Method, system and equipment for allocating access authority of dynamic scene perception

Abstract

The invention discloses a method, a system and a device for allocating access authority of dynamic scene perception, and relates to the technical field of data processing. The method comprises the following steps: determining a passing gate of a preset area in a target campus; collecting a gate passing scene image in real time; performing passage aggregation degree recognition based on the gate passage scene image, and when the passage aggregation degree is greater than a preset aggregation threshold, performing group face recognition on the gate passage scene image to generate a first type of personnel and a second type of personnel; executing authorization track extraction for the first class of personnel, and constructing first authorization track mapping; performing permission verification pass-free processing on the first type of personnel, and executing tracking verification after pass based on first authorization track mapping; and executing verification of a preset permission verification strategy on the second class of personnel, and issuing semantic micro-permissions for tracking verification. The technical problem that in the prior art, it is difficult to give consideration to fast passing and authority safety verification through a passing gate is solved, and the technical effect of improving passing efficiency and safety is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a dynamic scene-aware access permission allocation method, system and device. BACKGROUND

[0002] With the frequent entry and exit of personnel in areas such as campuses, enterprises and public places, the access management system is facing the challenge of access efficiency while ensuring safety. Traditional access gates usually rely on static permission verification methods such as card swiping and password input. Although this method is safe, it can cause access congestion and affect efficiency during peak hours, especially when multiple people are queuing. In particular, in time-critical situations, how to quickly complete access verification, ensure accurate identification of personnel permissions, and avoid security risks has become a pressing problem. Therefore, how to balance the speed of access and the security of permission verification has become an important research direction in access management systems. SUMMARY

[0003] The present application provides a dynamic scene-aware access permission allocation method, system and device, which solves the technical problem that the existing access gate cannot balance fast access and permission security verification.

[0004] In a first aspect, the present application provides a dynamic scene-aware access permission allocation method, which comprises: determining an access gate of a preset area in a target campus; collecting access gate scene images in real time through a non-permission verification camera of the access gate; identifying access aggregation based on the access gate scene images, and when the access aggregation is greater than a preset aggregation threshold, performing group face recognition on the access gate scene images to generate first-class personnel and second-class personnel, wherein the first-class personnel are dynamic authorized personnel, and the second-class personnel are temporary visitors; performing authorized trajectory extraction for the first-class personnel to construct a first authorized trajectory mapping; performing permission verification exemption for the first-class personnel, and performing tracking verification after access based on the first authorized trajectory mapping; performing verification of a preset permission verification strategy for the second-class personnel, and issuing semantic micro-permissions for tracking verification.

[0005] In a second aspect, the present application provides a dynamic scene-aware access permission allocation system, which comprises: The gate positioning module is configured to determine a pass gate of a preset area in a target campus; the image acquisition module is configured to acquire a gate pass scene image in real time through a non-authorization verification camera of the pass gate; the personnel classification module is configured to perform pass aggregation degree identification based on the gate pass scene image, and when the pass aggregation degree is greater than a preset aggregation threshold, perform group face recognition on the gate pass scene image to generate first personnel and second personnel, wherein the first personnel are dynamic authorized personnel, and the second personnel are temporary visitors; the trajectory extraction module is configured to perform authorized trajectory extraction on the first personnel to construct a first authorized trajectory mapping; the first processing module is configured to perform authorization verification exemption pass processing on the first personnel, and perform tracking verification after passing based on the first authorized trajectory mapping; and the second processing module is configured to perform verification of a preset authorization verification strategy on the second personnel, and issue semantic micro-authorization for tracking verification.

[0006] In a third aspect, the present application provides an electronic device, comprising: a memory configured to store executable instructions; and a processor configured to execute the executable instructions stored in the memory to implement the dynamic scene-aware pass authorization method provided by the present application.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages: First, the pass gate of a preset area in a target campus is determined. Then, a gate pass scene image is acquired in real time through a non-authorization verification camera of the pass gate. Further, pass aggregation degree identification is performed based on the gate pass scene image, and when the pass aggregation degree is greater than a preset aggregation threshold, group face recognition is performed on the gate pass scene image to generate first personnel and second personnel, wherein the first personnel are dynamic authorized personnel, and the second personnel are temporary visitors. Then, authorized trajectory extraction is performed on the first personnel to construct a first authorized trajectory mapping; authorization verification exemption pass processing is performed on the first personnel, and tracking verification is performed after passing based on the first authorized trajectory mapping. Finally, verification of a preset authorization verification strategy is performed on the second personnel, and semantic micro-authorization is issued for tracking verification. The technical problem that the pass gate in the prior art is difficult to balance fast pass and authorization security verification is solved, and the technical effect of improving pass efficiency and security is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0009] Figure 1 A flowchart of a dynamic scene-aware access permission allocation method provided by an embodiment of the present application is shown in the figure. Figure 2 A structural diagram of a dynamic scene-aware access permission allocation system provided by an embodiment of the present application is shown in the figure. Figure 3 A structural diagram of an exemplary electronic device of the present application is shown in the figure.

