Information reply method, device, computer equipment and storage medium

Abstract

The embodiments of the present application belong to the field of financial technology and relate to an information reply method, apparatus, computer equipment and storage medium, the method comprising the following steps: obtaining insurance structural information and insurance non-structural information; constructing an insurance field knowledge graph based on the insurance structural information and insurance non-structural information; performing semantic analysis on user conversation information to obtain conversation keywords and conversation semantic features; performing reasoning in the insurance field knowledge graph based on the conversation keywords and conversation semantic features to obtain user intent categories; calculating the confidence score of the user intent category and determining whether the confidence score is less than a preset confidence threshold; if less than, performing a query in the insurance field knowledge graph based on the user's needs to refine the information and generate a first reply content for reply; if greater than or equal to, generating a second reply content for reply. The present application can effectively provide accurate replies to user conversation content to improve the accuracy and effectiveness of the replies.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, specifically to the field of financial technology, and in particular to an information reply method, device, computer equipment and storage medium. Background Art

[0002] In traditional insurance business order processing, cumbersome and complex procedures, coupled with extensive documentation and rule verification, have always been key factors hindering efficiency and accuracy. Salespeople and underwriters must manually perform numerous operations, from data collection and entry to rule verification, each of which consumes significant time and effort. Furthermore, faced with complex and ever-changing order processing scenarios, manual operations often struggle to cope with unexpected issues, resulting in low order processing efficiency and difficulty ensuring accuracy.

[0003] To address this issue, the insurance industry has begun exploring intelligent order recording technology, aiming to streamline the order recording process and improve business efficiency through automated and intelligent means. However, in insurance order recording scenarios, the diversity and complexity of user intent pose significant challenges to intelligent order recording systems. Users may express multiple intents simultaneously in a single conversation, such as inquiring about insurance terms, modifying policyholder information, and inquiring about policy payment status. This requires order recording systems to possess robust multi-intent recognition capabilities.

[0004] At the same time, multi-round conversation management is also a key technical issue in intelligent insurance order recording. During multi-round conversations, the system needs to accurately understand the user's intent and rationally arrange the order and content of the conversation based on the priority and relevance of the intent. Furthermore, the transmission and association of contextual information is key to achieving conversational coherence. For example, if a user mentioned the policyholder information in the previous round of conversation and then modifies the policyholder information in the next round, the system should be able to automatically associate and fill in the relevant information, avoiding repeated inquiries, improving the effectiveness and rationality of the conversation responses, and saving time in the order recording process. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide an information reply method, apparatus, computer device and storage medium to solve the problem of being unable to effectively and accurately reply to the content of user conversations.

[0006] In order to solve the above technical problems, the embodiment of the present application provides an information reply method, which adopts the following technical solutions:

[0007] Obtain insurance structure information and insurance non-structure information;

[0008] Constructing an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information;

[0009] Obtaining user conversation information, performing semantic analysis on the user conversation information, and obtaining conversation keywords and conversation semantic features;

[0010] Reasoning in the insurance field knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category;

[0011] Calculating a confidence score for the user intent category, and determining whether the confidence score is less than a preset confidence threshold;

[0012] If the confidence score is less than the preset confidence threshold, obtaining user demand refinement information, and querying the insurance field knowledge graph based on the user demand refinement information to generate a first reply content for reply;

[0013] If the confidence score is greater than or equal to the preset confidence threshold, a search is performed in the insurance field knowledge graph based on the user intention category, the corresponding knowledge information is extracted, and the knowledge information is filled into the preset reply template to generate a second reply content for reply.

[0014] Furthermore, the step of obtaining insurance structure information and insurance non-structure information specifically includes:

[0015] Obtaining a structural information extraction identifier, and extracting insurance product information, underwriting rule information, and underwriting decision information from a database according to the knowledge information extraction identifier;

[0016] Obtaining a non-structured information extraction identifier, and extracting insurance clause information and claim case information from a database according to the non-structured information extraction identifier;

[0017] performing a first preprocessing on the insurance product information, the underwriting rule information, and the underwriting decision information to obtain the insurance structure information;

[0018] The extracted insurance clause information and the claim case information are subjected to a second preprocessing to obtain the insurance non-structured information.

[0019] Furthermore, the step of constructing an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information specifically includes:

[0020] Define insurance business entities, insurance business attributes, and insurance business entity relationships, and construct insurance domain knowledge ontology;

[0021] Integrating the insurance structure information into the insurance domain knowledge ontology to obtain an insurance domain knowledge graph framework;

[0022] Key information is extracted from the insurance non-structured information to obtain non-structured key information, and the non-structured key information is integrated into the insurance field knowledge graph framework to obtain the insurance field knowledge graph.

[0023] Furthermore, the steps of obtaining user conversation information, performing semantic analysis on the user conversation information, and obtaining conversation keywords and conversation semantic features specifically include:

[0024] Accessing user session records, and extracting the user conversation information from the user session records;

[0025] Performing word segmentation and part-of-speech tagging on the user conversation information to obtain conversation representation information;

[0026] performing named entity recognition on the conversation representation information to extract the conversation keywords from the conversation representation information;

[0027] The conversation keywords are represented by word vectors to obtain keyword semantic information, and the keyword semantic information is used as the conversation semantic feature.

[0028] Furthermore, the step of performing reasoning in the insurance field knowledge graph based on the conversation keywords and the conversation semantic features to obtain the user intent category specifically includes:

[0029] Inputting the conversation keywords and the conversation semantic features into the insurance field knowledge graph, and performing reasoning on the insurance field knowledge graph based on a knowledge reasoning algorithm to obtain a knowledge reasoning result;

[0030] The knowledge reasoning result is input into a pre-built intention recognition model to obtain the user intention category.

