Answer generation method, related device, equipment and storage medium

Abstract

The invention discloses an answer generation method, a related device, equipment and a storage medium, and the method comprises the steps: generating an initial answer of a to-be-answered question; obtaining a plurality of knowledge points related to the question and answer data and explanation description of each knowledge point; obtaining an understandable feedback result of the interpretation description of the target object on the knowledge points; in response to the fact that the feedback result is represented to be ununderstood, respectively selecting each knowledge point with the feedback result represented to be ununderstood as a target knowledge point, obtaining the explanation description of the target knowledge point again, and returning to the step of obtaining the feedback result of the understandability of the target object to the explanation description of the knowledge point; and generating a final answer of the to-be-answered question based on the to-be-answered question and the explanation description of each knowledge point in response to the fact that the feedback result of each knowledge point is represented to be understandable. According to the scheme, the understandability of the generated answer can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of natural language processing, and in particular to a method for generating an answer and related devices, equipment and storage media. Background Art

[0002] In recent years, thanks to the rapid development of generative models such as large language models, intelligent question-answering technology has been widely used in many fields such as education, office, and medical care.

[0003] However, existing intelligent question-answering technologies are often targeted at professionals who already have a certain amount of knowledge, but non-professionals who do not yet have a certain amount of knowledge are limited by factors such as cognitive level and often find it difficult to understand the output answers. Taking education scenarios as an example, existing popular science question-answering technologies are usually suitable for older students or students with a certain amount of knowledge, while primary school students often find it difficult to understand the output popular science answers. In view of this, how to improve the comprehensibility of generated answers has become an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present application is to provide an answer generation method and related devices, equipment and storage media, which can improve the comprehensibility of the generated answers.

[0005] In order to solve the above technical problems, the first aspect of the present application provides an answer generation method, including: generating an initial answer to a question to be answered; obtaining a number of knowledge points involved in the question and answer data and an explanation description of each knowledge point; wherein the question and answer data includes at least the question to be answered and the initial answer; obtaining feedback results on the comprehensibility of the target object's explanation description of the knowledge point; in response to the feedback results being characterized as incomprehensible, selecting each knowledge point characterized by the feedback results as incomprehensible as the target knowledge point, and re-obtaining the explanation description of the target knowledge point, and returning to the step of obtaining feedback results on the comprehensibility of the target object's explanation description of the knowledge point; in response to the feedback results of each knowledge point being characterized as understandable, generating a final answer to the question to be answered based on the question to be answered and the explanation description of each knowledge point.

[0006] In order to solve the above technical problems, the second aspect of the present application provides an answer generation device, including: an initial answer generation module, a question and answer data analysis module, an explanation and understanding feedback module, an interactive loop iteration module and a final answer generation module, the initial answer generation module is used to generate an initial answer to the question to be answered; the question and answer data analysis module is used to obtain a number of knowledge points involved in the question and answer data and an explanation description of each knowledge point; wherein the question and answer data at least includes the question to be answered and the initial answer; the explanation and understanding feedback module is used to obtain feedback results on the comprehensibility of the explanation description of the knowledge point by the target object; the interactive loop iteration module is used to select each knowledge point characterized by the feedback result as incomprehensible as the target knowledge point in response to the feedback result being characterized as incomprehensible, and re-acquire the explanation description of the target knowledge point, and return to the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object; the final answer generation module is used to generate a final answer to the question to be answered based on the question to be answered and the explanation description of each knowledge point in response to the feedback results of each knowledge point being characterized as understandable.

[0007] In order to solve the above technical problems, the third aspect of the present application provides an electronic device, which at least includes a memory and a processor coupled to each other, the memory at least stores program instructions, and the processor is used to execute the program instructions to implement the answer generation method in the above first aspect.

[0008] In order to solve the above technical problem, the fourth aspect of the present application provides a computer-readable storage medium, which stores program instructions that can be executed by a processor, and the program instructions are used to implement the answer generation method of the above first aspect.

[0009] The above scheme generates an initial answer to the question to be answered, obtains several knowledge points involved in the question and answer data and the explanation description of each knowledge point, and the question and answer data at least includes the question to be answered and the initial answer, and then obtains the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object, so that in response to the feedback result being characterized as incomprehensible, each knowledge point characterized by the feedback result as incomprehensible is selected as the target knowledge point, and the explanation description of the target knowledge point is re-obtained, and the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is returned, and in response to the feedback result of each knowledge point being characterized as understandable, based on the question to be answered and the explanation description of each knowledge point, the generation The final answer to the question to be answered is formed by combining the explanation and description of each knowledge point involved in the question and answer data when generating the final answer to the question to be answered, so that the explanation and description of the knowledge point can be reflected in the final answer, which helps to improve the comprehensibility of the generated answer. On the other hand, the feedback results of the comprehensibility of the target object’s explanation and description of the knowledge point are also referred to during the question and answer process. When it is characterized as incomprehensible, the explanation and description of the knowledge point are re-acquired and iterated in a loop until the feedback result of the target object’s comprehensibility is characterized as understandable. This can achieve that the target object can understand the explanation and description of each knowledge point when generating the final answer, which helps to improve the comprehensibility of the final answer as much as possible. Therefore, the comprehensibility of the generated answer can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of an embodiment of the answer generation method of the present application; Figure 2 It is a process diagram of an embodiment of the answer generation method of the present application; Figure 3 It is a schematic diagram of a framework of an embodiment of an answer generating device of the present application; Figure 4 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application; Figure 5 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0011] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0012] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0013] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the fragment " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0014] See also Figure 1 , Figure 1 This is a flowchart of an embodiment of the answer generation method of the present application. Specifically, it may include the following steps: Step S11: Generate an initial answer to the question to be answered.

[0015] In one implementation scenario, the questions to be answered may be obtained through text, voice, or other inputs, and the method for obtaining the questions to be answered is not limited herein.

