Method for transmitting video identification information through network

Abstract

The invention discloses a method for transmitting video identification information through a network, which relates to the technical field of video identification, and comprises the following steps: when network transmission video monitoring is carried out, acquiring the area coverage area of a campus network, and delimiting a monitoring management area according to the area coverage area; when video monitoring is transmitted through a network, different set areas of a monitoring management area are coded, abnormal feature points in a network video are identified according to video screening conditions, a video abnormal type report is generated according to the abnormal feature points, and identification is performed through a specific identification watermark of a campus; the method comprises the following steps: carrying out network connection on a student user side for searching through regional coding, obtaining student user side data to generate a student user behavior data analysis report, carrying out selective transmission through a campus privacy protection mechanism based on the campus privacy protection mechanism, achieving the purpose of carrying out health checking on a student user network video, and ensuring privacy and information security. And students are supervised and urged to construct good network video cognition.

Description

Technical Field

[0001] The present invention relates to the technical field of video recognition, and particularly to a method for transmitting video recognition information through a network. Background Art

[0002] Transmitting video recognition information through a network involves transmitting the content in a video through a network. Campus networks are becoming increasingly popular. On campus, transmitting videos through a network has become a common information dissemination method in many scenarios such as teaching, academic exchanges, and campus cultural activities. Campus networks carry a large amount of video data, including various types such as teaching courseware videos, academic lecture videos, and student activity record videos. During the transmission of this vast amount of video information, inevitably, some abnormal videos may appear. These abnormal videos may contain inappropriate content or videos with copyright disputes. In a special environment like a campus, the spread of such abnormal videos will not only have a negative impact on the physical and mental health of students but may also lead to legal disputes.

[0003] Most of the existing video recognition technologies are aimed at general network environments. Traditional retrieval methods may rely on file names and limited time information. Traditional monitoring methods are difficult to accurately identify abnormal videos, and there are still certain errors in identifying abnormal behaviors and content in complex scenarios. Due to the large number of student users on campus networks and the complex network usage behaviors, the traffic characteristics related to the spread of campus network video content are diverse and professional. Relying solely on content recognition may not be able to promptly detect abnormal videos that are spread by means of tampering with video identifiers and taking advantage of network transmission loopholes.

[0004] In view of the above technical deficiencies, a solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to: through the monitoring management area, conduct real-time monitoring of the videos distributed in different areas, rationally identify abnormalities in network videos, and at the same time protect the personal privacy of students and cultivate good network literacy and moral norms for students.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: A method for transmitting video recognition information through a network, including the following steps:

[0007] Step 1: When monitoring the transmission of videos through a network, obtain the regional coverage area of the campus network, delimit the monitoring management area according to the regional coverage area. The monitoring management area includes living areas, teaching areas, and learning areas, and corresponding network nodes are set in the monitoring management area. By encoding different set areas in the monitoring management area and assigning campus-specific identification watermarks to network videos.

[0008] Step 2: Generate video screening conditions based on the vocabulary and video content contained in the acquired online video. The video screening conditions include preliminary screening and in-depth verification for analyzing the video type. The in-depth verification includes three types of abnormal feature points: inappropriate words, inappropriate audio, and inappropriate behaviors. Identify the abnormal feature points in the online video, generate a video abnormal type report based on the abnormal feature points, and obtain the abnormal online video;

[0009] Step 3: Obtain the abnormal online video, identify it based on the specific identification watermark of the campus, obtain a regional watermark identification report, and transfer it to the monitoring and management area for regional identification. Search for the student user terminal through the regional coding of the monitoring and management area to obtain student user terminal data to generate a student user behavior data analysis report;

[0010] Step 4: Obtain the video abnormal type report and the student user behavior data analysis report, obtain the online video security assessment coefficient, establish a campus privacy protection mechanism based on the online video security assessment coefficient, and perform selective transmission through the campus privacy protection mechanism to obtain the network video feedback transmission requirements within the campus network;

[0011] Step 5: Obtain the network video feedback transmission requirements, search for the list of personnel associated with the transmission requirements within the campus network, and transfer it to the campus network management and control terminal. The campus management and control terminal sends a transmission signal to the personnel receiving terminal.

