Device, method and equipment for designing and executing AI workflow for teaching

Abstract

The invention discloses an AI workflow design and execution device, method and equipment for teaching, and relates to the technical field of AI intelligent interaction.The AI workflow design and execution device comprises a scheme export module and further comprises a data acquisition module, an analysis module, a selection storage module and a data integration module; the analysis module is connected with the data acquisition module, the selection storage module is connected with the analysis module and the data acquisition module, and the data integration module is connected with the selection storage module; the data acquisition module is used for acquiring learning video data of a specified student and marking according to a subject corresponding to the learning video data; the classroom learning state of the student and the corresponding learning data can be more comprehensively collected and analyzed through the arranged modules and methods, so that the matching degree of the specified learning path and the recommended learning plan with the student is higher, and the student can be more effectively assisted in promotion.

Description

Technical Field

[0001] The present invention relates to the technical field of AI intelligent interaction, and specifically to a device, method and equipment for the design and execution of an AI workflow for teaching. Background Art

[0002] An AI workflow is a new working mode that applies artificial intelligence technology to traditional work processes to improve work efficiency, automation level and intelligence level. Currently, in the teaching field, an AI workflow generally refers to decomposing complex teaching tasks into a series of smaller subtasks and introducing AI technology to process these subtasks, thereby forming an efficient, automated and intelligent teaching process. Its characteristics lie in combining the automated processing ability of AI and the process management ability of the workflow, being able to automatically execute repetitive teaching tasks, conduct data analysis and decision-making, optimize the teaching process path, etc., significantly improving teaching efficiency and quality; The AI workflow can automatically generate personalized learning paths according to students' learning habits, ability levels and learning goals. By analyzing students' learning data, AI can recommend learning resources and courses suitable for students, thereby meeting the personalized needs of students; When the existing devices for the design and execution of AI workflows are used for assisting teaching, most of them can only judge students' learning ability and learning degree by manually inputting corresponding information based on the evaluation results of teachers and identifying and modifying students' homework, and cannot analyze and monitor students' classroom learning status, resulting in incomplete and untimely data received during data collection. Furthermore, when generating a learning path for corresponding students through subsequent AI system analysis, the finally generated learning path has a low matching degree with the students, and cannot effectively assist the corresponding students in improving. Summary of the Invention

[0003] To solve the deficiencies mentioned in the above background art, the purpose of the present invention is to provide a device, method and equipment for the design and execution of an AI workflow for teaching.

[0004] In a first aspect, the purpose of the present invention can be achieved through the following technical solutions: A device for the design and execution of an AI workflow for teaching, comprising: A data collection module, an analysis module, a selection and storage module, a data integration module and a solution export module; The data collection module is used to collect the learning video data of a specified student, and mark the learning video data of the specified student with the corresponding subject; obtain the marked learning video data, and send the marked learning video data to the analysis module and the selection storage module; The analysis module is used to authenticate and analyze the marked learning video data, obtain the student identity information and learning behavior determination data, and send the student identity information and learning behavior determination data to the selection storage module; The selection storage module is used to classify and store the marked learning video data and learning behavior determination data according to the student identity information; The data integration module is used to summarize the marked learning video data and learning behavior determination data stored in the selection storage module, summarize and obtain the comprehensive learning indicators of the corresponding subject of the designated student based on the marked learning video data and learning behavior determination data, and send the comprehensive learning indicators of the corresponding subject of the designated student to the solution export module; The program export module is used to provide students with personalized learning plan programs based on workflow design and comprehensive learning indicators using artificial intelligence algorithms.

[0005] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the data acquisition module includes a monitoring unit, a tracking unit and a marking unit, the tracking unit is connected to the monitoring unit; the marking unit is connected to the monitoring unit; The monitoring unit is used to capture and record the learning data of the trainees; The tracking unit identifies and tracks the object being photographed based on computer vision, artificial intelligence technology and corresponding adjustment mechanisms; The marking unit sets the subject type label in advance according to the actual learning content to mark the collected and recorded video data, so as to obtain the marked learning video data.

