CN114268453A

CN114268453A - Power system unlocking method and device, computer equipment and storage medium

Info

Publication number: CN114268453A
Application number: CN202111362603.2A
Authority: CN
Inventors: 吴金宇; 陶文伟; 胡荣; 张喜铭; 李金�; 高宏慧
Original assignee: China Southern Power Grid Co Ltd
Current assignee: China Southern Power Grid Co Ltd
Priority date: 2021-11-17
Filing date: 2021-11-17
Publication date: 2022-04-01
Anticipated expiration: 2041-11-17
Also published as: CN114268453B

Abstract

The application relates to a power system unlocking method and device, computer equipment and a storage medium. The method comprises the steps that when a user needs to unlock the electric control room door, the to-be-verified identity, the to-be-verified face information, the to-be-verified dynamic face information, the to-be-verified sound information and the to-be-verified fingerprint information of the user are obtained, and the identity authentication result of the to-be-verified user is determined based on the comparison result of the to-be-verified identity and the pre-stored identity, the comparison result of the to-be-verified static face information and the to-be-verified dynamic face information and the pre-stored face information, the comparison result of the to-be-verified sound information and the comparison result of the to-be-verified fingerprint information and the pre-stored fingerprint information, so that whether the to-be-verified user is qualified to unlock the electric control room door is determined. Compared with the traditional verification mode through a simple password, the scheme improves the safety of the power system by determining to unlock the corresponding equipment in the power system when various types of authentication information pass authentication.

Description

Power system unlocking method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of information security technologies, and in particular, to a method and an apparatus for unlocking a power system, a computer device, and a storage medium.

Background

The electric power is energy using electric energy as power, and even in the current internet era, the electric power still has continuously increased demand, because we invent more products using electric power, such as computers, household appliances and the like, the continuous appearance of new technologies can not be denied to enable the electric power to become a necessity of people, a large-scale electric power system is one of the most important achievements in the human engineering science history, and is an electric power production and consumption system formed by links of power generation, power transmission, power transformation, power distribution, power utilization and the like, the control system of the current electric power system is complex, and if a foreign person invades, the great economic loss and potential safety hazard can be caused, so the verification of personnel operating the electric power system is particularly important. The current way of verifying a control room door in the power industry is generally to verify through a password. However, the way of authentication by a simple password is not high in security.

Therefore, the existing unlocking method for the power system has the defect of insufficient safety.

Disclosure of Invention

In view of the above, it is necessary to provide a power system unlocking method, apparatus, computer device and storage medium capable of improving security.

A method of unlocking a power system, the method comprising:

responding to an unlocking instruction based on a door of an electric control room in an electric power system, acquiring a user identifier input by a user to be verified, and simultaneously starting an identity card verification interface, a face verification interface, a voice verification interface and a fingerprint verification interface through verification equipment in the electric power system; the authentication device is disposed in a power control room door of the power system;

inquiring a user database according to the user identification to acquire corresponding pre-stored user information; the pre-stored user information comprises a pre-stored identity mark, pre-stored face information, pre-stored sound information and pre-stored fingerprint information;

acquiring an identity to be verified of a user to be verified based on the identity card verification interface; acquiring static face information to be verified and dynamic face information to be verified of a user to be verified based on the face verification interface; acquiring to-be-verified voice information of a to-be-verified user based on the voice verification interface; the fingerprint verification interface acquires the fingerprint information to be verified of the user to be verified;

and according to a first comparison result of the to-be-verified identity identifier and the prestored identity identifier, a second comparison result of the to-be-verified static face information and the to-be-verified dynamic face information and corresponding types of face information in the prestored face information, a third comparison result of the to-be-verified voice information and the prestored voice information and a fourth comparison result of the to-be-verified fingerprint information and the prestored fingerprint information, performing identity authentication on the to-be-verified user, and sending a door opening instruction to the verification equipment to unlock the electric control room door when the identity authentication is passed.

In one embodiment, the method further comprises:

acquiring an identity card number corresponding to an authenticated user as a pre-stored identity, and acquiring fingerprint information corresponding to the authenticated user as pre-stored fingerprint information;

acquiring sound information emitted by the authenticated user based on a preset verification character as pre-stored sound information, and acquiring image information when the authenticated user emits the pre-stored sound information;

acquiring static face information and dynamic face information corresponding to the authenticated user based on the image information, and taking the static face information and the dynamic face information as prestored face information;

and forming corresponding pre-stored user information of the authenticated user by the pre-stored identity identification, the pre-stored fingerprint information, the pre-stored sound information and the pre-stored face information, and storing the pre-stored user information into a user database.

