Information interaction method and device, information interaction system, electronic equipment and medium

Abstract

The invention provides an information interaction method and device, and relates to the technical field of education. According to the specific implementation scheme, a to-be-processed corpus sent by a learning object is received; based on the to-be-processed corpus and a pre-constructed vector database, determining interaction corpus information; sending the to-be-processed corpus and the interaction corpus information to a large language model to obtain courseware information and / or interaction information output by the large language model; sending the courseware information to an educational digital person with an educational role; and sending the interaction information to the partner digital person with the partner role, so that the education digital person and the partner digital person interact with the learning object in the course architecture. And the learning result information of the learning object is improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of educational technology, involving technical fields such as online education and artificial intelligence, and particularly relates to an information interaction method and device, an information interaction system, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the current field of online education, digital intelligent courseware has become an important means of educational informatization. However, although existing digital intelligent courseware provides rich educational resources and learning methods, there are still some problems in the actual teaching process. On the one hand, digital intelligent courseware often lacks a real interactive experience, making it difficult for students to truly immerse themselves in the learning environment; on the other hand, existing digital intelligent courseware lacks a simulated social learning mechanism and cannot effectively simulate the learning and communication scenarios in real life, thus affecting the learning experience of students. Summary of the Invention

[0003] The present disclosure provides an information interaction method and device, an electronic device, and a computer-readable storage medium.

[0004] According to a first aspect, an information interaction method is provided. The method includes: receiving a to-be-processed corpus sent by a learning object; determining interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; sending the to-be-processed corpus and the interaction corpus information to a large language model to obtain courseware information and / or interaction information output by the large language model; sending the courseware information to an educational digital human with an educational role to enable the educational digital human to interact with the learning object; and sending the interaction information to a partner digital human with a partner role to enable the partner digital human to interact with the learning object.

[0005] According to a second aspect, an information interaction device is provided. The device includes: a receiving unit configured to receive a to-be-processed corpus sent by a learning object; a determining unit configured to determine interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; an obtaining unit configured to send the to-be-processed corpus and the interaction corpus information to a large language model to obtain courseware information and / or interaction information output by the large language model; a sending unit configured to send the courseware information to an educational digital human with an educational role to enable the educational digital human to interact with the learning object; and an interaction unit configured to send the interaction information to a partner digital human with a partner role to enable the partner digital human to interact with the learning object.

[0006] According to a third aspect, an information interaction system is provided, which includes: a digital human interaction module, an educational digital human with an educational role, and a partner digital human with a partner role; the digital human interaction module is configured to receive the to-be-processed corpus sent by the learning object; determine the interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; send the to-be-processed corpus and the interaction corpus information to a large language model to obtain the courseware information and interaction information output by the large language model; send the courseware information to the educational digital human; send the interaction information to the partner digital human; the educational digital human generates teaching explanation information based on the courseware information and provides the teaching explanation information to the learning object; receives the classroom questions of the learning object and generates classroom answers to send to the learning object; the partner digital human generates learning corpus information based on the interaction information and the teaching explanation information and provides the learning corpus information to the learning object.

[0007] According to a fourth aspect, an electronic device is provided, which includes: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any implementation manner of the first aspect.

[0008] According to a fifth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to cause a computer to execute the method described in any implementation manner of the first aspect.

[0009] The information interaction method and apparatus provided by the embodiments of the present disclosure, first, receive the to-be-processed corpus sent by the learning object; second, determine the interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; third, send the to-be-processed corpus and the interaction corpus information to a large language model to obtain the courseware information and / or interaction information output by the large language model; then, send the courseware information to an educational digital human with an educational role to enable the educational digital human to interact with the learning object; finally, send the interaction information to a partner digital human with a partner role to enable the partner digital human to interact with the learning object. Thus, through this method, a real interaction experience can be achieved between the learning object and digital humans with different roles, enabling the learning object to immerse in the learning environment, effectively simulating the learning and communication scenarios in real life, and improving the learning experience of the learning object.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. Description of the Drawings

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation to the present disclosure. Among them:

[0012] Figure 1 is a flowchart of an embodiment of the information interaction method according to the present disclosure;

[0013] Figure 2 is a structural diagram of a course of the digital intelligent courseware autonomous learning platform in the present disclosure;

[0014] Figure 3 is a flowchart of another embodiment of the information interaction method according to the present disclosure;

[0015] Figure 4 is a flowchart of still another embodiment of the information interaction method according to the present disclosure;

[0016] Figure 5 is a schematic structural diagram of an embodiment of the information interaction device according to the present disclosure;

[0017] Figure 6 is a schematic structural diagram of another embodiment of the information interaction device according to the present disclosure;

[0018] Figure 7 is a schematic structural diagram of still another embodiment of the information interaction device according to the present disclosure;

[0019] Figure 8 is a schematic structural diagram of an embodiment of the information interaction system according to the present disclosure;

[0020] Figure 9 is a block diagram of an electronic device for implementing the information interaction method of the embodiments of the present disclosure. Detailed implementation manners

[0021] Unless otherwise clearly stated, throughout the specification and claims, the term "comprise" or its variations such as "comprises" or "including" etc. will be understood to include the stated elements or components, without excluding other elements or other components.

[0022] The following illustrates the technical solution of the present disclosure through specific embodiments. It should be understood that one or more steps mentioned in the present disclosure do not exclude the existence of other methods and steps before and after the combined steps, or other methods and steps can be inserted between these clearly mentioned steps. It should also be understood that these examples are only used to illustrate the present disclosure and not to limit the scope of the present disclosure. Unless otherwise specified, the numbers of the method steps are only for the purpose of identifying each method step, rather than limiting the arrangement order of each method or defining the implementation scope of the present disclosure. The change or adjustment of their relative relationship can also be regarded as the scope where the present disclosure can be implemented under the condition of no substantial technical content change.

[0023] There are no specific restrictions on the sources of the raw materials and instruments used in the embodiments, and they can be purchased on the market or prepared according to the conventional methods well-known to those skilled in the art.

[0024] Defects of existing digital intelligent courseware: Although existing digital intelligent courseware provides rich educational resources and learning methods, there are still some problems in the actual teaching process. On the one hand, digital intelligent courseware often lacks a real interactive experience, making it difficult for students to truly immerse themselves in the learning environment; on the other hand, existing digital intelligent courseware lacks a learning mechanism that imitates socialization and cannot effectively simulate the learning and communication scenarios in real life, thus affecting the information experience of students' learning results.