[0016] In an implementation scenario, the specific content of the questions to be answered can be set according to the application scenario. For example, taking the education scenario as an example, the questions to be answered include scientific questions (such as, "What are black holes made of?", "Is the effect of extinguishing a fire with hot water the same as that of extinguishing a fire with cold water?", "Why does ice float on the water?", etc.), or, taking the medical scenario as an example, the questions to be answered may include medical questions (such as, "What changes in physical health does graying hair indicate?", etc.). Of course, the above examples are only examples of several possible examples of questions to be answered, taking the education scenario and the medical scenario as examples, and do not limit the specific content of the questions to be answered. The specific content of the questions to be answered will not be given one by one here.

[0017] In an implementation scenario, in order to obtain an initial answer to a question to be answered, as a possible example, the question to be answered can be input into a large language model to obtain the output answer of the large language model as the initial answer. Alternatively, as another possible example, a search can be first performed based on the question to be answered (e.g., a search can be performed in external knowledge sources such as scientific literature databases, mainstream academic journals, and authoritative websites) to obtain the reference data required to answer the question to be answered (e.g., the latest data, research results, or theoretical explanations related to the question to be answered). Based on this, a prompt instruction can be constructed in combination with the question to be answered and the reference data, and the prompt instruction is used to instruct the large language model to answer the question to be answered in combination with the reference data, so as to guide the large language model to generate a more accurate initial answer through the reference data, and to avoid the "hallucination" phenomenon of the large language model itself as much as possible. The prompt instruction is then input into the large language model to obtain the output answer of the large language model as the initial answer, so that the large language model can give a more scientific answer based on authoritative knowledge, greatly reducing the risk of scientific errors when the model gives an isolated answer. For ease of description, in this case, the initial answer can be expressed as: …… (1) In the above formula (1), Indicates the initial answer, represents a large language model, Indicates questions to be answered. In addition, the large language model may specifically include but is not limited to open source models such as LLAMA, Bloom, etc., or the large language model may be obtained by fine-tuning parameters based on a specific corpus and an open source large model, or the large language model may also be a custom large model, and the specific source of the large language model is not limited here.

[0018] Step S12: Obtain several knowledge points involved in the question and answer data and explanations of each knowledge point.

[0019] In the disclosed embodiment, the question and answer data may include at least the question to be answered and the initial answer. For example, still taking the education scenario as an example, the question to be answered is "What is a black hole made of?", and the initial answer may be "A black hole is a celestial body formed by the gravitational collapse of a massive star after a supernova explosion. A black hole consists of an event horizon and a singularity. The event horizon is the boundary of the black hole, and the singularity is the core of the black hole...", then the two can constitute the question and answer data for further analysis of the question and answer data. Of course, the above example is only a possible example of question and answer data when taking the education scenario as an example. The specific content of the question and answer data is not limited here, and examples are not given one by one.

[0020] In an implementation scenario, as a possible example, after obtaining the question and answer data, analysis can be performed based on the question and answer data to obtain several knowledge points, and the explanation description of each knowledge point can be extracted from the question and answer data. Still taking the aforementioned question to be answered as the scientific question "What is a black hole made of?" as an example, the knowledge points may include but are not limited to at least one of scientific concepts and scientific phenomena, then analysis can be performed based on the question and answer data to obtain several knowledge points: "black hole", "event horizon", "singularity", and extract the description explanation of the knowledge point "black hole" from the question and answer data: "A black hole is a celestial body formed by the gravitational collapse of a massive star after a supernova explosion", the description explanation of the knowledge point "event horizon" "The event horizon is the boundary of a black hole", and the description explanation of the knowledge point "singularity" "The singularity is the core of a black hole". Of course, the above example is only a possible example of knowledge points and their description explanations in actual application, and other possible situations will not be given one by one here.

[0021] In a specific implementation scenario, the question and answer data can be analyzed by a large language model to obtain several knowledge points. Exemplarily, a prompt instruction can be constructed based on the question and answer data, and the prompt instruction is used to instruct the large language model to extract the knowledge points involved in answering the questions to be answered from the question and answer data, and then input the prompt instruction to the large language model to obtain the output result of the large language model, and several knowledge points can be obtained. It should be noted that the specific source of the large language model can be found in the aforementioned description of the large language model, which will not be repeated here.

[0022] In another specific implementation scenario, in addition to the aforementioned implementation method of obtaining several knowledge points through large language model analysis, the question and answer data can also be analyzed through a pre-trained deep learning model to obtain several knowledge points. Exemplarily, the deep learning model may include but is not limited to BERT (Bidirectional Encoder Representations from Transformers, bidirectional encoding representation based on Transformer), etc., and the specific architecture of the deep learning model is not limited here. Specifically, sample question and answer data can be obtained in advance, and the sample question and answer data is annotated with several sample knowledge points involved, and the sample question and answer data is processed based on the deep learning model to obtain several predicted knowledge points, and then based on the difference between the predicted knowledge points and the sample knowledge points, the network parameters of the deep learning model are adjusted, so that the deep learning model can learn how to analyze the knowledge points involved in answering the questions to be answered from the question and answer data through model training.

[0023] In another implementation scenario, as another possible example, after obtaining the question and answer data, it is also possible to analyze based on the question and answer data to obtain several candidate knowledge points. For example, the question and answer data can be analyzed by a large language model, a pre-trained deep learning model, etc., to obtain several knowledge points as candidate knowledge points. For details, please refer to the above-mentioned related descriptions, which will not be repeated here. In addition, during the analysis process, the hierarchical decision-making strategy in reinforcement learning can also be used to determine the core elements in the question and answer data. For details, please refer to the technical details of the hierarchical decision-making strategy in reinforcement learning, which will not be repeated here. On this basis, each candidate knowledge point related to answering the question to be answered can be selected as several knowledge points involved in the question and answer data, that is, the knowledge points involved in answering the question to be answered, and the initial explanation of each knowledge point in the question and answer data is extracted, and the professional explanation of each knowledge point is retrieved separately, and then for each knowledge point, the initial explanation is corrected based on the professional explanation to obtain the explanation description of the corresponding knowledge point. The above method, by selecting candidate knowledge points related to the question to be answered and using professional explanations to correct the extracted initial explanations, can, on the one hand, avoid redundant answers as much as possible and help improve the conciseness of the generated answers; on the other hand, it can avoid inaccurate, imprecise or factually incorrect answers as much as possible.