In one embodiment, the obtaining of the static face information and the dynamic face information corresponding to the authenticated user based on the image information includes:

acquiring an image when the authenticated user does not make a sound from the image information as a static face image;

and acquiring an image when the authenticated user makes a sound from the image information as a dynamic face image.

In one embodiment, after obtaining the static face information and the dynamic face information corresponding to the authenticated user based on the image information, the method further includes:

performing graying processing and normalization processing on the static face information and the dynamic face information to obtain processed static face information and processed dynamic face information;

inputting the processed static face information and the processed dynamic face information into a preset face recognition model, and acquiring static face image characteristics corresponding to the static face information and dynamic face image characteristics corresponding to each piece of processed dynamic face information;

extracting mouth feature data in the dynamic human face image features aiming at each dynamic human face image feature; the mouth feature data represents change data of a preset position on the mouth of the human face in the dynamic human face image features;

establishing a coordinate system based on the plurality of mouth feature data, and determining the coordinates of the mouth feature data in the coordinate system according to the acquisition time of the mouth feature data;

obtaining a face image function corresponding to the position transformation of the mouth feature data based on the coordinate fitting of the plurality of mouth feature data;

and taking the static face image characteristics, the dynamic face image characteristics and the face image function as prestored face information.

In one embodiment, the performing identity authentication on the user to be authenticated according to a first comparison result between the identity to be authenticated and the pre-stored identity, a second comparison result between the static face information to be authenticated and the dynamic face information to be authenticated and face information of a corresponding type in the pre-stored face information, a third comparison result between the voice information to be authenticated and the pre-stored voice information, and a fourth comparison result between the fingerprint information to be authenticated and the pre-stored fingerprint information includes:

acquiring a first similarity between the identity to be verified and the prestored identity as a first comparison result;

acquiring second similarity between the static face information to be verified and the dynamic face information to be verified and corresponding types of face information in the prestored face information respectively as a second comparison result;

acquiring a third similarity of the voice information to be verified and the prestored voice information as a third comparison result;

acquiring a fourth similarity between the fingerprint information to be verified and the prestored fingerprint information as a fourth comparison result;

and if the first comparison result is greater than a first similarity threshold, the second comparison result is greater than a second similarity threshold, the third comparison result is greater than a third similarity threshold, and the fourth comparison result is greater than a fourth similarity, determining that the user to be verified passes the identity authentication.

In one embodiment, the obtaining the second similarities between the static face information to be verified and the dynamic face information to be verified and the corresponding types of face information in the pre-stored face information respectively includes:

performing graying processing and normalization processing on the static face information to be verified and the dynamic face information to be verified to obtain processed static face information to be verified and a plurality of processed dynamic face information;

inputting the processed to-be-verified static face information and the processed dynamic face information into the preset face recognition model, and acquiring to-be-verified static face image features corresponding to the to-be-verified static face information and to-be-verified dynamic face image features corresponding to each processed to-be-verified dynamic face information;

acquiring a first Euclidean distance between the static face image features to be verified and the static face image features corresponding to the user identification, and acquiring a second Euclidean distance between each dynamic face image feature to be verified and the dynamic face image features corresponding to the user identification to obtain a plurality of second Euclidean distances;

if the first Euclidean distance is smaller than a first distance threshold value and the second Euclidean distances are smaller than second distance threshold values, extracting feature data of a mouth to be verified in the dynamic human face image features to be verified;

and acquiring the function similarity of the plurality of mouth feature data to be verified and the face image function corresponding to the user identification as the second similarity.

In one embodiment, the method further comprises:

if the number of times that the identity authentication result of the user to be verified is failed is larger than a preset number threshold, closing the identity card authentication interface, the face authentication interface, the voice authentication interface and the fingerprint authentication interface until the preset time is reached, and then starting again; the preset time threshold is in negative correlation with the restart time; the preset time is positively correlated with the number of times of restarting.

