A smart campus management system and method based on the Internet of Things

Abstract

The present application provides a smart campus management system and method based on the Internet of Things. The method predicts the passage pressure of the target access control gate through the passage flow of the target access control gate and the density of the flow of people in the monitoring area of ​​the target access control gate. According to the access records of each person to be passed, all people to be passed are divided into multiple personnel groups, and the access characteristics corresponding to each personnel group are determined. The trust labels corresponding to each personnel group in the monitoring area are set according to the characteristic differences between each access characteristic. The authentication confidence of the access control gate for the target person to be passed is determined based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust label of the personnel group to which the target person to be passed belongs. The opening of the access control gate is controlled based on the authentication confidence. The above scheme is based on the authentication confidence, which can realize the accurate authentication and identification of the passing personnel by the access control gate in high-traffic scenarios.

Description

Technical Field

[0001] The present application relates to the field of access control technology, and more specifically, to a smart campus management system and method based on the Internet of Things. Background Art

[0002] In today's digital age, with the rapid development of information security, access control has become one of the key technologies to ensure information security. In the early days, access control systems relied on simple password verification to achieve access, but this method is extremely easy to crack. In order to effectively protect information resources, the current access control system requires that only legal and authorized users can access, which greatly improves the effectiveness of access control. Among them, access control has also been widely used in smart campus management. For example, access control in smart campus access control systems. The access control of smart campus access control lies in multi-dimensional identity recognition, such as card swiping, fingerprint, facial recognition, etc., to accurately grant teachers and students different access rights.

[0003] In the existing access control, the access system will first authenticate the subject to ensure the legitimacy of its identity. When the authentication is successful, the access control system will authorize the subject's access request based on the preset access control policy and assign permissions based on the subject's role. If the permissions match, access is allowed, otherwise it is denied and relevant logs are recorded. However, in smart campus management, there is usually a high flow of people, and existing access control gates usually rely on fixed authentication methods for access control, which makes the pass authentication in high-flow scenarios interfere with the flow of people, making it difficult for the access control gate to accurately authenticate and identify passers-by in high-flow scenarios. Therefore, how to achieve accurate authentication and identification of passers-by by access control gates in high-flow scenarios has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a smart campus management system and method based on the Internet of Things, which can enable access control gates to accurately authenticate and identify passers-by in high-traffic scenarios.

[0005] In a first aspect, the present application provides a smart campus access control method, comprising the following steps:

[0006] Collect traffic flow of target access control gates within the campus area;

[0007] The passage pressure of the target access control gate in a pedestrian flow state is predicted by the passage flow and the crowd density in the monitoring area of ​​the target access control gate. When the passage pressure exceeds a preset range, the access records of each person waiting to pass in the monitoring area are retrieved from the monitoring center;

[0008] Based on all access records, each person waiting to pass through the monitoring area is divided into multiple groups. The access characteristics corresponding to each group are determined based on the access information of each person waiting to pass through when accessing the target access control gate. The trust labels corresponding to each group in the monitoring area are set based on the feature differences between the access characteristics.

[0009] When the target person to be passed in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence of the access control gate for the target person to be passed is determined based on the authentication deviation of the target person to be passed in different authentication dimensions and the trust label of the person group to which the target person to be passed belongs;

[0010] The opening of the access gate is controlled based on the authentication confidence.

[0011] In some embodiments, predicting the traffic pressure of the target access control gate in a pedestrian flow state based on the traffic flow and the crowd density in the monitoring area of ​​the target access control gate specifically includes:

[0012] Collect traffic flow data of the target access control gate;

[0013] Obtaining crowd density data within the monitoring area through monitoring equipment deployed in the monitoring area of ​​the target access control gate;

[0014] Calculating a dynamic traffic index of people flow in the monitoring area based on the traffic flow data and the people flow density data;

[0015] The traffic pressure prediction model of the target access control gate under the condition of pedestrian flow is established based on the traffic capacity of the target access control gate;

[0016] The dynamic traffic index is input as an input parameter into the traffic pressure prediction model, and the traffic pressure prediction model outputs the traffic pressure value of the target access control gate under the pedestrian traffic state.

[0017] In some embodiments, each person waiting to pass through the monitoring area is divided according to all access records to obtain multiple personnel groups, specifically including:

[0018] A person waiting to pass through the monitoring area is selected as the selected person waiting to pass through, and the number of access passes and the number of access interceptions are extracted from the access records corresponding to the selected person waiting to pass through;

[0019] Determining the access trustworthiness of the selected person waiting to pass according to the number of access passes and the number of access interceptions, and continuing to determine the access trustworthiness of the remaining persons waiting to pass;

[0020] Each person waiting to pass through the monitoring area is projected and clustered through all access trusts, thereby obtaining multiple personnel groups.

[0021] In some embodiments, determining the access characteristics corresponding to each personnel group according to the access information of each person waiting to pass in each personnel group when accessing the target access control gate specifically includes:

[0022] Obtain access information of each person waiting to pass in each personnel group when accessing the target access control gate;

[0023] Standardizing the access information of each person waiting to pass in each person group to obtain standardized access information of each person waiting to pass in each person group;

[0024] Extracting access parameters under different access dimensions from the standardized access information of each person to be passed;

[0025] Select a personnel group as the selected personnel group, determine the parameter change of the selected personnel group under the same access dimension based on all access parameters under the same access dimension in the selected personnel group, and then obtain the parameter change of the selected personnel group under different access dimensions;

[0026] Determine the access characteristics corresponding to the selected personnel group based on the parameter changes under different access dimensions;

[0027] Continue to determine the access characteristics corresponding to the remaining personnel groups.

