Knowledge interaction method and device based on thinking chain and computer storage medium

Abstract

The invention provides a thinking chain-based knowledge interaction method, a knowledge interaction device and a computer storage medium. The knowledge interaction method comprises the following steps: acquiring a knowledge question text; constructing an interactive thinking chain according to the knowledge question text; and sequentially outputting multiple rounds of interaction problems based on the interaction thinking chain, and determining the problem number of each round of interaction problems according to the interaction reply text corresponding to each round of interaction problems. Through the knowledge interaction method, the thinking chain of knowledge interaction is constructed, the user is guided to answer the knowledge interaction problem through multiple rounds of interaction problems, the interaction problem is adjusted in a personalized mode according to the user interaction content, heuristic guide interaction explanation is achieved, and the efficiency and effect of knowledge interaction are improved.

Description

Technical Field

[0001] This application relates to the field of knowledge interaction technology, and in particular to a knowledge interaction method, a knowledge interaction device, and a computer storage medium based on thought chains. Background Technology

[0002] With the rapid development of science and technology and artificial intelligence, a common method for answering humanities questions is to use Large Language Model (LLM). This method typically involves inputting text and then providing the answer in the relevant text. The answer is read aloud by a virtual avatar, and some underlined text and key information are added to the screen to teach children how to answer the question.

[0003] Current solutions for humanities problems using Large Language Models (LLMs) only leverage the capabilities of the language model itself. They provide relevant clues from the text and highlight key points for answering the question, presenting all this information to the user. However, the information is often presented in a disorganized and illogical manner, leaving users with only a superficial understanding. Even if they feel they've learned something, they may still struggle with similar problems later. This significantly increases the learning and comprehension costs, reduces learning efficiency, and negatively impacts the user experience. Summary of the Invention

[0004] To address the aforementioned technical problems, this application proposes a knowledge interaction method, a knowledge interaction device, and a computer storage medium based on a thought chain.

[0005] To address the aforementioned technical problems, this application proposes a knowledge interaction method based on thought chains, the knowledge interaction method comprising:

[0006] Obtain knowledge question text;

[0007] Construct an interactive thought chain based on the knowledge question text;

[0008] Based on the interactive thinking chain, multiple rounds of interactive questions are output sequentially, and the number and content of each round of interactive questions are determined according to the interactive response text corresponding to each round of interactive questions.

[0009] The step of determining the number and content of the interactive questions in each round based on the interactive response text corresponding to each round of interactive questions includes:

[0010] Retrieve the first interactive question for the current round of interactive questions, and the first interactive response text entered by the user upon initial input;

[0011] Compare the first interactive response text with the standard interactive response text of the first interactive question;

[0012] If the comparison result indicates that the response is correct, output a brief explanation text in the current round of interactive questions;

[0013] If the comparison result indicates an error, a second interactive question will be output based on the error message in the current round of interactive questions.

[0014] The step of continuing to output a second interactive question based on the content of the incorrect response in the current round of interactive questions includes:

[0015] Based on the content of the incorrect response, identify the target knowledge points;

[0016] Based on the target knowledge points, generate guiding interactive text;

[0017] Based on the guiding interactive text, the second interactive question will continue to be output.

[0018] Before continuing to output the second interactive question based on the guiding interactive text, the knowledge interaction method further includes:

[0019] Output the explanatory text of the target knowledge points, and / or external links to the knowledge points.

[0020] Before continuing to output the second interactive question based on the guiding interactive text, the knowledge interaction method further includes:

[0021] Based on the target knowledge points, locate and output the relevant text of the target material in the material text.

[0022] The knowledge interaction method shown also includes:

[0023] If the comparison result is no response, the third interaction question will be output based on the content of the unanswered question in the current round of interaction questions.

[0024] The knowledge interaction method further includes:

[0025] Based on all the interactive response texts of the multi-round interactive question, generate and output the error response analysis text and / or error response suggestion text during the knowledge interaction process.

[0026] The knowledge interaction method further includes:

[0027] Generate new knowledge question text based on the knowledge question text, the error response analysis text, and / or the error response suggestion text;

[0028] Multiple rounds of knowledge interaction will be conducted based on the new knowledge question text until the user's feedback response text meets the requirements of the knowledge question type.

[0029] To address the aforementioned technical problems, this application also proposes a knowledge interaction device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the knowledge interaction method as described above.