[0006] In combination with the first aspect, in some implementations of the first aspect, the analysis module further includes: the analysis module includes a recognition unit, an expression analysis unit and a determination unit, the recognition unit is connected to the data acquisition module; the expression analysis unit is connected to the recognition unit; the determination unit is connected to the expression analysis unit; The recognition unit performs identity recognition on the collected student video data based on local human feature analysis and pattern recognition algorithm to obtain student identity information, and generates an identity tag based on the student identity information and marks the corresponding student video data at the same time; The expression analysis unit analyzes the student's expression in the collected video based on computer vision technology and machine learning algorithms, and sends the student's expression analysis results to the determination unit; The determination unit determines the learning behavior of the student's designated subject based on the analysis result of the student's expression in combination with the label set in the learning video data to obtain the learning behavior determination data.

[0007] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the calculation process of the recognition unit performing identity recognition on the collected student video data based on local human feature analysis and graphic recognition algorithm is as follows: Get a picture with the facial features of a designated student; Locate the coordinates of the key points of the facial features in the facial feature image; Output the coordinates of the key points of the facial features; Matching based on the coordinates of the key points of the facial features; The student's identity is identified based on the matching results.

[0008] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the selection storage module includes a personal data storage unit and a classification output unit, the classification output unit is connected to the data acquisition module and to the analysis module; the personal data storage unit is connected to the classification output unit; The personal data storage unit is used to store all learning video data of the designated student; The classification output unit identifies the identity tags in the student's video data, and based on the identification results of the identity tags, transmits the student's learning video data and the corresponding learning behavior determination data to the corresponding personal data storage unit.

[0009] In combination with the first aspect, in some implementations of the first aspect, the data integration module further includes: the data integration module includes an update summary unit and an integration processing unit, the update summary unit is connected to the selection storage module; the integration processing unit is connected to the update summary unit; The updating and summarizing unit summarizes the learning video data of the designated student and the corresponding learning behavior determination data transmitted by the selection storage module in combination with the historical learning video data of the designated student and the corresponding historical learning behavior determination data; The integration processing unit generates a comprehensive learning indicator of the corresponding subject based on the aggregated learning video data and the corresponding learning behavior determination data in combination with a set statistical algorithm.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, the process of calculating the comprehensive learning index of the corresponding subject based on the aggregated learning video data and the corresponding learning behavior determination data combined with the set statistical algorithm is as follows: Obtaining the learning behavior determination data corresponding to the designated subject and designated stage of the student; Assigning scores based on the acquired learning behavior determination data to generate a learning behavior score; The average learning behavior score is calculated based on the average learning behavior scores of all stages of the specified subject to generate an average learning behavior score; A comprehensive learning indicator is generated according to the average learning behavior score.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the process of providing students with personalized learning plans using artificial intelligence algorithms based on workflow design and comprehensive learning indicators is as follows: Obtaining said comprehensive learning indicators for all subjects; Screening out the comprehensive learning indicators that do not meet the requirements; Matching corresponding students and corresponding subjects of the corresponding students based on the obtained comprehensive learning indicators that do not meet the requirements; The selected subjects will be arranged as key learning subjects in the corresponding students' study plans, and then the corresponding personalized study plans will be generated.

[0012] In a second aspect, in order to achieve the above-mentioned object, the present invention discloses a method for designing and executing an AI workflow for teaching, the method comprising the following steps: Acquire the learning video data of the students, and mark the learning video data of the students with the corresponding subjects; obtain the marked learning video data; The marked learning video data is authenticated, identified and analyzed to obtain the student identity information and learning behavior judgment data; Based on the marked learning video data and learning behavior judgment data, the comprehensive learning indicators of the corresponding subject of the designated students are summarized; Based on workflow design and comprehensive learning indicators, artificial intelligence algorithms are used to provide students with personalized learning plans.

[0013] In another aspect of the present invention, in order to achieve the above-mentioned purpose, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, an apparatus for designing and executing an AI workflow for teaching as described above is adopted.