[0025] In view of the defects of existing digital intelligent courseware, the present disclosure proposes an information interaction method, creating and integrating digital humans of two roles into the digital intelligent courseware platform. The design of these roles not only aims to simulate the educational interaction scenarios of real humans, providing personalized educational strategies, learning support and social interaction, but also incorporates adversarial, cooperative and competitive elements to form a hybrid learning environment that simulates the ecological environment of a real social environment. Figure 1 Flow 100 according to an embodiment of the information interaction method of the present disclosure is shown. The above information interaction method includes the following steps:

[0026] Step 101, receiving the corpus to be processed sent by the learning object.

[0027] In this embodiment, the execution subject on which the information interaction method runs can be an API (Application Programming Interface) of a digital intelligent courseware autonomous learning platform. The learning object sends the corpus to be processed to the digital intelligent courseware platform. Among them, the learning object is the object of online learning, and the learning object can be a student and the terminal owned by the student. The corpus to be processed is various questions and interaction contents put forward by the learning object to the AI digital human in the form of voice or text, such as course content, knowledge points, and problem descriptions of the learning object. Specifically, the corpus to be processed can be multimodal data, such as one or more of images, texts or voices.

[0028] In the technical solution of the present disclosure, the processing of the collection, storage, use, processing, transmission, provision and disclosure of the personal information of the learning object involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs. In the technical solution of the present disclosure, all data related to the learning object (such as the corpus to be processed) can be obtained from a public dataset or obtained from the learning object with the authorization of the learning object.

[0029] Step 102, determining the interactive corpus information based on the corpus to be processed and the pre-constructed vector database.

[0030] In this embodiment, the vector database is a knowledge base that stores vectors and corpora, where vectors and corpora are stored in a one-to-one correspondence. The interactive corpus information can include the context information of the corpus to be processed and historical interaction information. Among them, the context information is the context corpus information where the corpus to be processed is located, and the historical interaction information is the interaction content between the learning object and the educational digital human and the partner digital human in the historical period, such as user questions, feedback, selections, etc. The given questions mainly come from the interaction process between the learner and the AI digital human. Specifically, when learners encounter questions or need to further understand a certain knowledge point during the learning process, they can ask questions to the AI digital human in the form of voice or text. These questions are the given questions.

[0031] For example, when the learning object is learning a mathematics course, they may not understand a certain formula or theorem very well, and the corpus to be processed directly sent to the AI digital human is: "How is this formula derived?" or "What are the examples of this theorem in practical applications?" and so on. After receiving the corpus to be processed, the information interaction method converts the corpus to be processed into a vector representation, and then uses a similarity search algorithm to retrieve the interactive corpus information most relevant to the problem in the vector database, such as the implementation principle of the formula.

[0032] In this embodiment, in the digital intelligent courseware autonomous learning platform, users can upload course materials in any format, such as class notes, slides, textbooks, recorded voice records, etc. The digital intelligent courseware autonomous learning platform stores these course materials in the vector database for subsequent retrieval and generation. As Figure 2 shown in the structural diagram of the course of the digital intelligent courseware autonomous learning platform, this structural diagram starts from the large unit, and the large unit is subdivided into 13 teaching modules. Each teaching module contains 7 teaching steps, and these teaching steps are the main learning activities or stages within the module. In each teaching step, it is further divided into 7 micro-steps, and these micro-steps represent the specific actions or tasks required to achieve the teaching objectives.

[0033] In Figure 2 it, the large unit is the top layer of the course system and contains the theme or field of the entire course. Teaching module: There are 13 teaching modules under the large unit, and each module focuses on a specific knowledge or skill area within the large unit. Each teaching module contains 7 teaching steps, and each step is further divided into 7 micro-steps. These steps and micro-steps are the basic units for the learning object to learn, ensuring the systematicness and in-depthness of learning. In each step, the AI (Artificial Intelligence) digital human will appear in the 3rd, 4th, 5th, 6th, and 7th micro-step links to provide more specific and personalized learning support and interaction.

[0034] In this embodiment, the educational digital human is a digital human with an educational role and can provide courseware or educational knowledge for the learning object, and the partner digital human is a digital human with a partner role and can provide life or learning information for the learning object.

[0035] In this embodiment, the corpus to be processed is vectorized to obtain a vector to be processed; the vector to be processed is compared with the vectors in the pre-constructed vector database to determine the vectors with a similarity greater than the similarity threshold, and the corpus of the vectors with a similarity greater than the similarity threshold is extracted to obtain the interactive corpus information.

[0036] Step 103: Send the corpus to be processed and the interactive corpus information to the large language model to obtain the courseware information and / or interactive information output by the large language model.

[0037] In this embodiment, the large language model analyzes the corpus to be processed to determine the learning needs of the learning object, and determines the courseware information that can be directly used for teaching or learning by the educational digital human according to the learning needs; determines the interactive information that can be directly used for the partner digital human according to the learning needs.

[0038] In this embodiment, the courseware information is the generated courseware content and can be directly used for teaching or learning. When the courseware information is sent to the educational digital human, the educational digital human can directly convert the courseware information into corresponding teaching content, thus facilitating the learning object to learn.

[0039] In this embodiment, the interactive information is the interactive content generated for the partner digital human, which enables the partner digital human to interact with the learning object in real time.

[0040] Step 104: Send the courseware information to the educational digital human with an educational role so that the educational digital human can interact with the learning object.

[0041] In this embodiment, the courseware information is sent to the educational digital human with an educational role. The educational digital human can conduct corresponding course explanations for the learning object in the digital intelligent courseware autonomous learning platform. The learning object learns according to the explanations of the educational digital human and sends out the corpus to be processed again.

[0042] As the core interface of the system, the API is responsible for transmitting these analysis results and prediction information to the AI digital human, enabling the AI digital human to adjust its response mode and teaching content in real time according to the user's behavior and learning status. For example, when the user shows confusion about a certain knowledge point, the API will call the machine learning model and the user behavior analysis module to obtain the relevant analysis results and transmit this information to the AI digital human, enabling the AI digital human to provide targeted guidance and help in a timely manner.

[0043] Step 105: Send the interaction information to the partner digital human with the partner role so that the partner digital human can interact with the learning object.

[0044] In this embodiment, after the large language model outputs the interaction information, sending the interaction information to the partner digital human with the partner role can implement a socialized learning mechanism in the virtual digital intelligent courseware autonomous learning platform, simulate the learning and communication scenarios in real life, and improve the learning experience of the learning object.

