CN117557428A - Teaching assistance method and system based on AI vision - Google Patents

Teaching assistance method and system based on AI vision Download PDF

Info

Publication number
CN117557428A
CN117557428A CN202410043477.1A CN202410043477A CN117557428A CN 117557428 A CN117557428 A CN 117557428A CN 202410043477 A CN202410043477 A CN 202410043477A CN 117557428 A CN117557428 A CN 117557428A
Authority
CN
China
Prior art keywords
information
image
deviation
student
characteristic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202410043477.1A
Other languages
Chinese (zh)
Other versions
CN117557428B (en
Inventor
何昌红
严小伟
罗杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Huashisheng Electronic Technology Co ltd
Original Assignee
Shenzhen Huashisheng Electronic Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Huashisheng Electronic Technology Co ltd filed Critical Shenzhen Huashisheng Electronic Technology Co ltd
Priority to CN202410043477.1A priority Critical patent/CN117557428B/en
Publication of CN117557428A publication Critical patent/CN117557428A/en
Application granted granted Critical
Publication of CN117557428B publication Critical patent/CN117557428B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to an AI vision-based teaching auxiliary method and system, and relates to the technical field of auxiliary teaching, wherein the method comprises the following steps: acquiring real-time image detection information of a student side and current teaching content information; identifying real-time image information of the student head from real-time image detection information of the student end based on the preset student head characteristics; analyzing and processing the current teaching content information and the student head real-time image information to form current teaching image reference information; analyzing and processing the real-time image information of the head portrait of the student and the reference information of the current teaching image to form abnormal values of the head portrait image; and if and only if the abnormal value of the head portrait image is larger than the preset abnormal reference value, calling the head portrait reference information of the student based on the real-time image information of the student head portrait, and combining the head portrait reference information of the student with the preset abnormal reference early warning information of the student to serve as abnormal early warning information of the student and outputting the abnormal early warning information of the student. The application has the effect of facilitating the teacher to manage students in the teaching process.