[0010] Legend: gate positioning module 11, image acquisition module 12, personnel classification module 13, trajectory extraction module 14, first processing module 15, second processing module 16, processor 21, memory 22, input device 23, output device 24. DETAILED DESCRIPTION

[0011] The present application provides a dynamic scene-aware access permission allocation method, system and device, which solves the technical problem that the access gate in the prior art cannot balance fast access and permission security verification.

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0013] It should be noted that the terms "comprise" and "have" are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units does not have to be limited to those clearly listed steps or units, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0014] Embodiment one, as shown in the figure, the embodiment of the present application provides a dynamic scene-aware access permission allocation method, wherein the method comprises: Figure 1 determining the access gate of a preset area in a target campus.

[0015] In the embodiment of the present application, according to the building layout and personnel flow demand of the target campus, the area that needs to be managed for access permission is selected, and the access gate is set up in these areas, then the access gate is connected with the campus intelligent management platform, so that the state and access situation of the gate can be updated to the platform in real time.

[0016] The non-permission verification camera of the access gate acquires the access gate scene image in real time.

[0017] ​In the embodiments of the present application, non-authorization verification cameras are installed above each gate, which are responsible for monitoring and recording the activities and traffic of personnel around the gate, and are not directly used for verifying the traffic authorization of personnel, but are used to capture gate traffic scene images to analyze personnel gathering, identify queue length, traffic speed, etc.

[0018] Based on the gate traffic scene image, the traffic gathering degree is identified, and when the traffic gathering degree is greater than a preset gathering threshold, group face recognition is performed on the gate traffic scene image to generate first-class personnel and second-class personnel, wherein the first-class personnel are dynamic authorized personnel, and the second-class personnel are temporary visitors.

[0019] By analyzing the collected gate traffic scene image, the personnel density and distribution in the image are identified, and the traffic gathering degree is calculated. When the traffic gathering degree is greater than a preset gathering threshold, it indicates that congestion or personnel concentration has occurred in the gate area, and the system immediately starts the group face recognition process. The group face recognition is based on a deep learning algorithm, which can accurately detect and match multiple faces appearing in the image at the same time. By analyzing the facial features of each person, the identity of each traffic personnel is identified. Specifically, the system locates all faces in the image through a face detection model, extracts each face region from the image; uses a pre-trained face recognition network to extract features from each extracted face, and converts the unique features of each face (such as the positions and shapes of facial key points such as eyes, nose, and mouth) into high-dimensional feature vectors. These feature vectors can reflect the unique identity features of each traffic personnel; the system compares the extracted feature vectors with the known personnel information in the database, accurately identifies the identity of each traffic personnel by calculating the similarity between the feature vectors, for example, for the dynamic authorized personnel who have been authorized, the system matches their pre-stored facial features to confirm that they are first-class personnel; if the system fails to match the facial features, it is determined to be a second-class personnel, i.e. a temporary visitor. Through group face recognition, personnel are divided into first-class personnel and second-class personnel, wherein the first-class personnel are dynamic authorized personnel, i.e. personnel who have obtained long-term authorization (such as faculty, students, etc.); the second-class personnel are temporary visitors, i.e. external personnel who have not been authorized in advance but temporarily visit the campus.

[0020] Further, based on the gate traffic scene image, the traffic gathering degree is identified, including: Based on the gate traffic scene image, the personnel traffic rate and the queue length change within the camera field of view are identified to generate a traffic rate indicator and a queue length change indicator; the traffic duration is predicted based on the traffic rate indicator and the queue length change indicator, the ratio of the predicted duration to the preset non-gathering discrimination duration is calculated, and the traffic gathering degree is generated.

