A teaching prompt information generation system and method based on dynamic role image

Abstract

The application discloses a teaching prompt information generation system and method based on dynamic role image, relates to the technical field of education, and comprises a cooperative analysis module and a prompt information generation module; the cooperative analysis module and the prompt information generation module are connected; the cooperative analysis module is used for analyzing the cooperative ability and the cooperative contribution degree of students at each cooperative stage according to multi-modal behavior data and cooperative demand information of a target cooperative project, and sending the cooperative ability and the cooperative contribution degree to the prompt information generation module; the prompt information generation module is used for generating dynamic role images of students at each cooperative stage; and according to the dynamic role images and the cooperative stages corresponding to the dynamic role images, the cooperative prompt content of the students is generated to prompt the students to participate in the target cooperative project. Through the analysis of the cooperative ability and the contribution degree of the students, the application realizes accurate judgment on the cooperative performance of the students at different stages, can stimulate the learning potential of the students, and improves the overall cooperative efficiency of the group.

Description

Technical Field

[0001] This application relates to the field of educational technology, and in particular to a teaching prompt information generation system and method based on dynamic character profiles. Background Technology

[0002] Before project-based learning (PBL) or collaborative learning begins, students need to be grouped. Currently, students are mainly grouped by using static profiles of students. That is, based on static data such as students' personality tags, historical grades, and ability assessments before the start of collaborative learning, collaborative groups are divided and initial roles are assigned through feature matching algorithms.

[0003] However, static profiles are generated based on students' historical static data and can only reflect the students' state before collaborative learning begins. They cannot capture the dynamic behavioral characteristics of students as the situation changes at different stages of project-based or collaborative learning. Consequently, they cannot perceive the evolution of different roles such as "silent executor," "strong coordinator," and "detached thinker" caused by differences in students' personality, abilities, and behavioral patterns. This makes it impossible to make targeted adjustments to grouping results, role assignments, and collaborative guidance based on the dynamic changes in students' role status.

[0004] Students' collaborative roles remain unchanged from their initial roles, leading to more active participation from students who enjoy discussion and further silence from quiet students. This results in quiet students being unable to unleash their learning potential and students being unable to improve their abilities through collaborative projects. The mismatch between collaborative roles and dynamic situations can lead to communication problems within the collaborative group, thereby reducing the overall collaborative efficiency of the group. Summary of the Invention

[0005] In view of this, this application provides a teaching prompt information generation system and method based on dynamic role profiles. The main purpose is to improve the existing technology that groups students according to static profiles, where students' collaborative roles are always the initial collaborative roles. This results in students who like to discuss becoming more active in collaboration, while silent students become even more silent, which in turn prevents silent students from stimulating their learning potential and prevents students from improving their abilities through collaborative projects. Furthermore, the mismatch between collaborative roles and dynamic situations can lead to communication problems in collaborative groups, thereby reducing the overall collaborative efficiency of the group.

[0006] In the first aspect, this application provides a teaching prompt information generation system based on dynamic character profiles, including: a collaborative analysis module and a prompt information generation module; The collaborative analysis module and the prompt information generation module are connected; The collaboration analysis module is used to acquire multimodal behavior data of students in the target collaboration project; based on the multimodal behavior data and the collaboration requirements information of the target collaboration project, it analyzes the students' collaboration ability and contribution at each collaboration stage in the target collaboration project, and sends the collaboration ability and contribution to the prompt information generation module. The prompt information generation module is used to generate a dynamic role profile of the student at each collaborative stage of the target collaborative project based on the collaborative ability and the collaborative contribution; and to generate collaborative prompt content for the student based on the dynamic role profile and the corresponding collaborative stage, so as to prompt the student to participate in the target collaborative project according to the collaborative prompt content.

[0007] Optionally, the collaborative analysis module includes: a data processing module and a capability contribution analysis module; The data processing module is connected to the capability contribution analysis module, and the capability contribution analysis module is connected to the prompt information generation module; The data processing module is used to identify the student's multi-dimensional speech characteristics based on the speech data in the multi-modal behavioral data, and evaluate the student's active participation in the target collaborative project based on the multi-dimensional speech characteristics; identify the student's multi-dimensional thinking characteristics based on the text data in the multi-modal behavioral data, and evaluate the student's active thinking in the target collaborative project based on the multi-dimensional thinking characteristics; determine the teacher's evaluation data of the student's behavior in the target collaborative project based on the behavioral data in the multi-modal behavioral data, and send the active participation in speaking, the active thinking, and the behavioral data to the ability contribution analysis module; The capability contribution analysis module is used to analyze the student's collaborative ability and contribution at each stage of the target collaborative project based on the student's speaking activity level, thinking activity level, behavioral evaluation data, and collaborative requirements information of the target collaborative project, and sends the collaborative ability and contribution to the prompt information generation module.

[0008] Optionally, the capability contribution analysis module includes a feature data analysis module and a fusion analysis module; The feature data analysis module and the fusion analysis module are connected, and the fusion analysis module and the prompt information generation module are connected; The feature data analysis module is used to determine the multi-dimensional benchmark evaluation features and multi-dimensional adjustment evaluation features corresponding to the target collaborative project; based on the level of speaking activity, the level of thinking activity, and the behavioral evaluation data, it analyzes at least one benchmark feature data corresponding to the student and at least one feature data to be adjusted for the student in each collaborative stage of the target collaborative project according to the multi-dimensional benchmark evaluation features; The fusion analysis module is used to analyze the student's collaborative ability and contribution to each collaborative stage of the target collaborative project based on the baseline weights corresponding to the at least one baseline feature data and the adjustment weights corresponding to the at least one feature data to be adjusted.

[0009] Optionally, the fusion analysis module is connected to both the feature data analysis module and the prompt information generation module; The fusion analysis module is used to determine the benchmark weight corresponding to the at least one benchmark feature data; based on the collaboration requirement information of the target collaboration project, determine the stage feature score corresponding to each collaboration stage in the target collaboration project, and determine the adjustment weight corresponding to each collaboration stage based on the stage feature score; perform fusion analysis on the at least one benchmark feature data and the at least one feature data to be adjusted based on the benchmark weight and the adjustment weight to obtain the student's collaboration ability and collaboration contribution corresponding to each collaboration stage, and send the collaboration ability and collaboration contribution to the prompt information generation module.

[0010] Optionally, the prompt information generation module includes: a role information generation module and a prompt content generation module; The character information generation module and the prompt content generation module are connected; The role information generation module is used to determine the target collaboration scenario corresponding to the target collaboration stage in the target collaboration project, and to identify the student's collaboration role information in the target collaboration stage based on the target dynamic role profile, wherein the target collaboration stage is any stage in the target collaboration project. The prompt content generation module is used to generate collaboration prompt content for the student based on the target collaboration scenario and the collaboration role information, so as to prompt the student to participate in the target collaboration project according to the collaboration prompt content in the target collaboration stage.

[0011] Optionally, the prompt content generation module is used to generate at least one candidate prompt information corresponding to the student based on the target collaboration scenario and the collaboration role information, and determine the priority information corresponding to the at least one candidate prompt information; select target prompt information from the at least one candidate prompt information according to the priority information; and generate collaboration prompt content for the student based on the target prompt information.