[0012] Further, in the process of setting the corresponding network nodes in the monitoring and management area in Step 1, regional coding is assigned to the network nodes according to different regions, and the monitoring and management area is intelligently identified and divided according to the regional coding;

[0013] When assigning the specific identification watermark of the campus, the regional coding is incorporated into the identification watermark, and when performing network identification and uploading, the coding is automatically identified and adjusted according to different monitoring and management areas.

[0014] Further, when obtaining the network video report and sorting and marking the abnormal network videos in Step 2, during the preliminary identification, collect the abnormal network videos, extract sensitive words and behavioral actions, generate a sensitive word library and a behavioral action library. The sensitive word library and the behavioral action library are used as a sample training set to establish an identification model. The sample training set is used as input to output the abnormal network videos and perform abnormal type marking. The identification model identifies the input network videos.

[0015] When it is identified that the title has sensitive words, mark the online video as a text-sensitive word type;

[0016] When it is identified that the speech has sensitive words, mark the online video as a speech-sensitive word type;

[0017] When it is recognized that the behavior has indecent actions, discourse sensitive word types are marked for the network video.

[0018] Furthermore, the specific process of generating a video anomaly type report based on anomaly feature points is as follows:

[0019] S100. By collecting abnormal network videos and performing set feature extraction, extracting from sensitive word features, audio features, and action features, integrating to obtain a feature set, and training a deep learning model based on the feature set, fusing language, action, and audio features and inputting them into the deep learning model;

[0020] S101. Use the trained deep learning model to perform real-time analysis on the real-time transmitted video stream, judge the abnormal features of the network video according to the feature set, judge the abnormalities existing in the network video, and output the analysis results in the form of language. The output analysis results are the number of abnormal sensitive words, audio abnormal time periods, and action feature numbers;

[0021] S102. Predict the abnormal features that appear in the video through the deep learning model. Once an improper behavior is recognized, immediately trigger the corresponding alarm mechanism to determine it as abnormal. The specific analysis and calculation process is as follows:

[0022] The deep learning model predicts the abnormal feature L that appears in the video: L = A1×k1 + A2×K2 + A3×K3, where A1 is the number of language sensitive words in the recognized network video, A2 is the audio abnormal time period, A3 is the number of action features, and k1, k2, and k3 are all assigned weights.

[0023] Furthermore, in step four, obtaining student user terminal data to generate a student user behavior data analysis report includes the following process:

[0024] S200. The student user terminal will perform encrypted transmission and data limitation on student information, and specific data of each student user will be replaced with user replacement codes, so that the processed video does not directly identify the student's identity;

[0025] S201. Obtain the network video data published by student users when using the campus network, generate a student user video data set, and according to the search historical record information of the network video control terminal;

[0026] S202. Through the historical record information and the student user video data set, obtain the network videos successfully published by individuals and the network video data marked as abnormal, and obtain the abnormal proportion value of the abnormal network videos;

[0027] S203. Evaluate and calculate student users according to the proportion value, set the correct proportion value range of the network, and specifically classify the behaviors of student users according to the normal proportion value, which are divided into general student users, marked student users, and supervised student users. The process of calculating the abnormal proportion value H of abnormal network videos is as follows:

[0028] Where i = 1, 2, 3,..., n, n is the total number of network videos, Q1, Q2, Q3 are abnormal network videos, w1, w2, w3 are the assigned weight coefficients, C1 is the number of abnormal network videos, and C2 is the total number of network videos published by student users.

[0029] Furthermore, in step five, the process of obtaining the network video security evaluation coefficient is as follows:

[0030] S300. Obtain the video anomaly type report and the student user behavior data analysis report, obtain the student user anomaly value L and the abnormal proportion value H, and combine and evaluate and analyze the two;

[0031] S301. Conduct the network video security evaluation coefficient Q through the following process:

[0032] Preliminarily calculate the consistency index B:

[0033] Then calculate the complementarity index D:

[0034] Obtain the network video security evaluation coefficient Q: Q = r × B + (1 - r) × D, where r is the assigned weight coefficient;

[0035] S302. According to the obtained security evaluation coefficient, conduct an overall evaluation of the impact on network video security.

