Data processing method and system, and computing device, electronic device and storage medium

Abstract

The present disclosure relates to the fields of large model technology and intelligent tutoring. Provided are a data processing method and system, and a computing device, an electronic device and a storage medium. The method comprises: acquiring query data; on the basis of the type of a first subject corresponding to the query data, determining a target agent corresponding to the query data; and when the type of the first subject is a preset type, determining question data in the query data, and using the target agent to perform data generation on the question data to obtain first response data, wherein the first response data comprises first guidance data, and the first guidance data is used for guiding the first subject to determine answer data corresponding to the question data. The present disclosure solves the technical problem in the related art of low efficiency in communication and interaction during the process of teachers instructing students.

Description

Data processing methods, systems, computing devices, electronic devices and storage media Technical Field

[0001] This disclosure relates to artificial intelligence technology and the field of intelligent teaching aids. Specifically, it relates to a data processing method, system, computing device, electronic device, and storage medium. Background Technology

[0002] In traditional teaching scenarios, one teacher typically instructs multiple students. This model can have some problems. For example, it is difficult for the teacher to attend to each student's questions and responses, and it is also difficult to obtain timely feedback. Teachers need to rely on assignments and tests to understand the class's learning progress.

[0003] Specifically, students typically passively receive knowledge, simply listening to lectures and lacking opportunities for active learning. This can easily lead to a lack of initiative and creativity, making it difficult for them to truly understand and apply the knowledge they learn. Because the classroom involves one-way knowledge transmission from the teacher, it's difficult to stimulate students' interest, resulting in low motivation and a tendency towards learning fatigue and aversion to learning. Furthermore, because teachers face multiple students, it's difficult to meet the individualized learning needs of each student, leading to poor learning outcomes. In summary, this results in low efficiency of communication and interaction between teachers and students in related technologies.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This disclosure provides a data processing method, system, computing device, electronic device, and storage medium to at least address the technical problem of low efficiency in communication and interaction between teachers and students during teaching in related technologies.

[0006] According to one aspect of the present disclosure, a data processing method is provided, the method comprising: acquiring query data; determining a target agent corresponding to the query data based on the type of a first object corresponding to the query data; if the type of the first object is a preset type, determining question data in the query data, and using the target agent to generate data from the question data to obtain first response data, wherein the first response data includes first guidance data, the first guidance data being used to guide the first object to determine the answer data corresponding to the question data.

[0007] According to another aspect of the embodiments of this disclosure, a data processing method is also provided, the method comprising: acquiring query data; determining a target intelligent agent corresponding to the query data based on the type of a first object corresponding to the query data; if the type of the first object is a type of teaching object, determining a teaching problem in the query data, and using the target intelligent agent to generate data for the teaching problem to obtain first response data, wherein the first response data includes a problem-solving approach corresponding to the teaching problem.

[0008] According to another aspect of the embodiments of this disclosure, a data processing method is also provided, the method comprising: responding to an input command applied to an operation interface, determining query data corresponding to the input command; determining a target intelligent agent corresponding to the query data based on the type of a first object corresponding to the query data; if the type of the first object is a preset type, determining question data in the query data, and using the target intelligent agent to generate data from the question data to obtain first response data, wherein the first response data includes first guidance data, the first guidance data being used to guide the first object to determine the answer data corresponding to the question data; and outputting the first response data.

[0009] According to another aspect of the embodiments of this disclosure, a data processing method is also provided, the method comprising: acquiring query data by calling a first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter includes the query data; determining a target agent corresponding to the query data based on the type of a first object corresponding to the query data; if the type of the first object is a preset type, determining question data in the query data, and using the target agent to generate data on the question data to obtain first response data, wherein the first response data includes first guidance data, the first guidance data being used to guide the first object to determine the answer data corresponding to the question data; and outputting the first response data by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter includes the first response data.

[0010] According to another aspect of the embodiments of this disclosure, a data processing system is also provided, the system comprising: a client configured to send query data; a server connected to the client configured to determine a target agent corresponding to the query data based on the type of a first object corresponding to the query data, and, if the type of the first object is a preset type, determine question data in the query data, and use the target agent to generate data from the question data to obtain first response data, wherein the first response data includes first guidance data, the first guidance data being used to guide the first object to determine the answer data corresponding to the question data; the client is further configured to output the first response data.

[0011] According to another aspect of the present disclosure, a computing device is also provided, including: a memory storing an executable program; and a processor configured to run the program, wherein the program executes the methods in various embodiments of the present disclosure when it runs.

[0012] According to another aspect of the present disclosure, an electronic device is also provided, including: a memory storing an executable program; and a processor connected to the memory via a bus and configured to run the program, wherein the program executes the methods in various embodiments of the present disclosure when it runs.

[0013] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of the various embodiments of the present disclosure.

[0014] According to another aspect of the embodiments of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this disclosure.

[0015] According to another aspect of the embodiments of this disclosure, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods in various embodiments of this disclosure.

[0016] According to another aspect of the embodiments of this disclosure, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this disclosure.

[0017] In this embodiment, query data is acquired; based on the type of the first object corresponding to the query data, a target intelligent agent corresponding to the query data is determined; if the type of the first object is a preset type, question data in the query data is determined, and the target intelligent agent is used to generate data from the question data to obtain first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data. It is noteworthy that this disclosure can provide personalized intelligent education services according to the needs and characteristics of different objects, including personalized teaching guidance, learning content, learning plans, and learning methods. The generated first guidance data can guide the first object to determine the answer data corresponding to the question data. This answer data can be related to knowledge points, solution ideas, or solution processes for similar questions in the user's query data. In particular, it can cultivate the user's self-learning ability, allowing the user to understand knowledge points more deeply in the process of finding answers and cultivate problem-solving abilities. This makes the application of intelligent agents in the field of education more educational, thereby solving the technical problem of low efficiency in communication and interaction between teachers and students in related technologies.

[0018] It is worth noting that the above general description and the following detailed description are merely for illustrative and explanatory purposes and do not constitute a limitation thereof. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0020] Figure 1 is a schematic diagram of an application scenario of a data processing method according to an embodiment of the present disclosure;

[0021] Figure 2 is a flowchart of a data processing method according to an embodiment of the present disclosure;

[0022] Figure 3 is a schematic diagram of an optional data processing method for implementing intelligent teaching aid interaction according to an embodiment of the present disclosure;

[0023] Figure 4 is a schematic diagram of an optional data processing method according to an embodiment of the present disclosure applied to an intelligent teaching aid scenario;

[0024] Figure 5 is a flowchart of an optional data processing method according to an embodiment of the present disclosure;

[0025] Figure 6 is a flowchart of another optional data processing method according to an embodiment of the present disclosure;

[0026] Figure 7 is a flowchart of another optional data processing method according to an embodiment of the present disclosure;

[0027] Figure 8 is a schematic diagram of a data processing system according to an embodiment of the present disclosure;

[0028] Figure 9 is a structural block diagram of a computing device according to an embodiment of the present disclosure.

[0029] Figure 10 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] The technical solution disclosed herein is primarily implemented using large-scale model technology. Here, "large-scale model" refers to a deep learning model with a massive number of parameters, typically containing hundreds of millions, tens of billions, hundreds of billions, trillions, or even tens of trillions of parameters. Large-scale models, also known as foundation models, are pre-trained using large-scale unlabeled corpora to produce pre-trained models with hundreds of millions of parameters. These models are adaptable to a wide range of downstream tasks and exhibit good generalization ability. Examples include Large Language Models (LLMs) and multi-modal pre-training models.

[0033] It's important to note that in practical applications, large models can be fine-tuned using a small number of samples after pre-training, allowing them to be applied to various tasks. For example, large models can be widely used in Natural Language Processing (NLP), computer vision, and speech processing. Specifically, they can be applied to computer vision tasks such as Visual Question Answering (VQA), Image Captioning (IC), and Image Generation, as well as NLP tasks such as text-based sentiment classification, text summarization, and machine translation. Therefore, the main application scenarios for large models include, but are not limited to, digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design.

[0034] According to embodiments of this disclosure, a data processing method is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Considering the large number of model parameters in the large model and the limited computing resources of mobile terminals, the data processing method provided in this disclosure can be applied to the application scenario shown in Figure 1, but is not limited thereto. In the application scenario shown in Figure 1, the large model is deployed on server 10. Server 10 can connect to one or more client devices 20 via a local area network (LAN), wide area network (WAN), Internet, or other types of data networks. These client devices 20 may include, but are not limited to, smartphones, tablets, laptops, PDAs, personal computers, smart home devices, and in-vehicle devices. Client devices 20 can interact with users through a graphical user interface to invoke the large model, thereby implementing the method provided in this disclosure.

[0036] In this embodiment, the system comprising a client device and a server can perform the following steps: the client device can interact with the server; the server can acquire query data; based on the type of a first object corresponding to the query data, the target agent corresponding to the query data is determined; if the type of the first object is a preset type, the question data in the query data is determined, and the target agent is used to generate data from the question data to obtain first response data. It should be noted that this embodiment can be performed on the client device if the client device's operating resources can meet the deployment and operation conditions of a large model.

[0037] In the above operating environment, this disclosure provides a data processing method as shown in Figure 2. Figure 2 is a flowchart of a data processing method according to an embodiment of this disclosure. As shown in Figure 2, it may specifically include the following steps:

[0038] Step S202: Obtain query data.

[0039] The aforementioned query data can refer to query statements input by the user into the system. Query data can be data input by the user into the system in the form of voice, text, images, and documents. The specific content and format of the query data can be determined according to actual needs and are not limited here.

[0040] In one optional embodiment, query data can be obtained based on user input into the system in the form of voice, text, images, and documents. By obtaining query data, the system can better understand the user's needs and questions, thereby providing personalized teaching and learning solutions, improving teaching effectiveness, enhancing the level of intelligence in education and teaching, and facilitating the provision of more intelligent learning and teaching support services to users.

[0041] Step S204: Based on the type of the first object corresponding to the query data, determine the target intelligent agent corresponding to the query data.

[0042] The first object mentioned above can refer to the object that submits the data. The type of the first object can include, but is not limited to, teachers, students, parents, etc. Specifically, teachers, students, parents, etc. can be further identified and distinguished, which can be determined according to the actual situation, and is not limited here.

[0043] The aforementioned target intelligent agent can refer to different intelligent agents determined based on the type of the first object. For example, when the type of the first object is a teacher, the target intelligent agent can be a teaching assistant intelligent agent; when the type of the first object is a student, the target intelligent agent can be an intelligent teacher intelligent agent; when the type of the first object is a parent, the target intelligent agent can be an intelligent agent serving the parent. Specifically, for different students, etc., it can also be different intelligent teacher intelligent agents, etc. The target intelligent agent can be determined according to actual needs, and there is no limitation here.

[0044] In one optional embodiment, the target intelligent agent corresponding to the query data can be determined based on the type of the first object corresponding to the query data. Specifically, a relationship model between relevant objects can be pre-established, which may include the relationships between teachers, students, and parents, as well as their relationships with educational resources and course content. Simultaneously, a relationship model between the target intelligent agent and these objects can also be pre-established to accurately determine the target intelligent agent corresponding to the query data. This disclosure can utilize data mining and machine learning methods to analyze and process the query data, extracting the type of the corresponding first object, such as teacher, student, or parent, eliminating the need for user identity selection during use. Based on the pre-established relationship model and the trained machine learning model, the corresponding target intelligent agent, such as an intelligent teaching aid agent or an intelligent teacher agent, can be quickly determined according to the type of the first object corresponding to the query data. This enables the system to quickly and accurately determine the corresponding target intelligent agent based on the type of the first object corresponding to the query data, thereby realizing personalized intelligent services in the field of intelligent teaching aids.

[0045] This disclosure, by identifying the target intelligent agent corresponding to the query data, enables the provision of personalized intelligent education services based on the needs and characteristics of different individuals. These services include personalized teaching guidance, learning content, learning plans, and learning methods. Addressing the diverse needs of teachers, students, and parents, the system can provide targeted teaching resources and guidance, thereby improving teaching efficiency and quality. Based on the identified target intelligent agent, the system can provide intelligent decision support, including intelligent suggestions and guidance on teaching decisions, learning planning, and parental guidance. This enables the realization of personalized customization, improved teaching efficiency, resource integration and optimization, and intelligent decision support in the field of smart education, thereby promoting the intelligent and personalized development of education.

[0046] Step S206: If the type of the first object is a preset type, determine the question data in the query data, and use the target intelligent agent to generate data from the question data to obtain the first response data.

[0047] The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data.

[0048] The preset type mentioned above can refer to the student type, or it can refer to the ordinary user who needs to ask questions to get answers, etc. The preset type can be determined according to actual needs, and there is no limitation here.

[0049] The aforementioned first guiding data may refer to knowledge points, solutions, or solutions to similar questions related to the questions raised by students, or it may be terms, definitions, or multimedia data such as pictures and videos that guide users to solve problems. The first guiding data can be used to guide the first object to obtain the answer corresponding to the question data.

[0050] In one optional embodiment, question data can be identified from the query data, and a target intelligent agent can be used to generate data from the question data to obtain first response data. This can be achieved using technologies such as natural language processing (NLP), knowledge graphs, and machine learning. Specifically, firstly, identifying question data from the query data can be done using NLP techniques. NLP can understand and process text and speech data. When identifying question data from the query data, NLP techniques can be used to perform word segmentation, part-of-speech tagging, and syntactic analysis on the input text to accurately extract the question data. Secondly, generating data from the question data using the target intelligent agent can combine knowledge graphs and machine learning techniques. Knowledge graphs can contain rich entities and relationships, which can help the intelligent agent understand and generate first response data from the question data. Knowledge points and relationships in the knowledge graph can be used to guide the intelligent agent in generating data from the question data. Machine learning techniques can also be used to train the intelligent agent's ability to generate question data, such as using generative adversarial networks (GANs) to generate context-appropriate response data. The determined first response data may include first guiding data, which guides the first user to determine the answer data corresponding to the question data. This first guiding data may be knowledge points, solution approaches, or solution processes for similar questions related to the question data in the user's query data. When determining the first guiding data, natural language processing technology can be used to perform semantic analysis on the text in the knowledge base, thereby extracting knowledge points and solution approaches related to the question data.

[0051] In the above process, the query data can be the user's natural language data, and the question data can be data with substantial content or clear meaning from the query data. By processing the input query data through word segmentation, part-of-speech tagging, and syntactic analysis, the question data can be extracted. Knowledge points and relationships in a knowledge graph are used to guide the agent in generating question data. Machine learning techniques, such as generative adversarial networks, are used to train the agent's ability to generate question data. Finally, natural language processing techniques are used to perform semantic analysis on the text in the knowledge base to extract knowledge points and solution strategies related to the question data. Combining knowledge graphs and machine learning techniques allows the agent to generate more targeted and flexible question data, enabling it to generate appropriate responses based on different question data. In particular, it can cultivate users' self-learning abilities, allowing them to gain a deeper understanding of knowledge points and develop problem-solving skills while searching for answers, making the application of intelligent agents in the education field more educationally meaningful.

