Information processing method, electronic device, and computer storage medium

Abstract

The embodiments of the present application provide an information processing method, an electronic device, and a computer storage medium, which obtain subject question information input by a user; parse the subject question information to determine the universal test point information involved in the process of solving the subject question information; determine the universal test point content that matches the universal test point information from the test point content library; solve the subject question information to obtain targeted answer information corresponding to the subject question information; and display the targeted answer information and universal test point content for the subject question information. The solution of this implementation not only provides users with targeted answers to the subject question information, but also provides users with corresponding universal test point content. Since the universal test point content contains test point explanation content corresponding to the universal test point information, it can help users comprehensively and systematically master the test point content related to the subject question information to meet the user's learning needs.

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, electronic device, computer storage medium, and computer program product. Background Art

[0002] Currently, many applications on the market offer question search functionality. For example, users can enter a question to search, and the application will generate a corresponding answer based on the question. However, the answers currently provided by these applications are often very specific to the question, making it difficult for users to fully grasp the relevant learning content, thus failing to meet their learning needs. Summary of the Invention

[0003] In view of this, an embodiment of the present application provides an information processing solution to at least partially solve the above-mentioned problem.

[0004] According to a first aspect of an embodiment of the present application, an information processing method is provided, including: obtaining subject question information for a preset subject input by a user; parsing the subject question information to determine universal test point information involved in the solution process of the subject question information; determining universal test point content that matches the universal test point information from a pre-generated test point content library or a searched test 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 universal test point content for the subject question information.

[0005] According to a second aspect of an embodiment 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 a user on the user terminal, obtaining subject question information for a preset subject input by the user; sending the subject question information to a server; the server is used to parse the subject question information and determine the universal test point information involved in the solution process for the subject question information; determine the universal test point content that matches 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 and obtain 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.

[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, 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 a computer program; and the processor is used to execute the information processing method described in the first or second aspect above by running the computer program stored on the memory.

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

[0008] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the information processing method as described in the first aspect or the second aspect.

[0009] According to the information processing solution provided in the embodiment of the present application, the subject question information for the preset subject input by the user is obtained, and then the subject question information is parsed to determine the universal test point information involved in the solution process of the subject question information, and the universal test point content that matches the universal test point information is determined from the test point content library; in addition, the subject question information is also solved to obtain the targeted answer information corresponding to the subject question information, so that the targeted answer information and the above-mentioned universal test point content can be displayed to the user.

[0010] The solution provided in the embodiment of the present application not only provides users with targeted answers to subject question information, but also provides users with valuable universal test point content involved in the process of solving the subject question information. The universal test point content includes explanation content for universal test points, which can help users comprehensively and systematically grasp the common test point content involved in the subject question information to meet the user's learning needs.

[0011] The solution provided by the embodiment of the present application can provide users with targeted answers in scenarios where users are seeking specific answers to specific questions. At the same time, it can also intuitively present to users the explanation content corresponding to the universal test points (common test points) involved in the process of solving the specific subject questions. This avoids the user from having to perform additional question-and-answer interactive operations in order to seek the above-mentioned universal test points. For users, the embodiment of the present application can more likely achieve the effect of understanding a question and mastering a category of questions.

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

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0014] Figure 1 Schematic diagram of an information processing system according to an embodiment of the present application.

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

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

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

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

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

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

[0021] Figure 8 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present application.

[0023] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0024] Figure 1 An exemplary system applicable to the embodiment of the present application is shown. 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 The example in the figure shows multiple user devices 106, on which applications are provided for displaying subject question information, targeted answer information and universal test content.

[0025] The server 102 can be any appropriate device for storing information, data, programs and / or any other suitable type of content, including but not limited to distributed storage system devices, server clusters, computing server clusters, etc. In some embodiments, the server 102 can perform any appropriate function. For example, when the solution of the embodiment of the present application is implemented by the server 102, in some embodiments, the server 102 can be used to execute the information processing method. As an optional example, in some embodiments, the server 102 can first obtain the subject question information for the preset subject input by the user, and then parse the subject question information to obtain the universal test point information involved in the process of solving the subject question information; and determine 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; and solve the subject question information to obtain the targeted answer information corresponding to the subject question information, that is, the universal test point content and targeted answer information for the subject question information can be obtained. In some embodiments, the server 102 can receive subject question information sent by the user device 106, and after generating targeted answer information and universal test point content in the aforementioned manner, send the targeted answer information and universal test point content to the user device 106, so that the user device 106 displays the targeted answer information and universal test 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 hard-wired link, any other suitable communication link, or any suitable combination of such links.

[0027] Optionally, the user device 106 may be provided with an application that displays subject question information, targeted answer information, and universal test content. The user device 106 may include any one or more user devices suitable for displaying information, interacting with a user, etc. In some embodiments, the user device 106 may include any suitable type of device. For example, in some embodiments, the user device 106 may 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 is described below through multiple embodiments.

[0029] Figure 2 A flowchart of the steps of an information processing method according to an embodiment of the present application. According to the first aspect of the embodiment 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:

[0030] S202: Obtain subject title information for a preset subject input by the user.

[0031] For example, a discipline refers to a specific academic field or knowledge system. The embodiments of this application do not limit the classification method and specific content of the preset disciplines. For example, common discipline classifications include natural sciences, engineering technology, medicine, social sciences, humanities, and mathematics. The subject question information for a preset discipline can be question information within the scope of the preset discipline. When a user wants to obtain the answer to a subject question within a certain discipline, they can perform a subject question information input operation on the user terminal, such as taking a picture of the subject question information for the preset discipline or entering the question text, etc., to obtain an image or text containing the subject question information. The image or text containing the subject question information is then sent to the server via the user terminal. Subsequently, for the image containing the subject question information, image information recognition processing can be performed to obtain the subject question information for the preset discipline entered by the user; for the text entered by the user, the text can be used as the subject question information for the preset discipline entered by the user. For example, for mathematics, the subject question information entered by the user can be: "Solve this triangle problem: Find the angle of a triangle with sides of 3, 4, and 5."

[0032] S204: Analyze the subject question information and determine the universal test point information involved in the process of solving the subject question information; determine the universal test point content that matches the universal test point information from a pre-generated test point content library or a searched test point content library.

