Internal control learning system and method for acquiring internal control learning content

Abstract

The invention discloses an internal control learning system used for obtaining internal control learning content, comprising a terminal side used for processing a collected video stream of a user learning scene to generate an internal control learning request which is sent to a network side and contains user behavior text information; and the network side is used for calling a related knowledge database to carry out matching processing on the user behavior text information according to an internal control learning request containing the user behavior text information from the terminal side, obtaining internal control learning content matched with the user behavior text information, and feeding back the internal control learning content to the terminal side. The method for processing the video stream at the terminal side comprises the following steps: collecting the video stream of a user learning scene; extracting a target video time sequence feature ft from the video stream; obtaining user behavior text information according to a predetermined corresponding relationship between the target video time sequence feature ft and the user behavior; and generating an internal control learning request by analyzing the similarity and the duration of each frame of video of the target video time sequence feature ft.

Description

Technical Field

[0001] This invention relates to the field of video analysis and content recommendation technology, and in particular to an internal control learning system and method for acquiring internal control learning content. Background Technology

[0002] With the rapid development of artificial intelligence and the Internet of Things (IoT) technologies, smart terminal devices are increasingly being used in education, industrial inspection, security monitoring, and other fields. Traditional video signal processing systems typically rely on fixed algorithms or manual analysis, making it difficult to achieve efficient and accurate content recognition and knowledge matching. Particularly in the field of internal control, how to understand personnel work in real time, collect video signals, extract key features, and combine this with a knowledge base for intelligent feedback has become a key technological challenge for improving learning efficiency.

[0003] Internal control is a series of self-discipline, self-adjustment, and self-control methods and measures established by enterprises or organizations to achieve business objectives, ensure the safety and integrity of assets, ensure the authenticity and reliability of accounting information, improve operational efficiency and effectiveness, and comply with laws and regulations.

[0004] However, there is currently a lack of technology to effectively acquire internal control learning content or knowledge through video analysis. Summary of the Invention

[0005] The purpose of this invention is to provide an internal control learning system and method for acquiring internal control learning content. This invention obtains relevant internal control knowledge by continuously analyzing the user's office computer screen.

[0006] According to a first aspect of the present invention, an internal control learning system for acquiring internal control learning content includes: On the terminal side, it is used to process the video stream of the collected user learning scenario and generate an internal control learning request containing user behavior text information to be sent to the network side. On the network side, it is used to call the relevant knowledge database to match the user behavior text information according to the internal control learning request containing user behavior text information from the terminal side, obtain the internal control learning content that matches the user behavior text information, and feed the internal control learning content back to the terminal side. The terminal side includes: Video signal acquisition device, used to acquire video streams from user learning scenarios; The temporal feature extraction module is used to extract target video temporal features ft from the video stream; The user behavior acquisition module is used to receive the target video temporal feature ft and, based on the pre-determined correspondence between the target video temporal feature ft and user behavior, acquire user behavior text information. The behavior triggering module is used to generate triggering information for triggering the sending of learning requests by analyzing the similarity and duration of each frame of the target video temporal feature ft. The sending / receiving module is used to generate and send an internal control learning request containing user behavior text information to the network side based on the triggering information from the behavior triggering module and the user behavior text information from the user behavior acquisition module, and to receive the internal control learning content returned by the network side. The display module is used to display the internal control learning content returned by the network side.

[0007] Preferably, the temporal feature extraction module is composed of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scene.

[0008] Preferably, the behavior triggering module is composed of an LSTM network; the LSTM network generates triggering information when each frame of the target video temporal feature ft is similar and the duration of similar video frames is greater than a predetermined value.

[0009] Preferably, the user behavior text information includes the names of files and charts related to internal control work, as well as text information about the user's actions in processing files and charts.

[0010] Preferably, the network side includes: a matching module, used to determine the database containing the file and chart from the database cluster based on the file and chart names in the user behavior text information carried by the internal control learning request, and to search for internal control knowledge that matches the user's behavior of processing the file and chart; and a feedback module, used to feed back the internal control knowledge found by the network side matching module to the terminal side.