A power system unlocking device, the device comprising:

the first acquisition module is used for responding to an unlocking instruction based on a door of an electric control room in the electric power system, acquiring a user identifier input by a user to be verified, and simultaneously starting an identity card verification interface, a face verification interface, a voice verification interface and a fingerprint verification interface through verification equipment in the electric power system; the authentication device is disposed in a power control room door of the power system;

the second acquisition module is used for inquiring the user database according to the user identification and acquiring corresponding pre-stored user information; the pre-stored user information comprises a pre-stored identity mark, pre-stored face information, pre-stored sound information and pre-stored fingerprint information;

the third acquisition module is used for acquiring the identity to be verified of the user to be verified based on the identity card verification interface; acquiring static face information to be verified and dynamic face information to be verified of a user to be verified based on the face verification interface; acquiring to-be-verified voice information of a to-be-verified user based on the voice verification interface; the fingerprint verification interface acquires the fingerprint information to be verified of the user to be verified;

and the authentication module is used for performing identity authentication on the user to be authenticated according to a first comparison result of the to-be-authenticated identity identifier and the pre-stored identity identifier, a second comparison result of the to-be-authenticated static face information and the to-be-authenticated dynamic face information and corresponding types of face information in the pre-stored face information, a third comparison result of the to-be-authenticated sound information and the pre-stored sound information, and a fourth comparison result of the to-be-authenticated fingerprint information and the pre-stored fingerprint information, and sending a door opening instruction to the authentication equipment to unlock the electric control room door when the identity authentication is passed.

A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.

A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.

The power system unlocking method, the device, the computer equipment and the storage medium acquire the identity to be verified, the face information to be verified, the dynamic face information to be verified, the voice information to be verified and the fingerprint information to be verified of the user when the user triggers the unlocking instruction to the power control room door, and acquiring various pre-stored user information based on the user identification, and determining the identity authentication result of the user to be authenticated based on the comparison result of the identity identification to be authenticated and the pre-stored identity identification, the second comparison result of the static face information to be authenticated and the dynamic face information to be authenticated with the face information of the corresponding type in the pre-stored face information, the third comparison result of the sound information to be authenticated and the pre-stored sound information, and the fourth comparison result of the fingerprint information to be authenticated and the pre-stored fingerprint information, so as to determine whether the user to be authenticated is qualified to unlock the electric control room door. Compared with the traditional verification mode through a simple password, the scheme improves the safety of the power system by determining to unlock the corresponding equipment in the power system when various types of authentication information pass authentication.

Drawings

FIG. 1 is a diagram of an application environment of a power system unlocking method in one embodiment;

FIG. 2 is a flow diagram illustrating a method for unlocking a power system in one embodiment;

FIG. 3 is a flow chart illustrating a method for unlocking a power system in another embodiment;

FIG. 4 is a block diagram of an unlocking device for a power system according to an embodiment;

FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The power system unlocking method provided by the application can be applied to the application environment shown in fig. 1. Among other things, the terminal 102 may communicate with a power control chamber door in a power system. The terminal 102 may obtain a user identifier input by a user, start a corresponding verification interface through verification equipment in the power system, and obtain pre-stored user information corresponding to the user and a plurality of user information to be verified of the user when the user triggers an unlocking instruction of the power control room door, and the terminal 102 may determine whether the user is qualified to unlock the power control room door based on a comparison result between the obtained plurality of user information and corresponding information in the pre-stored user information. In some embodiments, the system further includes a server 104, the terminal 102 communicates with the server 104 through a network, and after the terminal 102 can obtain the user identifier of the user, the terminal can send a query instruction to the server 104, so that the server 104 can obtain the pre-stored user information corresponding to the user identifier from the user database and send the pre-stored user information to the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, a power system unlocking method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:

step S202, responding to an unlocking instruction based on a door of an electric control room in an electric power system, acquiring a user identification input by a user to be verified, and simultaneously starting an identity card verification interface, a face verification interface, a voice verification interface and a fingerprint verification interface through verification equipment in the electric power system; the authentication device is disposed in a power control room door of a power system.