Description

Teaching assistance method and system based on AI vision
Technical Field
The application relates to the technical field of auxiliary teaching, in particular to an AI vision-based teaching auxiliary method and system.
Background
The auxiliary teaching means that various technological means such as a computer, the Internet, multimedia and the like are used for assisting a teacher in teaching activities, helping students to better understand and master knowledge, and simultaneously reducing the teaching burden of the teacher so that the teaching is more efficient and convenient.
In the related art, computer aided teaching is an interactive bilateral activity process formed by independently learning by a teacher through computer coaching and students through computers. The teacher carries out the establishment of teaching plan, the arrangement of teaching content, the preparation of teaching material and the management of teaching process at the teacher end, and the student is learned the teaching content at student's end, and student and teacher pass through the network and carry out the transmission each other and show with the data information that student's end and teacher output to in time feedback study condition makes the teaching activity become the process of two-way communication.
With respect to the related art as described above, the applicant found the following drawbacks: when the computer is adopted to assist the teaching, the teacher is inconvenient to learn the real-time learning conditions of all students because the teacher and the students are not in the same space or in the multimedia teaching room, so that the students are inconvenient to manage in the teaching process.
Disclosure of Invention
In order to facilitate teachers to manage students in the teaching process, the application provides an AI vision-based teaching auxiliary method and system.
In a first aspect, the present application provides an AI vision-based teaching assistance method, which adopts the following technical scheme:
an AI vision-based teaching assistance method, comprising:
acquiring real-time image detection information of a student side and current teaching content information;
identifying real-time image information of the student head from real-time image detection information of the student end based on the preset student head characteristics;
analyzing and processing the current teaching content information and the student head real-time image information according to a preset teaching content image reference analysis method to form current teaching image reference information;
analyzing and processing the real-time image information of the head portrait of the student and the reference information of the current teaching image according to a preset head portrait image anomaly analysis method to form head portrait image anomaly values;
and if and only if the abnormal value of the head portrait image is larger than the preset abnormal reference value, calling the head portrait reference information of the student based on the real-time image information of the student head portrait, combining the head portrait reference information of the student with the preset abnormal reference early warning information of the student to serve as abnormal early warning information of the student, and outputting the abnormal early warning information of the student.
Optionally, the analyzing the current teaching content information and the real-time image information of the student head according to the preset teaching content image reference analysis method to form the current teaching image reference information includes:
retrieving teaching content category information based on the current teaching content information;
analyzing and acquiring content type student operation demand information corresponding to the teaching content type information according to the corresponding relation between the teaching content type information and the preset content type student operation demand information;
analyzing and acquiring content type student operation image characteristic information corresponding to the content type student operation demand information according to the corresponding relation between the content type student operation demand information and the preset content type student operation image characteristic information;
retrieving student head reference image information based on student head real-time image information;
and combining the student head reference image information with the content type student operation image characteristic information to form student head operation characteristic comprehensive image information, and taking the student head operation characteristic comprehensive image information as current teaching image reference information.
Optionally, the analyzing the real-time image information of the head portrait of the student and the reference information of the current teaching image according to the preset head portrait image anomaly analysis method to form the head portrait image anomaly value includes:
Analyzing and acquiring deviation information between the real-time image information of the head portrait of the student and the reference information of the current teaching image and taking the deviation information as the deviation information of the image of the head portrait of the student;
retrieving an image deviation position point and an image deviation position deviation value based on student head image deviation information;
according to the corresponding relation between the image deviation position deviation value and the preset image deviation position deviation influence value, analyzing and obtaining the image deviation position deviation influence value corresponding to the image deviation position deviation value;
retrieving image position characteristic information based on student head real-time image information;
taking the image position characteristic information corresponding to the image deviation position point as the image deviation position characteristic information;
analyzing the image deviation position characteristic information according to a preset deviation position characteristic influence analysis method to form a deviation position characteristic influence value;
analyzing and calculating a sum value between an image deviation position deviation influence value and a deviation position characteristic influence value and taking the sum value as an image deviation comprehensive influence value;
according to the corresponding relation between the image deviation comprehensive influence value and the preset image deviation comprehensive abnormal value, analyzing and obtaining the image deviation comprehensive abnormal value corresponding to the image deviation comprehensive influence value, and taking the image deviation comprehensive abnormal value as the head portrait image abnormal value.
Optionally, the analyzing the image deviation position feature information according to the preset deviation position feature influence analyzing method to form a deviation position feature influence value includes:
judging whether the image deviation position characteristic information belongs to content type student operation image characteristic information or not;
if so, analyzing and acquiring a deviation position characteristic operation influence value corresponding to the image deviation position characteristic information according to the corresponding relation between the image deviation position characteristic information and a preset deviation position characteristic operation influence value, and taking the deviation position characteristic reference influence value as the deviation position characteristic influence value;
if not, calling the deviation position characteristic type information based on the image deviation position characteristic information;
according to the corresponding relation between the deviation position characteristic type information and the preset deviation position characteristic type influence value, analyzing and obtaining a deviation position characteristic type influence value corresponding to the deviation position characteristic type information, and taking the deviation position characteristic type influence value as a deviation position characteristic influence value.
Optionally, the method further comprises the step of setting the deviation position feature reference influence value as a deviation position feature influence value or setting the deviation position feature type influence value as a deviation position feature influence value, specifically as follows:
Retrieving student head history application information based on student head real-time image information;
the method comprises the steps of calling historical application time points, historical application demand time periods and historical application event information based on student head historical application information;
analyzing and calculating a time period between a historical application time point and a current time point and taking the time period as an actual time period of the historical application;
judging whether the actual time period of the historical application is greater than the actual time period of the historical application;
if yes, continuing to output the deviation position characteristic influence value;
if not, analyzing and acquiring the history application event influence characteristic information corresponding to the history application event information according to the corresponding relation between the history application event information and the preset history application event influence characteristic information;
according to a preset historical application influence analysis method, historical application influence characteristic information is analyzed and processed to form a historical application influence value, and the historical application influence value is added into a deviation position characteristic influence value to form a new deviation position characteristic influence value.
Optionally, the analyzing the influence characteristic information of the historical application according to the preset historical application influence analysis method to form the historical application influence value includes:
Judging whether the image deviation position characteristic information belongs to the historical application influence characteristic information;
if yes, outputting a preset application event influence reference influence value and taking the application event influence value as a historical application influence value;
if not, taking the image deviation position characteristic information belonging to the history application event influencing characteristic information as image deviation event influencing characteristic information, and taking the image deviation position characteristic information not belonging to the history application event influencing characteristic information as image deviation residual characteristic information;
analyzing and calculating the difference between the feature number value corresponding to the residual feature information of the image deviation and the feature number value corresponding to the influence feature information of the image deviation, and taking the difference as the residual feature proportion value of the image deviation;
and analyzing and processing the residual characteristic proportion value of the image deviation according to a preset image deviation abnormality early warning analysis method to form image deviation abnormality early warning information, and outputting the image deviation abnormality early warning information.
Optionally, the analyzing the image deviation residual feature ratio value according to the preset image deviation abnormality pre-warning analysis method to form the image deviation abnormality pre-warning information includes:
