Data processing method and device based on natural language model and electronic equipment

Abstract

The embodiment of the invention provides a data processing method and device based on a natural language model and electronic equipment, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring financial data information and to-be-answered question information; performing knowledge representation on the financial data information, and creating a first data structure and a second data structure; creating an insurance data set according to the first data structure and the second data structure; training a preset natural language model through the insurance data set to obtain an automatic question and answer language model; in response to a user retrieval instruction, performing text analysis on the to-be-answered question information to obtain an analysis result; performing answer retrieval on the analysis result based on an automatic question and answer language model and an insurance data set to obtain a retrieval set; and when the retrieval set is empty or the preset answer statement does not exist in the retrieval set, converting the user retrieval instruction into a manual service conversion instruction. According to the embodiment of the invention, the problem processing efficiency and the service quality can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a data processing method, device, electronic device and medium based on a natural language model. Background Art

[0002] In the daily operation of the insurance industry, the stable operation of the business system is crucial to ensuring the quality of customer service and improving business processing efficiency. However, with the increasing complexity of insurance business and the continuous upgrading of technical systems, business system problems frequently occur, which are usually submitted to the system operation team in the form of work orders for processing.

[0003] Most existing work order processing systems rely on manual operations and simple automated processes, lacking intelligent support. This makes it difficult for the system to respond quickly to complex or unexpected problems, affecting the efficiency and quality of problem solving. In addition, due to low work order processing efficiency and frequent repetitive problems, customers often have to wait a long time to get answers or solutions to their problems, and the answers may not be consistent with customer expectations. This not only reduces customer satisfaction, but may also have a negative impact on the insurance company's brand image. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a data processing method, device, electronic device and medium based on a natural language model, which can improve the efficiency of problem handling and service quality and avoid the situation where the answer is inconsistent with the customer's expectations.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a data processing method based on a natural language model, the method comprising: Acquire financial data information and information about questions to be answered, wherein the financial data information includes a plurality of information about questions; Performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the problem information, wherein the first data structure is a data structure corresponding to a common problem, and the second data structure is a data structure corresponding to an associated problem; creating an insurance data set according to the first data structure and the second data structure; A preset natural language model is trained by using the insurance data set to obtain an automatic question-answering language model; In response to a user search instruction, performing text analysis on the question information to be answered to obtain an analysis result; Perform answer retrieval on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a retrieval set; When the search set is empty or there is no preset answer statement in the search set, the user search instruction is converted into a manual service instruction.

[0006] In some embodiments, the performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the question information includes: Performing data cleaning on the financial data information; Perform synonymous expansion on the financial data information after data cleaning to obtain a financial database; determining frequently asked questions information and frequently asked questions answers in the financial database; Establishing a first data structure according to the common question information and the common question answers; Performing part-of-speech analysis on the financial database to determine related question information and answers to related questions; A second data structure is established according to the associated question information and the associated question answers.

[0007] In some embodiments, the performing text analysis on the question information to be answered to obtain the analysis result includes: Performing word segmentation processing on the question information to be answered to obtain multiple question texts; Perform part-of-speech tagging on all the question texts to obtain tagging information; Extract keywords from the question text according to the annotation information to determine keyword information in the question text; An analysis result is generated according to the question text, the annotation information and the keyword information.

[0008] In some embodiments, the user search instruction includes a first user search instruction and a second user search instruction; the answer search is performed on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a search set, including: Extracting key entities in the analysis result according to the keyword information; In response to a first user search instruction, searching the key entity through the insurance data set; When the key entity does not exist in the insurance data set, performing synonymous replacement on the key entity to obtain replacement information; Retrieving the replacement information through the insurance data set; When the replacement information does not exist in the insurance data set, the analysis result is retrieved through the automatic question-answering language model to obtain a retrieval set.

[0009] In some embodiments, the searching the analysis results by the automatic question-answering language model to obtain a search set includes: In response to a second user search instruction, inputting the analysis result into the automatic question answering language model, so that the automatic question answering language model performs word vectorization on the annotation information to convert the annotation information into a vector of a preset length to obtain a word vector; Performing semantic analysis on the word vector by using the automatic question-answering language model, and outputting the analysis answer; The analysis answers are sorted to obtain a retrieval set.

[0010] In some embodiments, after converting the user search instruction into a manual service instruction, the method further includes: Collect manual response information; Performing sensitive information detection on the manual reply information; When the manual reply information passes the sensitive information detection, generating target reply information corresponding to the question information to be answered according to the manual reply information; The unanswered question information and the target answer information are added to the insurance dataset.

[0011] In some embodiments, after performing answer retrieval on the analysis result based on the automatic question-answering language model and the insurance dataset to obtain a retrieval set, the method further includes: When the search set is not empty and there is a preset answer sentence in the search set, a target answer sentence is determined in the search set.

[0012] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a data processing device based on a natural language model, the device comprising: An information acquisition module, used to acquire financial data information and information on questions to be answered, wherein the financial data information includes a plurality of question information; A knowledge representation module, used for performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the problem information, wherein the first data structure is a data structure corresponding to a common problem, and the second data structure is a data structure corresponding to an associated problem; A data set creation module, used to create an insurance data set according to the first data structure and the second data structure; A model training module, used to train a preset natural language model through the insurance data set to obtain an automatic question-answering language model; A text analysis module, used to perform text analysis on the question information to be answered in response to a user search instruction, and obtain an analysis result; An answer retrieval module, used to perform answer retrieval on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a retrieval set; The manual transfer module is used to convert the user search instruction into a manual service transfer instruction when the search set is empty or there is no preset answer statement in the search set.

[0013] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the data processing method based on the natural language model as described in the first aspect when executing the computer program.

[0014] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the data processing method based on the natural language model as described in the first aspect.

[0015] The data processing method, device, electronic device and storage medium based on the natural language model proposed in the present application first obtain financial data information and question information to be answered, and perform knowledge representation on the financial data information, so as to achieve accurate analysis of the financial data information, so as to create a first data structure and a second data structure corresponding to the question information in the financial data information, and achieve the creation of data structures for common problems and related problems, and then create an insurance data set based on the first data structure and the second data structure to achieve the construction of a professional database, so that a variety of question information can be integrated into the insurance data set to facilitate subsequent comprehensive retrieval of questions, and then, train a preset natural language model through the insurance data set, so that the natural language model can automatically process a large amount of text data, and obtain an automatic question-answering language model, so as to reduce Manual intervention, in response to user search instructions, performs text analysis on the questions to be answered, thereby analyzing the keywords that need to be searched in the information of the questions to be answered, obtaining analysis results, realizing accurate retrieval of the information of the questions to be answered, improving retrieval accuracy, and then performing answer retrieval on the analysis results based on the automatic question-answering language model and the insurance data set, realizing comprehensive retrieval of the information of the questions to be answered, and obtaining a search set, which can improve the efficiency of problem handling and service quality. When the search set is empty or there is no preset answer statement in the search set, it means that the information of the questions to be answered input by the user has not been solved, and then the user search instruction needs to be converted into a manual service instruction, so that the information of the questions to be answered can be manually replied, avoiding the situation where the answers are inconsistent with customer expectations, and realizing accurate answers to the information of the questions to be answered. The embodiment of the present application creates multiple data structures by performing knowledge representation on financial data information, and then creates an insurance data set through multiple data structures, and trains a natural language model, so as to realize automatic question-answering of the information of the questions to be answered, reduce manual input, and improve the efficiency of problem handling. In addition, when the search set is empty or there is no preset answer statement in the search set, the embodiment of the present application will perform a manual operation, thereby avoiding the situation where the answers are inconsistent with customer expectations, and realizing accurate answers to the information of the questions to be answered. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a data processing method based on a natural language model provided in an embodiment of the present application; Figure 2 yes Figure 1 Flow chart of step S102 in FIG. Figure 3 A flowchart of a method for performing text analysis on question information to be answered provided in an embodiment of the present application; Figure 4 yes Figure 1 Flow chart of step S106 in FIG. Figure 5A flow chart of a method for retrieving analysis results through an automatic question-answering language model provided in an embodiment of the present application; Figure 6 is a flow chart of a data processing method based on a natural language model provided by another embodiment of the present application; Figure 7 is a flow chart of a data processing method based on a natural language model provided by another embodiment of the present application; Figure 8 is a schematic diagram of the structure of a data processing device based on a natural language model provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0020] First, some nouns involved in this application are analyzed: Natural Language Processing (NLP): NLP uses computers to process, understand, and apply human languages ​​(such as Chinese, English, etc.). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is commonly used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis, and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0021] Frequently-Asked Questions (FAQ): FAQs have become a feature of the Internet. FAQs seem to have originated in many user-net groups as a way to familiarize new users with the rules. There are tens of thousands of FAQs on the World Wide Web.

[0022] JavaScript Object Notation (JSON): JSON is an open standard file format and data exchange format designed based on a subset of ECMAScript. It is easy for people to read and write, and easy for machines to parse and generate. JSON is a commonly used data format that has many uses in electronic data exchange, including data exchange between web applications and servers. Its concise and clear hierarchical structure effectively improves network transmission efficiency, making it an ideal data exchange language.

[0023] Extensible Markup Language (XML): A subset of the standard general markup language that can be used to mark data and define data types. It is a source language that allows users to define their own markup language. XML is a standard general markup language with good extensibility, separation of content and form, strict syntax requirements, and good value preservation.

[0024] The natural language model-based data processing method and device, electronic device, and storage medium provided in the embodiments of the present application can avoid situations where answers are inconsistent with customer expectations, thereby improving problem handling efficiency and service quality.

[0025] The following examples are used to illustrate the method. First, the data processing method based on the natural language model in the example of the present application is described.

[0026] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0027] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include computer vision technology, robotics technology, biometrics technology, module management technology of online meeting systems, natural language processing technology, and machine learning / deep learning.

[0028] The data processing method based on the natural language model provided in the embodiment of the present application relates to the field of data processing technology. The data processing method based on the natural language model provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements a data processing method based on a natural language model, etc., but is not limited to the above forms.

[0029] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0030] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0031] In the daily operation of the insurance industry, the stable operation of the business system is crucial to ensuring the quality of customer service and improving business processing efficiency. However, with the increasing complexity of insurance business and the continuous upgrading of technical systems, business system problems frequently occur, which are usually submitted to the system operation team in the form of work orders for processing.

[0032] Most existing work order processing systems rely on manual operations and simple automated processes, lacking intelligent support. This makes it difficult for the system to respond quickly to complex or unexpected problems, affecting the efficiency and quality of problem solving. In addition, due to low work order processing efficiency and frequent repetitive problems, customers often have to wait a long time to get answers or solutions to their problems, and the answers may not be consistent with customer expectations. This not only reduces customer satisfaction, but may also have a negative impact on the insurance company's brand image.

[0033] In order to solve the above problems, the present embodiment provides a data processing method, device, electronic device and storage medium based on a natural language model. First, financial data information and question information to be answered are obtained, and knowledge representation is performed on the financial data information, so as to achieve accurate analysis of the financial data information, so as to create a first data structure and a second data structure corresponding to the question information in the financial data information, and achieve the creation of data structures for common problems and related problems. Then, an insurance data set is created based on the first data structure and the second data structure, and a professional database is constructed, so that a variety of question information can be integrated into the insurance data set, which is convenient for subsequent comprehensive retrieval of questions. After that, a preset natural language model is trained through the insurance data set, so that the natural language model can automatically process a large amount of text data, and an automatic question-answering language model is obtained. It can reduce manual intervention, respond to user search instructions, perform text analysis on the questions to be answered, analyze the keywords that need to be searched in the question information to be answered, obtain analysis results, realize accurate retrieval of the question information to be answered, improve retrieval accuracy, and then perform answer retrieval on the analysis results based on the automatic question-answering language model and the insurance data set, realize comprehensive retrieval of the question information to be answered, obtain a retrieval set, and improve the efficiency of problem handling and service quality. When the retrieval set is empty or there is no preset answer statement in the retrieval set, it means that the question information to be answered input by the user has not been solved, then it is necessary to convert the user search instruction into a manual service instruction, so that the question information to be answered can be manually replied, avoid the situation where the answer is inconsistent with the customer's expectations, and realize accurate answers to the question information to be answered. The embodiment of the present application creates multiple data structures by performing knowledge representation on financial data information, and then creates an insurance data set through multiple data structures, and trains a natural language model, so as to realize automatic question-answering of the question information to be answered, reduce manual input, and improve the efficiency of problem handling. In addition, when the retrieval set is empty or there is no preset answer statement in the retrieval set, the embodiment of the present application will perform a manual operation, so as to avoid the situation where the answer is inconsistent with the customer's expectations, and realize accurate answers to the question information to be answered.

[0034] The following is a detailed description with reference to the accompanying drawings.

[0035] Figure 1 is an optional flowchart of a data processing method based on a natural language model provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S107.

[0036] Step S101, obtaining financial data information and information on questions to be answered, wherein the financial data information includes a plurality of question information.

[0037] In step S101 of some embodiments, financial data information and information on questions to be answered are obtained, and the financial data information includes multiple pieces of information on questions, so as to facilitate subsequent retrieval of the information on questions to be answered.

[0038] It should be noted that the financial data information in the embodiments of the present application may be common problem information collected from daily work order processing records, FAQs, technical documents and expert experience of insurance companies, etc., and the embodiments of the present application do not make specific restrictions.

[0039] Step S102: performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the question information.

[0040] It should be noted that the first data structure is a data structure corresponding to common questions, and the second data structure is a data structure corresponding to related questions.

[0041] In step S102 of some embodiments, knowledge representation is performed on the financial data information to improve the overall quality of the data, ensure data quality, and reduce the risk of making wrong decisions based on erroneous data, so as to create a first data structure and a second data structure corresponding to the problem information, thereby avoiding processing delays or errors caused by human factors, improving the overall quality of the data as a whole, ensuring data quality, and reducing the risk of making wrong decisions based on erroneous data.

[0042] It can be understood that the first data structure in the embodiment of the present application is structured data, and the second data structure is semi-structured data.

[0043] Step S103: Create an insurance data set according to the first data structure and the second data structure.

[0044] In step S103 of some embodiments, an insurance data set is created based on the first data structure and the second data structure to realize the construction of a professional database, so that a variety of problem information can be integrated into the insurance data set to facilitate subsequent comprehensive retrieval of the problem.

[0045] Step S104, training a preset natural language model using the insurance data set to obtain an automatic question-answering language model.

[0046] In step S104 of some embodiments, a preset natural language model is trained by using an insurance data set, and an automatic question-answering text generation model and an automatic question-answering language model are obtained through repeated training and optimization, thereby reducing manual intervention.

[0047] Specifically, the embodiment of the present application divides the insurance data set into a training set, a validation set, and a test set, and then trains the natural language model through the training set, the validation set, and the test set.

[0048] Step S105, in response to the user's search instruction, performing text analysis on the question information to be answered to obtain analysis results.

[0049] In step S105 of some embodiments, in response to a user search instruction, text analysis is performed on the question information to be answered, so as to better understand the grammatical structure and semantic content of the sentence, improve the relevance of the search results, obtain analysis results, and facilitate subsequent accurate retrieval in the insurance data set, thereby improving the accuracy of the retrieval.

[0050] Step S106, performing answer retrieval on the analysis results based on the automatic question-answering language model and the insurance data set to obtain a retrieval set.

[0051] In step S106 of some embodiments, answer retrieval is performed on the analysis results based on the automatic question-answering language model and the insurance data set to obtain a retrieval set, thereby achieving a comprehensive retrieval of the analysis results, improving the accuracy of the retrieval, reducing the number of times the user needs to perform multiple searches to find all relevant information, and improving retrieval efficiency.

[0052] Step S107, when the search set is empty or there is no preset answer statement in the search set, the user search instruction is converted into a manual service instruction.

[0053] In step S107 of some embodiments, when the search set is empty or there is no preset answer statement in the search set, it means that the question information to be answered input by the user has not been resolved, and the user search instruction needs to be converted into a manual service instruction, so that the question information to be answered can be manually replied to, avoiding the situation where the answer is inconsistent with the customer's expectations, and achieving accurate answers to the question information to be answered.

[0054] It should be noted that the answer statement in the embodiment of the present application can be set according to the needs of the user, and the embodiment of the present application does not make any specific limitations.

[0055] It is understandable that the embodiments of the present application can intelligently solve the problems of insurance companies in daily customer service and operation, such as the difficulty of event handling and the cumbersome process. It can effectively improve the efficiency of problem handling and service quality, and also reduce the manpower investment for the customer operation of insurance companies, thereby achieving the purpose of reducing costs and increasing efficiency.

[0056] See also Figure 2 In some embodiments, step S102 may also include but is not limited to steps S201 to S206.

[0057] Step S201, performing data cleaning on financial data information.

[0058] In step S201 of some embodiments, during the process of knowledge representation of financial data information, the embodiments of the present application will first perform data cleaning on the financial data information. Specifically, the financial data information will be processed for missing values, detected for outliers, and identified for duplicate data. Cleaning can remove erroneous, duplicate, and inconsistent data, and remove irrelevant information, thereby improving the overall quality of the data, ensuring data quality, and reducing the risk of making wrong decisions based on erroneous data.

[0059] It should be noted that the data cleaning operation includes but is not limited to data consistency check, data accuracy verification, data integrity check, data deduplication, format conversion, etc., and the embodiments of the present application do not make specific restrictions.

[0060] Step S202, performing synonym expansion on the financial data information after data cleaning to obtain a financial database.

[0061] In step S202 of some embodiments, in order to ensure the comprehensiveness of keyword retrieval, it is necessary to perform synonymous expansion of keywords, that is, to perform synonymous expansion on the financial data information after data cleaning. Specifically, keyword recognition is first performed on the financial data information to determine the keywords in the financial data information that need to be expanded, such as financial management, insurance, etc., and then synonymous expansion is performed on different keywords to obtain a financial database, which is convenient for subsequent comprehensive retrieval of keywords.

[0062] It should be noted that, taking the existence of keywords such as insurance and amount in financial data information as an example, after the financial data information is synonymously expanded, insurance can be expanded to include words such as buying insurance and choosing insurance, and amount can be expanded to include words such as how much money and share, etc., and the embodiments of this application do not make specific restrictions.

[0063] It can be understood that the embodiments of the present application can ensure that information related to keywords but with different wording is not missed when searching for financial data through synonym expansion, and can improve the relevance of search results and user satisfaction, and help identify and integrate similar concepts in different languages.

[0064] Step S203, determining the frequently asked questions information and the frequently asked questions answers in the financial database.

[0065] In step S203 of some embodiments, since there may be questions that have already appeared and have standard answers in the financial database, the embodiments of the present application can directly determine the common problem information and the common problem answers in the financial database to simplify the operation process.

[0066] It can be understood that the common problem information in the embodiments of the present application may include the insurance process of auto insurance, the insurance qualification of pension insurance, etc., and the embodiments of the present application do not make specific limitations.

[0067] Step S204: establishing a first data structure according to the frequently asked questions information and the frequently asked questions answers.

[0068] In step S204 of some embodiments, since the frequently asked questions information and the answers to frequently asked questions are already standard questions and answers, the answers to such questions can be found through traditional question-and-answer matching. Therefore, the embodiments of the present application can directly establish the form of question-answer pairs and directly perform structured data storage, that is, directly establish a first data structure based on the frequently asked questions information and the answers to frequently asked questions, which can simplify the data flow as a whole and improve problem handling efficiency.

[0069] It should be noted that, for simple data structures, the embodiments of the present application can be directly stored in semi-structured formats such as JSON or XML.

[0070] Step S205, performing part-of-speech analysis on the financial database to determine related question information and answers to related questions.

[0071] In step S205 of some embodiments, since there are clear associations between some data, the embodiments of the present application will also perform part-of-speech analysis on the financial database, analyze the specific part of speech of each word in the financial database, so as to determine whether there is an extended word for the current word, and finally determine the associated question information and the associated question answer based on the part of speech of each word and the expansion result, so as to ensure the integrity and reliability of the data.

[0072] Step S206: establishing a second data structure according to the associated question information and the associated question answers.

[0073] In step S206 of some embodiments, a second data structure is established based on the associated question information and the answers to the associated questions, so that the data structure is intuitive and easy to understand, which facilitates the subsequent improvement of data retrieval and analysis performance.

[0074] It is understandable that if there is a clear association relationship between data, the embodiment of the present application may consider using a relational database for storage, and represent the relationship between data through a table structure.

[0075] In some embodiments, in the process of traditional work order processing, faced with a large influx of work orders, operators often need to manually classify, identify problems, and handle them one by one. This manual processing method is not only time-consuming and labor-intensive, but also prone to processing delays or errors due to human factors. In addition, there may be a large number of repetitive problems in the insurance business system, such as system login anomalies, data query errors, etc. These problems occur repeatedly, taking up a lot of time and energy of operators, but have not been effectively solved or prevented. The embodiments of the present application can avoid processing delays or errors caused by human factors by performing operations such as data cleaning, synonym expansion, and part-of-speech analysis on financial data information, thereby improving the overall quality of data as a whole, ensuring data quality, and reducing the risk of making wrong decisions based on wrong data.

[0076] See also Figure 3 , Figure 3 A flow chart of a method for performing text analysis on question information to be answered provided in an embodiment of the present application, the method includes but is not limited to steps S301 to S304.

[0077] Step S301, performing word segmentation processing on the question information to be answered to obtain multiple question texts.

[0078] In step S301 of some embodiments, in the process of text analysis of the question information to be answered, the embodiment of the present application first performs word segmentation processing on the question information to be answered. Specifically, for languages ​​such as English that use spaces to separate words, the embodiment of the present application can directly perform word segmentation according to spaces. For languages ​​such as Chinese that do not have obvious word separators, word segmentation can be performed according to specific rules (such as length, character type) to obtain multiple question texts, so as to better understand the grammatical structure and semantic content of the sentence and improve the relevance of the search results.

[0079] Step S302: perform part-of-speech tagging on all question texts to obtain tagging information.

[0080] In step S302 of some embodiments, all question texts are tagged with parts of speech, thereby obtaining the part-of-speech tag of each word in the question text and obtaining tagging information, which can improve the understanding of the text content and thus improve the accuracy of classification and sentiment analysis.

[0081] It should be noted that the embodiment of the present application can perform word segmentation and part-of-speech tagging through python text annotation tools, Stanford NLP text annotation tools, etc., and the embodiment of the present application does not make specific limitations.

[0082] It can be understood that the annotation information in the embodiment of the present application includes the question sentence, the answer keyword position, the answer, etc.

[0083] Step S303: extract keywords from the question text according to the annotation information to determine the keyword information in the question text.

[0084] In step S303 of some embodiments, after obtaining the annotation information, the embodiments of the present application perform keyword extraction on the question text according to the annotation information, extract and identify key entities in the question, such as business type, product name, etc., and determine the keyword information in the question text to facilitate subsequent accurate retrieval in the insurance data set.

[0085] Step S304, generating analysis results according to the question text, annotation information and keyword information.

[0086] In step S304 of some embodiments, analysis results are generated based on the question text, annotation information, and keyword information to facilitate subsequent accurate retrieval in the insurance data set, thereby improving the accuracy of the retrieval.

[0087] See also Figure 4 In some embodiments, step S106 may also include but is not limited to steps S401 to S405.

[0088] It should be noted that the user search instruction includes a first user search instruction and a second user search instruction.

[0089] Step S401, extracting key entities in the analysis results according to keyword information.

[0090] Step S402: In response to a first user search instruction, searching for key entities through the insurance data set.

[0091] Step S403: When the key entity does not exist in the insurance data set, synonymous replacement is performed on the key entity to obtain replacement information.

[0092] Step S404, searching the replacement information through the insurance data set.

[0093] Step S405: When there is no replacement information in the insurance data set, the analysis results are retrieved through the automatic question-answering language model to obtain a retrieval set.

