Order recording method, device and equipment based on chat robot and storage medium

Abstract

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses an insurance policy recording method based on a chat robot, and the method comprises the steps: obtaining an insurance policy application document, carrying out the analysis, recognition and segmentation of text contents, and extracting insurance element fields; and analyzing the insurance element field based on the necessary recording information base through the chat robot, and judging whether missing necessary recording information data exists or not. If omission is found, the chat robot guides the user to supplement the data. And after the user supplements the data, obtaining target necessarily recorded data, and recording the extracted insurance element fields and the target necessarily recorded information into an insurance issuing system together. According to the method, the insurance policy application document is automatically analyzed, and the insurance element fields are extracted, so that the low efficiency and the error rate of manual operation are avoided, the document recording efficiency is improved, and the problem of human errors is reduced. And meanwhile, the user is intelligently guided to supplement missing information, so that the user operation is simplified, the input burden of the user is reduced, efficient information complementation is realized, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence technology and financial technology, and in particular to a chatbot-based order recording method, device, equipment and storage medium. Background Art

[0002] In the insurance industry's policy entry process, with the continuous increase in business volume and the diversification of insurance products, the traditional policy entry method faces many challenges. Existing technologies mainly rely on manual entry and manual verification, which has obvious limitations, especially in the information extraction and data verification stages.

[0003] The current policy entry system requires operators to manually extract key information (such as customer information, insured amount, insurance period, etc.) from the policy application documents. This manual operation process is time-consuming and labor-intensive, especially when processing a large number of policy applications, which is prone to delays and cannot meet the needs of rapid business processing.

[0004] The traditional way of recording insurance policies relies on manual verification, requiring operators to check each key information field one by one to ensure that the data in the insurance policy application document is complete and accurate. This process is not only time-consuming, but also prone to human negligence, resulting in omissions of required information or information entry errors, affecting the accuracy of the insurance policy and subsequent business processes.

[0005] The existing system lacks an intelligent guidance mechanism in the process of completing information. Users often need to rely on customer service staff to manually fill in the missing data in the insurance policy application, resulting in a cumbersome process and poor customer experience.

[0006] The data submission process after manual entry lacks automation, especially when it comes to complex insurance terms or multiple policies, and the data is poorly integrated with the backend system. Operators need to manually input the completed data into the insurance policy issuance system, which increases the possibility of errors and greatly prolongs the processing time.

[0007] To sum up, these problems make the policy entry process cumbersome, inefficient and error-prone. There is an urgent need for a technical solution that can realize automatic data entry to improve the intelligence level and processing efficiency of the entire process. Summary of the invention

[0008] The main purpose of the present invention is to provide a chatbot-based recording method, device, equipment and storage medium, aiming to solve the technical problem that the prior art relies on manual extraction of information from insurance policy application documents, which is inefficient and prone to errors.

[0009] To achieve the above object, the present invention provides a method for recording orders based on a chat robot, comprising:

[0010] Obtaining an insurance policy application document, parsing the insurance policy application document, identifying and segmenting text content, and extracting insurance element fields;

[0011] Analyzing the insurance factor field based on the mandatory information database by the chat robot to determine whether the insurance factor field omits mandatory information data;

[0012] If the insurance factor field omits mandatory information data, the chat robot outputs guidance information to guide the supplement of the missing mandatory information data;

[0013] Acquire supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

[0014] Furthermore, in order to achieve the above-mentioned purpose, the present invention provides a chatbot-based order recording device, comprising:

[0015] A document parsing module is used to obtain an insurance policy application document, parse the insurance policy application document, identify and segment the text content, and extract insurance element fields;

[0016] A data analysis module, used to analyze the insurance factor field based on the mandatory information database through a chat robot to determine whether the insurance factor field omits mandatory information data;

[0017] A chatbot interaction module, for outputting guidance information through the chatbot to guide the supplementation of the missing mandatory information data if the mandatory information data is omitted in the insurance factor field;

[0018] A data entry module is used to obtain supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

[0019] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a computer device, which includes a memory, a processor, and a chatbot-based order recording program stored in the memory and executable on the processor, wherein the chatbot-based order recording program, when executed by the processor, implements the steps of the chatbot-based order recording method as described above.

[0020] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a chatbot-based order recording program is stored, and when the chatbot-based order recording program is executed by a processor, the steps of the chatbot-based order recording method as described above are implemented.

[0021] Beneficial effects: The present invention relates to the fields of artificial intelligence technology and financial technology, and discloses a method for recording orders based on a chatbot, which obtains and parses the insurance policy application document, identifies and segments the text content, and extracts the insurance element field. Through the chatbot, the insurance element field is analyzed based on the mandatory information database to determine whether there is any missing mandatory information data. If omissions are found, the chatbot guides the user to supplement these data. After the user supplements the data, the target mandatory information is obtained, and the extracted insurance element field is entered into the insurance issuance system together with the target mandatory information. The present invention avoids the inefficiency and error rate of manual operation by automatically parsing the insurance policy application document and extracting the insurance element field, thereby improving the efficiency of recording orders and reducing the problem of human errors. At the same time, by intelligently guiding users to supplement the missing information, user operations are simplified, the user's input burden is reduced, efficient information completion is achieved, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0023] Figure 1 A schematic diagram of an application environment of a method for recording orders based on a chat robot in an embodiment of the present invention;

[0024] Figure 2 This is a flow chart of an embodiment of a method for recording an order based on a chat robot according to the present invention;

[0025] Figure 3 This is a functional module diagram of a preferred embodiment of the order recording device based on a chat robot of the present invention;

[0026] Figure 4 A schematic diagram of the structure of a computer device in one embodiment of the present invention;

