Assisted learning method based on intelligent agent, intelligent agent training method and device

Abstract

The invention provides an agent-based auxiliary learning method and device and an agent training method and device, and relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, large language models, natural language processing and smart learning. According to the implementation scheme, an intelligent agent corresponding to a target subject is pushed to a target user; based on the intelligent agent, course content of the course is extracted and summarized, and a knowledge outline of the course is obtained; and providing the knowledge outline to the target user.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of deep learning, large language models, natural language processing and intelligent learning technology, and specifically to an agent-based auxiliary learning method, an agent training method for a target subject, an apparatus, an electronic device, a computer-readable storage medium and a computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] Vocational education is booming in China, with a growing market size, diversified competition, strong policy support, continuous advancement of educational innovation, and sustained growth in market demand. Most users of vocational education are employed people, whose learning time is fragmented, easily disturbed by external factors, and unstable plans. These users need efficient learning paths and expect to obtain specific learning strategies and tool guidance for exams within a limited time.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides an agent-based assisted learning method, a training method for an agent of a target subject, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0006] According to one aspect of the present disclosure, an agent-based assisted learning method is provided, the method comprising: pushing an agent corresponding to a target subject to a target user, the target user being determined based on the consumption behavior of the course for the target subject; based on the agent, extracting and summarizing the course content of the course to obtain a knowledge outline of the course, the knowledge outline including the knowledge structure of the course, various knowledge points and the correspondence between the knowledge points and the course content; and providing the knowledge outline to the target user.

[0007] According to another aspect of the present disclosure, a training method for an intelligent agent of a target subject is provided, the method comprising: obtaining a sample outline and a sample course of the target subject, the sample outline comprising a knowledge structure of the target subject, various knowledge points, and a correspondence between the knowledge points and the course content in the sample course; based on an initial intelligent agent, extracting and summarizing the course content of the sample course to obtain a knowledge outline of the sample course; and adjusting the parameters of the initial intelligent agent based on the sample outline and the knowledge outline; wherein the intelligent agent is used to push to a target user, the target user is determined based on the consumption behavior of the course for the target subject, and the intelligent agent is used to extract and summarize the course content of the course to obtain a target knowledge outline of the course.

[0008] According to another aspect of the present disclosure, an agent-based auxiliary learning device is provided, which includes: a first push unit, configured to push an agent corresponding to a target subject to a target user, where the target user is determined based on the consumption behavior of the course for the target subject; a first acquisition unit, configured to extract and summarize the course content of the course based on the agent, and obtain a knowledge outline of the course, where the knowledge outline includes the knowledge structure of the course, various knowledge points, and the correspondence between the knowledge points and the course content; and a first providing unit, configured to provide the knowledge outline to the target user.

[0009] According to another aspect of the present disclosure, there is provided a training device for an intelligent agent of a target subject, the device comprising: a first acquisition unit, configured to acquire a sample outline and a sample course of the target subject, the sample outline comprising a knowledge structure of the target subject, various knowledge points and a correspondence between the knowledge points and the course content in the sample course; a second acquisition unit, configured to extract and summarize the course content of the sample course based on the initial intelligent agent, and obtain a knowledge outline of the sample course; and an adjustment unit, configured to adjust the parameters of the initial intelligent agent based on the sample outline and the knowledge outline; wherein the intelligent agent is used to push to a target user, the target user is determined based on the consumption behavior of the course for the target subject, and the intelligent agent is used to extract and summarize the course content of the course, and obtain a target knowledge outline of the course.

[0010] According to another aspect of the present disclosure, an electronic device is provided, 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 to enable the at least one processor to execute the above-mentioned agent-based assisted learning method or the above-mentioned training method for an agent of a target subject.

[0011] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the above-mentioned agent-based assisted learning method or the above-mentioned training method for an agent of a target subject.

[0012] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned agent-based assisted learning method or the above-mentioned training method for an agent of a target subject.

[0013] According to another aspect of the present disclosure, an intelligent agent is provided, including: an input module for receiving input information; a processing module for determining a target task based on the input information received by the input module, determining a target model based on the target task, and implementing the above-mentioned intelligent agent-based auxiliary learning method by calling the target model to obtain output information; and an output module for outputting the output information obtained by the processing module.