[0031] Furthermore, the step of calculating the confidence score of the user intent category and determining whether the confidence score is less than a preset confidence threshold specifically includes:

[0032] Inputting the user conversation information and the user intent category into a pre-built confidence prediction model to obtain the confidence score;

[0033] Matching the confidence scores with the user intent categories to obtain an intent confidence score set;

[0034] Extracting a corresponding preset confidence threshold from a database according to the user intention category;

[0035] The intention confidence score set is sorted from high to low according to the confidence score, and the confidence score ranked first is extracted and compared with the preset confidence threshold.

[0036] Furthermore, the step of obtaining detailed information about user needs, querying the insurance field knowledge graph based on the detailed information about user needs, and obtaining the first reply content for replying specifically includes:

[0037] determining a corresponding information database according to the user intention category, and extracting corresponding initial reply information from the information database according to the user intention category;

[0038] Returning the initial reply information to the user interface for reply, and obtaining the user demand refinement information returned by the user;

[0039] Search the insurance field knowledge graph based on the user demand refinement information to obtain demand entity nodes and demand relationship edges;

[0040] Acquire node attribute information of related entity nodes according to the demand entity node and the demand relationship edge, and determine key attribute information in the node attribute information of the related entity nodes according to the user demand refinement information;

[0041] Matching a corresponding reply template in a preset reply template library according to the key attribute information and the user demand refinement information;

[0042] The key attribute information is filled into the reply template as a parameter to generate the first reply content, and the first reply content is sent to the user interface for reply.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides an information reply device, which adopts the following technical solution:

[0044] Information acquisition module, used to obtain insurance structure information and insurance non-structure information;

[0045] A graph construction module, configured to construct an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information;

[0046] An information parsing module is used to obtain user conversation information, perform semantic parsing on the user conversation information, and obtain conversation keywords and conversation semantic features;

[0047] An information reasoning module, configured to perform reasoning in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category;

[0048] A score comparison module, configured to calculate a confidence score for the user intent category and determine whether the confidence score is less than a preset confidence threshold;

[0049] A first processing module is configured to obtain user demand refinement information if the confidence score is less than the preset confidence threshold, and query the insurance field knowledge graph based on the user demand refinement information to generate a first reply content for reply;

[0050] The second processing module is used to search the insurance field knowledge graph according to the user intention category if the confidence score is greater than or equal to the preset confidence threshold, extract the corresponding knowledge information, fill the knowledge information into the preset reply template, and generate a second reply content for reply.

[0051] 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:

[0052] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the information reply method as described in any one of the above items when executing the computer-readable instructions.

[0053] 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:

[0054] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the information reply method as described in any one of the above items.

[0055] Compared with the prior art, the embodiment of the present application has the following advantages: the embodiment obtains insurance structural information and insurance non-structural information; constructs an insurance domain knowledge graph based on the insurance structural information and the insurance non-structural information; obtains user conversation information, performs semantic analysis on the user conversation information, obtains conversation keywords and conversation semantic features; performs reasoning in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category; calculates a confidence score for the user intent category, and determines whether the confidence score is less than a preset confidence threshold; if the confidence score is less than the preset confidence threshold, obtains user demand refinement information, and queries the insurance domain knowledge graph based on the user demand refinement information to generate a first reply content for reply; if the confidence score is greater than or equal to the preset confidence threshold, searches the insurance domain knowledge graph based on the user intent category, extracts corresponding knowledge information, and fills the knowledge information into a preset reply template to generate a second reply content for reply. In this way, accurate replies are effectively provided to the user conversation content, thereby improving the accuracy and effectiveness of the replies. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] 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.

[0057] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0058] Figure 2 A flowchart of an embodiment of the information reply method according to the present application;

[0059] Figure 3 yes Figure 2 A flowchart of a specific implementation of step S20;

[0060] Figure 4 yes Figure 2 A flowchart of a specific implementation of step S30;

[0061] Figure 5 yes Figure 2 A flowchart of a specific implementation of step S40;

[0062] Figure 6 yes Figure 2 A flowchart of a specific implementation of step S50;

[0063] Figure 7 yes Figure 2 A flowchart of a specific implementation of step S60;

[0064] Figure 8 is a structural diagram of an embodiment of an information reply device according to the present application;

[0065] Figure 9 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0066] 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.

[0067] References to "embodiments" herein 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 refer to unrelated or alternative embodiments that are 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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 .

[0073] It should be noted that the information reply method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the information reply device is generally set in the server / terminal device.

[0074] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0075] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for replying information according to the present application. The method for replying information includes the following steps:

[0076] Step S10, obtaining insurance structural information and insurance non-structural information;

[0077] In this embodiment, insurance structural information refers to structured insurance knowledge information, including insurance product information, underwriting rule information, and underwriting decision information. Insurance product information includes the name, type, coverage, policy term, and premium amount of the insurance product. Underwriting rule information includes personal factors such as the insured's age, health status, occupation, and lifestyle, as well as the nature, value, and risk level of the insured. Underwriting decision information includes underwriting conditions (such as premium adjustments, coverage limitations, etc.) and whether further investigation or a medical examination is required. Insurance unstructured information refers to unstructured insurance-related text. It includes policy terms and claims case information. Policy terms and conditions refer to the core content of the insurance contract, which stipulates the rights and obligations between the insurance company and the insured. Claims case information refers to actual claims cases handled by the insurance company, typically including detailed information such as the accident description, claims process, and payout amount. Claims case information is typically recorded in text format and may also include multimedia materials such as images and videos.