[0014] Beneficial effects of the present invention: The present invention can collect and analyze students' classroom learning status and corresponding learning data more comprehensively through the provided modules and methods, so that the designated learning path and the recommended learning plan are more closely matched with the students, and can more effectively assist students in improving. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work. Figure 1 It is a structural schematic diagram of a device for designing and executing an AI workflow for teaching according to the present invention; Figure 2 It is a structural schematic diagram of a data acquisition module of the present invention; Figure 3 It is a structural schematic diagram of the analysis module of the present invention; Figure 4 is a structural schematic diagram of a selection storage module of the present invention; Figure 5 It is a structural schematic diagram of the data integration module of the present invention; Figure 6 is a flow chart of a method for designing and executing an AI workflow for teaching according to the present invention; Figure 7 It is a structural schematic diagram of an AI workflow design and execution device for teaching of the present invention; Figure 8 It is a schematic diagram of the structure of the back side of the AI ​​workflow design and execution device for teaching of the present invention; Fig. 9 It is a structural schematic diagram of the rotary gear drive mechanism and the rotating gear drive mechanism of the present invention.

[0016] In the figure: 100-data acquisition module, 200-analysis module, 300-selection storage module, 400-data integration module, 500-solution export module, 1001-monitoring unit, 1002-tracking unit, 1003-marking unit, 2001-recognition unit, 2002-expression analysis unit, 2003-determination unit, 3001-personal data storage unit, 3002-classification output unit, 4001-update summary unit, 4002-integration processing unit, 1-suction cup base, 2-rotating base, 3-shooting mechanism, 4-capture scanning element, 5-regulating component, 51-rotating gear driving mechanism, 52-rotating gear driving mechanism. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0018] like Figure 1 As shown, the present invention provides a device for designing and executing an AI workflow for teaching, comprising: The solution export module 500 further includes a data acquisition module 100, an analysis module 200, a selection storage module 300 and a data integration module 400; the analysis module 200 is connected to the data acquisition module 100, the selection storage module 300 is connected to the analysis module 200 and to the data acquisition module 100, the data integration module 400 is connected to the selection storage module 300 and to the solution export module 500; The data collection module 100 collects learning video data of designated students and marks the learning video data according to the subject corresponding to the learning video data; The analysis module 200 performs authentication and recognition on the collected and recorded student videos and analyzes the student video data; The selection and storage module 300: classifies and stores the generated student video data according to the student identity information; The data integration module 400 is used to aggregate all learning video data and learning behavior determination data of the designated student, and analyze and summarize the comprehensive learning indicators of the designated student's corresponding subject based on the aggregated learning video data and learning behavior determination data; The program export module 500 uses artificial intelligence algorithms to provide students with personalized learning plan programs based on the workflow design and the comprehensive learning indicators output by the data integration module 400.

[0019] See also Figure 2 , further, the data acquisition module 100 includes a monitoring unit 1001, a tracking unit 1002 and a marking unit 1003, the tracking unit 1002 is connected to the monitoring unit 1001; the marking unit 1003 is connected to the monitoring unit 1001; The monitoring unit 1001 is used to capture and record the learning data of the trainees; The tracking unit 1002 is used to identify and track the object being photographed based on computer vision, artificial intelligence technology and corresponding adjustment mechanisms; The marking unit 1003 sets the subject type label in advance according to the actual learning content to mark the collected and recorded video data.

[0020] In this embodiment, the tracking unit 1002 is based on computer vision and artificial intelligence technology, and can automatically identify and track the subject through real-time analysis of the shooting picture, so as to maintain the clarity and stability of the subject in the picture. First, the shooting picture is analyzed in real time to identify the position and movement trajectory of the subject. Then, based on this information, the system can automatically adjust the camera parameters, such as focal length, exposure, etc., to maintain the clarity and stability of the subject; The adjustment control structure adopted in the tracking unit 1002 and its corresponding monitoring device can enable the shooting device to automatically follow the movement of the shooting subject, ensure that the subject is always located in the center of the picture, avoid shaking or blurring during shooting, and thus better shoot the student's learning video data. When collecting student video data, the management personnel need to set the subject type label through the marking unit 1003 according to the corresponding subject of learning to mark the collected video, so that the learning video data of the specified student can be summarized and summarized by subject type later.

[0021] See also Figure 3 , further, the analysis module 200 includes a recognition unit 2001, an expression analysis unit 2002 and a determination unit 2003, the recognition unit 2001 is connected to the data acquisition module 100; the expression analysis unit 2002 is connected to the recognition unit 2001; the determination unit 2003 is connected to the expression analysis unit 2002; The identification unit 2001: performs identity recognition on the collected student video data based on local human feature analysis and pattern recognition algorithm, and generates an identity tag according to the recognition result and marks the corresponding student video data; Specifically, the calculation process of the identification unit 2001 for performing identity identification on the collected student video data based on local human feature analysis and pattern recognition algorithm is as follows: Get a picture with the facial features of a designated student; Locate the coordinates of the key points of the facial features in the facial feature image; Output the coordinates of the key points of the facial features; Matching based on the coordinates of the key points of the facial features; The student's identity is identified based on the matching results.