The power system may be a system including a plurality of power devices, and in order to ensure the safety of the plurality of power devices in the power system, it is necessary to set a device for limiting access for the power system, for example, a power control room door in the power system, where the power control room door may be an access device set in the power system, and the device may be set at an entrance and exit of a space such as the power control room, and may be used to control access rights of people needing to enter and exit. Corresponding verification equipment can be arranged in the electric control room door, and can be used for carrying out identity authentication and identification on personnel needing to enter and exit and determining whether the personnel are qualified to enter the electric control room. The terminal 102 may obtain a user identifier, such as a user name, input by a user to be authenticated after receiving an unlocking instruction for the door of the power control room, which is triggered by the user to be authenticated, and start an identity authentication interface, a face authentication interface, a voice authentication interface, and a fingerprint authentication interface on an authentication device in the power system at the same time. Each verification interface can collect the information of the user to be verified of the type corresponding to the user to be verified, so that the terminal 102 can form the verification interface based on the collected information of the plurality of users to be verified, and verify the unlocking authority of the user to be verified. The terminal 102 may authenticate the user to be authenticated through the inspection program, for example, an unlocking interface may be set in the inspection program, and after the unlocking instruction is triggered, the terminal 102 may edit the unlocking program, which includes an identity authentication program interface, a face recognition authentication program interface, a voice recognition authentication program interface, a fingerprint recognition authentication program interface, and the like. Wherein the verification program may be stored in a memory module of the terminal 102, which may be carried by a verification processor, such as a verification processor provided in the terminal 102.

Step S204, inquiring a user database according to the user identification to acquire corresponding pre-stored user information; the pre-stored user information comprises pre-stored identity identification, pre-stored face information, pre-stored sound information and pre-stored fingerprint information.

The user identifier may be an identifier, such as a name of the user, of the input terminal 102 after the user triggers an unlocking instruction for the power control chamber door. The terminal 102 may query the user database based on the user identifier, so that the terminal 102 may obtain pre-stored user information corresponding to the user identifier from the user database, where the pre-stored user information may include a pre-stored identity identifier, pre-stored face information, pre-stored voice information, pre-stored fingerprint information, and the like of the user, and thus the terminal 102 may use the pre-stored user information to authenticate whether the user to be verified is qualified to unlock the power control room door. The pre-stored user information may be user information of a valid user, for example, the terminal 102 collects information such as an identity, face information, voice information, and fingerprint information of a worker of the power system in advance by using the verification device, and stores the information in the memory as the pre-stored user information of the worker.

For example, when collecting pre-stored information of workers, the workers can input the identity cards, the faces, the voice and the fingerprints into corresponding programs in the system at the same time to form a primary file corresponding to each worker; the staff can also input their identity card, face, voice and fingerprint again and enter the corresponding program of the system at the same time, the terminal 102 can check, the initial file is converted into the final file after confirming without error. In order to avoid the situation that information of different employees is mixed together to cause information confusion and influence use, the terminal 102 can store final files containing pre-stored user information of the employees in a separate memory, and the memory can be connected with an automatic storage battery starting program.

Step S206, acquiring the identity to be verified of the user to be verified based on the identity card verification interface; acquiring static face information to be verified and dynamic face information to be verified of a user to be verified based on a face verification interface; acquiring to-be-verified voice information of a to-be-verified user based on a voice verification interface; and acquiring the fingerprint information to be verified of the user to be verified based on the fingerprint verification interface.

After the terminal 102 starts the identification card verification interface, the face verification interface, the voice verification interface and the fingerprint verification interface through the verification device in the power system, the user information to be verified of the corresponding type can be acquired based on each verification interface. For example, the terminal 102 may obtain an identity to be authenticated of the user to be authenticated based on the authentication interface; acquiring static face information to be verified and dynamic face information to be verified of a user to be verified based on a face verification interface; acquiring to-be-verified voice information of a to-be-verified user based on a voice verification interface; and acquiring the fingerprint information to be verified of the user to be verified based on the fingerprint verification interface. For example, when the user makes a voice, the terminal 102 may simultaneously acquire the voice information and the dynamic face information of the user as information to be verified. The terminal 102 may form a corresponding password authentication interface based on the collected information to be authenticated, for example, the user to be authenticated may input an identity card, a face, a voice, and a fingerprint on the corresponding authentication interface to form a password authentication interface, so that the terminal 102 may perform identity authentication on the user to be authenticated based on each item of information in the password authentication interface. Wherein, above-mentioned user's ID card, sound and fingerprint can be inputed through the input device, and user's face can be inputed by the camera to be convenient for input ID card, face, sound and fingerprint.

And S208, according to a first comparison result of the to-be-verified identity identifier and the pre-stored identity identifier, a second comparison result of the to-be-verified static face information and the to-be-verified dynamic face information and corresponding types of face information in the pre-stored face information, a third comparison result of the to-be-verified voice information and the pre-stored voice information and a fourth comparison result of the to-be-verified fingerprint information and the pre-stored fingerprint information, performing identity authentication on a user to be verified, and sending a door opening instruction to the verification equipment to unlock the electric control room door when the identity authentication is passed.