[0014] According to one or more embodiments of the present disclosure, users can learn courses more efficiently.

[0015] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0017] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0018] Figure 2 A flow chart of an agent-based assisted learning method according to an embodiment of the present disclosure is shown;

[0019] Figure 3 A flow chart of an agent-based assisted learning method according to an embodiment of the present disclosure is shown;

[0020] Figure 4 A schematic diagram of the architecture of an agent-based assisted learning system according to an exemplary embodiment of the present disclosure is shown;

[0021] Figure 5 A flow chart of a method for training an agent of a target subject according to an embodiment of the present disclosure is shown;

[0022] Figure 6A structural block diagram of an agent-based auxiliary learning device according to an embodiment of the present disclosure is shown;

[0023] Figure 7 A structural block diagram of a training device for an intelligent agent of a target subject according to an embodiment of the present disclosure is shown;

[0024] Figure 8 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0025] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0026] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0027] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0028] In the related art, if a user wants to learn a certain course, he usually studies by watching the video course of the course and obtains relevant information (exam preparation experience, learning materials, etc.) through online search. Since the related courses and information lack systematicity and are relatively complicated, users often cannot study efficiently.

[0029] The present disclosure provides an agent-based assisted learning method, which promptly identifies the user as a target user who is learning the target subject by identifying the user's consumption behavior for the target subject course (such as watching, backing up, transferring, etc.), and pushes the agent corresponding to the target subject to the user, so that the agent can perform targeted content extraction and summary for the course that the user is currently consuming, generate a knowledge outline suitable for the course, and provide it to the target user, thereby enabling the user to learn the course more efficiently.

[0030] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0031] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0032] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable execution of the agent-based assisted learning method of the present disclosure or the training method of an agent for a target subject.

[0033] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0034] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0035] The user can use client devices 101, 102, 103, 104, 105 and / or 106 to learn the course. The client device can provide an interface that enables the user of the client device to interact with the client device. The client device can also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0036] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0037] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0038] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0039] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0040] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and / or 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and / or 106.

[0041] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0042] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0043] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0044] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0045] According to the embodiments of the present disclosure, Figure 2 As shown, an agent-based assisted learning method is provided, including: step S201, pushing an agent corresponding to a target subject to a target user, where the target user is determined based on the consumption behavior of the course for the target subject; step S202, based on the agent, extracting and summarizing the course content of the course to obtain a knowledge outline of the course, where the knowledge outline includes the knowledge structure of the course, various knowledge points, and the correspondence between the knowledge points and the course content; and step S203, providing the knowledge outline to the target user.

[0046] Therefore, by identifying the user's consumption behavior for the target subject course (such as watching, backing up, transferring, etc.), the user is promptly identified as the target user who is studying the target subject, and the intelligent agent corresponding to the target subject is pushed to the user, so that the intelligent agent can perform targeted content extraction and summary for the course that the user is currently consuming, generate a knowledge outline suitable for the course, and provide it to the target user, so that the user can learn the course more efficiently.

[0047] The intelligent agent is also called an agent, which can provide specific intelligent services to users based on the large model capabilities. The intelligent agent corresponding to the target subject can be an intelligent agent corresponding to the target subject, which is used to provide users with relevant auxiliary learning services for the target subject.

[0048] In some embodiments, the agent may be a client that is pushed to a target user through a target application, wherein the user may study a course of a target subject through the target application, that is, the target application includes a course corresponding to the target subject.

[0049] In some exemplary embodiments, the target application may be a network disk application, and the user may study a target subject by watching courses stored in the network disk (eg, a video tutorial of a subject transferred or uploaded by the user).

[0050] In some exemplary embodiments, the user's consumption behavior for the above courses includes but is not limited to viewing, downloading, backing up, transferring, etc. In some exemplary embodiments, the above consumption behavior may also include purchasing, sharing, etc. of the courses, which is not limited here.