judging whether the image deviation residual characteristic proportion value is larger than a preset image deviation residual characteristic proportion reference value or not;
If yes, calling residual feature position points based on residual feature information of the image deviation;
according to the corresponding relation between the residual characteristic position points and the preset residual characteristic position abnormality early warning information, analyzing and obtaining residual characteristic position abnormality early warning information corresponding to the residual characteristic position points, and taking the residual characteristic position abnormality early warning information as image deviation abnormality early warning information;
if not, outputting preset image deviation reference early warning information and taking the preset image deviation reference early warning information as abnormal early warning information of students.
In a second aspect, the present application provides an AI vision-based teaching assistance system, which adopts the following technical scheme:
an AI vision-based teaching assistance system, comprising:
the acquisition module is used for acquiring real-time image detection information of the student end and current teaching content information;
a memory for storing a program of the AI-vision-based teaching assistance method according to any one of the first aspects;
a processor, a program in a memory capable of being loaded by the processor and implementing the AI vision-based teaching assistance method according to any one of the first aspects.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the method comprises the steps of obtaining real-time image detection information of a student end and current teaching content information, identifying student head real-time image information, analyzing and processing the current teaching content information and the student head real-time image information to form current teaching image reference information, analyzing and processing the student head real-time image information and the current teaching image reference information to form head image abnormal values, and if and only if the head image abnormal values are larger than abnormal reference values, retrieving student head reference information through the student head real-time image information, combining the student head reference information with preset student abnormal reference early warning information to be used as student abnormal early warning information and outputting the student abnormal early warning information, so that the students are detected through AI vision technology, and a teacher can manage the students in the teaching process conveniently;
2. Acquiring teaching content type information through current teaching content information, analyzing and acquiring content type student operation requirement information, analyzing and acquiring content type student operation image characteristic information through content type student operation requirement information, acquiring student head reference image information through student head real-time image information, combining the student head reference image information with the content type student operation image characteristic information to form student head operation characteristic comprehensive image information, and taking the student head operation characteristic comprehensive image information as current teaching image reference information, so that accuracy of acquired current teaching image reference information is improved;
3. the method comprises the steps of analyzing and obtaining deviation information between real-time image information of a student head and current teaching image reference information, taking the deviation information as student head image deviation information, calling image deviation position points and image deviation position deviation values, analyzing and obtaining image deviation position deviation influence values through the image deviation position deviation values, calling image position characteristic information through the student head image real-time image information, taking the image position characteristic information corresponding to the image deviation position points as image deviation position characteristic information, analyzing and processing the image deviation position characteristic information to form deviation position characteristic influence values, analyzing and calculating sum values between the image deviation position deviation influence values and the deviation position characteristic influence values, taking the sum values as image deviation comprehensive influence values, analyzing and obtaining image deviation comprehensive abnormal values through the image deviation comprehensive influence values, taking the image deviation comprehensive abnormal values as head image abnormal values, and accordingly improving accuracy of the obtained head image abnormal values.
Drawings
Fig. 1 is a flow chart of a method of AI vision-based teaching assistance in an embodiment of the present application.
Fig. 2 is a flowchart of a method for analyzing current teaching content information and real-time image information of a student head to form current teaching image reference information according to a preset teaching content image reference analysis method in an embodiment of the present application.
Fig. 3 is a flowchart of a method for analyzing real-time image information of a student head and reference information of a current teaching image according to a preset head image anomaly analysis method to form an anomaly value of the head image according to an embodiment of the present application.
Fig. 4 is a flowchart of a method for analyzing image deviation location feature information to form a deviation location feature influence value according to a preset deviation location feature influence analysis method according to an embodiment of the present application.
Fig. 5 is a flowchart of a method of an embodiment of the present application following a bias position feature reference impact value as a bias position feature impact value or following a bias position feature type impact value as a bias position feature impact value.
FIG. 6 is a flowchart of a method for analyzing historical application event influence characteristics according to a preset historical application influence analysis method to form a historical application influence value according to an embodiment of the present application.
Fig. 7 is a flowchart of a method for analyzing and processing residual feature ratio values of image deviation according to a preset image deviation abnormality pre-warning analysis method to form image deviation abnormality pre-warning information according to an embodiment of the present application.
Fig. 8 is a system flow diagram of AI vision-based teaching assistance in an embodiment of the present application.
Reference numerals illustrate: 1. an acquisition module; 2. a memory; 3. a processor.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to fig. 1 to 8 and the embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The embodiment of the application discloses an AI vision-based teaching assistance method.
Referring to fig. 1, an AI vision-based teaching assistance method includes:
step S100: and acquiring real-time image detection information and current teaching content information of the student side.
The student-side real-time image detection information is real-time image information used for indicating students to detect when the students use the student-side real-time image detection information, and the student-side real-time image detection information is detected and acquired by presetting the student-side image detection information. The current teaching content information is content information for indicating a teacher to conduct teaching at the current time, and the current teaching content information is obtained through inquiry from the teacher side.
Step S200: and identifying the real-time image information of the student head from the real-time image detection information of the student end based on the preset student head characteristics.
The student head features refer to information for indicating the position features of different student head features and the like, and the student head features are inquired and acquired from a database storing the student head features. The student head real-time image information refers to real-time image information for indicating to display the student head and other parts,
the student head real-time image information is identified from the student end real-time image detection information through the student head characteristics, so that the subsequent use is convenient.
Step S300: according to the preset teaching content image reference analysis method, analyzing and processing the current teaching content information and the student head real-time image information to form the current teaching image reference information.
The teaching content image reference analysis method is used for analyzing the current teaching image reference information, and the teaching content image reference analysis method is obtained by inquiring a database storing the teaching content image reference analysis method.
The current teaching content information and the student head real-time image information are analyzed and processed through the teaching content image reference analysis method, so that the current teaching image reference information is formed, and the subsequent use is convenient.
Step S400: according to a preset head portrait image anomaly analysis method, the real-time image information of the head portrait of the student and the current teaching image reference information are analyzed and processed to form head portrait image anomaly values.
The head image anomaly value is an anomaly degree value for indicating that the head image is abnormal, the head image anomaly analysis method is an analysis method for analyzing the head image anomaly value, and the head image anomaly analysis method is obtained by inquiring a database storing the head image anomaly analysis method.
And analyzing and processing the real-time image information of the head portrait of the student and the reference information of the current teaching image by using the head portrait image anomaly analysis method, so that the head portrait image anomaly value is formed, and the subsequent use is convenient.
Step S500: and if and only if the abnormal value of the head portrait image is larger than the preset abnormal reference value, calling the head portrait reference information of the student based on the real-time image information of the student head portrait, combining the head portrait reference information of the student with the preset abnormal reference early warning information of the student to serve as abnormal early warning information of the student, and outputting the abnormal early warning information of the student.
The anomaly reference value is a reference anomaly degree value which can be tolerated when the head portrait image is abnormal, and the anomaly reference value is obtained by inquiring a database storing the anomaly reference value. The student head reference information is reference information for indicating students corresponding to the student head, and the student head reference information is inquired and obtained from a database storing the student head reference information. The student abnormal reference early warning information refers to reference early warning information for indicating early warning when student abnormal conditions occur, and the student abnormal reference early warning information is inquired and obtained from a database storing the student abnormal reference early warning information. The student abnormality early warning information is early warning information for indicating early warning when abnormality exists in students.
