Video surveillance management method, system, device and medium for smart office

Abstract

The present application relates to a video surveillance management method, system, equipment and medium for smart office, the method includes obtaining the authority of enterprise personnel and performing activity authority matching processing, obtaining activity authority data that limits the activity range of each enterprise personnel, planning the movement path of the current enterprise personnel according to the activity authority data, and recording the activity trajectory of the current enterprise personnel, extracting the activity video data of the current enterprise personnel in the non-authorized area according to the activity trajectory, analyzing the activity video data, obtaining the number of unnecessary passes and the corresponding stay time of the current enterprise personnel in the non-authorized area, and jointly analyzing the risk of over-authority of the current enterprise personnel according to the unnecessary number of passes and the stay time, and performing early warning processing on the over-authority behavior of the current enterprise personnel according to the result of the risk analysis. The present application has the effect of improving the security within the enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of smart office, and in particular to a video surveillance management method, system, equipment and medium for smart office. Background Art

[0002] At present, with the continuous integration of information technology and office management, intelligent office management is gradually replacing human management. Simplifying internal management of enterprises through intelligent technology has become one of the main research directions of smart office.

[0003] Existing enterprise video surveillance usually manages enterprise entry and exit through visual access control. Cameras are set up in multiple areas within the enterprise to monitor the activities of people within the enterprise, and can be discovered in time when outsiders sneak into the enterprise or wander around the enterprise, reducing the loss or leakage of corporate property or business secrets. Summary of the invention

[0004] In order to improve the security within the enterprise, the present application provides a video surveillance management method, system, equipment and medium for smart office.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0006] A video surveillance management method for smart office, comprising:

[0007] Obtain the permissions of enterprise personnel and perform activity permission matching processing to obtain activity permission data that limits the scope of activities of each enterprise personnel;

[0008] Planning the movement path of the current enterprise personnel according to the activity authority data, and recording the activity trajectory of the current enterprise personnel, and extracting the activity video data of the current enterprise personnel in the non-authorized area according to the activity trajectory;

[0009] Analyze the activity video data to obtain the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time;

[0010] According to the number of unnecessary passes and the stay time, the risk of exceeding authority of the current enterprise personnel is jointly analyzed, and according to the result of the risk analysis of exceeding authority, the current enterprise personnel's cross-border behavior is warned.

[0011] By adopting the above technical solution, when enterprise personnel enter the enterprise monitoring range, the enterprise personnel authority is obtained, and the enterprise personnel's activity range authority is matched and processed, the activity range of each enterprise personnel is restricted according to the matched activity authority data, and the current enterprise personnel's movement path is planned in combination with the activity authority data, and the current enterprise personnel's real-time activity trajectory is combined to accurately extract the activity video data of the current enterprise personnel in the non-authorized area, which helps to extract effective data from massive video surveillance data and reduce the workload of video data analysis. In addition, the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time are extracted in combination with the video analysis results to perform an authority violation risk analysis, and then the current enterprise personnel's cross-border behavior is warned. This application uses the video surveillance data of enterprise personnel to judge and warn the cross-border behavior of personnel in the non-authorized area, improves the management uniformity of enterprise personnel activities, improves the internal security of the enterprise, and reduces the probability of loss of important documents or objects due to personnel crossing the boundary.

[0012] In a preferred example, the present application can be further configured as follows: the risk of overstepping authority of the current enterprise personnel is jointly analyzed based on the number of unnecessary passes and the stay time, and an early warning is performed on the overstepping authority behavior of the current enterprise personnel based on the result of the risk analysis, specifically including:

[0013] When the risk of exceeding authority reaches a preset risk threshold, the facial expression data of the current enterprise personnel in the inactive area is analyzed and processed to obtain the facial expression data of the current enterprise personnel;

[0014] Acquire the storage video stream of all important files in the inactive area, and analyze the file custody status when a person crosses the boundary according to the storage video stream;

[0015] When the file custody status is unattended and the person's demeanor data is abnormal, the current enterprise personnel are monitored and the risk of exceeding authority of the current enterprise personnel is determined;

[0016] Combined with the number of unnecessary passes and corresponding stay time of current enterprise personnel who are at risk of exceeding their authority, the activity tracks of risky persons are marked as out-of-bounds behavior, and early warning processing is carried out in combination with preset early warning instructions.