[0011] According to a second aspect of the present invention, an internal control learning system for acquiring internal control learning content includes: On the terminal side, it is used to process the video stream of the collected user learning scenario and generate an internal control learning request containing user behavior video information to be sent to the network side. On the network side, based on the internal control learning request containing user behavior video information from the terminal side, the system calls the relevant knowledge database to match the user behavior video information, obtain internal control learning content that matches the user behavior video information, and feeds back the internal control learning content to the terminal side.

[0012] The terminal side includes: Video signal acquisition device, used to acquire video streams from user learning scenarios; The temporal feature extraction module is used to extract target video temporal features ft from the video stream; The behavior triggering module is used to generate triggering information for triggering the sending of internal control learning requests by analyzing the similarity and duration of each frame of the target video temporal feature ft. The sending / receiving module is used to generate and send an internal control learning request containing the target video temporal features ft to the network side based on the triggering information from the behavior triggering module and the target video temporal features ft from the temporal feature extraction module, and to receive the internal control learning content returned by the network side. The display module is used to display the internal control learning content returned from the network side.

[0013] Preferably, the temporal feature extraction module is composed of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scene.

[0014] Preferably, the behavior triggering module is composed of an LSTM network; the LSTM network generates triggering information when each frame of the target video temporal feature ft is similar and the duration of similar video frames is greater than a predetermined value.

[0015] According to a third aspect of the present invention, an internal control learning method for acquiring internal control learning content includes: The terminal side processes the video stream of the collected user learning scenario to generate an internal control learning request containing text information about user behavior, which is sent to the network side. The network side calls the relevant knowledge database to match the user behavior text information based on the internal control learning request containing user behavior text information from the terminal side, obtains the internal control learning content that matches the user behavior text information, and feeds back the internal control learning content to the terminal side. The terminal side processes the collected video stream of the user learning scenario to generate internal control learning request text information containing user behavior information for sending to the network side, including: The video signal acquisition device collects video streams from the user's learning scenario; The temporal feature extraction module extracts the target video temporal features ft from the video stream; The user behavior acquisition module receives the target video temporal feature ft and, based on the pre-determined correspondence between the target video temporal feature ft and user behavior, acquires user behavior text information. The behavior triggering module analyzes the similarity and duration of each frame of the target video's temporal features ft to generate triggering information for sending learning requests; The sending / receiving module generates and sends an internal control learning request containing user behavior text information to the network side based on the triggering information from the behavior triggering module and the user behavior text information from the user behavior acquisition module, and receives the internal control learning content returned by the network side. The display module shows the internal control learning content returned from the network side.

[0016] According to a fourth aspect of the present invention, an internal control learning method for acquiring internal control learning content includes: The terminal side processes the video stream of the collected user learning scenario to generate an internal control learning request containing user behavior video information and sends it to the network side. Based on the internal control learning request containing user behavior video information from the terminal side, the network side calls the relevant knowledge database to match the user behavior video information, obtains internal control learning content that matches the user behavior video information, and feeds back the internal control learning content to the terminal side.

[0017] The terminal side processes the collected video streams of user learning scenarios to generate an internal control learning request containing user behavior video information, which is then sent to the network side. The video signal acquisition device collects video streams from the user's learning scenario; The temporal feature extraction module extracts the target video temporal features ft from the video stream; The behavior triggering module analyzes the similarity and duration of each frame of the target video's temporal features ft to generate triggering information for sending internal control learning requests. The sending / receiving module generates and sends an internal control learning request containing the target video temporal features ft to the network side based on the triggering information from the behavior triggering module and the target video temporal features ft from the temporal feature extraction module, and receives the internal control learning content returned by the network side. The display module shows the internal control learning content returned from the network side.

[0018] This invention, through video signal acquisition and feature analysis, combined with intelligent matching from databases or knowledge centers, can understand the user's work scenario in real time and dynamically recommend the most relevant learning content, achieving intelligent interaction of "what you see is what you learn". Attached Figure Description

[0019] Figure 1 This is a schematic diagram of a first embodiment of an internal control learning system for acquiring internal control learning content according to the present invention; Figure 2 This is a schematic diagram of a second embodiment of an internal control learning system for acquiring internal control learning content according to the present invention. Detailed Implementation

[0020] The technical concept of this invention is to acquire images using a built-in video signal acquisition device. The acquired signal is then processed through feature vector extraction, and the main content of the video signal is analyzed temporally. The feature vector values ​​are matched with the knowledge stored in the "knowledge brain," and the relevant learning content is then displayed on a display device.