If and only if the abnormal value of the head portrait image is larger than the abnormal reference value, the fact that the student has larger abnormality at the moment is indicated, so that the head portrait reference information of the student is called through the head portrait real-time image information of the student, and the head portrait reference information of the student and the abnormal reference early warning information of the student are combined to be used as abnormal early warning information of the student and output, so that the abnormality of the student is detected through the AI vision technology, and a teacher can manage the student in the teaching process conveniently.
When the abnormal value of the head portrait image is not larger than the abnormal reference value, the fact that the student has no larger abnormality at the moment is indicated, and the real-time image detection information of the student side is continuously acquired at the moment.
In step S300 shown in fig. 1, in order to further ensure the rationality of the current teaching image reference information, further separate analysis and calculation of the current teaching image reference information is required, specifically, the detailed description will be given by the steps shown in fig. 2.
Referring to fig. 2, according to a preset teaching content image reference analysis method, the present teaching content information and student head real-time image information are analyzed and processed to form the present teaching image reference information, which comprises the following steps:
step S310: and retrieving teaching content category information based on the current teaching content information.
The teaching content type information is type information for indicating that the content belongs to when teaching is performed at the current time, and the teaching content type information is obtained by inquiring a database storing the teaching content type information. The teaching content category information includes teaching content teaching category, teaching content talking category, teaching content question category, and the like.
The teaching content type information is called through the current teaching content information, so that the follow-up use is convenient.
Step S320: and analyzing and acquiring content type student operation requirement information corresponding to the teaching content type information according to the corresponding relation between the teaching content type information and the preset content type student operation requirement information.
The content type student operation requirement information is operation information for indicating operations required by students according to teaching content, and the content type student operation requirement information is obtained by inquiring a database storing the content type student operation requirement information.
The operation requirement information of the content type students is obtained through analysis of the teaching content type information, so that the follow-up use is convenient.
Step S330: and analyzing and acquiring content type student operation image characteristic information corresponding to the content type student operation requirement information according to the corresponding relation between the content type student operation requirement information and the preset content type student operation image characteristic information.
The content type student operation image characteristic information is used for indicating characteristic information in an image when students operate according to teaching content, and the content type student operation image characteristic information is inquired and obtained from a database storing the content type student operation image characteristic information.
And analyzing and acquiring the operation image characteristic information of the content type students through the operation requirement information of the content type students, so that the follow-up use is convenient. For example, when the teaching content type information is a teaching content teaching type, the content type student operation image feature information is a feature corresponding to a student's eye watching end, and when the teaching content type information is a teaching content question type, the content type student operation image feature information is a feature corresponding to a direction in which a student's eye is regarded as a question and a hand is questions.
Step S340: and calling the student head reference image information based on the student head real-time image information.
The student head reference image information is reference image information for indicating that the student head is under normal conditions, and the student head reference image information is inquired and obtained from a database storing the student head reference image information.
The student head reference image information is called through the student head real-time image information, so that the student head reference image information is convenient to use subsequently.
Step S350: and combining the student head reference image information with the content type student operation image characteristic information to form student head operation characteristic comprehensive image information, and taking the student head operation characteristic comprehensive image information as current teaching image reference information.
The student head operation characteristic comprehensive image information is used for indicating the student head to integrate operation characteristics with a standard image under normal conditions, combines the student head standard image information with content type student operation image characteristic information to form student head operation characteristic comprehensive image information, and uses the student head operation characteristic comprehensive image information as current teaching image standard information, so that accuracy of acquired current teaching image standard information is improved.
In step S400 shown in fig. 1, in order to further ensure the rationality of the current teaching image reference information, further separate analysis and calculation of the current teaching image reference information is required, specifically, the detailed description will be given by the steps shown in fig. 3.
Referring to fig. 3, according to a preset head portrait image anomaly analysis method, the method for analyzing and processing real-time image information of a student head portrait and reference information of a current teaching image to form an anomaly value of the head portrait image includes the following steps:
step S410: and analyzing and acquiring deviation information between the real-time image information of the head portrait of the student and the reference information of the current teaching image, and taking the deviation information as the deviation information of the image of the head portrait of the student.
The student head image deviation information is deviation information used for indicating that the student head image has deviation, and the deviation information between the student head real-time image information and the current teaching image reference information is analyzed and obtained and used as the student head image deviation information, so that the student head image deviation information is convenient to use subsequently.
Step S420: and retrieving an image deviation position point and an image deviation position deviation value based on the student head image deviation information.
The image deviation position points are position points used for indicating positions where the image deviation exists, and the image deviation position points are obtained by inquiring a database storing the image deviation position points. The image deviation position deviation value refers to a deviation degree value for indicating a position where an image is located when the image is deviated, and the image deviation position deviation value is obtained by inquiring a database storing the image deviation position deviation value.
The image deviation position points and the image deviation position deviation values are called through the head portrait image deviation information of the student, so that the subsequent use is convenient.
Step S430: and analyzing and acquiring the image deviation position deviation influence value corresponding to the image deviation position deviation value according to the corresponding relation between the image deviation position deviation value and the preset image deviation position deviation influence value.
The image deviation position deviation influence value refers to an influence degree value for indicating deviation of a position where the image deviation is located, and the image deviation position deviation influence value is obtained by inquiring a database storing the image deviation position deviation influence value.
And obtaining an image deviation position deviation influence value through image deviation position deviation value analysis, so that the subsequent use is convenient.
Step S440: and retrieving image position characteristic information based on the student head real-time image information.
The image position characteristic information is characteristic information corresponding to each position of the image, and the image position characteristic information is obtained by inquiring a database storing the image position characteristic information.
The image position characteristic information is called through the real-time image information of the head portrait of the student, so that the subsequent use is convenient.
Step S450: and taking the image position characteristic information corresponding to the image deviation position point as the image deviation position characteristic information.
The image deviation position characteristic information is characteristic information corresponding to deviation indicating the position where the image deviation is located, and the image position characteristic information corresponding to the image deviation position point is used as the image deviation position characteristic information, so that the subsequent use is convenient.
Step S460: and analyzing the image deviation position characteristic information according to a preset deviation position characteristic influence analysis method to form a deviation position characteristic influence value.
The deviation position characteristic influence value is an influence degree value used for indicating influence of a characteristic corresponding to a deviation position, the deviation position characteristic influence analysis method is an analysis method used for analyzing the deviation position characteristic influence value, and the deviation position characteristic influence analysis method is obtained by inquiring a database storing the deviation position characteristic influence analysis method.
And analyzing and processing the image deviation position characteristic information through a deviation position characteristic influence analysis method, so that a deviation position characteristic influence value is formed, and the follow-up use is convenient.
Step S470: and analyzing and calculating the sum value between the image deviation position deviation influence value and the deviation position characteristic influence value to be used as an image deviation comprehensive influence value.