[0045] For the information interaction method provided by the embodiments of the present disclosure, first, receive the to-be-processed corpus sent by the learning object; secondly, determine the interaction corpus information based on the to-be-processed corpus and the pre-constructed vector database; thirdly, send the to-be-processed corpus and the interaction corpus information to the large language model to obtain the courseware information and / or interaction information output by the large language model; then, send the courseware information to the educational digital human with the educational role so that the educational digital human can interact with the learning object; finally, send the interaction information to the partner digital human with the partner role so that the partner digital human can interact with the learning object. Thus, through this method, the learning object can have a real interaction experience with digital humans of different roles, enabling the learning object to immerse in the learning environment, effectively simulating the learning and communication scenarios in real life, and improving the learning experience of the learning object.

[0046] In some embodiments of the present disclosure, the above information interaction further includes: obtaining the object behavior data of the learning object; obtaining the habit information and preference information of the learning object based on the object behavior data; determining the teaching data and resource information based on the habit information and preference information, and sending the teaching data and resource information to the educational digital human.

[0047] In this embodiment, the object behavior data is a series of actions or operations that the object has performed. These actions or operations do not exist in isolation but are closely related to the attributes of the object. The source of the behavior data can be the operation records on the digital intelligent courseware autonomous learning platform, such as: learning duration, learning frequency, accessed courses, knowledge points, completed exercises, test scores, clicks, searches, favorites, and other interaction behaviors. The data form of the object behavior data can be structured data (such as log files, database records) or unstructured data (such as text, video records).

[0048] In this embodiment, the habit information can be the learning pattern of the learning object. For example: the daily learning time period, the preferred type of learning content (such as videos, texts, exercise questions), the learning progress and rhythm, etc. The preference information can be the interests and inclinations of the learning object. For example: the preference for certain topics (such as programming, mathematics), the preference for certain teaching methods (such as interactive learning, autonomous learning), etc. The obtaining of the habit information and preference information of the learning object based on the object behavior data as described above includes: extracting the learning actions of the learning object and the operation objects of the learning actions that appear more frequently than a preset number of times from the object behavior data, and using the learning actions and operation objects as the habit information of the learning object; extracting the behavior preferences that appear more frequently than a preset number of times from the object behavior data as the preference information of the learning object.

[0049] In this embodiment, the teaching data is to generate personalized learning suggestions based on the behavior data of the learning object. For example: recommending suitable learning content, adjusting the learning plan (such as increasing the learning time for certain knowledge points), providing learning skills and methods. The resource information can be the relevant resources recommended according to the preferences of the learning object. For example: suitable courses, textbooks, relevant exercise questions, test questions, extended reading materials or videos, etc.

[0050] In this embodiment, the generated teaching data and resource information are sent to the educational digital human, and the educational digital human interacts with the learning object based on this information to provide personalized learning support. This method can significantly improve the learning experience and effect, and provide more accurate learning support for the learning object.

[0051] In some alternative implementation manners of the present disclosure, the obtaining of the habit information and preference information of the learning object based on the object behavior data as described above includes: inputting the object behavior data into a pre-trained behavior analysis model to obtain the habit information and preference information of the learning object output by the behavior analysis model.

[0052] In this alternative implementation manner, the input data of the behavior analysis model can be the object behavior data, including learning duration, learning frequency, accessed content, test scores, etc. The output data is the habit information and preference information of the learning object. For example: the preference for the learning time period (such as morning, evening), the preference for the learning content (such as videos, texts, exercise questions), the learning progress and rhythm, the degree of interest in certain topics (such as programming, mathematics). When training the behavior analysis model, the training data used can be the historical behavior data and their corresponding habit and preference labels.

[0053] In this alternative implementation, the behavior analysis model can be a classifier or a regression model, mainly used for predicting user behavior and analyzing learning result information. These models can identify users' behavior patterns and learning habits by learning and training on users' historical data, so as to provide personalized teaching data and resources for the AI digital human. For example, if the model predicts that a user may have difficulties with a certain knowledge point, the AI digital human can prepare relevant learning materials and practice questions in advance to help the user better understand and master. User behavior analysis focuses on applying statistical analysis and pattern recognition techniques to deeply analyze users' behavior patterns. It can help understand users' learning habits and preferences, so as to provide more accurate teaching support for the AI digital human. For example, by analyzing users' behavior data on the platform, such as click-through rate, stay time, course progress, etc., it is possible to understand users' interest and mastery of different knowledge points, and then adjust the teaching strategies and content of the AI digital human.

[0054] In this alternative implementation, the behavior analysis model can input the behavior data of the learning object in real time or historically, and output the habit information and preference information of the learning object. The behavior analysis model can update the model regularly according to the new behavior data to improve the prediction accuracy, and improve the accuracy of predicting the habit information and preference information of the learning object.

[0055] In some embodiments of the present disclosure, there are multiple partner digital humans, and the partner roles of each partner digital human are different. The above information interaction method further includes: obtaining the object behavior data of the learning object; based on the object behavior data, obtaining the habit information and preference information of the learning object; performing semantic recognition on the interaction information to determine the semantic recognition result; based on the semantic recognition result, habit information and preference information, generating the role identifiers of each partner digital human and the output text under each role identifier; sending each role identifier and the output text under each role identifier to the corresponding partner digital human among the multiple partner digital humans, so that the partner digital human processes the output text from the perspective of the partner role corresponding to the role identifier.

[0056] In this embodiment, there are multiple partner digital humans and the partner roles of each partner digital human are different. For example, the partner roles include: adversarial role, competitive role, cooperative role, interfering role. The partner role of the partner digital human can be uniquely identified by the role identifier. When there are multiple partner roles, there are multiple role identifiers. Each partner digital human can determine the partner role it needs to implement based on the role identifier sent by the execution entity on which the information interaction method runs.

[0057] In this embodiment, the habit information of the learning object includes the interaction objects that the learning object is accustomed to in the historical period. For example, if the habit information indicates that the learning object is accustomed to sending information to a peer with stronger competitiveness in the historical period, the role identifier generated by the execution entity on which the information interaction method runs corresponds to a competitive role.

[0058] In this embodiment, the preference information of the learning object includes the preferred interaction objects of the learning object. For example, if the preference information indicates that the learning object prefers to communicate with gentle people, the role identifier generated by the execution entity on which the information interaction method runs corresponds to a cooperative role.

[0059] In this embodiment, the output text is the text that the partner digital human needs to output to the learning object. The output text is the text determined by the semantic recognition result. After the partner digital human determines its partner role through the role identifier, the output text can be processed into information corresponding to its partner role and output to the learning object. For example, the semantic recognition result is: guiding the learning object to learn knowledge point A. Then, under the role identifier of its cooperative role, the partner role outputs a detailed introduction to knowledge point A to the learning object, so that the learning object can absorb knowledge point A more effectively.