[0036] Furthermore, step four also includes finding the list of personnel associated with the transfer requirements within the campus network according to the network video feedback transfer requirements, transferring it to the campus network management and control terminal, and the campus management and control terminal sending a transfer signal to the personnel receiving end;

[0037] The specific process of analyzing according to the video feedback transfer requirements within the campus network is as follows:

[0038] S400. Establish a campus privacy protection mechanism, which is established according to the security evaluation coefficient, set the standard security evaluation coefficient s, and the real-time calculated network video security evaluation coefficient Q. The campus privacy protection mechanism includes personal feedback, guardianship feedback, and campus feedback;

[0039] S401. Obtain the network video security evaluation coefficient Q, analyze it according to the network video security evaluation coefficient Q and the standard evaluation coefficient s, and make specific divisions with s + s1, s + s2, and s + s3 as boundaries, representing personal feedback, guardianship feedback, and campus feedback, and s + s1 < s + s2 < s + s3, and output the campus privacy protection mechanism based on the comparative analysis results;

[0040] S402. Personal feedback means that the staff at the network video control end transmit warning information to online student users, without transmitting it to the supervisors of the student users;

[0041] Guardianship feedback means that the staff at the network video control end transmit student user information to the teacher supervision end and conduct offline guidance according to the supervising teachers of the student users;

[0042] Campus feedback means that the staff at the network video control end transmit student user information to the teacher supervision end and the school management department, and the supervision examination and supervision personnel conduct offline guidance.

[0043] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0044] The method for transmitting video recognition information through the network, when monitoring and transmitting videos through the network, encodes different set areas in the monitoring management area, identifies abnormal feature points in the network video according to the video screening conditions, generates a video anomaly type report based on the abnormal feature points, identifies through the specific identification watermark of the campus, searches for the student user terminal through the area encoding to obtain the student user terminal data to generate a student user behavior data analysis report, and based on the campus privacy protection mechanism, selectively transmits through the campus privacy protection mechanism to achieve the purpose of healthy review of the student user's network video, can protect privacy and information security, and urge students to build a good understanding of network videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Shows the schematic structural diagram of the method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] Embodiment 1:

[0048] As Figure 1As shown in the figure, a method for transmitting video recognition information through a network includes the following steps:

[0049] Step 1: When monitoring the network transmission of videos, obtain the regional coverage area of the campus network, delimit the monitoring and management area according to the regional coverage area. The monitoring and management area includes living areas, teaching areas, and learning areas, and corresponding network nodes are set in the monitoring and management area. By encoding different set areas in the monitoring and management area and assigning campus-specific identification watermarks to the network videos;

[0050] Step 2: Generate video screening conditions based on the words and video content contained in the obtained network videos. The video screening conditions include preliminary screening and in-depth verification for analyzing video types. The in-depth verification includes three types of abnormal feature points: inappropriate words, inappropriate audio, and inappropriate behaviors. Identify the abnormal feature points in the network videos, generate a video abnormal type report based on the abnormal feature points, and obtain abnormal network videos;

[0051] Step 3: Obtain abnormal network videos, identify them according to the campus-specific identification watermark, obtain a regional watermark identification report, and transmit it to the monitoring and management area for regional identification. Search for student user terminals through the regional coding of the monitoring and management area to obtain student user terminal data to generate a student user behavior data analysis report;

[0052] Step 4: Obtain the video abnormal type report and the student user behavior data analysis report, obtain the network video security evaluation coefficient, establish a campus privacy protection mechanism based on the network video security evaluation coefficient, and perform selective transmission through the campus privacy protection mechanism to obtain the network video feedback transmission requirements within the campus network;

[0053] Step 5: Obtain the network video feedback transmission requirements, search for the list of personnel associated with the transmission requirements within the campus network, and transmit it to the campus network management and control terminal. The campus management and control terminal sends a transmission signal to the personnel receiving terminal.

[0054] The campus network management and control terminal is responsible for the management and control of network videos and is connected to the personnel receiving terminal.

[0055] During the process of setting corresponding network nodes in the monitoring and management area in the above Step 1, the network nodes are encoded according to different regions, and the monitoring and management area is intelligently identified and divided according to the region codes;

[0056] When assigning the campus-specific identification watermark, the region code is incorporated into the identification watermark, and when performing network identification and uploading, the code is automatically identified and adjusted according to different monitoring and management areas.