[0022] The expression analysis unit 2002 analyzes the student's expression in the collected video based on computer vision technology and machine learning algorithm; The determination unit 2003 determines the learning behavior of the student in the designated subject according to the analysis result of the student's expression and the labels set in the learning video data.

[0023] In this embodiment, the recognition unit 2001 mainly adopts a biometric recognition technology based on human facial features for identity recognition, that is, face recognition technology. It judges the input face image or video stream based on human facial features, first determines whether there is a face, and if so, further gives the position, size and position information of each face and each major facial organ, and further extracts the identity features contained in each face based on this information, and compares it with known faces to identify the identity of each face, so as to identify the identity of each face, so that the corresponding identity label can be generated by identifying and determining the identity of the student, and then marked in the collected learning video data of the corresponding student, so as to facilitate the rapid identification of different student identities, thereby quickly collecting and storing the learning video data of the corresponding student; The expression analysis unit 2002 mainly adopts FER technology, namely, facial expression recognition (Facial Expression Recognition) technology. FER technology mainly relies on computer vision technology and machine learning algorithms. It can automatically identify human emotional states, such as happiness, sadness, anger, etc., by analyzing the expression features in facial images. In actual operation, the facial image is first captured through the collected learning video data, and the face in the image is located using face detection technology. On the basis of face detection, a specific algorithm or model is used to extract facial expression features from areas such as eyes, mouth, eyebrows, etc. These features include shape, texture and motion information, etc. Finally, based on the extracted features, a classifier or recognition algorithm is used to classify the expression, and the emotional states such as smile, anger, surprise, etc. are identified. By using the expression analysis unit 2002, the learning emotions of students in designated subjects can be monitored, so as to analyze the proportion of various emotions of students in the study of designated subjects, and then the learning behavior data such as the students' learning enthusiasm and learning attitude for this subject can be estimated according to the proportion of emotions. When analyzing the proportion of emotions, the emotional states corresponding to multiple types of expressions can be classified in advance, for example, normal listening feedback such as excitement, surprise, and smile can be set as positive emotions, and then tiredness, disgust, etc. can be set as negative emotions. In addition, the operator can also classify the degree types of positive emotions and negative emotions according to the actual operation situation, and then collect the proportion of emotions shown by students in the corresponding subject classroom; The determination unit 2003 determines the student's learning status and corresponding learning behavior in the corresponding subject learning according to the proportion of the student's emotions in the corresponding subject class. For example, if a student's emotions in the Chinese class are eight levels of positive emotions and two levels of negative emotions, it means that the student's interest and attitude towards learning Chinese subjects are positive. The emotion proportion corresponding to the specific determination method can be set according to the actual operation, so as to analyze and determine the student's learning behavior data for multiple subjects.

[0024] See also Figure 4 , further, the selection storage module 300 includes a personal data storage unit 3001 and a classification output unit 3002, the classification output unit 3002 is connected to the data acquisition module 100, and is connected to the analysis module 200; the personal data storage unit 3001 is connected to the classification output unit 3002; The personal data storage unit 3001 is used to store all learning video data of the designated student; The classification output unit 3002 identifies the identity tags in the student's video data, and based on the identification results of the identity tags, transmits the student's learning video data and the corresponding learning behavior determination data to the corresponding personal data storage unit 3001.

[0025] See also Figure 5 , further, the data integration module 400 includes an update summary unit 4001 and an integration processing unit 4002, the update summary unit 4001 is connected to the selection storage module 300; the integration processing unit 4002 is connected to the update summary unit 4001; The updating and summarizing unit 4001 summarizes the learning video data and the corresponding learning behavior determination data of the designated student transmitted by the selection storage module 300 in combination with the historical learning video data and the corresponding historical learning behavior determination data of the designated student; The integration processing unit 4002 generates a comprehensive learning indicator of the corresponding subject based on the aggregated learning video data and the corresponding learning behavior determination data combined with a set statistical algorithm.