[0060] The information interaction method provided in this embodiment obtains the object behavior data of the learning object; based on the object behavior data, obtains the habit information and preference information of the learning object; performs semantic recognition on the interaction information to determine the semantic recognition result; based on the semantic recognition result, habit information and preference information, generates the role identifiers of each partner digital human and the output text under each role identifier; and sends each role identifier and the output text under each role identifier to the corresponding partner digital human among multiple partner digital humans, so that the partner digital human processes the output text from the perspective of the partner role corresponding to the role identifier. This can enable the learning object to increase the diversity and freshness of learning through interaction with partner digital humans with different partner roles, continuously refresh the learning experience of the learning object, and prevent learners from getting bored with learning materials. By providing partner digital humans with different AI roles, a continuously changing and dynamic learning environment can be created, thereby improving the participation and learning efficiency of the learning object.

[0061] In some embodiments of the present disclosure, the above method further includes: determining the learning result information of the learning object based on the habit information and preference information; determining the teaching strategies and content of the educational digital human based on the learning result information, and sending the teaching strategies and content to the educational digital human.

[0062] In this embodiment, the habit information and preference information can be input into a pre-trained result classification model to obtain the learning result information of the learning object output by the result classification model. The result classification model is used to classify the learning results of the habit information and preference information of the learning object, dividing the habit information and preference information that are beneficial to the learning effect into one category and the habit information and preference information that are not beneficial to the learning effect into another category.

[0063] In this embodiment, the learning result information is the current result of the learning object. The learning result information includes the learning duration, learning frequency, knowledge point mastery, error rate, etc. of the learning object. Through the learning result information, the learning progress and effect of the learning object can be judged.

[0064] In this embodiment, the teaching strategies and content can be the information after adjusting the original teaching data and resource information. The teaching strategies and content can be the information that changes the data order in the teaching data and resource information, or the information obtained after adding new teaching suggestions and / or resource information to the educational data and resource information. For example, through the teaching data and resource information, it can be determined that the learning object performs poorly on certain knowledge points, and the educational digital human can provide more exercises or adjust the teaching method (such as increasing interactivity, using more intuitive teaching materials, etc.). If the learning object has already mastered certain content, the educational digital human can skip or simplify the relevant parts to improve the learning efficiency. The educational digital human conducts personalized teaching for the learning object according to the received teaching strategies and content.

[0065] Optionally, determining the teaching strategies and content of the educational digital human based on the above learning result information includes: performing a multi-index effect evaluation on the learning result information to obtain an evaluation result; and based on the evaluation result, matching the teaching strategies and content of the teaching digital human from a pre-set teaching strategy set. The multi-indices include: quantitative indices such as test scores, correct answering rates of knowledge points, error type distributions (such as concept confusion, calculation errors); practice indices such as learning duration, interaction frequency, micro-step completion efficiency, resource click preferences (such as videos, texts, experiments); and processing indices such as voice emotion analysis (such as frustration, excitement), text interaction emotion recognition (such as NLP emotion classification), physiological signals (such as eye movement tracking attention monitoring).

[0066] A pre-constructed evaluation model is used to perform multi-index evaluation on the learning results. The evaluation model can use lightweight machine learning (such as random forest, XGBoost) to grade the learning effect, such as excellent, passing, or requiring intervention; or based on a knowledge graph to associate incorrect knowledge points and identify weak links, such as the association of incorrect applications of Newton's laws.

[0067] The information interaction method provided in this embodiment determines the teaching strategies and content of the educational digital human based on the learning result information, sends the teaching strategies and content to the educational digital human, and the educational digital human can dynamically adjust the teaching strategies to provide a more personalized and efficient learning experience, improving the learning experience of the learning object.

[0068] Optionally, the above information interaction method further includes: determining the respective performance information of the digital humans with different roles in the partner digital humans based on the learning result information, and sending the corresponding performance information to each digital human in the partner digital humans. Among them, the digital humans with different roles include: the good student AI role, the bad student AI role, the neutral student AI role, and the digital human for increasing the interest during the class. The partner digital human with the good student AI role is used to play the role of a model student to guide and motivate other students to actively learn. The performance information of the partner digital human with the good student AI role includes sharing learning tip knowledge points, encouraging peers to conduct learning discussions and knowledge sharing. The partner digital human with the bad student AI role is used to simulate the student behaviors that may reduce learning efficiency in real life to improve the attractiveness of the teaching content. The performance information of the partner digital human with the bad student AI role includes: showing some bad learning habits to educate learners to avoid similar behaviors and stimulate learners' reflection and discussion through negative examples. The partner digital human with the neutral student AI role is used to play an ordinary student, reflecting the ordinary performance and attitude of most students. The performance information of the partner digital human with the bad student AI role includes: emotional response information reflecting common learning emotions such as confusion, curiosity, etc.; basic interaction information participating in basic learning activities and discussions. The digital human for increasing the interest during the class is used to enhance the attractiveness and emotional depth of the classroom by providing emotional support and interesting interactions. The performance information of the digital human for increasing the interest during the class includes: emotional support information for showing empathy and emotional support to help reduce learning pressure; gamified learning information for introducing game elements and challenges to make the learning process more vivid and interesting.

[0069] In some optional implementation manners of the present disclosure, the learning result information includes: different result levels and the knowledge points associated with each result level. The above determining the teaching strategies and content of the educational digital human based on the learning result information and sending the teaching strategies and content to the educational digital human includes: determining the hierarchical education strategies of the educational digital human corresponding to each result level based on each result level; introducing the corresponding knowledge points into the hierarchical education strategies of each result level, and extracting associated resources from the courseware library based on the knowledge points, and taking the hierarchical education strategies, knowledge points, and associated resources of all result levels as the teaching strategies and content, and sending the teaching strategies and content to the educational digital human.

[0070] In this alternative implementation, the learning result information is divided into different result levels (e.g., excellent, good, medium, need improvement, etc.). Each result level is associated with specific knowledge points or knowledge areas. For example, the excellent level may be associated with higher-order or extended knowledge points; the need improvement level may be associated with basic or knowledge points that need to be consolidated. Determine the hierarchical education strategy: Based on each result level, design corresponding hierarchical education strategies for each level. For example, for the learning objects at the "excellent" level, the educational digital human can adopt an extended teaching strategy to provide more challenging content or in-depth exploration of related knowledge points; for the learning objects at the "need improvement" level, the educational digital human can adopt a consolidating teaching strategy to provide more basic exercises or repeated explanations of key content.