[0024] In a specific implementation scenario, taking the question to be answered "Why does ice float on the water?" as an example, the initial answer can be "Ice floats on the water because its density is lower than that of water." Then, the question and answer data can be combined for analysis to obtain several candidate knowledge points "density", "density of ice", and "density of water". Since these three are all related to the question to be answered, several knowledge points involved in answering the question to be answered can be obtained: "density", "density of ice", and "density of water". The preceding concepts to be introduced to answer the question to be answered (that is, "density", "density of ice", and "density of water") can be introduced through knowledge point analysis. Alternatively, taking the question to be answered "Why does hair turn white?" as an example, the initial answer can be "Hair turns white because of the reduction of melanin, which is like pigment that can help our hair turn black. In addition, hormonal disorders in the body due to thyroid disease may also cause hair to turn white...", then the question and answer data can be combined for analysis to obtain several candidate knowledge points: "melanin", "thyroid", and "hormones", but the candidate knowledge points "thyroid" and "hormones" are not related to the question to be answered, and only the candidate knowledge point "melanin" is related to the question to be answered. Therefore, the candidate knowledge point "melanin" can be selected as the knowledge point involved in answering the question to be answered, and the knowledge points involved in the redundant answer to the question to be answered (i.e. "thyroid" and "hormones") in the initial answer can be excluded through knowledge point analysis.

[0025] In a specific implementation scenario, after the initial interpretation of each knowledge point is extracted from the question and answer data (the specific extraction method and examples can be found in the aforementioned related description and will not be repeated here; in addition, it is not ruled out that the initial interpretation of the knowledge point extracted from the question and answer data is "empty"), the initial interpretation of the knowledge point can be corrected in combination with the professional interpretation retrieved for the knowledge point (for example, the professional interpretation of the knowledge point can be retrieved from professional databases such as textbooks and technical dictionaries) to obtain an explanation description of the knowledge point.

[0026] Step S13: Obtaining feedback results on the understandability of the target object's explanation and description of the knowledge point.

[0027] In an implementation scenario, as a possible example, the target object may be an agent that simulates a real user. For example, when the real user is a primary school student, the target object may be an agent that simulates the cognitive level and comprehension ability of the primary school student. Of course, the above example is only a possible example of an agent in the actual application process, and does not limit other possible configuration methods of the agent in other possible situations. Other possible configuration methods of the agent are no longer given examples here. In addition, the configuration method of the agent used to simulate the real user can refer to the technical details of the agent, which will not be repeated here. On this basis, after obtaining the knowledge point and its explanation description, the instructions to be executed can be constructed based on the knowledge point and the explanation description of the knowledge point, and the instructions to be executed are used to execute the agent to feedback the comprehensibility of the knowledge point and its explanation description, and then input the instructions to be executed to the agent to obtain the output result of the agent as the feedback result. In the above method, after obtaining the knowledge point and the explanation description of the knowledge point, the interactive feedback on comprehensibility is realized by the agent, which can improve the feedback efficiency of comprehensibility.

[0028] In a specific implementation scenario, the incomprehensible word and sentence representation simulates the words or sentences that the intelligent agent of the real user judges when it simulates the understanding of the real user that it cannot understand in the explanation description; and the expected explanation method represents the way in which the intelligent agent of the real user expects to explain the knowledge point when judging the explanation description of the incomprehensible knowledge point, such as but not limited to: giving examples, making metaphors, telling stories, etc., and the specific possible situations of the expected explanation method will not be given one by one here.

[0029] In a specific implementation scenario, still taking the question to be answered "What are black holes made of?" as an example, among the several knowledge points involved, there is the knowledge point "black hole", and its explanation description may include "black holes are celestial bodies formed by the gravitational collapse of massive stars after supernova explosions...", then this knowledge point and its explanation description can be constructed to obtain the instruction to be executed "Please determine whether the explanation description of the knowledge point 'black hole' 'black holes are celestial bodies formed by the gravitational collapse of massive stars after supernova explosions...' is understandable. If not, please indicate the incomprehensible words or sentences, or the expected explanation method." Then, the instruction to be executed is input into the intelligent agent, and the feedback result of the intelligent agent can be obtained, such as "incomprehensible, the incomprehensible words are 'supernova', 'gravitational collapse', and the expected explanation method is 'give an example'". Of course, the above example is only one possible example of the feedback result in the actual application process, and other possible situations of the feedback result will not be given one by one here.