[0026] The calculation process of generating the comprehensive learning index of the corresponding subject based on the aggregated learning video data and the corresponding learning behavior determination data combined with the set statistical algorithm is as follows: Obtaining the learning behavior determination data corresponding to the designated subject and designated stage of the student; Assigning scores based on the acquired learning behavior determination data to generate a learning behavior score; The average learning behavior score is calculated based on the average learning behavior scores of all stages of the specified subject to generate an average learning behavior score; A comprehensive learning indicator is generated according to the average learning behavior score.

[0027] When this embodiment is used, the specific value assignment and scoring process is through behavioral judgment, mainly based on the proportion of positive and negative emotions in the designated subject class. The greater the proportion of positive emotions in the class, the higher the score, which also means that the student's classroom behavior is better. Therefore, the score can be directly based on the proportion of positive emotions. For example, if the proportion of positive emotions in the class is 85%, it is 85 points. Then, a comprehensive learning index is generated based on the generated average learning behavior score. Before calculating the comprehensive learning index, it is necessary to divide the level according to the average learning behavior score, for example, 20-40 is lower, 40-60 is middle, and 60-90 is upper, so as to facilitate a more intuitive display of the final comprehensive learning index. The personal data storage unit 3001 corresponds to the identity information of the trainee one by one. Each trainee has his or her own personal data storage unit 3001. When guiding the transmission of the collected learning video data and the learning behavior determination data, the classification output unit 3002 can quickly determine the trainee corresponding to the collected data through the identity tags carried by the corresponding learning video data and the corresponding learning behavior determination data, and then store and update the collected data to the corresponding personal data storage unit 3001; The update summary unit 4001 mainly summarizes all the learning video data and the corresponding learning behavior judgment data stored in the personal data storage unit 3001, and then analyzes the learning behavior judgment data of the personal data storage unit 3001 through the integration processing unit 4002. When performing the analysis, it is still classified according to the subject, and then the comprehensive learning indicators of the corresponding subjects of the students are analyzed and judged. For example, a student judges that physics and chemistry subjects need to be focused on and improved based on the subject test results. Then the program export module 500 will combine the overall judgment structure to specify a set of learning plans that focus on physics and chemistry subjects for the designated students, thereby helping students to improve and assisting teachers to provide better teaching guidance to designated students. Since the collected student data changes day by day with time, the comprehensive learning indicators made by the integration processing unit 4002 in each period will also be continuously updated and changed. The operator can summarize and organize according to the learning time so as to better understand the learning changes of each student in the corresponding subject.

[0028] Based on workflow design and comprehensive learning indicators, the process of using artificial intelligence algorithms to provide students with personalized learning plans is as follows: Obtaining said comprehensive learning indicators for all subjects; Screening out the comprehensive learning indicators that do not meet the requirements; Matching corresponding students and corresponding subjects of the corresponding students based on the obtained comprehensive learning indicators that do not meet the requirements; The selected subjects will be arranged as key learning subjects in the corresponding students' study plans, and then the corresponding personalized study plans will be generated.

[0029] Specifically, by analyzing the comprehensive learning indicators, the comprehensive learning indicators that do not meet the requirements, that is, the comprehensive learning indicators with scores lower than preset values, will be screened out, and the courses corresponding to the subjects of the screened-out comprehensive learning indicators that do not meet the requirements will be the courses that will be focused on in the future for the corresponding students. Embodiment 2

[0030] Second, as Figure 6 As shown, in order to achieve the above-mentioned purpose, the present invention discloses a method for designing and executing an AI workflow for teaching, the method comprising the following steps: S101: Acquire the learning video data of the students, and mark the learning video data of the students with the corresponding subjects; and obtain the marked learning video data; S102: Authentication, identification and analysis of the marked learning video data to obtain student identity information and learning behavior determination data; S103: Summarizing and obtaining the comprehensive learning index of the corresponding subject of the designated student based on the marked learning video data and the learning behavior determination data; S104: Based on workflow design and comprehensive learning indicators, use artificial intelligence algorithms to provide students with personalized learning plans.