[0071] In this alternative implementation, the hierarchical education strategies include: introducing high-order challenge tasks (such as interdisciplinary project design), enabling "adversarial learning" roles; strengthening knowledge expansion (such as case deepening), triggering "collaborative learning" scenarios; starting basic knowledge review (such as micro-step re-learning), invoking "expert agents" for targeted tutoring; if the same knowledge point is continuously incorrect ≥3 times, automatically switch to the "step-by-step guidance mode" (such as 3D animation disassembly steps); when the eye movement data indicates distracted attention, switch to "gamified learning" or "naughty student interference scenarios" to refocus.

[0072] In this alternative implementation, in each hierarchical education strategy, introduce the knowledge points associated with the result level. Based on these knowledge points, extract relevant associated resources (such as videos, exercise questions, case analyses, interactive modules, etc.) from the courseware library to support the teaching of the educational digital human. Send the teaching strategies and content to the educational digital human: Send the determined hierarchical education strategies, knowledge points, and associated resources to the educational digital human. The educational digital human dynamically adjusts the teaching content and methods according to the received information to provide personalized learning experiences for the learning objects. For example, assume that the learning result information of a learning object in the "mathematical geometry" field is evaluated as "need improvement", and the execution entity on which the information interaction method runs will perform the following steps: Determine that the hierarchical education strategy corresponding to the "need improvement" level is the consolidating teaching strategy, which is associated with the "basic geometry knowledge points" (such as triangle properties, angle calculations, etc.), and extract the associated resources related to these knowledge points (such as basic explanation videos, exercise questions, interactive geometry tools, etc.) from the courseware library. Send these strategies and resources to the educational digital human, and let it conduct teaching according to the specific situation of the learning object.

[0073] The method for determining and sending teaching strategies and content provided by this alternative implementation determines the hierarchical education strategy of the educational digital human corresponding to the result grading based on each result grading; introduces corresponding knowledge points into the hierarchical education strategies of each result grading, extracts associated resources from the courseware library based on the knowledge points, and uses the hierarchical education strategies, knowledge points, and associated resources of all result hierarchies as teaching strategies and content, and sends the teaching strategies and content to the educational digital human. Based on different result gradings of the learning object, determining the hierarchical education strategy enables the educational digital human to achieve precise and hierarchical teaching, improving the learning experience of the learning object.

[0074] In some alternative implementations of the present disclosure, the above-mentioned determining the interactive corpus information based on the corpus to be processed and the pre-constructed vector database includes: converting the corpus to be processed into a corpus vector; based on the corpus vector, matching course materials and emotional elements from the pre-constructed vector database; and using the course materials and emotional elements as the interactive corpus information.

[0075] In this alternative implementation, the corpus vector refers to the feature vector of the corpus to be processed. Depending on the data type of the corpus to be processed, the method of converting the corpus to be processed into a corpus vector is different. For example, when the corpus to be processed is text data, the corpus to be processed can be converted into a corpus vector by means of word embedding, and for video and audio data, the corpus vector of the corpus to be processed can be extracted through convolutional neural networks and recurrent neural networks.

[0076] In this alternative implementation, the course materials are the course information content involved in the learning of the learning object, such as courseware for different grades and different subjects; the emotional elements are various characteristics and factors related to emotions in the behavior of the learning object, including aspects such as emotions, emotional expressions, and emotional experiences, and are an expression and manifestation of the inner world of humans. Emotional elements play an important role in the psychological and social behaviors of individuals, affecting the mental health and social behaviors of individuals.

[0077] In this alternative implementation, by converting the corpus to be processed into a vector representation and detecting the relevant course materials and emotional elements, it is convenient for the executing entity to better understand and respond to the needs of the learning object.

[0078] In this alternative implementation, the vector database includes multiple library vectors, and each library vector has corresponding course materials and emotional elements. The above-mentioned matching course materials and emotional elements from the pre-constructed vector database based on the corpus vector includes: comparing the similarity between the corpus vector and the library vectors in the vector database, and in response to the similarity between the corpus vector and the library vector being greater than the similarity threshold, using the course materials and emotional elements corresponding to the library vector as the matched course materials and emotional elements.

[0079] The method for obtaining interactive corpus information provided by this alternative implementation converts the corpus to be processed into a corpus vector; based on the corpus vector, course materials and emotional elements are matched from a pre-constructed vector database; the course materials and emotional elements are used as interactive corpus information. By converting the corpus to be processed into a corpus vector, the corresponding course materials and emotional elements are matched, improving the comprehensiveness of the obtained interactive corpus information.

[0080] Optionally, the above information guidance method further includes: receiving feedback data of the learning object; sending the feedback data, the corpus to be processed, and the interactive corpus information to a large language model to obtain new courseware information and new interactive information output by the large language model; sending the new courseware information to the educational digital human; sending the new interactive information to the partner digital human. Among them, the feedback data is data for giving feedback on the educational digital human and / or the partner digital human, such as praising or objecting to the educational strategies output by the educational digital human, and giving positive or negative responses to the performance of the partner digital human.

[0081] Figure 3 Flow 300 of another embodiment of the information interaction method according to the present disclosure is shown. The information interaction method of this embodiment is applied to an educational digital human. The above information interaction method includes the following steps:

[0082] Step 301, receive courseware information.

[0083] In this embodiment, the courseware information is the generated courseware content, which can be directly used for teaching or learning. When the courseware information is sent to the educational digital human, the educational digital human can directly convert the courseware information into corresponding teaching content, facilitating learning for the learning object. The courseware information in step 301 can be Figure 1 The courseware information sent to the educational digital human of the present disclosure by the execution subject of the information interaction method shown (such as the API of the digital intelligent courseware self-study platform), and the courseware information is the information generated due to the corpus to be processed sent by the learning object.

[0084] Step 302, based on the courseware information, generate teaching explanation information and provide the teaching explanation information to the learning object.

[0085] In this embodiment, the teaching explanation information is the information explanation content sent by the educational digital human to the learning object. Through the teaching explanation information, the corresponding corpus to be processed can be effectively explained or interpreted for the learning object.

[0086] In this embodiment, the execution subject on which the information interaction method runs can decompose the courseware information according to the pre-set teaching strategies and content to generate teaching explanation information. For example, if the teaching strategies and content are progressive teaching, the execution subject progressively decomposes the different levels of content in the courseware information to generate teaching explanation information.

[0087] Optionally, the execution entity on which the information interaction method runs may also obtain teaching data and resource information from the API of the digital intelligent courseware autonomous learning platform, determine teaching strategies based on the teaching data, and generate teaching explanation information applicable to the teaching strategies according to the resource information and courseware information and the teaching strategies.