[0030] In another implementation scenario, as another possible example, the target object can also be a real user. Then, after obtaining the knowledge point and its explanation description, a prompt message can be constructed based on the knowledge point and its explanation description, and the prompt message is used to prompt the real user to provide feedback on the comprehensibility of the knowledge point and its explanation description, and then output the prompt message, and receive the input content of the real user in response to the prompt message as the feedback result. It should be noted that the real user can input the questions to be answered through terminal devices such as mobile phones, learning machines, and tablet computers, and the above-mentioned terminal devices can be integrated with program instructions for the method flow of the embodiment of the present disclosure, so that after obtaining the knowledge point and the explanation description of the knowledge point, the knowledge point and the explanation description of the knowledge point can be encapsulated as a prompt message and output. For example, the prompt message can be output in at least one way such as text display and voice playback to prompt the user to provide feedback on the comprehensibility of the explanation description of the knowledge point. Exemplarily, still taking the aforementioned unanswered question as an example, for the knowledge point "black hole", a prompt message can be constructed and outputted, "The explanation description of the knowledge point 'black hole' is 'a black hole is a celestial body formed by the gravitational collapse of a massive star after a supernova explosion...', can you understand it? If not, please point out the incomprehensible words or phrases, or the expected explanation method.", so that the real user can enter the feedback result in response to the prompt message, such as "I can't understand it, the incomprehensible words and phrases are 'supernova', 'gravitational collapse', and the expected explanation method is 'give an example'". Exemplarily, a drop-down menu or related options can be displayed on the aforementioned terminal device for the real user to select "can understand" or "cannot understand", and when the real user selects "cannot understand", the real user can be further prompted to enter at least one of the incomprehensible words or phrases and the expected explanation method. Of course, the real user can also provide feedback on the comprehensibility through voice input, so that the real user's feedback result on the comprehensibility of the knowledge point and its explanation description can be obtained through voice recognition. Of course, the above example is only one possible example of feedback results in actual application, and other possible situations of feedback results will not be given one by one here. In the above method, after obtaining the knowledge points and the explanations of the knowledge points, through understandable interactive feedback with real users, the participation perception of real users can be improved before the final answer is given.

[0031] In another implementation scenario, as another possible example, the target object may also include real users and agents simulating real users. On the one hand, based on the knowledge points and the explanation descriptions of the knowledge points, instructions to be executed can be constructed, and the instructions to be executed are used to provide feedback from the executing agent on the comprehensibility of the knowledge points and their explanation descriptions, and the instructions to be executed are input to the agent to obtain the output results of the agent. On the other hand, based on the knowledge points and the explanation descriptions of the knowledge points, prompt messages can be constructed, and the prompt messages are used to prompt real users to provide feedback on the comprehensibility of the knowledge points and their explanation descriptions, and the prompt messages are output. On this basis, it is possible to detect whether the input content of the real user in response to the prompt message is received within a preset time (e.g., 10 seconds, etc.). If received, the input content can be used as the feedback result, otherwise the output result of the agent can be used as the feedback result; or, the output result of the agent and the input content of the real user in response to the prompt message can be complemented to obtain the feedback result; or, the real user can be prompted whether to give feedback on comprehensibility. If the real user confirms not to give feedback, the output result of the agent can be used directly as the feedback result. Otherwise, if the real user confirms to give feedback, the input content of the real user in response to the prompt message can be received, and after receiving it, the input content of the real user can be used as the feedback result. Of course, the above three examples are only several possible ways to obtain feedback results when the target object includes a real user and an agent simulating a real user. Other possible ways of obtaining feedback are not limited to this situation, and no examples are given one by one.

[0032] Step S14: In response to the feedback result being characterized as incomprehensible, each knowledge point characterized as incomprehensible by the feedback result is selected as the target knowledge point, and the explanation description of the target knowledge point is re-obtained, and the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is returned.

[0033] In one implementation scenario, as a possible example, as mentioned above, when the feedback result is characterized as incomprehensible, the feedback result may also include at least one of incomprehensible words and sentences and expected interpretation methods. Then, based on the interpretation description of the target knowledge point and the feedback result, a prompt instruction may be constructed, and the prompt instruction is used to instruct the large language model to adjust the interpretation description of the target knowledge point with reference to at least one of the incomprehensible words and sentences and expected interpretation methods in the feedback result, and then input the prompt instruction to the large language model to obtain the output content of the large language model as a new interpretation description of the target knowledge point. For ease of understanding, let's take the aforementioned question to be answered "What are black holes made of?" as an example. As mentioned above, for the knowledge point "black hole" and its description, there is the following feedback result "incomprehensible, incomprehensible words and sentences are 'supernova' and 'gravitational collapse', and the expected interpretation method is 'give an example'", then the knowledge point "black hole" can be used as the target knowledge point, and combined with its interpretation description and the above feedback results, construct instructions including but not limited to prompts: The explanation and description of the target knowledge point "black hole" is "a black hole is formed by the gravitational collapse of a massive star after a supernova explosion. "... There are two incomprehensible words in this explanation: "supernova" and "gravitational collapse". Please explain. Use the "give examples" explanation method to explain these two incomprehensible words and sentences, and output the target knowledge point "black hole" new Explain the description.

[0034] It should be noted that the above example is only a possible example of a prompt instruction based on the question to be answered, "What are black holes made of?" Other possible situations will not be given one by one here. Still taking the above example as an example, after the above prompt instruction is input into the large language model, the output content of the large language model can be obtained, which may include but is not limited to: Imagine that the stars in the night sky are like the light bulbs in our lives. Most of them burn steadily. However, some stars experience a spectacular and catastrophic event at the end of their lives. The brightness of this explosion is many times higher than the normal brightness of the star, and can even It is seen by the naked eye on the distant Earth, and this is a supernova. A black hole is formed by the supernova explosion of a massive star. What is gravitational collapse? Gravitational collapse is like a game we play with sand. As we pile the sand higher and higher, the gravitational pull between the sand will become stronger and stronger, until a certain critical point, the sand The pile can no longer remain stable and begins to collapse inward. Similarly, stars or interstellar matter also collapse under the gravitational pull of their own matter. This inward collapse process occurs, and this is gravitational collapse.

[0035] It should be noted that the above example is only a possible example of the output content of the large language model, taking the question to be answered "What are black holes made of?" as an example, and other possible situations will not be given one by one here. The above method constructs a prompt instruction based on the explanation description and feedback results of the target knowledge point to instruct the large language model to adjust the explanation description of the target knowledge point with reference to at least one of the incomprehensible words and sentences in the feedback results and the expected explanation method. It can use the general understanding ability of the large language model to refer to the feedback results to tune the explanation description of the target knowledge point, which helps to improve the comprehensibility of the explanation description of the target knowledge point and improve the tuning efficiency of the explanation description.