[0057] When obtaining the network video report in Step 2 to sort and mark abnormal network videos in sequence, during the preliminary recognition, collect abnormal network videos, extract sensitive words and behavioral actions, generate a sensitive word library and a behavioral action library. The sensitive word library and the behavioral action library are used as a sample training set to establish an identification model. The sample training set is used as the input to output abnormal network videos and perform abnormal type marking. The identification model identifies the input network videos.

[0058] When it is identified that the title has sensitive words, mark the network video with the text sensitive word type.

[0059] When it is identified that the speech has sensitive words, mark the network video with the speech sensitive word type.

[0060] When it is identified that the behavior has indecent actions, mark the network video with the speech sensitive word type.

[0061] The specific process of generating a video abnormal type report according to the abnormal feature points is as follows:

[0062] S100. By collecting abnormal network videos and performing set feature extraction, and extracting from sensitive word features, audio features, and action features, after integration, a feature set is obtained. Based on the feature set, a deep learning model is trained. Integrate language, action, and audio features and input them into the deep learning model, and train the deep learning model.

[0063] When the deep learning model is being trained, when identifying abnormal network videos, it will output the number of abnormal sensitive words in the network video, the abnormal audio period, and the number of action features.

[0064] S101. Use the trained deep learning model to perform real-time analysis on the real-time transmitted video stream. According to the feature set, judge the abnormal features of the network video, judge the abnormalities existing in the network video, and output the analysis results in a language manner. The output analysis results are the number of abnormal sensitive words, the abnormal audio period, and the number of action features.

[0065] S102. Predict the abnormal features that appear in the video through the deep learning model. Once an improper behavior is identified, immediately trigger the corresponding alarm mechanism and determine it as abnormal. The specific analysis and calculation process is as follows:

[0066] The deep learning model predicts the abnormal feature L that appears in the video: L = A1×k1 + A2×K2 + A3×K3, where A1 is the number of language sensitive words in the identified network video, A2 is the abnormal audio period, A3 is the number of action features, and k1, k2, and k3 are all assigned weights.

[0067] In Step 4, obtain the student user terminal data to generate a student user behavior data analysis report, including the following process:

[0068]

[0068] The S200 student user terminal encrypts the transmission and limits the data of student information, and specific data of each student user will be replaced with user substitution codes, so that the processed video does not directly identify the student's identity;

[0069]

[0069] S201. Obtain the network video data published by student users when using the campus network, generate a student user video data set, and record information according to the search history of the control network video control end;

[0070]

[0070] S202. Through the historical record information of the student user video data set, obtain the network videos successfully published by individuals and the network video data marked as abnormal, and obtain the abnormal proportion value of the abnormal network videos;

[0071]

[0071] S203. Evaluate and calculate the student users according to the proportion value, set the correct proportion value range of the network, specifically divide the student user behavior according to the normal proportion value, and divide it into general student users, marked student users and supervised student users. The process of calculating the abnormal proportion value H of the abnormal network videos is as follows:

[0072] Where i = 1, 2, 3,..., n, n is the number of the total network videos, Q1, Q2, Q3 are abnormal network videos, w1, w2, w3 are the assigned weight coefficients, C1 is the number of abnormal network videos, and C2 is the total number of network videos published by student users.

[0073]

[0073] In step five, the process of obtaining the network video security evaluation coefficient is as follows:

[0074]

[0074] S300. Obtain the video anomaly type report and the student user behavior data analysis report, obtain the student user anomaly value L and the anomaly proportion value H, and combine and evaluate and analyze the two;

[0075]

[0075] S301. Conduct the network video security evaluation coefficient Q through the following process:

[0076]

[0076] Initially calculate the consistency index B:

[0077]

[0077] Then calculate the complementarity index D:

[0078]

[0078] Obtain the network video security evaluation coefficient Q: Q = r×B + (1 - r)×D, where r is the assigned weight coefficient;

[0079]

[0079] S302. According to the obtained security evaluation coefficient, conduct an overall evaluation of the impact on network video security.