[0021] Figure 1 This invention illustrates a first embodiment of an internal control learning system for acquiring internal control learning content, comprising: a terminal side, configured to analyze a video stream of a user learning scenario to generate an internal control learning request containing user behavior text information for transmission to a network side; and a network side, configured to, based on the internal control learning request containing user behavior text information from the terminal side, invoke a relevant knowledge database to match the user behavior text information, obtain internal control learning content matching the user behavior text information, and feed the internal control learning content back to the terminal side.

[0022] The terminal side of the internal control learning system of the present invention includes: a video signal acquisition unit for acquiring video streams of user learning scenarios; a temporal feature extraction module for extracting target video temporal features ft from the video stream; a user behavior acquisition module for receiving the target video temporal features ft and acquiring user behavior text information based on a pre-determined correspondence between the target video temporal features ft and user behavior; a behavior triggering module for generating trigger information for triggering the sending of learning requests by analyzing the similarity and duration of each frame of the target video temporal features ft; a sending / receiving module for generating and sending an internal control learning request containing user behavior text information to the network side based on the trigger information from the behavior triggering module and the user behavior text information from the user behavior acquisition module, and receiving internal control learning content returned by the network side; and a display module for displaying the internal control learning content returned by the network side.

[0023] The user learning scenarios of this invention include: user processing of OA (Office Automation) system processes, financial systems, news browsing, watching programs, document writing, etc. This invention extracts target video temporal features ft from the video stream, specifically extracting target video temporal features related to internal control work from the video stream used to collect user learning scenarios. Target video temporal features can be, for example, video temporal features related to internal control work such as user processing of OA processes or user processing of financial systems. Therefore, after the video stream of the user learning scenarios is processed by the temporal feature extraction module, video temporal features unrelated to internal control work are discarded, such as video temporal features of news browsing or watching programs, while obtaining the target video temporal features.

[0024] Since CNNs are suitable for image classification, the temporal feature extraction module of this invention can be composed of a trained CNN network. The CNN network is trained on a labeled training set and is trained to extract specific target video temporal features from the video stream, so as to extract target video temporal features ft from all video streams of the user learning scenario, such as the video temporal features ft of the user processing OA process and the video temporal features ft of the user processing the financial system.

[0025] This invention can extract the visual feature vector of each frame from the acquired video stream V={I1,I2,...,It} by running a lightweight CNN model (such as MobileNetV3), where It is the image of the t-th frame.

[0026] Since LSTM (Long Short-Term Memory) networks can establish temporal dependencies, the behavior triggering module of this invention can be constructed using an LSTM network. The LSTM network generates trigger information when each frame of the target video temporal feature ft is similar and the duration of these similar video frames exceeds a predetermined value. For example, if each frame of the target video temporal feature ft is a video frame representing the user processing the financial system, and the duration exceeds 30 seconds, it indicates that the user is processing the financial system, not just browsing it. In this case, the behavior trigger information indicating that the user is processing the financial system is output.

[0027] The user behavior acquisition module can save a list of relationships between all target video time-series features ft and user behavior. By searching this list, the user behavior acquisition module can obtain user behavior text information based on the target video time-series features ft, such as the names of files and charts related to internal control work, as well as the text information of user actions in processing files and charts.

[0028] The network side of the internal control learning system of the present invention in the first embodiment includes: a matching module, used to determine the database containing the file and chart in the database cluster according to the file and chart names in the user behavior text information carried by the internal control learning request, and search for internal control knowledge that matches the user's behavior of processing the file and chart; and a feedback module, used to feed back the internal control knowledge found by the network side matching module to the terminal side.

[0029] The first embodiment of the present invention has the following technical effects: 1) The terminal side only sends an internal control learning request to the network side when it determines that the user's continuous behavior involves internal control work, instead of sending a learning request to the network side in real time, which can greatly reduce network data transmission and avoid network congestion caused by excessive data traffic; 2) The terminal side sends the internal control learning request to the network side through text information, instead of directly sending the target time sequence feature ft to the network side, which can reduce data transmission traffic.