[0021] The system analyzes the collected gate passage scene images, identifies the passage rate of personnel in the images and the change in the queue length within the camera's field of view. The system calculates the number of personnel passing through the gate per unit time and generates a passage rate indicator based on these data to assess the speed of personnel flow. Specifically, the gate passage scene images are analyzed to identify each individual in the image, and a target detection algorithm (such as YOLO or Faster R-CNN) is used to locate each person in the image. After determining the position of each person, the displacement of the same person between different time frames is calculated to track their movement trajectory. In this process, a feature point-based tracking algorithm (such as KLT tracking algorithm or deep learning target tracking method) can be used to continuously track the position changes of each person in the video. By analyzing the movement distance of each person within a certain time interval, the system can calculate the number of personnel passing through the gate per unit time, and then generate a passage rate indicator that reflects the speed of personnel flow. If the passage rate is high, it indicates that the efficiency of personnel passing through the gate is high, and if the rate is low, it indicates that the speed of personnel passing through is slow, which may indicate congestion.

[0022] By analyzing the density and distribution of personnel in the gate passage scene images, a queue length change indicator is generated to measure the trend of queue changes and the degree of congestion. Specifically, a target detection algorithm (such as YOLO or Faster R-CNN) is used to identify all personnel in the image and extract the position of each individual. Based on this position information, the image is divided into multiple virtual grids, and the number of personnel in each grid is analyzed to determine the distribution of personnel. According to the relative position and arrangement of personnel, the start and end areas of the queue are automatically identified, and the length of the queue area is calculated by measuring the farthest distance of the queued personnel. On this basis, the change in queue length over time is monitored in real time, the rate of queue length change is calculated, and the queue length change indicator is generated. If the queue length increases rapidly in a short period of time, it indicates that the passage speed is slowing down and congestion may occur; conversely, if the queue length is relatively stable, it indicates that the passage is relatively smooth.

[0023] The system predicts the total passage time required to pass through the gate by real-time calculation of the passage rate indicator and the queue length change indicator. Passage time prediction is based on the current passage rate (i.e., the number of personnel passing through per unit time) and the change in queue length (i.e., the change rate of the queue area). The system combines these two indicators to calculate the total time required for all personnel to pass through the gate at the current passage rate. The prediction formula can be expressed as: predicted time = queue length / passage rate, where the queue length is the total length of all personnel in the current queue area, and the passage rate is the number of personnel passing through the gate per unit time.

[0024] The system calculates the ratio of the calculated predicted duration to the preset non-aggregation discrimination duration to obtain the passing aggregation degree. The non-aggregation discrimination duration is based on the average time of personnel passing under normal conditions without congestion in the passing process. When the ratio of the actual predicted duration to the preset duration is too high, it indicates that the current passing state has congestion or aggregation phenomenon.

[0025] Further, the passing aggregation degree recognition based on the gate passing scene image further includes: Connect the campus intelligent management platform to read the authorized opening features of the preset area; based on the authorized opening features and historical passing features, predict the passing aggregation degree distribution space, and construct the aggregation degree constraint interval; verify the passing aggregation degree with the aggregation degree constraint interval, and if the verification shows abnormal, send an abnormal aggregation reminder to the authority management personnel of the preset area.

[0026] The system connects the campus intelligent management platform to read the authorized opening features of the area from the platform, which includes the opening policy within a time period, personnel passing restrictions (such as areas open within a certain time period, personnel categories allowed to enter, etc.), and normal patterns of passing in the area (such as passing frequency during peak hours, fluidity during open time period, etc.).

[0027] The historical passing features, i.e. the passing data of the area in the same time period in the past, include historical personnel flow, queue length, passing time, and other passing patterns, as well as the passing speed and aggregation degree calculated based on these data.

[0028] Based on the authorized opening features and historical passing features, data mining or machine learning algorithms (such as regression analysis, time series prediction, etc.) are used to predict the future passing aggregation degree; by analyzing the relationship between historical passing features and authorized opening features, the system can predict the possible passing aggregation degree distribution of the area at a certain time or time period in the future. For example, if a large number of personnel usually pass through a certain area during a certain period, and the area is open for a specific activity, the system will estimate the passing aggregation degree of the area based on historical data. According to the predicted aggregation degree data, the system will construct an aggregation degree constraint interval, which is a range of allowed aggregation degree, reflecting the maximum and minimum personnel density that the area should have under normal passing conditions.

[0029] The system uses the aggregation degree constraint interval to verify the currently calculated passing aggregation degree. If the verification result shows that the current passing aggregation degree exceeds the preset normal range, the system will judge that there is an aggregation anomaly, indicating that there is a risk of excessive aggregation of personnel in the area. At this time, the system will send an abnormal aggregation reminder to the authority management personnel of the area, so that the administrator can take timely measures, such as scheduling personnel flow, increasing temporary open channels, or adjusting other passing strategies, to effectively avoid congestion or safety risks.