[0017] In a preferred example, the present application can be further configured as follows: the determination of the risk of exceeding authority of the current enterprise personnel specifically includes:

[0018] The risk coefficient of over-authority of the current enterprise personnel is expressed by formula (1), and the risk coefficient of over-authority of the current enterprise personnel is used to judge the risk of over-authority. Formula (1) is as follows:

[0019]

[0020] Among them, γ is the risk coefficient of overstepping authority of current enterprise personnel, and They respectively represent the probability of the current enterprise personnel staying in the inactive area when the document is unattended and the probability of the document being idle when unattended. f(x) and f(y) respectively represent the eye movement frequency and head movement frequency of the current enterprise personnel, which are obtained by analyzing the facial expression data of the characters. n and m respectively represent the number of eye movement and head movement times of the current enterprise personnel each time they pass through the inactive area.

[0021] In a preferred example, the present application can be further configured as follows: combining the number of unnecessary passes and the corresponding stay time of the current enterprise personnel who have the risk of exceeding authority, marking the activity track of the current enterprise personnel as an out-of-bounds behavior, and performing early warning processing in combination with the preset early warning instructions, specifically including:

[0022] The cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority is expressed by formula (2), which is as follows:

[0023]

[0024] Among them, μ 1 Indicates the cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority, N 1 Indicates the number of unnecessary passes by the current enterprise personnel during the period when the document is unattended, T 1 Indicates the duration of each non-essential stop;

[0025] Obtain the number of activities and corresponding stay time of the current enterprise personnel in the regulated activity area, and calculate the compliance activity coefficient of the current enterprise personnel through formula (3). Formula (3) is as follows:

[0026]

[0027] Among them, μ 2 represents the compliance activity coefficient of the current enterprise personnel in the standardized activity area, S represents the activity path of the current enterprise personnel in the standardized activity area, and N 0 Indicates the number of activities of the current enterprise personnel in the standardized activity area, T 0 Indicates the activity stay time corresponding to each standardized activity;

[0028] Calculate the ratio of the boundary crossing coefficient and the compliance activity coefficient, determine the boundary crossing risk level of the current enterprise personnel based on the ratio calculation result, and mark the boundary crossing risk of the current enterprise personnel's activity trajectory;

[0029] The marked activity track is marked as out-of-bounds behavior, and the out-of-bounds behavior of the current enterprise personnel is warned in combination with the preset warning instructions.

[0030] By adopting the above technical solution, when the risk of crossing the limit reaches the preset risk threshold, the facial expression analysis of the current enterprise personnel in the inactive area is performed on the video stream data, and the crossing behavior of the current enterprise personnel in the inactive area is further judged in combination with the facial expression of the person, so as to improve the accuracy of the analysis of the crossing behavior, and the storage video stream of all important files in the inactive area is combined to analyze the file custody status when there is a person crossing the boundary, including attended and unattended, to further judge the risk of the person crossing the boundary, when the file custody status is unattended and the person's demeanor is abnormal, the movement trajectory of the current enterprise personnel in the inactive area is monitored, and the risk of the current enterprise personnel crossing the authority is judged, so as to improve the accuracy of the judgment of the risk of crossing the authority, the behavior trajectory of the enterprise personnel with the risk of crossing the authority is monitored, and the corresponding number of unnecessary passes and the stay time of each pass are obtained, the current crossing behavior is marked, and the preset warning instructions are combined for warning processing, so as to improve the timeliness of the management of crossing behavior.

[0031] In a preferred example, the present application can be further configured as follows: analyzing the activity video data to obtain the number of unnecessary passes and corresponding stay times of the current enterprise personnel in the non-authorized area, specifically including:

[0032] Performing video stream analysis on the activity video data, if the current enterprise personnel enters a non-authorized area, marking the number of unnecessary passes of the current enterprise personnel, and obtaining the number of unnecessary passes of the current enterprise personnel;

[0033] The movement time from the time when the current enterprise personnel enters the non-authorized area to the time when they leave the non-authorized area is recorded, and the stay time of the current enterprise personnel in the non-authorized area is obtained.

[0034] By adopting the above technical solution and combining it with the video stream analysis results of the active video data, when the enterprise personnel enter the non-authorized area, the number of unnecessary passes is marked to obtain the current number of unnecessary passes of the enterprise personnel, and when the enterprise personnel enter the non-authorized area to leave the non-authorized area, the corresponding movement time is recorded, thereby obtaining the stay time in the non-authorized area, which helps to reduce omissions in the data collection of the cross-border behavior data of the enterprise personnel entering the non-authorized area.

[0035] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0036] A video surveillance management system for smart office, comprising:

[0037] The data acquisition module is used to obtain the permissions of enterprise personnel and perform activity permission matching processing to obtain activity permission data that limits the scope of activities of each enterprise personnel;

[0038] A data extraction module is used to plan the movement path of the current enterprise personnel according to the activity permission data, record the activity trajectory of the current enterprise personnel, and extract the activity video data of the current enterprise personnel in the non-authorized area according to the activity trajectory;

[0039] A data analysis module is used to analyze the activity video data to obtain the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time;

[0040] The over-limit management module is used to jointly analyze the over-authority risk of the current enterprise personnel according to the number of unnecessary passes and the stay time, and to issue an early warning to the over-limit behavior of the current enterprise personnel according to the over-authority risk analysis result.