[0078] Step S20: constructing an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information;

[0079] In this embodiment, the insurance domain knowledge graph is a graph-based data structure that uses nodes (representing entities) and edges (representing relationships) to display various types of information in the insurance industry. These entities can include insurance products, insurance companies, customers, risk factors, etc., while relationships describe the interactions and connections between these entities. By constructing the insurance domain knowledge graph, users can quickly query relevant knowledge information and provide reliable and effective information responses.

[0080] Step S30: obtaining user conversation information, performing semantic analysis on the user conversation information, and obtaining conversation keywords and conversation semantic features;

[0081] In this embodiment, user conversation information refers to the records of user conversations with the system's question-and-answer robot. User conversation information includes user input (text input, voice input, etc.), system response information (text response information, voice response information, multimedia response information, etc.), and conversation metadata (conversation time, conversation turn information, session ID, etc.). By performing semantic analysis on user conversation information, we can accurately obtain conversation keywords and conversation semantic features that reflect the user's information acquisition intention in the conversation.

[0082] Step S40, inferring the user intention category in the insurance field knowledge graph based on the conversation keywords and the conversation semantic features;

[0083] In this embodiment, conversation keywords are insurance-related entities mentioned in user conversation information, such as insurance products, customers, and insurance companies. Conversation semantic features are keyword semantic information obtained by using word vector representation for conversation keywords. Word vector representation converts conversation keywords into word vectors to capture the semantic similarity and relevance between words. User intent categories refer to the categories corresponding to the information acquisition intent revealed in user conversations. These categories may include purchase inquiries, claim applications, product comparisons, or complaints.

[0084] Step S50, calculating the confidence score of the user intention category, and determining whether the confidence score is less than a preset confidence threshold;

[0085] In this embodiment, the confidence score refers to the credibility corresponding to the judgment result of the user intention category. By calculating the confidence score of the user intention category, the reliability of the user intention category is judged to perform corresponding information generation and reply processing.

[0086] Step S60: If the confidence score is less than the preset confidence threshold, obtaining user demand refinement information, and querying the insurance field knowledge graph based on the user demand refinement information to generate a first reply content for reply;

[0087] In this embodiment, user requirement refinement information is the response information collected from the user after the initial response information is generated. This initial response information may include template information to guide the user in refining their requirements, such as "Please refine your current requirements to obtain a more accurate response information." The first response content is a system response generated by combining key attribute information obtained through a specific search within the insurance knowledge graph based on the user requirement refinement information with the corresponding response template. After the system generates the first response content, it is returned to the user through the corresponding path in the user interface for display.

[0088] Step S70: If the confidence score is greater than or equal to the preset confidence threshold, a search is performed in the insurance field knowledge graph according to the user intention category, the corresponding knowledge information is extracted, and the knowledge information is filled into the preset reply template to generate a second reply content for reply.

[0089] In this embodiment, a search is performed in the insurance field knowledge graph based on the user intent category to match the corresponding entities and relationships, thereby obtaining the knowledge information corresponding to the entities and relationships, and filling this part of the knowledge information into the preset reply template to generate a reply text message and return it to the user interface for reply.

[0090] This embodiment obtains insurance structural information and insurance non-structural information; constructs an insurance domain knowledge graph based on the insurance structural information and the insurance non-structural information; obtains user conversation information, performs semantic analysis on the user conversation information to obtain conversation keywords and conversation semantic features; infers the conversation keywords and the conversation semantic features in the insurance domain knowledge graph to obtain a user intent category; calculates a confidence score for the user intent category and determines whether the confidence score is less than a preset confidence threshold; if the confidence score is less than the preset confidence threshold, obtains user demand refinement information and queries the insurance domain knowledge graph based on the user demand refinement information to generate a first reply content for reply; if the confidence score is greater than or equal to the preset confidence threshold, searches the insurance domain knowledge graph based on the user intent category to extract corresponding knowledge information, and fills the knowledge information into a preset reply template to generate a second reply content for reply. This effectively provides accurate replies to user conversation content, thereby improving the accuracy and effectiveness of replies.

[0091] In some optional implementations of this embodiment, obtaining insurance structural information and insurance non-structural information includes the following steps:

[0092] Obtaining a structural information extraction identifier, and extracting insurance product information, underwriting rule information, and underwriting decision information from a database according to the knowledge information extraction identifier;

[0093] In this embodiment, the structural information extraction identifier is identification information corresponding to the insurance product information, underwriting rule information, and underwriting decision information. The structural information extraction identifier is used to perform a matching query in the database to effectively obtain the insurance product information, underwriting rule information, and underwriting decision information.

[0094] Obtaining a non-structured information extraction identifier, and extracting insurance clause information and claim case information from a database according to the non-structured information extraction identifier;

[0095] In this embodiment, the non-structured information extraction identifier is identification information corresponding to the insurance clause information and the claim case information. The non-structured information extraction identifier is used to perform a matching query in the database to effectively obtain the insurance clause information and the claim case information.

[0096] performing a first preprocessing on the insurance product information, the underwriting rule information, and the underwriting decision information to obtain the insurance structure information;

[0097] In this embodiment, the first preprocessing includes data cleaning (removing redundant information and correcting erroneous data), data standardization and structuring (defining data structure and standardizing data), and information extraction and summarization (extracting key information and summarizing information). This first preprocessing is performed on insurance product information, underwriting rules information, and underwriting decision information to obtain standardized and valid insurance structure information.