[0031] See also Figures 7 to 9 The present invention provides a device for designing and executing AI workflows for teaching, which may also include a suction cup base 1 and a monitoring component; the monitoring component includes a rotating base 2, a shooting mechanism 3, a capture scanning element 4 and a regulating component 5, and the regulating component 5 includes a rotating gear driving mechanism 51 and a rotating gear driving mechanism 52.

[0032] Furthermore, the rotating base 2 is rotatably mounted on the suction cup base 1; the shooting mechanism 3 is rotatably mounted on the rotating base 2, and is used to shoot and collect the learning video data of the students; the capture scanning element 4 is installed on the shooting mechanism 3; the regulating component 5 is connected to the rotating base 2, and is used to adjust the shooting angle and shooting range of the shooting mechanism 3.

[0033] Furthermore, the rotating base 2 is rotatably mounted on the suction cup base 1; the shooting mechanism 3 is rotatably mounted on the rotating base 2, and is used to shoot and collect the learning video data of the students; the capture scanning element 4 is installed on the shooting mechanism 3; the regulating component 5 is connected to the rotating base 2, and is used to adjust the shooting angle and shooting range of the shooting mechanism 3.

[0034] When the present embodiment is in use, four suction cups are arranged at the bottom of the suction cup base 1, so as to facilitate installation of the entire device on the desk. The suction cup base 1 is rotatably provided with the rotating base 2, and the shooting mechanism 3 is rotatably installed on the rotating base 2. The shooting mechanism 3 is mainly composed of a corresponding mounting shell and a shooting element. At the same time, a capturing scanning element 4 for moving is also arranged on the shooting surface of the shooting mechanism 3. The mounting shell of the shooting mechanism 3 is rotatably installed on the rotating base 2. The rotating base 2 and the shooting mechanism 3 are driven by the rotating gear driving mechanism 51 and the rotating gear driving mechanism 52 respectively. The rotating gear driving mechanism 51 and the rotating gear driving mechanism 52 are driven by the corresponding driving mechanism The rotating base 2 is rotated on the suction cup base 1 and the shooting mechanism 3 is rotated on the rotating base 2, so as to adjust the shooting range of the shooting mechanism 3, so as to realize the tracking shooting of the students by adjusting the shooting range of the shooting mechanism 3 through the capture scanning element 4 arranged on the shooting mechanism 3. In actual use, corresponding monitoring equipment can be set on each teacher's desk. After collecting the class data of the corresponding students, the shooting mechanism 3 can perform face recognition through the corresponding template, and then save the collected video data into the corresponding personal data storage unit 3001.

[0035] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0036] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by the processor to execute the above method. The storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0037] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0038] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.

Claims

1. A device for designing and executing AI workflows for teaching, characterized in that: include: Data collection module, analysis module, selection storage module, data integration module and solution export module; The data collection module is used to collect the learning video data of the designated students, and mark the learning video data of the designated students with the corresponding subjects; Obtaining the marked learning video data, and sending the marked learning video data to the analysis module and the selection storage module; The analysis module is used to authenticate and analyze the marked learning video data, obtain the student identity information and learning behavior determination data, and send the student identity information and learning behavior determination data to the selection storage module; The selection storage module is used to classify and store the marked learning video data and learning behavior determination data according to the student identity information; The data integration module is used to summarize the marked learning video data and learning behavior determination data stored in the selection storage module, summarize and obtain the comprehensive learning indicators of the corresponding subject of the designated student based on the marked learning video data and learning behavior determination data, and send the comprehensive learning indicators of the corresponding subject of the designated student to the solution export module; The program export module is used to provide students with personalized learning plan programs based on workflow design and comprehensive learning indicators using artificial intelligence algorithms.

2. The device for designing and executing AI workflow for teaching according to claim 1, characterized in that: The data acquisition module includes a monitoring unit, a tracking unit and a marking unit, wherein the tracking unit is connected to the monitoring unit; the marking unit is connected to the monitoring unit; The monitoring unit is used to capture and record the learning data of the trainees; The tracking unit identifies and tracks the object being photographed based on computer vision, artificial intelligence technology and corresponding adjustment mechanisms; The marking unit sets the subject type label in advance according to the actual learning content to mark the collected and recorded video data, so as to obtain the marked learning video data.