[0012] Optionally, the prompt information generation module is used to respond to the recognition of the student's target operation behavior data based on the collaborative prompt content participating in the target collaborative project, generate operation feedback information corresponding to the student based on the target operation behavior data, and update the student's dynamic role profile based on the operation feedback information.

[0013] Secondly, this application provides a method for generating teaching prompts based on dynamic character profiles, including: Obtain multimodal behavioral data of students in the target collaborative project; Based on the multimodal behavioral data and the collaboration requirements information of the target collaborative project, the student's collaboration ability and contribution to each stage of the target collaborative project are analyzed. Based on the collaborative ability and the degree of collaborative contribution, a dynamic role profile of the student is generated for each collaborative stage of the target collaborative project; Based on the dynamic character profile and the corresponding collaboration stage, collaboration prompts are generated for the student to guide them to participate in the target collaboration project.

[0014] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the teaching prompt information generation system based on dynamic character portraits described in the first aspect.

[0015] Fourthly, this application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the teaching prompt information generation system based on dynamic character portraits as described in the first aspect.

[0016] Fifthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the teaching prompt information generation system based on dynamic character portraits described in the first aspect.

[0017] Using the above technical solution, this application provides a teaching prompt information generation system and method based on dynamic role profiles, including: a collaboration analysis module and a prompt information generation module; the collaboration analysis module and the prompt information generation module are connected; the collaboration analysis module is used to analyze the student's collaboration ability and contribution at each collaboration stage based on multimodal behavioral data and the collaboration requirements information of the target collaboration project, and sends the collaboration ability and contribution to the prompt information generation module; the prompt information generation module is used to generate a dynamic role profile of the student at each collaboration stage of the target collaboration project; based on the dynamic role profile and the corresponding collaboration stage, the system generates collaboration prompt content for the student to prompt the student to participate in the target collaboration project according to the collaboration prompt content. Compared with existing technologies, this application analyzes students' collaborative abilities and contributions at each stage of the target collaborative project based on multimodal behavioral data and collaborative requirements information, enabling accurate judgment of students' collaborative performance at different stages. It generates dynamic role profiles for students at each stage of the target collaborative project based on their collaborative abilities and contributions, preventing students from being fixed in a single collaborative role. Furthermore, it generates collaborative prompts for students based on these dynamic role profiles and the corresponding collaborative stages, guiding students to participate in the target collaborative project according to these prompts, thereby stimulating students' learning potential and improving the overall collaborative efficiency of the group. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This illustration shows a schematic diagram of a teaching prompt information generation system based on dynamic character portraits provided in an embodiment of this application; Figure 2 The illustration shows a flowchart of a method for generating teaching prompts based on dynamic character portraits according to an embodiment of this application; Figure 3 This illustration shows a schematic diagram of the module interaction process of an example of context-aware collaborative role recognition and personalized prompts provided in an embodiment of this application; Figure 4 The illustration shows a flowchart of an example of context-aware collaborative role recognition and personalized prompts provided in an embodiment of this application; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0019] exist Figure 1 middle: 1-Collaboration Analysis Module; 11-Data Processing Module; 12-Capability Contribution Analysis Module; 121-Feature Data Analysis Module; 122-Fusion Analysis Module; 2- Prompt information generation module; 21- Role information generation module; 22- Prompt content generation module. Detailed Implementation

[0020] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0021] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0022] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0023] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0024] The following is combined Figure 1 This application describes a teaching prompt information generation system based on dynamic character portraits according to some embodiments.

[0025] This application provides a teaching prompt information generation system based on dynamic character portraits, such as... Figure 1As shown, the system includes a collaboration analysis module 11 and a prompt information generation module 22; the collaboration analysis module 1 and the prompt information generation module 2 are connected; the collaboration analysis module 1 is used to acquire multimodal behavior data of students in the target collaboration project; based on the multimodal behavior data and the collaboration requirements information of the target collaboration project, it analyzes the students' collaboration ability and contribution in each collaboration stage of the target collaboration project, and sends the collaboration ability and contribution to the prompt information generation module 2; the prompt information generation module 2 is used to generate a dynamic role profile of the students in each collaboration stage of the target collaboration project based on the collaboration ability and contribution; based on the dynamic role profile and the collaboration stage corresponding to the dynamic role profile, it generates collaboration prompts for the students to participate in the target collaboration project according to the collaboration prompts.

[0026] In this embodiment, the target collaborative project can be a project-based learning (PBL) or collaborative learning project. The target collaborative project can be used by students to complete specific learning tasks and achieve preset learning goals through group collaboration. For example, the target collaborative project in this embodiment can specifically be a scientific experiment inquiry project, an interdisciplinary practical project, etc.

[0027] In this embodiment, multimodal behavioral data can be various types of data related to collaborative behavior generated by students during the process of a collaborative project. Multimodal behavioral data can be used to comprehensively and multidimensionally reflect students' collaborative participation and performance. For example, the multimodal behavioral data in this embodiment may specifically include voice data, text data, and behavioral data. This multimodal behavioral data can be collected comprehensively and in real-time using tablets used by students in the classroom without their awareness.

[0028] In this embodiment, the collaboration requirements information may include the project objectives, expected outcomes, role division rules, and core requirements of each collaboration stage of the target collaboration project. This collaboration requirements information can be used to clarify the direction of project collaboration and the evaluation criteria for student collaboration performance. For example, the collaboration requirements information in this embodiment may specifically include stage requirements configured by the teacher before the project begins, such as emphasizing creative ideas during the brainstorming stage and ensuring task progress efficiency during the execution stage, as well as a description of the overall expected outcomes of the project and dimensions for evaluating role capabilities.

[0029] In the embodiments of this application, the collaboration stage can be different phases of the target collaboration project divided according to the time process and task advancement logic. The collaboration stage can be used to achieve precise phased analysis of students' collaboration performance. For example, the collaboration stage in the embodiments of this application may specifically include the goal explanation stage, discussion stage, execution stage, and review stage.

[0030] In this embodiment of the application, collaborative ability can be the comprehensive abilities demonstrated by students in communication, thinking, execution, innovation, and coordination during collaborative activities. Collaborative ability can be used to measure the basic competence level of students participating in collaborative activities. For example, collaborative ability in this embodiment of the application may specifically include speaking and expression ability, text creation and feedback ability, and task execution ability.

[0031] In this embodiment of the application, the collaborative contribution can be a quantitative representation of the specific contributions made by students to the achievement of group goals and the advancement of tasks at each stage of collaboration. The collaborative contribution can be used to evaluate the actual value of students in collaboration. For example, the collaborative contribution in this embodiment of the application may specifically include contributions such as proposing effective viewpoints through speaking, providing creative solutions through text output, and completing assigned tasks efficiently.