[0027] Figure 5 FIG. 4 is another schematic diagram of the structure of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0029] The order recording method based on the chat robot provided in the embodiment of the present invention can be applied in the following aspects: Figure 1In an application environment, the client communicates with the server through a network. The server can obtain the insurance policy application document through the client, parse the document, identify and segment the text content, and extract the insurance element field. The server receives the uploaded information of the chat robot from the client, analyzes the insurance element field based on the mandatory information database, and determines whether there is any missing mandatory information data. If omissions are found, the chat robot guides the user to supplement these data. After the user supplements the data, the target mandatory data is obtained, and the extracted insurance element field and the target mandatory data are entered into the insurance issuance system together. The present invention avoids the inefficiency and error rate of manual operation by automatically parsing the insurance policy application document and extracting the insurance element field, improves the efficiency of recording and reduces the problem of human error. At the same time, by intelligently guiding the user to supplement the missing information, the user operation is simplified, the input burden of the user is reduced, and the efficient completion of information is achieved, and the user experience is improved. Among them, the client can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0030] See also Figure 2 , Figure 2 This is a flow chart of an embodiment of a chatbot-based order recording method provided by the present invention. It should be noted that although a logical sequence is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0031] like Figure 2 As shown, the order recording method based on the chat robot proposed by the present invention includes the following steps:

[0032] S10, obtaining an insurance policy application document, parsing the insurance policy application document, identifying and segmenting text content, and extracting insurance element fields;

[0033] In this embodiment, obtaining the policy application document means receiving the original policy application document from the user through the system interface or file upload function. The document may be in multiple formats, such as PDF, Word, image or other formats. This step ensures that the system can receive policy application documents from different sources and prepare them for parsing.

[0034] The system interface is designed to support file uploads in multiple formats. Files can be received through the API, or the user interface allows users to upload files directly. The system identifies the format of the uploaded file to ensure the compatibility of the document, and stores the document on the server side for subsequent parsing and processing.

[0035] The purpose of parsing insurance policy application documents is to extract useful information from documents of different formats. The process uses different parsing technologies depending on the type of document. For text format, parsing can directly extract paragraph and field content; for image format, OCR technology is used to convert text in the image into text; for PDF format, layout parsing technology is used to identify and extract text and table content.

[0036] The system first identifies the document format and determines the applicable parsing technology. Text documents can be read directly, while image documents require OCR technology to convert the recognized characters into text. For PDF documents, layout parsing technology is used to process complex layout elements in the document, such as paragraphs, tables, and pictures, and convert them into structured text information.

[0037] Identifying text content is to extract key parts from the parsed document, and segmentation is to semantically divide these contents into blocks to distinguish different fields or information blocks. For example, different elements such as customer information, insurance amount, insurance period, etc. can be segmented into independent fields to facilitate subsequent processing and analysis.

[0038] The system uses natural language processing (NLP) technology or pre-trained models to perform semantic analysis and segmentation on text content. The system divides the text into multiple independent parts based on keywords, formatting rules, or positions in the document. Each part corresponds to a different field type, such as name, policy number, insurance amount, etc. For table content, the system extracts the content of each cell as the corresponding field.

[0039] Extracting insurance element fields is to classify the segmented text content and map it to the corresponding insurance fields. These fields may include customer information (name, ID number), policy information (policy number, insurance type, insured amount, etc.), ensuring that the order recording system can identify all key data.

[0040] The system matches text content with field templates through field annotation algorithms combined with predefined insurance element models. For example, paragraphs containing "name" or "policy number" are automatically mapped to customer name and policy number fields. The system stores the extracted fields in the database for subsequent operations and verification.

[0041] Through the above steps, key information can be automatically extracted from the insurance policy application documents, avoiding the inefficiency and error-prone problems in traditional manual data entry. The system automatically identifies and verifies the mandatory information data in the insurance policy through intelligent analysis technology, reducing manual intervention, greatly improving the efficiency and accuracy of insurance policy entry, and reducing the error rate.

[0042] S20, analyzing the insurance factor field based on the mandatory information database by the chat robot to determine whether the insurance factor field omits mandatory information data;

[0043] In this embodiment, the mandatory information database is a predefined database that records all mandatory fields of insurance products. The chatbot interacts with the mandatory information database through an interface to retrieve mandatory information items related to the current policy application document. These items include customer information, insured amount, insurance period, etc., which are the basis for the system to determine whether there is any missing information.

[0044] The chatbot first receives the parsed policy application document, identifies the type of insurance product involved in the policy, and then accesses the mandatory information database based on the product type. The system retrieves the list of mandatory information fields related to the product and prepares to compare it with the insurance element fields.

[0045] The policy application document is parsed by a parsing tool to extract key information fields, including customer name, policy number, insurance period, etc., which are called insurance element fields. These fields are the text content identified and segmented from the document for subsequent comparison.

[0046] The system identifies the format of the uploaded policy application document and uses the corresponding parsing technology according to the document format (such as PDF, Word or image). The parsed text is extracted through the field annotation algorithm to extract various insurance element fields and match them with the required information items.

[0047] The system compares the extracted insurance element fields with the list of fields in the mandatory information database. The goal of the analysis is to ensure that each mandatory field is extracted and identified, and to check the completeness and accuracy of the data.

[0048] The system uses a field matching algorithm to compare the extracted insurance element fields with the fields in the mandatory information database one by one. For each field, the system checks whether it exists, whether it is empty, and whether the data format meets the predefined standards (such as ID number format, date format, etc.).

[0049] After completing the field comparison, the system determines whether there is any required information data that has not been filled in or extracted in the insurance element field. If missing or incomplete fields are found, the system will record these omissions for subsequent processing.

[0050] Based on the analysis results, the system generates a field status list, where each field is marked as “complete” or “missing.” For missing fields, the system will feed them back to the chatbot, ready to guide the user to supplement the data.

