessing user insurance needs, comprising:

[0167] Obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system;

[0168] Obtain a preset timestamp sequence table, and construct a scoring system corresponding to the timestamp sequence table to obtain a second scoring system;

[0169] Receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library;

[0170] Identify user keywords in user conversation logs and obtain target keywords;

[0171] Scoring the target keywords based on the first scoring system to obtain a first demand score;

[0172] Identify the log segment where the target keyword is located, obtain the timestamp corresponding to the log segment, and obtain the target timestamp;

[0173] Scoring the target timestamp based on the second scoring system to obtain a second demand score;

[0174] A user insurance demand score is calculated based on the first demand score and the second demand score, and an insurance product suitable for the user is determined based on the user insurance demand score.

[0175] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0176] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0177] It should be noted that the non-Company's software tools or components appearing in the various embodiments of this application are merely examples and do not represent actual use.

[0178] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A method for assessing user insurance needs, characterized in that: include: Obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system; Obtaining a preset timestamp sequence table, and constructing a scoring system corresponding to the timestamp sequence table to obtain a second scoring system; Receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library; Identifying user keywords in the user conversation log to obtain target keywords; Scoring the target keyword based on the first scoring system to obtain a first demand score; Identify the log segment where the target keyword is located, and obtain the timestamp corresponding to the log segment to obtain the target timestamp; Scoring the target timestamp based on the second scoring system to obtain a second demand score; A user insurance demand score is calculated based on the first demand score and the second demand score, and an insurance product suitable for the user is determined based on the user insurance demand score.

2. The user insurance demand assessment method according to claim 1, characterized in that: The step of obtaining pre-collected user demand keywords and constructing a scoring system corresponding to the user demand keywords to obtain a first scoring system specifically includes: Acquire historical user conversation data, and identify user keywords from the historical user conversation data to obtain historical keywords; Performing semantic recognition on the historical keywords, and classifying the historical keywords based on the semantic recognition results, wherein the categories of the historical keywords include demand keywords and non-demand keywords; The classified historical keywords are divided into levels to obtain the hierarchical sequence of demand keywords and the hierarchical sequence of non-demand keywords; According to a preset first scoring criterion, the demand keyword hierarchical sequence and the non-demand keyword hierarchical sequence are scored and divided to generate the first scoring system.

3. The user insurance demand assessment method according to claim 2, characterized in that: The step of scoring and dividing the demand keyword hierarchical sequence and the non-demand keyword hierarchical sequence according to the preset first scoring criteria to generate the first scoring system specifically includes: Configuring a word frequency weight standard, a semantic weight standard, a user behavior weight standard, and a hierarchical weight standard to obtain the first scoring criteria; Based on the first scoring criteria, the word frequency weight, semantic weight, user behavior weight and hierarchical weight of the demand keywords and non-demand keywords in the historical keywords are respectively calculated; The calculated word frequency weight, the semantic weight, the user behavior weight, and the hierarchical weight are scored and normalized to obtain the first scoring system.

4. The user insurance demand assessment method according to claim 1, characterized in that: The step of obtaining a preset timestamp sequence table, constructing a scoring system corresponding to the timestamp sequence table, and obtaining a second scoring system specifically includes: Arranging a timestamp sequence according to a preset time interval to obtain the timestamp sequence table; According to a preset second scoring criterion, each time stamp in the time stamp sequence table is scored and divided to generate the second scoring system.

5. The user insurance demand assessment method according to claim 4, characterized in that: The step of scoring and dividing each time stamp in the time stamp sequence table according to a preset second scoring criterion to generate the second scoring system specifically includes: Configuring a time distribution weight standard, an activity weight standard, and a time decay weight standard to obtain the second scoring criterion; Calculate the time distribution weight, activity weight and time decay weight of each time stamp in the time stamp sequence table based on the second scoring criterion; The calculated time distribution weight, activity weight, and time decay weight are scored and normalized to obtain the second scoring system.

6. The user insurance demand assessment method according to claim 1, characterized in that: The step of scoring the target keyword based on the first scoring system to obtain a first demand score specifically includes: Obtain the user's initial demand rating; Identify demand keywords and non-demand keywords among the target keywords; Scoring the demand keywords in the target keywords based on the first scoring system to obtain a first score, wherein the first score is a positive score; Scoring the non-demand keywords in the target keywords based on the first scoring system to obtain a second score, wherein the second score is a positive score; The sum of the initial demand score, the first score, and the second score is calculated to obtain the first demand score.

7. The user insurance demand assessment method according to claim 1, characterized in that: After the step of calculating the user's insurance demand score based on the first demand score and the second demand score, the method further includes: Obtain the user's initial insurance demand type to obtain the first insurance demand type; Determining the insurance demand type corresponding to the user's insurance demand score based on a preset demand type benchmark to obtain a second insurance demand type; determining whether the first insurance demand type is the same as the second insurance demand type; If the first insurance requirement type is different from the second insurance requirement type, the user's insurance requirement type is updated to the second insurance requirement type.

8. A user insurance demand assessment device, characterized in that: include: The first system module is used to obtain pre-collected user demand keywords and construct a scoring system corresponding to the user demand keywords to obtain a first scoring system; The second system module is used to obtain a preset timestamp sequence table and construct a scoring system corresponding to the timestamp sequence table to obtain a second scoring system; The log acquisition module is used to receive the user's insurance demand assessment instruction and obtain the user's conversation log from the preset conversation log library; A keyword module, configured to identify user keywords in the user conversation log and obtain target keywords; A first scoring module, configured to score the target keyword based on the first scoring system to obtain a first demand score; A timestamp module is used to identify the log segment where the target keyword is located, and obtain the timestamp corresponding to the log segment to obtain the target timestamp; a second scoring module, configured to score the target timestamp based on the second scoring system to obtain a second demand score; A demand scoring module is used to calculate a user insurance demand score based on the first demand score and the second demand score, and to determine an insurance product suitable for the user based on the user insurance demand score.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the user insurance demand assessment method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the user insurance demand assessment method according to any one of claims 1 to 7.

Images