[0036] In another implementation scenario, as another possible example, as mentioned above, when the feedback result is characterized as incomprehensible, the feedback result may also include at least one of incomprehensible words and sentences and expected interpretation methods, then a preset knowledge base may be obtained, and the preset knowledge base may include several preset knowledge points and their respective interpretation descriptions, and the several preset knowledge points include the target knowledge point, and then the interpretation description of the target knowledge point in the preset knowledge base is selected as the target description, so that based on at least one of the incomprehensible words and sentences and expected interpretation methods in the feedback result, at least part of the target description can be extracted as a reference description, and then the interpretation description of the target knowledge point can be adjusted based on the reference description to obtain a new interpretation description of the target knowledge point. Still taking the aforementioned unanswered question "What are black holes made of?" as an example, as mentioned above, for the knowledge point "black hole" and its description explanation, there is the following feedback result "cannot be understood, the words and sentences that cannot be understood are 'supernova' and 'gravitational collapse', and the expected explanation method is 'give an example'", then the knowledge point "black hole" can be used as the target knowledge point, and the explanation description of the target knowledge point "black hole" in the preset knowledge base can be obtained (for example, at least including the aforementioned example "Imagine that the stars in the night sky are like...") as the target description, so that based on the incomprehensible words and sentences "supernova" and the expected explanation in the feedback results, Based on the interpretation method "give an example", "imagine that the stars in the night sky are like... they can even be seen by the naked eye on the distant earth, this is a supernova" is extracted from the target description as a reference description, and based on the incomprehensible words "gravitational collapse" in the feedback results and the expected interpretation method "give an example", "gravitational collapse is like we are playing a sand game... this is gravitational collapse" is extracted from the target description as a reference description, and then the interpretation description of the target knowledge point "black hole" can be adjusted based on the above two reference descriptions to obtain a new interpretation description of the target knowledge point "black hole". It should be noted that the above example is only a possible example of selecting a target description and extracting a reference description based on the question to be answered "What are black holes made of?", and other possible situations will not be given one by one here. In the above method, a new interpretation description of the target knowledge point is obtained by a series of operations such as obtaining the target description, extracting the reference description from the target description, and adjusting the interpretation description using the reference description, so that the tuning of the interpretation description of the target knowledge point can be more targeted.

[0037] It should be noted that after obtaining the new explanation description of the target knowledge point, for the new explanation description of the target knowledge point, the step of obtaining the feedback result of the understandability of the explanation description of the knowledge point by the target object can be returned to obtain the feedback result of the understandability of the new explanation description of the target knowledge point again, and the cycle is repeated until the latest explanation description of the target knowledge point is characterized as understandable. In addition, in this process, in order to improve the efficiency of question answering, the explanation description of the knowledge point whose feedback result is understandable does not need to obtain the feedback result of the understandability again.

[0038] Step S15: In response to the feedback results of each knowledge point being characterized as being understandable, a final answer to the question to be answered is generated based on the question to be answered and the explanation description of each knowledge point.

[0039] Specifically, when the latest feedback results of each knowledge point are characterized as understandable, the final answer to the question to be answered can be generated based on the question to be answered and the latest explanation description of each knowledge point. Exemplarily, a prompt instruction can be constructed in combination with the question to be answered and the latest explanation description of each knowledge point, and the prompt instruction is used to instruct the large language model to answer the question to be answered with reference to the latest explanation description of each knowledge point. This can not only ensure that the final answer can answer the question to be answered as much as possible, but also make the final answer as consistent as possible with the cognitive level and understanding ability of the real user, and can effectively guide the large language model to avoid generating "hallucinations" (i.e., wrong or fictitious content) as much as possible, and then input the prompt instruction to the large language model to obtain the output content of the large language model as the final answer to the question to be answered. Exemplarily, taking the question to be answered as a scientific question, the final answer can be expressed as: …… (2) In the above formula (2), Indicates the final answer, represents a large language model, Indicates a prompt suitable for scientific questions. Indicates knowledge points, Indicates the explanation description of the knowledge point, Represents a popular explanation of a knowledge point. It should be noted that in the disclosed embodiment, the popular explanation of a knowledge point is obtained by regenerating a new explanation description when the feedback result of the comprehensibility of the knowledge point is characterized as incomprehensible, that is, the popular explanation of the knowledge point can be considered as a part of the new explanation description. For details, please refer to the aforementioned related descriptions and examples, which will not be repeated here. It should be noted that in the disclosed embodiment, the large language model can be replaced by an artificial intelligence model obtained after knowledge distillation of the large language model (the number of parameters of the artificial intelligence model is less than that of the large language model), so as to improve the response speed of the model while still having high accuracy and professionalism. For details, please refer to the technical details of knowledge distillation, which will not be repeated here.