[0052] In this embodiment, query data is acquired; based on the type of the first object corresponding to the query data, a target intelligent agent corresponding to the query data is determined; if the type of the first object is a preset type, question data in the query data is determined, and the target intelligent agent is used to generate data from the question data to obtain first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data. It is noteworthy that this disclosure can provide personalized intelligent education services according to the needs and characteristics of different objects, including personalized teaching guidance, learning content, learning plans, and learning methods. The generated first guidance data can guide the first object to determine the answer data corresponding to the question data. This answer data can be related to knowledge points, solution ideas, or solution processes for similar questions in the user's query data. In particular, it can cultivate the user's self-learning ability, allowing the user to understand knowledge points more deeply in the process of finding answers and cultivate problem-solving abilities. This makes the application of intelligent agents in the field of education more educational, thereby solving the technical problem of low efficiency in communication and interaction between teachers and students in related technologies.

[0053] In the above embodiments of this disclosure, the target intelligent agent generates data from the question data to obtain first response data, including: generating first prompt information based on the question data, wherein the first prompt information is used to prompt the target intelligent agent to generate first guidance data and prohibit the generation of answer data; inputting the first prompt information to the target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain first response data.

[0054] In one optional embodiment, a first prompt message can be generated based on the question data using natural language processing techniques and machine learning algorithms. This prompt message can employ techniques such as text generation, answer derivation, or knowledge graph retrieval. The first prompt message can be guiding, prompting the target agent to generate first guiding data and prohibiting the direct generation of answer data. The first prompt message can be input into the target agent, which then generates first response data based on the question data. The target agent can utilize natural language generation models, knowledge graph retrieval, text reasoning, and other techniques to generate the first guiding data. The first guiding data can be knowledge points, solution approaches, or solutions to similar questions related to the question data in the user's query data, used to guide the first user to obtain the answer corresponding to the question data, rather than directly providing the answer.

[0055] In this process, by generating initial guiding data, the target agent can provide guided responses to user questions instead of directly providing answers. This helps users better understand the essence of the problem and the thought process behind the solution, improving learning effectiveness. The target agent can generate different initial guiding data based on different user questions, thereby achieving personalized responses. This better meets user needs and improves the user experience.

[0056] In the above embodiments of this disclosure, the method further includes: generating second prompt information based on question data, wherein the second prompt information is used to indicate the logical rules and relationships between question data and answer data; inputting first prompt information to a target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain first response data, including: inputting first prompt information and second prompt information to a target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain first response data.

[0057] The aforementioned second prompt can refer to a prompt message used in additional information to suggest that the target agent improve the quality of its response by using Thoughts on Thoughts (ToT) thinking chains and Goals-oriented Thinking (GoT) mind maps.

[0058] In one optional embodiment, generating a second prompt based on the question data can improve the quality of the agent's response. By inputting the second prompt into the target agent, the agent can better understand the logical rules and relationships between the question data and the answer data, thereby improving the accuracy and relevance of the response. Specifically, firstly, a knowledge base containing question and answer data can be pre-built. This knowledge base can include knowledge from various fields, such as mathematics, physics, and history. Then, a second prompt can be generated based on the question data; for example, the prompt can be generated according to the logical rules and relationships between the question and answer data. The prompt can include ToT thinking chains and GoT thinking maps to guide the agent in thinking about solutions to the problem. Next, the first and second prompts can be input into the target agent, which then uses the question data to generate the first response data. The target agent can generate the first response data based on the question data and the prompt, including knowledge points related to the question data in the user's query data, solution ideas, or the solution process for similar questions. The target agent outputs the generated first response data to the user, guiding the user to obtain the answer corresponding to the question data. In the above process, introducing a second prompt can help the agent better understand the logical rules and relationships between the problem data, improve the accuracy and relevance of the response, and thus enhance the user experience and learning effect.

[0059] In the above embodiments of this disclosure, when the type of the first object is not a preset type, the method further includes: obtaining target dialogue data of at least one historical object associated with the first object from the database based on the identification information of the first object, wherein the target dialogue data includes historical query data and historical response data of at least one historical object, and the historical response data is data obtained by using a historical agent to generate data from the historical query data; inputting the query data and target dialogue data into the target agent, and using the target agent to generate second response data, wherein the second response data includes historical query data, historical response data and second guidance data, and the second guidance data is used to guide the first object to provide guidance to at least one historical object.

[0060] In one optional embodiment, target dialogue data of historical objects associated with the first object can be retrieved from the database based on the identification information of the first object, which can help improve the teaching efficiency and personalized teaching level of teachers. Specifically, firstly, the system can retrieve historical objects associated with the current teacher, such as the historical dialogue data of each student in the class, from the database based on the identification information such as the current teacher's identity identifier (ID). The target dialogue data can include historical inquiry data and historical response data of the historical objects. Historical inquiry data can be questions or needs raised by students in the past, and historical response data can be responses from the system or teacher to these questions. This data can help the intelligent agent better understand the needs and questions of students. Next, the inquiry data and target dialogue data can be input into the target intelligent agent. The target intelligent agent can generate second response data by learning the patterns and rules in the historical dialogue data. The second response data can include historical inquiry data, historical response data, and second guidance data, which are used to guide the teacher in instructing students. The second guidance data can be intelligent teaching assistance suggestions, such as providing corresponding solutions or suggestions for the questions raised by students. This guidance data can help teachers better understand the needs of students and provide more effective teaching guidance.

[0061] In the above process, by analyzing students' historical dialogue data, the intelligent agent can better understand students' learning situations and needs, thereby providing personalized teaching suggestions and guidance to each student. Based on patterns and regularities in historical dialogue data, the intelligent agent can quickly generate response data and provide corresponding teaching suggestions, helping teachers resolve students' problems more quickly. Through guidance data, the intelligent agent can provide teachers with timely and targeted teaching suggestions, helping them better guide students, improve teaching effectiveness, and thus enhance teachers' teaching efficiency, personalized teaching level, and real-time guidance capabilities. This helps teachers better understand students' needs, provide more effective teaching guidance, and ultimately improve the overall teaching quality.

[0062] In the above embodiments of this disclosure, generating second response data using a target intelligent agent includes: analyzing target dialogue data using the target intelligent agent to generate an object profile of at least one historical object; and generating second response data using the object profile of at least one historical object and query data using the target intelligent agent.

[0063] In one alternative embodiment, a second response data can be generated using a target intelligent agent. This process may include analyzing target dialogue data to generate an object profile of at least one historical object, and then using these object profiles to generate the second response data. Specifically, first, target dialogue data can be collected and preprocessed. This dialogue data may be interactive dialogues between students and educational robots or intelligent teaching aids systems, including questions and answers. Data preprocessing may include noise removal, text tokenization, etc. Next, the target intelligent agent can analyze the target dialogue data to identify important information and patterns. Then, an object profile of at least one historical object can be analyzed and generated using the target intelligent agent. The object profile may include information such as learning progress and knowledge gaps. This information can help the system better understand the learning status and needs of the object. Finally, the generated object profile and query data, combined with the analytical capabilities of the target intelligent agent, can be used to generate the second response data. This data may be personalized suggestions, explanations, or guidance for the historical object, helping the object to better learn and master knowledge.

[0064] In the aforementioned process, the specific implementation of generating second response data using the target intelligent agent helps the intelligent teaching aid system better understand the needs of the learners and provide personalized learning support and guidance. By analyzing the learners' historical learning progress and weaknesses in knowledge points, the system can provide personalized learning support and suggestions to each learner, helping them better understand and master knowledge. Personalized learning support and guidance can improve the user experience, making learners more willing to use the intelligent teaching aid system for learning, thereby enhancing their learning enthusiasm and motivation.

[0065] In the above embodiments of this disclosure, the database also stores the storage time of different dialogue data; based on the identification information of the first object, obtaining the dialogue data of at least one historical object associated with the first object from the database includes: obtaining the dialogue data whose storage time is within a preset time period from the database to obtain initial dialogue data; and determining the target dialogue data from the initial dialogue data based on the identification information of the first object.

[0066] In one optional embodiment, dialogue data stored in a database can be used to assist the first subject in learning and provide personalized educational guidance. Specifically, the database stores the storage time of different dialogue data, which may include dialogues between students and teachers, dialogues between students, etc. Based on the first subject's identification information, the system can retrieve dialogue data of at least one historical subject associated with the first subject from the database. This dialogue data can help the system better understand the first subject's learning background, learning interests, and other information. Next, the system can filter dialogue data stored within a preset time period, such as the last 12 hours, to obtain initial dialogue data. This data may include recent learning progress, problem discussions, etc., helping the system to more accurately understand the first subject's current learning status. The preset time period can also be determined according to actual needs and is not limited here. Next, the system can determine target dialogue data from the initial dialogue data based on the first subject's identification information. The target dialogue data may be dialogue data related to the first subject's current learning content or dialogue data related to the first subject's learning needs. This data can help the system provide personalized educational guidance to the first subject, accurately answer questions, and guide learning.

[0067] Through the above steps, the system can better understand the learning needs and status of the first learner, providing personalized educational guidance. The system can perform data analysis and mining based on historical and current dialogue data to provide more accurate and effective learning suggestions. By acquiring dialogue data stored within a preset time period, the system can promptly understand the first learner's learning status and provide timely feedback and guidance. The system can also perform data analysis and mining based on historical and current dialogue data to provide more in-depth learning suggestions, thereby better understanding the first learner's learning needs and status, providing personalized educational guidance, and ultimately improving teaching effectiveness and user experience.

[0068] In the above embodiments of this disclosure, when the type of the first object is a preset type, the method further includes: determining a second object that is associated with the first object; generating current dialogue data based on the query data and the first response data; and storing the current dialogue data and the identification information of the second object in a database.

[0069] In one optional embodiment, a second object associated with the first object can be identified, and the dialogue data and the identification information of the second object can be stored in a database. Specifically, a data storage database system can be pre-established to store students' personal information, dialogue data, and relationships between students. The database system can use a relational database or a non-relational database, selecting the appropriate database technology according to specific needs. Secondly, natural language processing (NLP) technology can be used to analyze the dialogue data and extract key information. By analyzing the dialogue content between students, their relationships can be determined. NLP technology includes lexical analysis, syntactic analysis, and semantic analysis, which can help the system understand the dialogue content between students. Next, machine learning technology can be used to build a model of the relationships. Through supervised or unsupervised learning methods, the model can be trained to identify relationships between students. Machine learning technology can help the system learn from large amounts of dialogue data, finding patterns and rules hidden in the data. Based on the query data and the first response data, the system can generate current dialogue data based on the user's input and the system's response. The current dialogue data can include the user's question, the system's response, and other contextual information, taking into account the user's profile and historical dialogue records, allowing the system to generate more personalized answers and improve the user experience. Finally, the current dialogue data and the identification information of the second participant can be stored in the database. By storing the dialogue data and student identification information in a corresponding manner, the system can easily retrieve and analyze the data when needed. At the same time, the establishment of the database also provides basic data support for subsequent intelligent teaching support systems.

[0070] In the aforementioned process, by identifying the relationships between students, the system can better understand their needs and provide more personalized learning guidance and suggestions. Determining these relationships promotes interaction and communication among students, enhancing the learning atmosphere and improving learning outcomes. Simultaneously, analyzing these relationships allows for better allocation of teaching resources, improving resource utilization efficiency, and consequently, enhancing the system's personalized service level. This further promotes student interaction and communication, optimizes the allocation of teaching resources, and ultimately improves the overall effectiveness and user experience of the intelligent teaching support system.

[0071] In the above embodiments of this disclosure, determining the target intelligent agent corresponding to the query data based on the type of the first object corresponding to the query data includes: determining the current network environment of the first object; determining whether the first object meets preset conditions based on the network environment; and determining the target intelligent agent based on the type of the first object if it is determined that the first object meets the preset conditions.

[0072] In one optional embodiment, determining the current network environment of the first object can be achieved through network monitoring technology. This involves monitoring the network the first object is connected to to determine its environment. For example, parameters such as network bandwidth and latency can be detected to assess the quality of the network environment. If the first object is in a cloud education desktop environment, it may have higher bandwidth and lower latency, thus better supporting online learning and educational activities. Next, determining whether the first object meets preset conditions based on the network environment is to ensure that the first object can normally access and use related services. For example, if a condition is set that educational resources can only be accessed in a cloud education desktop environment, network environment detection can confirm whether the first object meets this condition. This can be achieved through technologies such as network access authentication and network address filtering. If the first object meets the preset conditions, the target intelligent agent can be determined based on the type of the first object to provide personalized intelligent education services for different types of users. For example, for users of different ages and with different learning needs, corresponding intelligent auxiliary teaching can be provided based on their specific learning interests and levels. This can be achieved through technologies such as user profiling and data mining.

[0073] Through the above process, personalized services can be achieved by the intelligent education system, improving users' learning outcomes and experience. Monitoring the network environment ensures users can learn in a stable network environment, avoiding interruptions and negative experiences caused by network problems. Determining whether users meet preset conditions ensures that only eligible users can access relevant educational resources, guaranteeing resource security and effective utilization. This, combined with the personalized services of the intelligent education system, further enhances users' learning outcomes and experience.

[0074] The technical solution proposed in this disclosure is described below with reference to an optional embodiment. This disclosure proposes an AI-powered teaching aid solution based on a cloud classroom. It proposes an AI teaching solution that, in a cloud-based teaching scenario, constructs an AI-powered teaching system based on the teacher-student relationship and educational model in a cloud computer lab. This system supports Socratic guided questioning on the student side and generates class and student question profiles on the teacher side. This helps improve students' problem-solving habits and facilitates teachers' control over teaching progress and questions, ultimately improving teaching quality.

[0075] In this disclosure, "cloud classroom" can refer to a cloud-based educational scenario-based solution that provides end-to-end cloud-based classroom management capabilities; "intelligent assistant" can refer to a cloud-based artificial intelligence platform that can provide basic AI Global Communication (GC) services and customized capabilities for educational individuals and enterprises; "AI teacher" can refer to the intelligent assistant function on the student's end, providing guided answers to students' classroom questions; and "AI teaching assistant" can refer to the intelligent assistant function on the teacher's end, which summarizes student questions, forms student profiles, and provides teaching guidance.

[0076] The cloud classroom disclosed herein can be integrated with artificial intelligence capabilities to build AI-powered teaching scenarios, providing each student's computer with its own AI teacher tools to answer questions. Teachers can easily obtain class-level learning progress and provide targeted instruction based on key issues and student weaknesses.

[0077] For students, their computers can be pre-installed with AI teacher capabilities. Students can consult with these AI teachers about problems and difficulties. The AI ​​teachers will provide problem-solving strategies rather than giving answers, thus preventing students from using AI to cheat. As usage increases, individual student learning profiles, such as learning progress and areas of weakness, will become increasingly clear.

[0078] For teachers, AI-powered teaching aids can be used. These aids come pre-installed with AI capabilities, allowing teachers to easily summarize class progress and individual student learning progress, which is then intelligently analyzed. The analysis results are divided into two parts: First, a summary and analysis of common weaknesses in the class's learning; second, AI-based teaching suggestions addressing these issues, providing teachers with timely feedback and enabling targeted instruction.

[0079] This disclosure aims to overcome the problem of AI teachers directly providing answers. It allows for stricter definitions and restrictions on the prompts provided by the target AI agent and constructs an education industry model to better address student questions. It employs guided responses tailored to different student groups, leading students through problem-solving and analytical processes, thereby improving teaching quality and efficiency. During use in a cloud computer lab, students can ask the AI ​​teacher questions, and the backend records the current instructor. Conversely, instructors can use AI-powered teaching tools to review student questions and conduct further teaching management.

[0080] This disclosure can use user input information and open source data as training datasets to continuously fine-tune the large-scale education model and gradually improve the quality of answers; based on cloud data center capabilities, it can accurately manage the teaching relationship between teachers and students, and the artificial intelligence teaching aids can then obtain the question and answer records of related students through the message center to form user profiles of classes and students.

[0081] This disclosure allows for fine-tuning of a large model, using a math application problem bank as the training set, and acquiring teaching resources such as lesson plans and video links as model data to enhance the model's richness and professionalism. The role definition and tasks clearly state that the target agent can use guided responses to help students master classroom knowledge, providing problem-solving strategies for math problems rather than directly giving answers. The constraints further emphasize that directly providing answers would disrupt teaching and cause serious consequences. Additional information suggests that the target agent use ToT thinking chains and GoT mind maps to improve response quality.

[0082] During the question-and-answer process on the student's end, the dialogue record can be stored in the message center along with the current instructor's ID. When summarizing on the teacher's end, the teacher can retrieve the corresponding student's question-and-answer records from the message center. For example, the teacher can retrieve the system information of the target intelligent agent from the past 12 hours. In response to the teacher's input of query data for classifying and analyzing questions, the target intelligent agent can classify and analyze the questions. For example, the teacher can input query data such as "Summarize the questions asked by students in the class and provide suggestions for improving teaching" to classify and analyze the questions. The specific representation of the query data can be determined according to actual needs and is not limited here.

[0083] The cloud education service disclosed herein provides a cloud computer lab solution, enabling teachers and students to attend classes via cloud computers. The intelligent assistant client can be installed on the cloud computer and can leverage the education service to obtain teacher-student relationships. For example, when 50 students in a class use the AI ​​teacher, the backend can record which teacher is conducting the class. The teacher's end can then retrieve information on which students asked questions, achieving data location and isolation. Furthermore, the intelligent assistant can be designed with target intelligent agent permission management. AI tools on the teacher and student sides need to be accessed via the cloud education desktop, and the education service can determine whether it is an education desktop.

[0084] Figure 3 is a schematic diagram of an optional data processing method for implementing intelligent teaching and learning interaction according to an embodiment of this disclosure. As shown in Figure 3, in the AI ​​cloud classroom, multiple student computers can be uniformly managed by the teacher's computer, including teaching broadcasts, mirroring, and homework submission and receipt. The teacher's computer can interact with the AI ​​teaching assistant. The AI ​​features on the teacher's end can include extracting student profiles at the class level, analyzing student questions, summarizing knowledge weaknesses at the class level, and thus assisting the teacher in targeted teaching. Students' computers can interact with the AI ​​teacher. The AI ​​features on the student's end can include guided question-and-answer sessions, guiding students to think and explore solutions themselves. This prevents students from using AI to avoid thinking about daily homework.

[0085] Figure 4 is a schematic diagram of an optional data processing method according to an embodiment of this disclosure applied to an intelligent teaching assistant scenario. As shown in Figure 4, the teacher, student 1, and student 2 can interact with their respective computer clients, and through these computer clients, interact with the intelligent assistant client, and then interact with the educational big data model. Specifically, the intelligent assistant client and the educational big data model can achieve dialogue with the AI ​​teaching assistant or dialogue with the AI ​​teacher. The cloud service education can obtain AI menus from multiple computer clients, and then access and store teaching records with the educational big data model. The educational big data model can also access and store messages with the message center.

[0086] The following is an optional embodiment of the technical solution proposed in this disclosure. When a student and AI teacher are interacting, for example, a student asks: "What is 19 * 25?" The AI ​​teacher can reply: "This is a multiplication problem. Before we calculate it directly, let's think about how to solve this problem more efficiently. First, can you tell me what the two numbers given in this problem are? What do we need to calculate?" The student replies: "19 and 25, calculate the product." The AI ​​teacher can reply: "Very good! You have correctly identified the two numbers in the problem: 19 and 25. We need to calculate their product. Now, let's think about how to calculate this multiplication more efficiently. There is a trick to make this calculation simpler. Do you notice any characteristics of the number 25? What is its relationship with 100? Hint: Think about what fraction of 100 25 is." The student replies: "1 / 4." The AI ​​teacher can reply: "Great! You have discovered an important relationship. 25 is indeed 1 / 4 of 100. This discovery can help us simplify the calculation. Let's rethink this problem using this relationship: 1. If we want to calculate 19 × 100, how would we do it?" This is a relatively simple calculation. 2. Then, since 25 is 1 / 4 of 100, 19 × 25 is actually equal to 1 / 4 of (19 × 100). Can you calculate 19 × 100 first? Then we'll continue to the next step. Student reply: 19 = 20 - 1. AI teacher can reply: Very clever thinking! You are using a very effective calculation strategy. Let's continue according to your idea: 1. You proposed 19 = 20 - 1, which is a good decomposition method. 2. Now, let's use this idea to calculate 19 × 100: ① 20 × 100 = 2000; ② 1 × 100 = 100; ③ Therefore, 19 × 100 = 2000 - 100 = 1900. 3. Now we know 19 × 100 = 1900. 4. Recall that what we ultimately want to find is 19 × 25, and 25 is 1 / 4 of 100. So, can you think of what we should do next? How do we use the result of 19 × 100 to get the answer to 19 × 25? Student replies: I understand. AI teacher can reply: Great! It seems you understand the solution. Since you say you understand, let's summarize the entire solution process to make sure we haven't missed any important steps: 1. We first identify that we need to calculate 19 × 25. 2. We notice that 25 is 1 / 4 of 100. 3. We calculate 19 × 100 = 1900. 4. Finally, we need to take 1 / 4 of 1900 to get the result of 19 × 25. Now, can you complete the last step and give the final answer? Remember to explain how you got this answer.

[0087] For example, a student asks: A construction team built a 480-kilometer-long highway, planning to complete it in 48 days, but finished in 40 days. How many more kilometers did they build per day on average than planned? The AI ​​teacher can reply: Okay, this is a great practical application problem. Let's analyze this problem step by step: 1. First, let's organize the information given in the problem: Total length of the highway: 480 kilometers; Planned construction period: 48 days; Actual construction period: 40 days. 2. The problem asks us to calculate how many more kilometers were built per day on average than planned. Now, let's think about the steps to solve this problem: 1. We need to know how many kilometers should have been built per day according to the plan. Can you calculate how many kilometers should have been built per day according to the plan? 2. Then, we need to calculate how many kilometers were actually built per day. Can you calculate how many kilometers were actually built per day? 3. Finally, we need to calculate the difference between these two numbers. Please try calculating the first two steps first. If you encounter difficulties, we can discuss them together. Student reply: Planned daily work: 480 / 48 = 10. Very good! You correctly calculated the planned daily workload. The AI ​​teacher can reply: Let's continue: 1. Planned daily workload: 480 ÷ 48 = 10 km / day. Now, let's calculate the actual daily workload: 2. The actual construction period is 40 days, and the total length is still 480 km. Can you calculate the actual daily workload? Hint: Use the same method as in step one, divide the total length by the actual number of days. Please calculate the actual daily workload, and then we will continue to the next step. Student reply: Actual 480 / 40 = 12. The AI ​​teacher can reply: Great! Your calculation is correct. Now we have two key data: 1. Planned daily workload: 10 km / day. 2. Actual daily workload: 12 km / day. Now we have come to the last step. The question asks us to calculate how many more kilometers were built per day than planned. Can you calculate this difference? It's the actual daily workload minus the planned daily workload. Please perform this final calculation and give the final answer. Remember to specify the unit (km). Student reply: 2. The AI ​​teacher can reply: Very good! Your calculation is completely correct. Let's summarize the entire solution process: 1. Planned daily workload: 480 ÷ 48 = 10 km / day 2. Actual daily workload: 480 ÷ 40 = 12 km / day 3. Extra road length built per day compared to the plan: 12 - 10 = 2 km / day Therefore, the final answer is: an average of 2 km more road was built per day than planned. You used division to calculate the average daily workload and then subtraction to find the difference. This problem not only tests basic mathematical operations but also involves efficiency calculations in practical engineering. Do you have any thoughts on this solution process? Or do you have any questions about similar word problems?

[0088] For example, a student asks: "Help me write an essay about the Beginning of Winter." The AI ​​teacher can reply: "Of course, I can help you write an essay about the Beginning of Winter. Let's plan the structure and content of this essay together. 1. Introduction: Describe the time of the Beginning of Winter (early October in the lunar calendar). Briefly introduce the position of the Beginning of Winter in the twenty-four solar terms. 2. Part One: Changes in Nature Weather changes: Temperature drops sharply, and it may start to snow. Plant changes: Leaves turn yellow and fall, and some plants enter a dormant state. Animal changes: Some animals begin to hibernate, and migratory birds fly south. 3. Part Two: Changes in People's Lives Clothing changes: People start to wear heavy winter clothes. Dietary changes: People like to eat warm and nourishing foods, such as mutton soup and ginger tea. Lifestyle habits: Indoor activities increase, and outdoor activities decrease. 4. Part Three: Traditional Customs of the Beginning of Winter Introduce some local customs for the Beginning of Winter, such as "pasting window decorations" and "eating dumplings." Describe the origin and significance of these customs. 5. Conclusion: Express expectations for winter. Summarize the feelings and thoughts brought about by the Beginning of Winter. What do you think of this structure? Is there anything you would like to emphasize or add?" We can further refine this outline based on your ideas.

[0089] Furthermore, when teachers and AI teaching assistants communicate, for example, a teacher might ask: "Summarize the questions asked by the students in the class and provide suggestions for improving teaching." The AI ​​teaching assistant can reply: "Okay, I will summarize the questions asked by the students in the class and provide corresponding suggestions for improving teaching." Student questions include: 1. "How many is 19 * 25?" A student raised a specific multiplication problem. During the discussion, the student demonstrated the idea of ​​using factorization (19 = 20 - 1) to simplify the calculation. 2. "A construction team is building a 480-kilometer-long highway, planning to complete it in 48 days, but it was completed in 40 days. How many more kilometers did they build per day than planned?" A student raised a practical application problem involving calculations of project progress and work efficiency. The calculation steps include: planned daily workload: 480 ÷ 48 = 10 kilometers / day; actual daily workload: 480 ÷ 40 = 12 kilometers / day; extra highway length built per day compared to plan: 12 - 10 = 2 kilometers / day. 3. "Help me write an essay about the Beginning of Winter." A student requested help crafting an essay about the Beginning of Winter. An outline structure was provided, including an introduction, changes in nature, changes in people's lives, traditional customs, and a conclusion. Teaching Improvement Suggestions: 1. Strengthen Basic Calculation Skills Problem Background: Students demonstrated understanding of the factorization method when solving 19*25, but may need more practice to solidify this skill. Improvement Measures: Summarize learning progress at the class level and provide teachers with targeted teaching suggestions. Provide More Practice: Design more similar multiplication problems, allowing students to calculate using the factorization method to enhance their flexible application ability. Explain Multiple Methods: In addition to the factorization method, other simplified algorithms can be introduced, such as vertical multiplication, approximation methods, etc., giving students more choices. Interactive Activities: Set up some group competitions or games in class to allow students to improve their calculation speed and accuracy through interaction. 2. Strengthen Training in Practical Application Problems Problem Background: Students showed good comprehension when solving practical application problems involving road construction teams, but still need further consolidation of problem-solving strategies for this type of problem. Improvement Measures: 1. Increase Practical Application Problems: Add more application problems related to real life, such as time management and cost calculation, to textbooks and workbooks. 2. Case Analysis: Guide students to gradually understand the problem background and clarify the solution steps through specific case analysis. 3. Step-by-Step Guidance: When explaining practical application problems, explain the calculation process and logical reasoning for each step in detail to ensure students can master the complete problem-solving process. 3. Improve Writing Skills Problem Background: Students demonstrate some creativity and structural awareness when brainstorming essays, but may need more guidance to refine details and expression. Improvement Measures: 4. Provide Model Essays: Showcase excellent model essays to help students learn how to organize language and paragraphs. 5. Writing Workshops: Regularly hold writing workshops to stimulate students' writing inspiration through group discussions and brainstorming. Feedback Mechanism: Establish an effective essay feedback mechanism to promptly correct students' essays and provide specific improvement suggestions, encouraging students to revise and improve repeatedly.These improvements can help students better master mathematical calculation skills.

[0090] According to embodiments of this disclosure, a data processing method is also provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0091] Figure 5 is a flowchart of a data processing method according to an embodiment of the present disclosure. As shown in Figure 5, the method may specifically include the following steps:

[0092] Step S502: Obtain query data.

[0093] In one optional embodiment, acquiring inquiry data involves collecting and analyzing user-submitted questions or needs to provide relevant teaching assistance and answers. This allows for a better understanding of user needs, personalized teaching services, and improved teaching efficiency. During the acquisition of inquiry data, the data can be categorized and organized according to the user's questions or needs. Categorizing and organizing the data helps to better understand the types of user questions and needs, providing a foundation for subsequent processing and analysis.

[0094] Step S504: Based on the type of the first object corresponding to the query data, determine the target intelligent agent corresponding to the query data.

[0095] In one optional embodiment, the target agent corresponding to the query data can be determined based on the type of the first object corresponding to the query data. After determining the target agent, it can be further analyzed whether the type of the first object is a type of teaching object. If the type of the first object is a type of teaching object, then the teaching question in the query data can be determined, and the target agent can be used to generate data for the teaching question to obtain the first response data. This allows for a better understanding of the user's teaching needs and provides the user with more precise teaching assistance.

[0096] Step S506: If the type of the first object is the type of the teaching object, determine the teaching question in the query data, and use the target intelligent agent to generate data for the teaching question to obtain the first response data, wherein the first response data includes the problem-solving ideas corresponding to the teaching question.

[0097] In one optional embodiment, after determining the teaching problem, a target intelligent agent can be used to generate data for the teaching problem, resulting in first response data. The first response data includes the problem-solving approach corresponding to the teaching problem. Through analysis and processing of the teaching problem, relevant teaching solutions and assistance can be provided to the user, improving the user's learning efficiency and performance.

[0098] The above process allows for the effective processing and analysis of user questions and needs, providing personalized teaching assistance and solutions. Furthermore, by analyzing and processing user learning questions, a better understanding of user learning needs can be achieved, leading to more precise teaching services. Ultimately, by analyzing and processing user learning questions, user learning needs can be better met, resulting in more personalized and accurate teaching services.

[0099] In the above embodiments of this disclosure, when the type of the first object is a teaching object type, the method further includes: obtaining target dialogue data of at least one historical teaching object associated with the first object from the database based on the identification information of the first object, wherein the target dialogue data includes historical inquiry data and historical response data of at least one historical teaching object, and the historical response data is data obtained by using a historical agent to generate data from the historical inquiry data; inputting the inquiry data and target dialogue data into the target agent, and using the target agent to generate second response data, wherein the second response data includes historical inquiry data, historical response data, and teaching guidance data.

[0100] In one optional embodiment, target dialogue data of at least one historical learner associated with the first object can be retrieved from a database based on the identification information of the first object. This target dialogue data includes historical inquiry and response data of the historical learners. It is possible to obtain historical dialogue data similar to the current learner to facilitate subsequent teaching guidance and response generation. Next, the current learner's inquiry data and the retrieved target dialogue data can be input into a target agent. The target agent is an intelligent system specifically designed for teaching guidance and response generation, capable of generating corresponding responses based on the input dialogue data and historical data. The target agent can analyze the current learner's inquiry data and historical dialogue data, and then generate second response data. The second response data includes the current learner's historical inquiry data, historical response data, and teaching guidance data. This data helps learners better understand and master relevant knowledge, providing more personalized and effective teaching guidance. Simultaneously, learners can obtain teaching content and guidance more closely aligned with their own needs, thereby improving learning effectiveness and experience.

[0101] In the above process, by analyzing historical dialogue data and current student inquiry data, the target intelligent agent can generate more targeted teaching guidance data to better meet the learning needs of students. The combination of historical response data and teaching guidance data helps students better understand and master knowledge, thereby improving learning outcomes. Through intelligent teaching support systems, the workload of teachers can be reduced, teaching resources saved, and teaching efficiency improved.

[0102] According to embodiments of this disclosure, a data processing method is also provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0103] Figure 6 is a flowchart of a data processing method according to an embodiment of the present disclosure. As shown in Figure 6, the method may specifically include the following steps:

[0104] Step S602: Respond to the input command applied to the operation interface and determine the query data corresponding to the input command.

[0105] Step S604: Based on the type of the first object corresponding to the query data, determine the target intelligent agent corresponding to the query data.

[0106] Step S606: If the type of the first object is a preset type, determine the question data in the query data, and use the target intelligent agent to generate data for the question data to obtain the first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data.

[0107] Step S608: Output the first response data.

[0108] According to embodiments of this disclosure, a data processing method is also provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0109] Figure 7 is a flowchart of a data processing method according to an embodiment of the present disclosure. As shown in Figure 7, the method may specifically include the following steps:

[0110] Step S702: Obtain query data by calling the first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter includes the query data.

[0111] Step S704: Based on the type of the first object corresponding to the query data, determine the target intelligent agent corresponding to the query data.

[0112] Step S706: If the type of the first object is a preset type, determine the question data in the query data, and use the target intelligent agent to generate data for the question data to obtain the first response data. The first response data includes the first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data.

[0113] Step S708: Output the first response data by calling the second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter includes the first response data.

[0114] According to an embodiment of this disclosure, a data processing system for implementing the above-described data processing method is also provided. FIG8 is a schematic diagram of a data processing system according to an embodiment of this disclosure. As shown in FIG8, the system includes a client 802 and a server 804.

[0115] The client is configured to send query data; the server is connected to the client and is configured to determine the target agent corresponding to the query data based on the type of the first object corresponding to the query data. If the type of the first object is a preset type, the server determines the question data in the query data and uses the target agent to generate data from the question data to obtain the first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data. The client is also configured to output the first response data.

[0116] Optionally, FIG9 is a structural block diagram of a computing device according to an embodiment of the present disclosure. As shown in FIG9, the computing device A may include: one or more (only one is shown in the figure) processors 102, memory 104 and peripheral interfaces 106, wherein the processors 102, memory 104 and peripheral interfaces 106 are interconnected through a bus 108.

[0117] The memory may be configured to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0118] The processor can access information and applications stored in the memory via a transmission device to execute the steps in each embodiment.

[0119] Embodiments of this disclosure can provide an electronic device. FIG10 is a structural block diagram of an electronic device according to an embodiment of this disclosure. As shown in FIG10, the electronic device may include: an input / output device 1002; a memory 1004; and a processor 1006, wherein the processor 1006 is connected to the input / output device 1002 and the memory 1004 via a bus 1008.

[0120] The memory may be configured to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0121] The processor can invoke an executable program stored in memory via a transmission device to execute the following method: Acquire query data. Based on the type of a first object corresponding to the query data, determine the target agent corresponding to the query data. If the type of the first object is a preset type, determine the question data in the query data, and use the target agent to generate data from the question data to obtain first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data.

[0122] Optionally, the target intelligent agent generates data from the question data to obtain first response data, including: generating first prompt information based on the question data, wherein the first prompt information is used to prompt the target intelligent agent to generate first guidance data and prohibit the generation of answer data; inputting the first prompt information into the target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain first response data.

[0123] Optionally, the method further includes: generating second prompt information based on the question data, wherein the second prompt information is used to indicate the logical rules and relationships between the question data and the answer data; inputting the first prompt information into the target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain the first response data, including: inputting the first prompt information and the second prompt information into the target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain the first response data.

[0124] Optionally, if the type of the first object is not a preset type, the method further includes: obtaining target dialogue data of at least one historical object associated with the first object from the database based on the identification information of the first object, wherein the target dialogue data includes historical query data and historical response data of at least one historical object, and the historical response data is data obtained by using a historical agent to generate data from the historical query data; inputting the query data and target dialogue data into the target agent, and using the target agent to generate second response data, wherein the second response data includes historical query data, historical response data and second guidance data, and the second guidance data is used to guide the first object to provide guidance to at least one historical object.

[0125] Optionally, generating second response data using the target intelligent agent includes: analyzing the target dialogue data using the target intelligent agent to generate an object profile of at least one historical object; and generating second response data using the object profile of at least one historical object and query data using the target intelligent agent.

[0126] Optionally, the database also stores the storage time of different dialogue data; based on the identification information of the first object, the database is used to obtain the dialogue data of at least one historical object that is associated with the first object, including: obtaining the dialogue data stored in the database within a preset time period to obtain the initial dialogue data; and determining the target dialogue data from the initial dialogue data based on the identification information of the first object.

[0127] Optionally, if the type of the first object is a preset type, the method further includes: determining a second object that is associated with the first object; generating current dialogue data based on the query data and the first response data; and storing the current dialogue data and the identification information of the second object in a database.

[0128] Optionally, determining the target agent corresponding to the query data based on the type of the first object corresponding to the query data includes: determining the current network environment of the first object; determining whether the first object meets preset conditions based on the network environment; and determining the target agent based on the type of the first object if it is determined that the first object meets the preset conditions.

[0129] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0130] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause the processing unit to execute the methods in the various embodiments of this disclosure.

[0132] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0133] Embodiments of this disclosure also provide a computer-readable storage medium. Optionally, in this embodiment, the computer-readable storage medium can be used to store program code executed by the method provided in the above embodiments.

[0134] Optionally, in this embodiment, the storage medium may be located in a computing device.

[0135] Optionally, in this embodiment, the computer-readable storage medium is configured to store an executable program, which, when the executable program is running, controls the device where the computer-readable storage medium is located to execute the method described in any of the above embodiments.

[0136] Embodiments of this disclosure also provide a computer program product. Optionally, in this embodiment, the computer program product may include a computer program that, when executed by a processor, implements the methods provided in the embodiments described above.

[0137] The aforementioned computer program products can refer to software programs that have been written, tested, and released, and can run on computers or other devices. Computer program products can include application programs, operating systems, utility software, etc., used to achieve specific functions or solve specific problems.

[0138] Embodiments of this disclosure also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium, which can be used to store a computer program that, when executed by a processor, implements the methods provided in the embodiments described above.

[0139] The aforementioned non-volatile computer-readable storage medium can refer to a medium for storing data. Non-volatile computer-readable storage media can retain data without loss when power is off and can be used to store long-term data, such as operating systems, applications, and user files. Non-volatile storage media can include hard disk drives, solid-state drives, optical disks, and flash memory storage devices, etc.

[0140] Embodiments of this disclosure also provide a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it implements the method provided in the above embodiments.

[0141] The aforementioned computer program can refer to a set of instructions used to tell the computer to perform specific tasks or operations. Computer programs can be written by programmers using specific programming languages ​​and can include algorithms, data structures, logic, and control flow. Computer programs can be used for a variety of purposes, including application software, operating systems, etc.

[0142] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0143] In the several embodiments provided in this disclosure, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0145] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0146] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0147] The above description is only a preferred embodiment of this disclosure. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure. Industrial applicability

[0148] This disclosure provides personalized intelligent education services based on the needs and characteristics of different users, including personalized teaching guidance, learning content, learning plans, and learning methods. It can guide a user to determine the answer data corresponding to the question data generated by the first guiding data. This answer data can be related to the knowledge points, solution approaches, or solutions to similar questions in the user's query data. In particular, it can cultivate users' self-learning ability, allowing them to gain a deeper understanding of knowledge points and develop problem-solving skills while searching for answers. This makes the application of intelligent agents in the field of education more educationally meaningful, thereby solving the technical problem of low efficiency in communication and interaction between teachers and students in related technologies.

Claims

1. A data processing method, comprising: Obtain query data; Based on the type of the first object corresponding to the query data, the target intelligent agent corresponding to the query data is determined; When the type of the first object is a preset type, the question data in the query data is determined, and the target intelligent agent is used to generate data on the question data to obtain the first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data.

2. The method according to claim 1, wherein, The step of generating first response data by utilizing the target intelligent agent on the question data includes: Based on the question data, a first prompt message is generated, wherein the first prompt message is used to prompt the target intelligent agent to generate the first guidance data and to prohibit the generation of the answer data; The first prompt information is input into the target intelligent agent, and the target intelligent agent is used to generate data from the question data to obtain the first response data.

3. The method according to claim 2, wherein, The method further includes: Based on the question data, a second prompt message is generated, wherein the second prompt message is used to indicate the logical rules and relationships between the question data and the answer data; The step of inputting the first prompt information to the target intelligent agent, and using the target intelligent agent to generate data from the question data to obtain the first response data includes: The first prompt and the second prompt are input into the target intelligent agent, and the target intelligent agent is used to generate data from the question data to obtain the first response data.

4. The method according to any one of claims 1 to 3, wherein, If the type of the first object is not the preset type, the method further includes: Based on the identification information of the first object, target dialogue data of at least one historical object that is associated with the first object is obtained from the database. The target dialogue data includes historical query data and historical response data of the at least one historical object. The historical response data is data obtained by using a historical agent to generate data from the historical query data. The query data and the target dialogue data are input into the target agent, and the target agent is used to generate second response data. The second response data includes the historical query data, the historical response data, and second guidance data. The second guidance data is used to guide the first object to provide guidance to the at least one historical object.

5. The method according to claim 4, wherein, The step of generating the second response data using the target agent includes: The target intelligent agent is used to analyze the target dialogue data to generate an object profile of the at least one historical object; The second response data is obtained by using the target intelligent agent to generate an object profile of the at least one historical object and the query data.

6. The method according to claim 4, wherein, The database also stores the storage times of different dialogue data; The step of retrieving dialogue data of at least one historical object associated with the first object from the database based on the identification information of the first object includes: Initial dialogue data is obtained by retrieving dialogue data stored within a preset time period from the database. Based on the identification information of the first object, the target dialogue data is determined from the initial dialogue data.

7. The method according to claim 4, wherein, If the type of the first object is the preset type, the method further includes: Identify a second object that is associated with the first object; Based on the query data and the first response data, generate the current dialogue data; The current dialogue data and the identification information of the second object are stored in the database.

8. The method according to any one of claims 1 to 3, wherein, Determining the target agent corresponding to the query data based on the type of the first object corresponding to the query data includes: Determine the current network environment of the first object; Based on the network environment, determine whether the first object meets the preset conditions; If the first object is determined to meet the preset conditions, the target intelligent agent is determined based on the type of the first object.

9. A data processing method, comprising: Obtain query data; Based on the type of the first object corresponding to the query data, the target intelligent agent corresponding to the query data is determined; When the type of the first object is the type of the teaching object, the teaching question in the query data is determined, and the target intelligent agent is used to generate data for the teaching question to obtain the first response data, wherein the first response data includes the problem-solving ideas corresponding to the teaching question.

10. The method according to claim 9, wherein, If the type of the first object is a teaching object type, the method further includes: Based on the identification information of the first object, target dialogue data of at least one historical teaching object that is associated with the first object is obtained from the database. The target dialogue data includes historical inquiry data and historical response data of the at least one historical teaching object. The historical response data is data obtained by using a historical agent to generate data from the historical inquiry data. The query data and the target dialogue data are input into the target agent, and the target agent is used to generate second response data, wherein the second response data includes the historical query data, the historical response data, and the teaching guidance data.

11. A data processing method, comprising: In response to an input command applied to the user interface, determine the query data corresponding to the input command; Based on the type of the first object corresponding to the query data, the target intelligent agent corresponding to the query data is determined; When the type of the first object is a preset type, the question data in the query data is determined, and the target intelligent agent is used to generate data for the question data to obtain the first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data. Output the first response data.

12. A data processing method, comprising: The query data is obtained by calling a first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter includes the query data; Based on the type of the first object corresponding to the query data, the target intelligent agent corresponding to the query data is determined; When the type of the first object is a preset type, the question data in the query data is determined, and the target intelligent agent is used to generate data for the question data to obtain the first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data. The first response data is output by calling the second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter includes the first response data.

13. A data processing system, comprising: The client is configured to send query data; The server, connected to the client, is configured to determine the target agent corresponding to the query data based on the type of the first object corresponding to the query data. If the type of the first object is a preset type, the server determines the question data in the query data and uses the target agent to generate data for the question data to obtain first response data. The first response data includes first guidance data, which is used to guide the first object to determine the answer data corresponding to the question data. The client is also configured to output the first response data.

14. A computing device, comprising: Memory, which stores executable programs; A processor is configured to run the program, wherein the program, when running, performs the method according to any one of claims 1 to 12.

15. An electronic device comprising: Memory, which stores executable programs; A processor, connected to the memory via a bus, is configured to run the program, wherein the program, when running, performs the method according to any one of claims 1 to 12.

16. A computer-readable storage medium comprising a stored executable program, wherein, When the executable program is executed, it controls the device containing the computer-readable storage medium to perform the method according to any one of claims 1 to 12.

17. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 12.

Images