Information processing method, electronic equipment and computer storage medium

Abstract

The embodiment of the invention provides an information processing method, electronic equipment and a computer storage medium. The information processing method comprises the steps of obtaining subject question information input by a user; the subject question information is analyzed, and universal examination point information involved in the solving process of the subject question information is determined; determining universality examination point content matched with the universality examination point information from an examination point content library; performing question solving on the subject question information to obtain targeted answer information corresponding to the subject question information; and aiming at the subject question information, displaying the targeted answer information and the universal examination point content. According to the scheme, the targeted answers for the subject question information are provided for the user, meanwhile, the corresponding universal examination point content is provided for the user, and due to the fact that the examination point explanation content corresponding to the universal examination point information is contained in the universal examination point content, the examination point explanation content corresponding to the universal examination point information is provided for the user; a user can be helped to comprehensively and systematically master examination point contents related to subject question information, so that the learning requirements of the user are met.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular, to an information processing method, an electronic device, a computer storage medium, and a computer program product. Background Art

[0002] Currently, many applications on the market can implement a problem search function. For example, users can search by inputting a problem, and the application can output corresponding answers according to the input problem. However, the answers currently output by applications are usually targeted answers according to the problem, which are difficult to help users comprehensively master the learning content related to the problem, resulting in the inability to meet the learning needs of users. Summary of the Invention

[0003] In view of this, the embodiments of the present application provide an information processing solution to at least partially solve the above problems.

[0004] According to the first aspect of the embodiments of the present application, an information processing method is provided, including: obtaining subject question information input by a user for a preset subject; analyzing the subject question information to determine general examination point information involved in the solution process for the subject question information; determining general examination point content matching the general examination point information from a pre-generated examination point content library or a searched examination point content library; solving the subject question information to obtain targeted answer information corresponding to the subject question information; and displaying the targeted answer information and the general examination point content for the subject question information.

[0005] According to the second aspect of the embodiments of the present application, an information processing method is provided, which is applied to a user terminal and includes: in response to an input operation of the user on the user terminal, obtaining subject question information input by the user for a preset subject; sending the subject question information to a server; the server is configured to analyze the subject question information to determine general examination point information involved in the solution process for the subject question information; determining general examination point content matching the general examination point information from a pre-generated examination point content library or a searched examination point content library; solving the subject question information to obtain targeted answer information corresponding to the subject question information; receiving the targeted answer information and the general examination point content for the subject question information returned by the server, and displaying them.

[0006] According to a third aspect of the embodiments of the present application, an electronic device is provided, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus; the memory is used for storing a computer program; the processor is used for executing the information processing method described in the foregoing first aspect or second aspect by running the computer program stored on the memory.

[0007] According to a fourth aspect of the embodiments of the present application, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the information processing method described in the first aspect or the second aspect is implemented.

[0008] According to a fifth aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the information processing method described in the first aspect or the second aspect is implemented.

[0009] According to the information processing solution provided by the embodiments of the present application, by obtaining the subject question information input by the user for a preset subject, then parsing the subject question information, determining the general examination point information involved in the solution process of the subject question information, and determining the general examination point content matching the general examination point information from the examination point content library; and further, solving the subject question information to obtain the targeted answer information corresponding to the subject question information, so that the targeted answer information and the above general examination point content can be displayed to the user.

[0010] The solution provided by the embodiments of the present application, while providing the user with the targeted answer for the subject question information, will also provide the user with valuable general examination point content involved in the solution process of the subject question information. The general examination point content includes the explanation content for the general examination point, which can help the user comprehensively and systematically master the common examination point content involved in the subject question information to meet the learning needs of the user.

[0011] The solution provided by the embodiments of the present application can, in the scenario where the user seeks a specific answer for a specific question, while providing the user with the targeted answer, also present the explanation content of the general examination point corresponding to the general examination point (common examination point) involved in the solution process of the specific subject question to the user intuitively. Avoiding the additional question-and-answer interaction operations that the user performs to seek the above general examination points. For the user, through the embodiments of the present application, it is more likely to achieve the effect of understanding one question and mastering a class of questions.

[0012] In summary, the embodiments of the present application do not require the user to perform additional operations, reduce the user operation cost, and can meet the learning needs of the user in a more efficient manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments described in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0014] Figure 1 It is a schematic diagram of an information processing system according to an embodiment of the present application.

[0015] Figure 2 It is a flowchart of the steps of an information processing method according to an embodiment of the present application.

[0016] Figures 3A to 3C It is a schematic diagram of the process of an information processing method according to an embodiment of the present application.

[0017] Figure 4 It is a flowchart of the steps of an information processing method according to another embodiment of the present application.

[0018] Figure 5 It is a schematic diagram of a scenario of an example of the information processing solution according to an embodiment of the present application.

[0019] Figure 6 It is a block diagram of the structure of an information processing device according to an embodiment of the present application.

[0020] Figure 7 It is a block diagram of the structure of an information processing device according to another embodiment of the present application.

[0021] Figure 8 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application shall fall within the scope of protection of the embodiments of the present application.

[0023] The following further illustrates the specific implementation of the embodiments of the present application with reference to the accompanying drawings of the embodiments of the present application.

[0024] Figure 1 An exemplary system applicable to the solution of the embodiments of the present application is shown. As Figure 1As shown, the system 100 may include a server 102, a communication network 104, and / or one or more user devices 106. Figure 1 For example, there are multiple user devices 106, and an application for displaying subject question information, targeted answer information, and general examination point content is set on the user device 106.

[0025] The server 102 may be any suitable device for storing information, data, programs, and / or any other appropriate type of content, including but not limited to distributed storage system devices, server clusters, computing server clusters, etc. In some embodiments, the server 102 may perform any suitable functions. For example, when implementing the solution of the embodiments of the present application by the server 102, in some embodiments, the server 102 may be used to execute an information processing method. As an alternative example, in some embodiments, the server 102 may first obtain the subject question information for a preset subject input by the user, and then parse the subject question information to obtain the general examination point information involved in the solution process of the subject question information; and determine the general examination point content that matches the general examination point information from a pre-generated examination point content library or a searched examination point content library; and solve the subject question information to obtain the targeted answer information corresponding to the subject question information, that is, the general examination point content and the targeted answer information for the subject question information can be obtained. In some embodiments, the server 102 may receive the subject question information sent by the user device 106, and after generating the targeted answer information and the general examination point content in the foregoing manner, send the targeted answer information and the general examination point content to the user device 106 so that the user device 106 can display the targeted answer information and the general examination point content.

[0026] In some embodiments, the communication network 104 can be any suitable combination of one or more wired and / or wireless networks. For example, the communication network 104 can include any one or more of the following: the Internet, an intranet, a Wide Area Network (WAN), a Local Area Network (LAN), a wireless network, a Digital Subscriber Line (DSL) network, a Frame Relay network, an Asynchronous Transfer Mode (ATM) network, a Virtual Private Network (VPN), and / or any other suitable communication network. The user device 106 can be connected to the communication network 104 via one or more communication links (e.g., communication link 112), and the communication network 104 can be linked to the server 102 via one or more communication links (e.g., communication link 114). The communication link can be any communication link suitable for transmitting data between the user device 106 and the server 102, such as a network link, a dial-up link, a wireless link, a hardwired link, any other suitable communication link, or any suitable combination of such links.

[0027] Optionally, the user device 106 can be provided with an application for displaying subject question information, targeted answer information, and general examination point content. The user device 106 can include any one or more user devices suitable for displaying information, interacting with users, etc. In some embodiments, the user device 106 can include any suitable type of device. For example, in some embodiments, the user device 106 can include a mobile device, a tablet computer, a laptop computer, a desktop computer, and / or any other suitable type of user device.