[0051] By intelligently analyzing the extracted insurance element fields with the required information database, the system can effectively detect whether there are omissions or erroneous information in the policy application documents, avoiding the tedious and error-prone problem of manual item-by-item verification. It not only improves the accuracy of the recording, but also ensures that all key information has been fully verified before entry, greatly reducing the error rate and optimizing the overall efficiency of insurance recording.

[0052] S30, if the insurance factor field omits mandatory information data, outputting guidance information through the chat robot to guide the supplement of the missing mandatory information data;

[0053] In this embodiment, the system first detects that some fields are missing or incompletely filled in the process of comparing the required information data. These fields may be key items in the required information database, such as the customer's ID number, insurance amount, etc.

[0054] The system checks the extracted insurance element fields one by one through field matching and format verification functions, and marks missing or incomplete fields. If the system finds that there are missing fields, it records these fields and generates a task list for subsequent processing.

[0055] After detecting missing fields, the system generates prompts to guide users to fill in the required information. The prompts include specific information items that users need to fill in, helping users understand which information is not yet filled in.

[0056] The system generates corresponding prompt words from the prompt template based on the missing mandatory information items. For example, "Please provide your ID number" or "Please fill in the insurance amount." These prompt words can be dynamically generated based on the mandatory fields of different insurance products.

[0057] As the user interaction interface, the chatbot is responsible for displaying prompts and guiding users to supplement the missing information. Through natural language interaction with users, the robot gradually collects users' supplementary information.

[0058] The chatbot receives prompts generated by the system and displays them to the user through the interface. For example, "Your insurance policy application information is incomplete. Please provide the following information: customer name, ID number, etc." The user can directly enter the supplementary data through the chatbot.

[0059] When the user enters supplementary data, the system verifies the entered information in real time to check the format and completeness, for example, whether the ID card number is in the correct format and whether the insurance amount meets the standards.

[0060] When the user enters data, the system performs real-time format verification to ensure that the entered data meets the requirements. If the format is incorrect or the information is incomplete, the chatbot will prompt the user to make corrections again. For example, "The ID number you entered is not in the correct format, please re-enter it."

[0061] When the supplementary data entered by the user passes verification, the system will update the supplementary complete information to the insurance element fields and store these fields in the system for subsequent entry into the insurance policy issuance system.

[0062] After confirming that all the information entered by the user is correct, the system automatically updates the previously missing fields and merges them with the complete insurance element fields. The updated information is stored in the database for subsequent order recording operations.

[0063] The chatbot outputs guidance information to guide users to supplement the missing mandatory information data. It can automatically detect the missing information in the policy application and prompt users to supplement in real time, effectively reducing the workload of manual information verification and the error rate in filling in information. The system can also perform real-time verification of the supplementary data entered by the user to ensure the accuracy of the input data, ultimately improving the integrity and efficiency of policy entry.

[0064] S40, obtaining supplementary data, extracting target mandatory data from the supplementary data based on the missing mandatory information data, and entering the insurance element field and the target mandatory data into the insurance policy issuance system.

[0065] In this embodiment, the system receives supplementary data from the user through a chatbot. Supplementary data refers to input data that may contain a variety of information provided by the user in response to the system prompt. Since the user may enter additional data beyond the required information database, the system needs to further process this data. The chatbot interacts with the user and prompts the user to enter relevant policy information, such as name, ID number, and insured amount. After the user provides these supplementary data, the system stores them and prepares them for further processing.

[0066] The system extracts the required target data from the supplementary data entered by the user according to the data requirements in the required information library. The user may enter a variety of information, but the system only needs to extract the target data related to the required fields defined in the required information library.

[0067] The system first identifies the information entered by the user, and uses field matching algorithms or preset rules to filter out the target mandatory data that corresponds to the data requirements in the mandatory information database. For example, if the mandatory information items are the insurance amount and the insurance period, the system will extract the insurance amount and the insurance period from the data entered by the user and ignore other irrelevant data.

[0068] After extracting the target required data, the system merges this data with the insurance element fields originally extracted from the policy application document. The merged data includes complete insurance application information, ensuring that the required items have been completed.

[0069] The system uses a data merging algorithm to merge the extracted target mandatory data with the previously extracted insurance element fields. The system ensures that there is no duplication or omission of data, and that each insurance element field contains complete information, especially the mandatory data supplemented by the user.

[0070] After the data is merged, the system automatically enters the complete insurance element fields and target required data into the insurance issuance system. This step ensures that the data can be received by the insurance system and used to generate formal insurance policies or other business processing.

[0071] The system connects with the insurance policy issuance system through API or database interface, and transmits the merged insurance element fields and target mandatory data to the policy issuance system. The system ensures the security and accuracy of the data transmission process to avoid policy issuance failure due to data loss or format errors.

[0072] Example description:

[0073] A customer applies for health insurance through a chatbot. The chatbot prompts the user to enter relevant mandatory information, such as the customer's health status, weight, age, occupation, etc. The user may respond by entering name, age, health status, weight, occupation, and additional optional information, such as home address, marital status, etc.

[0074] The system determines from the mandatory information database that the mandatory information items for health insurance include health status, weight, age and occupation. The system extracts this mandatory information from the data entered by the user. Even if the user enters additional information such as home address and marital status, the system will filter out this non-mandatory information and only keep health status, weight, age and occupation as the target mandatory data.

[0075] The system previously extracted some basic information from the policy application document, such as policy number, insured amount, insurance period, etc. Now, the system will merge the extracted mandatory data such as health status, weight, age, occupation, etc. with the previous basic insurance element fields to generate complete health insurance application data.

[0076] Finally, the system enters the merged complete policy data into the insurance issuance system. The system ensures that all data is complete and complies with business rules, such as the customer's health status and weight meet the underwriting conditions of health insurance. After receiving the complete data, the insurance issuance system calculates the insurance premium rate according to the system's business logic, generates a formal policy quotation, and feeds it back to the customer.