[0030] Figure 2 This invention illustrates a second embodiment of an internal control learning system for acquiring internal control learning content, comprising: a terminal side, configured to process a video stream of a user learning scenario collected from the terminal side to generate an internal control learning request containing user behavior video information, which is then sent to the network side; and a network side, configured to, based on the internal control learning request containing user behavior video information from the terminal side, invoke a relevant knowledge database to match the user behavior video information, obtain internal control learning content matching the user behavior video information, and feed the internal control learning content back to the terminal side.

[0031] In the second embodiment of the internal control learning system, the terminal side includes: a video signal acquisition unit for acquiring video streams of user learning scenarios; a temporal feature extraction module for extracting target video temporal features ft from the video stream; a behavior triggering module for generating trigger information for triggering the sending of internal control learning requests by analyzing the similarity and duration of each frame of the target video temporal features ft; a sending / receiving module for generating and sending an internal control learning request containing the target video temporal features ft to the network side based on the trigger information from the behavior triggering module and the target video temporal features ft from the temporal feature extraction module, and receiving internal control learning content returned by the network side; and a display module for displaying the internal control learning content returned by the network side.

[0032] In the second embodiment of the internal control learning system, user learning scenarios include: user processing of OA processes, financial systems, news browsing, watching programs, document writing, and other scenarios.

[0033] The temporal feature extraction module of the second embodiment of the internal control learning system is composed of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scenario.

[0034] The behavior triggering module of the second embodiment of the internal control learning system is composed of an LSTM network; the LSTM network generates triggering information when each video frame of the target video temporal feature ft is similar and the duration of the similar video frames is greater than a predetermined value.

[0035] The network side of the second embodiment of the internal control learning system includes: a matching module, used to perform similarity matching processing between the target video temporal features ft carried by the internal control learning request and the structured data in the knowledge base, and generate adapted internal control knowledge through a deep learning recommendation algorithm; and a feedback module, used to feed back the generated adapted internal control knowledge to the terminal side.

[0036] The main difference between the first and second embodiments of the internal control learning method of this invention is that the first embodiment generates an internal control learning request containing text information about user behavior on the terminal side, while the second embodiment generates an internal control learning request containing video information about user behavior on the terminal side. Therefore, the data transmission volume of the first embodiment is lower than that of the second embodiment.

[0037] The present invention also provides a first embodiment of an internal control learning method for obtaining internal control learning content, comprising: processing a video stream of a user learning scenario collected by the terminal side to generate an internal control learning request containing user behavior text information for sending to the network side; the network side, based on the internal control learning request containing user behavior text information from the terminal side, calling a relevant knowledge database to match the user behavior text information, obtaining internal control learning content that matches the user behavior text information, and feeding back the internal control learning content to the terminal side.

[0038] The terminal side processes the acquired video stream of the user learning scenario as follows: a video signal acquisition device acquires the video stream of the user learning scenario; a temporal feature extraction module extracts target video temporal features ft from the video stream; a user behavior acquisition module receives the target video temporal features ft and, based on a pre-determined correspondence between the target video temporal features ft and user behavior, acquires user behavior text information; a behavior triggering module analyzes the similarity and duration of each frame of the target video temporal features ft to generate trigger information for triggering the sending of learning requests; a sending / receiving module generates and sends an internal control learning request containing user behavior text information to the network side based on the trigger information from the behavior triggering module and the user behavior text information from the user behavior acquisition module, and receives the internal control learning content returned by the network side; and a display module displays the internal control learning content returned by the network side.

[0039] The temporal feature extraction module consists of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scene.

[0040] The behavior triggering module is composed of an LSTM network; the LSTM network generates trigger information when each frame of the target video temporal feature ft is similar and the duration of similar video frames is greater than a predetermined value.

[0041] The network side processes the internal control learning request from the terminal side as follows: The network side matching module determines the database containing the file and chart from the database cluster based on the file and chart names in the user behavior text information carried in the internal control learning request; the network side matching module searches for internal control knowledge that matches the user's behavior of processing files and charts by traversing the database of files and charts; the network side feedback module feeds back the internal control knowledge found by the network side matching module to the terminal side.

[0042] The present invention also provides a second embodiment of an internal control learning method for obtaining internal control learning content, comprising: processing a video stream of a user learning scenario collected by the terminal side to generate an internal control learning request containing user behavior video information and sending it to the network side; the network side, based on the internal control learning request containing user behavior video information from the terminal side, calling a relevant knowledge database to match the user behavior video information, obtaining internal control learning content that matches the user behavior video information, and feeding back the internal control learning content to the terminal side.