The image deviation comprehensive influence value is a comprehensive influence degree value for indicating the influence of the image deviation, and the sum value between the image deviation position deviation influence value and the deviation position characteristic influence value is analyzed and calculated and used as the image deviation comprehensive influence value, so that the subsequent use is convenient.
Step S480: according to the corresponding relation between the image deviation comprehensive influence value and the preset image deviation comprehensive abnormal value, analyzing and obtaining the image deviation comprehensive abnormal value corresponding to the image deviation comprehensive influence value, and taking the image deviation comprehensive abnormal value as the head portrait image abnormal value.
The image deviation integrated anomaly value is an integrated anomaly degree value indicating the occurrence of an image deviation, and is obtained by searching a database in which the image deviation integrated anomaly value is stored.
And obtaining an image deviation comprehensive abnormal value through analysis of the image deviation comprehensive influence value, and taking the image deviation comprehensive abnormal value as an image abnormal value of the head portrait, so that the accuracy of the obtained image abnormal value of the head portrait is improved.
In step S460 shown in fig. 3, in order to further secure the rationality of the deviation position characteristic influence value, further individual analysis calculation of the deviation position characteristic influence value is required, and specifically, the detailed description will be given by the steps shown in fig. 4.
Referring to fig. 4, according to a preset deviation position feature influence analysis method to analyze image deviation position feature information to form a deviation position feature influence value includes the steps of:
Step S461: and judging whether the image deviation position characteristic information belongs to content type student operation image characteristic information. If yes, go to step S462; if not, step S463 is executed.
And judging whether the characteristic information of the position of the image deviation belongs to the content type student operation image characteristic information or not, so as to judge whether the characteristic of the position of the image deviation is the characteristic of the student needing to operate or not.
Step S462: according to the corresponding relation between the image deviation position characteristic information and the preset deviation position characteristic operation influence value, analyzing and obtaining a deviation position characteristic operation influence value corresponding to the image deviation position characteristic information, and taking the deviation position characteristic reference influence value as a deviation position characteristic influence value.
The deviation position characteristic operation influence value is an influence degree value for indicating the influence of the characteristic of the position where the image deviation is located on the operation, and the deviation position characteristic operation influence value is obtained by inquiring a database storing the deviation position characteristic operation influence value.
When the image deviation position characteristic information belongs to content type student operation image characteristic information, the characteristic of the position where the image deviation is located is the characteristic that the student needs to operate, so that the deviation position characteristic operation influence value is obtained through analysis of the image deviation position characteristic information, and the deviation position characteristic reference influence value is used as the deviation position characteristic influence value, so that the accuracy of the obtained deviation position characteristic influence value is improved.
Step S463: and calling the deviation position characteristic type information based on the image deviation position characteristic information.
The offset position feature type information is type information indicating a feature of a position where an image offset is located, and is obtained by searching a database storing the offset position feature type information.
The deviation position characteristic type information is called through the image deviation position characteristic information, so that the follow-up use is convenient.
Step S464: according to the corresponding relation between the deviation position characteristic type information and the preset deviation position characteristic type influence value, analyzing and obtaining a deviation position characteristic type influence value corresponding to the deviation position characteristic type information, and taking the deviation position characteristic type influence value as a deviation position characteristic influence value.
The deviation position feature type influence value is an influence degree value indicating a type of feature of a position where the image deviation is located, and the deviation position feature type influence value is obtained by searching a database storing the deviation position feature type influence value.
When the image deviation position feature information does not belong to the content type student operation image feature information, the feature of the position where the image deviation is located is not the feature of the student needing to operate, so that the deviation position feature type influence value is obtained through analysis of the deviation position feature type information, and the deviation position feature type influence value is used as the deviation position feature influence value, and the accuracy of the obtained deviation position feature influence value is improved.
After step S462 or after step S464 shown in fig. 4, further individual analysis and calculation of the deviation position characteristic influence value is required in order to further secure the rationality of the deviation position characteristic influence value, and specifically, the steps shown in fig. 5 will be described in detail.
Referring to fig. 5, the step of taking the deviation position feature reference influence value as the deviation position feature influence value or taking the deviation position feature kind influence value as the deviation position feature influence value includes the steps of:
step S4621: and calling historical application information of the student head based on the student head real-time image information.
The student head history application information is application information for indicating students corresponding to the student head to apply for at history time, and the student head history application information is obtained by inquiring from a database storing the student head history application information.
The student head history application information is called through the student head real-time image information, so that the student head history application information is convenient to use subsequently.
Step S4622: and calling historical application time points, historical application demand time periods and historical application event information based on the student head historical application information.
The historical application time point is a time point for indicating the student corresponding to the student head to apply for at the historical time, and the historical application time point is obtained by inquiring from a database storing the historical application time point. The historical application demand time period is a duration time period for indicating students corresponding to the head portraits of the students to apply for the demand duration in the historical time, and the historical application demand time period is obtained by inquiring a database storing the historical application demand time period. The historical application event information is event information for indicating students corresponding to the head portraits of the students to apply for at historical time, and the historical application event information is obtained by inquiring from a database storing the historical application event information.
The historical application time point, the historical application demand time period and the historical application event information are called through the student head historical application information, so that the student head historical application information is convenient to use subsequently.
Step S4623: and analyzing and calculating the time period between the time point of the historical application and the current time point and taking the time period as the actual time period of the historical application.
The actual time period of the historical application is a duration time period which is used for indicating the students corresponding to the head portraits of the students to apply for the students in the historical time and is actually continuous, and the actual time period of the historical application is analyzed and calculated and used as the actual time period of the historical application through the time period between the time point of the historical application and the current time point, so that the students can use the head portraits conveniently and subsequently.
Step S4624: and judging whether the actual time period of the historical application is greater than the actual time period of the historical application. If yes, go to step S4625; if not, step S4626 is performed.
And judging whether the actual time period of the historical application is greater than the actual time period of the historical application, so as to judge whether the current time is still in the time period of the application of the student corresponding to the head of the student in the historical time.
Step S4625: and continuing to output the deviation position characteristic influence value.
When the actual time period of the historical application is greater than the actual time period of the historical application, the current time is not in the time period of the application of the student corresponding to the head portrait of the student in the historical time, so that the deviation position characteristic influence value is continuously output.
Step S4626: according to the corresponding relation between the history application event information and the preset history application event influence characteristic information, analyzing and obtaining the history application event influence characteristic information corresponding to the history application event information.
The history application event influencing characteristic information is characteristic information for indicating that the history application event influences characteristics, and the history application event influencing characteristic information is obtained by inquiring from a database storing the history application event influencing characteristic information.
When the actual time period of the historical application is not more than the actual time period of the historical application, the current time is in the time period of the application of the student corresponding to the head portrait of the student in the historical time, so that the historical application event influence characteristic information is obtained through the historical application event information analysis, and the follow-up use is convenient.
Step S4627: according to a preset historical application influence analysis method, historical application influence characteristic information is analyzed and processed to form a historical application influence value, and the historical application influence value is added into a deviation position characteristic influence value to form a new deviation position characteristic influence value.