[0098] The extracted insurance clause information and the claim case information are subjected to a second preprocessing to obtain the insurance non-structured information.

[0099] In this embodiment, the second preprocessing includes data cleaning (removing irrelevant information, standardizing formats, and processing special characters), text segmentation and standardization, and information extraction (entity recognition, relationship extraction, and event extraction). This second preprocessing of insurance clause information and claim case information yields standardized and valid insurance unstructured information.

[0100] This embodiment obtains a structural information extraction identifier and extracts insurance product information, underwriting rule information, and underwriting decision information from a database based on the knowledge information extraction identifier; obtains a non-structural information extraction identifier and extracts insurance clause information and claim case information from a database based on the non-structural information extraction identifier; performs a first preprocessing on the insurance product information, underwriting rule information, and underwriting decision information to obtain the insurance structural information; and performs a second preprocessing on the extracted insurance clause information and claim case information to obtain the insurance non-structural information. This effectively and accurately obtains structured insurance structural information and unstructured insurance non-structural information, providing effective and reliable data support for the subsequent construction of a knowledge graph in the insurance field.

[0101] refer to Figure 3 In some optional implementations of this embodiment, step S20 includes the following steps:

[0102] Step S201: define insurance business entities, insurance business attributes, and insurance business entity relationships to construct insurance domain knowledge ontology;

[0103] In this embodiment, an ontology modeling method is adopted to define the core business entities in the insurance field, wherein the core business entities include insurance policies, customers and claims. At the same time, the key attributes of the core business entities are defined. By analyzing the relationships between insurance business entities, an entity relationship model is constructed. The relationship includes the ownership relationship between insurance policies and customers and the corresponding relationship between insurance policies and claims. The defined insurance business entities, key attributes and the relationships are integrated to form a knowledge ontology of the insurance field.

[0104] Step S202: integrating the insurance structure information into the insurance domain knowledge ontology to obtain an insurance domain knowledge graph framework;

[0105] In this embodiment, key information elements of insurance structure information are extracted using a knowledge extraction algorithm. These extracted key information elements are then mapped to the insurance domain knowledge ontology for integration, thereby obtaining an insurance domain knowledge graph framework. A knowledge extraction algorithm is a technology that automatically identifies and extracts key information from structured or semi-structured data. The knowledge extraction algorithm is used to parse and extract insurance structure information. This step involves identifying and extracting key information elements related to insurance business entities, attributes, and relationships, such as the name of the policyholder, the identity of the insured, the type of insurance product, the insurance amount, the premium, underwriting conditions, and the claim settlement results. According to the structure of the knowledge ontology in the insurance field, the mapping rules between key information elements and entities, attributes and relationships in the knowledge ontology are defined. The extracted key information elements are mapped according to the defined mapping rules. This step includes matching the information elements with entities in the knowledge ontology, filling the attribute values ​​into the corresponding attribute fields, and establishing relationship links between entities. On the basis of the mapping, the extracted key information elements are integrated with the existing information in the knowledge ontology. This step includes dealing with problems such as information redundancy, conflict and missing information to ensure the accuracy and completeness of the knowledge graph.

[0106] Step S203: extract key information from the insurance non-structured information to obtain non-structured key information, and integrate the non-structured key information into the insurance field knowledge graph framework to obtain the insurance field knowledge graph.

[0107] In this embodiment, for insurance clause text data, a rule-based and pattern matching method is used to extract the underwriting rules in the insurance clauses, wherein the underwriting rules include the insured object, insurance liability and exclusions; for claim case text data, a deep learning-based knowledge extraction method is used to extract the claim decision information in the claim case, wherein the claim decision information includes the compensation amount and compensation conditions; the extracted underwriting rules and claim decision information are structured, and the structured underwriting rules and claim decision information are fused with the pre-built insurance domain knowledge graph framework to obtain a fused insurance domain knowledge graph, wherein the fusion includes entity alignment and relationship alignment. During the knowledge fusion process, a knowledge conflict detection method can be used to check the consistency of the newly added knowledge with the existing knowledge. If a conflict is detected, it is reviewed and corrected to ensure that the final insurance domain knowledge graph is valid and correct.

[0108] This embodiment constructs an insurance field knowledge ontology by defining insurance business entities, insurance business attributes, and insurance business entity relationships; integrates the insurance structural information into the insurance field knowledge ontology to obtain an insurance field knowledge graph framework; extracts key information from the insurance non-structural information to obtain non-structural key information, and integrates the non-structural key information into the insurance field knowledge graph framework, thereby obtaining an insurance field knowledge graph that effectively integrates insurance structural information and insurance non-structural information to facilitate subsequent knowledge reasoning processing.

[0109] refer to Figure 4 In some optional implementations of this embodiment, step S30 includes the following steps:

[0110] Step S301: accessing user conversation records and extracting user conversation information from the user conversation records;

[0111] In this embodiment, user conversation records are historical conversation records between the user and the system Q&A robot. The user conversation information required for the current Q&A session is extracted from the user conversation records using the corresponding timestamp to ensure the validity of the user conversation information. For example, if the user starts the Q&A session on the system at 3:10, the historical conversation records after that time are extracted based on the timestamp to obtain the user conversation information.