[0032] In this embodiment, the dynamic role profile can be a role description that is updated in real time based on the student's collaborative ability and contribution at each collaborative stage, combined with changes in the project context. The dynamic role profile can be used to reflect the dynamic state of the student during the collaborative process. For example, the dynamic role profile in this embodiment may specifically include role descriptions such as a burnt-out innovator, a conflict mediator, a silent executor, an assertive coordinator, or a detached thinker.

[0033] In this embodiment, the collaborative role can be a position that students naturally evolve based on their personality, abilities, and behavioral patterns during the collaborative process. The collaborative role can be used to reflect a student's unique function and participation style within the group. For example, the collaborative role in this embodiment could specifically be a creative initiator who excels at generating ideas, a coordinator who excels at resolving conflicts, or an executor who excels at implementing tasks, etc.

[0034] In this embodiment, the collaboration prompts can be targeted, timely, and actionable natural language guidance content generated based on the student's current dynamic role profile and the collaboration stage. The collaboration prompts can be used to stimulate students' enthusiasm for collaboration and optimize the group interaction process.

[0035] In this embodiment of the application, the collaboration analysis module 1 and the prompt information generation module 2 are connected. The collaboration analysis module 1 sends the collaboration ability and collaboration contribution to the prompt information generation module. The prompt information generation module 2 receives the collaboration ability and collaboration contribution and generates collaboration prompts for the students to prompt them to participate in the target collaboration project according to the collaboration prompts.

[0036] Compared with existing technologies, this embodiment uses a collaborative analysis module to analyze students' collaborative abilities and contributions at each collaborative stage based on multimodal behavioral data and the collaborative requirements of the target collaborative project, achieving accurate judgment of students' collaborative performance at different stages. A prompting information generation module generates dynamic role profiles for students at each collaborative stage of the target collaborative project based on their collaborative abilities and contributions, preventing students from being fixed in a single collaborative role. The prompting information generation module also generates collaborative prompts for students based on their dynamic role profiles and the corresponding collaborative stages, prompting students to participate in the target collaborative project according to the prompts, stimulating students' learning potential and improving the overall collaborative efficiency of the group.

[0037] As an optional approach, the collaboration analysis module 1 includes: a data processing module 11 and a capability contribution analysis module 12; the data processing module 11 is connected to the capability contribution analysis module 12, and the capability contribution analysis module 12 is connected to the prompt information generation module 2; the data processing module 11 is used to identify the multi-dimensional speech characteristics of students based on the speech data in the multi-modal behavioral data, and evaluate the students' speaking activity level in the target collaboration project based on the multi-dimensional speech characteristics; it is used to identify the multi-dimensional thinking characteristics of students based on the text data in the multi-modal behavioral data, and evaluate the students' thinking activity level in the target collaboration project based on the multi-dimensional thinking characteristics; it is used to determine the teacher's evaluation data of the students' behavior in the target collaboration project based on the behavior data in the multi-modal behavioral data, and send the speaking activity level, thinking activity level, and behavior data to the capability contribution analysis module 12; the capability contribution analysis module 12 is used to analyze the students' collaboration ability and collaboration contribution level in each collaboration stage of the target collaboration project based on the speaking activity level, thinking activity level, behavior evaluation data, and collaboration requirement information of the target collaboration project, and send the collaboration ability and collaboration contribution level to the prompt information generation module 2.

[0038] In this embodiment, the voice data can be audio stream data recorded by students using a tablet computer during the collaborative project. For example, the voice data in this embodiment may specifically include audio clips of students speaking, text content converted from speech to text, and corresponding student IDs, timestamps, and other associated information.

[0039] In this embodiment, the multi-dimensional speech features can be various quantitative features related to student speech extracted from voice data. For example, the multi-dimensional speech features in this embodiment may specifically include total speech duration, speech frequency, number of interruptions, number of questions asked, etc.

[0040] In this embodiment, the level of participation in speaking can be an evaluation of a student's initiative in speaking, derived from a comprehensive assessment of multi-dimensional speaking characteristics. This level of participation can be used to measure a student's collaborative engagement in language communication. For example, the level of participation in speaking in this embodiment can be specifically divided into three levels: high, medium, and low, or quantified through specific scores.

[0041] In this embodiment of the application, the process of recognizing students' multi-dimensional speech characteristics based on speech data in multimodal behavioral data, and evaluating students' active participation in the target collaborative project based on these multi-dimensional speech characteristics, may specifically include: the teacher pre-sets project goals, scenario settings, expected results, and relevant nodes on a tablet and then distributes the information to the project-based learning stage. The student's tablet can automatically start the audio recording module, and the audio can be uploaded to the cloud in real time in 10-second data packets for processing. The cloud service can call a pre-trained voiceprint pattern to separate the audio and assign a temporary ID to each student based on their speaking style. The system can compare each student's historical audio (one tablet corresponds to one ID; if the tablet has other applications that collect voice data, the tablet ID and student's voice can be bound together), and bind the temporary ID to the real student ID. The separated audio of each student is sent to ASR (Automatic Speech Recognition) to convert speech to text, and the text content is stored together with the student ID and timestamp.

[0042] In this embodiment of the application, the identification of multi-dimensional speaking features can be completed once every 5 minutes. The system can complete the statistics of features such as total speaking time, speaking frequency, interruption time, and questioning time based on the total duration of audio segments, the number of audio segments, whether a student's voice segment overlaps with another student's voice segment by more than 0.5 seconds, NIP analysis, etc. The evaluation of speaking activity can be based on the above multi-dimensional speaking features for comprehensive judgment.

[0043] In this embodiment of the application, the text data can be related data such as input, deletion, and comments generated by students on a tablet collaboration platform (such as online documents, chat areas, etc.) during the target collaborative project. The text data can be used to analyze students' thinking activities and expression tendencies. For example, the text data in this embodiment of the application may specifically include the solution content entered by students in online documents, the comments in chat areas, operation history and corresponding author IDs, timestamps, and other information.

[0044] In the embodiments of this application, multi-dimensional thinking features can be characteristics that reflect students' thinking methods, depth of thinking, and attitude tendencies, derived from text data through relevant algorithm analysis. For example, the multi-dimensional thinking features in the embodiments of this application may specifically include thinking quality dimensions (innovative, fair, average), attitude tendency dimensions (positive, negative), and interaction feedback dimensions (number of times replying to others), etc.

[0045] In this embodiment, the level of active thinking can be a measure of a student's initiative in thinking and expressing their thoughts, derived from a comprehensive analysis of multi-dimensional thinking characteristics. This level of active thinking can be used to measure a student's collaborative participation at the thinking level. For example, the level of active thinking in this embodiment can be specifically represented by a quantitative score or grade (high, medium, low).

[0046] For the embodiments of this application, the process of identifying students' multi-dimensional thinking characteristics based on text data in multimodal behavioral data may specifically include: when students complete input, deletion or comment operations on a tablet under this project system, the software development module (SDK) integrated in the tablet collaboration platform can capture relevant events such as author ID, operation content, operation history, and timestamp.