[0088] Optionally, the execution entity on which the information interaction method runs may also obtain teaching strategies and content from the API of the digital intelligent courseware autonomous learning platform, decompose the courseware information in multiple steps according to the teaching strategies, and generate teaching explanation information applicable to the teaching strategies.

[0089] Step 303: Receive the classroom questions of the learning object.

[0090] In this embodiment, the classroom questions are the questions sent by the learning object after receiving the teaching explanation information.

[0091] Step 304: Generate classroom answers based on the classroom questions and send the classroom answers to the learning object.

[0092] In this optional implementation, the classroom answers are the reply information to the classroom questions. After obtaining the classroom questions, the educational digital human selects relevant knowledge points from the courseware information and organizes the knowledge points according to the internal relationship of the knowledge points to obtain the classroom answers.

[0093] In this optional implementation, the educational digital human can directly send the classroom answers to the learning object through the digital intelligent courseware autonomous learning platform, so that the learning object can effectively learn the courseware information.

[0094] The information interaction method provided in this embodiment receives the courseware information, generates teaching explanation information based on the courseware information, provides the teaching explanation information to the learning object, receives the classroom questions of the learning object, generates classroom answers based on the classroom questions, and sends the classroom answers to the learning object, providing an effective learning means for the learning object and improving the learning experience of the learning object.

[0095] Optionally, the above information interaction method further includes: extracting vectors of the teaching explanation information and the classroom answers, and storing the vectors, the teaching explanation information, and the classroom answers in a vector database in a corresponding manner.

[0096] In some optional implementations of the present disclosure, the above information interaction method further includes: extracting semantic vectors and emotional vectors in the teaching explanation information and the classroom answers to obtain a first vector; storing the first vector, the teaching explanation information, and the classroom answers in a vector database in a corresponding manner.

[0097] In this alternative implementation, the first vector is obtained by vectorizing the semantics and emotions of the teaching explanation information and the classroom answers. By extracting the semantic vectors and emotion vectors from the teaching explanation information and the classroom answers, the teaching explanation information and the classroom answers can be effectively represented by the first vector. Storing the first vector in a vector database enables the determination of the teaching explanation information and the classroom answers through vector retrieval.

[0098] Figure 4 FIG. 400 shows a flowchart of yet another embodiment of the information interaction method according to the present disclosure. The information interaction method of this embodiment is applied to a partner digital human. The information interaction method includes the following steps:

[0099] Step 401, receive interaction information and teaching explanation information sent by an educational digital human.

[0100] In this embodiment, the interaction information is interaction content generated for the partner digital human, which enables the partner digital human to interact with the learning object in real time. The interaction information can be information generated due to the to-be-processed corpus sent by the learning object.

[0101] Step 402, generate learning corpus information based on the interaction information and the teaching explanation information.

[0102] In this embodiment, the learning corpus information is the understanding content of the teaching explanation information by the partner digital human when teaching the learning object. The learning corpus information is information sent by the partner digital human to help the learning object deeply understand the teaching explanation information.

[0103] In this embodiment, the above step 402 includes: determining an interaction content template with the learning object based on the interaction information; extracting interaction knowledge points based on the teaching explanation information; and filling the interaction knowledge points into the interaction content template to obtain the learning corpus information. For example, the interaction content template is: xx, do you know how to understand the place yy? After obtaining the knowledge points, fill the knowledge points into the "yy" position of the interaction content template to obtain the learning corpus information.

[0104] In this embodiment, the partner digital human also has corresponding roles. When the roles of the partner digital human are different, the content of the learning corpus information is different. For example, the partner digital human includes: a good student AI role, a bad student AI role, a neutral student AI role, and a digital human that increases the fun during the class. The partner digital human with the good student AI role is used to play the role of a model student, guiding and inspiring other students to actively learn. The learning corpus information of the partner digital human with the good student AI role includes sharing learning skill knowledge points, encouraging peers to conduct learning discussions and knowledge sharing. The partner digital human with the bad student AI role is used to simulate the student behaviors that may reduce learning efficiency in real life to improve the attractiveness of the teaching content. The learning corpus information of the partner digital human with the bad student AI role includes: demonstrating some bad learning habits to educate learners to avoid similar behaviors, so as to stimulate learners' reflection and discussion through negative teaching materials. The partner digital human with the neutral student AI role is used to play an ordinary student, reflecting the ordinary performance and attitudes of most students. The learning corpus information of the partner digital human with the bad student AI role includes: emotional response information, reflecting common learning emotions, such as confusion, curiosity, etc.; basic interaction information, participating in basic learning activities and discussions. The digital human that increases the fun during the class is used to enhance the attractiveness and emotional depth of the classroom by providing emotional support and interesting interactions. The learning corpus information of the digital human that increases the fun during the class includes: emotional support information, used to show empathy and emotional support to help reduce learning stress; gamified learning information, used to introduce game elements and challenges to make the learning process more vivid and interesting.

[0105] Step 403: Provide learning corpus information to the learning object.

[0106] The information interaction method provided in this embodiment receives the interaction information and the teaching explanation information sent by the educational digital human; based on the interaction information and the teaching explanation information, generates learning corpus information, and provides the learning corpus information to the learning object, effectively providing learning support for the learning object.

[0107] Optionally, the above information interaction method further includes: extracting the vector of the learning corpus information, and storing the vector and the learning corpus information in a vector database correspondingly. In this implementation, the learning corpus information may include: learning resources, collaborative tasks, emotional support, gamification, and other contents.

[0108] In some alternative implementation manners of the present disclosure, the above information interaction method further includes: extracting the semantic vector and the emotional vector of the learning corpus information to obtain a second vector, and storing the second vector and the learning corpus information in a vector database.

[0109] In this alternative implementation, the second vector is obtained after vector transformation of the semantics and emotions of the learning corpus information. By extracting the semantic vector and emotion vector from the learning corpus information, the teaching explanation information and classroom answers can be effectively represented by the second vector. Storing the second vector in the vector database enables the determination of the learning corpus information through vector retrieval.

[0110] Further referring to Figure 5 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an information interaction device, and this device embodiment corresponds to Figure 1 the method embodiment shown.

[0111] As shown in Figure 5 , the information interaction device 500 provided in this embodiment includes: a corpus receiving unit 501, a determination unit 502, a obtaining unit 503, a sending unit 504, and an interaction unit 505. Among them, the above-mentioned corpus receiving unit 501 can be configured to receive the to-be-processed corpus sent by the learning object. The above-mentioned determination unit 502 can be configured to determine the interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database. The above-mentioned obtaining unit 503 can be configured to send the to-be-processed corpus and the interaction corpus information to a large language model to obtain the courseware information and / or interaction information output by the large language model. The above-mentioned sending unit 504 can be configured to send the courseware information to an educational digital human with an educational role so that the educational digital human interacts with the learning object. The above-mentioned interaction unit 505 can be configured to send the interaction information to a partner digital human with a partner role so that the partner digital human interacts with the learning object.