[0112] Step S302: performing word segmentation and part-of-speech tagging on the user conversation information to obtain conversation representation information;

[0113] In this embodiment, word segmentation refers to the process of breaking a continuous text string into individual words or phrases. Word segmentation can be performed on user conversation information using a corresponding word segmentation tool. Part-of-speech tagging refers to assigning a part-of-speech label, such as noun, verb, or adjective, to each word based on word segmentation. This part-of-speech standard can also be performed using a word segmentation tool.

[0114] Step S303: performing named entity recognition on the conversation representation information to extract the conversation keywords from the conversation representation information;

[0115] In this embodiment, named entity recognition of conversation representation information can be achieved through a pre-trained NER model (such as BERT), by inputting the conversation representation information into the pre-trained NER model to output the corresponding NER model results, and then filtering out conversation keywords in the conversation representation information based on the NER model results.

[0116] Step S304: performing word vector representation on the conversation keywords to obtain keyword semantic information, and using the keyword semantic information as the conversation semantic feature.

[0117] In this embodiment, a pre-trained word vector model (a BERT model may be used) is used to represent conversation keywords using word vectors. The conversation keywords are input into the pre-trained word vector model to obtain corresponding word vectors. The cosine similarity of the word vectors is then calculated, cluster analysis is performed, and dimensionality reduction projection analysis is performed to obtain semantic relationships and potential semantic categories between keywords, thereby obtaining keyword semantic information.

[0118] This embodiment accesses user conversation records to extract user conversation information; performs word segmentation and part-of-speech tagging on the conversation information to obtain conversation representation information; performs named entity recognition on the conversation representation information to extract conversation keywords; represents the conversation keywords with word vectors to obtain keyword semantic information, and uses this keyword semantic information as the conversation semantic features. This allows for accurate acquisition of conversation keywords and conversation semantic features during user communication, facilitating subsequent inference operations based on user intent categories.

[0119] Continue to refer Figure 5 In some optional implementations of this embodiment, step S40 includes the following steps:

[0120] Step S401: Input the conversation keywords and the conversation semantic features into the insurance field knowledge graph, perform reasoning on the insurance field knowledge graph based on a knowledge reasoning algorithm, and obtain a knowledge reasoning result;

[0121] In this embodiment, by taking conversation keywords and conversation semantic features as input, the input is mapped to the corresponding nodes and relationships of the insurance field knowledge graph, where nodes represent entities in the insurance field, such as insurance products, customers, risks, etc.; relationships describe the associations between these entities, such as "belong to", "contain", "related", etc., and rule-based reasoning algorithms are applied to reason on nodes and relationships to obtain knowledge reasoning results.

[0122] Step S402: input the knowledge reasoning result into a pre-built intention recognition model to obtain the user intention category.

[0123] In this embodiment, user intent categories refer to the user's intent to obtain information during a conversation, and may include purchase inquiries, claim applications, product comparisons, or complaints. The pre-built intent recognition model can employ a decision tree model, which is trained and optimized by acquiring labeled sample data. This allows the decision tree model to accurately identify the corresponding user intent category based on the input data.

[0124] This embodiment inputs the conversation keywords and conversation semantic features into the insurance domain knowledge graph, performs reasoning on the insurance domain knowledge graph based on a knowledge reasoning algorithm, and obtains knowledge reasoning results. This knowledge reasoning result is then input into a pre-built intent recognition model to obtain the user intent category. This effectively achieves accurate user conversation intent recognition, facilitating subsequent confidence assessment based on the identified user intent category.

[0125] Continue to refer Figure 6 In some optional implementations of this embodiment, step S50 includes the following steps:

[0126] Step S501: input the user conversation information and the user intention category into a pre-built confidence prediction model to obtain the confidence score;

[0127] In this embodiment, the pre-built confidence prediction model can adopt a support vector machine model. This model is trained using a labeled dataset (containing user conversation information, corresponding intent categories, and confidence labels) to obtain a confidence prediction model that accurately outputs confidence scores. Corresponding features are then extracted from the user conversation information and user intent categories (using word embeddings such as Word2Vec and BERT), and these features are input into the confidence prediction model to obtain the corresponding confidence score. In this embodiment, the confidence score can be an integer or a percentage value on a percentage scale.

[0128] Step S502: Match the confidence scores with the user intent categories to obtain an intent confidence score set;

[0129] In this embodiment, each user intent category corresponds to a confidence score. User conversation information can include multiple user intent categories, allowing the output response to better suit the user's personality and needs. By associating user intent categories with confidence scores, a set of intent confidence scores is generated, including the categories and their corresponding confidence scores.

[0130] Step S503, extracting a corresponding preset confidence threshold from the database according to the user intention category;

[0131] In this embodiment, each user intent category corresponds to a different preset confidence threshold. For example, if the user intent category is product comparison, the preset confidence threshold is 70; if the user intent category is claim application, the preset confidence threshold is 80. This is because different user intent categories correspond to different conversation words and emotional values. During the specific implementation process, the preset confidence threshold can be set and adjusted according to actual conditions.

[0132] Step S504 : sorting the intention confidence score set from high to low according to the confidence score, and extracting the confidence score ranked first to compare with the preset confidence threshold.

[0133] In this embodiment, by sorting the intent confidence score set from high to low, the confidence score with the highest ranking can be directly extracted, and the user intent category corresponding to this confidence score is used as the primary user intent for reply determination. In specific implementations, multiple confidence scores can be compared according to the order of the sorted intent confidence score set, and different reply contents can be generated based on the comparison results. The different reply contents can then be merged according to certain rules to obtain diversified reply information for user replies.