[0047] In this embodiment of the application, the evaluation of students' active thinking in the target collaborative project based on multi-dimensional thinking characteristics can be achieved by analyzing students' operational content through NIP analysis, sentiment analysis models, text classification models, etc., and feature extraction can be completed according to different dimensions such as thinking quality and attitude tendency; features such as the number of comments and the number of replies to others can be collected to provide feedback on students' thinking activity and interaction enthusiasm; the evaluation of the level of thinking activity can be comprehensively judged by combining the characteristics of thinking quality dimension, attitude tendency dimension, and the number of replies to others.

[0048] In this embodiment, behavioral data can be data generated by teachers evaluating students' classroom performance during the collaborative project. For example, the behavioral data in this embodiment may specifically include evaluation tags, quantitative scores, and corresponding student IDs, current time, project stage, and other related information assigned by the teacher to the student.

[0049] In this embodiment, behavioral evaluation data can be data such as labels and quantitative scores given by teachers based on students' collaborative behavior. This behavioral evaluation data can provide a reference from the teacher's perspective for analyzing students' collaborative abilities and contributions. For example, the behavioral evaluation data in this embodiment may specifically include labels such as strong sense of responsibility and active collaboration, as well as quantitative scores from 0 to 10.

[0050] In this embodiment of the application, the process of determining the teacher's evaluation data of students' behavior in the target collaborative project based on the behavioral data in the multimodal behavioral data may specifically include: during the project-based learning process, the teacher can use the quick evaluation module of the tablet to support the operation of batch selection of students, batch tagging, and quantitative scoring; after the teacher enters the evaluation information, the system can automatically bind the tags and scores with the student ID, current time, and project stage, and the system can directly obtain the teacher's status and operation log on the tablet in the background, thereby determining the corresponding behavioral evaluation data.

[0051] In this embodiment of the application, the objective performance of students at the speaking level (level of active participation), the objective performance at the thinking level (level of active thinking), and the subjective evaluation given by teachers (behavioral evaluation data) can be comprehensively and accurately analyzed according to different stages of collaboration, in conjunction with the collaboration requirements information of the target collaborative project.

[0052] In this embodiment of the application, the data processing module 11 is connected to the capability contribution analysis module 12, and the capability contribution analysis module 12 is connected to the prompt information generation module 2; the data processing module 11 sends the speaking activity level, thinking activity level, and behavior data to the capability contribution analysis module 12; the capability contribution analysis module 12 sends the collaboration ability and collaboration contribution level to the prompt information generation module 2.

[0053] Optionally, the capability contribution analysis module 12 includes a feature data analysis module 121 and a fusion analysis module 122; the feature data analysis module 121 and the fusion analysis module 122 are connected, and the fusion analysis module 122 is connected to the prompt information generation module 2; the feature data analysis module 121 is used to determine the multi-dimensional benchmark evaluation features and multi-dimensional adjustment evaluation features corresponding to the target collaborative project; based on the level of speaking activity, the level of thinking activity, and behavioral evaluation data, it analyzes at least one benchmark feature data corresponding to the student and at least one feature data to be adjusted for the student in each collaborative stage of the target collaborative project according to the multi-dimensional benchmark evaluation features; the fusion analysis module 122 is used to analyze the student's collaborative ability and collaborative contribution in each collaborative stage of the target collaborative project based on the benchmark weight corresponding to at least one benchmark feature data and the adjustment weight corresponding to at least one feature data to be adjusted.

[0054] In this embodiment, the multi-dimensional benchmark evaluation features can be evaluation features set based on the core competency model of career planning that do not change with the collaboration stage. These multi-dimensional benchmark evaluation features can be used to ensure that each core competency feature is not completely ignored due to stage adaptation. For example, the multi-dimensional benchmark evaluation features in this embodiment may specifically include general competency-related features such as communication, collaboration, and responsibility.

[0055] In this embodiment, the multi-dimensional adjustment evaluation features can be evaluation features related to the core objectives of each stage of the target collaborative project and that change with the stage of collaboration. These multi-dimensional adjustment evaluation features can be used to adapt to the differentiated collaboration needs at different stages. For example, the multi-dimensional adjustment evaluation features in this embodiment may specifically include features such as idea generation, problem solving, and cross-group collaboration.

[0056] In this embodiment, the benchmark feature data can be quantitative data on a student's specific performance on multi-dimensional benchmark evaluation features. This benchmark feature data can be used to reflect a student's basic level in core competencies. For example, the benchmark feature data in this embodiment can specifically be a student's quantitative score on the responsibility benchmark evaluation feature. This benchmark feature data can be comprehensively derived by combining responsibility-related tags and quantitative scores from teacher evaluations, as well as whether the student completes assigned tasks on time.

[0057] In this embodiment of the application, the feature data to be adjusted can be quantitative data on the student's specific performance in adjusting evaluation features across multiple dimensions. This data can be used to reflect the student's ability to adapt to the needs of different stages. For example, in this embodiment, the feature data to be adjusted can specifically be the student's quantitative score on the evaluation features for proposing creative ideas. This data can be derived by combining innovative dimension features extracted from text data, the number of times new ideas were proposed from voice data, and other factors.

[0058] In the embodiments of this application, the benchmark weight can be the core importance benchmark value corresponding to multi-dimensional benchmark evaluation features, and the benchmark weight does not change with the collaboration stage. For example, the benchmark weight in the embodiments of this application may specifically include a benchmark weight of 0.4 corresponding to a sense of responsibility, a benchmark weight of 0.3 corresponding to the proposal of ideas, etc.

[0059] In the embodiments of this application, the adjustment weight can be a multi-dimensional adjustment of the dynamic importance weight of evaluation features at different collaboration stages, and the adjustment weight can change with the collaboration stage. For example, the adjustment weight in the embodiments of this application may specifically include an adjustment weight of 0.9 for idea generation in the brainstorming stage, and an adjustment weight of 0.3 in the execution stage, etc.

[0060] In this embodiment, the capability contribution analysis module 12 includes a feature data analysis module 121 and a fusion analysis module 122; the feature data analysis module 121 and the fusion analysis module 122 are connected, and the fusion analysis module 122 is connected to the prompt information generation module 2; the feature data analysis module 121 sends at least one baseline feature data corresponding to the student and at least one feature data to be adjusted for the student in each collaborative stage of the target collaborative project to the fusion analysis module 122; the fusion analysis module 122 sends the student's collaborative capability and collaborative contribution in each collaborative stage of the target collaborative project to the prompt information generation module 2.

[0061] Optionally, the fusion analysis module 122 is connected to the feature data analysis module 121 and the prompt information generation module 2, respectively. The fusion analysis module 122 is used to determine the benchmark weight corresponding to at least one benchmark feature data; based on the collaboration requirements information of the target collaboration project, it determines the stage feature score corresponding to each collaboration stage in the target collaboration project, and determines the adjustment weight corresponding to each collaboration stage based on the stage feature score; based on the benchmark weight and the adjustment weight, it performs fusion analysis on at least one benchmark feature data and at least one feature data to be adjusted to obtain the student's collaboration ability and collaboration contribution at each collaboration stage, and sends the collaboration ability and collaboration contribution to the prompt information generation module 2.