[0033] For example, for a specific subject, the subject question information proposed by the user usually involves some knowledge points that are frequently asked by users in the subject. In the embodiment of the present application, the above-mentioned knowledge point information can be referred to as universal test points. Furthermore, the universal test point information can be the name, logo and other identifiable information of the universal test point parsed from the subject question information. For example, in the subject of mathematics, the universal test point information involved in the process of solving the subject question information may include: trigonometric functions, the Pythagorean theorem, trigonometric identities, quadratic equations, and so on. For example, for the subject question information in the subject of mathematics: "Solve this triangle problem: find the angle of a triangle with sides of 3, 4, and 5." The universal test point information involved in the process of solving the subject question information includes the Pythagorean theorem and trigonometric functions.

[0034] The universal test point content may include the universal test point itself. Furthermore, the universal test point content may also include explanation content specific to the universal test point. That is, the universal test point content may include universal test point explanation content corresponding to the universal test point information. Correspondingly, the universal test point content may also include universal test point explanation content corresponding to the universal test point information. Exemplarily, the universal test point content in this embodiment may be rich media content, that is, the universal test point content may be embodied as multimedia content containing multiple media elements (e.g., at least two of images, audio, and video).

[0035] 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, the subject question information is parsed to obtain the universal test point information related to the subject question information. The universal test point information can then be matched with the test point information corresponding to the test point content contained in the test point content library, and the successfully matched test point content can be used as the universal test point content involved in the process of solving the subject question information.

[0036] In some optional embodiments, parsing the subject question information and determining the universal test point information involved in the process of solving the subject question information may include: performing keyword recognition on the subject question information to obtain first test point information; performing semantic analysis on the subject question information to obtain second test point information; and fusing the first test point information with the second test point information to determine the universal test point information involved in the subject question information. Correspondingly, determining the universal test point content that matches the universal test point information from a pre-generated test point content library or a searched test point content library may include: determining the universal test point content that matches the universal test point information from a pre-generated test point content library or a searched test point content library based on a predetermined mapping relationship between the test point information and the test point content.

[0037] Exemplarily, when parsing question information, keyword recognition can be performed on the subject topic information. For example, keyword recognition can be performed on the subject topic information based on a preset test point keyword thesaurus to obtain first test point information, such as the matched test point keywords. In addition, semantic analysis can be performed on the subject topic information, and further semantic recognition can be performed based on the context in the subject topic information to obtain second test point information, such as the test point information implicit in the subject topic information other than the test point keywords. Afterwards, the first test point information and the second test point information can be fused. For example, the first test point information and the second test point information can be simply merged, or the duplicate information in the first test point information and the second test point information can be removed first, and then the processed test point information can be merged, etc., so as to obtain universal test point information involved in the subject topic information.

[0038] In this embodiment, by performing keyword recognition on the subject title information, the explicit first test point information contained in the subject title information can be obtained, and then by performing semantic analysis on the subject title information, the implicit second test point information contained in the subject title information can be obtained. Then, by combining the first test point information and the second test point information, more comprehensive universal test point information involved in the subject title information can be analyzed to avoid missing test points in the subject title information.

[0039] In other optional embodiments, determining the universal test point content that matches the universal test point information from a pre-generated test point content library or a test point content library obtained by search may also include: determining the target historical question information that matches the universal test point information; and based on the predetermined mapping relationship between the historical question information and the test point content, determining that the test point content corresponding to the target historical question information is the universal test point content that matches the universal test point information from a pre-generated test point content library or a test point content library obtained by search.

[0040] Exemplarily, the test point content in the test point content library can be generated based on part of the question information in the preset question bank, and the preset question bank can include historical question information input by the user. After the test point content library is constructed, a mapping relationship between each test point content and the corresponding historical question information in the test point content library can be established. When matching the universal test point content corresponding to the universal test point information in multiple test point contents later, 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 the test point content corresponding to the target historical question information can be determined as the above-mentioned universal test point content according to the pre-set mapping relationship between the historical question information and the test point content. Optionally, after parsing the universal test point information involved in the subject question information solution process, it can be matched with the test point content contained in the test point content library based on the universal test point information, and the successfully matched test point content can be used as the above-mentioned universal test point content.

[0041] In this embodiment, when multiple test point contents are generated in advance based on historical question information, a mapping relationship between the historical question information and the test point contents is constructed, so that when the subject question information input by the user is subsequently matched with the universal test point contents, the corresponding target historical question information can be matched, and then based on the mapping relationship between the historical question information and the test point contents, it is quickly determined that the test point content corresponding to the target historical question information is the universal test point content.

[0042] Here, an exemplary description is given of the process of pre-generating a test point content library containing a plurality of test point contents in this embodiment.

[0043] In some optional embodiments, before obtaining the subject topic information input by the user, the method of this embodiment also includes: determining the test point title corresponding to the history topic information for the preset subject based on the user input; and generating the test point content corresponding to the history topic information through the target large language model based on the history topic information and the corresponding test point title.

[0044] Exemplarily, the multiple pre-generated test content can be generated based on the historical question information input by the user. In the process of generating the test content, the historical answer information and the corresponding historical question information corresponding to the historical question information can be obtained based on the historical question information, and then the test title corresponding to the historical question information is generated based on the historical answer information and the corresponding historical question information, that is, the title of the test content to be generated. Afterwards, the historical question information and the corresponding test title are input into the pre-trained target large language model, and the test content corresponding to the historical question information is generated by the target large language model.

[0045] 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) refers to a deep learning model trained using a large amount of text data, which enables 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 by training on large data sets. Large language models can learn the patterns and structure of natural language through large-scale unsupervised training, simulating the human language cognition and generation process to a certain extent.

[0046] In some optional embodiments, based on the historical topic information and the corresponding test point title, the test point content corresponding to the historical topic information is generated through the target large language model, including: based on the historical topic information and the corresponding test point title, searching from a preset knowledge base through a retrieval enhancement generation method to obtain a first retrieval result associated with the historical topic information and the test point title; parsing the historical topic information, the test point title and the first retrieval result to generate test point content prompt words, and inputting the test point content prompt words into the pre-trained target large language model to generate the test point content corresponding to the historical topic information through the target large language model.