The terminal 102 may compare the acquired user information to be verified with pre-stored information corresponding to each item in the pre-stored user information, so as to determine whether the user is qualified to unlock the power control room door. For example, the terminal 102 may compare the identity to be verified with a pre-stored identity to obtain a first comparison result; comparing the static face information to be verified and the dynamic face information to be verified with corresponding types of face information in prestored face information respectively to obtain a second comparison result; comparing the voice information to be verified with prestored voice information to obtain a third comparison result; and comparing the fingerprint information to be verified with the prestored fingerprint information to obtain a fourth comparison result. Therefore, the terminal 102 can perform identity authentication on the user to be verified based on the first comparison result, the second comparison result, the third comparison result and the fourth comparison result, and determine that the user has the authority to unlock the door of the power control room when the identity authentication is passed, so that the terminal 102 can send a door opening instruction to the verification device, and the verification device unlocks the door of the power control room after receiving the door opening instruction. Specifically, can be provided with the trick lock on the electric control room door, the battery automatic start-up procedure can start the battery, supplies power to the trick lock, and the trick lock can't work when avoiding having a power failure, and verification equipment can be through the mode unblock electric control room door of opening the trick lock.

Wherein, each comparison result may be a comparison result based on the similarity. The terminal 102 may allow the power control room door to be opened only if the above comparison results pass. For example, in an embodiment, performing identity authentication on a user to be authenticated according to a first comparison result between an identity to be authenticated and a pre-stored identity, a second comparison result between static face information to be authenticated and dynamic face information to be authenticated and face information of a corresponding type in the pre-stored face information, a third comparison result between voice information to be authenticated and the pre-stored voice information, and a fourth comparison result between fingerprint information to be authenticated and pre-stored fingerprint information, includes: acquiring a first similarity between the identity to be verified and a prestored identity as a first comparison result; acquiring second similarity between the static face information to be verified and the dynamic face information to be verified and face information of a corresponding type in the prestored face information respectively as a second comparison result; acquiring a third similarity of the voice information to be verified and the pre-stored voice information as a third comparison result; acquiring a fourth similarity between the fingerprint information to be verified and the prestored fingerprint information as a fourth comparison result; and if the first comparison result is greater than the first similarity threshold, the second comparison result is greater than the second similarity threshold, the third comparison result is greater than the third similarity threshold, and the fourth comparison result is greater than the fourth similarity, determining that the user to be verified passes the identity authentication. In this embodiment, the terminal 102 may obtain the similarity obtained by the comparison, to obtain a first similarity, a second similarity, a third similarity, and a fourth similarity, and the terminal 102 may set a corresponding similarity threshold for each comparison, where when the similarity is greater than or equal to the similarity threshold corresponding to the comparison, the comparison result is passed, and when the terminal 102 detects that the similarity obtained by the comparison is greater than the similarity threshold corresponding to the comparison, it may be determined that the user to be verified passes the identity authentication, for example, when the terminal 102 detects that the identity card, the face, the voice, and the fingerprint of the user are simultaneously consistent with the information pre-stored in the final file of the system, it may be determined that the lock is unlocked. The similarity thresholds may be the same or different in value. When the face information is compared, the similarity of the fitting function based on the face features can be compared based on the static face information and the dynamic face information.

According to the unlocking method of the power system, when a user triggers an unlocking instruction on a power control room door, the to-be-verified identity, the to-be-verified face information, the to-be-verified dynamic face information, the to-be-verified sound information and the to-be-verified fingerprint information of the user are obtained, various pre-stored user information is obtained based on the user identity, and the identity authentication result of the to-be-verified user is determined based on the comparison result of the to-be-verified identity and the pre-stored identity, the second comparison result of the to-be-verified static face information and the to-be-verified dynamic face information and the corresponding type of face information in the pre-stored face information, the third comparison result of the to-be-verified sound information and the pre-stored sound information, and the fourth comparison result of the to-be-verified fingerprint information and the pre-stored fingerprint information, so that whether the to-be-verified user is qualified to unlock the power control room door is determined. Compared with the traditional verification mode through a simple password, the scheme improves the safety of the power system by determining to unlock the corresponding equipment in the power system when various types of authentication information pass authentication.