[0041] By adopting the above technical solution, when enterprise personnel enter the enterprise monitoring range, the enterprise personnel authority is obtained, and the enterprise personnel's activity range authority is matched and processed, the activity range of each enterprise personnel is restricted according to the matched activity authority data, and the current enterprise personnel's movement path is planned in combination with the activity authority data, and the current enterprise personnel's real-time activity trajectory is combined to accurately extract the activity video data of the current enterprise personnel in the non-authorized area, which helps to extract effective data from massive video surveillance data and reduce the workload of video data analysis. In addition, the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time are extracted in combination with the video analysis results to perform an authority violation risk analysis, and then the current enterprise personnel's cross-border behavior is warned. This application uses the video surveillance data of enterprise personnel to judge and warn the cross-border behavior of personnel in the non-authorized area, improves the management uniformity of enterprise personnel activities, improves the internal security of the enterprise, and reduces the probability of loss of important documents or objects due to personnel crossing the boundary.

[0042] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0043] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the video surveillance management method for smart office when executing the computer program.

[0044] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the video surveillance management method for smart office.

[0046] In summary, the present application includes at least one of the following beneficial technical effects:

[0047] 1. When enterprise personnel enter the enterprise monitoring range, obtain enterprise personnel permissions, and match the enterprise personnel's activity range permissions. According to the matched activity permission data, limit the activity range of each enterprise personnel, plan the current enterprise personnel's movement path in combination with the activity permission data, and accurately extract the current enterprise personnel's activity video data in the non-authorized area in combination with the current enterprise personnel's real-time activity trajectory, which helps to extract effective data from massive video surveillance data and reduce the workload of video data analysis. In combination with the video analysis results, extract the number of unnecessary passes and corresponding stay time of the current enterprise personnel in the non-authorized area to conduct over-authority risk analysis, and then conduct early warning processing for the current enterprise personnel's over-boundary behavior. This application uses the video surveillance data of enterprise personnel to judge and warn the personnel's over-boundary behavior in the non-authorized area, improve the management uniformity of enterprise personnel activities, and improve the internal security of the enterprise, and reduce the probability of loss of important documents or objects due to personnel crossing the boundary;

[0048] 2. When the risk of crossing the limit reaches the preset risk threshold, the facial expressions of the current enterprise personnel in the inactive area are analyzed, and the crossing behavior of the current enterprise personnel in the inactive area is further judged based on the facial expressions and demeanor of the person, so as to improve the accuracy of the analysis of the crossing behavior. The storage video stream of all important files in the inactive area is combined to analyze the file custody status when there is a person crossing the boundary, including whether it is attended by someone or not, and further judge the risk of the person crossing the boundary. When the file custody status is unattended and the demeanor of the person is abnormal, the movement trajectory of the current enterprise personnel in the inactive area is monitored, and the risk of the current enterprise personnel crossing the authority is judged to improve the accuracy of the judgment of the risk of crossing the authority. The behavior trajectory of the enterprise personnel with the risk of crossing the authority is monitored, and the corresponding number of unnecessary passes and the stay time of each pass are obtained. The current crossing behavior is marked, and the preset warning instructions are combined for warning processing to improve the timeliness of the management of crossing behavior.

[0049] 3. Combined with the video stream analysis results of the active video data, when enterprise personnel enter the non-authorized area, the number of unnecessary passes is marked to obtain the current number of unnecessary passes of the enterprise personnel, and the corresponding movement time is recorded from the time the enterprise personnel enters the non-authorized area to the time they leave the non-authorized area, thereby obtaining the stay time in the non-authorized area, which helps to reduce omissions in the data collection of the cross-border behavior data of enterprise personnel entering the non-authorized area. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of an implementation method of a video surveillance management method for a smart office in this embodiment.

[0051] Figure 2 This is a flowchart for implementing step S30 of the video surveillance management method for smart office in this embodiment.

[0052] Figure 3 This is a flowchart for implementing step S40 of the video surveillance management method for smart office in this embodiment.

[0053] Figure 4 This is a flowchart for implementing step S404 of the video surveillance management method for smart office in this embodiment.

[0054] Figure 5 This is a structural block diagram of a video surveillance management system for a smart office in this embodiment.

[0055] Figure 6 It is a schematic diagram of the internal structure of a computer device used to implement a video surveillance management method for smart office. DETAILED DESCRIPTION

[0056] The present application is further described in detail below in conjunction with the accompanying drawings.