[0028] In some embodiments, setting the trust labels corresponding to each person group in the monitoring area based on the feature differences between the access features specifically includes:

[0029] Obtain the access characteristics of each personnel group and calculate the feature differences between each access characteristic;

[0030] Determine the range of each trust level when a person accesses the target access control gate based on all feature differences;

[0031] The trust level label of each personnel group is set based on the interval range of each trust level and the access characteristics of each personnel group.

[0032] In some embodiments, determining the authentication confidence of the access control machine for authenticating the target person to be passed based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust tag of the person group to which the target person to be passed belongs specifically includes:

[0033] Obtain authentication information of the target person to be passed under different authentication dimensions;

[0034] Extracting authentication features of each feature dimension from the authentication information under each authentication dimension;

[0035] The authentication features of each feature dimension are verified for deviation with the corresponding reference authentication features to obtain the authentication deviation of the target person under different authentication dimensions;

[0036] Determine the authentication loss of the access control gate in authenticating the target person to pass based on all authentication deviations;

[0037] The authentication confidence of the access control gate in performing pass authentication on the target person to be passed is determined by the authentication loss and the trust label of the person group to which the target person to be passed belongs.

[0038] In some embodiments, the traffic flow of the target access control gate is collected by a camera installed at the target access control gate.

[0039] In a second aspect, the present application provides an Internet of Things-based smart campus management system, which includes an access control gate and a monitoring center, wherein the access control gate and the monitoring center are connected via the Internet of Things, and the monitoring center includes an access control control unit, which includes:

[0040] The collection module is used to collect the traffic flow of the target access control gate in the campus area;

[0041] a processing module configured to predict the passage pressure of the target access control gate under a pedestrian flow state based on the passage flow rate and the crowd density within the monitoring area of ​​the target access control gate, and to retrieve access records of each person waiting to pass through the monitoring area from a monitoring center when the passage pressure exceeds a preset range;

[0042] The processing module is further configured to divide each person waiting to pass through the monitoring area according to all access records to obtain multiple personnel groups, determine the access characteristics corresponding to each personnel group according to the access information of each person waiting to pass through in each personnel group when accessing the target access control gate, and set the trust label corresponding to each personnel group in the monitoring area according to the characteristic differences between the various access characteristics;

[0043] The processing module is further configured to determine, when a target person to be passed in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence of the access control gate for the target person to be passed based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust tag of the person group to which the target person to be passed belongs;

[0044] An execution module is used to control the opening of the access control gate based on the authentication confidence.

[0045] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned smart campus access control method.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned smart campus access control method.

[0047] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0048] In the IoT-based smart campus management system and method provided by the present application, first, the traffic flow of the target access control gate in the campus area is collected; secondly, the traffic pressure of the target access control gate in the pedestrian traffic state is predicted based on the traffic flow and the crowd density in the monitoring area of ​​the target access control gate. When the traffic pressure exceeds a preset range, the access records of each person waiting to pass in the monitoring area are retrieved from the monitoring center; further, each person waiting to pass in the monitoring area is divided according to all the access records to obtain multiple personnel groups, and the access characteristics corresponding to each personnel group are determined according to the access information of each person waiting to pass in each personnel group when accessing the target access control gate, and the trust labels corresponding to each personnel group in the monitoring area are set according to the characteristic differences between the various access characteristics; then, when the target person waiting to pass in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence of the access control gate for authenticating the target person waiting to pass is determined based on the authentication deviation of the target person waiting to pass under different authentication dimensions combined with the trust label of the personnel group to which the target person waiting to pass belongs; finally, the opening of the access control gate is controlled based on the authentication confidence.

[0049] It can be seen that the present application can realize the accurate authentication and identification of passers-by by the access control gate in high pedestrian flow scenarios; firstly, the traffic pressure of the target access control gate under the pedestrian flow state is predicted by the traffic flow and the crowd density in the monitoring area of ​​the target access control gate, so as to effectively analyze the bearing capacity of the current target access control gate, and then effectively adjust the authentication strategy of the visiting personnel to avoid the authentication deviation caused by the interference of the crowd flow; secondly, based on the access records of each person to be passed in the monitoring area, each person to be passed is diverted to obtain multiple personnel groups, so as to identify the person to be passed with higher authentication trust in advance, and further improve the authentication accuracy of the passers-by; further, according to the access information of each person to be passed in each personnel group when accessing the target access control gate, the access characteristics corresponding to each personnel group are determined, and The trust label corresponding to each personnel group is set by the feature difference between each access feature to identify the trust level of the passerby in advance, and then the authentication loss of the current access control gate is judged based on the trust level of the identified passerby, so as to further verify the passerby, thereby avoiding the authentication deviation caused by the fixed authentication method of the access control gate; then, based on the authentication deviation of the target person to be passed in different authentication dimensions and the trust label of the personnel group to which the target person to be passed belongs, the authentication confidence of the access control gate for the pass authentication of the target person to be passed is determined, so as to accurately authenticate and identify the target person to be passed; finally, the opening of the target access control gate is controlled based on the authentication confidence; in summary, the technical solution provided by the present application can realize the accurate authentication and identification of passersby by the access control gate in high-traffic scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is an exemplary flow chart of a smart campus access control method according to some embodiments of the present application;

[0051] Figure 2 is an exemplary flow chart of determining passage pressure according to some embodiments of the present application;

[0052] Figure 3 is an exemplary flow chart of determining multiple personnel groups according to some embodiments of the present application;

[0053] Figure 4 is a schematic structural diagram of an access control unit according to some embodiments of the present application;

[0054] Figure 5 It is a structural diagram of a computer device for implementing a smart campus access control method according to some embodiments of the present application. DETAILED DESCRIPTION

[0055] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0056] refer to Figure 1 , which is an exemplary flow chart of a smart campus access control method according to some embodiments of the present application. The smart campus access control method 100 mainly includes the following steps:

[0057] In step 101, the traffic volume of the target access control gate in the campus area is collected.

[0058] In a specific implementation, a camera installed at the target access control gate collects the traffic flow of the target access control gate, and the traffic flow represents the number of people passing through the target access control gate in a unit time.

[0059] It should be noted that the target access control gate in this application is the access control gate at the campus gate. In addition, it can also be the access control gate at the campus library. There is no limitation here. The access control gate mainly controls access by authenticating visiting personnel.

[0060] In step 102, the traffic pressure of the target access control gate in the pedestrian traffic state is predicted based on the traffic flow and the crowd density in the monitoring area of ​​the target access control gate. When the traffic pressure exceeds the preset range, the access records of each person waiting to pass in the monitoring area are retrieved from the monitoring center.

[0061] In some embodiments, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart for determining passage pressure according to some embodiments of the present application. In this embodiment, the passage pressure of the target access control gate under the pedestrian flow state is predicted by the passage flow rate and the crowd density in the monitoring area of ​​the target access control gate, which can be achieved by the following steps:

[0062] First, in step 1021, the traffic flow data of the target access control gate is collected;

[0063] Next, in step 1022, the crowd density data in the monitoring area is obtained by the monitoring equipment deployed in the monitoring area of ​​the target access control gate;

[0064] Furthermore, in step 1023, a dynamic traffic index of the human flow in the monitoring area is calculated based on the traffic flow data and the human flow density data;

[0065] Then, in step 1024, a traffic pressure prediction model of the target access control gate under a pedestrian traffic state is established based on the traffic capacity of the target access control gate;

[0066] Finally, in step 1025, the dynamic traffic index is input as an input parameter into the traffic pressure prediction model, and the traffic pressure prediction model outputs the traffic pressure value of the target access control gate under the pedestrian traffic state.

[0067] In the specific implementation, first, the traffic flow data of the target access control gate is collected by a camera, and the traffic flow data includes traffic flow values ​​at different times, and the traffic flow value indicates the number of people passing through the target access control gate per unit time; secondly, the crowd density data in the monitoring area is obtained by the monitoring equipment deployed in the monitoring area of ​​the target access control gate, that is: the video stream of the monitoring area of ​​the target access control gate is collected by the camera, the crowd target is identified on the video stream through the YOLO algorithm in image processing, and the number of people per unit area is calculated, and then the crowd density data in the monitoring area is obtained, and the crowd density data includes crowd density values ​​at different times, and the crowd density indicates the number of people in the monitoring area of ​​the target access control gate per unit area; further, the dynamic traffic index of the crowd in the monitoring area is calculated based on the traffic flow data and the crowd density data, that is: the traffic flow data and the crowd density data are normalized respectively by minimum-maximum normalization, and then calculated respectively. The normalized traffic flow data and the pedestrian density data have a mean traffic flow and a mean pedestrian density, and the quotient of the mean traffic flow and the mean pedestrian density is used as the dynamic traffic index of the pedestrian flow in the monitoring area; then, a traffic pressure prediction model of the target access control gate under the pedestrian traffic state is established through the traffic capacity of the target access control gate, that is: according to the traffic capacity of the target access control gate, a traffic pressure prediction model of the target access control gate under the pedestrian traffic state is established by linear regression, and the traffic pressure prediction model is: traffic pressure = dynamic traffic index × weight factor, and the traffic capacity is the maximum number of people passing through the target access control gate per unit time, wherein the weight factor is obtained by training the historical traffic data through the decision tree in machine learning, and the weight factor reflects the actual influence of the dynamic traffic index on the traffic pressure; finally, the dynamic traffic index is input as an input parameter into the traffic pressure prediction model, and the traffic pressure prediction model outputs the traffic pressure value of the target access control gate under the pedestrian traffic state.

[0068] It should be noted that the dynamic traffic index in this embodiment represents the dynamic movement trend of the crowd in the monitoring area, and the dynamic traffic index can reflect the change of traffic flow relative to the crowd density; the traffic pressure prediction model in this embodiment represents a function for predicting the traffic pressure of the target access control gate; the traffic pressure value in this application represents the ability index of the access control gate to withstand the flow of people, and the traffic pressure reflects the heavy workload of the target access control gate that needs to be handled in actual use. In the management of smart campuses, facing a large number of people passing through, the authentication accuracy of the target access control gate will be affected by the flow of people. Therefore, by determining the traffic pressure, the current target access control gate's bearing capacity can be effectively analyzed, and then the authentication strategy of the visiting personnel can be effectively adjusted to improve the traffic authentication accuracy of the target access control gate.

[0069] In specific implementation, when the passage pressure exceeds the preset range, the access records of each person waiting to pass in the monitoring area are retrieved from the monitoring center, that is: when the passage pressure exceeds the preset range, an over-limit alarm signal is triggered. When the monitoring center receives the over-limit alarm signal, the access records of each person waiting to pass in the monitoring area are obtained from the access record database of the monitoring center. The access records include the number of visits passed, the number of visits intercepted, and the average visit time. Among them, the preset range in this embodiment is a pre-set safe passage pressure value, which can be set according to actual conditions and is not limited here.

[0070] It should be noted that, in this embodiment, the over-limit alarm signal represents a prompt signal automatically issued by the system. Specifically, the over-limit alarm signal is a prompt signal automatically issued by the system when the passage pressure exceeds the preset range. The access record in this application represents the information combination of the passer-by accessing the access control gate. By extracting the access record, the access trust level of the passer-by can be analyzed in advance, and then the authentication loss of the current access control gate can be judged based on the trust level of the passer-by, so as to further verify the passer-by, thereby avoiding the authentication deviation caused by the fixed authentication method of the access control gate.

[0071] In step 103, each person waiting to pass through the monitoring area is divided according to all access records to obtain multiple personnel groups, and the access characteristics corresponding to each personnel group are determined according to the access information of each person waiting to pass through in each personnel group when accessing the target access control gate. The trust label corresponding to each personnel group in the monitoring area is set according to the feature difference between each access characteristic.

[0072] In some embodiments, reference Figure 3As shown in FIG, this figure is an exemplary flow chart of determining multiple personnel groups according to some embodiments of the present application. In this embodiment, each person waiting to pass through the monitoring area is divided according to all access records, and multiple personnel groups can be obtained by the following steps:

[0073] First, in step 1031, a person waiting to pass through the monitoring area is selected as the selected person waiting to pass through, and the access pass count and access intercept count are extracted from the access record corresponding to the selected person waiting to pass through.

[0074] Then, in step 1032, the access trustworthiness of the selected person to be passed is determined based on the number of access passes and the number of access interceptions, and the access trustworthiness of the remaining persons to be passed is further determined;

[0075] Finally, in step 1033, projection clustering is performed on each person waiting to pass through the monitoring area using all access confidences, thereby obtaining multiple person groups.

[0076] In the specific implementation, first, a person waiting to pass in the monitoring area is selected as the selected person waiting to pass, and the number of access passes and the number of access interceptions are extracted from the access records corresponding to the selected person waiting to pass; then, the access trust of the selected person waiting to pass is determined based on the number of access passes and the number of access interceptions, and the access trust of the remaining persons waiting to pass is continued to be determined, that is, the number of access passes and the number of access interceptions are summed, and the quotient of the number of access passes and the sum is used as the access trust of the selected person waiting to pass, and the above steps are repeated to continue to determine the access trust of the remaining persons waiting to pass. In addition, in other embodiments, other methods can also be used. Its calculation method is to calculate the access trust of the person to be passed, which is not limited here; finally, all the access trusts are used to project and cluster each person to be passed in the monitoring area, and then multiple personnel groups are obtained, that is: based on all the access trusts, the K clustering algorithm is used to project and cluster each person to be passed in the monitoring area, and then multiple personnel groups are obtained. For example, multiple cluster centers are initialized based on all the access trusts, and each person to be passed is assigned to the cluster center closest to its access trust, and then multiple personnel groups are obtained. In addition, the DBSCAN classification in the density clustering algorithm can also be used to obtain multiple personnel groups, which is not limited here.

[0077] It should be noted that, in this embodiment, the access trust represents an indicator of the degree of trustworthiness of the passerby when accessing, that is, the greater the access trust, the greater the degree of trustworthiness of the passerby when accessing, and the smaller the access trust, the smaller the degree of trustworthiness of the passerby when accessing; the personnel grouping in this application represents a combination of multiple passersby, specifically, the personnel grouping is a group of passersby with similar access trust. By clustering all passersby, the passersby with high authentication reliability can be locked in advance, and then the authentication loss of the current access control gate can be judged based on the degree of trust in identifying the passersby, so as to further verify the passersby, thereby avoiding the authentication deviation caused by the fixed authentication method of the access control gate.

[0078] In some embodiments, the following steps may be used to determine the access characteristics corresponding to each personnel group based on the access information of each person waiting to pass in each personnel group when accessing the target access control gate, namely:

[0079] Obtain access information of each person waiting to pass in each personnel group when accessing the target access control gate;

[0080] Standardizing the access information of each person waiting to pass in each person group to obtain standardized access information of each person waiting to pass in each person group;

[0081] Extracting access parameters under different access dimensions from the standardized access information of each person to be passed;

[0082] Select a personnel group as the selected personnel group, determine the parameter change of the selected personnel group under the same access dimension based on all access parameters under the same access dimension in the selected personnel group, and then obtain the parameter change of the selected personnel group under different access dimensions;

[0083] Determine the access characteristics corresponding to the selected personnel group based on the parameter changes under different access dimensions;

[0084] Continue to determine the access characteristics corresponding to the remaining personnel groups.

[0085] In the specific implementation, first, the access information of each person to be passed in each personnel group when accessing the target access control gate is obtained from the access record database of the monitoring center, and the access information includes but is not limited to the access time, access frequency, access authority level, and access interception rate; secondly, the access information of each person to be passed in each personnel group is standardized by maximum-minimum normalization to obtain the standardized access information of each person to be passed in each personnel group. In addition, the access information of each person to be passed in each personnel group can also be standardized by Z-Score normalization to obtain the standardized access information of each person to be passed in each personnel group, which is not limited here; further, the access parameters under different access dimensions are extracted from the standardized access information of each person to be passed, that is: the mean access time under the time dimension, the mean access frequency under the access frequency dimension, the level quantization value under the access authority level dimension, and the mean interception under the access interception rate dimension are extracted from the standardized access information of each person to be passed, and the extracted values ​​are used as access parameters to obtain the access parameters of each person to be passed under different access dimensions; further, a personnel group is selected. The group is selected as the selected personnel group, and the parameter change of the selected personnel group under the same access dimension is determined based on all access parameters under the same access dimension in the selected personnel group, thereby obtaining the parameter change of the selected personnel group under different access dimensions. That is, a personnel group is selected as the selected personnel group, and the mean of all access parameters under the same access dimension in the selected personnel group is calculated, and the mean calculation result is used as the parameter change of the selected personnel group under the access dimension, thereby obtaining the parameter change of the selected personnel group under different access dimensions. Then, the access characteristics corresponding to the selected personnel group are determined based on the parameter changes under different access dimensions, that is, all parameter changes are weighted and summed, and the weighted sum result is used as the access characteristics corresponding to the selected personnel group. The weights of the parameter changes under different access dimensions can be set between 0 and 1 according to the degree of influence on authentication and access, which is not limited here. In addition, in other embodiments, other calculation methods can also be used to calculate the access characteristics corresponding to the selected personnel group, which is not limited here. Finally, the access characteristics corresponding to the remaining personnel groups are determined by the method of "determining the access characteristics corresponding to the selected personnel group based on the parameter changes under different access dimensions".

[0086] It should be noted that, in this embodiment, the access parameters represent characteristic values ​​that describe access behavior, specifically, the access parameters are the various behavioral characteristic values ​​when the passerby accesses the target access control gate; in this embodiment, the parameter change amount represents the change trend amount of the access parameter, specifically, the parameter change amount is the overall change trend amount of different access parameters under the same access dimension; the access features in this application represent the behavioral characteristics of the passerby accessing the target access control gate, and the access features are used to characterize the pattern of access behavior. These features can be used to support access control and authority management. By determining the access features, the overall access mode, operating status and security situation of the access control system can be effectively reflected, and it can support macro security management, performance optimization and anomaly detection, and avoid authentication deviations caused by human flow interference.

[0087] In some embodiments, setting the trust labels corresponding to each person group in the monitoring area based on the feature differences between the access features can be achieved by using the following steps, namely:

[0088] Obtain the access characteristics of each personnel group and calculate the feature differences between each access characteristic;

[0089] Determine the range of each trust level when a person accesses the target access control gate based on all feature differences;

[0090] The trust level label of each personnel group is set based on the interval range of each trust level and the access characteristics of each personnel group.

[0091] In the specific implementation, first, the access features of each personnel group are obtained, and the feature differences between the access features are calculated using the Euclidean distance; then, the interval ranges of each trust level when the passerby accesses the target access control gate are determined based on all the feature differences, that is, all the feature differences are arranged in ascending order, and all the feature differences after ascending order are divided by the three-part method to obtain three feature difference intervals, and the three feature difference intervals are used in order as the interval ranges of low sensitivity level, medium sensitivity level and high sensitivity level when the passerby accesses the target access control gate; finally, based on the interval range of each trust level and the access features of each personnel group, the trust label of each personnel group is set, that is, a personnel group is selected as the selected personnel group, the access features of the selected personnel group and the access features of the remaining personnel groups are averaged, and the corresponding difference average calculation result is used as the mapping value of the selected personnel group, the mapping value is mapped to the interval range of each trust level respectively, the trust level corresponding to the successfully mapped interval range is extracted as the trust label of the selected personnel group, and the trust labels of the remaining personnel groups are further determined.

[0092] It should be noted that, in this embodiment, the feature difference represents the deviation between access features; the interval range of the trust level in this embodiment represents the division range of different trust levels; the feature difference interval in this embodiment represents the division range of feature differences; the trust label in this application represents the tag information of the trust level of the passerby accessing the target access control gate. By determining the trust label, the authentication validity of the passerby can be effectively determined to achieve precise access control.

[0093] In step 104, when the target person to be passed in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence of the access control gate for the target person to be passed is determined based on the authentication deviation of the target person to be passed in different authentication dimensions and the trust label of the person group to which the target person to be passed belongs.

[0094] In specific implementation, when the target person waiting to pass in the monitoring area reaches the authentication area of ​​the access control gate, the target person waiting to pass is subjected to authentication evaluation in different dimensions.

[0095] In some embodiments, the authentication confidence of the access control machine for authenticating the target person to be passed can be determined based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust tag of the person group to which the target person to be passed belongs. The following steps can be used, namely:

[0096] Obtain authentication information of the target person to be passed under different authentication dimensions;

[0097] Extracting authentication features of each feature dimension from the authentication information under each authentication dimension;

[0098] The authentication features of each feature dimension are verified for deviation with the corresponding reference authentication features to obtain the authentication deviation of the target person under different authentication dimensions;

[0099] Determine the authentication loss of the access control gate in authenticating the target person to pass based on all authentication deviations;

[0100] The authentication confidence of the access control gate in performing pass authentication on the target person to be passed is determined by the authentication loss and the trust label of the person group to which the target person to be passed belongs.

[0101] In the specific implementation, first, the authentication information of the target person to be passed in different authentication dimensions is obtained through various sensors in the target access control gate. In this application, different authentication dimensions include face authentication dimension and fingerprint authentication dimension. For example, the authentication information of the target person to be passed in the face authentication dimension and fingerprint authentication dimension is obtained respectively through a camera and a fingerprint identifier, such as face image information and fingerprint information. In other embodiments, it can also be other authentication dimensions, which are not limited here; secondly, the authentication features corresponding to each feature dimension are extracted from the authentication information under each authentication dimension, that is: a feature extraction tool is used to extract the authentication features corresponding to each feature dimension from the authentication information under each authentication dimension. For example, under the face recognition authentication dimension, the image processing tool OpenCV is used to extract facial geometric features from the authentication information under the face recognition authentication dimension as the authentication features under the authentication dimension. Under the fingerprint authentication dimension, the image processing tool OpenCV can also be used to extract fingerprint texture from the authentication information under the fingerprint authentication dimension as the authentication features under the authentication dimension; further, the authentication features of each feature dimension are verified for deviation with the corresponding reference authentication features to obtain the authentication deviations of the target person to be passed in different authentication dimensions. That is: extract the reference authentication features of the target person to be passed in different authentication dimensions from the authentication database in the target access control gate, and calculate the difference between the authentication features of each feature dimension and the corresponding reference authentication features through Euclidean distance to obtain the authentication deviation of the target person to be passed in different authentication dimensions; then, determine the authentication loss of the access control gate for passing the target person to be passed based on all the authentication deviations, that is: assign different weights to the authentication deviations under each authentication dimension, perform weighted summation on all the authentication deviations, and use the weighted summation result as the authentication loss of the access control gate for passing the target person to be passed , wherein different weights are assigned to the authentication deviations under each authentication dimension, and the weights can be determined according to the importance of the authentication dimension in the overall authentication process, which is not limited here; finally, the authentication confidence of the access control machine for performing pass authentication on the target person to be passed is determined by the authentication loss and the trust label of the personnel group to which the target person to be passed belongs, that is: the trust label of the personnel group to which the target person to be passed belongs is obtained, the label quantization value of the trust label is extracted, the authentication loss and the label quantization value are feature quantized, and the authentication confidence of the access control machine when performing pass authentication on the target person to be passed is obtained.

[0102] It should be noted that, in this embodiment, authentication information represents various data and features used to verify the identity of the target person to pass; in this embodiment, authentication features represent specific attributes used for the identity of the person to pass during the authentication process; in this embodiment, authentication deviation represents the deviation between the authentication features of the target person to pass and the reference authentication features; in this embodiment, reference authentication features represent feature data used as a comparison standard, and the reference authentication features are usually collected and verified in advance, and are used to compare with the authentication features collected in real time to determine whether the identity of the target entity is consistent; in this embodiment, authentication loss represents the loss caused by inaccurate authentication results. Specifically, authentication loss is the loss caused by inaccurate authentication results or authentication failure due to the deviation between the authentication features and the reference authentication features.

[0103] In specific implementation, the label quantization value of the trust label is extracted, that is: the label quantization value of the trust label is set according to the number of trust labels, that is, the label quantization values ​​corresponding to the low trust level, the medium trust level and the high trust level are set to 0.3, 0.6 and 0.9 respectively, and the label quantization value of the trust label is extracted; the authentication loss and the label quantization value are feature quantized to obtain the authentication confidence of the access control machine when performing pass authentication on the target person to be passed, that is: the authentication loss and the label quantization value are weighted and summed, and the weighted sum result is used as the authentication confidence of the access control machine when performing pass authentication on the target person to be passed, wherein the weight values ​​of the authentication loss and the label quantization value can be set according to actual needs, which is not limited here. In addition, in other embodiments, other calculation methods can also be used to calculate the authentication confidence of the access control machine when performing pass authentication on the target person to be passed, which is not limited here.

[0104] It should be noted that, in this embodiment, the label quantization value represents the value after the label is numerically quantized; in this embodiment, the feature quantization represents the process of fusing different parameters in the same dimension; in this application, the authentication confidence represents an indicator of the degree of credibility of the authentication of passers-by, and the authentication confidence reflects the system's trust level in the authenticity of the user's identity, the legality of the behavior or the authentication result. In the access control system, the authentication confidence is usually used to measure the reliability of the authentication decision. If the authentication confidence is high, the system will be more inclined to believe that the authentication is passed; on the contrary, if the authentication confidence is low, further verification may be required or the authentication may be directly rejected. By determining the authentication confidence, the access control of the access control gate can be effectively realized, thereby improving the accuracy of the access authentication of the access control gate.

[0105] In step 105, the opening of the access gate is controlled based on the authentication confidence.

[0106] In some embodiments, controlling the opening of the access gate based on the authentication confidence level may be achieved by the following steps, namely:

[0107] The authentication confidence is compared with the confidence threshold. If the authentication confidence is greater than the confidence threshold, the access control gate is opened. If the authentication confidence is less than or equal to the confidence threshold, the access control gate issues an authentication abnormality prompt.

[0108] In specific implementation, in the access control system, the calculation result of the authentication confidence will be transmitted to the control logic module in real time. The control logic module compares the confidence value with the confidence threshold preset in the system. The confidence threshold is usually generated by statistical analysis of historical data or machine learning methods to ensure that normal passage and abnormal passage can be distinguished. When the authentication confidence is greater than the confidence threshold, the control logic module sends an opening signal to the execution unit of the access control gate. The execution unit is usually composed of an electronic control module and a mechanical locking device. When the execution unit receives the opening signal, the electronic control module releases the mechanical lock through the motor drive and triggers the physical action of opening the access door, such as the rotation of the gate rod or the sliding of the access control door panel. If the authentication confidence is less than or equal to the confidence threshold, the access control gate will issue an authentication abnormality prompt.

[0109] It should be noted that the confidence threshold in this embodiment is a pre-set standard authentication confidence, which is used to determine whether the target access gate is opened for the current target person to pass. It can be set according to actual needs and is not limited here.

[0110] In addition, another aspect of the present application, in some embodiments, the present application provides a smart campus management system based on the Internet of Things, the smart campus management system based on the Internet of Things includes an access control gate and a monitoring center, the access control gate and the monitoring center are connected through the Internet of Things, and the monitoring center includes an access control control unit, reference Figure 4 , which is a schematic diagram of the structure of an access control unit according to some embodiments of the present application. The access control unit 200 includes: a collection module 201, a processing module 202 and an execution module 203, which are described as follows:

[0111] Collection module 201, in this application, the collection module 201 is mainly used to collect the traffic flow of the target access control gate in the campus area;

[0112] Processing module 202, in this application, is mainly used to predict the passage pressure of the target access control gate under the pedestrian flow state based on the passage flow and the crowd density in the monitoring area of ​​the target access control gate. When the passage pressure exceeds a preset range, the access records of each person waiting to pass through the monitoring area are retrieved from the monitoring center;

[0113] The processing module 202 is further configured to divide each person waiting to pass through the monitoring area according to all access records to obtain multiple person groups, determine the access characteristics corresponding to each person group according to the access information of each person waiting to pass through in each person group when accessing the target access control gate, and set the trust label corresponding to each person group in the monitoring area according to the characteristic differences between the access characteristics;

[0114] In addition, the processing module 202 is further configured to determine, when a target person to be passed in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence level of the access control gate in authenticating the target person to be passed based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust tag of the person group to which the target person to be passed belongs;

[0115] The execution module 203 in this application is mainly used to control the opening of the access control gate based on the authentication confidence.

[0116] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned smart campus access control method.

[0117] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a smart campus access control method according to some embodiments of the present application. The smart campus access control method in the above embodiment can be Figure 5 The computer device 300 shown in FIG. 1 is implemented as shown in FIG. 1 , and the computer device 300 includes at least one processor 301 , a communication bus 302 , a memory 303 , and at least one communication interface 304 .

[0118] The processor 301 can be a general-purpose central processing unit (CPU), or an application specific integrated circuit (ASIC) or one or more processors for controlling the execution of the smart campus access control method in this application.

[0119] The communication bus 302 may be used to transmit information between the aforementioned components.

[0120] Memory 303 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD ROM) or other optical disc storage, an optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. Memory 303 may be independent and connected to processor 301 via communication bus 302. Memory 303 may also be integrated with processor 301.

[0121] Among them, the memory 303 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The determination of the smart campus access control method in the above embodiment can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0122] The communication interface 304 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0123] In a specific implementation, as an example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0124] The aforementioned computer device can be a general-purpose computer device or a dedicated computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of this application do not limit the type of computer device.

[0125] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned smart campus access control method.

[0126] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0127] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A smart campus access control method, characterized in that: The steps include: Collect traffic flow of target access control gates within the campus area; The passage pressure of the target access control gate in a pedestrian flow state is predicted by the passage flow and the crowd density in the monitoring area of ​​the target access control gate. When the passage pressure exceeds a preset range, the access records of each person waiting to pass in the monitoring area are retrieved from the monitoring center; Based on all access records, each person waiting to pass through the monitoring area is divided into multiple groups. The access characteristics corresponding to each group are determined based on the access information of each person waiting to pass through when accessing the target access control gate. The trust labels corresponding to each group in the monitoring area are set based on the feature differences between the access characteristics. When the target person to be passed in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence of the access control gate for the target person to be passed is determined based on the authentication deviation of the target person to be passed in different authentication dimensions and the trust label of the person group to which the target person to be passed belongs; The opening of the access gate is controlled based on the authentication confidence.

2. The method according to claim 1, wherein Predicting the traffic pressure of the target access control gate in a pedestrian flow state based on the traffic flow and the crowd density in the monitoring area of ​​the target access control gate specifically includes: Collect traffic flow data of the target access control gate; Obtaining crowd density data within the monitoring area through monitoring equipment deployed in the monitoring area of ​​the target access control gate; Calculating a dynamic traffic index of people flow in the monitoring area based on the traffic flow data and the people flow density data; The traffic pressure prediction model of the target access control gate under the condition of pedestrian flow is established based on the traffic capacity of the target access control gate; The dynamic traffic index is input as an input parameter into the traffic pressure prediction model, and the traffic pressure prediction model outputs the traffic pressure value of the target access control gate under the pedestrian traffic state.

3. The method according to claim 1, wherein According to all access records, each person waiting to pass through the monitoring area is divided into multiple groups, including: A person waiting to pass through the monitoring area is selected as the selected person waiting to pass through, and the number of access passes and the number of access interceptions are extracted from the access records corresponding to the selected person waiting to pass through; Determining the access trustworthiness of the selected person waiting to pass according to the number of access passes and the number of access interceptions, and continuing to determine the access trustworthiness of the remaining persons waiting to pass; Each person waiting to pass through the monitoring area is projected and clustered through all access trusts, thereby obtaining multiple personnel groups.

4. The method according to claim 1, wherein Determining the access characteristics corresponding to each personnel group according to the access information of each person waiting to pass in each personnel group when accessing the target access control gate specifically includes: Obtain access information of each person waiting to pass in each personnel group when accessing the target access control gate; Standardizing the access information of each person waiting to pass in each person group to obtain standardized access information of each person waiting to pass in each person group; Extracting access parameters under different access dimensions from the standardized access information of each person to be passed; Select a personnel group as the selected personnel group, determine the parameter change of the selected personnel group under the same access dimension based on all access parameters under the same access dimension in the selected personnel group, and then obtain the parameter change of the selected personnel group under different access dimensions; Determine the access characteristics corresponding to the selected personnel group based on the parameter changes under different access dimensions; Continue to determine the access characteristics corresponding to the remaining personnel groups.

5. The method according to claim 1, wherein The trust labels corresponding to each person group in the monitoring area are set by using the feature differences between the access features. Specifically, the following steps are used: Obtain the access characteristics of each personnel group and calculate the feature differences between each access characteristic; Determine the range of each trust level when a person accesses the target access control gate based on all feature differences; The trust level label of each personnel group is set based on the interval range of each trust level and the access characteristics of each personnel group.

6. The method according to claim 1, wherein The authentication confidence of the access control machine for the target person to be passed is determined based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust label of the person group to which the target person to be passed belongs. Specifically, the authentication confidence includes: Obtain authentication information of the target person to be passed under different authentication dimensions; Extracting authentication features of each authentication dimension from the authentication information under each authentication dimension; The authentication features of each authentication dimension are verified for deviation with the corresponding reference authentication features to obtain the authentication deviation of the target person under different authentication dimensions; Determine the authentication loss of the access control gate in authenticating the target person to pass based on all authentication deviations; The authentication confidence of the access control gate in performing pass authentication on the target person to be passed is determined by the authentication loss and the trust label of the person group to which the target person to be passed belongs.

7. The method according to claim 1, wherein The traffic flow of the target access control gate is collected by a camera installed at the target access control gate.

8. A smart campus management system based on the Internet of Things, comprising an access control gate and a monitoring center, wherein the access control gate and the monitoring center are connected via the Internet of Things, and the monitoring center comprises an access control unit, characterized in that: The access control unit comprises: The collection module is used to collect the traffic flow of the target access control gate in the campus area; a processing module configured to predict the passage pressure of the target access control gate under a pedestrian flow state based on the passage flow rate and the crowd density within the monitoring area of ​​the target access control gate, and to retrieve access records of each person waiting to pass through the monitoring area from a monitoring center when the passage pressure exceeds a preset range; The processing module is further configured to divide each person waiting to pass through the monitoring area according to all access records to obtain multiple personnel groups, determine the access characteristics corresponding to each personnel group according to the access information of each person waiting to pass through in each personnel group when accessing the target access control gate, and set the trust label corresponding to each personnel group in the monitoring area according to the characteristic differences between the various access characteristics; The processing module is further configured to determine, when a target person to be passed in the monitoring area reaches the authentication area of ​​the access control gate, the authentication confidence of the access control gate for the target person to be passed based on the authentication deviation of the target person to be passed under different authentication dimensions and the trust tag of the person group to which the target person to be passed belongs; An execution module is used to control the opening of the access control gate based on the authentication confidence.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the smart campus access control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the smart campus access control method according to any one of claims 1 to 7 is implemented.

Images