[0030] Further, if the verification shows abnormalities, it also includes: Real-time spatio-temporal event collection is performed to generate spatio-temporal event information; a sudden increase index of the passing aggregation degree relative to the aggregation degree constraint interval is calculated; a sudden increase impact analysis is performed using the spatio-temporal event information and matched with the sudden increase index; if the matching verification is passed, a permission sensitivity analysis is performed based on the region attribute of the preset region, and if the permission sensitivity level is less than a preset threshold, the third type of personnel without passing permission is released and the activity region is limited and tracked, and the permission management personnel is reported.

[0031] The system dynamically monitors the surrounding area of the passing gate, and collects spatio-temporal event information in the passing process of personnel in real time. The spatio-temporal event information includes the time, place, personnel involved, type of event (such as personnel queuing, passing speed change, etc.) and possible abnormal conditions. For example, when it rains, people gather in the library to avoid the rain, resulting in a sharp increase in the flow of people in the library.

[0032] The system compares the current passing aggregation degree with the preset aggregation degree constraint interval to calculate a sudden increase index, sudden increase index = (passing aggregation degree - upper limit of aggregation degree constraint interval) / upper limit of aggregation degree constraint interval. The sudden increase index reflects the sudden increase degree of the current aggregation degree compared with the normal interval. For example, if the degree of personnel concentration rises rapidly at a certain moment and obviously exceeds the normal passing range, the value of the sudden increase index will become higher.

[0033] The system combines the spatio-temporal event information with the sudden increase index to perform a sudden increase impact analysis in order to determine whether the abnormal fluctuation of the sudden increase index is related to certain specific events (such as special activities, personnel flow peaks, etc.). By matching the sudden increase index and the related event information, the system can verify whether there is a passing abnormality caused by special factors, so as to determine whether further intervention or adjustment of the passing strategy is needed.

[0034] If the matching verification passes, the system will conduct a permission sensitivity analysis based on the regional attributes of the preset area. Regional attributes include the passage nature of the area (such as whether it is a high-risk area or a restricted area), the security level of the area (such as whether it contains critical infrastructure or important equipment), and the access control requirements of the area (for example, whether strict permission management is required). Through analysis, the system can determine the permission sensitivity level of the area, which reflects the security requirements and control requirements for personnel flow. If the permission sensitivity level is less than the preset security threshold, it means that the security requirements of the area are relatively low, and the system will determine whether to release the third type of personnel (such as temporary visitors or unauthorized personnel) who do not have passage permissions. In this case, the system will allow temporary release of the third type of personnel, but only within a specific area. To ensure safety, the system will explicitly limit the activity area of these personnel to ensure they only pass through or act within the allowed area, avoiding high-risk or restricted access areas. In addition, the system will monitor the activity trajectory of these third type of personnel in real time to ensure they are under surveillance, and any unauthorized or abnormal behavior will be recorded and trigger an alarm. At the same time, the system will record the release information and activity trajectory of the third type of personnel in detail and report it to the permission management personnel.

[0035] Further, when the passage aggregation degree is greater than the preset aggregation threshold, the gate passage scene image is subjected to group face recognition to generate the first type of personnel and the second type of personnel, including: The gate passage scene image is subjected to group face recognition to generate a group face recognition result; based on the group face recognition result, dynamic authorized personnel and temporary visitors are divided to generate the first type of personnel and the second type of personnel.

[0036] When the system detects that the aggregation degree of the gate passage area exceeds the standard, it automatically triggers the group face recognition function. Through this function, the system uses advanced face detection algorithms (such as convolutional neural networks CNN or deep learning models) to detect multiple faces in the image. Based on the group face recognition result, i.e., by comparing the recognized facial features with the personnel information stored in the database, the system divides dynamic authorized personnel and temporary visitors. By comparing identity information, the system can automatically distinguish between two types of personnel: the first type of personnel is dynamic authorized personnel who have obtained authorization (such as employees or students who hold long-term valid certificates, etc.), and the second type of personnel is temporary visitors who need temporary authorization (such as outsiders, short-term activity participants, etc.).

[0037] Further, after generating the first type of personnel and the second type of personnel, it further includes: The second type of personnel is subjected to a preset permission verification strategy to identify the accompanying permissions of authorized personnel, and the fourth type of personnel is determined.