[0030] To address the aforementioned technical problems, this application also proposes a computer storage medium for storing program data, which, when executed by a computer, is used to implement the aforementioned knowledge interaction method.

[0031] Compared with existing technologies, the beneficial effects of this application are as follows: the knowledge interaction device acquires knowledge question text; constructs an interactive thought chain based on the knowledge question text; sequentially outputs multiple rounds of interactive questions based on the interactive thought chain, and determines the number of questions in each round of interactive questions based on the interactive response text corresponding to each round of interactive questions. Through the above knowledge interaction method, a thought chain for knowledge interaction is constructed, and users are guided to answer knowledge interaction questions through multiple rounds of interactive questions. The interactive questions are personalized according to the user's interaction content, achieving heuristic guidance and improving the efficiency and effectiveness of knowledge interaction. When outputting each round of interactive questions, the knowledge interaction device adjusts the number and content of the current round of interactive questions in real time based on the user's interactive response text, achieving a targeted explanation effect. For cases where the user's interactive response accuracy is high, the number of interactive questions is reduced to improve knowledge interaction efficiency; for cases where the user's interactive response accuracy is high, heuristic guidance interactive questions are added to improve the knowledge interaction effect. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] in:

[0034] Figure 1 This is a flowchart illustrating the first embodiment of the knowledge interaction method based on thought chain provided in this application;

[0035] Figure 2 This is a schematic diagram of an embodiment of the material text provided in this application;

[0036] Figure 3 This is an analytical diagram illustrating the thought process behind the solution provided in this application;

[0037] Figure 4 This is a schematic diagram illustrating the knowledge problem provided in this application;

[0038] Figure 5 yes Figure 1 The diagram shows the specific process flow of step S13 in the knowledge interaction method based on the thinking chain.

[0039] Figure 6 yes Figure 5 The diagram shows the specific process flow of step S134 in the knowledge interaction method based on the thinking chain.

[0040] Figure 7 This is a flowchart illustrating the second embodiment of the knowledge interaction method based on thought chain provided in this application;

[0041] Figure 8 This is a schematic diagram of the knowledge interaction summary and analysis content based on the thought chain provided in this application;

[0042] Figure 9 This is a flowchart illustrating the third embodiment of the knowledge interaction method based on thought chain provided in this application;

[0043] Figure 10 This is a schematic diagram of the structure of an embodiment of the knowledge interaction device provided in this application;

[0044] Figure 11 This is a schematic diagram of the structure of an embodiment of the computer storage medium provided in this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0046] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0047] This application's knowledge interaction method is applicable to humanities instruction, encyclopedic instruction, and elementary school tutoring. Taking humanities instruction as an example, the question formats of this application's knowledge interaction method can include, but are not limited to, Chinese reading comprehension questions and answers, English reading comprehension questions and answers, English multiple-choice questions and answers, and English cloze test questions and answers. Humanities instruction questions are often complex and diverse, especially Chinese and English reading comprehension questions and answers, whose corresponding background material sentences are semantically rich and lengthy. Current instruction methods focus on explaining the questions directly, providing answers in a didactic manner, resulting in too many difficult-to-understand parts, leaving children still confused. Furthermore, reading comprehension questions combine logic and textual analysis. Through analysis and summarization, this method teaches children thinking methods, enabling them to better understand the question, learn the question, and learn a type of question.

[0048] To address the aforementioned issues, this application proposes a humanities-based teaching method using an AI (Artificial Intelligence) teacher based on a problem-solving thought process chain. This method leverages a large model's ability to analyze textual problems, extracting the thought process chain for solving the question and teaching the child the solution. Furthermore, it analyzes the child's answers, combining the question-and-answer interaction during the explanation to identify areas of difficulty, pinpointing the reasons for errors, and providing targeted explanations. For areas the child understands, simple explanations are provided; for areas they don't understand, heuristic guidance is used, achieving one-on-one personalized tutoring to improve the child's learning efficiency. Finally, the method guides the child step-by-step to arrive at the answer independently, summarizing the reasons for their errors and providing suggestions for improvement.