[0080] Step 4 also includes finding the list of personnel associated with the transfer requirements within the campus network according to the transfer requirements of the network video feedback, and transferring it to the campus network management and control terminal. The campus management and control terminal sends a transfer signal to the personnel receiving terminal;

[0081] The specific process of analyzing according to the video feedback transfer requirements within the campus network is as follows:

[0082] S400. Establish a campus privacy protection mechanism, which is established according to the security assessment coefficient. Set the standard security assessment coefficient s and the real-time calculated network video security assessment coefficient Q. The campus privacy protection mechanism includes personal feedback, guardianship feedback, and campus feedback;

[0083] S401. Obtain the network video security assessment coefficient Q, analyze it according to the network video security assessment coefficient Q and the standard assessment coefficient s, and make specific divisions with s + s1, s + s2, s + s3 as the boundaries, representing personal feedback, guardianship feedback, and campus feedback, and s + s1 < s + s2 < s + s3. Output the campus privacy protection mechanism based on the comparative analysis results;

[0084] Personal feedback means that the staff of the network video control terminal transmit warning information to online student users and do not transmit it to the supervisors of student users;

[0085] Guardianship feedback means that the staff of the network video control terminal transmit student user information to the teacher supervision terminal and conduct offline guidance according to the supervisors of student users;

[0086] Campus feedback means that the staff of the network video control terminal transmit student user information to the teacher supervision terminal and the school management office, and the supervision examination and supervision personnel conduct offline guidance;

[0087] The campus privacy protection mechanism conducts selective transmission to achieve the purpose of healthy review of students' network videos, which can protect privacy and information security and urge students to build a good understanding of network videos.

[0088] The setting of the size of the interval and threshold is for the convenience of comparison. Regarding the size of the threshold, it depends on the amount of sample data and the number of base numbers set by those skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantified values.

[0089] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation;

[0090] In the two embodiments provided in the present application, it should be understood that the disclosed method can be implemented in other ways. For example, the method embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces, methods or modules, and can be in electrical, mechanical or other forms;

[0091] As mentioned above, the above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A method for transmitting video recognition information through a network, characterized in that, The following steps are involved: Step 1: When the network transmits video monitoring, obtain the regional coverage area of the campus network, and delineate the monitoring and management area according to the regional coverage area. The monitoring and management area includes the living area, teaching area, and learning area. Set up corresponding network nodes in the monitoring and management area, encode different set areas of the monitoring and management area, and give the network video a campus-specific identification watermark; Step 2: Generate video screening conditions based on the words and video content contained in the acquired online videos. The video screening conditions include preliminary screening and in-depth verification for analyzing video types. The in-depth verification includes three types of abnormal feature points: bad words, bad audio, and bad behavior. Identify abnormal feature points in online videos, generate video abnormality type reports based on abnormal feature points, and obtain abnormal online videos; Step 3: Obtain abnormal network videos, identify them according to the campus-specific identification watermark, obtain regional watermark identification reports, and pass them to the monitoring and management area for regional identification. Use the regional code of the monitoring and management area to search for network-connected student user terminals, obtain student user terminal data, and generate student user behavior data analysis reports; Step 4: Obtain video anomaly type reports and student user behavior data analysis reports to obtain the network video security assessment coefficient. Based on the network video security assessment coefficient, a campus privacy protection mechanism is established. Selective transmission is performed through the campus privacy protection mechanism to obtain the network video feedback transmission requirements within the campus network.

2. The method for transmitting video identification information through a network according to claim 1, characterized in that: In the process of setting the corresponding network nodes in the monitoring and management area in the above step 1, the network nodes are assigned regional codes according to different regions, and the monitoring and management areas are intelligently identified and divided according to the regional codes; When assigning a campus-specific identification watermark, the regional code is integrated into the identification watermark. When uploading for network identification, the code is automatically identified and adjusted according to different monitoring and management areas.

3. The method for transmitting video recognition information through a network according to claim 1, wherein When obtaining the network video report in step 2 to sort and mark the abnormal network videos in sequence, during the preliminary identification, the abnormal network videos are collected, and sensitive words and behaviors are extracted to generate a sensitive word library and a behavior library. The sensitive word library and the behavior library are used as sample training sets to establish a recognition model. The sample training set is used as input to output abnormal network videos and mark the abnormal types. The recognition model identifies the input network videos. When it is identified that there are sensitive words in the title, the online video is marked with sensitive word categories; When it is identified that the speech contains sensitive words, the network video is marked with sensitive word categories; When an indecent action is identified, the online video is marked with sensitive word categories.