[0038] After identifying the second type of personnel (temporary visitors), the system will further verify the identity of these personnel according to the preset permission verification strategy. The preset permission verification strategy may include temporary identification, pre-registered visitor information, visitor activity permissions, etc. The system determines whether temporary visitors need to be granted accompanying permissions, i.e. the related permissions of certain authorized personnel, according to these strategies. For example, if a visitor is accompanied by an authorized personnel (such as a faculty member or a student), the system may grant the visitor certain temporary access permissions or share certain access permissions with the authorized personnel. When the second type of personnel (temporary visitors) passes the permission verification and is determined to have accompanying permissions, the system will determine these visitors as the fourth type of personnel, and the fourth type of personnel will be classified into the first type of personnel. At the same time, the system will bind and track the fourth type of personnel with authorized personnel (such as accompanying faculty members or students), that is, it will continuously track the movement trajectory of the visitor and the authorized personnel, and ensure that they comply with the restrictions of the restricted area or the access rules during the access process. For example, the system will monitor the activity range of the fourth type of personnel in real time to ensure that they are limited to authorized areas or activities and do not exceed the permission boundary.

[0039] The authorized trajectory of the first type of personnel is extracted to construct a first authorized trajectory map.

[0040] The system monitors the access behavior of the first type of personnel and collects their activity trajectory within a specified time period. The system obtains the entry and exit data of these personnel through cameras and sensors (such as RFID, two-dimensional code scanning, etc.) installed in the access area. Whenever the first type of personnel passes through a certain access gate or enters a certain area, the system records the identity information, timestamp, and location coordinates of the personnel, and tracks their movement path in real time. The system extracts the movement path and behavior pattern of the personnel from the collected multi-dimensional data through authorized trajectory extraction, and constructs a first authorized trajectory map based on the extracted data, i.e. a movement route map of the personnel in the preset area.

[0041] The first type of personnel is subjected to permission verification to exempt from access processing, and tracking verification is performed after access based on the first authorized trajectory map.

[0042] When the system identifies the identity of the first type of personnel and confirms that they have valid access rights, it automatically waives their secondary access verification. This means that the personnel do not need to go through the verification steps such as re-swiping the card, entering the password, etc. when passing through the gate or entering the authorized area, thereby improving the efficiency of access. However, although the access verification is waived, the system will continue to monitor the subsequent activities of the personnel based on the first authorized trajectory mapping. The system tracks the action trajectory of the personnel in real time and compares it with the authorized trajectory established in advance to ensure that the personnel do not deviate from the predetermined path or enter unauthorized areas during access. If the action trajectory of the personnel deviates abnormally, the system will immediately issue an alert and record the information of the abnormal behavior for processing.

[0043] Further, the access verification of the first type of personnel is waived for access processing, and the tracking verification after access is performed based on the first authorized trajectory mapping, comprising: The first monitoring trajectory is determined by real-time monitoring by the camera in the preset area; the trajectory deviation is determined by comparing the first monitoring trajectory with the first authorized trajectory mapping; the trajectory access verification reminder is issued based on the trajectory deviation for trajectory deviation verification.

[0044] The system tracks and records the real-time access path of the first type of personnel through real-time monitoring by the camera in the preset area. The camera will capture the activity data of the personnel in the area and generate a first monitoring trajectory based on the location information of the personnel, which is the actual moving path of the personnel in the area. The system compares the generated first monitoring trajectory with the first authorized trajectory mapping established in advance, which is the preset access path of the personnel during the authorized period. By comparing the differences between the two, the system can determine whether there is a trajectory deviation, i.e., whether the personnel deviated from the authorized access route or entered an unauthorized area during actual access. If the system finds a trajectory deviation, i.e., the actual path of the personnel deviates from the authorized trajectory, the system will immediately issue a trajectory access verification reminder to notify the access management personnel to pay attention to the abnormal behavior of the personnel. At this time, the system will further verify the trajectory deviation, possibly by reconfirming the identity of the personnel or implementing other security control measures to ensure that the behavior of the personnel is within the authorized range.

[0045] The verification of the preset access verification strategy is performed on the second type of personnel, and semantic micro-access is issued for tracking verification.