[0028] Based on the above system, an embodiment of the present application provides an information processing solution, which will be described below through multiple embodiments.

[0029] Figure 2 It is a step flowchart of an information processing method according to an embodiment of the present application. According to the first aspect in the embodiments of the present application, an information processing method is provided. Referring to Figure 2 as shown, the method includes steps S202, S204, and S206. Specifically: S202: Obtain the subject question information for a preset subject input by the user.

[0030] Exemplarily, a discipline refers to a specific academic field or knowledge system. In the embodiments of the present application, the division method and specific content of the preset discipline are not limited. For example, common discipline classifications include natural science, engineering technology, medicine, social science, humanities, and mathematics, etc. The discipline question information for the preset discipline can be the question information within the scope of the preset discipline. When a user wants to obtain the answer corresponding to the discipline question within a certain discipline category, the user can perform an operation of inputting discipline question information on the user terminal, such as an operation of photographing the discipline question information for the preset discipline or an operation of inputting the question text, etc., to obtain an image or text containing the discipline question information. Then, the user terminal sends the image or text containing the discipline question information to the server. Subsequently, for the image containing the discipline question information, the discipline question information input by the user can be obtained through image information recognition processing; for the text input by the user, the text can be used as the discipline question information input by the user for the preset discipline. For example, for the mathematics discipline, the discipline question information input by the user can be: "Solve this triangle problem: For a triangle with side lengths 3, 4, and 5, find the angles."

[0031] S204. Analyze the discipline question information, and determine the general examination point information involved in the solution process for the discipline question information; determine the general examination point content that matches the general examination point information from the pre-generated examination point content library or the searched examination point content library.

[0032] Exemplarily, for a specific discipline, the discipline question information proposed by the user usually involves some knowledge points that are often asked by users within the discipline. In the embodiments of the present application, the above knowledge point information can be referred to as general examination points. Further, the general examination point information can be the name, identifier, and other identifiable information of the general examination points parsed from the discipline question information. For example, in the mathematics discipline, the general examination point information involved in the solution process of the discipline question information can include: trigonometric functions, Pythagorean theorem, trigonometric identities, quadratic equations, etc. Exemplarily, for the discipline question information in the mathematics discipline: "Solve this triangle problem: For a triangle with side lengths 3, 4, and 5, find the angles.", the general examination point information involved in the solution process of this discipline question information includes the Pythagorean theorem and trigonometric functions.

[0033] The general examination point content may include the general examination point itself. Further, the general examination point content may also include the explanatory content for the general examination point, that is: the general examination point content may include the general examination point explanatory content corresponding to the general examination point information. Correspondingly, the general examination point content may also include the general examination point explanatory content corresponding to the general examination point information. Exemplarily, the general examination point content in this embodiment may be rich media content, that is, the general examination point content may be embodied as multimedia content containing multiple media elements (such as at least two of pictures, audio, video, etc.).

[0034] In this embodiment, a test point content library containing multiple test point contents can be pre-generated or obtained through a search method. After obtaining the subject question information, by analyzing the subject question information, the general test point information involved in the subject question information can be obtained. Then, the general test point information can be matched with the test point information corresponding to the test point content contained in the test point content library, so that the successfully matched test point content can be used as the general test point content involved in the solution process of the subject question information.

[0035] In some alternative embodiments, analyzing the subject question information to determine the general test point information involved in the solution process for the subject question information includes: identifying keywords in the subject question information to obtain the first test point information; performing semantic analysis on the subject question information to obtain the second test point information; and fusing the first test point information and the second test point information to determine the general test point information involved in the subject question information. Correspondingly, determining the general test point content that matches the general test point information from a pre-generated test point content library or a searched test point content library may include: determining the general test point content that matches the general test point information from a pre-generated test point content library or a searched test point content library according to the pre-determined mapping relationship between the test point information and the test point content.

[0036] Exemplarily, when parsing the question information, keywords in the subject question information can be identified. For example, by identifying keywords in the subject question information according to a preset test point keyword library, the first test point information, such as the matched test point keywords, can be obtained. In addition, semantic analysis can also be performed on the subject question information, and further semantic recognition can be performed according to the context in the subject question information to obtain the second test point information, such as the test point information implied in the subject question information other than the test point keywords. Then, fusing the first test point information and the second test point information, for example, the first test point information and the second test point information can be simply combined, or after removing the duplicate information in the first test point information and the second test point information, the processed test point information can be combined, etc., so as to obtain the general test point information involved in the subject question information.

[0037] In this embodiment, by identifying keywords in the subject question information, the explicit first test point information contained in the subject question information can be obtained. Then, by performing semantic analysis on the subject question information, the implicit second test point information contained in the subject question information can be obtained. After that, by combining the first test point information and the second test point information, the more comprehensive and universal test point information involved in the subject question information can be analyzed and obtained, so as to avoid missing the test points in the subject question information.

[0038] In some other alternative embodiments, determining the universal test point content that matches the universal test point information from the pre-generated test point content library or the searched test point content library may also include: determining the target historical question information that matches the universal test point information; according to the pre-determined mapping relationship between the historical question information and the test point content, determining the test point content corresponding to the target historical question information from the pre-generated test point content library or the searched test point content library as the universal test point content that matches the universal test point information.

[0039] Exemplarily, the test point content in the test point content library may be generated according to some of the question information in the preset question bank, and the preset question bank may include the historical question information input by the user. After constructing the test point content library, the mapping relationship between each test point content in the test point content library and the corresponding historical question information can be established. When subsequently matching the universal test point content corresponding to the universal test point information among multiple test point contents, the target historical question information corresponding to the universal test point information can be matched from the historical question information according to the universal test point, and then according to the pre-set mapping relationship between the historical question information and the test point content, the test point content corresponding to the target historical question information is determined as the above-mentioned universal test point content. Optionally, after analyzing and obtaining the universal test point information involved in the solution process of the subject question information, based on the universal test point information, it can be matched with the test point content contained in the test point content library, and the successfully matched test point content is used as the above-mentioned universal test point content.

[0040] In this embodiment, when generating multiple test point contents according to the historical question information in advance, the mapping relationship between the historical question information and the test point content is constructed, so that when subsequently matching the universal test point content for the subject question information input by the user, the corresponding target historical question information can be matched, and then according to the mapping relationship between the historical question information and the test point content, it can be quickly determined that the test point content corresponding to the target historical question information is the universal test point content.

[0041] Here, an exemplary description is given for the process of pre-generating a test point content library containing multiple test point contents in this embodiment.

[0042] In some alternative embodiments, before obtaining the subject question information input by the user, the method of this embodiment further includes: determining the test point title corresponding to the historical question information according to the historical question information input by the user for a preset subject; generating the test point content corresponding to the historical question information through the target large language model according to the historical question information and the corresponding test point title.

[0043] Exemplarily, multiple pieces of pre-generated test point content can be generated according to the historical question information input by the user. In the process of generating the test point content, based on the historical question information, the corresponding historical answer information and the corresponding historical follow-up question information of the historical question information can be obtained, and then according to the historical answer information and the corresponding historical follow-up question information corresponding to the historical question information, the test point title corresponding to the historical question information is generated, that is, the title of the test point content to be generated. Then, the historical question information and the corresponding test point title are input into the pre-trained target large language model, and the test point content corresponding to the historical question information is generated through the target large language model.

[0044] The target large language model in this embodiment is a large language model that can generate knowledge point content based on question information and the corresponding knowledge point title. A large language model (LLM for short) refers to a deep learning model trained with a large amount of text data, enabling the model to generate natural language text or understand the meaning of language text. These models can provide in-depth knowledge and language production on various topics through training on a large dataset. The large language model can learn the patterns and structures of natural language through large-scale unsupervised training, and to a certain extent, simulate the human language cognition and generation process.

[0045] In some alternative embodiments, generating the test point content corresponding to the historical question information through the target large language model according to the historical question information and the corresponding test point title includes: retrieving from the preset knowledge base through the retrieval-enhanced generation method according to the historical question information and the corresponding test point title to obtain the first retrieval result associated with the historical question information and the test point title; parsing the historical question information, the test point title, and the first retrieval result to generate a test point content prompt, and inputting the test point content prompt into the pre-trained target large language model to generate the test point content corresponding to the historical question information through the target large language model.

[0046] In this embodiment, according to the historical question information input by the user, the examination point title corresponding to the historical question information is determined; then, based on the historical question information and the corresponding examination point title, the pre-trained target large language model is used to generate the examination point content corresponding to the historical question information, improving the generation efficiency of the examination point content. Moreover, by utilizing the content generation ability of the large language model, the content quality of the examination point content can be ensured. Additionally, the examination point content in this embodiment is generated based on the historical question information input by the user, that is, the examination point content can be generated for the common concerns of the users, so that the generated examination point content can more efficiently meet the aggregated needs of the users. That is to say: in the above embodiments of the present application, when generating the examination point content, on the one hand, the core examination point title is extracted and condensed from the question information of the user's historical questions, and then the examination point content is generated based on the extracted examination point title. The above extraction and condensation method of the core examination point title can make the finally generated examination point content better cover the questions raised by the users, thereby improving the universality and aggregation of the generated examination point content; on the other hand, after the examination point title is extracted, in the embodiments of the present application, the content generation ability of the large language model is adopted, and the examination point content is generated based on the historical question information and the examination point title to guide the model, so that the finally generated examination point content can better match the historical question information and the examination point title, improving the pertinence of the examination point content.

[0047] In some alternative embodiments, determining the examination point title corresponding to the historical question information according to the historical question information of the preset subject input by the user includes: obtaining multiple historical follow-up information for the historical question information of the preset subject input by the user; screening the multiple historical follow-up information through a preset screening rule to obtain the screened historical follow-up information; the preset screening rule is used to perform a relevance screening and a title style screening on the historical follow-up information with the historical question information; screening the screened historical follow-up information through a pre-trained target classification model to obtain the examination point title corresponding to the historical question information.

[0048] Exemplarily, referring to Figure 3A, in the process of generating the examination point title, multiple corresponding historical follow-up question information can be obtained according to the information of a single historical question. Here, multiple historical follow-up question information with click-through rates higher than the preset click-through threshold can be obtained according to the click-through rates of the respective historical follow-up question information corresponding to the historical question information, that is, the common problems of most users can be obtained, and subsequent examination point content generation can be carried out for the common problems of users, so that the generated examination point content can more efficiently meet the aggregated needs of users. Then, multiple historical follow-up question information can be screened through a preset screening rule to obtain the screened multiple historical follow-up question information. Among them, the preset screening rule is used to screen the historical follow-up question information for the relevance screening with the historical question information and the title style screening. For example, for the relevance screening with the historical question information, firstly, the historical follow-up question information corresponding to other historical question information with a similarity to the historical question information reaching the preset threshold can be obtained; secondly, since the multiple historical follow-up question information can include the follow-up question information of multiple rounds of questions for the historical question information, the follow-up question information of the first round of questions can be screened out as the screened historical follow-up question information through the preset screening rule. For the title style screening, the examination point title style can be set in the preset screening rule, including word count requirements, sentence pattern requirements, etc., and this embodiment does not limit this. By screening the historical follow-up question information that meets the examination point title style through the preset screening rule, the screened historical follow-up question information can be obtained.

[0049] After obtaining multiple screened historical follow-up question information, the screened historical follow-up question information can be input into a pre-trained target classification model, and the screened historical follow-up question information can be further classified through the target classification model, so as to obtain the examination point title corresponding to the historical question information according to the classification result. Here, the target classification model is a classification model trained through the positive sample data and negative sample data of the pre-annotated examination point titles.

[0050] A classification model is a model in machine learning used to divide data into different categories or labels, such as a decision tree model, a logistic regression model, a naive Bayes classifier, etc. This embodiment does not limit the classification model used; in the training of the classification model, positive sample data and negative sample data are usually used for training, where the positive sample data refers to the data samples corresponding to the target category. For example, the positive sample data in this embodiment can be the pre-annotated qualified examination point titles. The negative sample refers to the data samples that are opposite to the positive sample and do not belong to the target category. For example, the negative sample data in this embodiment can be the pre-annotated unqualified examination point titles.

[0051] In this embodiment, when generating the examination point title, the core examination point title is further extracted and refined from the user's historical question-asking behavior (including the question information of the first question asked and the follow-up information regarding the question information of the first question asked). The above-mentioned method of extracting and refining the core examination point title can enable the finally generated examination point content to better cover the questions raised by the user, thereby improving the universality and aggregation of the generated examination point content.

[0052] In addition, in this embodiment, after obtaining the historical follow-up information, multiple historical follow-up information is first screened from the aspects of relevance and title style through a preset screening rule to obtain historical follow-up information with a higher relevance and better style to the historical question information; then, the screened historical follow-up information is further screened through a pre-trained target classification model, so as to obtain the examination point title corresponding to the historical question information. In this embodiment, the historical follow-up information is screened multiple times based on the relevance, title style, and classification model, and thus the examination point title corresponding to the historical question information is obtained based on the finally screened historical follow-up information. Therefore, the relevance between the finally generated examination point title and the historical question information can be made higher, and the finally generated examination point title can be made more accurate and with a better style.

[0053] In some alternative embodiments, determining the examination point title corresponding to the historical question information according to the historical question information input by the user includes: determining the historical question information input by the user and obtaining multiple examination point information included in the historical question information; inputting the multiple examination point information into a pre-trained first large language model to output the examination point title corresponding to the historical question information; the first large language model is a large language model trained with the examination point information sample as the training data and the examination point title sample as the label.

[0054] Exemplarily, referring to Figure 3A , in addition to the aforementioned method of generating the examination point title, the examination point title can also be generated in the following way: First, the historical question information can be parsed to obtain multiple examination point information included in the historical question information. Then, the multiple examination point information is input into a pre-trained first large language model. The first large language model is a large language model pre-trained with the examination point information sample as the training data and the examination point title sample as the label. Then, the first large language model can output the examination point title corresponding to the historical question information.

[0055] Among them, a training dataset can be pre-constructed. Question information samples can be obtained from a preset question bank (including historical question information). By parsing the question information samples, examination point information samples can be obtained. The examination point information samples can include explicit examination point samples and implicit examination point samples, and the training data is composed of the examination point information samples. Correspondingly, corresponding label data: examination point title samples are constructed for the examination point information samples. Then, a training dataset is composed of the examination point information samples and the corresponding examination point title samples, and the large language model is fine-tuned using the training dataset to obtain the first large language model.

[0056] In this embodiment, the first large language model trained with the examination point information samples as the training data and the examination point title samples as the labels processes multiple examination point information corresponding to the historical question information to obtain the examination point titles corresponding to the historical question information. This method can better generate corresponding examination point titles for some historical question information with fewer or poorer follow-up question information, and the generation efficiency and accuracy are relatively high.

[0057] In some alternative embodiments, according to the historical question information and the corresponding examination point titles, the examination point content corresponding to the historical question information is generated through a target large language model, including: inputting the historical question information and the corresponding examination point titles into a pre-trained second large language model to output multiple query questions for the historical question information; for the multiple query questions, retrieving query results for the multiple query questions from a pre-constructed subject knowledge base; and inputting the query results and the examination point titles into a pre-trained third large language model to output the examination point content corresponding to the historical question information.

[0058] In some alternative embodiments, inputting the historical question information and the corresponding examination point titles into a pre-trained second large language model to output multiple query questions for the historical question information includes: performing information retrieval based on the historical question information and the corresponding examination point titles to obtain a second retrieval result associated with the historical question information and the examination point titles; and generating a query question prompt word according to the historical question information, the examination point titles, and the second retrieval result; inputting the query question prompt word into the pre-trained second large language model to guide the second large language model to generate multiple query questions for the historical question information through the query question prompt word.

[0059] In this embodiment, when generating corresponding test point content from the aspects for material collection when the query problem representation targets the test point information involved in the historical question information. The query problem is associated with the test point information included in the historical question information. For example, if the historical question information is a question corresponding to the legal discipline, the query problems may include: Q1 What laws are included, Q2 What are the cases of theft, Q3 What are the differences between charges, and so on. The query result is the test point content queried for the query problem. For example, the query result R1 for Q1 may be the specific content of the law, and the query result R2 for Q2 may be the case content of multiple theft cases, and so on.

[0060] The target large language model may include a second large language model and a third large language model. Among them, the second large language model is a large language model trained with the question information sample and the test point title sample as training data and the query problem sample as a label. The third large language model is a large language model trained with the test point paradigm sample as training data. Among them, the test point paradigm sample may refer to the test point content sample of the standardized structure corresponding to each discipline set in advance according to different disciplines. For example, for the legal discipline, it can be set that each test point content in the corresponding test point paradigm sample consists of four items: the content of the law, the analysis of the law, cases, and case analysis, and so on. This embodiment does not limit this.

[0061] The training data set for the second large language model can be pre-constructed. First, the question information samples corresponding to different disciplines can be obtained from a preset question bank (including historical question information). Correspondingly, the test point title samples corresponding to the question information samples can be obtained through the generation method of the test point title in the foregoing embodiment. For each discipline, the training data corresponding to the discipline is composed of the question information sample and the corresponding test point information sample. Correspondingly, the label data corresponding to the question information sample and the corresponding test point information sample for each discipline is constructed: the query problem sample. Then, the training data sets for each discipline are composed of the question information samples, the corresponding test point information samples, and the corresponding query problem samples for each discipline. Using this training data set to train the large language model, the second large language model can be obtained.

[0062] In some alternative embodiments, the process of training the large language model with the question information sample and the test point title sample as training data and the query problem sample as a label to obtain the second large language model may include: obtaining the query problem type information corresponding to multiple disciplines; based on the query problem type information corresponding to multiple disciplines, determining the corresponding query problem samples for the question information samples and the test point title samples corresponding to each discipline; using the question information samples and the test point title samples corresponding to each discipline as training data and the corresponding query problem samples as labels to train the large language model to obtain the second large language model.

[0063] Exemplarily, information on query question types corresponding to multiple different disciplines can be obtained. The query question type information can be characteristic information representing the disciplines corresponding to the query questions. The query question type information can include the angles of asking questions in the query questions and the proportion of the number of questions corresponding to each angle of asking questions. For example, for the legal discipline, Figure 3B the angles of asking questions and the corresponding proportions exemplified in Figure 3B . After that, based on the query question type information corresponding to each discipline, query question samples corresponding to each discipline can be generated for the sample of question information and the sample of examination point titles corresponding to each discipline. Finally, the training data is composed of the sample of question information and the sample of examination point titles corresponding to each discipline, and the large language model is fine-tuned with the corresponding query question samples as labels, and then the second large language model can be obtained.

[0064] In this embodiment, by classifying the query question type information corresponding to different disciplines and determining the query question samples corresponding to each discipline based on the query question type information corresponding to each discipline for the sample of question information and the sample of examination point titles corresponding to each discipline, the second large language model can be trained, so that the second large language model can output corresponding query questions for different disciplines more accurately and pertinently.

[0065] Similarly, a training data set for the third large language model can be pre-constructed, and an initial note paradigm sample can be constructed; after that, based on the style adjustment prompt information corresponding to each discipline, the initial examination point paradigm sample is adjusted by the large language model (such as ChatGPT) to obtain the examination point paradigm samples corresponding to each discipline. The training data set is composed of the examination point paradigm samples corresponding to each discipline, and the large language model is fine-tuned with this training data set to obtain the third large language model.

[0066] In some alternative embodiments, the process of constructing the examination point paradigm sample includes: obtaining the initial examination point paradigm sample; adjusting the initial examination point paradigm sample by the large language model based on the style adjustment prompt information corresponding to multiple disciplines to obtain the examination point paradigm sample.

[0067] Exemplarily, when constructing the examination point paradigm sample, an initial examination point paradigm sample can be constructed. After that, style adjustment prompt information corresponding to different disciplines can also be constructed. The style adjustment prompt information is used to guide the large language model to adjust the style of the initial examination point paradigm sample. Finally, the initial examination point paradigm sample and the style adjustment prompt information corresponding to each discipline are input into the large language model (such as ChatGPT), and the large language model adjusts the style of the initial examination point paradigm sample based on the style adjustment prompt information and outputs the examination point paradigm samples corresponding to each discipline.

[0068] In this embodiment, by constructing style adjustment prompt information corresponding to multiple disciplines and adjusting the initial examination point paradigm samples through a large language model, examination point paradigm samples corresponding to each discipline are obtained to train the third large language model, so that the third large language model can generate examination point content corresponding to different disciplines in a more accurate and targeted manner.

[0069] Refer to Figure 3C , after generating the examination point title, the historical question information and the corresponding examination point title can be input into the pre-trained second large language model. Here, the historical answer information corresponding to the historical question information can also be input into the second large language model. The historical answer information includes the answer content and the corresponding answer analysis content, which is not limited in this embodiment. Multiple query questions for the historical question information can be output through the second large language model. The query questions are associated with the examination point information included in the historical question information. For example, if the historical question information is a certain question corresponding to the legal discipline, the multiple query questions can include: Which laws are included in Q1, What are the cases of Q2 theft, What are the differences between Q3 charges, and so on. After that, for the generated multiple query questions, query results for each query question can be retrieved from the pre-constructed disciplinary knowledge base, such as R1, R2, R3, etc. Finally, the query results and the examination point title are input into the pre-trained third large language model, and the examination point content corresponding to the historical question information can be generated through the third large language model.

[0070] In this embodiment, by inputting the historical question information and the corresponding examination point title into the pre-trained second large language model to output multiple query questions for the historical question information; for the multiple query questions, retrieving query results for the multiple query questions from the pre-constructed disciplinary knowledge base; and inputting the query results and the examination point title into the pre-trained third large language model to output the examination point content corresponding to the historical question information, the examination point content corresponding to the historical question information of different disciplines can be generated efficiently and in batches. And since the examination point content is generated from the query results retrieved from the pre-constructed disciplinary knowledge base, the accuracy of the examination point content is improved.

[0071] In some alternative embodiments, inputting the historical question information and the corresponding examination point title into the pre-trained second large language model to output multiple query questions for the historical question information includes: performing information retrieval based on the historical question information and the corresponding examination point title to obtain a second retrieval result associated with the historical question information and the examination point title; and generating a query question prompt word according to the historical question information, the examination point title, and the second retrieval result; and inputting the query question prompt word into the pre-trained second large language model to guide the second large language model to generate multiple query questions for the historical question information through the query question prompt word.

[0072] Analyze the historical question information and the corresponding test point titles to generate query prompt information; input the query prompt information, the historical question information, and the corresponding test point titles into a pre-trained second large language model to output multiple query questions for the historical question information; the query prompt information is used to guide the second large language model to generate multiple query questions for the historical question information.

[0073] Exemplarily, after obtaining the historical question information and the corresponding test point titles, it is possible to determine the target subject to which the historical question information and the corresponding test point titles belong. For different target subjects, information retrieval can be performed in the target subject library to obtain a second retrieval result that is relevant to both the historical question information and the test point titles. Then, according to the prompt word generation rule corresponding to the target subject, based on the historical question information, the test point titles, and the second retrieval result, a corresponding query question prompt word, that is, the query prompt word prompt, is generated. After that, input the query question prompt word into the pre-trained second large language model, and based on the query question prompt word, guide the second large language model to output multiple query questions for the historical question information.

[0074] In this embodiment, by analyzing the historical question information and the corresponding test point titles, a query question prompt word is generated; using the query question prompt word to guide the second large language model to generate multiple query questions for the historical question information can improve the accuracy of the generated query questions.

[0075] S206. Solve the subject question information to obtain the targeted answer information corresponding to the subject question information.

[0076] Exemplarily, after obtaining the subject question information input by the user, targeted answer information for the subject question information can be generated. In the embodiments of the present application, the specific implementation manner for generating the targeted answer information is not limited. Exemplarily, it can be implemented by means of a generative language model. A generative language model is a neural network model based on deep learning, and its basic architecture can include a recurrent neural network (RNN), a long short-term memory network (LSTM), and a transformer, etc. Through strategies such as pre-training and fine-tuning, it can learn the general laws and structures of language on large-scale unlabeled text data, and then generate text that conforms to grammar and semantic rules according to the learned language patterns and knowledge. In the embodiments of the present application, the type of the generative language model used and the model structure, etc. can be not limited. Any suitable generative language model that can generate targeted answer information for the subject question information is applicable to the solutions in the embodiments of the present application.

[0077] The targeted answer information in this embodiment may include the answer content for the subject question information, and may also include the corresponding answer analysis content. This embodiment does not limit this. Taking the subject question information listed in S204 above, "Solve this triangle problem: A triangle with side lengths 3, 4, and 5, find the angles." as an example, the targeted answer information may include the specific answer to this subject question information: "A triangle with side lengths 3, 4, and 5 is a right triangle, and the angles are 36.87 degrees, 53.13 degrees, and 90 degrees respectively." Further, the targeted answer information may also include the solution process of the above specific answer.

[0078] S208. For the subject question information, display the targeted answer information and the general examination points content.

[0079] The information processing method provided in this embodiment, while providing the user with the targeted answer to the subject question information, will also provide the user with valuable general examination points content involved in this subject question information. The general examination points content includes the examination point explanation content for the general examination points involved in the subject question information, which can help the user comprehensively and systematically master the common examination points involved in the subject question information to meet the user's learning needs.

[0080] In addition, the solution provided in the embodiment of the present application can, in the scenario where the user seeks a specific answer for a specific question, while providing the user with the targeted answer, also present the examination point explanation content corresponding to the general examination points (common examination points) involved in the solution process of this specific subject question to the user intuitively. Avoid the additional question-and-answer interaction operations that the user performs to seek the above general examination points. For the user, through the embodiment of the present application, it is more likely to achieve the effect of understanding one question and mastering a class of questions.

[0081] In summary, the embodiment of the present application does not require the user to perform additional operations, reduces the user operation cost, and can meet the user's learning needs in a more efficient manner.

[0082] Optionally, in some embodiments, the process of displaying the targeted answer information and the general examination points content for the subject question information may include: Create an answer display page, and display the targeted answer information corresponding to the subject question information on the answer display page; in response to the interaction operation on the targeted answer information displayed on the answer display page, pop up a pop-up page containing the general examination points content.

[0083] Exemplarily, in the above embodiments of the present application, the targeted answer information corresponding to the subject question information is intuitively displayed on the answer display page. In this way, the user can quickly obtain the core information - the targeted answer to the subject question information, without having to search for the answer on the page. Further, when the user reads the targeted answer, relevant examination points can be obtained immediately by performing a preset interaction operation on the targeted answer (exemplarily, such as clicking on the keywords in the targeted answer, clicking on the preset icon, etc.), thereby effectively enhancing the interactivity and the coherence of learning. In addition, the targeted answer is displayed in the main content area of the answer display page, while the explanation content of the examination point is displayed in a further popped-up window. This layout makes the primary and secondary content clear, and the user can also clearly distinguish the core information and the extended information. In summary, the display method of the targeted answer information and the general examination point content in the above embodiments can further improve the user experience.

[0084] Optionally, in some embodiments, after displaying the targeted answer information and the general examination point content for the subject question information, it is also possible to: Generate marking information in response to a marking operation on the displayed targeted answer information and general examination point content; generate a Q&A note based on the subject question information, the targeted answer information, the general examination point content, and the marking information.

[0085] Specifically, in the above embodiments, by generating the Q&A note, the user can more conveniently review and summarize the questions asked, improving the overall usage experience. And more importantly, by generating the Q&A note, the question, answer, examination point, and marking data can be integrated together. The user can quickly view the relevant examination points and their own marking data while reading the answer, reducing the time for searching and organizing, and improving the learning efficiency.

[0086] Optionally, in some embodiments, after generating the Q&A note, it is also possible to: Determine the target Q&A notes related to the same general examination point content from a note library containing multiple Q&A notes; merge the target Q&A notes to generate a topic category note for the same general examination point content.

[0087] Specifically, in the above embodiments, after generating the corresponding Q&A note for the subject question information input by the user, the Q&A note is further sorted out, so that different Q&A notes related to the same general examination point content are incorporated into the same general examination point category to obtain a topic category note for the same general examination point. In this way, the user can conduct a detailed and systematic check for omissions on the general examination point through the topic category note corresponding to a certain general examination point, thereby helping the user quickly and efficiently master the general examination point.

[0088] Figure 4 It is a flowchart of steps of another information processing method according to an embodiment of the present application. According to the second aspect in the embodiments of the present application, an information processing method is provided, which is applied to a user terminal. Referring to Figure 4 As shown, the method includes steps S402, S404, and S406. Specifically: S402. In response to an input operation of a user on the user terminal, obtain subject question information input by the user for a preset subject.

[0089] Exemplarily, the user terminal may provide an input interface. The user can perform an input operation of subject question information through the input interface. After the user terminal detects the input operation of the user, the subject question information input by the user can be obtained.

[0090] In some optional embodiments, in response to an input operation of a user on the user terminal, obtaining subject question information input by the user for a preset subject includes: in response to a shooting operation of the user on the user terminal, obtaining an image containing subject question information input by the user; performing information recognition on the image containing subject question information to obtain the subject question information input by the user.

[0091] Exemplarily, a shooting button may be set in the input interface of the user terminal. The user can shoot a question through the shooting button. After the user terminal detects the shooting operation of the user, an image containing subject question information input by the user can be obtained. Then, the user terminal performs information recognition on the image containing subject question information. For example, multimodal information recognition can be performed to obtain the subject question information contained in the image.

[0092] In this embodiment, by providing an input method of taking a photo to search for questions to the user, the input efficiency of the user can be improved, which is convenient for the user to quickly input questions and enhances the user experience.

[0093] In some optional embodiments, in response to an input operation of a user on the user terminal, obtaining subject question information input by the user for a preset subject includes: in response to a text input operation of the user on the user terminal, obtaining the subject question information input by the user for a preset subject.

[0094] Exemplarily, an input box may also be set in the input interface of the user terminal. The user can input question information through the input box. Then, after the user terminal detects the text input operation in the input box, the subject question information input by the user in the input box is obtained. In this embodiment, by providing an input method of text input to the user, it is convenient for the user to use in various question-asking scenarios and enhances the user experience.

[0095] S404. Send the subject question information to the server. The server is used to parse the subject question information, determine the general examination point information involved in the solution process for the subject question information, determine the general examination point content that matches the general examination point information from a pre-generated examination point content library or a searched examination point content library, and solve the subject question to obtain the targeted answer information corresponding to the subject question information.

[0096] The server in this embodiment is used to implement the corresponding information processing methods in multiple method embodiments of the foregoing first aspect, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0097] S406. Receive the targeted answer information and general examination point content for the subject question information returned by the server, and display them.

[0098] Exemplarily, after the user terminal receives the targeted answer information and general examination point content for the subject question information returned by the server, it displays the targeted answer information and general examination point content. This embodiment does not limit the display method.

[0099] For the information processing method provided in the embodiment of the present application, after the user terminal detects the input operation of the user on the user terminal, it obtains the subject question information input by the user and sends the subject question information to the server. The server determines the general examination point content that matches the general examination point information from the examination point content library according to the general examination point information included in the subject question information, and solves the subject question to obtain the targeted answer information, and returns it to the user terminal. The user terminal receives the targeted answer information and general examination point content for the subject question information returned by the server, can display the answer to the subject question to the user, and at the same time, will also provide the user with the corresponding general examination point content. The general examination point content includes the examination point explanation content corresponding to the general examination point information, so as to help the user comprehensively and systematically master the examination point content related to the subject question information to meet the user's learning needs. And there is no need for the user to perform additional operations, reducing the user operation cost and meeting the user's learning needs in a more efficient way.

[0100] In some optional embodiments, when receiving the targeted answer information and general examination point content for the subject question information returned by the server and displaying them, the method in this embodiment further includes: receiving at least one historical follow-up question information associated with the general examination point information sent by the server, and displaying the historical follow-up question information.

[0101] Specifically, when receiving the targeted answer information and the general examination point content for the subject question information from the server, one or more historical follow-up question information associated with the general examination point information can also be received from the server. Subsequently, while displaying the targeted answer information and the general examination point content, the historical follow-up question information can also be displayed so that the user can further select the historical follow-up question information that meets their own needs for viewing, without the user having to repeatedly enter the same follow-up question information as the historical follow-up question information, thereby enhancing the user experience.

[0102] In some alternative embodiments, after displaying the historical follow-up question information, the method of this embodiment further includes: in response to a click operation by the user on the historical follow-up question information, obtaining the historical answer information corresponding to the historical follow-up question information previously received from the server, and displaying the historical answer information.

[0103] Exemplarily, when receiving one or more historical follow-up question information associated with the general examination point information from the server, the historical answer information corresponding to the historical follow-up question information can also be received. After displaying the one or more historical follow-up question information, a click operation by the user on the historical follow-up question information can be detected, and based on the click operation, the historical answer information corresponding to the historical follow-up question information can be further displayed, so that the user can quickly view the historical answer information corresponding to the historical follow-up question information, without the server having to repeatedly generate the answer information for the historical follow-up question information, saving device resources.

[0104] Next, with reference to Figure 5 the following scenario schematic diagram, an exemplary description of an overall implementation process of the information processing solution of the embodiments of the present application will be given. As Figure 5 shown, the user takes an image containing subject question information on the input interface of the user terminal, obtains the subject question information, and sends the subject question information to the server. The server obtains the subject question information, and then parses the subject question information to obtain the general examination point information contained in the subject question information; and determines the general examination point content that matches the general examination point information from the examination point content library; the general examination point content contains the examination point explanation content corresponding to the general examination point information; in addition, a targeted answer information for the subject question information is generated through a generative language model, that is, the general examination point content and the targeted answer information for the subject question information can be obtained, and the general examination point content and the targeted answer information for the subject question information are returned to the user terminal. The user terminal receives the targeted answer information and the general examination point content for the subject question information from the server and displays them on the display interface.

[0105] It should be understood that Figure 5 more details of the overall implementation process shown in Figure 5The overall implementation process shown is only some examples for easy understanding of the embodiments of the present application, and does not impose any limitation on the embodiments of the present application.

[0106] It can be understood that the foregoing description of the information processing method is only some exemplary descriptions of the embodiments of the present application, and does not impose any limitation on the embodiments of the present application.

[0107] Referring to Figure 6 , a structural block diagram of an information processing device according to an exemplary embodiment of the present application is shown.

[0108] According to a third aspect in the embodiments of the present application, an information processing device is provided, including: a first acquisition module 602, a test point matching module 604, a solution module 606, and a first display module 608.

[0109] Among them, the first acquisition module 602 is configured to acquire subject question information input by a user for a preset subject; the test point matching module 604 is configured to parse the subject question information to determine general test point information involved in the solution process for the subject question information; determine general test point content matching the general test point information from a pre-generated test point content library or a searched test point content library; the solution module 606 is configured to solve the subject question information to obtain targeted answer information corresponding to the subject question information; the first display module 608 is configured to display the targeted answer information and the general test point content for the subject question information.

[0110] In some alternative embodiments, the test point matching module 604 is specifically configured to: identify keywords in the subject question information to obtain first test point information; perform semantic analysis on the subject question information to obtain second test point information; fuse the first test point information and the second test point information to determine the general test point information involved in the subject question information; and determine general test point content matching the general test point information from a pre-generated test point content library or a searched test point content library according to a pre-determined mapping relationship between test point information and test point content.

[0111] In some alternative embodiments, the first display module 608 is specifically configured to create an answer display page and display the targeted answer information corresponding to the subject question information on the answer display page; and in response to an interaction operation on the targeted answer information displayed on the answer display page, pop up a pop-up page containing the general test point content.

[0112] In some alternative embodiments, the information processing device further includes a note generation module, configured to generate marking information in response to a marking operation on the displayed targeted answer information and the general test point content; and generate a Q&A note based on the subject question information, the targeted answer information, the general test point content, and the marking information.

[0113] In some alternative embodiments, the note generation module is further configured to: after generating the Q&A notes, determine target Q&A notes related to the same general examination point content from a note library containing multiple Q&A notes; merge the target Q&A notes to generate a topic category note for the same general examination point content.

[0114] In some alternative embodiments, the information processing device further includes: a test point content generation module, configured to determine a test point title corresponding to the historical question information according to the historical question information of a preset subject input by the user; and generate test point content corresponding to the historical question information through a target large language model according to the historical question information and the corresponding test point title.

[0115] In some alternative embodiments, when the test point content generation module executes the step of generating test point content corresponding to the historical question information through a target large language model according to the historical question information and the corresponding test point title, it is specifically configured to: retrieve from a preset knowledge base through a retrieval enhancement generation method according to the historical question information and the corresponding test point title to obtain a first retrieval result associated with the historical question information and the test point title; analyze the historical question information, the test point title, and the first retrieval result to generate a test point content prompt, and input the test point content prompt into the pre-trained target large language model to generate test point content corresponding to the historical question information through the target large language model.

[0116] In some alternative embodiments, when the test point content generation module executes the step of determining a test point title corresponding to the historical question information according to the historical question information of a preset subject input by the user, it is specifically configured to: obtain multiple historical follow-up questions for the historical question information of a preset subject input by the user; screen the multiple historical follow-up questions through a preset screening rule to obtain the screened historical follow-up questions; the preset screening rule is used to screen the historical follow-up questions for the relevance to the historical question information and the title style; and screen the screened historical follow-up questions through a pre-trained target classification model to obtain a test point title corresponding to the historical question information.

[0117] In some alternative embodiments, when the test point content generation module executes the step of determining a test point title corresponding to the historical question information according to the historical question information of a preset subject input by the user, it is specifically configured to: determine the historical question information of a preset subject input by the user, and obtain multiple test point information included in the historical question information; input the multiple test point information into a pre-trained first large language model to output a test point title corresponding to the historical question information; the first large language model is a large language model trained with test point information samples as training data and test point title samples as labels.

[0118] In some alternative embodiments, when the examination point content generation module executes the step of generating examination point content corresponding to the historical question information according to the historical question information and the corresponding examination point title through the target large language model, it is specifically configured to: input the historical question information and the corresponding examination point title into a pre-trained second large language model, and output multiple query questions for the historical question information; the second large language model is a large language model trained with question information samples and examination point title samples as training data and query question samples as labels; for the multiple query questions, retrieve query results for the multiple query questions from a pre-constructed subject knowledge base; input the query results and the examination point title into a pre-trained third large language model, and output the examination point content corresponding to the historical question information; the third large language model is a large language model trained with examination point paradigm samples as training data.

[0119] In some alternative embodiments, when the examination point content generation module executes the step of inputting the historical question information and the corresponding examination point title into a pre-trained second large language model and outputting multiple query questions for the historical question information, it is specifically configured to: perform information retrieval based on the historical question information and the corresponding examination point title to obtain a second retrieval result associated with the historical question information and the examination point title; and generate a query question prompt word according to the historical question information, the examination point title, and the second retrieval result; input the query question prompt word into the pre-trained second large language model to guide the second large language model to generate multiple query questions for the historical question information through the query question prompt word.

[0120] In some alternative embodiments, the information processing device further includes: A training module, configured to obtain query question type information corresponding to multiple subjects; based on the query question type information corresponding to multiple subjects, determine corresponding query question samples for the question information samples and examination point title samples corresponding to each subject; use the question information samples and examination point title samples corresponding to each subject as training data, and use the corresponding query question samples as labels to train a large language model to obtain a second large language model.

[0121] In some alternative embodiments, the information processing device further includes: A construction module, configured to obtain an initial examination point paradigm sample; based on the style adjustment prompt information corresponding to multiple subjects, adjust the initial examination point paradigm sample through a large language model to obtain an examination point paradigm sample.

[0122] The information processing device of this embodiment is used to implement the corresponding information processing methods in the multiple method embodiments of the foregoing first aspect, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here. In addition, the function implementation of each module in the information processing device of this embodiment can refer to the corresponding part of the description in the foregoing method embodiments, which will not be elaborated here either.

[0123] Referring to Figure 7 , a structural block diagram of an information processing device according to an exemplary embodiment of the present application is shown.

[0124] According to a fourth aspect in the embodiments of the present application, an information processing device is provided, which is applied to a user terminal and includes a second acquisition module 702, a sending module 704, and a second display module 706.

[0125] Among them, the second acquisition module 702 is configured to, in response to an input operation of a user on the user terminal, acquire subject question information input by the user for a preset subject; the sending module 704 is configured to send the question information to the server; the server is configured to analyze the subject question information, determine general examination point information involved in the solution process for the subject question information; determine general examination point content matching the general examination point information from a pre-generated examination point content library or a searched examination point content library; perform question solving on the subject question information to obtain targeted answer information corresponding to the subject question information; the second display module 706 is configured to receive the targeted answer information and the general examination point content for the subject question information returned by the server and perform display.

[0126] In some alternative embodiments, the second acquisition module 702 is further configured to: in response to a shooting operation of the user on the user terminal, acquire an image containing subject question information input by the user; perform information recognition on the image containing the subject question information to obtain the subject question information input by the user.

[0127] In some alternative embodiments, the second acquisition module 702 is further configured to: in response to a text input operation of the user on the user terminal, acquire subject question information input by the user for a preset subject.

[0128] In some alternative embodiments, the second display module 706 is further configured to: receive at least one historical follow-up question information associated with the general examination point information sent by the server and perform display on the historical follow-up question information.

[0129] In some alternative embodiments, the second display module 706 is further configured to: in response to a click operation of the user on the historical follow-up question information, acquire historical answer information corresponding to the historical follow-up question information previously received from the server and perform display on the historical answer information.

[0130] The information processing device in this embodiment is used to implement the corresponding information processing methods in multiple method embodiments of the foregoing second aspect, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here. In addition, the function implementation of each module in the information processing device in this embodiment can refer to the description of the corresponding part in the foregoing method embodiments, which will not be elaborated here either.

[0131] According to a fifth aspect of the embodiments of the present application, an electronic device is provided, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus; the memory is used for storing a computer program; the processor is used for executing the information processing method according to the foregoing first aspect or second aspect by running the computer program stored on the memory.

[0132] Figure 8 The structural block diagram of an optional electronic device in the embodiments of the present application is shown. The embodiments of the present application do not limit the specific implementation of the electronic device 800. Exemplarily, with reference to Figure 8 , the electronic device 800 provided by the embodiments of the present application includes: a processor 802, a communication interface 804, a memory 806, and a communication bus 808. Among them: The processor 802, the communication interface 804, and the memory 806 complete communication with each other through the communication bus 808.

[0133] The communication interface 804 is used for communicating with other electronic devices or servers.

[0134] The processor 802 is used for executing the computer program 810, and specifically can execute the relevant steps in any of the foregoing information processing method embodiments.

[0135] Specifically, the computer program 810 may include program code, and the program code includes computer operation instructions.

[0136] The processor 802 may be a CPU, or a GPU (Graphic Processing Unit), or an application specific integrated circuit ASIC, or one or more integrated circuits configured to implement the embodiments of the present application. One or more processors included in the intelligent device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0137] The memory 806 is used for storing the computer program 810. The memory 806 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0138] The computer program 810 can specifically be used to cause the processor 802 to execute the information processing method in any of the foregoing embodiments.

[0139] For the specific implementation of each step in the computer program 810, reference may be made to the corresponding steps and descriptions in the corresponding units in any of the foregoing information processing method embodiments, which will not be elaborated herein. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding process descriptions in the foregoing method embodiments, which will not be elaborated herein again.

[0140] The electronic device 800 in the embodiments of the present application has been described in detail in the foregoing information processing method embodiments. Therefore, the relevant content and beneficial effects thereof can be understood with reference to the above method embodiments and will not be elaborated herein.

[0141] According to the sixth aspect of the embodiments of the present application, the embodiments of the present application further provide a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the information processing method described in any one of the foregoing multiple method embodiments. The computer storage medium includes but is not limited to: Compact Disc Read-Only Memory (CD-ROM), Random Access Memory (RAM), floppy disk, hard disk, magneto-optical disk, etc.

[0142] According to the seventh aspect of the embodiments of the present application, the embodiments of the present application further provide a computer program product, including a computer program. When the computer program is executed by a processor, it implements the information processing method described in any one of the above multiple method embodiments.

[0143] The embodiments of the electronic device 800 / computer storage medium / computer program product in the embodiments of the present application have been described in detail in the foregoing information processing method embodiments. Therefore, the relevant content and beneficial effects thereof can be understood with reference to the above method embodiments and will not be elaborated herein.

[0144] In addition, it should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data for training the model, data for analysis, stored data, displayed data, etc.) related to users involved in the embodiments of the present application are all information and data authorized by the users or fully authorized by all parties. And the collection, use, and processing of the relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0145] It should be noted that, according to the needs of implementation, each component / step described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0146] The methods according to the embodiments of the present application described above can be implemented in hardware, firmware, or be implemented as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or be implemented as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and to be downloaded through a network and stored in a local recording medium, so that the methods described herein can be stored on such a software process on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA)). It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component (such as a Random Access Memory (RAM), a Read-Only Memory (ROM), a flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods described herein are implemented. In addition, when a general-purpose computer accesses the code for implementing the methods shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0147] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for a specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present application.