[0047] In this embodiment, the test point title corresponding to the historical question information is determined based on the historical question information input by the user; then, the test point content corresponding to the historical question information is generated based on the historical question information and the corresponding test point title through the pre-trained target large language model, thereby improving the generation efficiency of the test point content. Moreover, the content generation capability of the large language model can ensure the content quality of the test point content. In addition, the test point content in this embodiment is generated based on the historical question information input by the user, that is, the test point content can be generated for the common concerns of the user, so that the generated test point content can more efficiently meet the user's aggregation needs. That is: in the above embodiment of the present application, when generating the test point content, on the one hand, the core test point titles are extracted and condensed from the question information of the user's historical questions, and then the test point content is generated based on the extracted test point titles. The above-mentioned method of extracting and concise core test point titles can make the final test point content better cover the questions raised by users, thereby improving the universality and aggregation of the generated test point content; on the other hand, after extracting the test point titles, the embodiment of the present application adopts the content generation capability of the large language model to generate test point content based on historical question information and the test point title guidance model, so that the final generated test point content can better match the historical question information and the test point title, thereby improving the pertinence of the test point content.

[0048] In some optional embodiments, based on the history question information for a preset subject input by a user, determining the test point title corresponding to the history question information includes: obtaining multiple historical question information for the history question information for a preset subject input by the user; filtering the multiple historical question information through preset filtering rules to obtain filtered historical question information; the preset filtering rules are used to filter the historical question information for correlation with the history question information and for title style; and filtering the filtered historical question information through a pre-trained target classification model to obtain the test point title corresponding to the history question information.

[0049] For example, referring to Figure 3ADuring the process of generating a test point title, multiple corresponding historical follow-up information can be obtained based on a single historical question information. Here, based on the click counts of each historical follow-up information corresponding to the historical question information, multiple historical follow-up information with click counts exceeding a preset click threshold can be obtained. This can identify common questions shared by most users, and subsequent test point content generation can be performed based on these common questions, allowing the generated test point content to more efficiently meet user aggregation needs. Subsequently, the multiple historical follow-up information can be filtered using preset filtering rules to obtain multiple filtered historical follow-up information. The preset filtering rules are used to filter the historical follow-up information for relevance to the historical question information and for title style. For example, with respect to the relevance filtering to the historical question information, firstly, historical follow-up information corresponding to other historical question information whose similarity to the historical question information reaches a preset threshold can be obtained. Secondly, since the multiple historical follow-up information can include follow-up information from multiple rounds of questions regarding the historical question information, the preset filtering rules can be used to filter the follow-up information from the first round of questions as the filtered historical follow-up information. For title style screening, the preset screening rules can set the test point title style, including word count requirements, sentence structure requirements, etc., which are not limited in this embodiment. The historical question information that meets the test point title style is screened out by the preset screening rules, and the filtered historical question information can be obtained.

[0050] After obtaining multiple pieces of filtered historical question information, the filtered historical question information can be input into a pre-trained target classification model. The target classification model is used to further classify the filtered historical question information, thereby obtaining the test point titles corresponding to the historical question information based on the classification results. Here, the target classification model is a classification model trained using pre-labeled positive and negative sample data of the test point titles.

[0051] A classification model is a model used in machine learning 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 data samples corresponding to the target category. For example, the positive sample data in this embodiment can be pre-labeled qualified test point titles. Negative samples refer to data samples that do not belong to the target category, as opposed to positive samples. For example, the negative sample data in this embodiment can be pre-labeled unqualified test point titles.

[0052] In this embodiment, when generating the test point titles, the core test point titles are further extracted and condensed from the user's historical questioning behavior (including the question information of the first question, and the follow-up question information for the first question information). The above-mentioned method of extracting and condensing the core test point titles can make the final generated test point content better cover the questions raised by the user, thereby improving the universality and aggregation of the generated test point content.

[0053] In addition, in this embodiment, after obtaining the historical question information, the plurality of historical question information is first screened in terms of relevance and title style using preset screening rules to obtain historical question information with a higher relevance to the historical question information and a better style; thereafter, the screened historical question information is screened a second time using a pre-trained target classification model to obtain the test point titles corresponding to the historical question information. In this embodiment, the historical question information is screened multiple times based on relevance, title style, and classification model, thereby obtaining the test point titles corresponding to the historical question information based on the ultimately screened historical question information. Therefore, the correlation between the ultimately generated test point titles and the historical question information can be made higher, and the ultimately generated test point titles can be made more accurate and have a better style.

[0054] In some optional embodiments, based on the historical question information input by the user, determining the test point title corresponding to the historical question information includes: determining the historical question information input by the user, and obtaining multiple test point information contained in the historical question information; inputting the multiple test point information into a pre-trained first large language model, and outputting the 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.

[0055] For example, referring to Figure 3A In addition to the aforementioned method of generating test point titles, test point titles can also be generated in the following way: first, the historical question information can be parsed to obtain multiple test point information contained in the historical question information, and then the multiple test point information is input into the pre-trained first large language model. The first large language model is a large language model that is pre-trained with test point information samples as training data and test point title samples as labels. Then, the first large language model can output the test point title corresponding to the historical question information.

[0056] A training dataset can be pre-constructed. Question information samples can be obtained from a preset question bank (including historical question information). These question information samples are parsed to obtain test point information samples. These test point information samples can include explicit test point samples and implicit test point samples, and the test point information samples constitute the training data. Correspondingly, corresponding label data is constructed for the test point information samples: test point title samples. The test point information samples and the corresponding test point title samples then form a training dataset. The training dataset is used to fine-tune the large language model, resulting in the first large language model.

[0057] In this embodiment, the first language model obtained by training with test point information samples as training data and test point title samples as labels is used to process multiple test point information corresponding to historical question information to obtain test point titles corresponding to the historical question information. This method can better generate corresponding test point titles for some historical question information with less follow-up information or poor quality, and has high generation efficiency and accuracy.

[0058] In some optional embodiments, based on the historical topic information and the corresponding test point titles, test point content corresponding to the historical topic information is generated through the target large language model, including: inputting the historical topic information and the corresponding test point titles into a pre-trained second large language model, and outputting multiple query questions for the historical topic information; for the multiple query questions, retrieving query results for the multiple query questions from a pre-built subject knowledge base; inputting the query results and test point titles into a pre-trained third large language model, and outputting the test point content corresponding to the historical topic information.

[0059] In some optional embodiments, the historical topic information and the corresponding test point titles are input into a pre-trained second language model, and multiple query questions for the historical topic information are output, including: performing information retrieval based on the historical topic information and the corresponding test point titles to obtain a second search result associated with the historical topic information and the test point title; and generating query question prompt words based on the historical topic information, the test point title and the second search result; and inputting the query question prompt words into the pre-trained second language model to guide the second language model to generate multiple query questions for the historical topic information through the query question prompt words.