In one embodiment, further comprising: acquiring an identity card number corresponding to the authenticated user as a pre-stored identity, and acquiring fingerprint information corresponding to the authenticated user as pre-stored fingerprint information; acquiring sound information emitted by an authenticated user based on a preset verification character as pre-stored sound information, and acquiring image information when the authenticated user emits the pre-stored sound information; acquiring static face information and dynamic face information corresponding to the authenticated user based on the image information, and taking the static face information and the dynamic face information as prestored face information; and forming corresponding pre-stored user information of the authenticated user by the pre-stored identity identification, the pre-stored fingerprint information, the pre-stored sound information and the pre-stored face information, and storing the pre-stored user information into a user database.

In this embodiment, before the terminal 102 authenticates the user to be authenticated, the terminal may collect and store the information of the valid user in advance to form a user database. The terminal 102 may obtain the identification number corresponding to the authenticated user in advance as a pre-stored identification, for example, by an input device, and the terminal 102 may obtain the fingerprint information corresponding to the authenticated user as pre-stored fingerprint information, for example, by a fingerprint collector. The terminal 102 may further obtain sound information emitted by the authenticated user based on the preset verification text as pre-stored sound information, for example, collected by a microphone. The preset verification text may be a text corresponding to the sound wave feature for collecting the user, so that the terminal 102 may form the sound wave feature based on the sound information sent by the authenticated user, and use the sound wave feature as the pre-stored sound information for comparison. When the terminal 102 collects the sound information, the terminal 102 may also collect the pre-stored face information of the user through the camera, the pre-stored face information includes static face information and dynamic face information, the static face information may be a face image of the user when the face is static, and the dynamic face information may be a face image of the user when the face moves. The terminal 102 may form the pre-stored user information corresponding to the authenticated valid user from the pre-stored identity, the pre-stored fingerprint information, the pre-stored voice information, and the pre-stored face information of the valid user, which are collected in advance, and store the pre-stored identity, the pre-stored fingerprint information, the pre-stored voice information, and the pre-stored face information into the user database. The terminal 102 may also extract features of the static face image and the dynamic face in the pre-stored face information in advance, and then store the extracted features in the user database. Therefore, the final file of each authenticated user in the user database prestores the unique identification information of the identity card, the face image feature point information, the self-defined sound content, the sound wave feature information, the fingerprint feature information and the like.

Through the embodiment, the terminal 102 can collect and store the pre-stored user information of the authenticated legal user in advance, so that whether the user to be verified is allowed to open the power control room door or not can be determined based on the comparison result of the pre-stored user information and the user information of the user to be verified, and the safety of the power system is improved.

In one embodiment, obtaining static face information and dynamic face information corresponding to an authenticated user based on image information includes: acquiring an image when the authenticated user does not make a sound from the image information as a static face image; and acquiring an image when the authenticated user makes a voice from the image information as a dynamic face image.

In this embodiment, the image information may be the image information of the authenticated user when the terminal 102 collects the pre-stored sound information of the authenticated user, and may be, for example, a video information. The terminal 102 may obtain a static face image and a dynamic face image corresponding to the authenticated user based on the image information. In the information acquisition and user verification processes, the face verification at least acquires static face images for face recognition, and in order to further improve the verification accuracy, the face verification acquires the static face images and the face images in the sound verification process for face recognition, so that the face recognition accuracy is improved, and the living body detection can be realized. The terminal 102 may acquire, from the video information, an image when the authenticated user does not make a sound as a static face image, and the terminal 102 may acquire, from the video information, an image when the authenticated user makes a sound as a dynamic face image. For example, the terminal 102 may acquire a video of an authenticated worker when inputting sound content and sound wave feature information, extract a static face image of the worker from the video (i.e., an image when the worker does not make a sound), set the static face image as a first face image, the terminal 102 may further extract a dynamic face image when the worker makes a sound, set the dynamic face image as a second face image, and the terminal 102 may extract a node according to sound data because the worker makes a sound with a large number of motions. So that the terminal 102 can obtain a static face image and a plurality of dynamic face images of the authenticated user.

Through the embodiment, the terminal 102 can acquire various types of face images and verify the face images of the user to be verified based on the various types of face images, so that the verification accuracy is improved, and the safety of the power system is also improved.