[0049] This application proposes a knowledge interaction method for AI teachers based on problem-solving thought chains. The core idea of ​​this method is as follows: users upload test questions that require tutoring, and a large-scale Chinese language LLM model generates the answers and explanations for the test questions. Through the slow thinking of the large-scale model, the thought chain of the question is constructed, teaching children the problem-solving methods. This not only enables them to learn the specific question but also a type of question. The model also accurately identifies the user's mistakes by recognizing the user's answers and guiding questions during the explanation process. It provides detailed explanations of the correct and incorrect steps, and brief guidance on the correct steps, providing personalized tutoring to improve learning efficiency. Finally, based on the summary of the user's mistakes, personalized learning suggestions are given.

[0050] Please refer to the details. Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the knowledge interaction method based on thought chain provided in this application.

[0051] The knowledge interaction method of this application is applied to a knowledge interaction device, which can be a server, a terminal device, or a system in which the server and the terminal device cooperate with each other. Accordingly, the various parts of the knowledge interaction device, such as each unit, subunit, module, and submodule, can all be set in the server, all in the terminal device, or separately in the server and the terminal device.

[0052] Furthermore, the aforementioned server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules, such as software or software modules used to provide distributed server functionality, or as a single software program or software module; no specific limitations are made here.

[0053] like Figure 1 As shown, the specific steps are as follows:

[0054] Step S11: Obtain the knowledge question text.

[0055] In this embodiment, the knowledge interaction device acquires the text of the knowledge question to be interacted with. Taking the humanities as an example, the content to be interacted with includes, but is not limited to, the material text and the knowledge question text. For the material text, please refer to [link / reference needed]. Figure 2 , Figure 2 This is a schematic diagram of one embodiment of the material text provided in this application. Corresponding to... Figure 2 The text of the material shown could be accompanied by the following knowledge question: "Can the last sentence of the article, 'It seems he is really poor,' be deleted? Why?"

[0056] The interactive content can be obtained by the user by taking a picture or other means to capture an image containing a humanities question. Then, image recognition methods such as OCR (Optical Character Recognition) can be used to recognize the captured image to obtain the text content of the humanities question to be answered and the user's handwriting area.

[0057] In other embodiments, the content to be interacted with can also be transmitted and input directly as data.

[0058] Step S12: Construct an interactive thought chain based on the knowledge question text.

[0059] In this embodiment of the application, the knowledge interaction device provides online answers and explanations through the Large Language Model (LLM), and constructs an interactive thought chain for the question through the model's slow thinking.

[0060] The interactive thought chain of this application may include, for example: Figure 3 The analytical diagram of the solution's thought process shown can also be interpreted as follows: Figure 4 The diagram shown illustrates the analysis of knowledge-related issues.

[0061] Step S13: Output multiple rounds of interactive questions sequentially based on the interactive thinking chain, and determine the number of questions and the content of each round of interactive questions based on the interactive response text corresponding to each round of interactive questions.

[0062] In this embodiment of the application, the knowledge interaction device is based on Figure 3 The analysis diagram shown sequentially generates and outputs multi-turn interaction questions. The principle behind generating these multi-turn interaction questions lies in determining the user's response. Figure 3 Whether the understanding of each part shown is thorough and accurate, that is, judging the user's understanding based on the user's interactive responses. Figure 3 The level of knowledge mastery shown.

[0063] Specifically, the user's interactive response text in this application mainly includes two parts: first, the user's answer text to the knowledge question; second, the user's answer text to multi-round interactive questions. The input methods for the above-mentioned answer text also include, but are not limited to: recognizing the handwritten answer area by OCR or directly transmitting and inputting data.

[0064] For each round of interactive question generation, the knowledge interaction device needs to adaptively adjust the number and content of the interactive questions based on the user's response text for each round. The number and content of the interactive questions reflect the depth of the interactive questions; that is, the deeper the interactive questions, the more questions there are in the current round, and the closer the content of the current round's interactive questions is to the user's responses. Figure 3 The analysis content shown in the diagram is as follows.

[0065] The knowledge interaction device of this application adjusts the question depth of each round of interaction based on the user's interactive response text. For interaction questions that the user misunderstands, the question depth is increased to deepen the user's understanding of the interaction question; for interaction questions that the user understands correctly, the question depth is decreased to improve the user's knowledge interaction efficiency.

[0066] Please refer to the details. Figure 5 , Figure 5 yes Figure 1 The diagram shows the specific process flow of step S13 in the knowledge interaction method based on the thought chain.

[0067] like Figure 5 As shown, the specific steps are as follows:

[0068] Step S131: Obtain the first interactive question for the current round of interactive questions, and the first interactive response text entered by the user for the first time.