[0060] In this embodiment, the query question represents the test point information involved in the historical topic information, and from which aspects to collect materials when generating the corresponding test point content. The query question is associated with the test point information contained in the historical topic information. For example, if the historical topic information is a topic corresponding to a law subject, the query question may include: Q1 What laws are included, Q2 What are the cases of theft, Q3 What are the differences between the charges, etc. The query result is the test point content queried for the query question. For example, the query result R1 for Q1 can be the content of a specific law, and the query result R2 for Q2 can be the content of multiple theft cases, and so on.

[0061] The target large language model may include a second large language model and a third large language model. The second large 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. The third large language model is a large language model trained with test point paradigm samples as training data. The test point paradigm samples may refer to test point content samples with standardized structures corresponding to different disciplines that are pre-set according to different disciplines. For example, for legal disciplines, the test point content in the corresponding test point paradigm samples may be composed of the following four contents: legal content, legal analysis, cases, and case analysis, etc. This embodiment does not limit this.

[0062] A training data set for the second largest language model can be pre-built. First, question information samples corresponding to different subjects can be obtained from a preset question bank (including historical question information). Accordingly, the test point title samples corresponding to the question information samples can be obtained through the method of generating test point titles in the aforementioned embodiment. For each subject, the question information samples and the corresponding test point information samples constitute the training data corresponding to the subject. Accordingly, for each subject's question information samples and the corresponding test point information samples, the label data corresponding to the subject is constructed: the query question sample. Afterwards, the question information samples, the corresponding test point information samples, and the corresponding query question samples of each subject constitute the training data set for each subject. The large language model is trained using this training data set to obtain the second largest language model.

[0063] In some optional embodiments, the process of training a large language model using question information samples and test point title samples as training data and query question samples as labels to obtain a second large language model may include: obtaining query question type information corresponding to multiple subjects; based on the query question type information corresponding to multiple subjects, determining corresponding query question samples for the question information samples and test point title samples corresponding to each subject; using the question information samples and test point title samples corresponding to each subject as training data and using the corresponding query question samples as labels to train the large language model to obtain a second large language model.

[0064] For example, query question type information corresponding to multiple different disciplines can be obtained. The query question type information can be characteristic information representing the discipline corresponding to the query question. The query question type information can include the question angle of the query question and the proportion of questions corresponding to each question angle. For example, for the law discipline, Figure 3B The question angles and corresponding proportions of the examples in the example are then analyzed. Based on the query question type information corresponding to each subject, query question samples corresponding to each subject are generated using the corresponding question information samples and test point title samples. Finally, the training data is composed of the corresponding question information samples and test point title samples for each subject. The large language model is fine-tuned using the corresponding query question samples as labels to obtain the second large language model.

[0065] In this embodiment, by dividing the corresponding query question type information into different subjects, and based on the query question type information corresponding to each subject, the query question samples corresponding to each subject are determined for the question information samples and test point title samples corresponding to each subject, so as to train the second largest language model, so that the second largest language model can output the corresponding query questions for different subjects more accurately and specifically.

[0066] Similarly, a training dataset for the third largest language model can be constructed in advance, and an initial note paradigm sample can be constructed; then, based on the style adjustment prompt information corresponding to each subject, the initial test point paradigm sample is adjusted through a large language model (such as ChatGPT) to obtain the test point paradigm samples corresponding to each subject. The test point paradigm samples corresponding to each subject constitute a training dataset, and the large language model is fine-tuned using this training dataset to obtain the third largest language model.

[0067] In some optional embodiments, the process of constructing the test point paradigm sample includes: obtaining an initial test point paradigm sample; adjusting the initial test point paradigm sample through a large language model based on style adjustment prompt information corresponding to multiple subjects to obtain a test point paradigm sample.

[0068] For example, when constructing test point paradigm samples, an initial test point paradigm sample can be constructed. Subsequently, corresponding style adjustment prompts can be constructed for different subjects. The style adjustment prompts are used to guide the large language model to perform style adjustments on the initial test point paradigm sample. Finally, the initial test point paradigm sample and the style adjustment prompts corresponding to each subject are input into the large language model (e.g., ChatGPT). The large language model performs style adjustments on the initial test point paradigm sample based on the style adjustment prompts, and outputs test point paradigm samples corresponding to each subject.

[0069] In this embodiment, by constructing style adjustment prompt information corresponding to multiple subjects, the initial test point paradigm samples are adjusted through the large language model to obtain test point paradigm samples corresponding to each subject, so as to train the third language model. This allows the third language model to generate test point content of corresponding styles for different subjects more accurately and specifically.

[0070] Reference Figure 3C After generating the test point title, the historical question information and the corresponding test point title can be input into the pre-trained second language model. Here, the historical answer information corresponding to the historical question information can also be input into the second language model. The historical answer information includes the answer content and the corresponding answer analysis content. This embodiment does not limit this. The second language model can be used to output multiple query questions for the historical question information. The query questions are associated with the test point information contained in the historical question information. For example, if the historical question information is a question corresponding to a legal subject, the multiple query questions may include: Q1 What laws are included, Q2 What are the cases of theft, Q3 What are the differences between the charges, and so on. Afterwards, for the multiple query questions generated, the query results for each query question can be retrieved from the pre-built subject knowledge base, such as R1, R2, R3, etc. Finally, the query results and the test point title are input into the pre-trained third language model, and the test point content corresponding to the historical question information can be generated through the third language model.

[0071] In this embodiment, by inputting historical topic information and corresponding test point titles into a pre-trained second language model, multiple query questions for the historical topic information are output; for the multiple query questions, query results for the multiple query questions are retrieved from a pre-built subject knowledge base; the query results and test point titles are input into a pre-trained third language model, and the test point content corresponding to the historical topic information is output. This allows for efficient and batch generation of test point content corresponding to historical topic information of different subjects, and since the test point content is generated through query results retrieved from a pre-built subject knowledge base, the accuracy of the test point content is improved.

[0072] In some optional embodiments, the historical topic information and the corresponding test point titles are input into a pre-trained second language model, and multiple query questions for the historical topic information are output, including: performing information retrieval based on the historical topic information and the corresponding test point titles to obtain a second search result associated with the historical topic information and the test point title; and generating query question prompt words based on the historical topic information, the test point title and the second search result; and inputting the query question prompt words into the pre-trained second language model to guide the second language model to generate multiple query questions for the historical topic information through the query question prompt words.

[0073] Analyze the historical question information and the corresponding test point titles to generate query prompt information; input the query prompt information, historical question information and the corresponding test point titles into a pre-trained second language model to output multiple query questions for the historical question information; the query prompt information is used to guide the second language model to generate multiple query questions for the historical question information.