[0057] In one embodiment, if Figure 1 As shown, the present application discloses a video surveillance management method for smart office, which specifically includes the following steps:

[0058] S10: Obtain the permissions of enterprise personnel and perform activity permission matching processing to obtain activity permission data that limits the scope of activities of each enterprise personnel.

[0059] Specifically, when enterprise personnel enter and exit the company, the facial information of the enterprise personnel is obtained through the preset visual access control and matched with the pre-stored enterprise employee information to obtain the enterprise personnel authority. The enterprise personnel authority is related to the nature of the personnel's position, and the scope of personnel's activities within the enterprise is limited in combination with the enterprise personnel authority, that is, activity authority matching processing is performed. According to the results of the limited activity authority matching, the scope of activities of each enterprise personnel within the enterprise is restricted. For example, the activity authority of personnel in the production department is limited to the production workshop, the activity authority of personnel in the R&D department is limited to the R&D workshop, and the authority of the management department is for all workshops. When personnel from the production department or R&D department go to the management department, they need to apply or file in advance.

[0060] S20: planning the movement path of the current enterprise personnel according to the activity authority data, recording the activity trajectory of the current enterprise personnel, and extracting the activity video data of the current enterprise personnel in the non-authorization area according to the activity trajectory.

[0061] Specifically, based on the video data of the current enterprise personnel appearing in the surveillance video, the direction of action of the current enterprise personnel is predicted, and the movement path of the current enterprise personnel is planned based on the activity permission data combined with the permission area and non-authorization area in the movement direction, such as avoiding the non-authorization area or when it is necessary to pass through the non-authorization area, performing fixed-point avoidance according to the important file storage location in the non-authorization area, thereby obtaining the movement path planning result of the current enterprise personnel, and recording the activity trajectory of the current enterprise personnel in real time for comparison and analysis with the planned movement path to determine whether the current enterprise personnel are active in an unplanned area. When the enterprise personnel are active in an unplanned non-authorization area, the activity video data of the current enterprise personnel in the non-authorization area is extracted in combination with the monitoring equipment in the non-authorization area, so as to facilitate the key monitoring of the current enterprise personnel.

[0062] S30: Analyze the activity video data to obtain the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time.

[0063] Specifically, Figure 2 As shown, step S30 includes:

[0064] S301: parsing the video stream of the activity video data, if the current enterprise personnel enters the non-authorized area, marking the unnecessary passing times of the current enterprise personnel, and obtaining the unnecessary passing times of the current enterprise personnel.

[0065] Specifically, the video stream of the active video data is parsed through a preset video parsing algorithm, including continuous tracking and positioning based on the facial features of the personnel, and when the current enterprise personnel enter the non-authorized area, the number of unnecessary passes of the current enterprise personnel is marked, that is, the number of times the current enterprise personnel appear in the non-authorized area, thereby obtaining the number of unnecessary passes of the current enterprise personnel.

[0066] S302: Record the time taken by the current enterprise personnel from entering the non-authorized area to leaving the non-authorized area, and obtain the stay time of the current enterprise personnel in the non-authorized area.

[0067] Specifically, in combination with the surveillance video of the non-authorized area, the time point when the current enterprise personnel enters the non-authorized area is recorded, and according to the movement direction of the current enterprise personnel in the non-authorized area, it is judged whether the current enterprise personnel leaves the monitoring range of the non-authorized area to enter another non-authorized monitoring area such as the leadership office or the file storage room, or returns to the authorized area. If the current enterprise personnel returns from the non-authorized area to the authorized area, the movement time from the current enterprise personnel entering to leaving the non-authorized area is used as the corresponding residence time. If the current enterprise personnel enters another non-authorized monitoring area, the current enterprise personnel is monitored in a focused manner, and the time taken for the current enterprise personnel to enter another non-authorized monitoring area is used as the corresponding residence time. In combination with the normal movement speed of the current enterprise personnel, when the residence time is too long or too short, it is marked as an abnormal residence.

[0068] S40: Based on the number of unnecessary passes and the duration of stay, jointly analyze the risk of over-authority of the current enterprise personnel, and issue early warnings to the over-authority behavior of the current enterprise personnel based on the results of the risk analysis.

[0069] Specifically, Figure 3 As shown, step S40 includes:

[0070] S401: When the risk of exceeding authority reaches a preset risk threshold, the facial expression data of the current enterprise personnel in the inactive area is analyzed and processed to obtain the facial expression data of the current enterprise personnel.