[0040] As a possible example, see Figure 2 , Figure 2 1 is a schematic diagram of the process of an embodiment of the answer generation method of the present application. Figure 2 As shown, still taking the education scenario as an example, for the scientific question to be answered, "What are black holes made of?", we can first combine the retrieval enhancement technology of the large language model to obtain the initial answer to the question to be answered, "Black holes are made up of event horizons and singularities...", and use the knowledge extractor (such as a large language model, or a deep learning model such as BERT, please refer to the above related description for details) to analyze several knowledge points and explanations of the knowledge points from the question and answer data, and use the professional knowledge of the knowledge points in the professional knowledge base to correct the extracted explanations, so as to maximize the scientific nature of the explanations of the knowledge points. On this basis, for each knowledge point and its explanation (such as Figure 2 In the knowledge point 1 "black hole", knowledge point 2 "event horizon" and knowledge point 3 "singularity" and their explanation descriptions), the feedback result of the target object's comprehensibility can be obtained, and when the feedback result is characterized as incomprehensible, the knowledge parser (such as a large language model, a preset knowledge base, etc., please refer to the aforementioned related description for details) is combined with the feedback result to regenerate a new explanation description of the knowledge point, until the target object's feedback result on the comprehensibility of the explanation description of the knowledge point is understandable, then the question to be answered, the knowledge point and its explanation description and popular explanation can be combined to generate prompt instructions. In addition, when generating prompt instructions, it can be further combined with task descriptions, output specifications, examples, etc., which are not limited here. Finally, the prompt instruction can be input into the answer generator (such as a large language model, please refer to the aforementioned related description for details) to obtain the final answer to the question to be answered. Of course, Figure 2 What is shown is only one possible example of the process of generating the final answer when the question to be answered is the scientific question "What are black holes made of?" Other possible situations will not be given examples one by one here.

[0041] The above scheme generates an initial answer to the question to be answered, obtains several knowledge points involved in the question and answer data and the explanation description of each knowledge point, and the question and answer data at least includes the question to be answered and the initial answer, and then obtains the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object, so that in response to the feedback result being characterized as incomprehensible, each knowledge point characterized by the feedback result as incomprehensible is selected as the target knowledge point, and the explanation description of the target knowledge point is re-obtained, and the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is returned, and in response to the feedback result of each knowledge point being characterized as understandable, based on the question to be answered and the explanation description of each knowledge point, the above scheme generates an initial answer to the question to be answered and the explanation description of each knowledge point, and then obtains the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object. The final answer to the question to be answered is formed by combining the explanation and description of each knowledge point involved in the question and answer data when generating the final answer to the question to be answered, so that the explanation and description of the knowledge point can be reflected in the final answer, which helps to improve the comprehensibility of the generated answer. On the other hand, the feedback results of the comprehensibility of the target object’s explanation and description of the knowledge point are also referred to during the question and answer process. When it is characterized as incomprehensible, the explanation and description of the knowledge point are re-acquired and iterated in a loop until the feedback result of the target object’s comprehensibility is characterized as understandable. This can achieve that the target object can understand the explanation and description of each knowledge point when generating the final answer, which helps to improve the comprehensibility of the final answer as much as possible. Therefore, the comprehensibility of the generated answer can be improved.

[0042] See also Figure 3 , Figure 3 It is a schematic diagram of the framework of an embodiment of the answer generation device of the present application. The answer generation device 30 includes: an initial answer generation module 31, a question and answer data analysis module 32, an explanation and understanding feedback module 33, an interactive loop iteration module 34 and a final answer generation module 35. The initial answer generation module 31 is used to generate an initial answer to the question to be answered; the question and answer data analysis module 32 is used to obtain several knowledge points involved in the question and answer data and the explanation description of each knowledge point; wherein the question and answer data at least includes the question to be answered and the initial answer; the explanation and understanding feedback module 33 is used to obtain the feedback result of the understandability of the explanation description of the knowledge point by the target object; the interactive loop iteration module 34 is used to respond to the feedback result being characterized as incomprehensible, then select each knowledge point characterized as incomprehensible by the feedback result as the target knowledge point, and re-acquire the explanation description of the target knowledge point, and return to the step of obtaining the feedback result of the understandability of the explanation description of the knowledge point by the target object; the final answer generation module 35 is used to respond to the feedback results of each knowledge point being characterized as understandable, based on the question to be answered and the explanation description of each knowledge point, to generate the final answer to the question to be answered.

[0043] In the above scheme, the answer generation device 30 generates an initial answer to the question to be answered, and obtains a number of knowledge points involved in the question and answer data and an explanation description of each knowledge point, and the question and answer data at least includes the question to be answered and the initial answer, and then obtains the feedback result of the comprehensibility of the target object's explanation description of the knowledge point, so that in response to the feedback result being characterized as incomprehensible, each knowledge point characterized by the feedback result as incomprehensible is selected as the target knowledge point, and the explanation description of the target knowledge point is re-obtained, and the step of obtaining the feedback result of the comprehensibility of the target object's explanation description of the knowledge point is returned, and in response to the feedback result of each knowledge point being characterized as understandable, based on the question to be answered and the explanation description of each knowledge point Description, generate the final answer to the question to be answered, so on the one hand, when generating the final answer to the question to be answered, the explanation description of each knowledge point involved in the question and answer data is combined, so that the explanation description of the knowledge point can be reflected in the final answer, which helps to improve the comprehensibility of the generated answer. On the other hand, in the question and answer process, the feedback result of the comprehensibility of the target object's explanation description of the knowledge point is also referred to, and when it is characterized as incomprehensible, the explanation description of the knowledge point is re-obtained and iterated in a loop until the feedback result of the target object's comprehensibility is characterized as understandable. It can be achieved that when generating the final answer, the target object can understand the explanation description of each knowledge point, which helps to improve the comprehensibility of the final answer as much as possible. Therefore, the comprehensibility of the generated answer can be improved.

[0044] In some disclosed embodiments, the target object is an intelligent agent simulating a real user, and the explanation and understanding feedback module 33 includes a first construction submodule, which is used to construct instructions to be executed based on knowledge points and their explanation descriptions; wherein the instructions to be executed are used to execute the intelligent agent to provide feedback on the comprehensibility of the knowledge points and their explanation descriptions; the explanation and understanding feedback module 33 includes a first acquisition submodule, which is used to input the instructions to be executed into the intelligent agent to obtain the output result of the intelligent agent as a feedback result.

[0045] In some disclosed embodiments, the target object is a real user, and the explanation and understanding feedback module 33 includes a second construction submodule, which is used to construct a prompt message based on the knowledge point and the explanation description of the knowledge point; wherein the prompt message is used to prompt the real user to provide feedback on the comprehensibility of the knowledge point and its explanation description; the explanation and understanding feedback module 33 includes a second acquisition submodule, which is used to output the prompt message and receive the input content of the real user in response to the prompt message as a feedback result.