[0069] In this embodiment of the application, the first interaction question in the current round of interaction expresses the user's response to... Figure 3 The analysis diagram illustrates the comprehension of any interactive element, such as "highlighting the honesty and trustworthiness of the herdsmen" or "expressing the author's praise." The knowledge interaction device primarily analyzes the user's level of understanding of the interactive question based on the user's input of the interactive response text.

[0070] Step S132: Compare the first interactive response text with the standard interactive response text of the first interactive question.

[0071] In this embodiment, the knowledge interaction device matches the user-input interactive response text with the standard interactive response text generated by LLM, and analyzes the user's understanding of the interactive question based on the similarity score. Higher similarity indicates a higher level of understanding, while lower similarity indicates a lower level of understanding.

[0072] Step S133: If the comparison result indicates that the response is correct, output a simple explanation text in the current round of interactive questions.

[0073] In this embodiment, when the similarity between the user-input interactive response text and the standard interactive response text generated by the LLM exceeds a preset threshold, the knowledge interaction device determines that the user's response to the current interactive question is correct. At this time, the knowledge interaction device considers the user's understanding to be correct, and the large language model only needs to directly output a simple explanation text after the current round of interactive questions, that is, output the analysis process of the large language model in the solution chain for the current interactive question.

[0074] Step S134: If the comparison result is an error, continue to output the second interactive question in the current round of interactive questions based on the error content.

[0075] In this embodiment, when the similarity between the user-input interactive response text and the standard interactive response text generated by the LLM is lower than a preset threshold, the knowledge interaction device determines that the user's response to the current interactive question is incorrect. At this point, the knowledge interaction device considers the user's understanding to be flawed. The device then inputs the flawed content into the large language model, outputs the interactive question indicating the user's misunderstanding, and guides the user to rethink and rephrase the flawed content.

[0076] The knowledge interaction device in this application continues to generate heuristic explanations for knowledge points that users misunderstand, guiding users step by step to interact and think more deeply about the knowledge points they misunderstand.

[0077] Furthermore, please refer to the logic for generating the corresponding interactive questions in the knowledge interaction method of this application. Figure 6 , Figure 6 yes Figure 5 The diagram shows the specific process flow of step S134 in the knowledge interaction method based on the thought chain.

[0078] like Figure 6 As shown, the specific steps are as follows:

[0079] Step S1341: Determine the target knowledge point based on the error response.

[0080] In this embodiment, the knowledge interaction device determines the user's incorrect response content by comparing the user's input interactive response text with the standard interactive response text generated by LLM, and then determines the target knowledge point of the incorrect response content. For the correct part of the response, it is not necessary to generate a corresponding interactive question.

[0081] Step S1342: Generate guiding interactive text based on the target knowledge points.

[0082] In this embodiment of the application, the knowledge interaction device generates guiding interactive text based on the target knowledge point. The guiding interactive text may include interactive text with two guiding directions: first, guidance on understanding the target knowledge point; second, guidance on how the target knowledge point is reflected in the material text.

[0083] Step S1343: Continue to output the second interactive question based on the guiding interactive text.

[0084] In this embodiment, the knowledge interaction device continues to generate interactive questions corresponding to the guiding interactive text through LLM, guiding the user to understand and think about the target knowledge points.

[0085] Step S135: If the comparison result is no response, continue to output the third interaction question in the current round of interaction questions based on the content of the unanswered question.

[0086] In this embodiment of the application, during the comparison between the interactive response text input by the user and the standard interactive response text generated by the LLM, if the knowledge interaction device analyzes that the user has not responded to all or part of the interactive questions, it can also generate and output targeted interactive questions for the unanswered questions, guiding the user to provide supplementary responses to these unanswered questions.

[0087] Furthermore, before outputting interactive questions targeting a specific knowledge point, the knowledge interaction device can first output explanatory text or external links to that knowledge point. The explanatory text provides a theoretical explanation of the target knowledge point; while the external links connect to external knowledge bases. Users can click on these links to navigate to an external interface to access related content, including but not limited to textual materials, audio-visual materials, etc.