[0071] Specifically, a risk threshold can be set based on the number of activities of personnel in non-authorized areas within a unit of time. For example, if the number of activities reaches 5 times within an hour, it is considered that there is a risk of exceeding authority. When the risk of exceeding authority reaches the preset risk threshold, the surveillance video stream data of the current enterprise personnel in the non-active area is analyzed, and the facial expression features of the characters in the surveillance video stream are extracted. For example, the main features of facial expressions are analyzed through the PCA analysis method, including the number of eye movements, the number of head turns, etc., so as to obtain the facial expression data of the current enterprise personnel.

[0072] S402: Acquire the storage video streams of all important files in the inactive area, and analyze the file custody status when a person crosses the boundary according to the storage video streams.

[0073] Specifically, when the number of times a non-active area is accessed by unauthorized personnel exceeds a preset risk threshold, the storage monitoring video data of all important files in the current non-authorized area is obtained, and the storage video stream data is analyzed to determine whether there is anyone supervising the current file storage office, such as whether the leader's office is currently occupied or unoccupied.

[0074] S403: When the file custody status is unattended and the person's demeanor data is abnormal, the current enterprise personnel are monitored intensively and the risk of exceeding authority of the current enterprise personnel is determined.

[0075] Specifically, when the file custody status is unattended, for example, if the leader is away and important files in the office are left unattended, and there is an abnormal demeanor of the people in the non-authorized area outside the office, such as turning the head too frequently or the eyeballs turning more than the normal frequency, then it means that the current company personnel have an abnormal demeanor in the non-authorized area, and it is necessary to focus on monitoring the current company personnel, and make a risk judgment of exceeding authority based on the person's demeanor and the time they stay outside the office, including that the more nervous the demeanor and the longer the stay, the greater the risk.

[0076] Specifically, the risk coefficient of the current enterprise personnel exceeding their authority is expressed by formula (1), and the risk coefficient of the current enterprise personnel exceeding their authority is used to judge the risk of the current enterprise personnel exceeding their authority. Formula (1) is as follows:

[0077]

[0078] Among them, γ is the risk coefficient of overstepping authority of current enterprise personnel, and They respectively represent the probability of the current enterprise personnel staying in the inactive area when the document is unattended and the probability of the document being idle when unattended. f(x) and f(y) respectively represent the eye movement frequency and head movement frequency of the current enterprise personnel, which are obtained by analyzing the facial expression data of the characters. n and m respectively represent the number of eye movement and head movement times of the current enterprise personnel each time they pass through the inactive area.

[0079] S404: Based on the number of unnecessary passes and corresponding stay time of the current enterprise personnel who are at risk of exceeding their authority, the activity track of the risky personnel is marked as an out-of-bounds behavior, and a warning is processed in combination with the preset warning instructions.

[0080] Specifically, Figure 4 As shown, step S404 includes:

[0081] S4041: The cross-border coefficient of the current enterprise personnel who have the risk of exceeding authority is expressed by formula (2), and formula (2) is as follows:

[0082]

[0083] Among them, μ 1 Indicates the cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority, N 1 Indicates the number of unnecessary passes by the current enterprise personnel during the period when the document is unattended, T 1 Indicates the duration of each non-essential stop.

[0084] S4042: Obtain the number of activities and corresponding stay time of the current enterprise personnel in the regulated activity area, and calculate the compliance activity coefficient of the current enterprise personnel through formula (3). Formula (3) is as follows:

[0085]

[0086] Among them, μ 2 represents the compliance activity coefficient of the current enterprise personnel in the standardized activity area, S represents the activity path of the current enterprise personnel in the standardized activity area, and N 0 Indicates the number of activities of the current enterprise personnel in the standardized activity area, T 0 Indicates the activity stay time corresponding to each standardized activity.

[0087] Specifically, video analysis is performed on the video stream data of the current enterprise personnel in the standardized activity area, the number of activities of the current enterprise personnel is extracted and the stay time of each activity is counted, so as to obtain the number of activities and the corresponding stay time in the standardized activity area.

[0088] S4043: Calculate the ratio of the boundary crossing coefficient and the compliance activity coefficient, determine the boundary crossing risk level of the current enterprise personnel based on the ratio calculation result, and mark the boundary crossing risk of the current enterprise personnel's activity trajectory.

[0089] Specifically, through μ 1 / μ 2 The ratio of the cross-border coefficient and the compliance activity coefficient is calculated. The higher the ratio, the higher the cross-border risk level of the current enterprise personnel. Similarly, the lower the ratio, the lower the cross-border risk level of the current enterprise personnel. The activity trajectory of the current enterprise personnel is marked with cross-border risk labels, that is, the cross-border risk labels are marked in combination with the facial features of the current enterprise personnel.

[0090] S4044: Mark the marked activity track as out-of-bounds behavior, and conduct an early warning process on the out-of-bounds behavior of the current enterprise personnel in combination with the preset early warning instructions.