[0077] Through the above steps, the system can intelligently extract target data that meets the mandatory information requirements from the supplementary data entered by the user. After completing the mandatory information supplement, all key information is merged into complete policy data and entered into the insurance policy issuance system to ensure that the data entered into the insurance policy issuance system is complete and accurate. This reduces the possibility of user input errors, improves the efficiency and accuracy of data processing, and enables the insurance policy issuance system to quickly process policy applications and generate formal policies.

[0078] The present invention relates to the field of artificial intelligence technology, and discloses a method for recording orders based on a chatbot. The method obtains an insurance policy application document, parses the document, identifies and segments the text content, and extracts insurance element fields. The chatbot analyzes the insurance element fields based on a required information database to determine whether there are missing required information data. If omissions are found, the chatbot guides the user to supplement these data. After the user supplements the information, the supplementary data is obtained, and the extracted insurance element fields are entered into the insurance issuance system together with the supplementary data. The present invention avoids the inefficiency and error rate of manual operation by automatically parsing the insurance policy application document and extracting the insurance element fields, thereby improving the efficiency of recording orders and reducing the problem of human errors. At the same time, by intelligently guiding users to supplement the missing information, user operations are simplified, the input burden of users is reduced, efficient information completion is achieved, and user experience is improved.

[0079] In one embodiment, the above S20 includes:

[0080] S201, determining the current insurance conditions based on the insurance policy application document by the chat robot;

[0081] S202, determining current mandatory information items from the mandatory information database based on the current insurance conditions;

[0082] S203, comparing the current mandatory information item with the insurance factor field to determine whether the insurance factor field omits mandatory information data.

[0083] In this embodiment, the system first needs to extract the customer's insurance conditions from the insurance policy application document through the chatbot. The insurance conditions may include the customer's age, insurance type, insurance amount, etc., to ensure that the system can determine the insured's specific insurance needs.

[0084] The chatbot automatically extracts key information (such as customer age, insured amount, insurance period, etc.) from the policy application document and stores this information as insurance conditions in the system. Natural language processing (NLP) technology or field matching algorithms can be used to identify key information in the document and ultimately generate a structured set of insurance conditions.

[0085] According to the customer's insurance conditions, the system extracts the mandatory information items that match the current insurance situation from the mandatory information database. The mandatory information database contains mandatory fields for different insurance products, such as customer information, insurance amount, insurance period, etc. The system will dynamically generate the currently applicable mandatory information items based on the specific insurance conditions.

[0086] The system queries the mandatory information database, matches the current insurance conditions, and generates a corresponding list of mandatory information items. For example, for health insurance products, the system may extract mandatory fields such as health status and insurance period from the database. This process is implemented through field mapping or dynamic query to ensure that mandatory information related to the customer's insurance conditions is generated.

[0087] The system then compares the mandatory information items extracted from the mandatory information database with the insurance element fields extracted from the policy application document to check whether there is any missing or incomplete mandatory information data. The purpose of the comparison is to ensure that all necessary insurance information is included in the policy application.

[0088] The system uses a field matching algorithm to compare the extracted insurance element fields with the list of mandatory information items one by one to check whether each field is complete and accurate. If some mandatory information fields are found to be empty or do not meet the standards, the system will mark them as missing items. The comparison results will be stored in the system for subsequent data supplementation and correction processes.

[0089] Through the above steps, this embodiment can automatically identify the insurance conditions in the policy application document, dynamically determine the corresponding mandatory information items, and determine whether the insurance element fields are missing or incomplete through intelligent comparison. The workload of manual information verification is reduced and the accuracy and efficiency of data entry are improved. By dynamically matching the mandatory information items, the system can adapt to different insurance products and customer needs, ensure that all key information is fully verified before entry, avoid omissions, and improve the automation level of the policy entry process and business processing efficiency.

[0090] In one embodiment, after the above S201, the method further includes:

[0091] S2011, receiving the insurance change information input by the user through the chat robot, and updating the current insurance conditions according to the insurance change information;

[0092] S2012, based on the updated insurance conditions, determining updated mandatory information from the mandatory information database;

[0093] S2013, comparing the updated mandatory information with the insurance element fields to determine whether additional element data needs to be supplemented;

[0094] S2014: If additional element data is required, the chat robot guides the user to submit the additional element data.

[0095] In this embodiment, the system receives any changes made by the user after the initial submission of the policy information through the chatbot. For example, the user may modify the insurance type, insured amount, or insurance period. These changes are used to update the current insurance conditions in the system.

[0096] The system interacts with users through chatbots, and users submit changed insurance information in the chat interface. The system receives these changed data in real time and updates them in the insurance conditions. Through natural language processing (NLP) technology or form input, the system can accurately identify the updated items submitted by users.

[0097] After receiving the change information input by the user, the system updates the current insurance conditions. The updated insurance conditions reflect the user's latest needs, such as the modified insurance amount, insurance period, etc.

[0098] The system uses field mapping and update mechanisms to overwrite or add new data entered by the user to the current insurance conditions. For example, if the user updates the insurance amount, the system replaces the previous value with the new amount data. This process is implemented through database update operations.

[0099] After the insurance conditions are updated, the system will re-determine the updated mandatory information from the mandatory information database. As the insurance conditions have changed, the mandatory information items may also be adjusted accordingly, such as adding or reducing certain mandatory fields.

[0100] The system revisits the mandatory information database and matches the corresponding mandatory fields based on the new insurance conditions. This process is achieved by dynamically querying the mandatory information database. The system regenerates a list of mandatory information items based on the new conditions to ensure that the fields in the database match the latest insurance requirements.

[0101] The system compares the updated mandatory information items with the current insurance element fields, checks whether the currently extracted fields meet the latest mandatory requirements, and determines whether there is any missing or unfilled additional element data.

[0102] Through field matching and data integrity checking, the system compares the updated mandatory information with the extracted insurance element fields. If any fields are missing or not filled in, the system marks these fields for subsequent processing.