[0046] The system performs a preset permission verification policy on the second type of personnel, such as temporary identification or active participation identity authentication, to ensure that their access permissions are legal. Once the verification is passed, the system issues semantic micro-permissions according to the access requirements, i.e., limiting the executable operations and behavior scope of the personnel in a specific time and area. These micro-permissions can finely control the activities of the visitor, such as access to specific areas, stay time, and interactive objects, etc. Subsequently, the system tracks and verifies the activities of the personnel through real-time monitoring devices to ensure that their behavior is within the authorized scope. If their behavior deviates from the permission scope, the system will immediately issue an alarm and intervene in time. Through this fine-grained permission management and continuous monitoring, the system effectively guarantees the access efficiency of temporary visitors while ensuring the safety of the area.

[0047] Further, the verification of performing a preset permission verification policy on the second type of personnel and issuing semantic micro-permissions for tracking verification include: Based on the preset permission verification policy, the temporary task of the second type of personnel and the associated sub-area are determined. The semantic micro-permission configuration is performed based on the temporary task and the associated sub-area, including time limit, path limit, area limit, and interactive object limit. The permission tracking verification is performed after the second type of personnel passes through the semantic micro-permission, and an over-limit warning is issued when the permission is deviated.

[0048] The system determines the temporary task of the second type of personnel and the associated sub-area that needs to be accessed according to the preset permission verification policy. The temporary task may include participating in a specific activity, meeting, or other temporary authorized task, and the associated sub-area is the range of areas that the personnel is allowed to enter.

[0049] The system configures semantic micro-permissions for the second type of personnel based on the temporary task and the associated sub-area. The semantic micro-permissions include limiting the access time, path, area, and interactive objects of the personnel. For example, the system may allow the personnel to access a specified area within a certain time period and only along a predetermined path, or specify that the personnel can only interact with certain specific personnel.

[0050] The system performs permission tracking verification after the visitor passes through. By monitoring the activities of the personnel in real time, the system verifies whether their behavior meets the predetermined conditions by comparing with the semantic micro-permissions. If the personnel deviates from the preset permission scope, such as entering an unauthorized area or exceeding the allowed activity time, the system will immediately trigger an over-limit warning and take emergency measures, such as issuing a warning, limiting further access, or notifying the permission management personnel to intervene.

[0051] In summary, the embodiments of the present application have at least the following technical effects: First, determine the access gates in the preset areas within the target campus. Then, use the non-authorization verification camera at the access gate to collect the access scene images in real time. Furthermore, based on the access scene images at the access gate, traffic concentration is identified. When the traffic concentration is greater than the preset concentration threshold, group face recognition is performed on the access scene images at the access gate to generate the first category of personnel and the second category of personnel, where the first category of personnel are dynamically authorized personnel and the second category of personnel are temporary visitors. Then, authorization trajectory extraction is performed for the first category of personnel, and a first authorization trajectory mapping is constructed; permission verification is performed on the first category of personnel to exempt them from access processing, and tracking verification after access is performed based on the first authorization trajectory mapping. Finally, the preset permission verification strategy is verified for the second category of personnel, and semantic micro-permissions are issued for tracking verification. This solves the technical problem in the existing technology that access gates are difficult to balance rapid access and permission security verification, and achieves the technical effect of improving access efficiency and security.

[0052] The second embodiment is based on the same inventive concept as the dynamic scene perception access authority allocation method in the above embodiment. Figure 2 As shown, the present application provides a dynamic scene-aware access authority allocation system, wherein the system includes: The gate positioning module 11 is used to determine the access gate of the preset area in the target campus; the image acquisition module 12 is used to collect the gate access scene image in real time through the non-authorization verification camera of the access gate; the personnel classification module 13 is used to identify the access concentration based on the gate access scene image. When the access concentration is greater than the preset concentration threshold, group face recognition is performed on the gate access scene image to generate the first category of personnel and the second category of personnel, wherein the first category of personnel is dynamically authorized personnel and the second category of personnel is temporary visitors; the trajectory extraction module 14 is used to perform authorization trajectory extraction for the first category of personnel and construct a first authorization trajectory mapping; the first processing module 15 is used to perform permission verification exemption access processing on the first category of personnel, and perform tracking verification after access based on the first authorization trajectory mapping; the second processing module 16 is used to verify the preset permission verification strategy for the second category of personnel, and issue semantic micro-permissions for tracking verification.

[0053] Furthermore, the personnel classification module 13 is configured to perform the following method: Connect to the campus smart management platform to read the authorized opening characteristics of the preset area; based on the authorized opening characteristics and historical traffic characteristics, predict the traffic concentration distribution space and construct a concentration constraint interval; verify the traffic concentration with the concentration constraint interval. If the verification shows an abnormality, send an abnormal concentration reminder to the authority management personnel of the preset area.