[0062] In this application embodiment, determining the benchmark weight corresponding to at least one benchmark feature data can be based on the core competency model of career planning by assigning a fixed benchmark value to each benchmark evaluation feature. For example, the benchmark weight of responsibility can be set to 0.4, and the benchmark weight of creative proposal can be set to 0.3. The benchmark weight will not change with the change of the collaboration stage.

[0063] In this embodiment, based on the collaboration requirements information of the target collaborative project, the stage feature score corresponding to each collaboration stage in the target collaborative project can be determined. The core objectives of each collaboration stage can be clarified based on the collaboration requirements information of the target collaborative project, and a corresponding fit score can be assigned to each adjustment evaluation feature. The range of stage feature scores can usually be [0,1] (0 means completely irrelevant, 1 means extremely relevant). The setting of stage feature scores can adopt expert scoring and user-defined modes. The relevance configuration of general project stages can be built-in, and teachers can dynamically configure and customize adjustments when initiating projects.

[0064] In this embodiment, determining the adjustment weight for each collaboration stage based on the stage feature score can be achieved by combining the stage feature score and the adjustment coefficient. adjustment coefficient The value range is typically [0.1, 1.0]. The adjustment coefficient can be used to control the strength of the influence of the stage feature score on the adjustment weight; the adjustment coefficient The larger the value, the more significant the impact of stage differences on the adjustment weight; the adjustment coefficient... The smaller the value, the closer the adjusted weight is to the baseline value, indicating a more moderate impact from stage differences; initially, it can be... Set to 0.5 (medium impact). Further optimization can be achieved through user feedback and data iteration. The specific calculation formula for adjusting the weight is shown in Formula 1, where... This can represent the adjusted weight of feature k at time t (corresponding to a certain collaboration stage). The baseline weight of feature k can be represented, and Relevance(Phase(t),k) can represent the stage-feature relevance score (i.e., stage feature score).

[0065] (Formula 1) In this embodiment of the application, at least one benchmark feature data and at least one feature data to be adjusted are fused and analyzed based on the benchmark weight and the adjustment weight. The collaborative ability and collaborative contribution of students at each collaborative stage can be obtained by weighted summation or other methods.

[0066] Optionally, the prompt information generation module 2 includes: a role information generation module 21 and a prompt content generation module 22; the role information generation module 21 and the prompt content generation module 22 are connected; the role information generation module 21 is used to determine the target collaboration scenario corresponding to the target collaboration stage in the target collaboration project, and to identify the student's collaboration role information in the target collaboration stage based on the target dynamic role profile, wherein the target collaboration stage is any stage in the target collaboration project; the prompt content generation module 22 is used to generate the student's collaboration prompt content based on the target collaboration scenario and collaboration role information, so as to prompt the student to participate in the target collaboration project in the target collaboration stage according to the collaboration prompt content.

[0067] In this embodiment, the target collaboration scenario can be contextual information such as the specific collaboration atmosphere, task progress status, and group interaction during the target collaboration stage. The target collaboration scenario can be used to make the collaboration prompts more relevant to the current actual collaboration environment. For example, the target collaboration scenario in this embodiment may specifically include scenarios with differing viewpoints during the discussion stage, scenarios with delayed task progress during the execution stage, and scenarios with insufficient creativity during the brainstorming stage.

[0068] In this embodiment, the collaborative role information can be the specific role determined by the student based on a dynamic role profile during the target collaboration stage. This collaborative role information can be used to make the collaboration prompts more suitable for the student's role characteristics. For example, the collaborative role information in this embodiment can specifically be a conflict mediator, idea initiator, execution participant, or silent executor.

[0069] In this embodiment of the application, the prompt information generation module 2 includes a role information generation module 21 and a prompt content generation module 22; the role information generation module 21 and the prompt content generation module 22 are connected; the role information generation module 21 sends the target collaboration scenario corresponding to the target collaboration stage and the collaboration role information of the target collaboration stage to the prompt content generation module 22.

[0070] Optionally, the prompt content generation module 22 is used to generate at least one candidate prompt information for a student based on the target collaboration scenario and collaboration role information, and determine the priority information corresponding to the at least one candidate prompt information; select the target prompt information from the at least one candidate prompt information according to the priority information; and generate the student's collaboration prompt content based on the target prompt information.

[0071] In this embodiment, the candidate prompts can be multiple compliant guiding statements generated based on the target collaboration scenario and collaboration role information. These candidate prompts can provide diverse prompt options. For example, specific candidate prompts in this embodiment may include trying to synthesize viewpoints to find common ground, or proactively asking others for their opinions on your ideas.

[0072] In this embodiment, the priority information can be ranking information obtained after evaluating the importance, adaptability, and executability of candidate prompt information. The priority information can be used to filter out the optimal prompt information. For example, in this embodiment, the priority information can specifically be the priority score corresponding to the candidate prompt information; the higher the score, the higher the priority.

[0073] In this embodiment of the application, the target prompt information may be the prompt information with the highest priority and most suitable for the needs selected from multiple candidate prompt information, and the target prompt information may be used to generate the final collaborative prompt content.

[0074] In this embodiment of the application, the generation of candidate prompt information can be based on a combined architecture of rule engine, statistical learning, and large language model (LLM). Through role recognition algorithm, context recognition algorithm, template matching and fine-tuning algorithm, student roles, group contexts and prompt templates are mapped. The large language model used can be LLMLight, which is a lightweight dedicated language model obtained by fine-tuning the Qwen2.5-1.5B model through instructions. The training data of the large language model can be deeply integrated with the goal and context data in project-based learning, as well as teacher feedback and collaborative dialogue records from real educational scenarios to ensure the educational effectiveness and contextual relevance of the generated content. The large language model can receive multi-dimensional embedding vectors such as role embedding (Ri), context embedding (Ct), intervention goal embedding (g), and student profile embedding (Pi) as input, and output personalized natural language prompts.

[0075] For the embodiments of this application, the specific process of generating collaborative prompts for students based on target prompt information may include: assembling multi-dimensional information such as project goals, roles, and contexts into a structured natural language instruction based on role information identified by the intelligent analysis layer, and sending it to the LLM; receiving the structured assembly instruction through a lightweight model deployed locally and fine-tuned with high-quality educational dialogue data, and generating multiple candidate prompts in real time, wherein the priority of the prompts can be determined based on a comprehensive evaluation of factors such as the fit between the prompts and the student's personal profile (such as historical acceptance preferences and personality traits), the executability of the prompts, and the relevance of the prompts to solving the current collaborative problem; selecting the target prompts may involve the system automatically sorting the candidate prompts by priority and selecting the prompt with the highest priority; and generating collaborative prompt content based on the target prompts.

[0076] Optionally, the prompt information generation module 2 is used to respond to the recognition of the target operation behavior data of the student participating in the target collaborative project based on the collaborative prompt content, generate corresponding operation feedback information for the student based on the target operation behavior data, and update the dynamic role profile of the student based on the operation feedback information.