[0091] Specifically, the movement trajectory of the current enterprise personnel with an out-of-bounds label in the inactive area is marked as an out-of-bounds behavior. Combined with the preset early warning instructions, if there is an out-of-bounds behavior, an alarm message will be issued to the supervisory personnel in the corresponding inactive area, prompting the supervisory personnel to issue an early warning for the out-of-bounds behavior of the current enterprise personnel.

[0092] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0093] In one embodiment, a video surveillance management system for a smart office is provided, and the video surveillance management system for a smart office corresponds one-to-one to the video surveillance management method for a smart office in the above embodiment. Figure 5 As shown, the video surveillance management system of the smart office includes a data acquisition module, a data extraction module, a data analysis module and an over-limit management module. The detailed description of each functional module is as follows:

[0094] The data acquisition module is used to obtain the permissions of enterprise personnel and perform activity permission matching processing to obtain activity permission data that limits the scope of activities of each enterprise personnel.

[0095] The data extraction module is used to plan the movement path of the current enterprise personnel according to the activity permission data, record the activity trajectory of the current enterprise personnel, and extract the activity video data of the current enterprise personnel in the non-authorized area according to the activity trajectory.

[0096] The data analysis module is used to analyze the activity video data and obtain the number of unnecessary passes and corresponding stay time of the current enterprise personnel in the non-authorized area.

[0097] The over-limit management module is used to jointly analyze the risk of over-authority of current enterprise personnel based on the number of unnecessary passes and the duration of stay, and to issue early warnings to the over-limit behavior of current enterprise personnel based on the results of the over-authority risk analysis.

[0098] Preferably, the limit crossing management module specifically includes:

[0099] The expression analysis submodule is used to analyze the facial expressions of the current enterprise personnel in the video stream data of the inactive area when the risk of exceeding authority reaches a preset risk threshold, so as to obtain the facial expression data of the current enterprise personnel.

[0100] The guarding analysis submodule is used to obtain the storage video stream of all important files in the inactive area, and analyze the file guarding status when a person crosses the boundary according to the storage video stream.

[0101] The risk judgment submodule is used to focus on monitoring the current enterprise personnel and judge the risk of exceeding authority of the current enterprise personnel when the file supervision status is unattended and the character's demeanor data is abnormal.

[0102] The early warning processing submodule is used to combine the number of unnecessary passes and corresponding stay time of current enterprise personnel who are at risk of exceeding their authority, mark the activity trajectory of risky personnel as out-of-bounds behavior, and perform early warning processing in combination with preset early warning instructions.

[0103] Preferably, the risk of exceeding authority of current enterprise personnel is determined to include:

[0104] The risk coefficient of over-authority of the current enterprise personnel is expressed by formula (1), and the risk coefficient of over-authority of the current enterprise personnel is used to judge the risk of over-authority. Formula (1) is as follows:

[0105]

[0106] Among them, γ is the risk coefficient of overstepping authority of current enterprise personnel, and They respectively represent the probability of the current enterprise personnel staying in the inactive area when the document is unattended and the probability of the document being idle when unattended. f(x) and f(y) respectively represent the eye movement frequency and head movement frequency of the current enterprise personnel, which are obtained by analyzing the facial expression data of the characters. n and m respectively represent the number of eye movement and head movement times of the current enterprise personnel each time they pass through the inactive area.

[0107] Preferably, the early warning processing submodule specifically includes:

[0108] The cross-border coefficient calculation unit is used to express the cross-border coefficient of the current enterprise personnel who have the risk of exceeding the authority through formula (2). Formula (2) is as follows:

[0109]

[0110] Among them, μ 1 Indicates the cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority, N 1 Indicates the number of unnecessary passes by the current enterprise personnel during the period when the document is unattended, T 1 Indicates the duration of each non-essential stop.

[0111] The compliance coefficient calculation unit is used to obtain the number of activities and corresponding stay time of the current enterprise personnel in the standardized activity area, and calculate the compliance activity coefficient of the current enterprise personnel through formula (3). Formula (3) is as follows:

[0112]

[0113] Among them, μ 2 represents the compliance activity coefficient of the current enterprise personnel in the standardized activity area, S represents the activity path of the current enterprise personnel in the standardized activity area, and N 0 Indicates the number of activities of the current enterprise personnel in the standardized activity area, T 0 Indicates the activity stay time corresponding to each standardized activity.

[0114] The risk marking unit is used to calculate the ratio of the boundary crossing coefficient and the compliance activity coefficient, determine the boundary crossing risk level of the current enterprise personnel based on the ratio calculation result, and mark the boundary crossing risk of the current enterprise personnel's activity trajectory.

[0115] The early warning processing unit is used to mark the marked activity track as an out-of-bounds behavior, and to carry out early warning processing on the out-of-bounds behavior of the current enterprise personnel in combination with the preset early warning instructions.