[0054] Furthermore, the personnel classification module 13 is configured to perform the following method: spatiotemporal event information is generated; a sudden increase index of the passing aggregation degree relative to the aggregation degree constraint interval is calculated; a sudden increase influence analysis is performed using the spatiotemporal event information, and is matched and verified with the sudden increase index; if the matching and verification passes, a permission sensitivity analysis is performed based on the regional attribute of the preset area, and if the permission sensitivity level is less than a preset threshold, the third type of personnel without passing permission is released and the activity area is limited and tracked, and the permission management personnel is reported.

[0055] Further, the personnel classification module 13 is used to perform the following method: A passing rate and a queuing length change in the camera field of view are identified based on the gate passing scene image, and a passing rate index and a queuing length change index are generated; a passing time is predicted using the passing rate index and the queuing length change index, a ratio of the predicted time to a preset non-aggregation discrimination time is calculated, and the passing aggregation degree is generated.

[0056] Further, the personnel classification module 13 is used to perform the following method: A group face recognition is performed on the gate passing scene image, and a group face recognition result is generated; a dynamic authorized personnel and a temporary visitor are divided based on the group face recognition result, and the first type of personnel and the second type of personnel are generated.

[0057] Further, the personnel classification module 13 is used to perform the following method: The second type of personnel is called to perform a preset permission verification strategy to identify authorized personnel and associated permissions, and a fourth type of personnel is determined; the fourth type of personnel is classified into the first type of personnel and is bound and tracked with the associated authorized personnel.

[0058] Further, the first processing module 15 is used to perform the following method: A first monitoring track is determined by real-time monitoring of the camera in the preset area; a track deviation is determined by comparing the first monitoring track with the first authorized track mapping; a track permission verification reminder is issued based on the track deviation, and a track deviation verification is performed.

[0059] Further, the second processing module 16 is used to perform the following method: A temporary task and an associated sub-area of the second type of personnel are determined based on the preset permission verification strategy; a semantic micro-permission configuration is performed based on the temporary task and the associated sub-area, including time limit, path limit, area limit and interactive object limit; a permission tracking verification is performed after the second type of personnel passes based on the semantic micro-permission, and an over-limit early warning is performed when the second type of personnel deviates from the semantic micro-permission.

[0060] Embodiment three,Figure 3 Figure 1 shows a structural schematic diagram of an electronic device provided for Embodiment Three of the present application, which shows a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present application. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functions and usage range of the embodiments of the present application. As shown in Figure 1, the electronic device comprises a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more, Figure 3 As shown in Figure 1, the electronic device comprises a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more, Figure 3 As an example, the processor 21 in the electronic device, the memory 22, the input device 23 and the output device 24 can be connected through a bus or other means, Figure 3 As an example, the processor 21 in the electronic device, the memory 22, the input device 23 and the output device 24 can be connected through a bus or other means,

[0061] The memory 22 is a computer readable storage medium, which can be used to store software programs, computer executable programs and modules, such as the program instructions / modules of the dynamic scene perception access right allocation method in the embodiments of the present application. The processor 21 executes the software programs, instructions and modules stored in the memory 22, thereby performing various function applications and data processing of the electronic device, i.e. implementing the dynamic scene perception access right allocation method described above.

[0062] It should be noted that the above-mentioned sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present application. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0063] The above description is merely the preferred embodiments of the present application and should not be used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

[0064] The present application and the drawings are merely exemplary descriptions of the present application, and should be considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and changes.

Claims

1. A method of dynamic scene-aware access right allocation, characterized in that, The method comprises: determining a passageway gate of a preset area in a target campus; real-time collection of gate passageway scene images by a non-authorization verification camera of the passageway gate; passage gathering degree recognition based on the gate passageway scene images, when the passage gathering degree is greater than a preset gathering threshold, group face recognition of the gate passageway scene images, generating first type personnel and second type personnel, wherein the first type personnel are dynamic authorized personnel, and the second type personnel are temporary visitors; authorization trajectory extraction for the first type personnel, constructing a first authorization trajectory mapping; authorization verification exemption for the first type personnel, and tracking verification after passage based on the first authorization trajectory mapping; verification of a preset authorization verification strategy for the second type personnel, and issuing semantic micro-authorization for tracking verification.