[0103] If the system finds that the insurance factor field is missing additional factor data (such as additional terms or special insurance conditions), the chatbot guides the user to supplement this information. Additional factor data is additional information items generated based on the user's update needs.

[0104] The system generates prompts through the chatbot, showing the user the additional data items that have not been filled in, and guiding the user to enter them step by step. This process generates personalized prompts through dynamic prompt templates to ensure that users can complete the required additional information.

[0105] Through the above steps, this embodiment can dynamically adjust the insurance conditions according to the latest needs of the user, and re-match the latest mandatory information items from the mandatory information database to achieve intelligent insurance condition management. The system can automatically detect the lack of additional information and guide the user to supplement it through a chat robot, avoiding manual item-by-item verification, greatly improving the efficiency and accuracy of policy entry, while providing users with flexible and personalized services.

[0106] In one embodiment, in the above S30, the chat robot outputs guidance information to guide the supplement of the missing mandatory information data, including:

[0107] S301, determining the mandatory information item corresponding to the mandatory information data from the mandatory information database;

[0108] S302, generating corresponding data supplement prompt words according to the required information items and a prompt template, so as to guide the user to input supplementary data;

[0109] S303, displaying the data supplement prompt speech to the user through the chat robot, prompting the user to input supplementary data;

[0110] S304, upon receiving the supplementary data input by the user, determining whether the input supplementary data includes all the missing mandatory information data;

[0111] S305: If the supplementary data does not include all the missing mandatory information data, a data supplement prompting speech is regenerated to prompt the user to continue inputting the mandatory information data that has not been supplemented.

[0112] In this embodiment, the system first determines the mandatory information items required in the current policy entry process from the mandatory information library. The mandatory information library contains all mandatory fields related to the insurance product, and the system will determine which mandatory information has not been completed based on the current insurance conditions.

[0113] The system dynamically generates a list of mandatory information that matches the current insurance product and the user's insurance conditions by querying the mandatory information database. The system detects missing items from the extracted policy data and records the information that needs to be supplemented.

[0114] After determining the missing items of the required information, the system generates corresponding prompts to guide the user to fill in the missing information. The prompts are generated based on a preset prompt template so as to clearly and concisely prompt the user to enter specific data.

[0115] The system generates personalized prompts for each missing mandatory information item by matching prompt templates. For example, for a missing ID number, the system generates a prompt: "Please provide your ID number." These prompts are displayed to users through chatbots.

[0116] The system displays the generated prompt words to the user through the chatbot. As the interface for user interaction, the chatbot sends prompt information to the user in real time, reminding the user to supplement the missing mandatory information data.

[0117] The chatbot receives prompt information generated by the system and displays it to the user in a dialog box. For example, the user will see the prompt "Please fill in your policyholder name" and related input boxes on the interface, allowing the user to enter the missing data directly in the chat interface.

[0118] After receiving the supplementary data entered by the user, the system will check whether the data is complete in real time and determine whether all missing mandatory information items have been supplemented. If the input data is incomplete or incorrect, the system will prompt the user to supplement it again.

[0119] The system uses the data verification module to check the format and content of the supplementary data entered by the user to ensure that the input meets the requirements. For example, the system will verify whether the format of the ID card number is correct. If the format is incorrect or the field is empty, the system will mark the information as incomplete and wait for the user to further supplement it.

[0120] If the supplementary data entered by the user is incomplete, the system will regenerate a prompt and prompt the user to fill in the incomplete required information again. This cycle guides the user until all the required information items are completed.

[0121] When data verification fails, the system will send new prompts to the user through the chatbot to inform them of the information that has not been fully supplemented. For example, the system may prompt "The ID card number format is incorrect, please re-enter" and redisplay the input box.

[0122] This embodiment guides users to supplement the required information data through the chatbot, and can dynamically generate personalized prompts to ensure that users supplement the key information missing in the insurance policy application item by item. Automatically verify the data entered by the user, and provide real-time feedback on missing data or incorrect format, avoiding errors and duplications in the information filling process, and significantly improving the completeness and accuracy of insurance policy entry. At the same time, as an interactive interface, the chatbot simplifies the user's operation, making the information supplement process more efficient and smooth.

[0123] In one embodiment, in the above S10, the insurance policy application document is parsed, the text content is identified and segmented, and the insurance element fields are extracted, including:

[0124] S101, identifying the format of the insurance policy application document, including text format, image format or PDF format;

[0125] S102, if the insurance policy application document is a document in text format, parse the text paragraphs, titles and lists of the insurance policy application document to extract text content;

[0126] S103, if the insurance policy application document is in an image format, convert the text content in the image into text using OCR technology to generate converted text content;

[0127] S104, if the insurance policy application document is in PDF format, use layout parsing technology to process layout elements in the document and parse them into text content;

[0128] S105, segmenting and annotating the parsed text content, distinguishing and extracting different types of insurance element fields.

[0129] In this embodiment, the system first detects the format of the insurance policy application document through the document recognition module to determine whether the document is in text format, image format or PDF format. Different document formats require different parsing technologies to extract the text content therein.

[0130] The system detects the file type of the uploaded document through the document format recognition algorithm. The file header or extension can provide format information, and the system identifies the file format based on this information, such as DOCX, PDF, JPEG, etc. Based on the recognition result, the system will select the corresponding parsing method for subsequent processing.

[0131] If the policy application document is in text format, the system will directly parse the paragraphs, titles and lists in the document to extract the text. The structure of a text-based document is relatively simple and usually does not involve complex typesetting, so the required information can be obtained by directly parsing the text content.

[0132] The system uses text parsing tools to directly read the paragraph structure in the document and identify the titles, lists, and key fields. Through regular expressions, natural language processing (NLP) and other technologies, the system maps the text content of each paragraph to the corresponding insurance element field (such as name, policy number, etc.).