[0116] Preferably, the data analysis module specifically includes:

[0117] The data analysis submodule is used to perform video stream analysis on the active video data. If the current enterprise personnel enters the non-authorized area, the unnecessary passing times of the current enterprise personnel are marked to obtain the unnecessary passing times of the current enterprise personnel.

[0118] The data recording submodule is used to record the time taken by the current enterprise personnel from entering the non-authorized area to leaving the non-authorized area, and obtain the residence time of the current enterprise personnel in the non-authorized area.

[0119] For the specific definition of the video surveillance management system for smart office, please refer to the definition of the video surveillance management method for smart office mentioned above, which will not be repeated here. Each module in the above-mentioned video surveillance management system for smart office can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0120] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store intermediate data in the video surveillance management process of the enterprise. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a video surveillance management method for smart office is implemented.

[0121] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video surveillance management method for smart office are implemented.

[0122] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0123] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0124] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A video surveillance management method for smart office, It is characterized in that include: Obtain the permissions of enterprise personnel and perform activity permission matching processing to obtain activity permission data that limits the scope of activities of each enterprise personnel; Planning the movement path of the current enterprise personnel according to the activity authority data, and recording the activity trajectory of the current enterprise personnel, and extracting the activity video data of the current enterprise personnel in the non-authorized area according to the activity trajectory; Analyze the activity video data to obtain the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time; According to the number of unnecessary passes and the stay time, jointly analyze the risk of overstepping authority of the current enterprise personnel, and carry out early warning processing on the overstepping authority behavior of the current enterprise personnel according to the result of the risk analysis; The method of analyzing the risk of overstepping authority of the current enterprise personnel based on the number of unnecessary passes and the stay time, and carrying out early warning processing on the overstepping authority behavior of the current enterprise personnel according to the risk analysis result of overstepping authority specifically includes: When the risk of exceeding authority reaches a preset risk threshold, the facial expression data of the current enterprise personnel in the inactive area is analyzed and processed to obtain the facial expression data of the current enterprise personnel; Acquire the storage video stream of all important files in the inactive area, and analyze the file custody status when a person crosses the boundary according to the storage video stream; When the file custody status is unattended and the person's demeanor data is abnormal, the current enterprise personnel are monitored and the risk of exceeding authority of the current enterprise personnel is determined; Combined with the number of unnecessary passes and corresponding stay time of current enterprise personnel who are at risk of exceeding their authority, the activity tracks of risky personnel are marked as out-of-bounds behavior, and early warning processing is carried out in combination with the preset early warning instructions; The above-mentioned determination of the risk of exceeding authority of the current enterprise personnel specifically includes: The risk coefficient of over-authority of the current enterprise personnel is expressed by formula (1), and the risk coefficient of over-authority of the current enterprise personnel is used to judge the risk of over-authority. Formula (1) is as follows: Among them, γ is the risk coefficient of overstepping authority of current enterprise personnel, and They represent the probability of the current enterprise personnel staying in the inactive area and the probability of the document being idle when the document is unattended, respectively. f(x) and f(y) represent the eye movement frequency and head movement frequency of the current enterprise personnel, respectively, which are obtained by analyzing the facial expression data of the person. n and m represent the number of eye movement and head movement times of the current enterprise personnel each time they pass through the inactive area, respectively. Among them, the method combines the number of unnecessary passes and the corresponding stay time of the current enterprise personnel who have the risk of exceeding authority, marks the activity track of the current enterprise personnel as an out-of-bounds behavior, and performs warning processing in combination with the preset warning instructions, specifically including: The cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority is expressed by formula (2), which is as follows: Among them, μ 1 Indicates the cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority, N 1 Indicates the number of unnecessary passes by the current enterprise personnel during the period when the document is unattended, T 1 Indicates the duration of each non-essential stop; Obtain the number of activities and corresponding stay time of the current enterprise personnel in the regulated activity area, and calculate the compliance activity coefficient of the current enterprise personnel through formula (3). Formula (3) is as follows: Among them, μ 2 represents the compliance activity coefficient of the current enterprise personnel in the standardized activity area, S represents the activity path of the current enterprise personnel in the standardized activity area, and N 0 Indicates the number of activities of the current enterprise personnel in the standardized activity area, T 0 Indicates the activity stay time corresponding to each standardized activity; Calculate the ratio of the boundary crossing coefficient and the compliance activity coefficient, determine the boundary crossing risk level of the current enterprise personnel based on the ratio calculation result, and mark the boundary crossing risk of the current enterprise personnel's activity trajectory; The marked activity track is marked as out-of-bounds behavior, and the out-of-bounds behavior of the current enterprise personnel is warned in combination with the preset warning instructions.