2. The dynamic scene-aware access permission allocation method of claim 1, wherein, The passage gathering degree recognition based on the gate passageway scene images further comprises: connecting a campus intelligent management platform to read the authorized open features of the preset area; passage gathering degree distribution space prediction based on the authorized open features and historical passage features, constructing a gathering degree constraint interval; verifying the passage gathering degree with the gathering degree constraint interval, and issuing an abnormal gathering reminder to the authorization management personnel of the preset area if the verification shows an abnormality.

3. The dynamic scene-aware access permission allocation method of claim 2, wherein, If the verification shows an abnormality, further comprising: real-time spatio-temporal event collection to generate spatio-temporal event information; calculating a sudden increase index of the passage gathering degree relative to the gathering degree constraint interval; sudden increase influence analysis with the spatio-temporal event information, and matching verification with the sudden increase index; if the matching verification is passed, authorization sensitivity analysis based on the area attributes of the preset area, if the authorization sensitivity level is less than a preset threshold, releasing and limiting tracking of the third type personnel who do not have passage authorization in the activity area, and reporting the authorization management personnel.

4. The dynamic scene-aware access permission allocation method of claim 1, wherein, The passage gathering degree recognition based on the gate passageway scene images comprises: personnel passage rate and queue length change recognition within the camera field of view based on the gate passageway scene images, generating a passage rate index and a queue length change index; passage time length prediction with the passage rate index and the queue length change index, calculating the ratio of the predicted time length to the preset non-gathering discrimination time length, and generating the passage gathering degree.

5. The dynamic scene-aware access permission allocation method of claim 4, wherein, When the passage gathering degree is greater than the preset gathering threshold, group face recognition of the gate passageway scene images, generating first type personnel and second type personnel, comprising: group face recognition of the gate passageway scene images to generate a group face recognition result; dynamic authorized personnel and temporary visitor division based on the group face recognition result, generating the first type personnel and the second type personnel.

6. The dynamic scene-aware access permission allocation method of claim 5, wherein, After generating the first type personnel and the second type personnel, further comprising: calling the second type personnel to perform authorization personnel associated authorization identification based on a preset authorization verification strategy, to determine fourth type personnel; binding the fourth type personnel to the first type personnel and the associated authorized personnel for binding tracking.

7. The dynamic scene-aware access permission assignment method of claim 1, wherein, The first type of personnel is exempted from access processing by authority verification, and tracking verification after access is performed based on the first authorized trajectory mapping, including: Determine the first monitoring trajectory by real-time monitoring through the camera in the preset area; Determine the trajectory deviation by comparing the first monitoring trajectory with the first authorized trajectory mapping; Issue a trajectory authority verification reminder based on the trajectory deviation, and perform trajectory deviation verification.

8. The dynamic scene-aware access permission allocation method of claim 1, wherein, The second type of personnel is verified by a preset authority verification strategy, and semantic micro-authority is issued for tracking verification, including: Determine the temporary task and associated sub-area of the second type of personnel based on the preset authority verification strategy; Configure semantic micro-authority based on the temporary task and associated sub-area, including time limit, path limit, area limit and interactive object limit; Authority tracking verification is performed after the second type of personnel passes through based on the semantic micro-authority, and an over-limit warning is given when the semantic micro-authority is deviated.

9. A dynamic scene-aware access rights allocation system, characterized in that The system for implementing the dynamic scene-aware access authority allocation method of any one of claims 1-8, the system comprising: Gate positioning module, for determining the access gate of the preset area in the target campus; Image acquisition module, for acquiring real-time gate access scene images through non-authority verification cameras of the access gate; Personnel classification module, for identifying access aggregation based on the gate access scene images, and when the access aggregation is greater than a preset aggregation threshold, performing group face recognition on the gate access scene images to generate first type of personnel and second type of personnel, wherein the first type of personnel is dynamic authorized personnel, and the second type of personnel is temporary visitor; Trajectory extraction module, for performing authorized trajectory extraction for the first type of personnel, and constructing a first authorized trajectory mapping; First processing module, for performing authority verification on the first type of personnel to exempt from access processing, and performing tracking verification after access based on the first authorized trajectory mapping; Second processing module, for performing verification of the second type of personnel by a preset authority verification strategy, and issuing semantic micro-authority for tracking verification.

10. An electronic device, comprising: The electronic device comprises: A memory for storing executable instructions; A processor for executing the executable instructions stored in the memory to implement the dynamic scene-aware access authority allocation method of any one of claims 1-8. The electronic device comprises: A memory for storing executable instructions; A processor for executing the executable instructions stored in the memory to implement the dynamic scene-aware access authority allocation method of any one of claims 1-8.

Images