[0094] In steps S401 to S405 of some embodiments, in the process of retrieving answers to the analysis results based on the automatic question-answering language model and the insurance data set, the embodiment of the present application first extracts the key entities in the analysis results based on the keyword information. By identifying the key entities, relevant information can be more accurately located, and the interference of irrelevant results can be reduced. In response to the first user search instruction, the key entities are retrieved through the insurance data set, and user needs are quickly responded to, which helps to allocate service resources more effectively and improve work efficiency. When the key entity does not exist in the insurance data set, it means that data consistent with the key entity has not been retrieved in the insurance data set, and the key entity needs to be synonymously replaced. Replacement can capture documents that use different vocabulary to express the same or similar concepts, thereby improving the comprehensiveness of the search results and obtaining replacement information. The replacement information is then retrieved through the insurance data set. Synonym replacement helps find documents that may not directly use the original keywords but are content-related, thereby improving the relevance of the search results. When replacement information does not exist in the insurance data set, it means that data consistent with the replacement information has not been retrieved in the insurance data set. It is necessary to retrieve the analysis results through an automatic question-and-answer language model to obtain a retrieval set, achieve comprehensive retrieval of the analysis results, improve retrieval accuracy, reduce the number of times users need to perform multiple searches to find all relevant information, and improve retrieval efficiency.

[0095] It is understandable that the embodiment of the present application begins to respond to the first user's search instruction to perform question search. If the corresponding content is not found through the keyword, the keyword is replaced with a synonym and then searched again. For example, "the process of buying insurance" is the same as "the process of insurance", so that documents that use different words to express the same or similar concepts can be captured.

[0096] It is worth noting that after responding to the first user's search instruction, the embodiment of the present application will also convert the format of the analysis results, converting the format of the analysis results into a query statement or format, such as JSON or XML, etc., so as to facilitate retrieval in the insurance data set.

[0097] See also Figure 5 , Figure 5 A flow chart of a method for retrieving analysis results through an automatic question-answering language model provided in an embodiment of the present application, the method including but not limited to steps S501 to S503.

[0098] Step S501, in response to the second user search instruction, input the analysis result into the automatic question answering language model, so that the automatic question answering language model performs word vectorization on the annotation information to convert the annotation information into a vector of a preset length to obtain a word vector.

[0099] Step S502: perform semantic analysis on the word vectors through the automatic question-answering language model and output the analysis answer.

[0100] Step S503, sorting the analysis answers to obtain a search set.

[0101] In steps S501 to S503 of some embodiments, in the process of retrieving the analysis results through the automatic question-answering language model, in response to the second user search instruction, the analysis results are input into the automatic question-answering language model, so that the automatic question-answering language model performs word vectorization on the annotation information to convert the annotation information into a vector of a preset length to obtain a word vector, which is convenient for subsequent precise analysis of the word vector and improves the accuracy of the retrieval. The word vector is then semantically analyzed by the automatic question-answering model to determine the semantics expressed by the word vector, and the analysis answer corresponding to the question information to be answered is output. Finally, the analysis answer is sorted, for example, duplicates are removed, sorted, etc., to obtain a retrieval set, thereby achieving a comprehensive retrieval of the analysis information and retrieving accurate answers to the question.

[0102] It should be noted that the automatic question-answering language model in the embodiment of the present application includes a Word2Vec pre-trained model and a Transformer model. Specifically, the embodiment of the present application uses the Word2Vec pre-trained model to word vectorize the annotation information, and uses the Transformer model to perform semantic analysis on the word vector.

[0103] See also Figure 6 , Figure 6 It is a flowchart of a data processing method based on a natural language model provided by another embodiment of the present application, and the method includes but is not limited to steps S601 to S604.

[0104] It should be noted that step S601 to step S604 occur after the user search instruction is converted into a manual service instruction.

[0105] Step S601, collecting manual reply information.

[0106] Step S602: Perform sensitive information detection on the manual reply information.

[0107] Step S603, when the manual reply information passes the sensitive information detection, target reply information corresponding to the question information to be answered is generated according to the manual reply information.

[0108] Step S604: Add the question information to be answered and the target answer information to the insurance data set.

[0109] In steps S601 to S604 of some embodiments, after the user search instruction is converted into a manual service instruction, the embodiments of the present application will also collect manual reply information, that is, the answer to the manual reply to the question information to be answered, and then perform sensitive information detection on the manual reply information to reduce the risk of personal privacy leakage. By identifying and protecting sensitive information, the overall data security is improved. When the manual reply information passes the sensitive information detection, it means that there is no sensitive information in the manual reply information, and the target reply information corresponding to the question information to be answered can be directly generated according to the manual reply information to achieve an accurate answer to the question information to be answered. Finally, the question information to be answered and the target reply information are added to the insurance data set to achieve real-time update of the insurance data set, which is convenient for subsequent retrieval of other questions, and the real-time update of the data set can ensure that the information retrieved by the user is the latest, thereby improving the accuracy and relevance of question matching.