[0133] If the policy application document is in image format, the system needs to use OCR (Optical Character Recognition) technology to convert the text information in the image into processable text content. OCR technology can recognize the characters in the image and generate corresponding text to facilitate subsequent text analysis.

[0134] The system calls an OCR engine (such as Tesseract) to perform character recognition on documents in image format. OCR technology converts characters in the image into text format and performs basic text cleaning and formatting. The converted text is extracted for subsequent segmentation and annotation operations.

[0135] If the policy application document is in PDF format, the system uses layout parsing technology to process the layout elements in the document. PDF documents usually contain complex layout structures such as tables, images, paragraphs and titles. Layout parsing technology can identify these elements and extract the text content.

[0136] The system uses a PDF parsing engine (such as PDFBox or PyMuPDF) to parse the document layout. The system identifies tables, paragraphs, and other layout elements in the PDF and extracts the text content one by one. These texts are standardized into continuous text paragraphs for subsequent segmentation and annotation processing.

[0137] After obtaining the text content, the system needs to further segment and annotate the text. Segmentation is to decompose the text into multiple independent fields, while annotation is to classify these fields into different types of insurance elements (such as customer information, policy number, insured amount, etc.).

[0138] The system uses NLP technology or rule-based field segmentation algorithms to segment the parsed text content into blocks. Each text paragraph is annotated as a specific insurance element field based on its semantics or format. For example, a paragraph containing "name" will be annotated as the customer name field, and other element fields such as policy number and insurance amount will also be automatically classified and annotated.

[0139] This embodiment automatically identifies and parses insurance policy application documents in different formats. The system can flexibly handle multiple document formats such as text, images, and PDF, and achieves efficient and accurate insurance element field extraction. The application of OCR and layout parsing technology ensures that documents with complex layouts can also be accurately identified. The segmentation and annotation technology further converts the parsed text content into structured insurance element fields. It reduces manual intervention, improves the efficiency and accuracy of insurance recording, and is suitable for insurance policy application scenarios in various formats.

[0140] In one embodiment, in the above S10, after extracting the insurance element field, the method further includes:

[0141] S106, verifying whether the data format of the insurance factor field is correct, and adjusting the data format that does not meet the standard to the standard format;

[0142] S107, detecting whether there is abnormal data in the insurance factor field through a pre-trained machine learning model, and deleting the detected abnormal data;

[0143] S108, comparing the insurance factor field with standard data in the insurance product database to confirm that the insurance factor field meets business requirements.

[0144] In this embodiment, after extracting the insurance element fields, the system needs to verify whether the data format of these fields is correct. Each insurance element field (such as ID number, date, amount, etc.) has its specific format requirements, and ensuring that all data meets the predefined standards is a key step.

[0145] The system performs format checks on each insurance element field through the data format validation module. Regular expressions or predefined format rules are used to validate fields. For example, the system checks whether the ID card number is in the format of 18 digits, whether the date conforms to the "YYYY-MM-DD" format, etc. For fields that do not conform to the standard format, the system automatically adjusts them to the correct format or provides correction prompts to the user.

[0146] The system uses a pre-trained machine learning model to perform anomaly detection on the extracted insurance factor fields. The machine learning model can identify possible abnormal data, such as abnormal insurance amount, mismatch between age and insurance type, etc. The accuracy of abnormal data identification can be improved through model training.

[0147] The system calls a pre-trained machine learning model to analyze the insurance factor fields. The machine learning model has been trained with a large amount of historical data and can identify abnormal data that does not conform to the insurance business logic. For example, when the system identifies that the insured amount in the policy does not match the standard range of the insurance product, it will mark this item as abnormal data. The detected abnormal data can be automatically deleted or marked as an error, and trigger further processing.

[0148] The system compares the verified and tested insurance element fields with the standard data in the insurance product database to confirm that these fields meet business requirements. The insurance product database contains standard insurance product information and parameters, such as the standard coverage range and insured age requirements for different insurance products.

[0149] The system compares the insurance element fields with the corresponding standards in the insurance product database through database query and field matching algorithm. For example, the system compares the insured amount in the policy with the standard insured amount range of the insurance product in the database to ensure that the insured amount is within a reasonable range. If it does not meet the business requirements, the system will mark these fields and feedback to the user or system administrator.

[0150] This embodiment performs format verification, anomaly detection, and comparison with standard data on the extracted insurance element fields, so that the system can ensure that all entered data meets format requirements and business standards. The pre-trained machine learning model can automatically identify potential abnormal data, reduce the workload of manual review, and improve the accuracy of data entry. Automatic correction of data format and processing of abnormal data reduce errors in the recording process, ensure that the data entered into the system is complete, accurate, and in compliance with the insurance company's business rules, thereby improving the efficiency and quality of policy entry.

[0151] In one embodiment, in the above S40, after obtaining the supplementary data and extracting the target mandatory data from the supplementary data based on the missing mandatory information data, the method further includes:

[0152] S401, analyzing the insurance element fields and the target required data through a chat robot to generate complete insurance policy application data;

[0153] S402, generating a preliminary quotation scheme based on the complete insurance policy application data, wherein the preliminary quotation scheme includes insurance premium, insurance period and insurance terms;

[0154] S403: Feedback the preliminary quotation plan to the user through the chat robot.

[0155] In this embodiment, after the user supplements the required information data, the system receives this data through the chatbot and conducts a comprehensive analysis of the insurance element fields and the user's supplemented data to ensure that all required fields are fully filled in and there are no omissions. This analysis process will ensure that the data provided by the user meets the business requirements and can generate a complete insurance policy application.

[0156] The system receives the supplementary data entered by the user through the chatbot and merges this data with the previously extracted insurance element fields. The system analyzes the integrity and consistency of the data through field matching and data verification mechanisms to ensure that the supplemented data meets the standards. The complete data after analysis is stored as a set of insurance policy application data for subsequent use.