[0046] In some disclosed embodiments, when the feedback result is characterized as incomprehensible, the feedback result also includes at least one of incomprehensible words and sentences and expected interpretation methods, and the interactive loop iteration module 34 includes a third construction submodule, which is used to construct a prompt instruction based on the interpretation description of the target knowledge point and the feedback result; wherein the prompt instruction is used to instruct the large language model to adjust the interpretation description of the target knowledge point with reference to at least one of the incomprehensible words and sentences and expected interpretation methods in the feedback result; the interactive loop iteration module 34 includes a third acquisition submodule, which is used to input the prompt instruction to the large language model to obtain the output content of the large language model as a new interpretation description of the target knowledge point.

[0047] In some disclosed embodiments, when the feedback result is characterized as incomprehensible, the feedback result also includes at least one of incomprehensible words and sentences and expected interpretation methods, and the interactive loop iteration module 34 includes a knowledge base acquisition submodule for acquiring a preset knowledge base; wherein the preset knowledge base includes a number of preset knowledge points and their respective interpretation descriptions, and the number of preset knowledge points includes a target knowledge point; the interactive loop iteration module 34 includes an interpretation description selection submodule for selecting an interpretation description of a target knowledge point in the preset knowledge base as a target description; the interactive loop iteration module 34 includes an interpretation description extraction submodule for extracting at least part of the target description as a reference description based on at least one of the incomprehensible words and sentences and expected interpretation methods in the feedback result; the interactive loop iteration module 34 includes an interpretation description correction submodule for adjusting the interpretation description of the target knowledge point based on the reference description to obtain a new interpretation description of the target knowledge point.

[0048] In some disclosed embodiments, the question and answer data analysis module 32 includes an analysis submodule for performing analysis based on the question and answer data to obtain a number of candidate knowledge points; the question and answer data analysis module 32 includes a selection submodule for selecting candidate knowledge points related to answering the question to be answered as a number of knowledge points; the question and answer data analysis module 32 includes an extraction submodule for extracting an initial explanation of each knowledge point in the question and answer data; the question and answer data analysis module 32 includes a retrieval submodule for separately retrieving professional explanations of each knowledge point; the question and answer data analysis module 32 includes a correction submodule for correcting the initial explanation of each knowledge point based on the professional explanation to obtain an explanation description of the corresponding knowledge point.

[0049] In some disclosed embodiments, the questions to be answered include scientific questions, and the knowledge points include at least one of scientific concepts and scientific phenomena.

[0050] See also Figure 4 , Figure 4It is a schematic diagram of the framework of an embodiment of an electronic device of the present application. The electronic device 40 includes at least a memory 41 and a processor 42 coupled to each other, the memory 41 stores at least program instructions, and the processor 42 is used to execute the program instructions to implement the steps in any of the above-mentioned answer generation method embodiments. For details, please refer to the aforementioned disclosed embodiments, which will not be repeated here. As a possible example, the electronic device 40 may include but is not limited to an office notebook, an e-book reader, a smart phone, a tablet computer, a learning machine, etc., and the specific type of the electronic device 40 is not limited here.

[0051] Specifically, the processor 42 is used to control itself and the memory 41 to implement the steps in any of the above-mentioned answer generation method embodiments. The processor 42 can also be called a CPU (Central Processing Unit). The processor 42 may be an integrated circuit chip with signal processing capabilities. The processor 42 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 42 can be implemented by an integrated circuit chip.

[0052] In the above scheme, the electronic device 40 generates an initial answer to the question to be answered, obtains several knowledge points involved in the question and answer data and the explanation description of each knowledge point, and the question and answer data at least includes the question to be answered and the initial answer, and then obtains the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object, so that in response to the feedback result being characterized as incomprehensible, each knowledge point characterized by the feedback result as incomprehensible is selected as the target knowledge point, and the explanation description of the target knowledge point is re-obtained, and the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is returned, and in response to the feedback result of each knowledge point being characterized as understandable, based on the question to be answered and the explanation description of each knowledge point The final answer to the question to be answered is generated by combining the explanation description of each knowledge point involved in the question and answer data when generating the final answer to the question to be answered, so on the one hand, the explanation description of the knowledge point can be reflected in the final answer, which helps to improve the comprehensibility of the generated answer. On the other hand, the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is also referred to in the question and answer process, and when it is characterized as incomprehensible, the explanation description of the knowledge point is re-acquired and iterated in a loop until the feedback result of the comprehensibility of the target object is characterized as understandable. It can be achieved that when generating the final answer, the target object can understand the explanation description of each knowledge point, which helps to improve the comprehensibility of the final answer as much as possible. Therefore, the comprehensibility of the generated answer can be improved.

[0053] See also Figure 5 , Figure 5 1 is a schematic diagram of a framework of an embodiment of a computer-readable storage medium 50 of the present application. The computer-readable storage medium 50 stores program instructions 51 that can be executed by a processor, and the program instructions 51 are used to implement the steps in any of the above-mentioned answer generation method embodiments.