[0077] In this embodiment of the application, the target operational behavior data can be relevant behavioral data generated by students participating in a target collaborative project based on collaborative prompts. This target operational behavior data can be used to evaluate the intervention effect of the prompts. For example, the target operational behavior data in this embodiment may specifically include multimodal behavioral data such as the student's speaking initiation speed, speaking content, text comment content, and task execution progress after the prompts.

[0078] In this embodiment, the operation feedback information can be information obtained by quantitatively evaluating the changes in student behavior after responding to prompts based on target operation behavior data. This operation feedback information can be used to provide a basis for updating dynamic character profiles and optimizing system strategies. For example, the operation feedback information in this embodiment may specifically include a quantitative reward score of 0-10 points, which can be determined based on the student's behavioral changes.

[0079] In this embodiment of the application, in response to the identification of student's target operation behavior data based on collaborative prompts, the generation of corresponding operation feedback information for the student can adopt a dual-stage reward system of immediate and delayed rewards. Immediate rewards (feedback delay less than or equal to 5 minutes) can target the direct behavioral changes of the target student. Immediate rewards may include speaking initiation speed (time taken for the first speech after prompting, the shorter the time, the higher the reward) and speaking quality (judged by semantic analysis to determine whether it conforms to the prompt guidance direction). Delayed rewards (feedback period = current task period) can take into account both individual long-term changes and group effectiveness. Delayed rewards may include student participation improvement rate (compared with the same period in history), number of creative proposals (number of new viewpoints approved by the group), group task completion quality (accuracy rate, innovation score), and member collaboration satisfaction (anonymous peer review score). The reward value can be calculated by weighting, and the weights can be dynamically adjusted according to the teaching objectives. The output quantitative score of 0-10 is used as the core content of the operation feedback information.

[0080] In this embodiment, updating the student's dynamic role profile based on operation feedback information can be done according to the operation feedback information. If the operation feedback information shows a significant change in the student's collaboration ability or contribution, the student's dynamic role profile can be updated. Simultaneously, relevant data can be fed back to the project-based learning system. After the project ends, a performance summary report for each student in project-based learning can be automatically generated, and teachers can complete evaluations based on the reports. If the student's performance summary report in project-based learning is correct and approved, each student's growth file can be updated promptly, completing data accumulation. If the student's performance summary report in project-based learning is incorrect, teachers can provide evaluations, and technical personnel can use data queries and verification at each layer to locate the problem, eliminating random errors in real-time iteration to improve strategy stability. For example, this can be achieved by adjusting the features of the intelligent analysis layer, the basic weights of each feature, and the adjustment coefficients. Alternatively, new data can be fed into the LLM to complete fine-tuning and optimize the prompt generation capability, thereby achieving continuous optimization of dynamic character profiles and self-evolution of the system.

[0081] This embodiment provides a method for generating teaching prompts based on dynamic character profiles, such as... Figure 2As shown, the method includes: Step 201: Obtain multimodal behavioral data of students in the target collaborative project.

[0082] In this application embodiment, obtaining the multimodal behavioral data of students in the target collaborative project can be obtaining the voice data, text data and behavioral data generated by students collaborating in project-based learning (PBL) or collaborative learning projects.

[0083] Step 202: Based on multimodal behavioral data and the collaborative needs information of the target collaborative project, analyze the students' collaborative ability and contribution in each collaborative stage of the target collaborative project.

[0084] In this embodiment of the application, based on multimodal behavioral data and the collaborative requirements information of the target collaborative project, the analysis of students' collaborative ability and contribution in each collaborative stage of the target collaborative project can be carried out by combining the collected multi-dimensional behavioral data and the collaborative requirements of the project itself, and systematically analyzing students' collaborative ability and contribution in stages. The collaborative requirements information can be configured by the teacher in the project-based learning system before the start of project-based learning.

[0085] Step 203: Based on collaboration ability and contribution, generate dynamic role profiles of students at each stage of the target collaboration project.

[0086] In the embodiments of this application, generating a dynamic role profile of a student at each stage of the target collaborative project based on collaborative ability and contribution can be achieved by integrating and processing multi-dimensional data to calculate and generate quantified behavioral feature vectors; students are classified into corresponding collaborative roles through relevant models, and the role profile can be continuously and dynamically updated as the project progresses and student behavior changes, ensuring that the role profile can match the student's real collaborative performance in real time.

[0087] Step 204: Based on the dynamic role profile and the corresponding collaboration stage, generate collaboration prompts for students to guide them in participating in the target collaboration project.

[0088] In this embodiment, the collaborative prompts generated for students, based on dynamic role profiles and the corresponding collaboration stages, can specify the specific scenario of the target collaboration stage and the student's role within that stage. The prompts are generated based on scenario requirements and role characteristics. For example, in a discussion stage where there are differing opinions, prompts generated for students acting as conflict mediators can guide them to coordinate viewpoints and promote consensus. In a brainstorming stage where creativity is lacking, prompts generated for students acting as idea initiators can guide them to share more innovative ideas.

[0089] Compared with existing technologies, this embodiment analyzes students' collaborative abilities and contributions at each collaborative stage based on multimodal behavioral data and the collaborative requirements of the target collaborative project, achieving accurate judgment of students' collaborative performance at different stages. By generating dynamic role profiles for students at each collaborative stage of the target collaborative project based on their collaborative abilities and contributions, it avoids students being fixed in a single collaborative role. Furthermore, by generating collaborative prompts for students based on their dynamic role profiles and the corresponding collaborative stages, it guides students to participate in the target collaborative project according to these prompts, stimulating their learning potential and improving the overall collaborative efficiency of the group.

[0090] Optionally, embodiments of this application also provide an example of context-aware collaborative role recognition and personalized prompts. The module interaction flowchart of the context-aware collaborative role recognition and personalized prompts example is shown below. Figure 3 As shown, Figure 3 It includes the information flow and collaboration logic between five modules: project-based learning system, data collection, intelligent analysis, intervention feedback layer, and student client. This corresponds to the complete process in project-based learning, from configuration and data collection to analysis and intervention. Specific steps may include: Step 1: The project-based learning system, as the basic configuration layer, will transmit the project learning objectives, expected outcomes, and stage scenario settings to the intelligent analysis module, and at the same time transmit the student's personal historical records to the intelligent analysis module to provide a basis for subsequent analysis.

[0091] Step 2: After receiving the configuration information from the project-based learning system, the data acquisition module creates an acquisition task to collect students' behavior, voice, and text data during collaboration (i.e., the multimodal behavior data of this application) and transmits this student data to the intelligent analysis module.

[0092] Step 3: The intelligent analysis module combines project configuration information and student data to assemble and generate user profiles (i.e., the dynamic role profile of this application) and instructions. Then, the instructions based on projects, roles, and contexts are passed to the intervention feedback layer. At the same time, the intelligent analysis module is responsible for storing the profiles. Subsequently, it will also send the student's project performance and project learning report back to the project-based learning system, which will then update the student's personal historical records.

[0093] Step 4: After receiving instructions from the intelligent analysis module, the intervention feedback layer generates structured instructions and pushes personalized prompts to the student client. At the same time, the intervention feedback layer dynamically monitors the real-time feedback from the student client, records the feedback information and updates the strategy to form a closed loop of intervention.

[0094] Step 5: The student client receives personalized prompts from the intervention feedback layer (i.e., personalized collaboration prompts for this application) and simultaneously returns its own operational feedback to the intervention feedback layer, completing the interaction with the system.

[0095] As an optional approach, the flowchart of the context-aware collaborative role recognition and personalized prompt example in this application embodiment is as follows: Figure 4 As shown, Figure 4 The specific process may include the following steps: Step 1: Complete the initial configuration of the scenario parameters, including the basic parameters such as the collaborative scenario, learning objectives, and stage requirements corresponding to project-based learning.

[0096] Step 2: Collect multimodal data (i.e., the multimodal behavioral data of this application) in the field through the data acquisition layer. Based on the initialized context parameters, start the acquisition process and collect multimodal behavioral data such as voice, text, and behavior generated by students in the collaboration process in the field.

[0097] Step 3: Calculate features and update profiles using the intelligent analysis layer. Input the collected multimodal data into the intelligent analysis layer to calculate student collaboration-related features (such as the level of participation in speaking and thinking), and update the dynamic role profile of students in the current collaboration stage.

[0098] Step 4: Enter the intervention and feedback layer to determine whether the effective conditions have been triggered. Combining the features and profile information output by the intelligent analysis layer, determine whether the trigger conditions for personalized prompts are met (such as the need to optimize student collaboration performance, the intervention scenario that is suitable for the current role, etc.).

[0099] Step 5: If the effective conditions are not triggered, continue to monitor and provide feedback. If the trigger conditions are not met, continue to monitor the student's collaborative behavior data in real time and wait for the right time to intervene.

[0100] Step 6: If the valid conditions are triggered, generate personalized prompts (i.e., personalized collaboration prompts for this application). When the trigger conditions are met, based on the current collaboration context and the student's dynamic role profile, generate targeted personalized collaboration prompts.

[0101] Step 7: Push personalized prompts to student clients. Push the generated personalized prompts to the learning terminals used by students (such as collaborative tablets, learning platforms, etc.) to guide students to adjust their collaborative participation methods.

[0102] Step 8: Implement reinforcement learning and reward mechanisms through the effect tracking layer. After the prompt is pushed, start the effect tracking process and use reinforcement learning and reward mechanisms to track and record the students' collaborative behavior and effect data after receiving the prompt.

[0103] Step 9: Construct a self-feedback mechanism to transmit data back to the data acquisition layer. Based on the feedback data obtained from effect tracking, construct a self-feedback mechanism to transmit this data back to the data acquisition layer, providing new evidence for subsequent multimodal data acquisition, feature calculation, and profile updates, forming a complete closed loop for collaborative intervention.

[0104] Optionally, the acquisition of multimodal behavioral data of students in the target collaborative project in this embodiment can be achieved through a data acquisition layer. The workflow of the data acquisition layer includes targeted processing of speech data (i.e., speech type data of multimodal behavioral data in this application), text data (i.e., text type data of multimodal behavioral data in this application), and behavioral data (i.e., behavioral type data of multimodal behavioral data in this application). Speech data can be processed by audio frame input, noise reduction, speaker separation, speech-to-text conversion, and feature extraction to complete speech analysis. Text data can be processed by text data cleaning, word segmentation, semantic analysis, and text feature extraction. Behavioral data can be processed by data normalization, sentiment analysis, behavioral feature analysis, and behavioral feature modeling.

[0105] Compared with existing technologies, this embodiment achieves multi-dimensional and accurate evaluation of students' collaborative performance by identifying corresponding features through multimodal data, determining teacher evaluations, and combining them with collaborative needs; it enhances the comprehensiveness and relevance of collaborative ability and contribution analysis by determining benchmarks, adjusting evaluation features and corresponding data, and combining relevant weight analysis; it achieves accurate calculation of students' collaborative ability and contribution at each stage by determining benchmarks, adjusting weights, and integrating corresponding data; it improves the adaptability of prompts to stages and roles by determining target collaborative scenarios and generating prompt content; it optimizes and filters collaborative prompt content by generating candidate prompts, determining priorities, and selecting target prompts; and it achieves real-time optimization of dynamic role profiles by identifying students' operational behaviors based on prompts, generating feedback, and updating profiles.

[0106] Based on the above, Figure 1 The system shown in this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described... Figure 1 The system shown.

[0107] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0108] like Figure 5The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising: At least one processor 301; and, Memory 302 is communicatively connected to at least one processor 301; wherein, The memory 302 stores instructions that can be executed by at least one processor, such that the at least one processor can execute the teaching prompt information generation system based on the dynamic character portrait as described above.

[0109] Figure 5 Take processor 301 as an example.

[0110] The electronic device may also include an input device 303 and an output device 304.

[0111] The processor 301, memory 302, input device 303, and output device 304 can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0112] Memory 302, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the teaching prompt information generation system based on dynamic character portraits in the embodiments of this application. Figure 1 The system shown. The processor 301 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 302, thereby realizing the teaching prompt information generation system based on dynamic character portraits in the above embodiment.

[0113] The memory 302 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the dynamic character profile-based instructional prompt information generation system. Furthermore, the memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 302 may optionally include memory remotely located relative to the processor 301, and these remote memories may be connected via a network to the apparatus executing the dynamic character profile-based instructional prompt information generation system. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0114] Input device 303 can receive user clicks and generate signal inputs related to user settings and function control of the teaching prompt information generation system based on dynamic character portraits. Output device 304 may include display devices such as a display screen.

[0115] One or more modules are stored in memory 302, and when run by one or more processors 301, the teaching prompt information generation system based on dynamic character portraits in any of the above method embodiments is executed.

[0116] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0117] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0118] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. By applying the solution of this embodiment, compared with the prior art, this embodiment analyzes the students' collaborative ability and contribution at each stage of the target collaborative project based on multimodal behavioral data and collaborative requirement information of the target collaborative project, achieving a stage-based and accurate judgment of students' collaborative performance; by generating dynamic role profiles of students at each stage of the target collaborative project based on collaborative ability and contribution, it avoids students being fixed in a single collaborative role; by generating collaborative prompts for students based on the dynamic role profiles and the corresponding collaborative stages, it prompts students to participate in the target collaborative project according to the collaborative prompts, stimulating students' learning potential and improving the overall collaborative efficiency of the group; through multimodal data... By identifying corresponding features, determining teacher evaluations, and combining them with collaboration needs, a multi-dimensional and accurate evaluation of students' collaborative performance can be achieved. By determining benchmarks, adjusting evaluation features and corresponding data, and combining relevant weight analysis, the comprehensiveness and relevance of the analysis of collaborative ability and contribution can be improved. By determining benchmarks, adjusting weights, and integrating corresponding data, accurate calculation of students' collaborative ability and contribution at each stage can be achieved. By determining target collaboration scenarios and student collaboration roles, prompt content is generated, improving the adaptability of prompts to stages and roles. By generating candidate prompts, determining priorities, and selecting target prompts, the collaborative prompt content can be optimized and filtered. By identifying students' operational behaviors based on prompts, generating feedback, and updating profiles, real-time optimization of dynamic role profiles can be achieved.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0121] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0122] It should be noted that the technical solutions in this application are not limited to the teaching prompt information generation system and method based on dynamic character portraits, but can also be extended to related applications of the same type that need to be controlled. All of these should fall within the protection scope of this application. No specific limitations are made here regarding the related applications that need to be controlled.

[0123] All articles and references disclosed above, including patent applications and publications, are incorporated herein by reference for various purposes. The term “substantially constitutes…” used to describe a combination should include the identified elements, components, parts, or steps, as well as other elements, components, parts, or steps that do not substantially affect the essential novelty of the combination. The use of the terms “comprising” or “including” to describe combinations of elements, components, parts, or steps herein also contemplates embodiments substantially constituted by such elements, components, parts, or steps. The use of the term “may” herein is intended to indicate that any described attribute included by “may” is optional.

[0124] Multiple elements, components, parts, or steps can be provided by a single integrated element, component, part, or step. Alternatively, a single integrated element, component, part, or step can be divided into multiple separate elements, components, parts, or steps. The use of "a" or "an" to describe an element, component, part, or step does not imply the exclusion of other elements, components, parts, or steps.

[0125] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this teaching should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be considered as a failure of the applicant to consider that subject matter as part of the disclosed subject matter. It is evident that various modifications and variations can be made to this application by those skilled in the art without departing from the spirit and scope of this application. Thus, this application is also intended to include such modifications and variations if they fall within the scope of the claims and their equivalents.

Claims

1. A teaching prompt information generation system based on dynamic character portraits, characterized in that, include: Collaborative analysis module and prompt message generation module; The collaborative analysis module and the prompt information generation module are connected; The collaboration analysis module is used to acquire multimodal behavior data of students in the target collaboration project; based on the multimodal behavior data and the collaboration requirements information of the target collaboration project, it analyzes the students' collaboration ability and contribution at each collaboration stage in the target collaboration project, and sends the collaboration ability and contribution to the prompt information generation module. The prompt information generation module is used to generate a dynamic role profile of the student at each collaborative stage of the target collaborative project based on the collaborative ability and the collaborative contribution; and to generate collaborative prompt content for the student based on the dynamic role profile and the corresponding collaborative stage, so as to prompt the student to participate in the target collaborative project according to the collaborative prompt content.

2. The system according to claim 1, characterized in that, The collaborative analysis module includes: a data processing module and a capability contribution analysis module; The data processing module is connected to the capability contribution analysis module, and the capability contribution analysis module is connected to the prompt information generation module; The data processing module is used to identify the student's multi-dimensional speech characteristics based on the speech data in the multi-modal behavioral data, and evaluate the student's active participation in the target collaborative project based on the multi-dimensional speech characteristics; identify the student's multi-dimensional thinking characteristics based on the text data in the multi-modal behavioral data, and evaluate the student's active thinking in the target collaborative project based on the multi-dimensional thinking characteristics; determine the teacher's evaluation data of the student's behavior in the target collaborative project based on the behavioral data in the multi-modal behavioral data, and send the active participation in speaking, the active thinking, and the behavioral data to the ability contribution analysis module; The capability contribution analysis module is used to analyze the student's collaborative ability and contribution at each stage of the target collaborative project based on the student's speaking activity level, thinking activity level, behavioral evaluation data, and collaborative requirements information of the target collaborative project, and sends the collaborative ability and contribution to the prompt information generation module.

3. The system according to claim 2, characterized in that, The capability contribution analysis module includes a feature data analysis module and a fusion analysis module; The feature data analysis module and the fusion analysis module are connected, and the fusion analysis module and the prompt information generation module are connected; The feature data analysis module is used to determine the multi-dimensional benchmark evaluation features and multi-dimensional adjustment evaluation features corresponding to the target collaborative project; based on the level of speaking activity, the level of thinking activity, and the behavioral evaluation data, it analyzes at least one benchmark feature data corresponding to the student and at least one feature data to be adjusted for the student in each collaborative stage of the target collaborative project according to the multi-dimensional benchmark evaluation features; The fusion analysis module is used to analyze the student's collaborative ability and contribution to each collaborative stage of the target collaborative project based on the baseline weights corresponding to the at least one baseline feature data and the adjustment weights corresponding to the at least one feature data to be adjusted.

4. The system according to claim 3, characterized in that, The fusion analysis module is connected to the feature data analysis module and the prompt information generation module, respectively. The fusion analysis module is used to determine the benchmark weights corresponding to the at least one benchmark feature data; Based on the collaboration requirements information of the target collaboration project, determine the stage feature score corresponding to each collaboration stage in the target collaboration project, and determine the adjustment weight corresponding to each collaboration stage based on the stage feature score; perform fusion analysis on the at least one benchmark feature data and the at least one feature data to be adjusted based on the benchmark weight and the adjustment weight to obtain the student's collaboration ability and collaboration contribution corresponding to each collaboration stage, and send the collaboration ability and collaboration contribution to the prompt information generation module.

5. The system according to claim 1, characterized in that, The prompt information generation module includes: a role information generation module and a prompt content generation module; The character information generation module and the prompt content generation module are connected; The role information generation module is used to determine the target collaboration scenario corresponding to the target collaboration stage in the target collaboration project, and to identify the student's collaboration role information in the target collaboration stage based on the target dynamic role profile, wherein the target collaboration stage is any stage in the target collaboration project. The prompt content generation module is used to generate collaboration prompt content for the student based on the target collaboration scenario and the collaboration role information, so as to prompt the student to participate in the target collaboration project according to the collaboration prompt content in the target collaboration stage.

6. The system according to claim 5, characterized in that, The prompt content generation module is used to generate at least one candidate prompt information corresponding to the student based on the target collaboration scenario and the collaboration role information, and determine the priority information corresponding to the at least one candidate prompt information; and select the target prompt information from the at least one candidate prompt information according to the priority information. Based on the target prompt information, the student's collaborative prompt content is generated.

7. The system according to claim 1, characterized in that, The prompt information generation module is used to respond to the recognition of the student's target operation behavior data based on the collaborative prompt content participating in the target collaborative project, generate operation feedback information corresponding to the student based on the target operation behavior data, and update the student's dynamic role profile based on the operation feedback information.

8. A method for generating teaching prompts based on dynamic character portraits, characterized in that, The system applied to any one of claims 1-7 comprises: Obtain multimodal behavioral data of students in the target collaborative project; Based on the multimodal behavioral data and the collaboration requirements information of the target collaborative project, the student's collaboration ability and contribution to each stage of the target collaborative project are analyzed. Based on the collaborative ability and the degree of collaborative contribution, a dynamic role profile of the student is generated for each collaborative stage of the target collaborative project; Based on the dynamic character profile and the corresponding collaboration stage, collaboration prompts are generated for the student to guide them to participate in the target collaboration project.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the teaching prompt information generation system based on dynamic character portraits as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The system includes the teaching prompt information generation system based on dynamic character portraits, as described in any one of claims 1 to 7.

Images