[0110] It is worth noting that in the process of performing sensitive information detection on manual reply information, the embodiment of the present application will perform sensitive word detection on the manual reply information based on preset sensitive words, where the sensitive words may be personal identity information, financial data, and the like.

[0111] It should be noted that when the manual reply information fails the sensitive information detection, the identified sensitive information will be marked, and then the marked sensitive information will be desensitized, for example, masking operation, encryption operation, etc. Finally, the desensitized information will be displayed to the user to achieve safe display of information and avoid leakage of sensitive information.

[0112] It is understandable that if the questions raised by users can be answered quickly and these answers can be retrieved by other users, it will improve user satisfaction with the service.

[0113] See also Figure 7 , Figure 7 is a flowchart of a data processing method based on a natural language model provided by another embodiment of the present application, Figure 7 The method may include but is not limited to step S701.

[0114] It should be noted that step S701 occurs after answer retrieval is performed on the analysis results based on the automatic question-answering language model and the insurance dataset.

[0115] Step S701, when the search set is not empty and there is a preset answer sentence in the search set, determine the target answer sentence in the search set.

[0116] In step S701 of some embodiments, after answer retrieval is performed on the analysis results based on the automatic question-answering language model and the insurance data set, when the retrieval set is non-empty and there is a preset answer sentence in the retrieval set, it means that a sentence corresponding to the question information to be answered has been retrieved through the automatic question-answering language model or the insurance data set, and the sentence is a preset answer sentence, so the target answer sentence can be directly determined in the retrieval set to achieve accurate retrieval of the question information to be answered.

[0117] See also Figure 8 The embodiment of the present application also provides a data processing device based on a natural language model, the device comprising: The information acquisition module 801 is used to acquire financial data information and information about questions to be answered, wherein the financial data information includes a plurality of question information; The knowledge representation module 802 is used to perform knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the problem information, wherein the first data structure is a data structure corresponding to the common problem, and the second data structure is a data structure corresponding to the associated problem; A data set creation module 803, used to create an insurance data set according to the first data structure and the second data structure; A model training module 804 is used to train a preset natural language model using an insurance data set to obtain an automatic question-answering language model; The text analysis module 805 is used to perform text analysis on the question information to be answered in response to the user's search instruction to obtain the analysis result; An answer retrieval module 806 is used to retrieve answers to the analysis results based on the automatic question-answering language model and the insurance data set to obtain a retrieval set; The transfer module 807 is used to convert the user's search instruction into a transfer to manual service instruction when the search set is empty or there is no preset answer statement in the search set.

[0118] In some embodiments, the data processing device based on the natural language model further includes an information collection module and a target determination module, wherein the information collection module is used to collect manual reply information; perform sensitive information detection on the manual reply information; when the manual reply information passes the sensitive information detection, generate target reply information corresponding to the question information to be answered according to the manual reply information; and add the question information to be answered and the target reply information to the insurance data set. The target determination module is used to determine the target answer sentence in the retrieval set when the retrieval set is not empty and there is a preset answer sentence in the retrieval set.

[0119] The specific implementation of the data processing device based on the natural language model is basically the same as the specific implementation of the data processing method based on the natural language model mentioned above, and will not be repeated here.

[0120] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned data processing method based on the natural language model. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0121] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes: The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the data processing method based on the natural language model in the embodiment of this application; Input / output interface 903, used to implement information input and output; Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.); A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904); The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0122] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned data processing method based on the natural language model.

[0123] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0124] The data processing method, device, electronic device and storage medium based on the natural language model provided in the embodiments of the present application first obtain financial data information and question information to be answered, perform knowledge representation on the financial data information, thereby realizing accurate analysis of the financial data information, so as to create a first data structure and a second data structure corresponding to the question information in the financial data information, realize the creation of data structures for common problems and related problems, and then create an insurance data set based on the first data structure and the second data structure to realize the construction of a professional database, so that a variety of question information can be integrated into the insurance data set to facilitate subsequent comprehensive retrieval of questions, and then, train a preset natural language model through the insurance data set, so that the natural language model can automatically process a large amount of text data, and obtain an automatic question-answering language model, so that it can Reduce manual intervention, respond to user search instructions, perform text analysis on the questions to be answered, analyze the keywords that need to be searched in the question information to be answered, obtain analysis results, realize accurate retrieval of the question information to be answered, improve retrieval accuracy, and then perform answer retrieval on the analysis results based on the automatic question-answering language model and the insurance data set, realize comprehensive retrieval of the question information to be answered, and obtain a search set, which can improve the efficiency of problem handling and service quality. When the search set is empty or there is no preset answer statement in the search set, it means that the question information to be answered input by the user has not been solved, then it is necessary to convert the user search instruction into a manual service instruction, so that the question information to be answered can be manually replied, and the situation that the answer is inconsistent with the customer's expectations can be avoided, and the accurate answer to the question information to be answered can be achieved. The embodiment of the present application creates multiple data structures by performing knowledge representation on financial data information, and then creates an insurance data set through multiple data structures, and trains a natural language model, so that the automatic question-answering of the question information to be answered can be realized, which reduces manual input and can improve the efficiency of problem handling. In addition, when the search set is empty or there is no preset answer statement in the search set, the embodiment of the present application will perform a manual operation, so as to avoid the situation that the answer is inconsistent with the customer's expectations, and achieve an accurate answer to the question information to be answered.