[0088] This application's knowledge interaction method acquires knowledge question text; constructs an interactive thought chain based on the knowledge question text; sequentially outputs multiple rounds of interactive questions based on the interactive thought chain, and determines the number of questions in each round of interactive questions based on the interactive response text corresponding to each round of interactive questions. Through the above knowledge interaction method, a knowledge interaction thought chain is constructed, and users are guided to answer knowledge interaction questions through multiple rounds of interactive questions. Interactive questions are personalized according to user interaction content to achieve heuristic guidance and improve the efficiency and effectiveness of knowledge interaction. When outputting each round of interactive questions, the knowledge interaction device adjusts the number and content of the current round of interactive questions in real time based on the user's interactive response text to achieve targeted explanation effects. For cases where the user's interactive response accuracy is high, the number of interactive questions is reduced to improve knowledge interaction efficiency; for cases where the user's interactive response accuracy is high, heuristic guidance interactive questions are added to improve the knowledge interaction effect.

[0089] Please continue reading. Figure 7 , Figure 7 This is a flowchart illustrating the second embodiment of the knowledge interaction method based on thought chain provided in this application.

[0090] like Figure 7 As shown, the specific steps are as follows:

[0091] Step S21: Obtain the knowledge question text.

[0092] Step S22: Construct an interactive thought chain based on the knowledge question text.

[0093] Step S23: Output multiple rounds of interactive questions sequentially based on the interactive thinking chain, and determine the number of questions and the content of each round of interactive questions based on the interactive response text corresponding to each round of interactive questions.

[0094] In this embodiment of the application, the contents of steps S21 to S23 are as follows: Figure 1 The steps S11 and S13 of the knowledge interaction method shown have been described in detail and will not be repeated here.

[0095] Step S24: Based on all the interactive response texts of the multi-round interactive question, generate and output the error response analysis text and / or error response suggestion text in the knowledge interaction process.

[0096] In this embodiment of the application, after the entire knowledge interaction is completed, the large language model combines the user's answers and responses during the guidance process to determine the user's error in the question and provides personalized suggestions for the error, so that the user knows where the problem is and can learn more efficiently.

[0097] Specifically, please refer to Figure 8 , Figure 8 This is a schematic diagram of the knowledge interaction summary and analysis content based on the thought chain provided in this application.

[0098] like Figure 8 As shown, the knowledge interaction summary and analysis content can include the automatically generated answer content of the knowledge question text output by the large language model, as well as all interactive response texts of the large language model to the user's indentation. Combining the entire interaction process and guidance process, the summary and analysis can provide personalized analysis and personalized suggestions for the user.

[0099] Please continue reading. Figure 9 , Figure 9 This is a flowchart illustrating the third embodiment of the knowledge interaction method based on thought chain provided in this application.

[0100] like Figure 9 As shown, the specific steps are as follows:

[0101] Step S31: Obtain the knowledge question text.

[0102] Step S32: Construct an interactive thought chain based on the knowledge question text.

[0103] Step S33: Output multiple rounds of interactive questions sequentially based on the interactive thinking chain, and determine the number of questions and the content of each round of interactive questions based on the interactive response text corresponding to each round of interactive questions.

[0104] Step S34: Based on all the interactive response texts of the multi-round interactive question, generate and output the error response analysis text and / or error response suggestion text in the knowledge interaction process.

[0105] In this embodiment of the application, the contents of steps S31 to S34 are as follows: Figure 7 The steps S21 and S24 of the knowledge interaction method shown have been explained in detail and will not be repeated here.

[0106] Step S35: Generate new knowledge question text based on the knowledge question text, error response analysis text, and / or error response suggestion text.

[0107] In this embodiment of the application, the knowledge interaction device analyzes the error response analysis text and error response suggestion text determined in step S34 to adjust the knowledge question text in step S31, so as to generate new knowledge question text that tends to ask questions again about the user's misunderstanding or misunderstanding in the previous knowledge interaction process, so as to verify whether the user truly understands the knowledge interaction content of the large language model.

[0108] Step S36: Perform multiple rounds of knowledge interaction based on the new knowledge question text until the user's feedback response text meets the requirements of the knowledge question type.

[0109] In this embodiment of the application, the knowledge interaction device re-executes Figure 1 The knowledge interaction process shown continues until the large language model determines that the user's understanding of the knowledge interaction problem has reached a standard level or above.

