Online education intelligent customer service feedback method and system based on generative artificial intelligence

Abstract

The present invention relates to the field of intelligent customer service technology, and more specifically, to a method and system for intelligent customer service feedback in online education based on generative artificial intelligence. The solution includes designing the structure of an operations and management platform; completing type and vocabulary management of sensitive terms; completing plugin configuration for the management platform; after obtaining the current question, extracting answers from the current knowledge base for retrieval and feedback; for questions without such answers, screening solutions and scenarios with the fewest backend inquiries based on the number of backend inquiries, updating the knowledge base online, and providing feedback on the retrieval questions; and screening questions and answers intelligently generated by the knowledge base. This solution uses generative artificial intelligence methods to automatically generate information, complete online information feedback, and reduce reliance on manual customer service.

Description

Technical Field

[0001] The present invention relates to the field of intelligent customer service technology, and more specifically, to an online education intelligent customer service feedback method and system based on generative artificial intelligence. Background Art

[0002] The importance of intelligent customer service systems lies in their ability to significantly improve customer service quality and efficiency through automation and intelligence, while reducing costs and providing data-driven decision support for businesses. With the continuous advancement of technology, intelligent customer service systems will continue to develop and improve, becoming a key component of a company's core competitiveness. When implementing intelligent customer service systems, companies should consider key factors such as technology selection, data integration, and staff training to ensure effective system operation and maximize return on investment. In the future, intelligent customer service systems will place greater emphasis on emotion recognition, multi-channel interaction, and self-learning capabilities to provide a more humane and personalized customer service experience.

[0003] Prior to this invention, traditional customer service systems primarily relied on retrieval technology, with limited capabilities for understanding the semantics of user questions and generating responses. They could only answer based on fixed rules, resulting in a single interactive approach that struggled to meet the complex and diverse needs of users. Furthermore, the construction of their knowledge base relied primarily on manually composing question-and-answer pairs, which was time-consuming and labor-intensive, making the construction of the knowledge base cumbersome. Summary of the Invention

[0004] In view of the above problems, the present invention proposes an online education intelligent customer service feedback method and system based on generative artificial intelligence, which automatically generates information through generative artificial intelligence methods, completes online information feedback, and reduces dependence on manual customer service.

[0005] According to a first aspect of an embodiment of the present invention, an online education intelligent customer service feedback method based on generative artificial intelligence is provided.

[0006] In one or more embodiments, preferably, the online education intelligent customer service feedback method based on generative artificial intelligence includes:

[0007] Conduct structural design of operation and maintenance and management platform;

[0008] Complete type management and vocabulary management of sensitive words;

[0009] Complete the plug-in settings of the management platform;

[0010] After obtaining the current question, extract the answer from the current knowledge base for retrieval feedback;

[0011] For the questions that do not have such answers, we filter out the solutions and scenarios with the least backend inquiries based on the number of backend inquiries, update the knowledge base online, and provide feedback on the search questions;

[0012] Filter questions and answers intelligently generated by the knowledge base.

[0013] In one or more embodiments, preferably, the structural design of the operation and management platform specifically includes:

[0014] Provide a management platform for operation and maintenance and management personnel;

[0015] The operation and maintenance and management platform is set up to include knowledge base management, question management, feedback management, question and answer session management, common question management, associative question management, sensitive word management and statistical management.

[0016] In one or more embodiments, preferably, completing the type management and vocabulary management of sensitive words specifically includes:

[0017] Get the current question and automatically filter out sensitive words contained in the question;

[0018] Sensitive words are divided into type management and vocabulary management:

[0019] The type management page includes fuzzy query, create, edit and delete functions;

[0020] The vocabulary management page includes functions such as query by sensitive word type, fuzzy query by sensitive word, create, edit, and delete.

[0021] In one or more embodiments, preferably, completing the plug-in setting of the management platform specifically includes:

[0022] Set up pre-set plugin registration methods and structures for the management platform;

[0023] Set the triggering and mapping calling mode of the plug-in on the management platform;

[0024] The questions raised in the settings must be filtered by scenarios through the plug-in of the management platform. The scenarios are pre-set ranges and cannot be added later.