[0125] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0126] It can be understood by those skilled in the art that Figure 1-9 The technical solutions shown in the figure do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figure, or a combination of certain steps, or different steps.

[0127] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0128] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0129] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0130] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0135] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A data processing method based on a natural language model, characterized in that: The method comprises: Acquire financial data information and information about questions to be answered, wherein the financial data information includes a plurality of information about questions; Performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the problem information, wherein the first data structure is a data structure corresponding to a common problem, and the second data structure is a data structure corresponding to an associated problem; creating an insurance data set according to the first data structure and the second data structure; A preset natural language model is trained by using the insurance data set to obtain an automatic question-answering language model; In response to a user search instruction, performing text analysis on the question information to be answered to obtain an analysis result; Perform answer retrieval on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a retrieval set; When the search set is empty or there is no preset answer statement in the search set, the user search instruction is converted into a manual service instruction.

2. The data processing method based on the natural language model according to claim 1, characterized in that: The performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the problem information includes: Performing data cleaning on the financial data information; Perform synonymous expansion on the financial data information after data cleaning to obtain a financial database; determining frequently asked questions information and frequently asked questions answers in the financial database; Establishing a first data structure according to the common question information and the common question answers; Performing part-of-speech analysis on the financial database to determine related question information and answers to related questions; A second data structure is established according to the associated question information and the associated question answers.

3. The data processing method based on the natural language model according to claim 1, characterized in that: The text analysis of the question information to be answered is performed to obtain the analysis result, including: Performing word segmentation processing on the question information to be answered to obtain multiple question texts; Perform part-of-speech tagging on all the question texts to obtain tagging information; Extract keywords from the question text according to the annotation information to determine keyword information in the question text; An analysis result is generated according to the question text, the annotation information and the keyword information.

4. The data processing method based on the natural language model according to claim 3 is characterized in that: The user search instruction includes a first user search instruction and a second user search instruction; the answer search is performed on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a search set, including: Extracting key entities in the analysis result according to the keyword information; In response to a first user search instruction, searching the key entity through the insurance data set; When the key entity does not exist in the insurance data set, performing synonymous replacement on the key entity to obtain replacement information; Retrieving the replacement information through the insurance data set; When the replacement information does not exist in the insurance data set, the analysis result is retrieved through the automatic question-answering language model to obtain a retrieval set.

5. The data processing method based on the natural language model according to claim 4 is characterized in that: The step of retrieving the analysis result by using the automatic question-answering language model to obtain a retrieval set includes: In response to a second user search instruction, inputting the analysis result into the automatic question answering language model, so that the automatic question answering language model performs word vectorization on the annotation information to convert the annotation information into a vector of a preset length to obtain a word vector; Performing semantic analysis on the word vector by using the automatic question-answering language model, and outputting the analysis answer; The analysis answers are sorted to obtain a retrieval set.

6. The data processing method based on the natural language model according to claim 1, characterized in that: After converting the user search instruction into a manual service instruction, the method further includes: Collect manual response information; Performing sensitive information detection on the manual reply information; When the manual reply information passes the sensitive information detection, generating target reply information corresponding to the question information to be answered according to the manual reply information; The unanswered question information and the target answer information are added to the insurance dataset.

7. The data processing method based on the natural language model according to claim 1, characterized in that: After performing answer retrieval on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a retrieval set, the method further includes: When the search set is not empty and there is a preset answer sentence in the search set, a target answer sentence is determined in the search set.

8. A data processing device based on a natural language model, characterized in that: The device comprises: An information acquisition module, used to acquire financial data information and information on questions to be answered, wherein the financial data information includes a plurality of question information; A knowledge representation module, used for performing knowledge representation on the financial data information to create a first data structure and a second data structure corresponding to the problem information, wherein the first data structure is a data structure corresponding to a common problem, and the second data structure is a data structure corresponding to an associated problem; A data set creation module, used to create an insurance data set according to the first data structure and the second data structure; A model training module, used to train a preset natural language model through the insurance data set to obtain an automatic question-answering language model; A text analysis module, used to perform text analysis on the question information to be answered in response to a user search instruction, and obtain an analysis result; An answer retrieval module, used to perform answer retrieval on the analysis result based on the automatic question-answering language model and the insurance data set to obtain a retrieval set; The manual transfer module is used to convert the user search instruction into a manual service transfer instruction when the search set is empty or there is no preset answer statement in the search set.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the data processing method based on a natural language model as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the data processing method based on a natural language model described in any one of claims 1 to 7 is implemented.

Images