[0148] As used herein, the term "including" and its variations are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". It should be noted that the concepts such as "first", "second", etc. mentioned in the embodiments of the present application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. It should be noted that the modifications of "one" and "a plurality" mentioned in the embodiments of the present application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0149] The above embodiments are only used to illustrate the embodiments of the present application, rather than to limit the embodiments of the present application. Those of ordinary skill in the relevant technical field can also make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The patent protection scope of the embodiments of the present application shall be defined by the claims.

Claims

1. An information processing method, comprising: Obtain subject title information for a preset subject input by the user; Parsing the subject question information, determining universal test point information involved in the process of solving the subject question information; determining universal test point content matching the universal test point information from a pre-generated test point content library or a searched test point content library; Solve the subject question information to obtain targeted answer information corresponding to the subject question information; With respect to the subject question information, the targeted answer information and the universal examination point content are displayed.

2. The method according to claim 1, wherein: The step of analyzing the subject question information and determining universal examination point information involved in the process of solving the subject question information includes: Perform keyword recognition on the subject title information to obtain first test point information; perform semantic analysis on the subject title information to obtain second test point information; The first test point information and the second test point information are integrated to determine the universal test point information involved in the subject question information; The determining of universal test point content matching the universal test point information from a pre-generated test point content library or a searched test point content library includes: According to the predetermined mapping relationship between the test point information and the test point content, the universal test point content matching the universal test point information is determined from a pre-generated test point content library or a searched test point content library.

3. The method according to claim 1, wherein: The display of the targeted answer information and the universal test content for the subject question information includes: Creating an answer display page, and displaying targeted answer information corresponding to the subject question information on the answer display page; In response to the interactive operation on the targeted answer information displayed in the answer display page, a pop-up page containing the universal test point content pops up.

4. The method according to any one of claims 1 to 3, wherein: The method further comprises: In response to a marking operation on the displayed targeted answer information and the universal test point content, generating marking information; Based on the subject question information, the targeted answer information, the universal test point content and the marking information, question and answer notes are generated.

5. The method according to claim 4, wherein: After generating the question-and-answer notes, the method further includes: From the note library containing multiple question-and-answer notes, determine the target question-and-answer notes involving the same universal test point content; Merge the target question and answer notes to generate test point category notes for the same universal test point content.

6. The method according to claim 1, wherein: Before obtaining subject title information for a preset subject input by a user, the method further includes: Determining the test point title corresponding to the history topic information according to the history topic information input by the user for the preset subject; According to the historical topic information and the corresponding test point title, test point content corresponding to the historical topic information is generated through a target large language model.

7. The method according to claim 6, wherein: The step of generating test point content corresponding to the history topic information by using a target large language model according to the history topic information and the corresponding test point title includes: According to the historical question information and the corresponding test point title, searching from a preset knowledge base through a search enhancement generation method to obtain a first search result associated with the historical question information and the test point title; Parse the history question information, the test point title and the first search result to generate test point content prompt words, and input the test point content prompt words into a pre-trained target large language model to generate test point content corresponding to the history question information through the target large language model.

8. The method according to claim 6, wherein: The step of determining the examination point title corresponding to the history topic information for the preset subject according to the history topic information input by the user includes: Acquire multiple pieces of historical inquiry information for the historical question information of the preset subject input by the user; The plurality of historical inquiry information are screened by using preset screening rules to obtain screened historical inquiry information; the preset screening rules are used to screen the historical inquiry information for relevance to the historical title information and for title style; The filtered historical question information is filtered through a pre-trained target classification model to obtain the test point titles corresponding to the historical question information.

9. The method according to claim 6, wherein: The step of determining the examination point title corresponding to the history topic information for the preset subject according to the history topic information input by the user includes: Determine the history question information for the preset subject input by the user, and obtain multiple test point information contained in the history question information; The multiple test point information are input into a pre-trained first large language model, and the test point titles corresponding to the history question information are output; the first large language model is a large language model trained with test point information samples as training data and test point title samples as labels.

10. The method according to any one of claims 6 to 9, wherein: The step of generating test point content corresponding to the history topic information by using a target large language model according to the history topic information and the corresponding test point title includes: Input the history question information and the corresponding test point title into a pre-trained second language model, and output multiple query questions for the history question information; the second language model is a large language model trained with question information samples and test point title samples as training data and query question samples as labels; Retrieving query results for the multiple query questions from a pre-built subject knowledge base; The query result and the test point title are input into a pre-trained third language model, and the test point content corresponding to the history question information is output; the third language model is a large language model trained with test point paradigm samples as training data.

11. The method according to claim 10, wherein: The step of inputting the history topic information and the corresponding test point title into a pre-trained second language model and outputting a plurality of query questions for the history topic information includes: Performing information retrieval based on the historical topic information and the corresponding test point title to obtain a second search result associated with the historical topic information and the test point title; and generating a query question prompt word based on the historical topic information, the test point title and the second search result; The query question prompt words are input into a pre-trained second language model, so as to guide the second language model to generate a plurality of query questions for the historical topic information through the query question prompt words.

12. The method according to claim 11, wherein: The method further comprises: Get query question type information corresponding to multiple subjects; Based on the query question type information corresponding to the multiple subjects, determine the corresponding query question samples for the question information samples and the test point title samples corresponding to each subject; The subject information samples and the test point title samples corresponding to each subject are used as training data, and the corresponding query question samples are used as labels to train the large language model to obtain the second large language model.

13. The method according to claim 10, wherein: The construction process of the test point paradigm sample includes: Obtain the initial test point paradigm sample; Based on the style adjustment prompt information corresponding to multiple subjects, the initial test point paradigm sample is adjusted through a large language model to obtain the test point paradigm sample.

14. An information processing method, applied to a user terminal, comprising: In response to an input operation of a user on the user terminal, obtaining subject title information for a preset subject input by the user; Sending the subject title information to the server; The server is used to parse the subject question information, determine the universal test point information involved in the process of solving the subject question information; determine the universal test point content matching the universal test point information from a pre-generated test point content library or a searched test point content library; solve the subject question information to obtain the targeted answer information corresponding to the subject question information; Receive the targeted answer information and the universal test point content for the subject question information returned by the server, and display them.

15. The method according to claim 14, wherein: The step of obtaining subject title information for a preset subject input by the user in response to an input operation of the user at the user terminal includes: In response to a shooting operation of the user at the user terminal, acquiring an image input by the user and containing subject title information; Information recognition is performed on the image containing the subject title information to obtain the subject title information input by the user.

16. The method according to claim 14, wherein: The step of obtaining subject title information for a preset subject input by the user in response to an input operation of the user at the user terminal includes: In response to a text input operation of a user at the user terminal, subject title information for a preset subject input by the user is obtained.

17. The method according to any one of claims 14 to 16, wherein: When receiving the targeted answer information and the universal test point content for the subject question information returned by the server and displaying them, the method further includes: Receive at least one piece of historical questioning information associated with the universal test point information sent by the server, and display the historical questioning information.

18. The method according to claim 17, wherein: After displaying the historical inquiry information, the method further includes: In response to a user's click operation on the historical question information, historical answer information corresponding to the historical question information received in advance from the server is obtained, and the historical answer information is displayed.

19. An electronic device comprising: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 18 by running the computer program stored in the memory.

20. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 18 is implemented.

21. A computer program product comprising computer instructions, the computer instructions instructing a computing device to execute the method according to any one of claims 1-18.

Images