3. The device for designing and executing AI workflow for teaching according to claim 2, characterized in that: The analysis module includes a recognition unit, an expression analysis unit and a determination unit, wherein the recognition unit is connected to the data acquisition module; the expression analysis unit is connected to the recognition unit; and the determination unit is connected to the expression analysis unit. The recognition unit performs identity recognition on the collected student video data based on local human feature analysis and pattern recognition algorithm to obtain student identity information, and generates an identity tag based on the student identity information and marks the corresponding student video data at the same time; The expression analysis unit analyzes the student's expression in the collected video based on computer vision technology and machine learning algorithms, and sends the student's expression analysis results to the determination unit; The determination unit determines the learning behavior of the student's designated subject based on the analysis result of the student's expression in combination with the label set in the learning video data to obtain the learning behavior determination data.

4. The device for designing and executing AI workflow for teaching according to claim 3, characterized in that: The calculation process of the recognition unit for identity recognition of the collected student video data based on local human feature analysis and pattern recognition algorithm is as follows: Get a picture with the facial features of a designated student; Locate the coordinates of the key points of the facial features in the facial feature image; Output the coordinates of the key points of the facial features; Matching based on the coordinates of the key points of the facial features; The student's identity is identified based on the matching results.

5. The device for designing and executing AI workflow for teaching according to claim 4, characterized in that: The selection storage module includes a personal data storage unit and a classification output unit, the classification output unit is connected to the data acquisition module and to the analysis module; the personal data storage unit is connected to the classification output unit; The personal data storage unit is used to store all learning video data of the designated student; The classification output unit identifies the identity tags in the student's video data, and based on the identification results of the identity tags, transmits the student's learning video data and the corresponding learning behavior determination data to the corresponding personal data storage unit.

6. The device for designing and executing AI workflow for teaching according to claim 5, characterized in that: The data integration module includes an update summary unit and an integration processing unit, wherein the update summary unit is connected to the selection storage module; the integration processing unit is connected to the update summary unit; The updating and summarizing unit summarizes the learning video data of the designated student and the corresponding learning behavior determination data transmitted by the selection storage module in combination with the historical learning video data of the designated student and the corresponding historical learning behavior determination data; The integration processing unit generates a comprehensive learning indicator of the corresponding subject based on the aggregated learning video data and the corresponding learning behavior determination data in combination with a set statistical algorithm.

7. The device for designing and executing AI workflow for teaching according to claim 6, characterized in that: The calculation process of generating the comprehensive learning indicators of the corresponding subject based on the aggregated learning video data and the corresponding learning behavior judgment data combined with the set statistical algorithm is as follows: Obtaining the learning behavior determination data corresponding to the designated subject and designated stage of the student; Assigning scores based on the acquired learning behavior determination data to generate a learning behavior score; The average learning behavior score is calculated based on the average learning behavior scores of all stages of the specified subject to generate an average learning behavior score; A comprehensive learning indicator is generated according to the average learning behavior score.

8. The device for designing and executing AI workflow for teaching according to claim 7, characterized in that: Based on workflow design and comprehensive learning indicators, the process of using artificial intelligence algorithms to provide students with personalized learning plans is as follows: Obtaining said comprehensive learning indicators for all subjects; Screening out the comprehensive learning indicators that do not meet the requirements; Matching corresponding students and corresponding subjects of the corresponding students based on the obtained comprehensive learning indicators that do not meet the requirements; The selected subjects will be arranged as key learning subjects in the corresponding students' study plans, and then the corresponding personalized study plans will be generated.

9. A method for designing and executing an AI workflow for teaching, using a device for designing and executing an AI workflow for teaching as claimed in any one of claims 1 to 7, characterized in that: The method comprises the following steps: Obtain the students' learning video data and mark the students' learning video data with corresponding subjects; Obtain labeled learning video data; The marked learning video data is authenticated, identified and analyzed to obtain the student identity information and learning behavior judgment data; Based on the labeled learning video data and learning behavior judgment data, the comprehensive learning indicators of the corresponding subject of the designated students are summarized; Based on workflow design and comprehensive learning indicators, artificial intelligence algorithms are used to provide students with personalized learning plans.

10. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: The memory stores a computer program that can be run on the processor. When the processor loads and executes the computer program, the device for designing and executing an AI workflow for teaching according to any one of claims 1 to 8 is used.

Images