[0025] In one or more embodiments, preferably, after obtaining the current question, extracting the answer from the current knowledge base for retrieval feedback specifically includes:

[0026] Get the current question, search in the current knowledge base, and provide direct feedback if there is an answer;

[0027] If there is no such answer, a new question feedback template is created, wherein the new question feedback template includes a standard question, a standard answer, and a user ID;

[0028] For questions that do not have such answers in the feedback, submit a request for multi-scene matching and provide feedback on the screen to start multi-scene adaptive matching.

[0029] In one or more embodiments, preferably, the method of filtering out the solutions and scenarios with the least backend inquiries based on the number of backend inquiries for the unanswered questions, updating the knowledge base online, and feeding back the retrieval questions specifically includes:

[0030] Get the current number of backend inquiries, sort them and get the solutions with the least inquiries;

[0031] Obtain all scenario categories of the current knowledge base and extract the scenarios with the least queries under the current scenario category;

[0032] Push the fewest scenarios and solutions to users, and select the most relevant scenarios and solutions;

[0033] The most relevant scenarios and solutions are reorganized into a new module, and AI-powered question-answering methods are used to generate several new questions and answers.

[0034] Add new questions and answers to the original knowledge base;

[0035] The analysis is repeated until a matching answer is found, completing the feedback of the retrieval question.

[0036] In one or more embodiments, preferably, the screening of questions and answers intelligently generated by the knowledge base specifically includes:

[0037] Get all newly generated questions and answers in this Q&A session;

[0038] Determine the consistency of the scenario, directly delete questions and answers that are inconsistent with the scenario and the current question, and update the knowledge base.

[0039] According to a second aspect of an embodiment of the present invention, an online education intelligent customer service feedback system based on generative artificial intelligence is provided.

[0040] In one or more embodiments, preferably, the online education intelligent customer service feedback system based on generative artificial intelligence includes:

[0041] The management platform's settings module is used for operation and maintenance and structural design of the management platform;

[0042] Sensitive word screening module, used to complete sensitive word type management and vocabulary management;

[0043] Plug-in setting module, used to complete the plug-in settings of the management platform;

[0044] The standard answer library module is used to extract the answers in the current knowledge base for retrieval feedback after obtaining the current question;

[0045] The least-questioned scenario module is used to screen out the solutions and scenarios with the least backend inquiries based on the number of backend inquiries for the questions that do not have such answers, update the knowledge base online, and provide feedback on the search questions;

[0046] The scenario selection module is used to filter the questions and answers intelligently generated by the knowledge base.

[0047] According to a third aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method according to any one of the first aspect of the embodiment of the present invention is implemented.

[0048] According to a fourth aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement any one of the methods described in the first aspect of the embodiment of the present invention.

[0049] The technical solutions provided by the embodiments of the present invention may have the following beneficial effects:

[0050] In the solution of the present invention, a question feedback method based on retrieval and rapid question answering is implemented through rapid matching of questions and scenarios.

[0051] In the solution of the present invention, for problems that cannot be matched, rapid improvement and supplementation are carried out through matching low usage scenarios with high correlation, thereby realizing intelligent information feedback.

[0052] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0053] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1This is a flowchart of an online education intelligent customer service feedback method based on generative artificial intelligence according to an embodiment of the present invention.

[0056] Figure 2 This is a flowchart of the structural design of the operation and management platform in the online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0057] Figure 3 This is a flowchart of completing type management and vocabulary management of sensitive words in an online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0058] Figure 4 This is a flowchart of completing the plug-in settings of the management platform in the online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0059] Figure 5 This is a flowchart of an online education intelligent customer service feedback method based on generative artificial intelligence in an embodiment of the present invention, which extracts answers from the current knowledge base for retrieval and feedback after obtaining the current question.

[0060] Figure 6 This is a flowchart of an online education intelligent customer service feedback method based on generative artificial intelligence in an embodiment of the present invention, which filters out solutions and scenarios with the least background inquiries based on the number of background inquiries for questions that have no answers, updates the knowledge base online, and provides feedback on the retrieval questions.

[0061] Figure 7 This is a flowchart of screening questions and answers intelligently generated by a knowledge base in an online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0062] Figure 8 This is a structural diagram of an online education intelligent customer service feedback system based on generative artificial intelligence according to an embodiment of the present invention.

[0063] Figure 9 It is a structural diagram of an electronic device in one embodiment of the present invention. DETAILED DESCRIPTION

[0064] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0066] The importance of intelligent customer service systems lies in their ability to significantly improve customer service quality and efficiency through automation and intelligence, while reducing costs and providing data-driven decision support for businesses. With the continuous advancement of technology, intelligent customer service systems will continue to develop and improve, becoming a key component of a company's core competitiveness. When implementing intelligent customer service systems, companies should consider key factors such as technology selection, data integration, and staff training to ensure effective system operation and maximize return on investment. In the future, intelligent customer service systems will place greater emphasis on emotion recognition, multi-channel interaction, and self-learning capabilities to provide a more humane and personalized customer service experience.

[0067] Prior to this invention, traditional customer service systems primarily relied on retrieval technology, with limited capabilities for understanding the semantics of user questions and generating responses. They could only answer based on fixed rules, resulting in a single interactive approach that struggled to meet the complex and diverse needs of users. Furthermore, the construction of their knowledge base relied primarily on manually composing question-and-answer pairs, which was time-consuming and labor-intensive, making the construction of the knowledge base cumbersome.

[0068] In an embodiment of the present invention, a method and system for online education intelligent customer service feedback based on generative artificial intelligence is provided. This solution uses generative artificial intelligence methods to automatically generate information, complete online information feedback, and reduce reliance on manual customer service.

[0069] According to a first aspect of an embodiment of the present invention, an online education intelligent customer service feedback method based on generative artificial intelligence is provided.

[0070] Figure 1This is a flowchart of an online education intelligent customer service feedback method based on generative artificial intelligence according to an embodiment of the present invention.

[0071] In one or more embodiments, preferably, the online education intelligent customer service feedback method based on generative artificial intelligence includes:

[0072] S101. Conduct structural design of operation and management platform;

[0073] S102. Complete type management and vocabulary management of sensitive words;

[0074] S103, completing the plug-in settings of the management platform;

[0075] S104. After obtaining the current question, extract the answer from the current knowledge base for retrieval feedback;

[0076] S105: For the unanswered questions, select solutions and scenarios with the least backend inquiries based on the number of backend inquiries, update the knowledge base online, and provide feedback on the search questions;

[0077] S106. Screen the questions and answers intelligently generated by the knowledge base.

[0078] In an embodiment of the present invention, by building an intelligent artificial intelligence question-answering system, combining plug-in selection and scenario and question-answering analysis, and combining automatic identification of question generation and answer generation, it is possible to quickly supplement non-standard questions that cannot be quickly fed back, and efficiently complete artificial intelligence information generation.

[0079] Figure 2 This is a flowchart of the structural design of the operation and management platform in the online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0080] like Figure 2 As shown, in one or more embodiments, preferably, the structural design of the operation and management platform specifically includes:

[0081] S201, provide a management platform for operation and maintenance and management personnel;

[0082] S202. Setting the operation and maintenance and management platform includes knowledge base management, question management, feedback management, question-and-answer session management, frequently asked questions management, associative question management, sensitive word management, and statistical management.

[0083] In an embodiment of the present invention, a management platform system designed for operations and management personnel is involved. The system provides a series of functional modules, including knowledge base management, question management, feedback management, question and answer session management, frequently asked questions management, associative question management, sensitive word management, and statistical management. These functions are designed to help managers update and maintain the knowledge base of the intelligent question and answer system, manage user interactions (such as likes and dislikes), analyze user feedback, and generate statistical reports to evaluate system performance. In addition, the system also supports a multi-user system, allowing different systems to access different knowledge bases. The operation and maintenance and management platform can complete the following operations to edit, add, delete and other update operations on the knowledge base knowledge, and automatically trigger the update of the intelligent question and answer system; support the management of default reply questions for no matching answers, further understand the questions that the current user needs to consult, and improve the knowledge base; manage and analyze the feedback content of user likes and dislikes; manage the information related to the consultation session and whether the answer to the question is accurate; support the screening and spot check judgment of questions and answers to improve the knowledge base; edit, add, delete and other update operations on the commonly used questions on the right side of the intelligent customer service question and answer system client; manage the associative questions of the text entered for the question, and perform update operations such as editing, adding, deleting, etc.; import existing sensitive word libraries, and can edit, add, delete and other update operations on sensitive words; perform statistics according to time, and generate statistical analysis reports based on user feedback information, such as reply efficiency, like rate, and failure rate; it is necessary to support multi-user systems for different systems and support different systems to access different knowledge bases.

[0084] Figure 3 This is a flowchart of completing type management and vocabulary management of sensitive words in an online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0085] like Figure 3 As shown, in one or more embodiments, preferably, completing the type management and vocabulary management of sensitive words specifically includes:

[0086] S301. Obtain the current question and automatically filter out sensitive words contained in the question;

[0087] S302. Sensitive words are divided into type management and vocabulary management:

[0088] S303, the type management page includes fuzzy query, create, edit and delete functions;

[0089] S304. The vocabulary management page includes functions such as query by sensitive word type, fuzzy query by sensitive word, create, edit, and delete.

[0090] In an embodiment of the present invention, the current question is obtained, and the sensitive words contained in the question are automatically filtered; sensitive words are divided into type management and vocabulary management: the type management page includes fuzzy query, create, edit and delete functions; fuzzy query is performed according to the sensitive word type; a new sensitive word type is created; entering the editing interface, the original sensitive word type information can be modified; clicking the delete button, the data is deleted; the vocabulary management page includes query by sensitive word type, fuzzy query by sensitive word, create, edit, and delete functions; query by sensitive word type; fuzzy query by sensitive word; drop down to select the sensitive word type, enter the sensitive word and status; click the edit button in the operation column to enter the editing interface, the original vocabulary information can be modified; click the delete button to delete the data.

[0091] Figure 4 This is a flowchart of completing the plug-in settings of the management platform in the online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0092] like Figure 4 As shown, in one or more embodiments, preferably, the completion of the plug-in setting of the management platform specifically includes:

[0093] S401, setting a pre-set plug-in registration method and structure for the management platform;

[0094] S402: Setting the triggering and mapping calling mode of the plug-in on the management platform;

[0095] S403. The questions raised in the settings must be screened by scenarios through the plug-in of the management platform. The scenarios are pre-set ranges and cannot be added later.

[0096] In an embodiment of the present invention, a plug-in processing flow is set up, specifically including plug-in registration and matching, triggering, and automatic routing strategies: 1) Plug-in registration and matching: The functions of the enterprise software are encapsulated into an API, including an API description file and a plug-in description file. The plug-in description file defines the functions and applicable scenarios of the plug-in in detail. The API description file clearly describes the API and its parameters that the plug-in needs to call. After the API is encapsulated, the plug-in needs to be registered with the big model: upload the API description file and the plug-in description file. 2) Plug-in triggering and automatic routing strategy: During the user-system dialogue process, the big model automatically identifies the user's intent through pre-defined scenario descriptions, and intelligently maps the user's input to the appropriate plug-in and API interface. First, it is triggered by the user's question: the user's intent is identified and the corresponding plug-in scenario is hit. Then, additional questions are asked when necessary to obtain more parameters. Once there is enough information, the system automatically matches the specific API interface under the plug-in scenario, completing the mapping from user input to API call.

[0097] Figure 5 This is a flowchart of an online education intelligent customer service feedback method based on generative artificial intelligence in an embodiment of the present invention, which extracts answers from the current knowledge base for retrieval and feedback after obtaining the current question.

[0098] like Figure 5 As shown, in one or more embodiments, preferably, after obtaining the current question, extracting the answer in the current knowledge base for retrieval feedback specifically includes:

[0099] S501. Obtain the current question, search the current knowledge base, and directly provide feedback if the answer is found;

[0100] S502: If there is no such answer, create a new question feedback template, wherein the new question feedback template includes a standard question, a standard answer, and a user ID;

[0101] S503: For questions that do not have such answers, submit a request for multi-scene matching, and provide feedback on the screen to start multi-scene adaptive matching.

[0102] In an embodiment of the present invention, questions and answers that are missing from the knowledge base can be temporarily supplemented in Business Management - Backstage Management - Automatic Reply Management. When asking questions and answers, the question will first be screened to see if it is a question in the automatic reply management. The specific query logic is as follows: obtain the question raised by the client user; search the corpus in the automatic reply management according to the question; obtain the standard question of the question according to the corpus; search the standard answer management according to the standard question to obtain the standard answer; both pages support fuzzy search according to the course name; create a new automatic reply management containing corpus, standard question (the data source is the standard question in the standard answer management) and user id (the data source is user management); create a new standard answer management containing standard question, standard answer, user id (the data source is user management), among which, the multi-scenario adaptive matching is started once for the question that does not have such an answer, based on the number of backstage inquiries, to screen out the solutions and scenarios with the least backstage inquiries, update the knowledge base online, and feedback the flowchart of the retrieval question.

[0103] Figure 6 This is a flowchart of an online education intelligent customer service feedback method based on generative artificial intelligence in an embodiment of the present invention, which filters out solutions and scenarios with the least background inquiries based on the number of background inquiries for questions that have no answers, updates the knowledge base online, and provides feedback on the retrieval questions.

[0104] like Figure 6 As shown, in one or more embodiments, preferably, the problem without such an answer is screened out based on the number of background inquiries, and the solutions and scenarios with the least background inquiries are selected, and the knowledge base is updated online, and the search question is fed back, specifically including:

[0105] S601: Obtain the current number of backend inquiries and sort them to obtain several solutions with the least inquiries;

[0106] S602: Obtain all scenario categories of the current knowledge base and extract the scenarios with the least queries under the current scenario category;

[0107] S603: Push the minimum scenarios and the minimum solutions to the user, and select the scenario and solution with the strongest relevance;

[0108] S604: The most relevant scenarios and solutions are reorganized into a new module, and a number of new questions and answers are generated using AI-based question-answering methods.

[0109] S605, adding new questions and new answers to the original knowledge base;

[0110] S606: Re-analyze until an answer match is found, completing the feedback of the search question.

[0111] In this embodiment of the present invention, the current backend query count can be obtained by counting the number of various questions raised by users. This data is then sorted to identify the solutions with the lowest number of queries. If this answer is no longer available, it indicates that the previously recommended answers were generally difficult to obtain. Alternatively, previous recommendations were biased. Therefore, less popular but highly relevant solutions are prioritized, allowing for a gradual screening process to identify the appropriate answers. Next, we need to obtain all scenario categories within the current knowledge base. This can be achieved by analyzing the content within the knowledge base and categorizing it into different scenarios. We then extract the scenarios with the lowest number of queries within the current scenario category. Once we have the lowest number of scenarios and solutions, we push them to users. Users can select the most relevant scenarios and solutions based on their specific needs. This ensures that the information provided to users is the most targeted and practical. The most relevant scenarios and solutions are reorganized into a new module. This module uses AI-powered question-and-answer generation methods to generate several new questions and answers. These questions and answers are more closely aligned with users' actual needs, improving the practicality of the knowledge base. The newly generated questions and answers are then added to the original knowledge base. In this way, the content of the knowledge base will be continuously updated and expanded to meet the ever-changing needs of users. Finally, we need to re-analyze until there is an answer match. This means that we need to constantly check the content in the knowledge base to ensure that it can accurately answer the user's question. Once a matching answer is found, we can complete the feedback of the retrieval question and provide the user with a satisfactory solution.

[0112] The specific method for reading the number of backend inquiries includes: using the first calculation formula to calculate the number of inquiries of a single IP per unit time;

[0113] Calculate the number of background inquiries using the second calculation formula;

[0114] The first calculation formula is:

[0115] IPC=ZZ÷F

[0116] Among them, ZZ is the total number of inquiries per IP per unit time, F is the number of question categories, and IPC is the number of inquiries per IP per unit time;

[0117] The second calculation formula is:

[0118]

[0119] Where zs is the number of backend inquiries, IPCi is the number of inquiries per IP per unit time, i is the IP number, and ss is the total number of IPs.

[0120] Figure 7 This is a flowchart of screening questions and answers intelligently generated by a knowledge base in an online education intelligent customer service feedback method based on generative artificial intelligence in one embodiment of the present invention.

[0121] like Figure 7 As shown, in one or more embodiments, preferably, the screening of questions and answers intelligently generated by the knowledge base specifically includes:

[0122] S701. Obtain all newly generated questions and answers in this Q&A session;

[0123] S702: Determine the consistency of the scenario, directly delete the questions and answers that are inconsistent with the scenario and the current question, and update the knowledge base.

[0124] In this embodiment of the present invention, all new questions and answers generated by artificial intelligence in this Q&A session are first collected. Next, each newly generated question and its corresponding answer are evaluated for scenario consistency. Specifically, this is done to check whether the question matches the scenario to which it belongs. If the question and the scenario are inconsistent, then the question and its answer are considered irrelevant and need to be deleted from the knowledge base. Finally, after screening, the remaining highly relevant questions and answers are updated to the knowledge base to ensure the continuous improvement of the accuracy and practicality of the knowledge base.

[0125] According to a second aspect of an embodiment of the present invention, an online education intelligent customer service feedback system based on generative artificial intelligence is provided.

[0126] Figure 8 This is a structural diagram of an online education intelligent customer service feedback system based on generative artificial intelligence according to an embodiment of the present invention.

[0127] In one or more embodiments, preferably, the online education intelligent customer service feedback system based on generative artificial intelligence includes:

[0128] The management platform setting module 801 is used for operation and maintenance and structural design of the management platform;

[0129] Sensitive word screening module 802, used to complete sensitive word type management and word management;

[0130] The plug-in setting module 803 is used to complete the plug-in setting of the management platform;

[0131] The standard answer library module 804 is used to extract the answer from the current knowledge base for retrieval feedback after obtaining the current question;

[0132] The least question scenario module 805 is used to screen out the solutions and scenarios with the least backend questions based on the number of backend questions for the questions that do not have such answers, update the knowledge base online, and provide feedback on the search questions;

[0133] The scenario selection module 806 is used to screen the questions and answers intelligently generated by the knowledge base.

[0134] In the embodiment of the present invention, a system applicable to different structures is realized through a series of modular designs. The system can achieve closed-loop, reliable and efficient execution through collection, analysis and control.

[0135] According to a third aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method according to any one of the first aspect of the embodiment of the present invention is implemented.

[0136] According to a fourth aspect of the embodiments of the present invention, an electronic device is provided. Figure 9 It is a structural diagram of an electronic device in one embodiment of the present invention. Figure 9 The electronic device shown is a general-purpose online education intelligent customer service feedback device based on generative artificial intelligence. The electronic device can be a smartphone, tablet computer, or other device. As shown, the electronic device 900 includes a processor 901 and a memory 902. The processor 901 is electrically connected to the memory 902. The processor 901 is the control center of the terminal 900, connecting the various parts of the entire terminal using various interfaces and lines. By running or calling computer programs stored in the memory 902 and calling data stored in the memory 902, the processor executes various functions of the terminal and processes data, thereby monitoring the terminal as a whole.

[0137] In this embodiment, the processor 901 in the electronic device 900 will load the instructions corresponding to the processes of one or more computer programs into the memory 902 according to the following steps, and the processor 901 will run the computer program stored in the memory 902 to realize various functions: perform structural design of the operation and maintenance and management platform; complete type management and vocabulary management of sensitive words; complete plug-in settings of the management platform; after obtaining the current question, extract the answer in the current knowledge base for retrieval and feedback; for the question that has no such answer, screen out the solutions and scenarios with the least background inquiries based on the number of background inquiries, update the knowledge base online, and feedback the retrieval questions; screen the questions and answers intelligently generated by the knowledge base.

[0138] Memory 902 can be used to store computer programs and data. The computer programs stored in memory 902 contain instructions that can be executed by the processor. Computer programs can be composed of various functional modules. Processor 901 executes various functional applications and processes data by calling computer programs stored in memory 902.

[0139] The technical solutions provided by the embodiments of the present invention may have the following beneficial effects:

[0140] In the solution of the present invention, a question feedback method based on retrieval and rapid question answering is implemented through rapid matching of questions and scenarios.

[0141] In the solution of the present invention, for problems that cannot be matched, rapid improvement and supplementation are carried out through matching low usage scenarios with high correlation, thereby realizing intelligent information feedback.