The historical application influence value is an influence degree value for indicating influence of the historical application, the historical application influence analysis method is an analysis method for analyzing the influence value of the historical application, and the historical application influence analysis method is obtained by inquiring a database storing the historical application influence analysis method.
The historical application influence analysis method is used for analyzing and processing the historical application event influence characteristic information, so that a historical application influence value is formed, the historical application influence value is added into the deviation position characteristic influence value to form a new deviation position characteristic influence value, and the accuracy of the obtained deviation position characteristic influence value is improved.
In step S4627 shown in fig. 5, in order to further secure the rationality of the historical application influence value, further individual analysis and calculation of the historical application influence value is required, and specifically, the detailed description will be given by the steps shown in fig. 6.
Referring to fig. 6, according to a preset method for analyzing influence of a historical application, the method for analyzing influence characteristic information of a historical application to form an influence value of the historical application includes the following steps:
step S46271: judging whether the image deviation position characteristic information belongs to the history application influence characteristic information. If yes, go to step S46272; if not, step S46273 is performed.
And judging whether the characteristic information of the image deviation position belongs to the history application and influence the characteristic information, so as to judge whether the characteristic of the position where the image deviation is located is caused by the history application.
Step S46272: and outputting a preset application event influence reference influence value and taking the preset application event influence reference influence value as a historical application influence value.
The application-related influence reference influence value is a reference influence degree value indicating influence of application related matters, and the application-related influence reference influence value is obtained by inquiring from a database storing the application-related influence reference influence value.
When the image deviation position feature information belongs to the history application influence feature information, the feature of the position where the image deviation is located is caused by the history application, so that the accuracy of the acquired history application influence value is improved by outputting a preset application influence reference influence value and taking the preset application influence value as the history application influence value.
Step S46273: image deviation position characteristic information belonging to historical application event influence characteristic information is used as image deviation event influence characteristic information, and image deviation position characteristic information not belonging to historical application event influence characteristic information is used as image deviation residual characteristic information.
The image deviation event influencing characteristic information is characteristic information corresponding to the image deviation generated by the applicant, and the image deviation remaining characteristic information is characteristic information except for the image deviation event influencing characteristic information.
When the image deviation position characteristic information is unevenly distributed in the history application influence characteristic information, the characteristic that the image deviation is located is not caused by the history application, so that the image deviation position characteristic information which is distributed in the history application influence characteristic information is used as the image deviation influence characteristic information, and the image deviation position characteristic information which is not distributed in the history application influence characteristic information is used as the image deviation residual characteristic information, thereby being convenient for subsequent use.
Step S46274: and analyzing and calculating the difference between the feature number value corresponding to the residual feature information of the image deviation and the feature number value corresponding to the influence feature information of the image deviation, and taking the difference as the residual feature proportion value of the image deviation.
The image deviation residual characteristic proportion value is a proportion value between a residual characteristic in the image deviation and a characteristic corresponding to the application event generated image deviation, and is convenient to use subsequently by analyzing and calculating the difference value between a characteristic number value corresponding to the image deviation residual characteristic information and a characteristic number value corresponding to the image deviation event influence characteristic information.
Step S46275: and analyzing and processing the residual characteristic proportion value of the image deviation according to a preset image deviation abnormality early warning analysis method to form image deviation abnormality early warning information, and outputting the image deviation abnormality early warning information.
The image deviation abnormality early warning information is early warning information for indicating that the image deviation is abnormal, the image deviation abnormality early warning analysis method is an analysis method for analyzing the image deviation abnormality early warning information, and the image deviation abnormality early warning analysis method is obtained by inquiring a database storing the image deviation abnormality early warning analysis method.
The image deviation residual characteristic proportion value is analyzed and processed through the image deviation abnormality early warning analysis method, so that image deviation abnormality early warning information is formed, and the image deviation abnormality early warning information is output, so that early warning is timely carried out when the image deviation is abnormal, and a teacher at a teacher end can know timely.
In step S46275 shown in fig. 6, in order to further secure the rationality of the image deviation abnormality warning information, further individual analysis and calculation of the image deviation abnormality warning information is required, and specifically, the steps shown in fig. 7 will be described in detail.
Referring to fig. 7, according to a preset image deviation abnormality pre-warning analysis method, to analyze and process the image deviation residual feature ratio value to form image deviation abnormality pre-warning information includes the following steps:
step S462751: and judging whether the image deviation residual characteristic proportion value is larger than a preset image deviation residual characteristic proportion reference value. If yes, go to step S462752; if not, step S462754 is performed.
The image deviation residual feature ratio reference value is a reference ratio value for indicating tolerance between residual features in the image deviation and features corresponding to the application event generated image deviation, and is obtained by inquiring from a database storing the image deviation residual feature ratio reference value.
And judging whether the residual characteristic proportion value of the image deviation is larger than a preset residual characteristic proportion reference value of the image deviation or not, so as to judge whether the residual characteristic in the image deviation is excessive or not.
Step S462752: and calling the residual feature position points based on the residual feature information of the image deviation.
The residual feature position points are position points used for indicating positions of residual features in the image deviation, and the residual feature position points are obtained by inquiring a database storing the residual feature position points.
When the image deviation residual characteristic proportion value is larger than the preset image deviation residual characteristic proportion reference value, the fact that the residual characteristics in the image deviation are excessive at the moment is indicated, so that residual characteristic position points are called through the image deviation residual characteristic information, and the follow-up use is convenient.
Step S462753: and analyzing and acquiring residual characteristic position abnormality early-warning information corresponding to the residual characteristic position points according to the corresponding relation between the residual characteristic position points and preset residual characteristic position abnormality early-warning information, and taking the residual characteristic position abnormality early-warning information as image deviation abnormality early-warning information.
The residual characteristic position abnormality early warning information is early warning information for indicating abnormality in the position where the residual characteristic in the image deviation is located, and the residual characteristic position abnormality early warning information is obtained by inquiring a database storing the residual characteristic position abnormality early warning information.
And acquiring residual characteristic position abnormality early warning information through residual characteristic position point analysis, and taking the residual characteristic position abnormality early warning information as image deviation abnormality early warning information, so that the subsequent use is convenient.
Step S462754: and outputting preset image deviation reference early warning information and taking the preset image deviation reference early warning information as abnormal early warning information of students.
The image deviation reference early warning information is early warning information for indicating that reference early warning is carried out on the image deviation, and the image deviation reference early warning information is obtained by inquiring a database storing the image deviation reference early warning information.
When the image deviation residual characteristic proportion value is not larger than the preset image deviation residual characteristic proportion reference value, the fact that residual characteristics in the image deviation are not excessive at the moment is indicated, and preset image deviation reference early warning information is output and used as student abnormality early warning information, and therefore accuracy of the acquired student abnormality early warning information is improved.
Referring to fig. 8, based on the same inventive concept, an embodiment of the present invention provides an AI vision-based teaching assistance system, including:
the acquisition module 1 is used for acquiring real-time image detection information and current teaching content information of a student side;
a memory 2 for storing a program of the AI-vision-based teaching assistance method as described in any one of fig. 1 to 7;
The processor 3, the program in the memory can be loaded by the processor to be executed and implement the AI vision-based teaching assistance method as described in any one of fig. 1 to 7.
The foregoing description of the preferred embodiments of the present application is not intended to limit the scope of the application, in which any feature disclosed in this specification (including abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.