In one embodiment, after obtaining the static face information and the dynamic face information corresponding to the authenticated user based on the image information, the method further includes: performing graying processing and normalization processing on the static face information and the dynamic face information to obtain processed static face information and processed dynamic face information; inputting the processed static face information and the plurality of processed dynamic face information into a preset face recognition model, and acquiring static face image characteristics corresponding to the static face information and dynamic face image characteristics corresponding to each piece of processed dynamic face information; extracting mouth feature data in the dynamic human face image features aiming at each dynamic human face image feature; the mouth feature data represents change data of a preset position on the mouth of the face in the dynamic face image features; establishing a coordinate system based on the plurality of mouth feature data, and determining the coordinates of the mouth feature data in the coordinate system according to the acquisition time of the mouth feature data; obtaining a face image function corresponding to the position transformation of the mouth feature data based on the coordinate fitting of the plurality of mouth feature data; and taking the static face image characteristics, the dynamic face image characteristics and the face image function as prestored face information.

In this embodiment, when the terminal 102 collects the pre-stored face information of the authenticated user in advance, the collected static face information and dynamic face information may be processed correspondingly, for example, feature extraction processing. The terminal 102 may perform graying processing and normalization processing on the pre-collected static face information, and perform graying processing and normalization processing on the pre-collected multiple dynamic face information to obtain processed static face information and multiple processed dynamic face information. The terminal 102 may input the processed static face information and the plurality of processed dynamic face information into a preset face recognition model, so as to obtain a static face image feature corresponding to the static face information output by the preset face recognition model and a dynamic face image feature corresponding to each piece of dynamic face image information. For example, the preset face recognition model may be a face recognition model based on a VGG16 neural network, the static face information may be a first face image, the dynamic face information may be a second face image, and the terminal 102 may perform image preprocessing on the first face image and the second face image, including converting the first face image and the second face image into a gray scale image and performing normalization operation; training a face recognition model based on a VGG16 neural network; and inputting the preprocessed first face image and the preprocessed second face image into a face recognition model, and outputting a static face image characteristic serving as a first face image characteristic and a dynamic face image characteristic serving as a second face image characteristic.

The terminal 102 extracts the mouth feature data of the user in each dynamic face image feature. The mouth feature data may be a change position of a preset position on the mouth of the face in the dynamic face image feature of the user, for example, a plurality of acquisition points are set on the mouth of the user in advance, and when the user speaks, the position of the preset acquisition point on the mouth changes, so that the terminal 102 may record corresponding data of the change of the position of the acquisition point as the mouth feature data. The terminal 102 may establish a coordinate system based on a plurality of mouth feature data, and determine coordinates of the mouth feature data in the coordinate system according to the acquisition time of the mouth feature data. For example, in the dynamic face image features corresponding to the multiple pieces of dynamic face information, the positions of the same acquisition points in each dynamic face image may be different, so that the terminal 102 may determine the coordinates of the mouth feature data in the coordinate system based on the acquisition time of the acquisition points. After determining the coordinates of each mouth feature data in the coordinate system, the terminal 102 may obtain a face image function corresponding to the mouth feature data position transformation based on coordinate fitting of a plurality of mouth feature data. Therefore, the terminal 102 may store the extracted static face image features, dynamic face image features, and the fitted face image function as pre-stored face information. For example, the terminal 102 may extract feature data of the mouth from data of a second face image feature representing a dynamic face image feature, establish a coordinate system, obtain coordinates of the feature data of the mouth in the coordinate system according to a time sequence, fit a function corresponding to the position transformation of the feature data of each mouth, and the terminal 102 may further screen out a function whose coordinate position transformation is smaller than a set value, and obtain a face image function; and finally, pre-storing the first human face image characteristic, the second human face image characteristic and the human face image function in the system.

Through the embodiment, the terminal 102 can extract corresponding face image features from the face information acquired in advance and fit the face image function, so that the unlocking permission of the electric control room door of the user to be verified can be identified based on the face image features and the face image function, and the safety of the electric power system is improved.

In one embodiment, obtaining second similarities between the static face information to be verified and the dynamic face information to be verified and corresponding types of face information in the pre-stored face information respectively comprises: performing graying processing and normalization processing on the static face information to be verified and the dynamic face information to be verified to obtain processed static face information to be verified and a plurality of processed dynamic face information; inputting the processed static face information to be verified and the plurality of processed dynamic face information into a preset face recognition model, and acquiring the static face image characteristics to be verified corresponding to the static face information to be verified and the dynamic face image characteristics to be verified corresponding to each processed dynamic face information to be verified; acquiring a first Euclidean distance between a static face image feature to be verified and a static face image feature corresponding to a user identifier, and acquiring a second Euclidean distance between each dynamic face image feature to be verified and a dynamic face image feature corresponding to the user identifier to obtain a plurality of second Euclidean distances; if the first Euclidean distance is smaller than the first distance threshold value and the second Euclidean distances are smaller than the second distance threshold value, extracting feature data of a mouth to be verified in the dynamic human face image features to be verified; and acquiring the function similarity of the plurality of mouth feature data to be verified and the face image function corresponding to the user identification as a second similarity.