[0112] In this embodiment, in the information interaction device 500: the specific processing of the corpus receiving unit 501, the determination unit 502, the obtaining unit 503, the sending unit 504, and the interaction unit 505 and the technical effects brought by them can respectively refer to Figure 1 the relevant descriptions of step 101, step 102, step 103, step 104, and step 105 in the corresponding embodiment, which will not be elaborated here.

[0113] In some embodiments of the present disclosure, the above-mentioned device 500 further includes: an analysis unit (not shown in the figure), and the above-mentioned analysis unit is configured to: obtain the object behavior data of the learning object; based on the object behavior data, obtain the habit information and preference information of the learning object; based on the habit information and preference information, determine the teaching data and resource information, and send the teaching data and resource information to the educational digital human.

[0114] In some embodiments of the present disclosure, there are multiple above-mentioned partner digital humans, and the partner roles of each partner digital human are different. The above-mentioned device 500 further includes: a role division unit (not shown in the figure), and the above-mentioned role division unit is configured to: obtain the object behavior data of the learning object; based on the object behavior data, obtain the habit information and preference information of the learning object; perform semantic recognition on the interaction information to determine the semantic recognition result; based on the semantic recognition result, the habit information and the preference information, generate the role identifiers of each partner digital human and the output text under each role identifier; send each role identifier and the output text under each role identifier to the corresponding partner digital human among the multiple partner digital humans, so that the partner digital human processes the output text from the perspective of the partner role corresponding to the role identifier.

[0115] In some embodiments of the present disclosure, the above-mentioned device 500 further includes: a planning unit (not shown in the figure), and the above-mentioned planning unit is configured to: based on the habit information and preference information, determine the learning result information of the learning object, and the learning result information includes: different result levels and the knowledge points associated with each result level; based on each result level, determine the hierarchical education strategy of the educational digital human corresponding to this result level; introduce the corresponding knowledge points into the hierarchical education strategies of each result level, and extract the associated resources from the courseware library based on the knowledge points; use the hierarchical education strategies, knowledge points, and associated resources of all result levels as teaching strategies and content, and send the teaching strategies and content to the educational digital human.

[0116] In some embodiments of the present disclosure, the determination unit 502 of the above-mentioned device is further configured to: convert the to-be-processed corpus into a corpus vector; based on the corpus vector, match the course materials and emotional elements from the pre-constructed vector database; use the course materials and emotional elements as the interactive corpus information.

[0117] For the information interaction device provided by the embodiments of the present disclosure, first, the corpus receiving unit 501 receives the to-be-processed corpus sent by the learning object; second, the determination unit 502 determines the interactive corpus information based on the to-be-processed corpus and the pre-constructed vector database; third, the obtaining unit 503 sends the to-be-processed corpus and the interactive corpus information to the large language model to obtain the courseware information and / or interaction information output by the large language model; then, the sending unit 504 sends the courseware information to the educational digital human with an educational role, so that the educational digital human interacts with the learning object; finally, the interaction unit 505 sends the interaction information to the partner digital human with a partner role, so that the partner digital human interacts with the learning object. Thus, through this method, a real interactive experience can be achieved between the learning object and digital humans with different roles, enabling the learning object to immerse in the learning environment, effectively simulating the learning and communication scenarios in real life, and improving the learning experience of the learning object.

[0118] Further reference is made to Figure 6 , as an implementation of the methods shown in the above figures, the present disclosure provides another embodiment of an information interaction device, which is applied to an educational digital human, and this device embodiment corresponds to Figure 3 the method embodiment shown

[0119] As shown in Figure 6 , the information interaction device 600 provided in this embodiment includes: a courseware receiving unit 601, an explanation unit 602, a question receiving unit 603, and an answer generating unit 604. Among them, the above-mentioned courseware receiving unit 601 can be configured to receive courseware information. The above-mentioned explanation unit 602 can be configured to generate teaching explanation information based on the courseware information and provide the teaching explanation information to the learning object. The above-mentioned question receiving unit 603 can be configured to receive the classroom questions of the learning object. The above-mentioned answer generating unit 604 can be configured to generate classroom answers based on the classroom questions and send the classroom answers to the learning object.

[0120] In this embodiment, in the information interaction device 600: the specific processing of the courseware receiving unit 601, the explanation unit 602, the question receiving unit 603, and the answer generating unit 604 and the technical effects brought by them can respectively refer to Figure 3 the relevant descriptions of step 301, step 302, step 303, and step 304 in the corresponding embodiments, which will not be elaborated here.

[0121] In some embodiments of the present disclosure, the above-mentioned information interaction device 600 further includes: a first storage unit (not shown in the figure), and the first storage unit is configured to: extract the semantic vector and the emotion vector from the teaching explanation information and the classroom answers to obtain a first vector; store the first vector, the teaching explanation information, and the classroom answers in a vector database in a corresponding manner.

[0122] Further reference is made to Figure 7 , as an implementation of the methods shown in the above figures, the present disclosure provides yet another embodiment of an information interaction device, which is applied to a partner digital human, and this device embodiment corresponds to Figure 4 the method embodiment shown

[0123] As shown in Figure 7As shown in the figure, the information interaction device 700 provided in this embodiment includes: an information receiving unit 701, a corpus generating unit 702, and a providing unit 703. Among them, the above-mentioned information receiving unit 701 can be configured to receive interaction information and teaching explanation information sent by an educational digital human. The above-mentioned corpus generating unit 702 can be configured to generate learning corpus information based on the interaction information and the teaching explanation information. The above-mentioned providing unit 703 can be configured to provide the learning corpus information to a learning object. In this embodiment, in the information interaction device 700: the specific processing of the information receiving unit 701, the corpus generating unit 702, and the providing unit 703 and the technical effects brought by them can be respectively referred to Figure 4 the relevant descriptions of steps 401, 402, and 403 in the corresponding embodiments, which will not be elaborated here.

[0124] In some embodiments of the present disclosure, the above-mentioned information interaction device 700 further includes: a second storage unit (not shown in the figure), and the second storage unit is configured to: extract a semantic vector and an emotion vector from the learning corpus information to obtain a second vector; store the second vector and the learning corpus information in a vector database correspondingly.