2. The video surveillance management method for smart office according to claim 1, It is characterized in that The analyzing of the activity video data to obtain the number of unnecessary passes and corresponding stay time of the current enterprise personnel in the non-authorized area specifically includes: Performing video stream analysis on the activity video data, if the current enterprise personnel enters a non-authorized area, marking the number of unnecessary passes of the current enterprise personnel, and obtaining the number of unnecessary passes of the current enterprise personnel; The movement time from the time when the current enterprise personnel enters the non-authorized area to the time when they leave the non-authorized area is recorded, and the stay time of the current enterprise personnel in the non-authorized area is obtained.

3. A video surveillance management system for smart office, It is characterized in that include: The data acquisition module is used to obtain the permissions of enterprise personnel and perform activity permission matching processing to obtain activity permission data that limits the scope of activities of each enterprise personnel; A data extraction module is used to plan the movement path of the current enterprise personnel according to the activity permission data, record the activity trajectory of the current enterprise personnel, and extract the activity video data of the current enterprise personnel in the non-authorized area according to the activity trajectory; A data analysis module is used to analyze the activity video data to obtain the number of unnecessary passes by the current enterprise personnel in the non-authorized area and the corresponding stay time; The over-limit management module is used to jointly analyze the over-authority risk of the current enterprise personnel according to the number of unnecessary passes and the stay time, and to carry out early warning processing on the over-limit behavior of the current enterprise personnel according to the over-authority risk analysis result; The over-limit management module specifically includes: The expression analysis submodule is used to analyze the expression of the current enterprise personnel in the video stream data of the non-active area when the risk of exceeding the authority reaches a preset risk threshold, so as to obtain the expression data of the current enterprise personnel; A guard analysis submodule, used for acquiring the storage video stream of all important files in the inactive area, and analyzing the file guard status when a person crosses the boundary according to the storage video stream; A risk judgment submodule is used to focus on monitoring the current enterprise personnel and judge the risk of exceeding authority of the current enterprise personnel when the file custody status is unattended and the character's demeanor data is abnormal; The early warning processing submodule is used to combine the unnecessary passing times and corresponding stay time of the current enterprise personnel who have the risk of exceeding their authority, mark the activity track of the risky personnel as out-of-bounds behavior, and perform early warning processing in combination with the preset early warning instructions; The above-mentioned determination of the risk of exceeding authority of the current enterprise personnel specifically includes: The risk coefficient of over-authority of the current enterprise personnel is expressed by formula (1), and the risk coefficient of over-authority of the current enterprise personnel is used to judge the risk of over-authority. Formula (1) is as follows: Among them, γ is the risk coefficient of overstepping authority of current enterprise personnel, and They represent the probability of the current enterprise personnel staying in the inactive area and the probability of the document being idle when the document is unattended, respectively. f(x) and f(y) represent the eye movement frequency and head movement frequency of the current enterprise personnel, respectively, which are obtained by analyzing the facial expression data of the person. n and m represent the number of eye movement and head movement times of the current enterprise personnel each time they pass through the inactive area, respectively. The warning processing submodule specifically includes: The cross-border coefficient calculation unit is used to express the cross-border coefficient of the current enterprise personnel who have the risk of exceeding the authority through formula (2). Formula (2) is as follows: Among them, μ 1 Indicates the cross-border coefficient of the current enterprise personnel who have the risk of exceeding their authority, N 1 Indicates the number of unnecessary passes by the current enterprise personnel during the period when the document is unattended, T 1 Indicates the duration of each non-essential stop; The compliance coefficient calculation unit is used to obtain the number of activities and corresponding stay time of the current enterprise personnel in the standardized activity area, and calculate the compliance activity coefficient of the current enterprise personnel through formula (3). Formula (3) is as follows: Among them, μ 2 represents the compliance activity coefficient of the current enterprise personnel in the standardized activity area, S represents the activity path of the current enterprise personnel in the standardized activity area, and N 0 Indicates the number of activities of the current enterprise personnel in the standardized activity area, T 0 Indicates the activity stay time corresponding to each standardized activity; The risk marking unit is used to calculate the ratio of the boundary crossing coefficient and the compliance activity coefficient, determine the boundary crossing risk level of the current enterprise personnel based on the ratio calculation result, and mark the boundary crossing risk of the current enterprise personnel's activity trajectory; The early warning processing unit is used to mark the marked activity track as an out-of-bounds behavior, and to carry out early warning processing on the out-of-bounds behavior of the current enterprise personnel in combination with the preset early warning instructions.

4. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the video surveillance management method for smart office as described in any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of the video surveillance management method for smart office as described in any one of claims 1 to 2 are implemented.

Images