[0043] The terminal side processes the video stream of the user learning scenario as follows: a video signal acquisition device acquires the video stream of the user learning scenario; a temporal feature extraction module extracts the target video temporal feature ft from the video stream; a behavior triggering module analyzes the similarity and duration of each frame of the target video temporal feature ft to generate trigger information for triggering the sending of an internal control learning request; a sending / receiving module generates and sends an internal control learning request containing the target video temporal feature ft to the network side based on the trigger information from the behavior triggering module and the target video temporal feature ft from the temporal feature extraction module, and receives the internal control learning content returned by the network side; and a display module displays the internal control learning content returned by the network side.

[0044] In the second embodiment of the internal control learning method, the temporal feature extraction module is composed of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scenario.

[0045] In the second embodiment of the internal control learning method, the behavior triggering module is composed of an LSTM network; the LSTM network generates triggering information when each frame of the target video temporal feature ft is similar and the duration of similar video frames is greater than a predetermined value.

[0046] In the second embodiment of the internal control learning method, the processing of the internal control learning request on the network side includes: the network-side matching module performs similarity matching between the target video temporal feature ft carried by the internal control learning request and the structured data in the knowledge base, and generates suitable internal control knowledge through a deep learning recommendation algorithm; the network-side feedback module feeds back the generated suitable internal control knowledge to the terminal side.

[0047] The invention will now be illustrated with a financial approval example.

[0048] When a user modifies a purchase contract, the video capture module captures a video stream including the user's modifications to the purchase contract. The temporal feature extraction module extracts the target video temporal features ft from the video stream of the user-modified "modification terms" in the procurement contract; The behavior triggering module issues a trigger message when it detects three consecutive modifications to the same clause; The user behavior acquisition module sends the target video temporal feature ft of the "Modify Terms" to the network side; The network side uses knowledge base matching to find the knowledge of "procurement approval hierarchical system" and related error cases: "Company A's over-level approval incident in 2023".

[0049] The network side generates an approval flowchart with highlighted violations and sends the flowchart, related error cases, and the "Compliance Approval SOP" to the terminal side.

[0050] The above-mentioned technical solution of the present invention can achieve the following technical effects: 1) Real-time perception of user learning scenarios (such as daily login to the system, document notes, web page operations) through video acquisition module; 2) The terminal side only sends the internal control learning request to the network after determining that a user behavior has occurred, thereby greatly reducing network information transmission and reducing interaction latency.

[0051] Although the present invention has been described in detail above, it is not limited thereto, and those skilled in the art can make various modifications based on the principles of the present invention. Therefore, all modifications made in accordance with the principles of the present invention should be understood to fall within the protection scope of the present invention.

Claims

1. An internal control learning system for acquiring internal control learning content, comprising: On the terminal side, it is used to process the video stream of the collected user learning scenario and generate an internal control learning request containing user behavior text information to be sent to the network side. On the network side, it is used to call the relevant knowledge database to match the user behavior text information according to the internal control learning request containing user behavior text information from the terminal side, obtain the internal control learning content that matches the user behavior text information, and feed the internal control learning content back to the terminal side. The terminal side includes: The video signal acquisition module is used to acquire video streams from the user's learning scenario; The temporal feature extraction module is used to extract target video temporal features ft from the video stream; The user behavior acquisition module is used to receive the target video temporal feature ft and, based on the pre-determined correspondence between the target video temporal feature ft and user behavior, acquire user behavior text information. The behavior triggering module is used to generate triggering information for triggering the sending of learning requests by analyzing the similarity and duration of each frame of the target video temporal feature ft. The sending / receiving module is used to generate and send an internal control learning request containing user behavior text information to the network side based on the triggering information from the behavior triggering module and the user behavior text information from the user behavior acquisition module, and to receive the internal control learning content returned by the network side. The display module is used to display the internal control learning content returned by the network side.

2. The internal control learning system according to claim 1, wherein the temporal feature extraction module is composed of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scenario.

3. The internal control learning system according to claim 1 or 2, wherein the behavior triggering module is composed of an LSTM network; the LSTM network generates the triggering information when each frame of the target video temporal feature ft is similar and the duration of the similar video frames is greater than a predetermined value.