[0134] This embodiment inputs the user conversation information and the user intent category into a pre-built confidence prediction model to obtain the confidence score; then associates the confidence score with the user intent category to obtain a set of intent confidence scores; then, based on the user intent category, extracts the corresponding preset confidence threshold from the database; and finally, sorts the set of intent confidence scores from high to low confidence score, extracting the top-ranked confidence score and comparing it with the preset confidence threshold. This effectively determines the accuracy of the user intent category, facilitating subsequent processing based on the determination result.

[0135] Continue to refer Figure 7 In some optional implementations of this embodiment, step S60 includes the following steps:

[0136] Step S601, determining a corresponding information database according to the user intention category, and extracting corresponding initial reply information from the information database according to the user intention category;

[0137] In this embodiment, the user intent category is used as a query condition to match the corresponding information database. Then, a traversal query is performed within the information database using the category keyword corresponding to the user intent category to extract the corresponding initial response information. This initial response information is a standard template response information pre-set based on the user intent category, and the content can be modified according to actual circumstances.

[0138] Step S602: returning the initial reply information to the user interface for reply, and obtaining the user demand refinement information returned by the user;

[0139] In this embodiment, the initial response information may include content guiding the user to refine their needs, such as "Please refine your current needs to obtain more accurate response information." By returning the initial response information to the user interface for reply, the user is effectively guided to provide more detailed user need details to facilitate subsequent processing.

[0140] Step S603: Search the insurance field knowledge graph based on the user demand refinement information to obtain demand entity nodes and demand relationship edges;

[0141] In this embodiment, a corresponding search query is constructed based on user demand refinement information. The search query can be a combination of one or more keywords or a more complex query statement, which is used to locate relevant entity nodes and relationship edges in the knowledge graph. The constructed search query is then input into the knowledge graph system in the insurance field to retrieve and return relevant entity nodes and relationship edges, thereby effectively obtaining entity nodes and demand relationship edges.

[0142] Step S604: acquiring node attribute information of related entity nodes according to the demand entity node and the demand relationship edge, and determining key attribute information in the node attribute information of the related entity nodes according to the user demand refinement information;

[0143] In this embodiment, starting from a demand entity node, the knowledge graph is traversed along the relationship edges to other related entity nodes. For each traversed related entity node, node attribute information is extracted. For example, a demand entity node represents an insurance product, a customer, a risk event, etc., while a demand relationship edge represents the purchasing relationship between the product and the customer, or the association between the risk event and the insurance product. Node attribute information includes information such as the insurance product's premium, coverage, and claim conditions; the customer's age, occupation, and health status; and the type and probability of the risk event. This analysis analyzes the detailed description of user demand information, including detailed information that significantly influences decision-making. This detailed information includes the user's specific requirements for the insurance product (such as coverage and premium budget); their level of concern for risk events (such as high-probability risk events); and a description of the customer's own situation (such as age and health status). Based on the detailed user demand information, key attribute information directly related to the user's demand is filtered from the extracted node attribute information. In this embodiment, the filtered key attribute information can be sorted to facilitate finding the most important information.

[0144] Step S605: matching a corresponding reply template in a preset reply template library according to the key attribute information and the user demand refinement information;

[0145] In this embodiment, similarity matching is performed in the preset reply template library through the information content of key attribute information and user demand refinement information, and a text similarity algorithm (such as cosine similarity, Jaccard similarity, edit distance, etc.) can be used to calculate the similarity between the extracted information and the preset reply template, so as to find the corresponding reply template.

[0146] Step S606: Fill the key attribute information into the reply template as a parameter to generate the first reply content, and send the first reply content to the user interface for reply.

[0147] In this embodiment, after filling the key attribute information into the reply template, the generated reply information can be checked. The checking steps include data format check, internal logic check, external logic check, language quality check, etc. When the check is completed, the generated reply information is sent as the first reply content to the user interface for reply.

[0148] This embodiment determines the corresponding information database according to the user intention category, and extracts the corresponding initial reply information from the information database according to the user intention category; returns the initial reply information to the user interface for reply, and obtains the user demand refinement information returned by the user; searches the insurance field knowledge graph according to the user demand refinement information to obtain demand entity nodes and demand relationship edges; obtains node attribute information of related entity nodes according to the demand entity nodes and the demand relationship edges, and determines key attribute information in the node attribute information of the related entity nodes according to the user demand refinement information; matches the corresponding reply template in the preset reply template library according to the key attribute information and the user demand refinement information; fills the key attribute information into the reply template as a parameter, generates the first reply content, and sends the first reply content to the user interface for reply. This effectively achieves the regeneration of the first reply content that better meets the user intention and needs for user reply, thereby improving the accuracy of the reply to user information.

[0149] 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).

[0150] 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.

[0151] Further references Figure 8 , as a response to the above Figure 1 In order to realize the method shown in the figure, the present application provides an embodiment of an information reply device. Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0152] like Figure 8 As shown, the information reply device 800 of this embodiment includes: an information acquisition module 801, a graph construction module 802, an information analysis module 803, an information reasoning module 804, a score comparison module 805, a first processing module 806, and a second processing module 807. Among them:

[0153] Information acquisition module 801, used to acquire insurance structure information and insurance non-structure information;

[0154] A graph construction module 802 is used to construct an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information;

[0155] An information parsing module 803 is used to obtain user conversation information, perform semantic parsing on the user conversation information, and obtain conversation keywords and conversation semantic features;

[0156] An information reasoning module 804 is configured to perform reasoning in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category;

[0157] Score comparison module 805, used to calculate the confidence score of the user intention category and determine whether the confidence score is less than a preset confidence threshold;

[0158] A first processing module 806 is configured to obtain user demand refinement information if the confidence score is less than the preset confidence threshold, and query the insurance field knowledge graph based on the user demand refinement information to generate a first reply content for reply;

[0159] The second processing module 807 is used to search the insurance field knowledge graph according to the user intention category if the confidence score is greater than or equal to the preset confidence threshold, extract the corresponding knowledge information, fill the knowledge information into the preset reply template, and generate a second reply content for reply.