[0142] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0143] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0146] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An online education intelligent customer service feedback method based on generative artificial intelligence is characterized by: The method includes: Conduct structural design of operation and maintenance and management platform; Complete type management and vocabulary management of sensitive words; Complete the plug-in settings of the management platform; After obtaining the current question, extract the answer from the current knowledge base for retrieval feedback; For questions that don't have an answer, we filter out the solutions and scenarios with the least backend inquiries based on the number of backend inquiries, update the knowledge base online, and provide feedback on the search questions. Filter questions and answers intelligently generated by the knowledge base; Among them, for the questions that do not have such answers, the number of backend inquiries is used to screen out the solutions and scenarios with the least backend inquiries, update the knowledge base online, and feedback the search questions, specifically including: Get the current number of backend inquiries, sort them and get the solutions with the least inquiries; Obtain all scenario categories of the current knowledge base and extract the scenarios with the least queries under the current scenario category; Push the fewest scenarios and solutions to users, and select the most relevant scenarios and solutions; The most relevant scenarios and solutions are reorganized into a new module, and AI-powered question-answering methods are used to generate several new questions and answers. Add new questions and answers to the original knowledge base; The analysis is repeated until a matching answer is found, completing the feedback of the retrieval question.

2. The online education intelligent customer service feedback method based on generative artificial intelligence according to claim 1, characterized in that: The structural design of the operation and maintenance and management platform specifically includes: Provide a management platform for operation and maintenance and management personnel; The operation and maintenance and management platform is set up to include knowledge base management, question management, feedback management, question and answer session management, common question management, associative question management, sensitive word management and statistical management.

3. The online education intelligent customer service feedback method based on generative artificial intelligence according to claim 1, characterized in that: The completion of sensitive word type management and word management specifically includes: Get the current question and automatically filter out sensitive words contained in the question; Sensitive words are divided into type management and vocabulary management: The type management page includes fuzzy query, create, edit and delete functions; The vocabulary management page includes functions such as query by sensitive word type, fuzzy query by sensitive word, create, edit, and delete.

4. The online education intelligent customer service feedback method based on generative artificial intelligence according to claim 1, characterized in that: The plug-in setting of the said completion management platform specifically includes: Set up pre-set plugin registration methods and structures for the management platform; Set the triggering and mapping calling mode of the plug-in on the management platform; The questions raised in the settings must be filtered by scenarios through the plug-in of the management platform. The scenarios are pre-set ranges and cannot be added later.

5. The online education intelligent customer service feedback method based on generative artificial intelligence according to claim 1, characterized in that: After obtaining the current question, the answer in the current knowledge base is extracted for retrieval feedback, specifically including: Get the current question, search in the current knowledge base, and provide direct feedback if there is an answer; If there is no such answer, a new question feedback template is created, wherein the new question feedback template includes a standard question, a standard answer, and a user ID; For questions that do not have such answers in the feedback, submit a request for multi-scene matching and provide feedback on the screen to start multi-scene adaptive matching.

6. The online education intelligent customer service feedback method based on generative artificial intelligence according to claim 1, characterized in that: The screening of questions and answers intelligently generated by the knowledge base specifically includes: Get all newly generated questions and answers in this Q&A session; Determine the consistency of the scenario, directly delete questions and answers that are inconsistent with the scenario and the current question, and update the knowledge base.

7. The online education intelligent customer service feedback system based on generative artificial intelligence is characterized by: The system is used to implement the method according to any one of claims 1 to 6, and the system comprises: The management platform's settings module is used for operation and maintenance and structural design of the management platform; Sensitive word screening module, used to complete sensitive word type management and vocabulary management; Plug-in setting module, used to complete the plug-in settings of the management platform; The standard answer library module is used to extract the answers in the current knowledge base for retrieval feedback after obtaining the current question; The least-questioned scenario module is used to screen out the solutions and scenarios with the least backend inquiries based on the number of backend inquiries for the questions that do not have such answers, update the knowledge base online, and provide feedback on the search questions; The scenario selection module is used to filter the questions and answers intelligently generated by the knowledge base.

8. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 6 when executed by a processor.

9. An electronic device comprising a memory and a processor, characterized in that: The memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 6.

Images