[0157] After analyzing and confirming the supplementary data, the system generates complete policy application data. This data set contains all insurance element fields and the mandatory information data supplemented by the user, which serves as the basis for generating an insurance pre-quotation plan.

[0158] The system stores the merged insurance element fields and supplementary data as complete policy application data. During the data merging and verification process, the system ensures that each required field complies with the predefined format and requirements to avoid omissions or format errors. The generated policy application data then enters the next step of the quotation generation process.

[0159] The system automatically generates a pre-quotation plan based on the complete policy application data. The pre-quotation plan includes key information such as insurance premium, insurance period and insurance terms, ensuring that users can quickly understand the preliminary pricing of the policy.

[0160] The system accesses the insurance product database, combines the user's policy application data, and generates a preliminary quotation plan according to the established rate rules, insurance terms, etc. For example, the system automatically calculates the premium based on the user's insurance amount, insured age and other information, and generates a complete quotation plan including the insurance period and insurance terms. The plan is dynamically calculated based on the pricing model and rules of the insurance product.

[0161] After generating the pre-quotation plan, the system will feedback the plan to the user through the chatbot. The chatbot serves as an interactive interface, displays detailed quotation information, and allows users to view and refer to it. Users can make decisions based on the plan and further confirm or modify the application information.

[0162] After receiving the pre-quotation plan generated by the system, the chatbot will present it to the user through the interactive interface. For example, the chatbot will show the user "Your pre-quotation is: premium XXX yuan, insurance period X years, insurance terms are as follows", and allow the user to view the detailed terms. The user can make a decision based on the quotation plan, confirm the policy or modify relevant information.

[0163] This embodiment guides users to supplement data through a chatbot, automatically analyzes and generates complete policy application data, and generates a pre-quotation plan based on this, which greatly reduces manual intervention and improves the automation level of policy entry and quotation generation. The generation of the pre-quotation plan is based on the user's specific insurance needs and product data to ensure the accuracy and transparency of the quotation. Users can view and confirm the quotation in real time through the chatbot, which greatly improves the user experience and business processing efficiency.

[0164] In one embodiment, a chatbot-based order recording device is provided, and the chatbot-based order recording device corresponds one-to-one to the chatbot-based order recording method in the above embodiment. Figure 3 , Figure 3 This is a functional module diagram of a preferred embodiment of the order recording device based on a chat robot of the present invention. It includes a document parsing module 10, a data analysis module 20, a chat robot interaction module 30 and a data entry module 40. The functional modules are described in detail as follows:

[0165] The document parsing module 10 is used to obtain the insurance policy application document, parse the insurance policy application document, identify and segment the text content, and extract the insurance element field;

[0166] The data analysis module 20 is used to analyze the insurance factor field based on the mandatory information database through a chat robot to determine whether the insurance factor field omits mandatory information data;

[0167] The chatbot interaction module 30 is used to output guidance information through the chatbot to guide the supplement of the missing mandatory information data if the mandatory information data is omitted in the insurance factor field;

[0168] The data entry module 40 is used to obtain supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

[0169] In one embodiment, the data analysis module 20 is specifically used for:

[0170] Determining the current insurance conditions based on the insurance policy application document by the chat robot;

[0171] Determining current mandatory information items from the mandatory information database based on the current insurance conditions;

[0172] The current mandatory information item is compared with the insurance element field to determine whether the insurance element field omits mandatory information data.

[0173] In one embodiment, the data analysis module 20 is specifically used for:

[0174] Receiving insurance change information input by the user through the chat robot, and updating the current insurance conditions according to the insurance change information;

[0175] Based on the updated insurance conditions, determining updated mandatory information from the mandatory information database;

[0176] Based on the comparison between the updated mandatory information and the insurance element fields, it is determined whether additional element data needs to be supplemented;

[0177] If additional element data needs to be supplemented, the chat robot guides the user to submit the additional element data.

[0178] In one embodiment, the chatbot interaction module 30 is specifically used to:

[0179] Determining the mandatory information item corresponding to the mandatory information data from the mandatory information database;

[0180] According to the required information items, a corresponding data supplement prompt speech is generated according to a prompt template to guide the user to input supplementary data;

[0181] The chat robot displays the data supplement prompt speech to the user, prompting the user to input supplementary data;

[0182] When receiving the supplementary data input by the user, determining whether the input supplementary data includes all the missing mandatory information data;

[0183] If the supplementary data does not include all the missing mandatory information data, a data supplement prompt speech is regenerated to prompt the user to continue to input the mandatory information data that has not yet been supplemented.

[0184] In one embodiment, the document parsing module 10 is specifically used for:

[0185] Identify the format of the policy application document, including text format, image format or PDF format;

[0186] If the insurance policy application document is a document in text format, parse the text paragraphs, titles and lists of the insurance policy application document to extract text content;

[0187] If the insurance policy application document is in an image format, the text content in the image is converted into text using OCR technology to generate converted text content;

[0188] If the insurance policy application document is in PDF format, the layout elements in the document are processed using layout parsing technology and parsed into text content;

[0189] The parsed text content is segmented and annotated to distinguish and extract different types of insurance element fields.

[0190] In one embodiment, the document parsing module 10 is specifically used for:

[0191] Verify whether the data format of the insurance element field is correct, and adjust the data format that does not meet the standard to the standard format;

[0192] Detecting whether there is abnormal data in the insurance factor field through a pre-trained machine learning model, and deleting the detected abnormal data;

[0193] The insurance element fields are compared with standard data in the insurance product database to confirm that the insurance element fields meet business requirements.

[0194] In one embodiment, the data entry module 40 is specifically used for:

[0195] Analyze the insurance element fields and the target required data through a chatbot to generate complete insurance policy application data;

[0196] Generate a pre-quotation plan based on the complete insurance policy application data, the pre-quotation plan including insurance premium, insurance period and insurance terms;

[0197] The preliminary quotation scheme is fed back to the user through the chat robot.

[0198] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the service side of a method for recording an order based on a chat robot.

[0199] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a method for recording an order based on a chat robot

[0200] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0201] Obtaining an insurance policy application document, parsing the insurance policy application document, identifying and segmenting text content, and extracting insurance element fields;

[0202] Analyzing the insurance factor field based on the mandatory information database by the chat robot to determine whether the insurance factor field omits mandatory information data;

[0203] If the insurance factor field omits mandatory information data, the chat robot outputs guidance information to guide the supplement of the missing mandatory information data;

[0204] Acquire supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

[0205] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0206] Obtaining an insurance policy application document, parsing the insurance policy application document, identifying and segmenting text content, and extracting insurance element fields;

[0207] Analyzing the insurance factor field based on the mandatory information database by the chat robot to determine whether the insurance factor field omits mandatory information data;

[0208] If the insurance factor field omits mandatory information data, the chat robot outputs guidance information to guide the supplement of the missing mandatory information data;

[0209] Acquire supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

[0210] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0211] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0212] It should be noted that if software tools or components other than those of the Company appear in the embodiments of the present application, they are only used for illustration and do not represent actual use. Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0213] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for recording orders based on a chat robot, characterized in that: The following steps are involved: Obtaining an insurance policy application document, parsing the insurance policy application document, identifying and segmenting text content, and extracting insurance element fields; Analyzing the insurance factor field based on the mandatory information database by the chat robot to determine whether the insurance factor field omits mandatory information data; If the insurance factor field omits mandatory information data, the chat robot outputs guidance information to guide the supplement of the missing mandatory information data; Acquire supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

2. The method for recording orders based on a chat robot according to claim 1, characterized in that: Analyzing the insurance factor field based on the mandatory information database by the chat robot to determine whether the insurance factor field omits mandatory information data, including: Determining the current insurance conditions based on the insurance policy application document by the chat robot; Determining current mandatory information items from the mandatory information database based on the current insurance conditions; The current mandatory information item is compared with the insurance element field to determine whether the insurance element field omits mandatory information data.

3. The method for recording orders based on a chat robot as claimed in claim 2, characterized in that: After the chat robot determines the current insurance conditions based on the insurance policy application document, the method further includes: Receiving insurance change information input by the user through the chat robot, and updating the current insurance conditions according to the insurance change information; Based on the updated insurance conditions, determining updated mandatory information from the mandatory information database; Based on the comparison between the updated mandatory information and the insurance element fields, it is determined whether additional element data needs to be supplemented; If additional element data needs to be supplemented, the chat robot guides the user to submit the additional element data.

4. The method for recording orders based on a chat robot according to claim 1, characterized in that: The chat robot outputs guidance information to guide the supplement of missing mandatory information data, including: Determining the mandatory information item corresponding to the mandatory information data from the mandatory information database; According to the required information items, a corresponding data supplement prompt speech is generated according to a prompt template to guide the user to input supplementary data; The chat robot displays the data supplement prompt speech to the user, prompting the user to input supplementary data; When receiving the supplementary data input by the user, determining whether the input supplementary data includes all the missing mandatory information data; If the supplementary data does not include all the missing mandatory information data, a data supplement prompt speech is regenerated to prompt the user to continue to input the mandatory information data that has not yet been supplemented.

5. The method for recording orders based on a chat robot as claimed in claim 1, characterized in that: Parse the insurance policy application document, identify and segment the text content, and extract the insurance element fields, including: Identify the format of the policy application document, including text format, image format or PDF format; If the insurance policy application document is a document in text format, parse the text paragraphs, titles and lists of the insurance policy application document to extract text content; If the insurance policy application document is in an image format, the text content in the image is converted into text using OCR technology to generate converted text content; If the insurance policy application document is in PDF format, the layout elements in the document are processed using layout parsing technology and parsed into text content; The parsed text content is segmented and annotated to distinguish and extract different types of insurance element fields.

6. The order recording method based on a chat robot as claimed in claim 1, characterized in that: After extracting the insurance element fields, it also includes: Verify whether the data format of the insurance element field is correct, and adjust the data format that does not meet the standard to the standard format; Detecting whether there is abnormal data in the insurance factor field through a pre-trained machine learning model, and deleting the detected abnormal data; The insurance element fields are compared with standard data in the insurance product database to confirm that the insurance element fields meet business requirements.

7. The order recording method based on a chat robot as claimed in claim 1, characterized in that: After obtaining the supplementary data and extracting the target mandatory data from the supplementary data based on the missing mandatory information data, the method further includes: Analyze the insurance element fields and the target required data through a chatbot to generate complete insurance policy application data; Generate a pre-quotation plan based on the complete insurance policy application data, the pre-quotation plan including insurance premium, insurance period and insurance terms; The preliminary quotation scheme is fed back to the user through the chat robot.

8. A chatbot-based order recording device, characterized in that: The order recording device based on the chat robot includes: A document parsing module is used to obtain an insurance policy application document, parse the insurance policy application document, identify and segment the text content, and extract insurance element fields; A data analysis module, used to analyze the insurance factor field based on the mandatory information database through a chat robot to determine whether the insurance factor field omits mandatory information data; A chatbot interaction module, for outputting guidance information through the chatbot to guide the supplementation of the missing mandatory information data if the mandatory information data is omitted in the insurance factor field; A data entry module is used to obtain supplementary data, extract target mandatory data from the supplementary data based on the missing mandatory information data, and enter the insurance element field and the target mandatory data into the insurance policy issuance system.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a chatbot-based order recording program stored in the memory and executable on the processor. When the chatbot-based order recording program is executed by the processor, the steps of the chatbot-based order recording method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a chatbot-based order recording program, which, when executed by a processor, implements the steps of the chatbot-based order recording method as described in any one of claims 1-7.

Images