[0160] This embodiment, by employing the above-mentioned information reply device, can obtain insurance structural information and insurance non-structural information; construct an insurance domain knowledge graph based on the insurance structural information and the insurance non-structural information; obtain user conversation information, perform semantic analysis on the user conversation information to obtain conversation keywords and conversation semantic features; perform inference in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category; calculate a confidence score for the user intent category and determine whether the confidence score is less than a preset confidence threshold; if the confidence score is less than the preset confidence threshold, obtain user demand refinement information and query the insurance domain knowledge graph based on the user demand refinement information to generate a first reply content for reply; if the confidence score is greater than or equal to the preset confidence threshold, search the insurance domain knowledge graph based on the user intent category to extract corresponding knowledge information, and fill the knowledge information into a preset reply template to generate a second reply content for reply. This effectively provides accurate replies to the user conversation content, thereby improving the accuracy and effectiveness of the replies.

[0161] To solve the above technical problems, the present application also provides a computer device. Figure 9 , Figure 9 This is a basic structural block diagram of the computer device in this embodiment.

[0162] The computer device 9 includes a memory 91, a processor 92, and a network interface 93 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 9 with components 91-93, 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 microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0163] 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.

[0164] The memory 91 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, 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, magnetic disk, optical disk, etc. In some embodiments, the memory 91 may be an internal storage unit of the computer device 9, such as the hard disk or memory of the computer device 9. In other embodiments, the memory 91 may also be an external storage device of the computer device 9, such as a plug-in hard disk equipped on the computer device 9, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. Of course, the memory 91 may also include both the internal storage unit of the computer device 9 and its external storage device. In this embodiment, the memory 91 is generally used to store the operating system and various application software installed on the computer device 9, such as computer-readable instructions of the information reply method. In addition, the memory 91 can also be used to temporarily store various types of data that have been output or are to be output.

[0165] In some embodiments, the processor 92 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 92 is generally used to control the overall operation of the computer device 9. In this embodiment, the processor 92 is used to execute computer-readable instructions stored in the memory 91 or process data, such as computer-readable instructions for executing the information reply method.

[0166] The network interface 93 may include a wireless network interface or a wired network interface. The network interface 93 is generally used to establish a communication connection between the computer device 9 and other electronic devices.

[0167] This embodiment, by employing the aforementioned computer device, can obtain insurance structural information and insurance non-structural information; construct an insurance domain knowledge graph based on the insurance structural information and the insurance non-structural information; obtain user conversation information, perform semantic analysis on the user conversation information to obtain conversation keywords and conversation semantic features; perform inference in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category; calculate a confidence score for the user intent category and determine whether the confidence score is less than a preset confidence threshold; if the confidence score is less than the preset confidence threshold, obtain user demand refinement information and query the insurance domain knowledge graph based on the user demand refinement information to generate a first reply content for reply; if the confidence score is greater than or equal to the preset confidence threshold, search the insurance domain knowledge graph based on the user intent category to extract corresponding knowledge information, and fill the knowledge information into a preset reply template to generate a second reply content for reply. This effectively provides accurate replies to the user conversation content, thereby improving the accuracy and effectiveness of the replies.

[0168] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the information reply method as described above.

[0169] This embodiment, by using the computer-readable storage medium, can obtain insurance structural information and insurance non-structural information; construct an insurance domain knowledge graph based on the insurance structural information and the insurance non-structural information; obtain user conversation information, perform semantic analysis on the user conversation information to obtain conversation keywords and conversation semantic features; perform inference in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category; calculate a confidence score for the user intent category and determine whether the confidence score is less than a preset confidence threshold; if the confidence score is less than the preset confidence threshold, obtain user demand refinement information, and query the insurance domain knowledge graph based on the user demand refinement information to generate a first reply content for reply; if the confidence score is greater than or equal to the preset confidence threshold, search the insurance domain knowledge graph based on the user intent category, extract corresponding knowledge information, and fill the knowledge information into a preset reply template to generate a second reply content for reply. This effectively provides accurate replies to the user conversation content, thereby improving the accuracy and effectiveness of the replies.

[0170] 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.