[0054] In the above scheme, the computer-readable storage medium 50 generates an initial answer to the question to be answered, obtains several knowledge points involved in the question-and-answer data and an explanation description of each knowledge point, and the question-and-answer data at least includes the question to be answered and the initial answer, and then obtains the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object, so that in response to the feedback result being characterized as incomprehensible, each knowledge point characterized by the feedback result as incomprehensible is selected as the target knowledge point, and the explanation description of the target knowledge point is re-obtained, and the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is returned, and in response to the feedback result of each knowledge point being characterized as understandable, based on the question to be answered and the explanation description of each knowledge point, the target object is fed back to the computer and the computer ... The explanation description is used to generate the final answer to the question to be answered. Therefore, on the one hand, when generating the final answer to the question to be answered, the explanation description of each knowledge point involved in the question and answer data is combined, so that the explanation description of the knowledge point can be reflected in the final answer, which helps to improve the comprehensibility of the generated answer. On the other hand, in the question and answer process, the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is also referred to, and when it is characterized as incomprehensible, the explanation description of the knowledge point is re-obtained and iterated in a loop until the feedback result of the comprehensibility of the target object is characterized as understandable. This can achieve that the target object can understand the explanation description of each knowledge point when generating the final answer, which helps to improve the comprehensibility of the final answer as much as possible. Therefore, the comprehensibility of the generated answer can be improved.

[0055] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0056] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0057] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or 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, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0058] The units described 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 present embodiment.

[0059] 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.

[0060] 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 is essentially 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. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0061] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A method for generating an answer, characterized in that: include: Generate initial answers to the questions to be answered; Acquire several knowledge points involved in the question and answer data and explanations of each of the knowledge points; wherein the question and answer data at least includes the question to be answered and the initial answer; Obtaining feedback results on the understandability of the target object's explanation and description of the knowledge point; In response to the feedback result being characterized as incomprehensible, each of the knowledge points characterized as incomprehensible by the feedback result is selected as a target knowledge point, and the explanation description of the target knowledge point is re-acquired, and the step of obtaining the feedback result of the comprehensibility of the explanation description of the knowledge point by the target object is returned; In response to the feedback results of each of the knowledge points being characterized as being understandable, a final answer to the question to be answered is generated based on the question to be answered and the explanation description of each of the knowledge points.

2. The method according to claim 1, characterized in that The target object is an intelligent agent simulating a real user, and the step of obtaining feedback results on the understandability of the target object's explanation and description of the knowledge point includes: Based on the knowledge point and the explanation description of the knowledge point, construct an instruction to be executed; wherein the instruction to be executed is used to execute the agent to provide feedback on the understandability of the knowledge point and its explanation description; The to-be-executed instruction is input to the agent to obtain an output result of the agent as the feedback result.

3. The method according to claim 1, characterized in that The target object is a real user, and the step of obtaining the feedback result of the understandability of the target object's explanation and description of the knowledge point includes: Based on the knowledge point and the explanation description of the knowledge point, construct a prompt message; wherein the prompt message is used to prompt the real user to provide feedback on the comprehensibility of the knowledge point and its explanation description; The prompt message is output, and input content of the real user in response to the prompt message is received as the feedback result.

4. The method according to claim 1, characterized in that: In the case where the feedback result is characterized as being incomprehensible, the feedback result further includes at least one of an incomprehensible word or sentence and an expected interpretation method, and the reacquiring the interpretation description of the target knowledge point includes: Based on the explanation description of the target knowledge point and the feedback result, construct a prompt instruction; wherein the prompt instruction is used to instruct the large language model to adjust the explanation description of the target knowledge point with reference to at least one of the incomprehensible words and sentences in the feedback result and the expected explanation method; The prompt instruction is input into the large language model to obtain the output content of the large language model as a new explanation description of the target knowledge point.

5. The method according to claim 1, characterized in that: In the case where the feedback result is characterized as being incomprehensible, the feedback result further includes at least one of an incomprehensible word or sentence and an expected interpretation method, and the reacquiring the interpretation description of the target knowledge point includes: Acquire a preset knowledge base; wherein the preset knowledge base includes a number of preset knowledge points and their respective explanation descriptions, and the number of preset knowledge points includes the target knowledge point; Selecting the explanation description of the target knowledge point in the preset knowledge base as the target description; Based on at least one of the incomprehensible words and sentences and the expected interpretation method in the feedback result, extract at least part of the target description as a reference description; The explanation description of the target knowledge point is adjusted based on the reference description to obtain a new explanation description of the target knowledge point.

6. The method according to claim 1, characterized in that The acquisition of question and answer data involves several knowledge points and explanations of each of the knowledge points, including: Analyze the question and answer data to obtain several candidate knowledge points; Selecting each of the candidate knowledge points related to answering the question to be answered as the plurality of knowledge points; Extracting the initial explanation of each of the knowledge points in the question and answer data, and respectively retrieving the professional explanation of each of the knowledge points; For each of the knowledge points, the initial interpretation is corrected based on the professional interpretation to obtain an interpretation description corresponding to the knowledge point.

7. The method according to any one of claims 1 to 6, characterized in that: The questions to be answered include scientific questions, and the knowledge points include at least one of scientific concepts and scientific phenomena.

8. An answer generating device, characterized in that: include: An initial answer generation module, used to generate an initial answer to the question to be answered; A question and answer data analysis module, used to obtain a number of knowledge points involved in the question and answer data and an explanation description of each of the knowledge points; wherein the question and answer data at least includes the question to be answered and the initial answer; An explanation and understanding feedback module is used to obtain feedback results on the understandability of the explanation and description of the knowledge point by the target object; An interactive loop iteration module, for, in response to the feedback result being characterized as incomprehensible, selecting each of the knowledge points characterized as incomprehensible by the feedback result as a target knowledge point, and reacquiring an explanation description of the target knowledge point, and returning to the step of obtaining a feedback result of the comprehensibility of the explanation description of the knowledge point by the target object; The final answer generation module is used to generate a final answer to the question to be answered based on the question to be answered and the explanation description of each knowledge point in response to the feedback results of each knowledge point being characterized as being understandable.

9. An electronic device, characterized in that: The system at least comprises a memory and a processor coupled to each other, wherein the memory at least stores program instructions, and the processor is used to execute the program instructions to implement the answer generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Program instructions that can be executed by a processor are stored, and the program instructions are used to implement the answer generation method according to any one of claims 1 to 7.

Images