[0051] In some embodiments, it is possible to detect whether the user has consumption behavior for a certain course on the target application, and in response to detecting the existence of consumption behavior for the target subject course, the user is determined as a target user, that is, a user who may be studying the target subject.

[0052] After a target user is identified, the intelligent agent corresponding to the target subject can be pushed to the target user.

[0053] In some embodiments, the intelligent agent can extract and summarize the course content of the above-mentioned target subject that the target user is studying, and generate a corresponding knowledge outline based on the course.

[0054] In some embodiments, the above-mentioned courses may include text course content (such as document materials corresponding to the target subject), and the intelligent agent may analyze and summarize the above-mentioned document materials and extract knowledge points to generate a knowledge outline of the course.

[0055] In some embodiments, the above-mentioned knowledge outline may include the knowledge structure of the above-mentioned course, each knowledge point, and the correspondence between each knowledge point and the course content. Among them, each knowledge point may also include one or more of the summary of the knowledge point, the knowledge explanation, or the shorthand notes; for courses that only contain text content, the above-mentioned correspondence may be, for example, the location of the original course content involved in each knowledge point in the above-mentioned document materials; if the target user is studying the course through a network disk application, the above-mentioned correspondence may also record the file path information of the original course content involved in each knowledge point in the network disk.

[0056] After obtaining the above knowledge outline, it can be provided to the target user, so that the user can study the above course conveniently and systematically based on the knowledge outline generated by the course content of the above course.

[0057] In some embodiments, the course may include at least one course video, and the correspondence may include a correspondence between a knowledge point and at least one video clip in the course video.

[0058] Therefore, when a course includes a course video, the convenience of user learning can be further improved by matching knowledge points with video clips in the course video.

[0059] In some embodiments, the course content of the above-mentioned courses usually includes one or more course videos. When generating the knowledge outline, the voice in the video course can be first extracted, and the subtitles of the video course can be obtained based on the voice. The subtitles of the above-mentioned courses are analyzed and summarized and the knowledge points are extracted through the above-mentioned intelligent agent, so as to generate the knowledge outline of the course.

[0060] In some embodiments, the analysis and summary of the subtitles of the course and the extraction of knowledge points can be obtained based on the knowledge outline generation capability based on the large language model corresponding to the target subject provided by the intelligent agent, for example, the knowledge outline generation model integrated in the intelligent agent. The intelligent agent or the knowledge outline generation model can be obtained through supervised fine-tuning training based on the general large language model, and the specific training method will be described in detail below.

[0061] In some embodiments, an entrance to the above-mentioned intelligent agent may be provided on the course video playback interface of the above-mentioned course or the material display interface of the above-mentioned course for users to perform convenient operations.

[0062] In some embodiments, the entry for the agent may also be provided at a certain location in the information recommendation list of the target application.

[0063] In some embodiments, the intelligent agent is pushed to the target user via an information recommendation list. The above-mentioned intelligent agent-based assisted learning method may also include: determining the target user's consumption demand level for the course based on the type of consumption behavior, the consumption behavior including at least one of watching, downloading, backing up and transferring; and determining the insertion position of the intelligent agent in the information recommendation list based on the consumption demand level.

[0064] Therefore, through the types of user consumption behaviors, the target user's consumption demand for courses can be determined, and then the recommended position of the intelligent agent in the information recommendation list can be determined, so as to realize personalized intelligent agent recommendations for different users and improve user experience.

[0065] The intelligent agent of each target subject is aimed at a certain group of people in vocational education. For example, the intelligent agent corresponding to the target subject of first-level construction engineer is aimed at the group of construction engineers in the civil construction industry.

[0066] In some embodiments, the target user of the agent corresponding to the target subject can be determined based on the user's consumption behavior of the course of the target subject in the target application.

[0067] In some embodiments, the target users can be further divided according to the degree of consumption demand based on the categories of their consumption behaviors for the above courses, and then the intelligent entities can be pushed in different positions in the information recommendation list according to the degree of consumption demand of the target users.

[0068] In some exemplary embodiments, the target users can be further divided into three categories: high-precision group, precise group and confused group. Among them, users whose behaviors of playing or watching a certain course video of the target subject account for more than 50% of the total video playing behaviors on a certain day can be determined as high-precision users; users who have performed consumption behaviors such as backing up, transferring or downloading the course content of the target subject are determined as precise users; users who have consumed course content of other subjects of the same category as the target subject are determined as confused groups. Thus, the consumption needs of the target users for the target course are determined by the categories of the users' consumption behaviors. It is understandable that the relevant technical personnel can set the method of dividing the target users according to actual needs, which will not be elaborated here.

[0069] After the target users are divided, the recommended position of the agent in the information recommendation list can be further determined according to the consumption demand levels of target users of different categories, thereby realizing personalized agent recommendations for different users and improving user experience.

[0070] In some embodiments, based on the degree of consumer demand, determining the insertion position of the intelligent agent in the information recommendation list may include: determining the insertion position of the intelligent agent in the information recommendation list according to the principle that the higher the degree of consumer demand, the closer the insertion position.

[0071] Therefore, by determining the insertion position of the intelligent agent in the information recommendation list according to the principle that the higher the consumer demand, the earlier the insertion position, the intelligent agent service can more easily reach high-demand users while reducing disturbance to low-demand users.

[0072] In some exemplary embodiments, the consumption demand of high-precision users is relatively high. When pushing intelligent agents to such users, the intelligent agents can be inserted at the front of the information recommendation list so that the users here can more conveniently obtain the services of the intelligent agents. On the contrary, the consumption demand of confused users is usually not high. When pushing intelligent agents to such users, the intelligent agents can be inserted at the back of the information recommendation list to reduce the disturbance to low-demand users.

[0073] In some embodiments, the above-mentioned agent-based assisted learning method may also include: in response to detecting the target user's learning behavior for the first knowledge point in the knowledge outline, generating at least one exercise question through the agent based on the course content corresponding to the first knowledge point.

[0074] Therefore, by detecting the user's learning behavior for the first knowledge point in real time and generating exercises in time to provide to the user, the convenience of user learning can be further improved.

[0075] In some embodiments, in response to detecting the user's consumption behavior for the course content, the first knowledge point corresponding to the course content can be determined based on the correspondence between the course content and the knowledge points in the knowledge syllabus, and it can be considered that the user has learned the first knowledge point and has a certain degree of learning and understanding of the first knowledge point. On this basis, the intelligent agent can push exercises corresponding to the first knowledge point to detect the user's mastery of the knowledge point.

[0076] In some embodiments, the exercises can be generated by the agent based on the relevant course content of the first knowledge point. In some embodiments, the exercises can also be retrieved from the Internet by the agent based on the first knowledge point and the relevant course content.

[0077] In some embodiments, the above-mentioned agent-based assisted learning method may also include: in response to the target user completing at least one exercise, determining the target user's mastery of the first knowledge point according to the target user's answer results; and through the agent, pushing the learning content of the next learning stage to the target user based on the mastery level and the knowledge outline.

[0078] Therefore, based on the user's answers, the user's mastery of the first knowledge point is determined, and then the next stage of learning content is pushed to the user based on the degree of mastery, thereby further improving the convenience of user learning.

[0079] In some exemplary embodiments, in response to the user answering the question correctly, it can be considered that the user has mastered the first knowledge point, and the next knowledge point of the first knowledge point is obtained in the knowledge outline, and the relevant course content, knowledge explanation and shorthand notes of the knowledge point are pushed to the user. In some embodiments, the learning progress of the first knowledge point can be updated to 100% at the same time, and the current timestamp is recorded to update and record the user's learning progress in real time.

[0080] In some exemplary embodiments, in response to the user's incorrect answer, it can be considered that the user still needs to consolidate the learning of the first knowledge point, and the knowledge explanation, shorthand notes, etc. of the first knowledge point are pushed to the user based on the knowledge outline. After the user completes the learning, the practice questions are pushed again until the user answers correctly or skips the learning of the knowledge point.

[0081] In some embodiments, Figure 3 As shown, the above-mentioned agent-based assisted learning method may also include: step S301, determining whether the target user is in the preliminary preparation stage based on the interaction content between the target user and the agent, wherein the interaction content includes at least one of the information content browsed by the target user through the agent and the query text sent by the target user to the agent; step S302, in response to determining that the target user is in the preliminary preparation stage, searching and summarizing information related to the target subject based on the agent to obtain target information, wherein the target information includes at least one of the test information, test preparation experience, and learning materials of the target subject; and step S303, providing the target information to the target user.

[0082] For a certain target subject, the user's needs may also include one or more of the following: obtaining test preparation experience, obtaining learning materials, obtaining basic information (including test information, knowledge point explanations, etc.), etc. The overall learning path may include test information, test preparation experience, learning materials, knowledge learning, and achievement verification.

[0083] In some embodiments, based on the interaction content between the target user and the agent, it is possible to determine the approximate learning stage of the user. If the user is determined to be in the preliminary preparation stage based on the interaction content with the agent, the agent can collect information related to the target subject in real time, summarize and generate relevant target information and push it to the target user.

[0084] This can further improve the convenience for users to obtain information related to the target subject.

[0085] Figure 4 A schematic diagram of the architecture of an agent-based assisted learning system according to an exemplary embodiment of the present disclosure is shown.

[0086] In some exemplary embodiments, Figure 4 As shown in the figure, the agent-based assisted learning system can be developed based on the application development platform, which can provide large model capabilities and scheduling frameworks. On this basis, the system can realize services for video content understanding, knowledge point extraction, and knowledge outline generation through the agent, and push knowledge points, exercises, and knowledge point review content to users based on their current learning progress, and update the user's learning progress based on the user's consumption results of the pushed content.

[0087] In some exemplary embodiments, the entrance to the above-mentioned agent can be provided on the course video playback interface or the course material display interface for users to conveniently operate. In some exemplary embodiments, the entrance to the above-mentioned agent can also be provided at a certain position in the information recommendation list of the target application.

[0088] In some embodiments, Figure 5 As shown, a training method for an intelligent agent of a target subject is provided, comprising: step S501, obtaining a sample outline and a sample course of the target subject, the sample outline comprising the knowledge structure of the target subject, various knowledge points and the correspondence between the knowledge points and the course content in the sample course; step S502, based on the initial intelligent agent, extracting and summarizing the course content of the sample course to obtain the knowledge outline of the sample course; and step S503, adjusting the parameters of the initial intelligent agent based on the sample outline and the knowledge outline; wherein the intelligent agent is used to push to the target user, the target user is determined based on the consumption behavior of the course for the target subject, and the intelligent agent is used to extract and summarize the course content of the course to obtain the target knowledge outline of the course.

[0089] The training method for the target subject agent can be used to train an agent for the agent-based auxiliary learning method. By identifying the user's consumption behavior for the target subject course (such as viewing, backing up, transferring, etc.), the user is promptly identified as the target user who is learning the target subject, and the agent corresponding to the target subject is pushed to the user, so that the agent can extract and summarize the content of the course currently consumed by the user in a targeted manner, generate a knowledge outline suitable for the course, and provide it to the target user, so that the user can learn the course more efficiently.

[0090] Currently, large language models are developing rapidly. Their powerful semantic understanding and human instruction compliance capabilities make them the best choice for processing text data. Knowledge outline is a specific task, which requires supervised fine-tuning to fine-tune the large model and improve its performance on this task.

[0091] In some embodiments, the sample outline may be an exam outline corresponding to the target subject, including the knowledge framework and various knowledge points of the target subject. The sample course may include a course of the target subject with a high number of hits or views on the Internet.

[0092] In some embodiments, the correspondence between knowledge points and course content can be obtained in the following manner: first, the course content of the sample course is extracted, and the extracted course content is analyzed and summarized through a large language model to obtain the knowledge points corresponding to the course content; by means of similarity calculation, the sample outline knowledge points and course content knowledge points with a similarity higher than a preset relevance are matched to determine the correspondence between the knowledge points of the sample outline and the course content.

[0093] In some embodiments, for the target subject, one or more sets of the above-mentioned sample data can be obtained in the above-mentioned manner, and the initial intelligent agent can be trained based on the above-mentioned sample data until the optimization goal is reached, thereby obtaining an intelligent agent capable of generating a knowledge outline.

[0094] In some embodiments, the sample course includes at least one course video, and the correspondence includes a correspondence between a knowledge point and at least one video clip in the course video.

[0095] In some embodiments, Figure 6 As shown, an agent-based auxiliary learning device 600 is provided, and the device 600 includes: a first push unit 610, configured to push the agent corresponding to the target subject to the target user, and the target user is determined based on the consumption behavior of the course for the target subject; a first acquisition unit 620, configured to extract and summarize the course content of the course based on the agent, and obtain the knowledge outline of the course, the knowledge outline includes the knowledge structure of the course, each knowledge point and the correspondence between the knowledge point and the course content; and a first providing unit 630, configured to provide the knowledge outline to the target user.

[0096] in, Figure 6 The various units of the device 600 shown in FIG. 6 can be compared with those of the reference Figure 2 The steps in the agent-assisted learning method described above correspond to each other. Therefore, the operations, features and advantages described above for the agent-assisted learning method described above are also applicable to the device 600 and the various units included therein. For the sake of brevity, some operations, features and advantages are not repeated here.

[0097] In some embodiments, the intelligent agent is pushed to the target user via an information recommendation list. The above-mentioned intelligent agent-based auxiliary learning device may also include: a first determination unit, configured to determine the target user's consumption demand level for the course based on the type of consumption behavior, the consumption behavior including at least one of watching, downloading, backing up and transferring; and a second determination unit, configured to determine the insertion position of the intelligent agent in the information recommendation list based on the consumption demand level.

[0098] In some embodiments, the second determination unit may be further configured to determine the insertion position of the agent in the information recommendation list according to the principle that the higher the consumer demand, the earlier the insertion position.

[0099] In some embodiments, the course may include at least one course video, and the correspondence may include a correspondence between a knowledge point and at least one video clip in the course video.

[0100] In some embodiments, the above-mentioned agent-based assisted learning device may also include: a generation unit, which is configured to generate at least one exercise question based on the course content corresponding to the first knowledge point in the knowledge outline through the agent in response to detecting the target user's learning behavior for the first knowledge point in the knowledge outline.

[0101] In some embodiments, the above-mentioned agent-based assisted learning device may also include: a third determination unit, configured to determine the target user's mastery of the first knowledge point in response to the target user completing at least one exercise question according to the target user's answer result; and a second push unit, configured to push the learning content of the next learning stage to the target user through the agent based on the mastery level and the knowledge outline.

[0102] In some embodiments, the above-mentioned agent-based assisted learning device may also include: a fourth determination unit, configured to determine whether the target user is in the preliminary preparation stage based on the interaction content between the target user and the agent, wherein the interaction content includes at least one of the information content browsed by the target user through the agent and the query text sent by the target user to the agent; a second acquisition unit, configured to search and summarize information related to the target subject based on the agent in response to determining that the target user is in the preliminary preparation stage to obtain target information, the target information including at least one of the test information, test preparation experience, and learning materials of the target subject; and a second providing unit, configured to provide the target information to the target user.

[0103] In some embodiments, Figure 7As shown, a training device 700 for an intelligent agent of a target subject is provided, and the device 700 includes: a first acquisition unit 710, configured to acquire a sample outline and a sample course of the target subject, the sample outline including the knowledge structure of the target subject, various knowledge points, and the correspondence between the knowledge points and the course content in the sample course; a second acquisition unit 720, configured to extract and summarize the course content of the sample course based on the initial intelligent agent, and obtain the knowledge outline of the sample course; and an adjustment unit 730, configured to adjust the parameters of the initial intelligent agent based on the sample outline and the knowledge outline; wherein the intelligent agent is used to push to the target user, the target user is determined based on the consumption behavior of the course for the target subject, and the intelligent agent is used to extract and summarize the course content of the course, and obtain the target knowledge outline of the course.

[0104] in, Figure 7 The various units of the device 700 shown in FIG. 7 can be used in conjunction with the reference Figure 5 The above-described operations, features and advantages of the training method for an agent of a target subject are corresponding to the steps in the training method for an agent of a target subject. Thus, the operations, features and advantages described above for the training method for an agent of a target subject are also applicable to the apparatus 700 and the various units included therein. For the sake of brevity, some operations, features and advantages are not described in detail herein.

[0105] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0106] According to an embodiment of the present disclosure, there is also provided an intelligent agent including: an input module for receiving input information; a processing module for determining a target task based on the input information received by the input module, determining a target model based on the target task, and implementing the above-mentioned intelligent agent-based auxiliary learning method by calling the target model to obtain output information; and an output module for outputting the output information obtained by the processing module.

[0107] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0108] refer to Figure 8, a block diagram of an electronic device 800 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, 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 personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0109] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0110] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 can be any type of device that can input information to the electronic device 800. The input unit 806 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 807 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 808 can include but is not limited to a disk, an optical disk. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0111] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 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, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the above-mentioned agent-based auxiliary learning method or the above-mentioned training method for the agent of the target subject. For example, in some embodiments, the above-mentioned agent-based auxiliary learning method or the above-mentioned training method for the agent of the target subject may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the above-mentioned agent-based auxiliary learning method or the above-mentioned training method for the agent of the target subject may be executed. Alternatively, in other embodiments, the computing unit 801 may be configured in any other suitable manner (e.g., by means of firmware) to execute the above-mentioned agent-based assisted learning method or the above-mentioned training method for an agent of a target subject.

[0112] Various implementations of the systems and techniques described above herein 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), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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 special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0114] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 input, voice input, or tactile input).

[0116] The systems and techniques described herein may 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 with a graphical user interface or a web browser through which a user can interact with implementations 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 may 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.

[0117] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0118] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0119] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. An agent-based assisted learning method, the method comprising: Pushing an agent corresponding to a target subject to a target user, the target user being determined based on consumption behavior of a course for the target subject; Based on the agent, extract and summarize the course content of the course to obtain a knowledge outline of the course, wherein the knowledge outline includes the knowledge structure of the course, various knowledge points, and the corresponding relationship between the knowledge points and the course content; as well as The knowledge outline is provided to the target user.

2. The method according to claim 1, wherein: The agent pushes the information recommendation list to the target user, and the method further includes: Determining the target user's consumption demand for the course according to the type of the consumption behavior, wherein the consumption behavior includes at least one of viewing, downloading, backing up, and transferring; and Based on the degree of consumption demand, the insertion position of the agent in the information recommendation list is determined.

3. The method according to claim 2, wherein: The step of determining the insertion position of the agent in the information recommendation list based on the degree of consumption demand includes: The insertion position of the agent in the information recommendation list is determined according to the principle that the higher the degree of consumer demand, the earlier the insertion position.

4. The method according to any one of claims 1 to 3, wherein: The course includes at least one course video, and the corresponding relationship includes a corresponding relationship between the knowledge point and at least one video clip in the course video.

5. The method according to any one of claims 1 to 4, further comprising: In response to detecting the target user's learning behavior for a first knowledge point in the knowledge outline, at least one exercise is generated by the agent based on the course content corresponding to the first knowledge point.

6. The method according to claim 5, further comprising: In response to the target user completing the at least one exercise question, determining the target user's mastery of the first knowledge point according to the target user's answer result; as well as Through the intelligent agent, based on the mastery level and the knowledge outline, the learning content of the next learning stage is pushed to the target user.

7. The method according to any one of claims 1 to 6, further comprising: Determining whether the target user is in the preliminary preparation stage based on the interactive content between the target user and the agent, wherein the interactive content includes at least one of the information content browsed by the target user through the agent and the query text sent by the target user to the agent; In response to determining that the target user is in an early preparation stage, searching and summarizing information related to the target subject based on the agent to obtain target information, the target information including at least one of test information, test preparation experience, and learning materials of the target subject; and The target information is provided to the target user.

8. A method for training an agent for a target subject, the method comprising: Obtaining a sample syllabus and a sample course of the target subject, wherein the sample syllabus includes a knowledge framework of the target subject, various knowledge points, and a correspondence between the knowledge points and course content in the sample course; Based on the initial agent, extract and summarize the course content of the sample course to obtain the knowledge outline of the sample course; as well as Based on the sample outline and the knowledge outline, adjusting the parameters of the initial agent; wherein, The intelligent agent is used to push to the target user, and the target user is determined based on the consumption behavior of the course for the target subject, and the intelligent agent is used to extract and summarize the course content of the course to obtain the target knowledge outline of the course.

9. According to the method of claim 8, the sample course includes at least one course video, and the corresponding relationship includes the corresponding relationship between the knowledge point and at least one video clip in the course video.

10. An agent-based auxiliary learning device, comprising: A first push unit is configured to push an agent corresponding to a target subject to a target user, the target user being determined based on a consumption behavior of a course for the target subject; A first acquisition unit is configured to extract and summarize the course content of the course based on the agent to obtain a knowledge outline of the course, wherein the knowledge outline includes a knowledge framework of the course, various knowledge points, and a corresponding relationship between the knowledge points and the course content; as well as The first providing unit is configured to provide the knowledge outline to the target user.

11. The device according to claim 10, wherein: The agent pushes the information recommendation list to the target user, and the device further includes: A first determining unit is configured to determine the target user's consumption demand for the course according to the type of the consumption behavior, wherein the consumption behavior includes at least one of viewing, downloading, backing up, and transferring; and The second determination unit is configured to determine the insertion position of the agent in the information recommendation list based on the consumption demand level.

12. The device according to claim 11, wherein The second determining unit is further configured to: The insertion position of the agent in the information recommendation list is determined according to the principle that the higher the degree of consumer demand, the earlier the insertion position.

13. The device according to any one of claims 10 to 12, wherein: The course includes at least one course video, and the corresponding relationship includes a corresponding relationship between the knowledge point and at least one video clip in the course video.

14. The device according to any one of claims 10 to 13, further comprising: The generating unit is configured to generate at least one exercise question based on the course content corresponding to the first knowledge point through the intelligent agent in response to detecting the learning behavior of the target user for the first knowledge point in the knowledge outline.

15. The apparatus according to claim 14, further comprising: A third determining unit is configured to determine, in response to the target user completing the at least one exercise question, the mastery degree of the target user on the first knowledge point according to the answer result of the target user; as well as The second push unit is configured to push the learning content of the next learning stage to the target user through the intelligent agent based on the mastery level and the knowledge outline.

16. The device according to any one of claims 10 to 15, further comprising: a fourth determining unit configured to determine whether the target user is in the preliminary preparation stage based on the interactive content between the target user and the agent, wherein the interactive content includes at least one of the information content browsed by the target user through the agent and the query text sent by the target user to the agent; A second acquisition unit is configured to, in response to determining that the target user is in an early preparation stage, search and summarize information related to the target subject based on the agent to obtain target information, wherein the target information includes at least one of test information, test preparation experience, and learning materials of the target subject; and A second providing unit is configured to provide the target information to the target user.

17. A training device for an intelligent agent of a target subject, the device comprising: A first acquisition unit is configured to acquire a sample syllabus and a sample course of the target subject, wherein the sample syllabus includes a knowledge framework of the target subject, various knowledge points, and a correspondence between the knowledge points and course content in the sample course; A second acquisition unit is configured to extract and summarize the course content of the sample course based on the initial agent to obtain the knowledge outline of the sample course; as well as An adjustment unit is configured to adjust the parameters of the initial agent based on the sample outline and the knowledge outline; wherein, The intelligent agent is used to push to the target user, and the target user is determined based on the consumption behavior of the course for the target subject, and the intelligent agent is used to extract and summarize the course content of the course to obtain the target knowledge outline of the course.

18. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed 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 perform the method according to any one of claims 1 to 9.

19. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-9.

20. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

21. An intelligent agent comprises: An input module, used for receiving input information; A processing module, configured to determine a target task based on the input information received by the input module, determine a target model based on the target task, and implement the method according to any one of claims 1 to 7 by calling the target model to obtain output information; An output module is used to output the output information obtained by the processing module.

Images