Claims (8)

1. An AI vision-based teaching assistance method, comprising:
acquiring real-time image detection information of a student side and current teaching content information;
identifying real-time image information of the student head from real-time image detection information of the student end based on the preset student head characteristics;
analyzing and processing the current teaching content information and the student head real-time image information according to a preset teaching content image reference analysis method to form current teaching image reference information;
analyzing and processing the real-time image information of the head portrait of the student and the reference information of the current teaching image according to a preset head portrait image anomaly analysis method to form head portrait image anomaly values;
And if and only if the abnormal value of the head portrait image is larger than the preset abnormal reference value, calling the head portrait reference information of the student based on the real-time image information of the student head portrait, combining the head portrait reference information of the student with the preset abnormal reference early warning information of the student to serve as abnormal early warning information of the student, and outputting the abnormal early warning information of the student.
2. The AI-vision-based teaching assistance method according to claim 1, wherein analyzing the current teaching content information and the student head real-time image information to form the current teaching image reference information according to the preset teaching content image reference analysis method comprises:
retrieving teaching content category information based on the current teaching content information;
analyzing and acquiring content type student operation demand information corresponding to the teaching content type information according to the corresponding relation between the teaching content type information and the preset content type student operation demand information;
analyzing and acquiring content type student operation image characteristic information corresponding to the content type student operation demand information according to the corresponding relation between the content type student operation demand information and the preset content type student operation image characteristic information;
Retrieving student head reference image information based on student head real-time image information;
and combining the student head reference image information with the content type student operation image characteristic information to form student head operation characteristic comprehensive image information, and taking the student head operation characteristic comprehensive image information as current teaching image reference information.
3. The AI-vision-based teaching assistance method according to claim 2, wherein analyzing the real-time image information of the student head and the current teaching image reference information to form the head image outlier according to the preset head image outlier analysis method comprises:
analyzing and acquiring deviation information between the real-time image information of the head portrait of the student and the reference information of the current teaching image and taking the deviation information as the deviation information of the image of the head portrait of the student;
retrieving an image deviation position point and an image deviation position deviation value based on student head image deviation information;
according to the corresponding relation between the image deviation position deviation value and the preset image deviation position deviation influence value, analyzing and obtaining the image deviation position deviation influence value corresponding to the image deviation position deviation value;
retrieving image position characteristic information based on student head real-time image information;
Taking the image position characteristic information corresponding to the image deviation position point as the image deviation position characteristic information;
analyzing the image deviation position characteristic information according to a preset deviation position characteristic influence analysis method to form a deviation position characteristic influence value;
analyzing and calculating a sum value between an image deviation position deviation influence value and a deviation position characteristic influence value and taking the sum value as an image deviation comprehensive influence value;
according to the corresponding relation between the image deviation comprehensive influence value and the preset image deviation comprehensive abnormal value, analyzing and obtaining the image deviation comprehensive abnormal value corresponding to the image deviation comprehensive influence value, and taking the image deviation comprehensive abnormal value as the head portrait image abnormal value.
4. The AI-vision-based teaching assistance method according to claim 3, wherein analyzing the image deviation position feature information to form the deviation position feature influence value according to the preset deviation position feature influence analysis method includes:
judging whether the image deviation position characteristic information belongs to content type student operation image characteristic information or not;
if so, analyzing and acquiring a deviation position characteristic operation influence value corresponding to the image deviation position characteristic information according to the corresponding relation between the image deviation position characteristic information and a preset deviation position characteristic operation influence value, and taking the deviation position characteristic reference influence value as the deviation position characteristic influence value;
If not, calling the deviation position characteristic type information based on the image deviation position characteristic information;
according to the corresponding relation between the deviation position characteristic type information and the preset deviation position characteristic type influence value, analyzing and obtaining a deviation position characteristic type influence value corresponding to the deviation position characteristic type information, and taking the deviation position characteristic type influence value as a deviation position characteristic influence value.
5. The AI-vision-based teaching assistance method according to claim 4, further comprising the step of following the deviation position feature reference influence value as the deviation position feature influence value or following the deviation position feature category influence value as the deviation position feature influence value, concretely comprising the steps of:
retrieving student head history application information based on student head real-time image information;
the method comprises the steps of calling historical application time points, historical application demand time periods and historical application event information based on student head historical application information;
analyzing and calculating a time period between a historical application time point and a current time point and taking the time period as an actual time period of the historical application;
judging whether the actual time period of the historical application is greater than the actual time period of the historical application;
If yes, continuing to output the deviation position characteristic influence value;
if not, analyzing and acquiring the history application event influence characteristic information corresponding to the history application event information according to the corresponding relation between the history application event information and the preset history application event influence characteristic information;
according to a preset historical application influence analysis method, historical application influence characteristic information is analyzed and processed to form a historical application influence value, and the historical application influence value is added into a deviation position characteristic influence value to form a new deviation position characteristic influence value.
6. The AI-vision-based teaching assistance method according to claim 5, wherein analyzing the history application event influence feature information to form the history application influence value according to the preset history application influence analysis method comprises:
judging whether the image deviation position characteristic information belongs to the historical application influence characteristic information;
if yes, outputting a preset application event influence reference influence value and taking the application event influence value as a historical application influence value;
if not, taking the image deviation position characteristic information belonging to the history application event influencing characteristic information as image deviation event influencing characteristic information, and taking the image deviation position characteristic information not belonging to the history application event influencing characteristic information as image deviation residual characteristic information;
Analyzing and calculating the difference between the feature number value corresponding to the residual feature information of the image deviation and the feature number value corresponding to the influence feature information of the image deviation, and taking the difference as the residual feature proportion value of the image deviation;
and analyzing and processing the residual characteristic proportion value of the image deviation according to a preset image deviation abnormality early warning analysis method to form image deviation abnormality early warning information, and outputting the image deviation abnormality early warning information.
7. The AI-vision-based teaching assistance method according to claim 6, wherein analyzing the image deviation residual feature ratio value according to the preset image deviation abnormality pre-warning analysis method to form the image deviation abnormality pre-warning information includes:
judging whether the image deviation residual characteristic proportion value is larger than a preset image deviation residual characteristic proportion reference value or not;
if yes, calling residual feature position points based on residual feature information of the image deviation;
according to the corresponding relation between the residual characteristic position points and the preset residual characteristic position abnormality early warning information, analyzing and obtaining residual characteristic position abnormality early warning information corresponding to the residual characteristic position points, and taking the residual characteristic position abnormality early warning information as image deviation abnormality early warning information;
If not, outputting preset image deviation reference early warning information and taking the preset image deviation reference early warning information as abnormal early warning information of students.
8. An AI vision-based teaching assistance system, comprising:
the acquisition module (1) is used for acquiring real-time image detection information of a student side and current teaching content information;
a memory (2) for storing a program of the AI vision-based teaching assistance method according to any one of claims 1 to 7;
a processor (3), a program in a memory being loadable by the processor and implementing the AI vision-based teaching assistance method as claimed in any one of claims 1 to 7.
CN202410043477.1A 2024-01-11 2024-01-11 Teaching assistance method and system based on AI vision Active CN117557428B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410043477.1A CN117557428B (en) 2024-01-11 2024-01-11 Teaching assistance method and system based on AI vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410043477.1A CN117557428B (en) 2024-01-11 2024-01-11 Teaching assistance method and system based on AI vision