[0125] As Figure 8 shown in the figure, the information interaction system 800 provided in this embodiment includes: a digital human interaction module 801, an educational digital human 802, and a partner digital human 803. The digital human interaction module 801 is used to receive the to-be-processed corpus sent by a learning object; determine interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; send the to-be-processed corpus and the interaction corpus information to a large language model to obtain courseware information and interaction information output by the large language model; send the courseware information to the educational digital human 802; send the interaction information to the partner digital human 803; the educational digital human 802 provides teaching explanation information to the learning object based on the courseware information; receives the classroom questions of the learning object and generates classroom answers to send to the learning object; the partner digital human 803 provides learning corpus information to the learning object based on the interaction information and the teaching explanation information.

[0126] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0127] Figure 9FIG. 0 shows a schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their manners of operation are merely examples and are not intended to limit the implementations of the present disclosure described and / or claimed herein.

[0128] As Figure 9 shown, the device 900 includes a computing unit 901 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0129] A plurality of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as, for example, a keyboard, a mouse, etc.; an output unit 907, such as, for example, various types of displays, speakers, etc.; a storage unit 908, such as, for example, a magnetic disk, an optical disk, etc.; and a communication unit 909, such as, for example, a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0130] The computing unit 901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 executes the various methods and processes described above, such as the information interaction method. For example, in some embodiments, the information interaction method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the information interaction method described above can be executed. Alternatively, in other embodiments, the computing unit 901 can be configured to execute the information interaction method by any other suitable means (e.g., by means of firmware).

[0131] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable information interaction device, such that when the program code is executed by the processor or controller, the patterns / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0133] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0135] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0136] It should be understood that various forms of the flows shown above can be used, with steps reordered, added, or removed. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitation is set herein.

[0137] The foregoing description of specific exemplary embodiments of the present disclosure is for purposes of illustration and exemplification. These descriptions are not intended to limit the present disclosure to the precise forms disclosed, and it is apparent that many modifications and variations are possible in light of the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles of the present disclosure and its practical applications, so that those skilled in the art can implement and utilize the various different exemplary embodiments of the present disclosure, as well as various different selections and modifications. The scope of the present disclosure is intended to be defined by the claims and their equivalents.

Claims

1. An information interaction method, the method comprising: Receiving the corpus to be processed sent by the learning object; Determining interaction corpus information based on the corpus to be processed and a pre-constructed vector database; Sending the corpus to be processed and the interaction corpus information to a large language model to obtain courseware information and / or interaction information output by the large language model; Sending the courseware information to an educational digital human with an educational role, so that the educational digital human interacts with the learning object; Sending the interaction information to a partner digital human with a partner role, so that the partner digital human interacts with the learning object.

2. The method according to claim 1, the method further comprising: Obtaining the object behavior data of the learning object; Based on the object behavior data, obtaining the habit information and preference information of the learning object; Based on the habit information and preference information, determining teaching data and resource information, and sending the teaching data and resource information to the educational digital human.

3. The method according to claim 1, there are multiple partner digital humans, and the partner roles of each partner digital human are different. The method further comprises: Obtaining the object behavior data of the learning object; Based on the object behavior data, obtaining the habit information and preference information of the learning object; Performing semantic recognition on the interaction information to determine a semantic recognition result; Based on the semantic recognition result, the habit information and the preference information, generating role identifiers for each partner digital human and output texts under each role identifier; Sending each role identifier and the output text under each role identifier to the corresponding partner digital human among the multiple partner digital humans, so that the partner digital human processes the output text from the perspective of the partner role corresponding to the role identifier.

4. The method according to claim 2 or 3, the method further comprising: Based on the habit information and preference information, determining the learning result information of the learning object, the learning result information including: different result levels and knowledge points associated with each result level; Based on each result level, determining the hierarchical education strategy of the educational digital human corresponding to the result level; Introducing the corresponding knowledge points into the hierarchical education strategies of each result level, and extracting associated resources from the courseware library based on the knowledge points; Taking the hierarchical education strategies, knowledge points and associated resources of all result levels as teaching strategies and content, and sending the teaching strategies and content to the educational digital human.

5. The method according to claim 1, the determining interaction corpus information based on the corpus to be processed and a pre-constructed vector database includes: Converting the corpus to be processed into a corpus vector; Based on the corpus vector, matching course materials and emotional elements from a pre-constructed vector database; Taking the course materials and the emotional elements as interaction corpus information.

6. An information interaction method, applied to an educational digital human, the method comprising: Receiving courseware information; Based on the courseware information, generating teaching explanation information, and providing the teaching explanation information to a learning object; Receiving the classroom questions of the learning object; Generate a classroom answer based on the classroom question and send the classroom answer to the learning object.

7. The method according to claim 6, wherein the method further comprises: Extract semantic vectors and sentiment vectors from the teaching explanation information and the classroom answer to obtain a first vector; Correspondingly store the first vector, the teaching explanation information, and the classroom answer in a vector database.

8. An information interaction method applied to a partner digital human, the method comprising: Receive interaction information and teaching explanation information sent by an educational digital human; Generate learning corpus information based on the interaction information and the teaching explanation information; Provide the learning corpus information to a learning object.

9. The method according to claim 8, wherein the method further comprises: Extract semantic vectors and sentiment vectors from the learning corpus information to obtain a second vector; Correspondingly store the second vector and the learning corpus information in a vector database.

10. An information interaction device, the device comprising: A corpus receiving unit configured to receive a to-be-processed corpus sent by a learning object; A determining unit configured to determine interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; A obtaining unit configured to send the to-be-processed corpus and the interaction corpus information to a large language model to obtain courseware information and / or interaction information output by the large language model; A sending unit configured to send the courseware information to an educational digital human with an educational role, so that the educational digital human interacts with the learning object; An interaction unit configured to send the interaction information to a partner digital human with a partner role, so that the partner digital human interacts with the learning object.

11. An information interaction system, the system comprising: A digital human interaction module, an educational digital human with an educational role, and a partner digital human with a partner role; The digital human interaction module is used to receive a to-be-processed corpus sent by a learning object; Determine interaction corpus information based on the to-be-processed corpus and a pre-constructed vector database; send the to-be-processed corpus and the interaction corpus information to a large language model to obtain courseware information and interaction information output by the large language model; send the courseware information to the educational digital human; Send the interaction information to the partner digital human; The educational digital human generates teaching explanation information based on the courseware information and provides the teaching explanation information to the learning object; Receive a classroom question from the learning object and generate a classroom answer to send the classroom question to the learning object; The partner digital human generates learning corpus information based on the interaction information and the teaching explanation information and provides the learning corpus information to the learning object.

12. An electronic device, characterized in that, Comprising: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the method according to any one of claims 1-9.

13. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

Images