4. The method for transmitting video recognition information through a network according to claim 1, wherein The specific process of generating a video anomaly type report based on abnormal feature points is as follows: S100. Collect abnormal network videos, perform set feature extraction, extract from sensitive word features, audio features, and action features, integrate to obtain a feature set, train a deep learning model based on the feature set, fuse the feature set and input it into the deep learning model, and train the deep learning model; S101. Use the trained deep learning model to perform real-time analysis on the real-time transmitted video stream, judge the abnormal features of the network video according to the feature set, judge the abnormalities existing in the network video, and output the analysis results in the form of language. The output analysis results are the number of abnormal sensitive words, audio abnormal time periods, and action feature numbers; S102. Predict the abnormal features that appear in the video through the deep learning model. Once bad behaviors are identified, immediately trigger the corresponding alarm mechanism to determine it as abnormal. The specific analysis and calculation process is as follows: The deep learning model predicts the abnormal feature L that appears in the video: L = A1×k1 + A2×K2 + A3×K3, where A1 is the number of language sensitive words in the identified network video, A2 is the audio abnormal time period, A3 is the number of action features, and k1, k2, and k3 are all assigned weights.

5. The method for transmitting video recognition information through a network according to claim 1, wherein In step four, obtain the student user terminal data to generate a student user behavior data analysis report, including the following process: S200. The student user terminal will perform encrypted transmission and data limitation on student information, and specific data of each student user will be replaced with user substitution codes, so that the processed video does not directly identify the student's identity; S201. Obtain the network video data published by student users when using the campus network, generate a student user video data set, and according to the search historical record information of the network video control terminal; S202. Through the historical record information and the student user video data set, obtain the network videos successfully published by individuals and the network video data marked as abnormal, and obtain the abnormal proportion value of the abnormal network videos; S203. Evaluate and calculate the student users according to the proportion value, set the correct proportion value range of the network, specifically divide the student user behaviors according to the normal proportion value, and divide them into general student users, marked student users, and supervised student users. The process of calculating the abnormal proportion value H of the abnormal network videos is as follows: Where i = 1, 2, 3, …, n, n is the total number of network videos, Q1, Q2, Q3 are abnormal network videos, w1, w2, w3 are assigned weight coefficients, C1 is the number of abnormal network videos, and C2 is the total number of network videos posted by student users.

6. The method for transmitting video recognition information through a network according to claim 1, characterized in that In step five, the process of obtaining the network video security evaluation coefficient includes the following: S300. Obtain the video abnormal type report and the student user behavior data analysis report, obtain the student user abnormal value L and the abnormal proportion value H, and combine and evaluate and analyze the two; S301. Perform the network video security evaluation coefficient Q through the following process: Preliminary calculation of the consistency index B: Then calculate the complementarity index D: Obtain the network video security evaluation coefficient Q: Q = r×B + (1 - r)×D, where r is the assigned weight coefficient; S302. According to the obtained security evaluation coefficient, conduct an overall evaluation of the network video security.

7. The method for transmitting video recognition information through a network according to claim 1, wherein Step four also includes searching for the list of personnel associated with the transfer requirements within the campus network according to the network video feedback transfer requirements, transmitting it to the campus network management control terminal, and the campus management control terminal sending a transfer signal to the personnel receiving terminal; The specific process of analyzing according to the video feedback transfer requirements within the campus network is as follows: S400. Establish a campus privacy protection mechanism based on the security assessment coefficient. Set the standard security assessment coefficient s and calculate the real-time network video security assessment coefficient Q. The campus privacy protection mechanism includes personal feedback, guardian feedback, and campus feedback. S401. Obtain the network video security assessment coefficient Q, analyze it according to the network video security assessment coefficient Q and the standard assessment coefficient s, and make specific divisions with s + s1, s + s2, and s + s3 as boundaries, representing personal feedback, guardian feedback, and campus feedback respectively, and s + s1 < s + s2 < s + s3. Output the campus privacy protection mechanism based on the comparative analysis results. Personal feedback means that the staff at the network video control end send warning information to online student users without passing it on to the supervisors of the student users. Guardian feedback means that the staff at the network video control end transmit the student user information to the teacher supervision end and provide offline guidance according to the supervising teachers of the student users. Campus feedback means that the staff at the network video control end transmit the student user information to the teacher supervision end and the school management office, and the supervision examiners and supervisors provide offline guidance.

Images