[0074] For example, after obtaining the history question information and the corresponding test point title, the target discipline to which the history question information and the corresponding test point title belong can be determined. For each target discipline, information can be searched within the target discipline database to obtain a second search result related to both the history question information and the test point title. Then, based on the history question information, the test point title, and the second search result, a corresponding query prompt, i.e., a query prompt, is generated according to the prompt word generation rules corresponding to the target discipline. The query prompt is then input into a pre-trained second language model. Based on the query prompt, the second language model is guided to output multiple queries specific to the history question information.

[0075] In this embodiment, query prompt words are generated by analyzing the historical question information and the corresponding test point titles; the query prompt words are used to guide the second language model to generate multiple query questions for the historical question information, which can improve the accuracy of the generated query questions.

[0076] S206: Solve the subject question information to obtain targeted answer information corresponding to the subject question information.

[0077] Exemplarily, after obtaining the subject title information input by the user, targeted answer information for the subject title information can be generated. In the embodiment of the present application, there is no limitation on the specific implementation method for generating targeted answer information. Exemplarily, it can be implemented with the help of a generative language model. The generative language model is a neural network model based on deep learning. The basic architecture can include a recurrent neural network (RNN), a long short-term memory network (LSTM), and a transformer, etc. It can learn the general laws and structures of language on large-scale unlabeled text data through strategies such as pre-training and fine-tuning, and then generate text that conforms to grammatical and semantic rules based on the learned language patterns and knowledge. In the embodiment of the present application, there is no limitation on the type of generative language model used and the model structure, etc. Any suitable generative language model that can generate targeted answer information for subject title information is applicable to the solution of the embodiment of the present application.

[0078] The targeted answer information of this embodiment may include the answer content for the subject question information and may also include the corresponding answer analysis content, which is not limited in this embodiment. Taking the subject question information listed in S204 above as an example, "Solve this triangle problem: a triangle with sides of 3, 4, and 5, find the angle.", the targeted answer information may include the specific answer to the subject question information: "A triangle with sides of 3, 4, and 5 is a right triangle with angles of 36.87 degrees, 53.13 degrees, and 90 degrees, respectively." Furthermore, the targeted answer information may also include the process of solving the above specific answer.

[0079] S208. Display targeted answer information and universal test content based on subject question information.

[0080] The information processing method provided in this embodiment not only provides users with targeted answers to subject question information, but also provides users with valuable universal test point content related to the subject question information. The universal test point content includes test point explanation content for the universal test points involved in the subject question information, which can help users comprehensively and systematically grasp the common test point content involved in the subject question information to meet the user's learning needs.

[0081] In addition, the solution provided by the embodiment of the present application can provide users with targeted answers in scenarios where users are seeking specific answers to specific questions. At the same time, it can also intuitively present to users the explanation content corresponding to the universal test points (common test points) involved in the process of solving other questions in the specific subject. This avoids the user from having to perform additional question-and-answer interactive operations to seek the above-mentioned universal test points. For users, through the embodiment of the present application, it is more likely to achieve the effect of understanding a question and mastering a category of questions.

[0082] In summary, the embodiments of the present application do not require the user to perform additional operations, reduce the user's operating costs, and can meet the user's learning needs in a more efficient manner.

[0083] Optionally, in some embodiments, the process of displaying targeted answer information and universal test content for subject question information may include:

[0084] Create an answer display page, and display targeted answer information corresponding to the subject question information on the answer display page; in response to interactive operations on the targeted answer information displayed on the answer display page, pop-up a pop-up page containing universal test point content.

[0085] For example, in the above embodiment of the present application, the targeted answer information corresponding to the subject question information is first intuitively displayed on the answer display page, so that the user can quickly obtain the core information - the targeted answer to the subject question information, without having to look for the answer in the page. Furthermore, when reading the targeted answer, the user can instantly obtain the relevant test points by performing preset interactive operations on the targeted answer (for example, such as clicking on keywords in the targeted answer, clicking on preset icons, etc.), thereby effectively enhancing interactivity and learning continuity. In addition, the targeted answer is displayed in the main content area of the answer display page, and the test point explanation content is displayed in a further pop-up window display. This layout method makes the main and secondary content clear, and the user can also clearly distinguish between core information and extended information. In summary, the display method of the targeted answer information and universal test point content in the above embodiment can further enhance the user experience.

[0086] Optionally, in some embodiments, after displaying targeted answer information and universal test content for subject question information, you may also:

[0087] In response to the marking operation on the displayed targeted answer information and universal test point content, marking information is generated; based on the subject question information, targeted answer information, universal test point content and marking information, question and answer notes are generated.

[0088] Specifically, in the above-mentioned embodiment, by generating Q&A notes, users can more conveniently review and summarize the questions they asked, improving the overall user experience. Furthermore, and more importantly, by generating Q&A notes, questions, answers, test points, and tagged data can be integrated together. While reading the answers, users can quickly view related test points and their own tagged data, reducing search and organization time and improving learning efficiency.

[0089] Optionally, in some embodiments, after generating the question and answer notes, you may also:

[0090] From a 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.

[0091] Specifically, the above embodiment, after generating the corresponding question and answer notes for the subject question information input by the user, further organizes the question and answer notes, thereby merging different question and answer notes covering the same universal test point content into the same universal test point category, thereby obtaining test point category notes for the same universal test point. In this way, the user can use the test point category notes corresponding to a universal test point to conduct a detailed and systematic review of the universal test point, thereby helping the user to master the universal test point quickly and efficiently.

[0092] Figure 4 Flowchart of another information processing method according to an embodiment of the present application. According to a second aspect of the embodiment of the present application, an information processing method is provided, which is applied to a user terminal. Figure 4 As shown, the method includes steps S402, S404 and S406, specifically:

[0093] S402: In response to an input operation of the user at the user terminal, obtaining subject topic information for a preset subject input by the user.

[0094] For example, the user terminal may provide an input interface, and the user may input subject topic information through the input interface. After the user terminal detects the user's input operation, the user terminal may obtain the subject topic information input by the user.

[0095] In some optional embodiments, in response to the user's input operation on the user terminal, subject title information for a preset subject input by the user is obtained, including: in response to the user's shooting operation on the user terminal, an image containing subject title information input by the user is obtained; and information recognition is performed on the image containing subject title information to obtain the subject title information input by the user.

[0096] Exemplarily, a shooting button can be set in the input interface of the user terminal, and the user can use the shooting button to shoot the question. After the user terminal detects the user's shooting operation, the image containing the subject title information input by the user can be obtained. Thereafter, the image containing the subject title information can be identified by the user terminal, for example, multimodal information recognition can be performed, so as to obtain the subject title information contained in the image.

[0097] This embodiment can improve the user's input efficiency by providing the user with an input method of taking a photo to search for questions, facilitate the user to quickly input questions, and enhance the user experience.

[0098] In some optional embodiments, in response to the user's input operation on the user terminal, subject title information for a preset subject input by the user is obtained, including: in response to the user's text input operation on the user terminal, subject title information for a preset subject input by the user is obtained.

[0099] For example, an input box may be provided in the input interface of the user terminal, through which the user may enter question information. The user terminal then detects the text input operation in the input box and obtains the subject question information entered by the user in the input box. In this embodiment, a text input method is provided to the user, which is convenient for the user to use in various questioning scenarios and improves the user experience.

[0100] S404. Send the subject question information to the server; the server is used to parse the subject question information and determine the universal test point information involved in the solution process of the subject question information; determine the universal test point content that matches 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 and obtain targeted answer information corresponding to the subject question information.

[0101] The server of this embodiment is used to implement the corresponding information processing methods in the multiple method embodiments of the first aspect mentioned above, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0102] S406: Receive the targeted answer information and universal test point content for the subject question information returned by the server and display them.

[0103] Exemplarily, after receiving the targeted answer information and universal test point content for the subject question information returned by the server, the user terminal displays the targeted answer information and universal test point content. This embodiment does not limit the display method.

[0104] The information processing method provided by the embodiment of the present application is that after the user terminal detects the input operation of the user at 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 universal test point content that matches the universal test point information from the test point content library based on the universal test point information contained in the subject question information, and solves the subject question information to obtain targeted answer information, and returns it to the user terminal. The user terminal receives the targeted answer information and universal test point content for the subject question information returned by the server, and can display the answer to the subject question information to the user. At the same time, it also provides the user with the corresponding universal test point content. The universal test point content contains the test point explanation content corresponding to the universal test point information, thereby helping the user to comprehensively and systematically master the test point content related to the subject question information to meet the user's learning needs. In addition, there is no need for the user to perform additional operations, which reduces the user's operating costs and meets the user's learning needs in a more efficient way.

[0105] In some optional embodiments, when receiving and displaying the targeted answer information and universal test point content for the subject question information returned by the server, the method of this embodiment also includes: receiving at least one historical question information associated with the universal test point information sent by the server, and displaying the historical question information.

[0106] Specifically, when receiving the targeted answers and universal test points for the subject questions from the server, one or more historical follow-up questions associated with the universal test points can also be received from the server. Subsequently, while displaying the targeted answers and universal test points, the historical follow-up questions can also be displayed, allowing users to further select the historical follow-up questions that meet their needs for review, eliminating the need for users to repeatedly enter the same follow-up questions as those in the previous question, thus improving the user experience.

[0107] In some optional embodiments, after displaying the historical question information, the method of this embodiment further includes: in response to a user's click operation on the historical question information, obtaining historical answer information corresponding to the historical question information received in advance from the server, and displaying the historical answer information.

[0108] For example, when receiving one or more historical question information associated with universal test point information from the server, historical answer information corresponding to the historical question information may also be received. After displaying one or more historical question information, a user's click operation on the historical question information may be detected, and based on the click operation, the historical answer information corresponding to the historical question information may be further displayed, so that the user can quickly access the historical answer information corresponding to the historical question information, eliminating the need for the server to repeatedly generate answer information for the historical question information, thereby saving device resources.

[0109] Below, refer to Figure 5 The scene diagram shown in FIG. 1 is used to exemplify the overall implementation process of the information processing solution of the embodiment of the present application. Figure 5 As shown, the user captures 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, then parses the subject question information to obtain the universal test point information contained in the subject question information; then, from the test point content library, it determines the universal test point content that matches the universal test point information; the universal test point content includes test point explanation content corresponding to the universal test point information; in addition, targeted answer information for the subject question information is generated through a generative language model, that is, universal test point content and targeted answer information for the subject question information can be obtained, and the universal test point content and targeted answer information for the subject question information are returned to the user terminal. The user terminal receives the targeted answer information and universal test point content for the subject question information returned by the server and displays them on the display interface.

[0110] It should be understood that Figure 5 More details of the overall implementation process shown can also be understood in conjunction with the above embodiments, and Figure 5The overall implementation process shown is only some examples to facilitate understanding of the embodiments of the present application and does not constitute any limitation to the embodiments of the present application.

[0111] It will be understood that the above description of the information processing method is merely an exemplary description of the embodiments of the present application and does not constitute any limitation on the embodiments of the present application.

[0112] Reference Figure 6 , shows a structural block diagram of an information processing device according to an exemplary embodiment of the present application.

[0113] According to a third aspect of an embodiment 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 .

[0114] Among them, the first acquisition module 602 is used to obtain the subject question information for the preset subject input by the user; the test point matching module 604 is used to parse the subject question information and determine the universal test point information involved in the solution process of the subject question information; determine 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; the solution module 606 is used to solve the subject question information and obtain the targeted answer information corresponding to the subject question information; the first display module 608 is used to display the targeted answer information and the universal test point content for the subject question information.

[0115] In some optional embodiments, the test point matching module 604 is specifically used to: perform keyword recognition on the subject topic information to obtain first test point information; perform semantic analysis on the subject topic information to obtain second test point information; integrate the first test point information and the second test point information to determine the universal test point information involved in the subject topic information; and determine the universal test point content that matches the universal test point information from a pre-generated test point content library or a searched test point content library based on a mapping relationship between the predetermined test point information and the test point content.

[0116] In some optional embodiments, the first display module 608 is specifically used to create an answer display page, and display targeted answer information corresponding to the subject question information on the answer display page; in response to interactive operations on the targeted answer information displayed on the answer display page, a pop-up page containing universal test point content pops up.

[0117] In some optional embodiments, the information processing device also includes a note generation module for generating marking information in response to a marking operation on the displayed targeted answer information and universal test point content; and generating question and answer notes based on subject question information, targeted answer information, universal test point content and marking information.

[0118] In some optional embodiments, the note generation module is also used to: after generating the question and answer notes, determine the target question and answer notes involving the same universal test point content from a note library containing multiple question and answer notes; merge the target question and answer notes to generate test point category notes for the same universal test point content.

[0119] In some optional embodiments, the information processing device also includes: a test point content generation module, which is used to determine the test point title corresponding to the history topic information for a preset subject based on the user input; and generate the test point content corresponding to the history topic information through the target large language model based on the history topic information and the corresponding test point title.

[0120] In some optional embodiments, the test point content generation module, when executing the step of generating test point content corresponding to the historical topic information and the corresponding test point title through the target large language model, is specifically used to: search from a preset knowledge base through a retrieval enhancement generation method based on the historical topic information and the corresponding test point title, and obtain a first retrieval result associated with the historical topic information and the test point title; parse the historical topic information, the test point title and the first retrieval result, generate test point content prompt words, and input the test point content prompt words into the pre-trained target large language model, and generate test point content corresponding to the historical topic information through the target large language model.

[0121] In some optional embodiments, the test point content generation module, when executing the step of determining the test point title corresponding to the history question information for a preset subject based on the history question information input by the user, is specifically used to: obtain multiple historical question information for the history question information for a preset subject input by the user; filter the multiple historical question information through preset filtering rules to obtain filtered historical question information; the preset filtering rules are used to filter the historical question information for correlation with the historical question information and for title style; and filter the filtered historical question information through a pre-trained target classification model to obtain the test point title corresponding to the history question information.

[0122] In some optional embodiments, the test point content generation module, when executing the step of determining the test point titles corresponding to the history topic information for a preset subject based on the history topic information input by the user, is specifically used to: determine the history topic information for the preset subject input by the user, and obtain multiple test point information contained in the history topic information; input the multiple test point information into a pre-trained first large language model, and output the test point titles corresponding to the history topic 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.

[0123] In some optional embodiments, the test point content generation module, when executing the step of generating test point content corresponding to the historical topic information through the target large language model based on the historical topic information and the corresponding test point title, is specifically used to: input the historical topic information and the corresponding test point title into a pre-trained second large language model, and output multiple query questions for the historical topic information; the second large language model is a large language model trained with topic information samples and test point title samples as training data and query question samples as labels; for multiple query questions, retrieve query results for multiple query questions from a pre-built subject knowledge base; input the query results and test point titles into a pre-trained third large language model, and output test point content corresponding to the historical topic information; the third large language model is a large language model trained with test point paradigm samples as training data.

[0124] In some optional embodiments, the test point content generation module, when executing the step of inputting the historical question information and the corresponding test point title into the pre-trained second largest language model and outputting multiple query questions for the historical question information, is specifically used to: perform information retrieval based on the historical question information and the corresponding test point title to obtain a second retrieval result associated with the historical question information and the test point title; and generate query question prompt words based on the historical question information, the test point title and the second retrieval result; input the query question prompt words into the pre-trained second largest language model to guide the second largest language model to generate multiple query questions for the historical question information through the query question prompt words.

[0125] In some optional embodiments, the information processing device further includes:

[0126] The training module is used to obtain query question type information corresponding to multiple subjects; based on the query question type information corresponding to multiple subjects, the corresponding query question samples are determined for the question information samples and test point title samples corresponding to each subject; the question information samples and 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.

[0127] In some optional embodiments, the information processing device further includes:

[0128] A construction module is used to obtain an 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 a test point paradigm sample.

[0129] The information processing device of this embodiment is used to implement the corresponding information processing methods in the multiple method embodiments of the first aspect described above, and has the beneficial effects of the corresponding method embodiments, which are not described in detail here. In addition, the functional implementation of each module in the information processing device of this embodiment can refer to the description of the corresponding parts in the aforementioned method embodiments, and are not described in detail here.

[0130] Reference Figure 7 , shows a structural block diagram of an information processing device according to an exemplary embodiment of the present application.

[0131] According to a fourth aspect of 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 .

[0132] Among them, the second acquisition module 702 is used to respond to the user's input operation on the user terminal and obtain the subject question information for the preset subject input by the user; the sending module 704 is used to send the question information to the server; the server is used to parse the subject question information and determine the universal test point information involved in the solution process of the subject question information; determine 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; solve the subject question information and obtain the targeted answer information corresponding to the subject question information; the second display module 706 is used to receive the targeted answer information and universal test point content for the subject question information returned by the server, and display them.

[0133] In some optional embodiments, the second acquisition module 702 is further used to: obtain an image containing subject title information input by the user in response to a shooting operation of the user on the user terminal; perform information recognition on the image containing subject title information to obtain the subject title information input by the user.

[0134] In some optional embodiments, the second acquisition module 702 is further configured to: in response to a text input operation of the user at the user terminal, acquire subject title information for a preset subject input by the user.

[0135] In some optional embodiments, the second display module 706 is further configured to receive at least one piece of historical inquiry information associated with the universal test point information sent by the server, and display the historical inquiry information.

[0136] In some optional embodiments, the second display module 706 is further configured to: in response to a user's click operation on the historical question information, obtain historical answer information corresponding to the historical question information received in advance from the server, and display the historical answer information.

[0137] The information processing device of this embodiment is used to implement the corresponding information processing methods in the multiple method embodiments of the second aspect described above, and has the beneficial effects of the corresponding method embodiments, which are not described in detail here. In addition, the functional implementation of each module in the information processing device of this embodiment can refer to the description of the corresponding parts in the aforementioned method embodiments, and are not described in detail here.

[0138] According to the fifth aspect of the embodiments of the present application, an electronic device is provided, 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; and the processor is used to execute the information processing method of the first or second aspect mentioned above by running the computer program stored in the memory.

[0139] Figure 8 The embodiment of the present application does not limit the specific implementation of the electronic device 800. As an example, refer to Figure 8 The electronic device 800 provided in the embodiment of the present application includes: a processor 802, a communication interface 804, a memory 806, and a communication bus 808.

[0140] The processor 802 , the communication interface 804 , and the memory 806 communicate with each other via a communication bus 808 .

[0141] The communication interface 804 is used to communicate with other electronic devices or servers.

[0142] The processor 802 is configured to execute the computer program 810 , and specifically may execute the relevant steps in any of the aforementioned information processing method embodiments.

[0143] Specifically, the computer program 810 may include program codes including computer operation instructions.

[0144] Processor 802 may be a CPU, a Graphics Processing Unit (GPU), an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0145] The memory 806 is used to store the computer program 810. The memory 806 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0146] The computer program 810 may be specifically configured to enable the processor 802 to execute the information processing method in any of the aforementioned embodiments.

[0147] The specific implementation of each step in computer program 810 can be found in the corresponding descriptions of the corresponding steps and units in any of the aforementioned information processing method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, the specific working processes of the devices and modules described above can refer to the corresponding process descriptions in the aforementioned method embodiments, and will not be repeated here.

[0148] The electronic device 800 in the embodiment of the present application has been described in detail in the aforementioned information processing method embodiment, so its relevant content and beneficial effects can be understood with reference to the aforementioned method embodiment and will not be repeated here.

[0149] According to a sixth aspect of the embodiments of the present application, the embodiments of the present application further provide a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the information processing method described in any of the aforementioned method embodiments. The computer storage medium includes, but is not limited to, a compact disc read-only memory (CD-ROM), random access memory (RAM), a floppy disk, a hard disk, or a magneto-optical disk.

[0150] According to the seventh aspect of the embodiments of the present application, the embodiments of the present application also provide a computer program product, including a computer program, which, when executed by a processor, implements the information processing method described in any one of the above-mentioned multiple method embodiments.

[0151] The electronic device 800 / computer storage medium / computer program product embodiment in the embodiment of the present application has been described in detail in the aforementioned information processing method embodiment, so its relevant content and beneficial effects can be understood with reference to the above-mentioned method embodiment and will not be repeated here.

[0152] In addition, it should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used for model training, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0153] It should be pointed out that, according to the needs of implementation, the various components / steps 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.

[0154] The methods according to the embodiments of the present application described above can be implemented in hardware, firmware, or 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 as computer code originally stored in a remote recording medium or non-transitory machine-readable medium downloaded via a network and then stored in a local recording medium. Thus, the methods described herein can be stored in such software processing 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 will be understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component (e.g., random access memory (RAM), read-only memory (ROM), flash memory, etc.) that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods described herein are implemented. Furthermore, when a general-purpose computer accesses the code for implementing the methods described herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the methods described herein.

[0155] Those skilled in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for specific applications, but such implementation should not be considered to be beyond the scope of the embodiments of this application.

[0156] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". It should be noted that the concepts of "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 "multiple" mentioned in the embodiments of the present application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0157] The above implementation methods are only used to illustrate the embodiments of the present application, and are not intended to limit the embodiments of the present application. Ordinary technicians in the relevant technical field can 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 fall within the scope of the embodiments of the present application, and the scope of patent protection of the embodiments of the present application should be defined by the claims.

Claims

1. An information processing method, comprising: Obtain subject title information for preset subjects input by the user; Analyzing the subject question information and determining universal test point information involved in the solution process of the subject question information; Determining target history topic information that matches the universal test point information; determining, based on a predetermined mapping relationship between the history topic information and the test point content, from a pre-generated test point content library, the test point content corresponding to the target history topic information as the universal test point content that matches the universal test point information; Solve the subject question information to obtain targeted answer information corresponding to the subject question information; For the subject question information, display the targeted answer information and the universal test content; The test point content generation process in the test point content library includes: determining the test point title corresponding to the history topic information for the preset subject input by the user; performing information retrieval based on the history topic information and the corresponding test point title to obtain a second search result associated with the history topic information and the test point title; generating query question prompt words based on the history topic information, the test point title and the second search result; inputting the query question prompt words into a pre-trained second language model to guide the second language model to generate multiple query questions for the history topic information through the query question prompt words; for multiple query questions, retrieving query results for the multiple query questions from a pre-built subject knowledge base; inputting the query results and the test point title into a third language model to output the test point content corresponding to the history topic information.

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 question information to obtain first test point information; perform semantic analysis on the subject question 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.

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: generating marking information in response to a marking operation on the displayed targeted answer information and the universal test point content; 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 covering the same universal test points; 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 Generating the test point content corresponding to the historical topic information by using a target large language model according to the historical 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 historical 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 historical question information through the target large language model.

7. The method according to claim 1, wherein The step of determining, based on the history topic information for the preset subject input by the user, a test point title corresponding to the history topic information, includes: Acquire multiple pieces of historical inquiry information for the history 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 question 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.

8. The method according to claim 1, wherein The step of determining, based on the history topic information for the preset subject input by the user, a test point title corresponding to the history topic information, includes: Determining the history question information for the preset subject input by the user, and obtaining multiple test point information included 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.

9. The method according to claim 1, wherein The method further comprises: Obtain query question type information corresponding to multiple disciplines; 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 question information samples and the test point title samples corresponding to each subject are used as training data, and the large language model is trained with the corresponding query question samples as labels to obtain the second large language model.

10. The method according to claim 1, wherein The third language model is a large language model trained using test point paradigm samples as training data. The construction process of the test point paradigm samples includes: Obtaining initial test point paradigm samples; 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.

11. 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 topic information for a preset subject input by the user; Sending the subject topic information to the server; The server is configured to parse the subject question information, determine universal test point information involved in a process of solving the subject question information, determine target history question information that matches the universal test point information, determine, based on a predetermined mapping relationship between history question information and test point content, from a pre-generated test point content library that the test point content corresponding to the target history question information is the universal test point content that matches the universal test point information, solve the subject question information, and obtain 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; The test point content generation process in the test point content library includes: performing information retrieval based on historical topic information and corresponding test point titles to obtain a second search result associated with the historical topic information and the test point title; generating query question prompt words based on the historical topic information, the test point title and the second search result; inputting the query question prompt words into a pre-trained second language model to guide the second language model to generate multiple query questions for the historical topic information through the query question prompt words; for multiple query questions, retrieving query results for multiple query questions from a pre-built subject knowledge base; inputting the query results and the test point title into a third language model to output the test point content corresponding to the historical topic information.

12. The method according to claim 11, wherein The step of obtaining subject topic information for a preset subject input by the user in response to an input operation of the user on the user terminal includes: In response to a shooting operation of the user on the user terminal, acquiring an image input by the user containing subject topic information; Information recognition is performed on the image containing the subject title information to obtain the subject title information input by the user.

13. The method according to claim 11, wherein The step of obtaining subject topic information for a preset subject input by the user in response to an input operation of the user on the user terminal includes: In response to a text input operation of the user on the user terminal, subject title information for a preset subject input by the user is obtained.

14. The method according to any one of claims 11 to 13, 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.

15. The method according to claim 14, 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.

16. 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 15 by running the computer program stored in the memory.

17. 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 15 is implemented.

18. A computer program product comprising computer instructions, wherein the computer instructions instruct a computing device to execute the method according to any one of claims 1 to 15.

Images