4. The internal control learning system according to claim 3, wherein the user behavior text information includes the names of files and charts related to internal control work, as well as text information about the user's actions in processing files and charts.

5. The internal control learning system according to claim 4, wherein the network side comprises: The matching module is used to determine the database containing the file and chart from the database cluster based on the file and chart names in the user behavior text information carried by the internal control learning request, and to search for internal control knowledge that matches the user's behavior of processing the file and chart. The feedback module is used to feed back the internal control knowledge found by the network-side matching module to the terminal side.

6. An internal control learning system for acquiring internal control learning content, comprising: On the terminal side, it is used to process the video stream of the collected user learning scenario and generate an internal control learning request containing user behavior video information to be sent to the network side. On the network side, it is used to call the relevant knowledge database to match the user behavior video information according to the internal control learning request containing user behavior video information from the terminal side, obtain the internal control learning content that matches the user behavior video information, and feed the internal control learning content back to the terminal side. The terminal side includes: Video signal acquisition device, used to acquire video streams from user learning scenarios; The temporal feature extraction module is used to extract target video temporal features ft from the video stream; The behavior triggering module is used to generate triggering information for triggering the sending of internal control learning requests by analyzing the similarity and duration of each frame of the target video temporal feature ft. The sending / receiving module is used to generate and send an internal control learning request containing the target video temporal features ft to the network side based on the triggering information from the behavior triggering module and the target video temporal features ft from the temporal feature extraction module, and to receive the internal control learning content returned by the network side. The display module is used to display the internal control learning content returned from the network side.

7. The internal control learning system according to claim 6, wherein the temporal feature extraction module is composed of a trained CNN network; the CNN network is trained to be a neural network for extracting specific target video temporal features from the video stream, so as to extract target video temporal features ft from the video stream of the user learning scenario.

8. The internal control learning system according to claim 6 or 7, wherein the behavior triggering module is composed of an LSTM network; the LSTM network generates the triggering information when each frame of the target video temporal feature ft is similar and the duration of the similar video frames is greater than a predetermined value.

9. An internal control learning method for acquiring internal control learning content, comprising: The terminal side processes the video stream of the collected user learning scenario to generate an internal control learning request containing text information about user behavior, which is sent to the network side. The network side calls the relevant knowledge database to match the user behavior text information based on the internal control learning request containing user behavior text information from the terminal side, obtains the internal control learning content that matches the user behavior text information, and feeds back the internal control learning content to the terminal side. The terminal side processes the collected video stream of the user learning scenario to generate internal control learning request text information containing user behavior information for sending to the network side, including: The video signal acquisition device collects video streams from the user's learning scenario; The temporal feature extraction module extracts the target video temporal features ft from the video stream; The user behavior acquisition module receives the target video temporal feature ft and, based on the pre-determined correspondence between the target video temporal feature ft and user behavior, acquires user behavior text information. The behavior triggering module analyzes the similarity and duration of each frame of the target video's temporal features ft to generate triggering information for sending learning requests; The sending / receiving module generates and sends an internal control learning request containing user behavior text information to the network side based on the triggering information from the behavior triggering module and the user behavior text information from the user behavior acquisition module, and receives the internal control learning content returned by the network side. The display module shows the internal control learning content returned from the network side.

10. An internal control learning method for acquiring internal control learning content, comprising: The terminal side processes the video stream of the collected user learning scenario to generate an internal control learning request containing user behavior video information and sends it to the network side. The network side, based on the internal control learning request containing user behavior video information from the terminal side, calls the relevant knowledge database to match the user behavior video information, obtains the internal control learning content that matches the user behavior video information, and feeds back the internal control learning content to the terminal side. The terminal side processes the collected video streams of user learning scenarios to generate an internal control learning request containing user behavior video information, which is then sent to the network side. The video signal acquisition device collects video streams from the user's learning scenario; The temporal feature extraction module extracts the target video temporal features ft from the video stream; The behavior triggering module analyzes the similarity and duration of each frame of the target video's temporal features ft to generate triggering information for sending internal control learning requests. The sending / receiving module generates and sends an internal control learning request containing the target video temporal features ft to the network side based on the triggering information from the behavior triggering module and the target video temporal features ft from the temporal feature extraction module, and receives the internal control learning content returned by the network side. The display module shows the internal control learning content returned from the network side.

Images