[0110] This application provides a knowledge interaction method for AI teachers based on problem-solving thought chains. When users generate answers and explanations for humanities questions using a Large Language Model (LLM), the model constructs a problem-solving thought chain for the question through slow thinking, teaching users how to think about the question and master the problem-solving approach. At the same time, based on user answers and interactive content, it identifies the steps that users do not understand and provides targeted, heuristic guidance to ensure that children thoroughly understand the areas they do not understand. Finally, based on the interactive content and user answers during the tutoring process, it summarizes the reasons for the user's mistakes and provides personalized suggestions for the question.

[0111] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0112] To implement the aforementioned knowledge interaction method based on thought chains, this application also proposes a knowledge interaction device, for details please refer to [link / reference needed]. Figure 10 , Figure 10 This is a schematic diagram of the structure of an embodiment of the knowledge interaction device provided in this application.

[0113] The knowledge interaction device 400 in this embodiment includes a processor 41, a memory 42, an input / output device 43, and a bus 44.

[0114] The processor 41, memory 42, and input / output device 43 are respectively connected to the bus 44. The memory 42 stores program data, and the processor 41 is used to execute the program data to implement the knowledge interaction method based on the thought chain in the above embodiment.

[0115] In this embodiment, processor 41 can also be referred to as a CPU (Central Processing Unit). Processor 41 may be an integrated circuit chip with signal processing capabilities. Processor 41 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor, or processor 41 can be any conventional processor.

[0116] This application also provides a computer storage medium; please refer to the following: Figure 11 , Figure 11 This is a schematic diagram of a computer storage medium according to an embodiment of the present application. The computer storage medium 600 stores a computer program 61, which, when executed by a processor, is used to implement the knowledge interaction method based on thought chain in the above embodiment.

[0117] When the embodiments of this application are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A knowledge interaction method based on thought chains, characterized in that, The knowledge exchange method includes: Obtain knowledge question text; Construct an interactive thought chain based on the knowledge question text; Based on the interactive thinking chain, multiple rounds of interactive questions are output sequentially, and the number and content of each round of interactive questions are determined according to the interactive response text corresponding to each round of interactive questions.

2. The knowledge interaction method according to claim 1, characterized in that, The step of determining the number of questions and the content of questions in each round of interaction based on the interactive response text corresponding to each round of interaction questions includes: Retrieve the first interactive question for the current round of interactive questions, and the first interactive response text entered by the user upon initial input; Compare the first interactive response text with the standard interactive response text of the first interactive question; If the comparison result indicates that the response is correct, output a brief explanation text in the current round of interactive questions; If the comparison result indicates an error, a second interactive question will be output based on the error message in the current round of interactive questions.

3. The knowledge interaction method according to claim 2, characterized in that, The step of continuing to output a second interactive question based on the content of the incorrect response in the current round of interactive questions includes: Based on the content of the incorrect response, identify the target knowledge points; Based on the target knowledge points, generate guiding interactive text; Based on the guiding interactive text, the second interactive question will continue to be output.

4. The knowledge interaction method according to claim 3, characterized in that, Before continuing to output the second interactive question based on the guiding interactive text, the knowledge interaction method further includes: Output the explanatory text of the target knowledge points, and / or external links to the knowledge points.

5. The knowledge interaction method according to claim 3, characterized in that, Before continuing to output the second interactive question based on the guiding interactive text, the knowledge interaction method further includes: Based on the target knowledge points, locate and output the relevant text of the target material in the material text.

6. The knowledge interaction method according to claim 2, characterized in that, The knowledge interaction method shown also includes: If the comparison result is no response, the third interaction question will be output based on the content of the unanswered question in the current round of interaction questions.

7. The knowledge interaction method according to claim 1, characterized in that, The knowledge interaction method further includes: Based on all the interactive response texts of the multi-round interactive question, generate and output the error response analysis text and / or error response suggestion text during the knowledge interaction process.

8. The knowledge interaction method according to claim 7, characterized in that, The knowledge interaction method further includes: Generate new knowledge question text based on the knowledge question text, the error response analysis text, and / or the error response suggestion text; Multiple rounds of knowledge interaction will be conducted based on the new knowledge question text until the user's feedback response text meets the requirements of the knowledge question type.

9. A knowledge interaction device, characterized in that, The knowledge interaction device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the knowledge interaction method as described in any one of claims 1 to 8.

10. A computer storage medium, characterized in that, The computer storage medium is used to store program data, which, when executed by the computer, is used to implement the knowledge interaction method as described in any one of claims 1 to 8.

Images