Publications (2)

Publication Number Publication Date
CN117557428A true CN117557428A (en) 2024-02-13
CN117557428B CN117557428B (en) 2024-05-07

Family

ID=89811494

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410043477.1A Active CN117557428B (en) 2024-01-11 2024-01-11 Teaching assistance method and system based on AI vision

Country Status (1)

Country Link
CN (1) CN117557428B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020082971A1 (en) * 2018-10-24 2020-04-30 江苏君英天达人工智能研究院有限公司 Real-time classroom monitoring and evaluation system and operation and creation method thereof
CN111402093A (en) * 2020-02-17 2020-07-10 浙江创课网络科技有限公司 Internet precision teaching tutoring management system based on big data and artificial intelligence
CN112052800A (en) * 2020-09-08 2020-12-08 河南城建学院 Intelligent teaching auxiliary system for foreign language teaching based on Internet of things
CN113570916A (en) * 2021-08-03 2021-10-29 浙江鸿昌机械有限公司 Multimedia remote teaching auxiliary method, equipment and system
CN114241549A (en) * 2021-11-22 2022-03-25 独数一智(北京)信息科技有限公司 Remote reading accompanying system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020082971A1 (en) * 2018-10-24 2020-04-30 江苏君英天达人工智能研究院有限公司 Real-time classroom monitoring and evaluation system and operation and creation method thereof
CN111402093A (en) * 2020-02-17 2020-07-10 浙江创课网络科技有限公司 Internet precision teaching tutoring management system based on big data and artificial intelligence
CN112052800A (en) * 2020-09-08 2020-12-08 河南城建学院 Intelligent teaching auxiliary system for foreign language teaching based on Internet of things
CN113570916A (en) * 2021-08-03 2021-10-29 浙江鸿昌机械有限公司 Multimedia remote teaching auxiliary method, equipment and system
CN114241549A (en) * 2021-11-22 2022-03-25 独数一智(北京)信息科技有限公司 Remote reading accompanying system

Also Published As

Publication number Publication date
CN117557428B (en) 2024-05-07

Similar Documents

Publication Publication Date Title
CN107024917B (en) It was found that the unit control apparatus of the abnormal reason of manufacture machinery
JP6837597B2 (en) Active learning systems and methods
US10423669B2 (en) Manufacturing process visualization apparatus and method
CN111739617B (en) Medical image artificial intelligence quality control labeling method, device, equipment and storage medium
DE112021002946T5 (en) Diagnostic device, server and diagnostic method
CN115392512A (en) Equipment maintenance method and system based on AR technology and related equipment
JP3718765B2 (en) Plant diagnostic equipment
CN117557428B (en) Teaching assistance method and system based on AI vision
JP2002312017A (en) Work evaluation device, work evaluation method and program to realize work evaluation method in computer
EP3783545A1 (en) System and method for automatically capturing technology transfer knowledge
CN114192583B (en) Scada platform-based strip steel rolling process quality monitoring method and system
CN112396923B (en) Marketing teaching simulation system
CN115204572A (en) Improved space-time alignment-based Castrip digital portrait generation and construction method
CN111531581B (en) Industrial robot fault action detection method and system based on vision
CN110855467B (en) Network comprehensive situation prediction method based on computer vision technology
CN113554909A (en) Online education platform
JP2020194355A (en) Data collection system for machine learning and data collection method
CN115392505B (en) Abnormality processing system and method for auto-parts automatic installation robot
WO2023008330A1 (en) Work situation analysis system and work situation analysis method
CN114171166B (en) Management system of model of visual digital pathological artificial intelligence
CN116703622B (en) Vehicle damage identification method and system
Alfaro-Viquez et al. Monitoring human performance through deep learning and computer vision in industry 4.0
JPH06124291A (en) Handwritten character inputting method for plant operation monitor ytem and plant operation monitor system
CN117911205A (en) Student information analysis and evaluation system based on big data
US20220300467A1 (en) Storage medium, learning device, and data collection system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant