CN114863506B

CN114863506B - Authentication method, device and system of admission permission and identity authentication terminal

Info

Publication number: CN114863506B
Application number: CN202210270111.9A
Authority: CN
Inventors: 许钢锋; 洪建兵; 赖峰; 曾显光; 张奕煌; 樊一尘
Original assignee: Zhuhai Unitech Power Technology Co Ltd
Current assignee: Zhuhai Unitech Power Technology Co Ltd
Priority date: 2022-03-18
Filing date: 2022-03-18
Publication date: 2023-05-26
Anticipated expiration: 2042-03-18
Also published as: WO2023173785A1; CN114863506A

Abstract

The invention provides a method, a device, a system and an identity authentication terminal for verifying permission, which relate to the technical field of security protection, and the method comprises the following steps: acquiring face characteristics of a face in the view range of a camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; generating admission application information based on the identity recognition result, and sending the admission application information to a remote permission terminal so as to verify whether a target person has admission permission or not through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal; and if receiving the admission indication information sent by the remote permission terminal, controlling the admission of the target personnel. According to the method, on one hand, illegal personnel can be prevented from entering important places through the access control card and the key, on the other hand, the authentication processing capacity can be improved, the recognition efficiency and the accuracy are improved, and the safety of the important places is guaranteed.

Description

Authentication method, device and system of admission permission and identity authentication terminal

Technical Field

The present invention relates to the field of security technologies, and in particular, to a method, an apparatus, a system, and an identity authentication terminal for verifying access rights.

Background

For some important sites, strict control and manager access are required to ensure safety. For example, a transformer substation is an important place in a power grid system, and is a power facility for the power grid system to transform voltage, receive and distribute electric energy, control power flow direction and regulate voltage, and the normal operation of the transformer substation is related to the operation safety of the whole power grid, so that personnel accessing the transformer substation need to be strictly controlled. In the related art, access personnel are generally managed by means of keys, access cards, face recognition and the like. However, the management modes have larger security holes, for example, after an illegal person takes a key or an access card, the illegal person can enter a place to generate security threat to the place; the single-machine processing capability of the face recognition device is limited, so that the recognition efficiency and accuracy are low, the recognition of illegal personnel is omitted, and the safety of important places is still difficult to guarantee.

Disclosure of Invention

Therefore, the invention aims to provide a verification method, a device, a system and an identity authentication terminal of access rights, so as to prevent illegal personnel from entering important places through an access card and a key, improve the processing capacity of authentication, improve the recognition efficiency and accuracy and ensure the safety of the important places.

In a first aspect, an embodiment of the present invention provides a method for verifying an admission right, where the method is applied to an identity authentication terminal, where the identity authentication terminal is in communication connection with a remote permission terminal; the identity authentication terminal stores the identity information of legal personnel issued in advance by the remote permission terminal; the identity authentication terminal is provided with a camera; the method comprises the following steps: acquiring face characteristics of a face in the view range of a camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; generating admission application information based on the identity recognition result, and sending the admission application information to a remote permission terminal so as to verify whether a target person has admission permission or not through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal; and if receiving the admission indication information sent by the remote permission terminal, controlling the admission of the target personnel.

The step of acquiring the face characteristics of the face in the view range of the camera, and identifying the person identity of the target person corresponding to the face characteristics based on the face characteristics and the identity information of legal persons to obtain an identity recognition result comprises the following steps: acquiring an initial frame image shot by a camera, and extracting first texture data of the initial frame image; inputting the first texture data into a pre-trained texture model to detect whether a face exists in an initial frame image through the texture model, and extracting texture feature data of the face if the face exists; and based on the texture feature data and the identity information of legal personnel, identifying the personnel identity of the target personnel corresponding to the face features, and obtaining an identity identification result.

The step of extracting the first texture data of the initial frame image includes: performing feature blurring processing on the initial frame image, and extracting initial texture data of the processed initial frame image; weighting the initial texture data based on preset weight parameters to obtain first texture data; the weight parameters corresponding to the data points of the edge positions in the first texture data are lower than the weight parameters corresponding to the data points except the edge positions in the first texture data.

The texture model is obtained by training in the following way: determining a target sample image based on a preset training sample set; the sample label of the target sample image comprises an identity mark of a human face in the target sample image; extracting texture sample data of a target sample image, inputting the texture sample data into an initial model, and outputting an intermediate result; calculating a loss value based on the intermediate result and the sample label, and updating model parameters of the initial model in a regression test mode based on the loss value; and continuing to execute the step of determining the target sample image based on the preset training sample set until the loss value converges to obtain a texture model.

The step of identifying the personnel identity of the target personnel corresponding to the face features based on the texture feature data and the identity information of the legal personnel to obtain an identity identification result comprises the following steps: comparing the texture feature data with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a first identification result of the target person; extracting face features of a face in a target subsequent frame image of an initial frame image through a deep learning model which is trained in advance; comparing the face characteristics with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a second identification result of the target person; and determining the identity recognition result of the target person based on the first recognition result and the second recognition result.

The step of extracting the face features of the face in the target subsequent frame image of the initial frame image by the deep learning model which is completed through pre-training comprises the following steps: determining the motion trend of a human face in an initial frame image; determining the position of a face in a subsequent frame image of the initial frame image based on the motion trend; determining a subsequent frame image which contains a human face and is a specified frame number from the initial frame image as a target subsequent frame image; and inputting the target subsequent frame image into a pre-trained deep learning model, and outputting the face characteristics of the face in the target subsequent frame image.

The step of determining the identity recognition result of the target person based on the first recognition result and the second recognition result includes: and if the first identification result and the second identification result are different, determining the second identification result as the identity identification result of the target person.

The method further comprises the following steps: if the comparison of the texture feature data and the identity information of legal personnel fails, extracting the face features of the face in the target follow-up frame image of the initial frame image through a deep learning model which is trained in advance; comparing the face characteristics with the identity information of legal personnel; if the comparison of the face features and the identity information of legal personnel fails, the target personnel is determined to be illegal personnel.

The step of generating admission application information based on the identification result and transmitting the admission application information to the remote permission terminal includes: based on a preset data packet format, packaging the identity recognition result as admission application information; the admission application information comprises packet header data and packet body data; the packet header data includes at least: instruction identification, event instruction code type, identification of remote permission terminal and event creation time; the event instruction code is used for indicating the analysis format of the admission application information; the instruction identifier is used for checking whether the admission application information is complete or not; the bag body data comprise an identity recognition result; and sending the admission application information to the remote permission terminal.

The step of controlling the admission of the target personnel if the admission indication information sent by the remote permission terminal is received comprises the following steps: if receiving the admission indication information sent by the remote permission terminal, extracting an instruction identifier from the packet header data of the admission indication information, and checking whether the admission indication information is complete or not based on the instruction identifier; if the admission indication information is complete, extracting event instruction codes from a packet header data body of the admission indication information, and determining an analysis format of the admission indication information based on the event instruction codes; and analyzing inclusion data in the access indication information based on the analysis format to obtain the access indication, and controlling the access of the target personnel based on the access indication.

In a second aspect, an embodiment of the present invention provides an apparatus for verifying an admission right, where the apparatus is disposed at an identity authentication terminal, and the identity authentication terminal is in communication connection with a remote permission terminal; the identity authentication terminal stores the identity information of legal personnel issued in advance by the remote permission terminal; the identity authentication terminal is provided with a camera; the device comprises: the identity recognition module is used for acquiring the face characteristics of the face in the visual field range of the camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; the admission application module is used for generating admission application information based on the identity recognition result, and sending the admission application information to the remote permission terminal so as to verify whether a target person has admission permission or not through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal; and the admission control module is used for controlling the admission of target personnel if the admission indication information sent by the remote permission terminal is received.

In a third aspect, an embodiment of the present invention provides an identity authentication terminal, including a processor and a memory, where the memory stores machine executable instructions executable by the processor, and the processor executes the machine executable instructions to implement the above-mentioned method for verifying admission rights.

In a fourth aspect, the embodiment of the invention provides a verification system of admission authority, which comprises an identity authentication terminal, a remote permission terminal, a mobile communication transmission module, an administrator terminal and a cloud storage platform; the mobile communication transmission module is arranged between the identity authentication terminal and the remote permission terminal and is used for realizing communication between the identity authentication terminal and the remote permission terminal.

The remote permission terminal is used for: receiving admission application information sent by an identity authentication terminal; the admission application information is generated by the identity authentication terminal in the following way: acquiring face characteristics of a face in the view range of a camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; generating admission application information based on the identity recognition result; determining whether a target person corresponding to the admission application information has an admission right or not based on a preset admission condition; and if the access permission exists, sending access indication information to the identity authentication terminal so as to control the access of the target personnel through the identity authentication terminal.

In a fifth aspect, embodiments of the present invention provide a machine-readable storage medium storing machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement a method of verifying admission rights as described above.

The embodiment of the invention has the following beneficial effects:

the authentication method, the authentication device, the authentication system and the authentication terminal of the access permission acquire the face characteristics of the face in the view range of the camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; generating admission application information based on the identity recognition result, and sending the admission application information to a remote permission terminal so as to verify whether a target person has admission permission or not through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal; and if receiving the admission indication information sent by the remote permission terminal, controlling the admission of the target personnel. In the mode, the identity authentication terminal recognizes the identity of a person through a face recognition mode, and the remote permission terminal determines whether the person has access permission or not, so that illegal persons can be prevented from entering important places through the access control card and the key, the authentication processing capability can be improved, the recognition efficiency and the accuracy are improved, and the safety of the important places is guaranteed.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are some embodiments of the invention and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of an example of a hardware scenario provided in an embodiment of the present invention;

fig. 2 is a flowchart of a method for verifying an admission right according to an embodiment of the present invention;

FIG. 3 is a flowchart of another method for verifying access rights according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of interaction among an administrator, an authentication system and an identity authentication terminal according to an embodiment of the present invention;

FIG. 5 is a flowchart of an illegal event reporting and temporary authorization application provided by an embodiment of the present invention;

FIG. 6 is a flowchart of another method for verifying access rights according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of interaction of an administrator with authorization data according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of a verification device for access rights according to an embodiment of the present invention;

fig. 9 is a schematic diagram of an identity authentication terminal or a remote permission terminal according to an embodiment of the present invention.

Fig. 10 is a flowchart of communication between an authentication terminal and a remote permission terminal through a mobile communication transmission module according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

For ease of understanding, the present embodiment will be described with a substation as an example of a place. The transformer substation is an electric power facility for converting voltage, receiving and distributing electric energy, controlling electric power flow direction and regulating voltage of a power grid system, and is a core place of the power grid system. In the related art, the access of substation personnel can be controlled and managed in several ways:

Mode 1, installing a mechanical lock at the entrance of a transformer and distribution station, and keeping a key by a special person; the management is mainly based on oral permission mode, and no personnel entering the substation record information. In addition, since the key does not have an identification function, if some external personnel or illegal personnel take the key, the key can be directly opened to enter the power transformation and distribution station, and no personnel entry record information is left. Therefore, there is a great safety hazard in the way of installing a mechanical lock at the doorway, for example: the legality of personnel entering the transformer substation cannot be defined, for an operator, related conditions in a station room cannot be obtained before the personnel enter and exit the transformer substation, the personnel flow cannot be monitored in real time, the number of the personnel entering the transformer substation cannot be checked, if safety accidents occur in the operation process, the personnel cannot be timely rescued, and the like, and the personnel cannot be traced back when the safety events occur.

In the mode 2, a technical protection system is installed at the entrance of a 110kV/35kV power transformation and distribution station, and arming and disarming are performed by combining a card swiping device with an entrance guard card; for example, a person who has permission to enter the substation is provided with an access control card, and the access control card permission is set to limit the doors which can be opened by the person, so that the access control card has a certain safety guarantee function. However, as the access card and the key are the same, the access card has no identity recognition function, so that anyone can open the door as long as the access card is taken, no personnel enter recorded information, and the problems of the potential safety hazard and difficult tracing during the occurrence of the safety accident are also existed.

Mode 3, based on the deep learning convolutional neural network, establishing a face recognition system; in this way, the single-machine equipment performs face recognition and authentication, which may have the problems of poor single-machine processing capability, limited recognition range, long recognition time and the like, resulting in low face recognition efficiency and accuracy.

Based on the above, the method, the device, the system and the identity authentication terminal for verifying the access right provided by the embodiment of the invention can be used in a substation or other places in a power grid system, can also be applied to a data security room and places of important property, and can be used for verifying the access right in various places.

For the sake of understanding the present embodiment, fig. 1 is an example of a hardware scenario involved in the embodiment of the present invention. The verification system of the permission comprises an identity authentication terminal, a remote permission terminal, a mobile communication transmission module, an administrator terminal and a cloud storage platform; the identity authentication terminal is usually a device arranged at a site gate, and the remote permission terminal can be a server, a computer, a cloud server or a mobile terminal. The identity authentication terminal is provided with a camera, identity judgment is carried out in a face recognition mode, the mobile communication transmission module can be specifically a 5G (5 th Generation Mobile Communication Technology, fifth generation mobile communication technology) transmission network module in fig. 1, and the mobile communication transmission module is generally arranged between the identity authentication terminal and a remote permission terminal and is used for realizing communication between the identity authentication terminal and the remote permission terminal, the remote permission terminal can receive information sent by the identity authentication terminal, and feedback information is sent to the identity authentication terminal, other remote systems and a cloud storage platform after judgment is carried out based on preset conditions. The administrator terminal can be a computer or other mobile terminal equipment, and is used for the administrator to realize operations such as data input, permission change and the like.

In this embodiment, a method for verifying access rights is provided, where the method is applied to an identity authentication terminal, where the identity authentication terminal is in communication connection with a remote permission terminal; the identity authentication terminal stores the identity information of legal personnel issued in advance by the remote permission terminal; the identity authentication terminal is provided with a camera; as shown in fig. 2, the method for verifying the admission authority includes the following steps:

step S201, obtaining face characteristics of a face in a camera view range; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result;

in general, an identity authentication terminal is installed at a doorway of a place, such as a station room doorway of a transformer substation, and is in communication connection with a remote permission terminal, wherein identity information of legal personnel issued in advance by the remote permission terminal is stored in the identity authentication terminal, and the identity information can be, for example, photos of the legal personnel, identity card information or held access card information; the identity authentication terminal is provided with a camera. The identity authentication terminal can control the camera to collect face data of a person in the visual field of the camera.

In one mode, when a target person appears in the view field of the camera, the camera can shoot a face image comprising the target person, and as the face image shot by the camera is a color image and contains overlarge information data, the calculation of the image recognition process is increased, and in addition, the definition of the image is influenced by factors such as illumination intensity, the face image needs to be preprocessed, for example: graying processing, noise reduction processing, compression processing, and the like.

In an alternative approach, the image is grayed out. The image after gray processing is changed from three channels into a single channel, and the dimension reduction processing is carried out on the image, so that the calculated amount can be reduced, and the data processing is convenient. In actual implementation, gray scale processing may have various implementations, for example: component method, maximum method, average method, weighted average method, etc.

In another alternative, the image is noise reduced, and the image is typically contaminated with noise, such as: salt and pepper noise, impulse noise, gaussian noise, etc., wherein salt and pepper noise contains randomly occurring black and white intensity values, impulse noise contains only random white intensity values (positive impulse noise) or black intensity values (negative impulse noise), gaussian noise contains noise whose intensity follows a gaussian or normal distribution, in one way, a multi-directional filter of a derivative of a two-dimensional gaussian function is used to denoise a relevant picture, and a gaussian filter is used to filter the picture in order to eliminate noise interference, so that "sharp" changes in the gray level of the picture can be reduced, i.e. the picture becomes blurred, and it can be understood that each pixel takes the average value of surrounding pixels.

In another alternative mode, the image is compressed, that is, the image data is transformed and combined according to a certain rule, the image is represented by using the smallest data amount as possible, most of the images have larger correlation between adjacent pixels, and the images in the front frame and the rear frame of the sequence have larger correlation, that is, space redundancy and time redundancy are formed, and the problem that the original image data is redundant to cause the waste of bit number can be solved by compressing the images, so that the purpose of data compression is realized.

After preprocessing the pictures, the pictures can be input into a trained face recognition model, and the face features are extracted through the face recognition model.

In one mode, the identity authentication terminal stores identity information of legal personnel issued by the remote permission terminal in advance, and when the remote permission terminal is actually realized, an administrator manages the personnel of the power transformation and distribution station through the administrator terminal, firstly, the personnel allowed to enter and exit the power transformation and distribution station submit registration information to the administrator, and then the administrator stores the registration information of the personnel allowed to enter and exit the power transformation and distribution station to the remote permission terminal. The registration information may include important information related to personnel, such as name, age, gender, unit, photo, identification number, contact information, etc. The legal personnel refer to personnel submitted with registration information and approved by an administrator, and the registration information of the legal personnel is stored in a remote permission terminal and a cloud storage platform. In addition, the remote permission terminal also stores information such as the admittance time and admittance place of legal personnel. If a legal person enters the admittance site at the admittance time, or enters the admittance site at the admittance time, the legal person can be regarded as an illegal person.

After acquiring the face characteristics of a face in the visual field range based on the camera, combining the identity information of legal personnel issued in advance by a remote permission terminal stored in an identity authentication terminal, and identifying the personnel identity of a target personnel corresponding to the face characteristics, wherein if the face characteristics are consistent with one of the legal personnel identity information stored in the identity authentication terminal, the identity recognition result of the personnel is successful; specifically, the identity information of the legal person comprises a photo of the legal person, and if the face features are consistent with the face features in the photo of the legal person, the identity recognition result of the person can be considered to be successful; if the face characteristics of the person are not consistent with any legal person identity information stored in the identity authentication terminal, the identity recognition result of the person fails. In addition, the identification can be performed through other identity information, for example, the identity card information and the access card information of the target person are acquired through related equipment, and if the target person accords with the face characteristics in the photo of a legal person, accords with the identity card information of the legal person and accords with the access card information of the legal person, the identity identification result of the person can be considered to be successful.

Step S202, generating admission application information based on an identity recognition result, and sending the admission application information to a remote permission terminal so as to verify whether a target person has admission permission or not through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal;

in one mode, if the identification result is successful, the identification terminal generates admission application information and sends the admission application information to the remote permission terminal through the mobile communication transmission module. The admission application information comprises a target person name, identification time, a successful identification result of the identity of the target person, time for applying for entering and the like, which are identified by the identity authentication terminal. After receiving the admission application information, the remote permission terminal verifies whether the target personnel has admission permission, if so, the remote permission terminal sends admission indication information to the identity authentication terminal, and if not, the remote permission terminal sends non-admission warning information to the identity authentication terminal.

In addition, if the location state corresponding to the identity authentication terminal does not allow personnel to enter, at the moment, after receiving the admission application information, the remote permission terminal still does not have the admission permission, and then the indication information of refusing the admission is sent to the identity authentication terminal.

In another way, if the identification result fails, for example: the method comprises the steps that an external person enters a working area of a power transformation and distribution station, or a legal person enters an admittance place at a non-admittance time, enters the non-admittance place at the admittance time and enters the non-admittance place at the non-admittance time, at this time, an identity authentication terminal reports an illegal event to a remote permission terminal, the remote permission terminal informs a manager to perform corresponding processing after receiving the reported illegal event, and meanwhile, the remote permission terminal also stores data and records the site situation.

And step S203, if the admission indication information sent by the remote permission terminal is received, controlling the admission of the target personnel.

Specifically, after receiving the admission indication information sent by the remote permission terminal, the identity authentication terminal confirms that the target personnel is legal, and controls the target personnel to admit into the target area. For example, the identity authentication terminal may be connected to a gate, and if the admission indication information is received, the gate is controlled to open, so as to allow the target personnel to enter.

In actual implementation, the remote permission terminal is also in communication connection with an administrator terminal, the administrator terminal can judge the equipment safety of the substation, and if the administrator terminal detects that equipment is electrified or other dangerous conditions, the administrator terminal can send information of refusing to access to the remote permission terminal, and even if the identity recognition is successful, the administrator terminal does not enable target personnel to enter. Based on the method, the related conditions in the station room are acquired before the operator enters the power transformation and distribution station, so that the safety of the operator is improved.

The following embodiment provides a specific implementation manner for acquiring the face characteristics of a face in the view range of a camera, and identifying the personnel identity of a target personnel corresponding to the face characteristics based on the face characteristics and the identity information of legal personnel to obtain an identity identification result.

Acquiring an initial frame image shot by a camera, and extracting first texture data of the initial frame image; inputting the first texture data into a pre-trained texture model to detect whether a face exists in an initial frame image through the texture model, and extracting texture feature data of the face if the face exists; and based on the texture feature data and the identity information of legal personnel, identifying the personnel identity of the target personnel corresponding to the face features, and obtaining an identity identification result.

In general, after a frame image captured by a camera is acquired, the frame image is usually required to be subjected to preprocessing including one or more of graying processing, noise reduction processing, and compression processing. In actual implementation, when a target person appears in the field of view of the camera near the identity authentication terminal, the camera can shoot an image of the target person. When the target person first appears in the image shot in the view range of the camera, the image is the initial frame image, and the initial frame image is preprocessed, for example: graying processing, noise reduction processing, compression processing and the like, and preparation work is carried out for subsequent image segmentation, image recognition and image analysis.

Further, first texture data of the preprocessed initial frame image are extracted, the first texture data can embody texture features of the initial frame image, wherein the texture features are global features, surface properties of a picture or a scene corresponding to a picture region can be described, intra-class differences of textures can be reduced as much as possible by quantifying a certain rule of gray level change or color change in the region, and meanwhile inter-class differences of textures can be increased as much as possible. In actual implementation, a weighted average method is used to take a weighted average of pixel values in a local window or a non-local window of the face picture as an output pixel value. Aiming at the characteristics of regional openness, personnel flow uncertainty and the like of the power transformation and distribution station, in one mode, the bilateral filtering weighting algorithm is adopted to extract texture features, so that the effects of maintaining edges and reducing noise smoothly can be achieved, and the method is well applicable to scenes such as high dynamic tone, mapping, picture detail enhancement and the like.

Further, carrying out feature blurring processing on the initial frame image, and extracting initial texture data of the processed initial frame image; weighting the initial texture data based on preset weight parameters to obtain first texture data; the weight parameters corresponding to the data points of the edge positions in the first texture data are lower than the weight parameters corresponding to the data points except the edge positions in the first texture data.

And setting a weight parameter corresponding to the data point of the edge position in the first texture data, which is lower than the weight parameter corresponding to the data point except the edge position in the first texture data, and based on the weight parameter, abnormal pixel values at the edge can be avoided.

In the mode, the texture model recognizes the face in the image through the texture data of the image, the recognition speed can be improved, the face appearing in the image can be rapidly captured, the missing detection of the face of an illegal person is avoided, and the detection efficiency is improved. The texture model is trained by adopting extracted texture data instead of an initial frame image, the method avoids direct extraction of image features, and the dimension of the feature value of the face can be reduced by half by using weighted operation, so that the recognition efficiency is improved.

The preset training sample set includes a plurality of sample images, the sample images are randomly selected from the training sample set or sequentially selected as the target sample images, the identity of the face included in the target sample images is identified by a sample tag, specifically, the sample tag may include identity information of the face, and through the sample tag, the training model learns the association between the face and the identity information of the face. First, the target sample image is preprocessed. Wherein the preprocessing includes graying processing, noise reduction processing, compression processing, and the like, and extracts texture sample data of the preprocessed target sample image, inputs the texture sample data into the initial model, extracts feature point data of the preprocessed target sample image, and generates an intermediate result based on the feature point data.

After the intermediate result is obtained, the training effect of the initial model is measured through a preset loss function, wherein the loss function is used for representing the difference degree between the prediction and the actual data, namely the difference between the sample label and the intermediate result. Therefore, the smaller the loss function value, the better the training effect of the representative model. In order to achieve the purpose of reducing the loss value, a regression test mode can be adopted to optimize the algorithm, and model parameters of the initial model are updated. And continuing to execute the step of determining the target sample image based on the preset training sample set until the loss value is not changed, and setting the initial model as a texture model.

Considering that the identification accuracy of the texture model is limited, in a specific implementation manner, the texture feature data is compared with the identity information of the legal person, and the identity information successfully compared in the identity information of the legal person is used as a first identification result of the target person; extracting face features of a face in a target subsequent frame image of an initial frame image through a deep learning model which is trained in advance; comparing the face characteristics with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a second identification result of the target person; and determining the identity recognition result of the target person based on the first recognition result and the second recognition result.

For example, by comparing the texture feature data with the identity information of the legal person, the obtained first recognition result is that the target person is the legal person a, and comparing the face feature with the identity information of the legal person, the obtained second recognition result is that the target person is the legal person a, and at this time, the identity recognition result of the target person can be determined to be the legal person a.

In the above process, the step of extracting the face features of the face in the target subsequent frame image of the initial frame image through the pre-trained deep learning model may be specifically implemented by the following manner: determining the motion trend of a human face in an initial frame image; determining the position of a face in a subsequent frame image of the initial frame image based on the motion trend; determining a subsequent frame image which contains a human face and is a specified frame number from the initial frame image as a target subsequent frame image; and inputting the target subsequent frame image into a pre-trained deep learning model, and outputting the face characteristics of the face in the target subsequent frame image.

In actual implementation, the motion trend of the face coordinate under multiple frames can be judged through a tracking algorithm to determine whether the currently locked person is the same person. In actual implementation, if the initial frame image contains a face 1, and the motion difference of the same face in two adjacent frame images is not large, the next frame image of the initial frame image is considered, the face 1 is searched near the position area of the initial frame image in the next frame image, and the searched face is determined as the face 1; meanwhile, the specific position of the face 1 in the next frame image is obtained, and the motion trend of the face can be determined based on the positions of the face 1 in the initial frame image and the next frame image. Based on the motion trend, the position of the face in the subsequent frame image can be deduced.

The target subsequent frame image may be a subsequent frame image that is a specified frame number from the initial frame image, and the specified frame number may be 50 frames, 100 frames, or the like. By the above motion trend, the position of the face 1 in the subsequent frame image of the target can be presumed.

The deep learning model can be obtained by training in the following manner. Specifically, a first sample image is determined based on a preset training set; the first sample tag of the first sample image includes: region identification of the region where the face is located in the first sample image; preprocessing a first sample image, and inputting the preprocessed first sample image into an initial model to obtain a first intermediate result; updating model parameters of the initial model in a gradient descent mode based on the first intermediate result, the first sample label and a preset first loss function; continuing to execute the step of determining the first sample image based on the preset training set until the first intermediate result output by the initial model is converged to obtain a basic model; and training the basic model again based on preset texture sample data to obtain a face recognition model.

The preset training set includes a plurality of groups of training images, sample images are randomly selected from the training set or sequentially selected, and the sample images are used as the first sample images, wherein the first sample images include a face area and a non-face area, the area where the face is located in the first sample images is identified by a first sample tag, for example, the first sample tag may be specifically a rectangular frame, and the image area in the rectangular frame is the area where the face is located. The first sample image is then preprocessed. The preprocessing may include graying processing, scaling processing, and the like, and the preprocessed first sample image is input into the initial model to obtain a first intermediate result. The initial model may be a convolution model or other artificial intelligence model, such as a YOLO neural network model.

After the initial model outputs the first intermediate result, the training effect of the initial model is measured through a preset first loss function, wherein the first loss function is used for representing the difference degree between the prediction and the actual data, namely the difference between the first intermediate result and the first sample label, so that the smaller the first loss function value is, the better the training effect of the model is represented. In order to achieve the purpose of reducing the first loss function value, a gradient descent mode is adopted to optimize the algorithm, and model parameters of the initial model are updated. And continuing to execute the step of determining the first sample image by the preset training set until the first intermediate result output by the initial model is converged, namely, the first loss function value is kept unchanged, setting the initial model as a basic model, and then training the basic model again based on texture sample data to obtain a face recognition model.

In a specific implementation manner, for the preprocessed first sample image, performing deep learning training by using a YOLO neural network, performing compression transformation on the first sample image to obtain an image with 608×608 pixels, performing operation on parameters of the picture pixels, the multiple convolution pooling layers and the full connection layer, and finally outputting a bounding box of the detected face pixels. And solving to obtain a model by a gradient descent method, extracting 1024-dimension characteristic values by using a convolutional neural network, converging the characteristic values of each dimension by using the gradient descent method, and completing basic model manufacture.

Comparing the texture feature data with the identity information of legal personnel to obtain a first identification result; and comparing the face characteristics with the identity information of legal personnel to obtain a second recognition result. Considering that the accuracy of the first recognition result obtained through the texture feature data is limited, if the first recognition result and the second recognition result are different, determining the second recognition result as the identity recognition result of the target person.

After the identity recognition result of the target person is determined, the identity recognition result is sent to the remote permission terminal for authentication, in the process, the deep learning model can be called for multiple times to extract the face characteristics of the target person, the face characteristics are compared with the identity information of legal persons, and if the comparison results are the same legal person, the authentication of the permission is carried out to the remote permission terminal.

Further, if the comparison of the texture feature data and the identity information of legal personnel fails, extracting the face features of the face in the target follow-up frame image of the initial frame image through a deep learning model which is trained in advance; comparing the face characteristics with the identity information of legal personnel; if the comparison of the face features and the identity information of legal personnel fails, the target personnel is determined to be illegal personnel.

Specifically, if the comparison of the texture feature data and the identity information of the legal person fails, the situation that the target person is not the legal person can be primarily judged, at the moment, the comparison is performed again through the face features, if the comparison still fails, the situation that the target person is not the legal person is confirmed, and at the moment, an illegal person event can be reported.

The following embodiments provide specific implementations of a body recognition result.

Specifically, acquiring certificate acquisition information of a target person corresponding to the face characteristics; the certificate acquisition information comprises identity card information and/or access card information; comparing the face characteristics and the certificate acquisition information with the identity information of legal personnel, and taking the successfully compared identity information in the identity information of the legal personnel as the identity recognition result of the target personnel.

In an optional mode, after the identity authentication terminal obtains the face characteristics, the identity authentication terminal also needs to obtain certificate acquisition information of a target person corresponding to the face characteristics; the certificate collection information comprises identity card information and access card information, or the certificate collection information only comprises identity card information, or the collection information only comprises access card information, and the certificate collection information is a physical certificate for a target person to enter an access place. The identity card information needs to be information consistent with the registration information within the effective period, and the access card is a card identifier of an IC card equipped for a target person by a manager after the target person performs real-name registration and the remote permission terminal stores the registration information. Comparing the face characteristics and the certificate acquisition information with the identity information of legal personnel, wherein the identity information of the legal personnel is issued to an identity authentication terminal in advance by a remote permission terminal, the legal personnel is the personnel who perform real-name registration, and the registration information of the legal personnel is stored in the remote permission terminal. In addition, the remote permission terminal also stores information such as the admittance time and admittance place of legal personnel. If a legal person enters the admittance site at the admittance time, or enters the admittance site at the admittance time, the identity of the legal person is lost and becomes an illegal person.

Under the condition, if the identity information of a legal person is corresponding to the face characteristics and the certificate acquisition information in the identity information of the legal person, namely the comparison is successful, the successfully-compared identity information is used as the identity recognition result of the target person.

Under another condition, if the identity information of the legal person does not exist, the identity information successfully compared is determined that the target person is an illegal person, and an image containing the target person is acquired through a camera; and generating alarm information based on the image of the target person, and sending the alarm information to the remote permission terminal.

That is, after the target person swipes the face, the access control card and the identity card are swiped, or only the access control card is swiped or only the identity card is swiped, and if one of the access control card and the identity card does not correspond to the prestored identity information of the legal person, the identity comparison fails, that is, the identity information which is successfully compared does not exist, and the target person is determined to be an illegal person. And then, acquiring a plurality of groups of images comprising the target personnel through the camera, comparing the plurality of groups of images of the target personnel, selecting one or more images which can most highlight the identity characteristics of the target personnel, generating alarm information, and sending the alarm information to the remote permission terminal.

The following embodiments provide specific implementations of sending admission application information.

Specifically, based on a preset data packet format, the identity recognition result is packaged into admission application information; the admission application information comprises packet header data and packet body data; the packet header data includes at least: instruction identification, event instruction code type, identification of remote permission terminal and event creation time; the event instruction code is used for indicating the analysis format of the admission application information; the instruction identifier is used for checking whether the admission application information is complete or not; the bag body data comprise an identity recognition result; and sending the admission application information to the remote permission terminal.

After the identification is successful, the identification result is required to be packaged into admission application information, wherein the admission application information comprises packet header data and packet body data; the packet header data includes at least: instruction identification, event instruction code type, identification of remote permission terminal and event creation time; the instruction identification is named as order ID, the Type is string, the instruction identification is used for checking whether admission application information is complete, UUID (Universally Unique Identifier, universal unique identification Code) is used, the order ID of an instruction with the same inclusion format needs to be consistent in response and reply, the name of an event instruction Code is order Code, the Type is int, the event instruction Code is used for indicating the analysis format of the admission application information, the event instruction Code corresponds to inclusion data, the name of the event instruction Code Type is order Type, the Type is int, and the event instruction Code Type is used for the following events: the name of the identifier of the remote permission terminal is client Type, the Type is int, the identifier can be used for the remote permission terminal and the identity authentication terminal, the name of the event creation Time is create Time, the Type is Date, and the unix timestamp is adopted, so that the accuracy can be achieved. The inclusion data comprises an identity recognition result, and if the identity recognition result is successful, the admission application information is sent to the remote permission terminal. Table 1 below shows the details of the packet format.

TABLE 1

The data packet format indicates the analysis format of the admission application information through the event instruction code, and the instruction identification is used for checking whether the admission application information is complete or not, so that the purpose of data communication can be achieved by only sending one piece of information between communication equipment, the communication quantity is reduced, and the communication efficiency is improved. Meanwhile, the naming code of the communication is contained in the data of the orderCode, the communication content is contained in the eventData format, the final analysis format can be directly determined according to the oederCode when the JSON character string is analyzed, errors can be avoided when the JSON character string is processed according to the instruction sequence, the efficiency of extracting target data from the JSON character string is improved, the instruction set contains the orderID as verification, the information loss caused by the asynchronous communication process can be effectively solved through verification in the mode, the process of deserializing element character strings irrelevant to processing instructions is avoided through the design of the format, the efficiency of extracting the target data from the JSON character string is improved, and meanwhile, the related verification field is designed, so that the purpose of information integrity verification is achieved.

The following embodiments provide a specific implementation of controlling the admission of a target person.

Specifically, if receiving the admission indication information sent by the remote permission terminal, extracting an instruction identifier from the packet header data of the admission indication information, and checking whether the admission indication information is complete or not based on the instruction identifier; if the admission indication information is complete, extracting event instruction codes from a packet header data body of the admission indication information, and determining an analysis format of the admission indication information based on the event instruction codes; and analyzing inclusion data in the access indication information based on the analysis format to obtain the access indication, and controlling the access of the target personnel based on the access indication.

If the identity authentication terminal receives the admission information prompt sent by the remote permission terminal, the admission application indication information comprises packet header data and packet body data, an instruction identifier can be extracted from the packet header data, and whether the admission indication information is complete can be checked through the instruction identifier. In order to achieve the purpose of indicating information integrity, the embodiment provides a transmission protocol, when in communication, a naming code is contained in orderCode data, communication content is contained in a eventDate format, incomplete admission indicating information is avoided, and information loss caused by a communication asynchronous process is effectively solved. Further, an event instruction code is extracted from the packet header data body of the admission instruction information, the analysis format of the admission instruction information is determined according to the event instruction code, the packet body data is obtained from the event instruction code, and the packet body data comprises the operation description of the corresponding data, so that the admission instruction can be obtained through the packet body data. And the identity authentication terminal controls the admission of the target personnel according to the admission prompt.

When the method is actually implemented, after the target personnel is controlled to be admitted, an admission record of the target personnel is sent to a remote permission terminal, wherein the admission record comprises the following steps: identity information of the target person, admission time and admission place. After the identity authentication terminal controls the admission of the target personnel, the admission record of the target personnel is sent to the remote permission terminal, and based on the admission record, the personnel entering in and out of the place corresponding to the identity authentication terminal can be registered, and the admission record comprises: identity information, admission time and admission place of target personnel; the admission record may also be stored to the cloud storage platform. When a safety accident occurs, people in the power transformation and distribution station are timely rescued, and meanwhile follow-up tracing work is convenient to smoothly carry out.

In another way, access to the substation is also obtained for temporary personnel who need access to the substation.

Specifically, acquiring identity information of temporary personnel, and generating a temporary authorization application based on the identity information of the temporary personnel; the temporary authorization application is sent to the remote permission terminal, so that temporary access permission of temporary personnel is issued through the remote permission terminal; and receiving the information of the temporary admittance authority of the temporary personnel, and controlling the admittance of the temporary personnel.

Before entering the target area, temporary personnel need to apply for temporary authorization application to the administrator, and meanwhile, real name registration information including important information related to personnel such as name, age, sex, unit, photo, identity card number, contact mode and the like needs to be submitted to the administrator. Or the temporary personnel submits the registration information to the manager after the remote permission terminal fills in the registration information, the manager examines and verifies the identity information of the temporary personnel after acquiring the identity information of the temporary personnel, generates a temporary authorization application based on the identity information of the temporary personnel after confirming that the temporary personnel has the permission, and sends the temporary authorization application to the remote permission terminal. The remote permission terminal issues the temporary access permission to the identity authentication terminal, and the identity authentication terminal can control the temporary personnel to access after receiving the temporary access permission of the temporary personnel. The temporary access permission comprises information such as access time and access place of temporary personnel. If the temporary personnel does not enter at the admittance time or enter the non-admittance place, the identity authentication terminal generates an illegal event and reports the illegal event to the remote permission terminal, and stores and records the field condition, and simultaneously, the identity authentication terminal sends a notification to the manager terminal.

The following embodiment provides another verification method of access rights, which is applied to a remote permission terminal, wherein the remote permission terminal is in communication connection with an identity authentication terminal; as shown in fig. 3, the method for verifying the admission authority includes:

step S301, receiving admission application information sent by an identity authentication terminal; the admission application information is generated by the identity authentication terminal in the following way: acquiring face characteristics of a face in the view range of a camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; generating admission application information based on the identity recognition result;

after the identity authentication terminal successfully identifies the identity of the target person, the access application information is sent to the remote permission terminal through the mobile communication transmission module. The admission application information is generated by an identity authentication terminal, specifically, when a target person appears in the visual field of the camera, the camera can shoot a face image comprising the target person, the face image is preprocessed and then input into a face recognition model to extract the face feature, the personnel identity of the target person corresponding to the face feature is identified based on the face feature and legal person information which is issued to the identity authentication terminal in advance by a remote permission terminal, and if the identification is successful, the admission application information is generated based on the successful result of the identity identification. The admission application information comprises the name of the target person identified by the identity authentication terminal, the identification time, the successful identification result of the identity of the target person, the time of application for entering and the like.

Step S302, determining whether a target person corresponding to the admission application information has admission permission or not based on preset admission conditions;

and presetting an admission condition at the remote permission terminal, wherein the admission condition comprises the following steps: the access application personnel must be legal personnel which are trained in relevant safety and qualified, the access application time is within the range of the authorized access time, the access application place is the access application place, and the working environment of the target access place when the access application is performed is a safe environment, etc. And the remote permission terminal judges whether a target person corresponding to the admission application information sent by the identity authentication terminal has the admission permission or not according to the preset admission condition.

Specifically, if the admission application information meets the preset admission condition, the target personnel corresponding to the admission application information has the admission authority, and if the admission application information does not meet the preset admission condition, the target personnel corresponding to the admission application information does not have the admission authority.

Step S303, if the access permission is provided, sending access indication information to the identity authentication terminal so as to control the access of the target personnel through the identity authentication terminal.

If the target person corresponding to the admission application information sent by the identity authentication terminal has the admission permission, the remote permission terminal sends admission indication information to the identity authentication terminal, and the admission indication information has various implementation modes, for example: sign indicating information, text indicating information, etc. The admission indication information is used for prompting the identity authentication terminal to control the admission of target personnel.

In another manner, if the target person corresponding to the admission application information sent by the identity authentication terminal does not have the admission permission, the remote permission terminal sends a warning message to the identity authentication terminal, where the warning message has multiple implementation manners, for example: cross symbol warning information, exclamation mark warning information and character warning information. The warning information is used for prompting the identity authentication terminal to prevent the target personnel from admitting, the identity authentication terminal receives the warning information and can acquire image information of the target personnel through the camera to generate warning information, the warning information is sent to the remote permission terminal, the remote permission terminal sends the warning information to the manager terminal, data are stored, and site conditions are recorded. Meanwhile, the remote permission terminal also stores illegal events to the cloud storage platform.

According to the verification method of the access permission, the access condition is preset in the remote permission terminal, whether a target person has the access permission is determined based on the access application information sent by the identity authentication terminal, and the person who is controlled to enter and exit the transformer and distribution station is strictly controlled, so that the safe operation of the transformer and distribution station is ensured.

The following provides a specific implementation manner for determining whether the target personnel corresponding to the admission application information has the admission condition.

Specifically, the admission application information is sent to an administrator terminal, and if an admission instruction of the administrator terminal is received, it is determined that a target person corresponding to the admission application information has an admission condition; or, acquiring the location state of the location corresponding to the identity authentication terminal, and determining whether the target personnel corresponding to the admission application information have the admission condition or not based on the location state.

The remote permission terminal is in communication connection with an administrator terminal; in one mode, after receiving the admission application information sent by the identity authentication terminal, the remote permission terminal sends the admission application information to an administrator terminal, the administrator terminal checks according to the identity information of a target person in the admission application, and if the check is successful, it is determined that the target person corresponding to the admission application information has an admission condition. In another mode, the administrator terminal may obtain a location state of a location corresponding to the identity authentication terminal, and determine whether the target person corresponding to the admission application information has an admission condition according to the location state. For example: if equipment is electrified in the place corresponding to the identity authentication terminal, namely the state of the place is in a dangerous state, even if the target person corresponding to the admission application information is legal, the target person is not admitted. Based on the method, the access condition is determined by detecting the safety information of the place corresponding to the identity authentication terminal in advance, so that a safe operation environment is provided for operators.

Further, the remote permission terminal receives the admission records of the target personnel sent by the identity authentication terminal, and counts the number of the current personnel in the place corresponding to the identity authentication terminal; judging whether the number of the current personnel reaches a preset personnel number threshold value, and if so, setting the place state of the place corresponding to the identity authentication terminal as a first place state; wherein the first venue status is for indicating: the corresponding place personnel of the identity authentication terminal are full, and no admission condition exists.

In one mode, the authentication terminal may send an admission record of the target person to the remote permission terminal, where the admission record includes personnel information that enters a location corresponding to the authentication terminal on the same day before the admission application information is sent, for example: the remote permission terminal receives the admission records of target persons sent by the identity authentication terminal, and calculates and counts the number of current persons in the place corresponding to the identity authentication terminal when the admission application is submitted. Further, a personnel number threshold is preset at the remote permission terminal, and the personnel number threshold represents the maximum value of the personnel number which can be accommodated in the place corresponding to the identity authentication terminal. Comparing the counted current personnel number in the place corresponding to the identity authentication terminal with a preset personnel number threshold, if the counted current personnel number in the place corresponding to the identity authentication terminal is larger than the preset personnel number threshold, the situation that the personnel in the place corresponding to the identity authentication terminal is full, namely the first place state, is indicated, and the place corresponding to the identity authentication terminal does not have an access condition any more.

The remote permission terminal is in communication connection with the cloud storage platform, and further, the access records of the target personnel sent by the identity authentication terminal are received and stored in the cloud storage platform; wherein the admission record comprises: identity information of the target person, admission time and admission place.

In one mode, the cloud storage platform is mainly used for storing and managing data of the substation, for example: data acquisition, picture display, data recording, etc. And after receiving the admission record of the target person sent by the identity authentication terminal, the remote permission terminal stores the admission record in the cloud storage platform. The admission record comprises personnel identity information, admission time, admission place and the like of a place corresponding to the identity authentication terminal. Based on the method, if a security event occurs, the number of people and the personnel information of the place in the dangerous state can be timely judged based on the access information, so that people in the dangerous state can be timely and accurately rescued, and meanwhile, follow-up tracing work is convenient to smoothly carry out.

Further, the remote permission terminal is in communication connection with the cloud storage platform, and if the alarm information sent by the identity authentication terminal is received, the alarm information is sent to a designated administrator terminal; and storing the alarm information to a cloud storage platform. After receiving the alarm information sent by the identity authentication terminal, the remote permission terminal sends the alarm information to a designated administrator terminal, and the administrator processes the alarm information. The number of times of the alarm information of the target personnel can influence the result of the admission application of the target personnel, if the alarm information appears for a plurality of times on a certain target personnel, the target personnel can be judged to be malicious illegal personnel, a blacklist can be added, and the admission application of the target personnel is not passed.

Further, the remote permission terminal is in communication connection with the manager terminal, and if a temporary authorization application sent by the identity authentication terminal is received, the temporary authorization application is sent to the manager terminal; and receiving a confirmation instruction returned by the administrator terminal, and sending the temporary admission permission information of the temporary personnel to the identity authentication terminal. After receiving the temporary authorization application sent by the identity authentication terminal, the remote permission terminal sends the temporary authorization application to an administrator terminal, the administrator checks the identity information of the temporary personnel, judges whether the temporary personnel has access permission, if so, sends a confirmation instruction to the remote permission terminal, and after receiving the confirmation instruction returned by the administrator terminal, the remote permission terminal sends the temporary access permission information of the temporary personnel to the identity authentication terminal.

For easy understanding of the above embodiments, reference may be made to fig. 4, which is a schematic diagram of interaction among an administrator, an authentication system and an authentication terminal. Specifically, an administrator can authorize a target person through an administrator terminal according to real-name registration information of the target person and real-time status of a place, and issue an authorization instruction to an authentication system, firstly, the system converts the authorization instruction into data, converts the data into an instruction set meeting a data packet format, then issues an operation instruction set to an identity authentication terminal through a WebSocket protocol, and after the identity authentication terminal receives the instruction set, extracts instruction information and collects authentication data of the target person, including: and generating an authorization record by the IC card number, the identity card, the face recognition result and the like. And then sending the authorization record to an authentication system, carrying out cloud storage on the authorization record, generating authorization record report data, and sending the authorization record report data to an administrator. Based on the information, the administrator can obtain the identity information and the identity authentication mode information of the target personnel, and display the report data to the target personnel, so that the target personnel can clearly see the access information of the target personnel.

An embodiment of an illegal event and temporary personnel application for temporary authorization is provided below, see fig. 5. Before the operation, the operator needs to swipe a card and swipe a face to finish identity authentication, if the authentication terminal authorization check is not passed, the event is judged to be an illegal event, the illegal event is reported to a remote permission terminal, the remote permission terminal stores data, records the site condition and notifies the manager. For temporary personnel inbound work, temporary authorization is required to be applied to management personnel, the management personnel is checked, the target temporary personnel accords with the access condition and has access permission, the temporary authorization of the temporary personnel is approved, an authorization receipt is sent to a remote permission terminal, the remote permission terminal is sent to an identity authentication terminal, and the access permission is obtained based on the temporary personnel, namely the authorization is successful.

The following embodiment provides another embodiment of the method for verifying the admission authority, which can be seen in fig. 6.

The identity authentication terminal pre-stores the identity information of legal personnel issued by the remote permission terminal, the identity authentication terminal recognizes the legal identity of the target personnel before the target personnel enters the station room, and reports the information of the access personnel, namely the authorization information, to the remote permission terminal, meanwhile, the camera takes a face picture and sends the face picture to the remote permission terminal, based on the face picture, the remote permission terminal can count and analyze the access condition of the station room, store and record the information of the access personnel, and inform the manager terminal of the access condition. In one mode, if a place person corresponding to a certain identity authentication terminal is full, authorization change occurs, that is, even if the target person is a legal person, the admission application cannot pass. The remote permission terminal sends the authorization change information to the identity authentication terminal to achieve the purpose of updating authorization.

FIG. 7 is a schematic diagram of interaction of an administrator with authorization data. The administrator can perform operations such as adding, editing, deleting and the like on the registered data, the authorized records and the like of the personnel. The authorization records may include sites, gate rooms, areas, authorization times, etc. The authorization data is managed on the Web operation platform, and an API (Application Programming Interface, application program interface) interface provided by the cloud is called through an HTTPS (Hyper Text Transfer Protocol over SecureSocket Layer, hypertext transfer security protocol) protocol to store. The cloud service stores the data to the database through ORM (Object Relational Mapping, object relationship mapping) map store. The Web operation platform requests the request header Authorization token for verification on an API interface provided by the cloud service, performs MD5 information abstract algorithm encryption transmission on key data, and stores the key table and key field data in an encryption mode by a database.

The operation system comprises an identity authentication device, a 5G transmission network module, a cloud storage platform and an authentication system, wherein the identity authentication device judges identity in a face recognition mode, the 5G transmission network module provides a 5G network architecture for the identity authentication device, accelerates data transmission rate, reduces network delay, the cloud storage platform is responsible for storing and backing up authentication data, and the authentication system judges personnel access rights; the authentication steps of the system are as follows: the face acquisition module acquires face data, extracts face features locally by establishing 3D face model data, prepares a pre-recognition model in a deep learning mode, improves recognition efficiency, sends an authentication request to the authentication system after identity authentication is completed, recognizes personnel permission, uploads a recognition result through a 5G transmission network module after recognition is completed, and stores records on a cloud storage platform; according to the system, network transmission time is greatly shortened through a 5G network transmission mode, the whole process identification efficiency is improved, meanwhile, a cloud storage platform is deployed at a cloud end, the data security is improved, authentication and authorization are separated through an authentication system, and batch authorization of personnel is achieved.

Corresponding to the above method embodiment, referring to fig. 8, an apparatus for verifying admission rights is provided in an authentication terminal, where the authentication terminal is in communication connection with a remote permission terminal; the identity authentication terminal stores the identity information of legal personnel issued in advance by the remote permission terminal; the identity authentication terminal is provided with a camera; the device comprises:

the identity recognition module 81 is used for acquiring the face characteristics of the face in the view range of the camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result;

the admission application module 82 is configured to generate admission application information based on the identification result, and send the admission application information to the remote permission terminal, so as to verify whether the target person has the admission permission through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal;

and the admission control module 83 is used for controlling the admission of the target personnel if the admission indication information sent by the remote permission terminal is received.

The verification device of the access permission acquires the face characteristics of the face in the view range of the camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics, and obtaining an identity identification result; generating admission application information based on the identity recognition result, and sending the admission application information to a remote permission terminal so as to verify whether a target person has admission permission or not through the remote permission terminal; if the access permission exists, sending access indication information to the identity authentication terminal; and if receiving the admission indication information sent by the remote permission terminal, controlling the admission of the target personnel. In the mode, the identity authentication terminal shoots a face picture through the camera, the face characteristic is obtained through the face recognition model, and then the face characteristic is compared with legal personnel identity information issued by the remote permission terminal in advance to obtain an identity recognition result.

The identity recognition module is further used for: acquiring an initial frame image shot by a camera, and extracting first texture data of the initial frame image; inputting the first texture data into a pre-trained texture model to detect whether a face exists in an initial frame image through the texture model, and extracting texture feature data of the face if the face exists; and based on the texture feature data and the identity information of legal personnel, identifying the personnel identity of the target personnel corresponding to the face features, and obtaining an identity identification result.

The identity recognition module is further used for: performing feature blurring processing on the initial frame image, and extracting initial texture data of the processed initial frame image; weighting the initial texture data based on preset weight parameters to obtain first texture data; the weight parameters corresponding to the data points of the edge positions in the first texture data are lower than the weight parameters corresponding to the data points except the edge positions in the first texture data.

The identity recognition module is further used for training to obtain a texture model through the following modes: determining a target sample image based on a preset training sample set; the sample label of the target sample image comprises an identity mark of a human face in the target sample image; extracting texture sample data of a target sample image, inputting the texture sample data into an initial model, and outputting an intermediate result; calculating a loss value based on the intermediate result and the sample label, and updating model parameters of the initial model in a regression test mode based on the loss value; and continuing to execute the step of determining the target sample image based on the preset training sample set until the loss value converges to obtain a texture model.

The identity recognition module is further used for: comparing the texture feature data with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a first identification result of the target person; extracting face features of a face in a target subsequent frame image of an initial frame image through a deep learning model which is trained in advance; comparing the face characteristics with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a second identification result of the target person; and determining the identity recognition result of the target person based on the first recognition result and the second recognition result.

The identity recognition module is further used for: determining the motion trend of a human face in an initial frame image; determining the position of a face in a subsequent frame image of the initial frame image based on the motion trend; determining a subsequent frame image which contains a human face and is a specified frame number from the initial frame image as a target subsequent frame image; and inputting the target subsequent frame image into a pre-trained deep learning model, and outputting the face characteristics of the face in the target subsequent frame image.

The identity recognition module is further used for: and if the first identification result and the second identification result are different, determining the second identification result as the identity identification result of the target person.

The device further comprises: an illegal personnel determination module for: if the comparison of the texture feature data and the identity information of legal personnel fails, extracting the face features of the face in the target follow-up frame image of the initial frame image through a deep learning model which is trained in advance; comparing the face characteristics with the identity information of legal personnel; if the comparison of the face features and the identity information of legal personnel fails, the target personnel is determined to be illegal personnel.

The admission application module is further configured to: based on a preset data packet format, packaging the identity recognition result as admission application information; the admission application information comprises packet header data and packet body data; the packet header data includes at least: instruction identification, event instruction code type, identification of remote permission terminal and event creation time; the event instruction code is used for indicating the analysis format of the admission application information; the instruction identifier is used for checking whether the admission application information is complete or not; the bag body data comprise an identity recognition result; and sending the admission application information to the remote permission terminal.

The admission control module is further configured to: if receiving the admission indication information sent by the remote permission terminal, extracting an instruction identifier from the packet header data of the admission indication information, and checking whether the admission indication information is complete or not based on the instruction identifier; if the admission indication information is complete, extracting event instruction codes from a packet header data body of the admission indication information, and determining an analysis format of the admission indication information based on the event instruction codes; and analyzing inclusion data in the access indication information based on the analysis format to obtain the access indication, and controlling the access of the target personnel based on the access indication.

The embodiment also provides an identity authentication terminal and a remote permission terminal, wherein the identity authentication terminal or the remote permission terminal comprises a processor and a memory, the memory stores machine executable instructions which can be executed by the processor, and the processor executes the machine executable instructions to realize the verification method of the admission permission of the claims.

Referring to fig. 9, the authentication terminal or remote permission terminal includes a processor 100 and a memory 101, the memory 101 storing machine executable instructions executable by the processor 100, the processor 100 executing the machine executable instructions to implement the above-described authentication method of admission authority.

Further, the authentication terminal and the remote permission terminal shown in fig. 9 further include a bus 102 and a communication interface 103, and the processor 100, the communication interface 103, and the memory 101 are connected through the bus 102.

The memory 101 may include a high-speed random access memory (RAM, random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 103 (which may be wired or wireless), and may use the internet, a wide area network, a local network, a metropolitan area network, etc. Bus 102 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in fig. 9, but not only one bus or one type of bus.

The processor 100 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 100 or by instructions in the form of software. The processor 100 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processor, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and, in combination with its hardware, performs the steps of the method of the previous embodiment.

The embodiment also provides a verification system of the access permission, which comprises an identity authentication terminal, a remote permission terminal, a mobile communication transmission module, an administrator terminal and a cloud storage platform; the mobile communication transmission module is arranged between the identity authentication terminal and the remote permission terminal and is used for realizing communication between the identity authentication terminal and the remote permission terminal.

Taking 5GDTU (Data Transfer Unit, data transmission unit) as an example, for the purpose of understanding, refer to fig. 10.

The identity authentication terminal is provided with reading configuration, establishes communication connection with the 5GDTU, sends data to the 5GDTU through an RJ45 network port, and the 5GDTU and the remote permission terminal communicate wirelessly through 5G so as to proxy and forward the data sent by the identity authentication terminal.

The present embodiment also provides a machine-readable storage medium storing machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the above-described method of verifying admission rights.

The embodiment of the invention provides a method, a device, a system and a computer program product of an access permission verification terminal, which comprise a computer readable storage medium storing program codes, wherein the instructions included in the program codes can be used for executing the method described in the embodiment of the method, and specific implementation can be referred to the embodiment of the method and is not repeated herein.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.

In addition, in the description of embodiments of the present invention, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood by those skilled in the art in specific cases.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an operation and maintenance management device, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

Finally, it should be noted that: the above examples are only specific embodiments of the present invention for illustrating the technical solution of the present invention, but not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the foregoing examples, it will be understood by those skilled in the art that the present invention is not limited thereto: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims

1. The verification method of the admission authority is characterized in that the method is applied to an identity authentication terminal, and the identity authentication terminal is in communication connection with a remote permission terminal; the identity authentication terminal stores the identity information of legal personnel issued by the remote permission terminal in advance; a camera is arranged in the identity authentication terminal; the method comprises the following steps:

acquiring face characteristics of a face in the view range of the camera, and identifying the personnel identity of a target personnel corresponding to the face characteristics based on the face characteristics and the identity information of legal personnel to obtain an identity identification result;

generating admission application information based on the identity recognition result, and sending the admission application information to the remote permission terminal so as to verify whether the target personnel has admission permission or not through the remote permission terminal; if the identity authentication terminal has the access permission, sending access indication information to the identity authentication terminal;

if receiving the admission indication information sent by the remote permission terminal, controlling the admission of the target personnel;

the step of obtaining the face characteristics of the face in the camera view range, identifying the person identity of the target person corresponding to the face characteristics based on the face characteristics and the identity information of the legal person, and obtaining an identity identification result comprises the following steps:

Acquiring an initial frame image shot by the camera, and extracting first texture data of the initial frame image;

inputting the first texture data into a pre-trained texture model to detect whether a face exists in the initial frame image through the texture model, and extracting texture feature data of the face if the face exists;

and identifying the personnel identity of the target personnel corresponding to the face features based on the texture feature data and the identity information of the legal personnel to obtain an identity identification result.

2. The method according to claim 1, wherein the step of extracting the first texture data of the initial frame image comprises:

performing feature blurring processing on the initial frame image, and extracting initial texture data of the processed initial frame image;

weighting the initial texture data based on a preset weight parameter to obtain first texture data; and the weight parameters corresponding to the data points of the edge positions in the first texture data are lower than the weight parameters corresponding to the data points except the edge positions in the first texture data.

3. The method of claim 1, wherein the texture model is trained by:

Determining a target sample image based on a preset training sample set; the sample label of the target sample image comprises an identity mark of a human face in the target sample image;

extracting texture sample data of the target sample image, inputting the texture sample data into an initial model, and outputting an intermediate result;

calculating a loss value based on the intermediate result and the sample label, and updating model parameters of the initial model in a regression test mode based on the loss value;

and continuing to execute the step of determining the target sample image based on the preset training sample set until the loss value converges to obtain the texture model.

4. The method according to claim 1, wherein the step of identifying the person identity of the target person corresponding to the face feature based on the texture feature data and the identity information of the legal person, and obtaining an identity identification result includes:

comparing the texture feature data with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a first recognition result of the target person;

extracting the face characteristics of the face in a target subsequent frame image of the initial frame image through a pre-trained deep learning model;

Comparing the face characteristics with the identity information of the legal person, and taking the successfully compared identity information in the identity information of the legal person as a second recognition result of the target person;

and determining the identity recognition result of the target person based on the first recognition result and the second recognition result.

5. The method of claim 4, wherein the step of extracting face features of the face in a target subsequent frame image of the initial frame image by a pre-trained deep learning model comprises:

determining the motion trend of the human face in the initial frame image;

determining the position of the face in a subsequent frame image of the initial frame image based on the motion trend;

determining a subsequent frame image which contains the face and is a specified frame number away from the initial frame image as a target subsequent frame image;

and inputting the target subsequent frame image into a pre-trained deep learning model, and outputting the face characteristics of the face in the target subsequent frame image.

6. The method of claim 4, wherein the step of determining the identity of the target person based on the first and second recognition results comprises:

And if the first identification result and the second identification result are different, determining the second identification result as the identity identification result of the target person.

7. The method according to claim 4, wherein the method further comprises:

if the comparison of the texture feature data and the identity information of the legal person fails, extracting the face feature of the face in the target subsequent frame image of the initial frame image through a deep learning model which is trained in advance;

comparing the face characteristics with the identity information of the legal person;

and if the comparison of the face features and the identity information of the legal personnel fails, determining the target personnel as illegal personnel.

8. The method of claim 1, wherein generating admission application information based on the identification result, and transmitting the admission application information to the remote licensing terminal, comprises:

based on a preset data packet format, the identity recognition result is packaged into admission application information; the admission application information comprises packet header data and packet body data; the packet header data includes at least: instruction identification, event instruction code type, identification of the remote permission terminal and event creation time; the event instruction code is used for indicating the analysis format of the admission application information; the instruction identifier is used for checking whether the admission application information is complete or not; the inclusion data comprises the identity recognition result;

And sending the admission application information to the remote permission terminal.

9. The method of claim 1, wherein the step of controlling admission of the target person if admission indication information sent by the remote permission terminal is received, comprises:

if receiving the admission indication information sent by the remote permission terminal, extracting an instruction identifier from the packet header data of the admission indication information, and checking whether the admission indication information is complete or not based on the instruction identifier;

if the admission indication information is complete, extracting event instruction codes from a packet header data body of the admission indication information, and determining an analysis format of the admission indication information based on the event instruction codes;

and analyzing inclusion data in the access indication information based on the analysis format to obtain an access indication, and controlling the access of the target personnel based on the access indication.

10. The device is characterized in that the device is arranged at an identity authentication terminal, and the identity authentication terminal is in communication connection with a remote permission terminal; the identity authentication terminal stores the identity information of legal personnel issued by the remote permission terminal in advance; a camera is arranged in the identity authentication terminal; the device comprises:

The identity recognition module is used for acquiring the face characteristics of the face in the visual field range of the camera; based on the face features and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face features to obtain an identity identification result;

the admission application module is used for generating admission application information based on the identity recognition result, and sending the admission application information to the remote permission terminal so as to verify whether the target personnel have admission permission or not through the remote permission terminal; if the identity authentication terminal has the access permission, sending access indication information to the identity authentication terminal;

the admission control module is used for controlling the admission of the target personnel if receiving the admission indication information sent by the remote permission terminal;

the identity recognition module is also used for acquiring an initial frame image shot by the camera and extracting first texture data of the initial frame image; inputting the first texture data into a pre-trained texture model to detect whether a face exists in the initial frame image through the texture model, and extracting texture feature data of the face if the face exists; and identifying the personnel identity of the target personnel corresponding to the face features based on the texture feature data and the identity information of the legal personnel to obtain an identity identification result.

11. An identity authentication terminal comprising a processor and a memory, the memory storing machine executable instructions executable by the processor, the processor executing the machine executable instructions to implement the method of verifying admission rights of any of claims 1-9.

12. The verification system of the access permission is characterized by comprising an identity authentication terminal, a remote permission terminal, a mobile communication transmission module, an administrator terminal and a cloud storage platform;

the mobile communication transmission module is arranged between the identity authentication terminal and the remote permission terminal and is used for realizing communication between the identity authentication terminal and the remote permission terminal;

the remote permission terminal is configured to: receiving admission application information sent by the identity authentication terminal; the admission application information is generated by the identity authentication terminal in the following way: acquiring face characteristics of a face in the view range of a camera; based on the face characteristics and the identity information of legal personnel, identifying the personnel identity of a target personnel corresponding to the face characteristics to obtain an identity identification result; generating admission application information based on the identity recognition result;

Determining whether a target person corresponding to the admission application information has an admission right or not based on a preset admission condition;

if the access permission exists, sending access indication information to the identity authentication terminal so as to control the access of the target personnel through the identity authentication terminal;

the remote licensing terminal is further configured to: acquiring an initial frame image shot by the camera, and extracting first texture data of the initial frame image; inputting the first texture data into a pre-trained texture model to detect whether a face exists in the initial frame image through the texture model, and extracting texture feature data of the face if the face exists; and identifying the personnel identity of the target personnel corresponding to the face features based on the texture feature data and the identity information of the legal personnel to obtain an identity identification result.

13. A machine-readable storage medium storing machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement a method of verifying admission rights according to any one of claims 1-9.