[0171] 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 replying information, characterized in that: The steps include: Obtain insurance structure information and insurance non-structure information; Constructing an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information; Obtaining user conversation information, performing semantic analysis on the user conversation information, and obtaining conversation keywords and conversation semantic features; Reasoning in the insurance field knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category; Calculating a confidence score for the user intent category, and determining whether the confidence score is less than a preset confidence threshold; If the confidence score is less than the preset confidence threshold, obtaining user demand refinement information, and querying the insurance field knowledge graph based on the user demand refinement information to generate a first reply content for reply; If the confidence score is greater than or equal to the preset confidence threshold, a search is performed in the insurance field knowledge graph based on the user intent category, corresponding knowledge information is extracted, and the knowledge information is filled into a preset reply template to generate a second reply content for reply; The step of calculating the confidence score of the user intention category and determining whether the confidence score is less than a preset confidence threshold specifically includes: Inputting the user conversation information and the user intent category into a pre-built confidence prediction model to obtain the confidence score; Matching the confidence scores with the user intent categories to obtain an intent confidence score set; Extracting a corresponding preset confidence threshold from a database according to the user intention category; Sorting the intention confidence score set from high to low according to the confidence score, and extracting the confidence score ranked first for comparison with the preset confidence threshold; The step of obtaining detailed user demand information, querying the insurance field knowledge graph based on the detailed user demand information, and obtaining the first reply content for replying specifically includes: determining a corresponding information database according to the user intention category, and extracting corresponding initial reply information from the information database according to the user intention category; Returning the initial reply information to the user interface for reply, and obtaining the user demand refinement information returned by the user; Search the insurance field knowledge graph based on the user demand refinement information to obtain demand entity nodes and demand relationship edges; Acquire node attribute information of related entity nodes according to the demand entity node and the demand relationship edge, and determine key attribute information in the node attribute information of the related entity nodes according to the user demand refinement information; Matching a corresponding reply template in a preset reply template library according to the key attribute information and the user demand refinement information; The key attribute information is filled into the reply template as a parameter to generate the first reply content, and the first reply content is sent to the user interface for reply.

2. The information reply method according to claim 1, characterized in that: The step of obtaining insurance structure information and insurance non-structure information specifically includes: Obtaining a structural information extraction identifier, and extracting insurance product information, underwriting rule information, and underwriting decision information from a database according to the knowledge information extraction identifier; Obtaining a non-structured information extraction identifier, and extracting insurance clause information and claim case information from a database according to the non-structured information extraction identifier; performing a first preprocessing on the insurance product information, the underwriting rule information, and the underwriting decision information to obtain the insurance structure information; The extracted insurance clause information and the claim case information are subjected to a second preprocessing to obtain the insurance non-structured information.

3. The information reply method according to claim 1, characterized in that: The step of constructing an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information specifically includes: Define insurance business entities, insurance business attributes, and insurance business entity relationships, and construct insurance domain knowledge ontology; Integrating the insurance structure information into the insurance domain knowledge ontology to obtain an insurance domain knowledge graph framework; Key information is extracted from the insurance non-structured information to obtain non-structured key information, and the non-structured key information is integrated into the insurance field knowledge graph framework to obtain the insurance field knowledge graph.

4. The information reply method according to claim 1, characterized in that: The steps of obtaining user conversation information, performing semantic analysis on the user conversation information, and obtaining conversation keywords and conversation semantic features specifically include: Accessing user session records, and extracting the user conversation information from the user session records; Performing word segmentation and part-of-speech tagging on the user conversation information to obtain conversation representation information; performing named entity recognition on the conversation representation information to extract the conversation keywords from the conversation representation information; The conversation keywords are represented by word vectors to obtain keyword semantic information, and the keyword semantic information is used as the conversation semantic feature.

5. The information reply method according to claim 1, characterized in that: The step of inferring the user intent category in the insurance field knowledge graph based on the conversation keywords and the conversation semantic features specifically includes: Inputting the conversation keywords and the conversation semantic features into the insurance field knowledge graph, and performing reasoning on the insurance field knowledge graph based on a knowledge reasoning algorithm to obtain a knowledge reasoning result; The knowledge reasoning result is input into a pre-built intention recognition model to obtain the user intention category.

6. An information reply device, characterized in that: include: Information acquisition module, used to obtain insurance structure information and insurance non-structure information; A graph construction module, configured to construct an insurance field knowledge graph based on the insurance structure information and the insurance non-structure information; An information parsing module is used to obtain user conversation information, perform semantic parsing on the user conversation information, and obtain conversation keywords and conversation semantic features; An information reasoning module, configured to perform reasoning in the insurance domain knowledge graph based on the conversation keywords and the conversation semantic features to obtain a user intent category; A score comparison module, configured to calculate a confidence score for the user intent category and determine whether the confidence score is less than a preset confidence threshold; A first processing module is configured to obtain user demand refinement information if the confidence score is less than the preset confidence threshold, and query the insurance field knowledge graph based on the user demand refinement information to generate a first reply content for reply; A second processing module is configured to, if the confidence score is greater than or equal to the preset confidence threshold, search the insurance field knowledge graph based on the user intent category, extract corresponding knowledge information, fill the knowledge information into a preset reply template, and generate a second reply content for reply; The score comparison module is also used to: Inputting the user conversation information and the user intent category into a pre-built confidence prediction model to obtain the confidence score; Matching the confidence scores with the user intent categories to obtain an intent confidence score set; Extracting a corresponding preset confidence threshold from a database according to the user intention category; Sorting the intention confidence score set from high to low according to the confidence score, and extracting the confidence score ranked first for comparison with the preset confidence threshold; The first processing module is further configured to: determining a corresponding information database according to the user intention category, and extracting corresponding initial reply information from the information database according to the user intention category; Returning the initial reply information to the user interface for reply, and obtaining the user demand refinement information returned by the user; Search the insurance field knowledge graph based on the user demand refinement information to obtain demand entity nodes and demand relationship edges; Acquire node attribute information of related entity nodes according to the demand entity node and the demand relationship edge, and determine key attribute information in the node attribute information of the related entity nodes according to the user demand refinement information; Matching a corresponding reply template in a preset reply template library according to the key attribute information and the user demand refinement information; The key attribute information is filled into the reply template as a parameter to generate the first reply content, and the first reply content is sent to the user interface for reply.

7. 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 information reply method according to any one of claims 1 to 5 when executing the computer-readable instructions.

8. 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 information reply method according to any one of claims 1 to 5.

Images