In this embodiment, the terminal 102 may collect static face information to be verified and dynamic face information to be verified of a user to be verified in actual verification, and compare similarity with corresponding face information in pre-stored face information based on a plurality of kinds of collected face information. For the collected to-be-verified static face information and to-be-verified dynamic face information of the to-be-verified user, the terminal 102 may perform graying processing and normalization processing on the to-be-verified static face information, and perform graying processing and normalization processing on the multiple to-be-verified dynamic face information, to obtain processed to-be-verified static face information and multiple processed dynamic face information. The terminal 102 may input the processed to-be-verified static face information and the plurality of processed dynamic face information into the trained preset face recognition model, and obtain a to-be-verified static face image feature corresponding to the to-be-verified static face information output by the preset face recognition model and a to-be-verified dynamic face image feature corresponding to each piece of to-be-verified dynamic face information. The preset face recognition model may be a face recognition model based on a VGG16 neural network.

After the terminal 102 extracts the static face image features to be verified and the dynamic face image features to be verified, in comparison with the prestored face information, the terminal 102 may obtain a first euclidean distance between the static face image features to be verified and the static face image features in the prestored face information corresponding to the user identifier of the user to be verified, and the terminal 102 may further obtain a second euclidean distance between each dynamic face image feature to be verified and the dynamic face image features corresponding to the user to be verified, so as to obtain a plurality of second euclidean distances. For example, in the dynamic face image to be verified, the acquisition point of the mouth feature data of the user to be verified may correspond to the mouth acquisition point in the dynamic face image in the pre-stored face information corresponding to the user identifier, so that the terminal 102 may acquire the euclidean distance between the two acquisition points based on the corresponding acquisition points. The euclidean distance is a commonly used distance definition, and refers to the real distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance from the point to the origin). The euclidean distance in two and three dimensions is the actual distance between two points. The terminal 102 may determine the similarity between the image features based on the first euclidean distance and the second euclidean distance acquired above. The terminal 102 may compare the first euclidean distance with the first distance threshold, if the first euclidean distance is smaller than the first distance threshold and the plurality of second euclidean distances are smaller than the second distance thresholds, the terminal 102 may determine that the to-be-verified static face image feature and the to-be-verified dynamic face image feature meet the requirements, and when the first euclidean distance is greater than the first distance threshold or one of the second euclidean distances is greater than the second distance threshold, the terminal 102 may determine that the to-be-verified static face image feature or the to-be-verified dynamic face image feature do not meet the requirements, and may stop verification. The terminal 102 may extract the mouth feature data to be verified from the plurality of dynamic face images to be verified after both the static face image features to be verified and the dynamic face image features to be verified meet requirements, so that the terminal 102 may obtain the function similarity of the mouth feature data to be verified and the face image function pre-stored corresponding to the user identifier of the user to be verified, as the second similarity. Then when the second similarity is greater than the second similarity threshold, the terminal 102 may determine that the face verification of the user to be verified passes.

For example, when a user to be authenticated needs to unlock and open a door of the power control room, the terminal 102 may obtain a video of a worker to be authenticated when voice is authenticated, extract an image from the video, input a face recognition model after preprocessing, obtain face features of the worker, calculate euclidean distances between the face features and first face image features and between the face features and second face image features respectively, obtain similarity, extract feature data of a mouth of the worker when the terminal 102 detects that the similarity exceeds a set threshold, determine whether the mouth is matched with a face image function, and if so, the terminal 102 may determine that face authentication passes.

Through the embodiment, the terminal 102 can perform face verification on the user to be verified based on the comparison result of the extracted features of the face image of the user to be verified and the pre-stored face image features and the comparison result of the face image function to be verified of the user to be verified and the pre-stored face image function, so that the safety of the power system can be improved.

In one embodiment, further comprising: if the number of times that the identity authentication result of the user to be verified is failed is larger than the preset number threshold, closing the identity card authentication interface, the face authentication interface, the voice authentication interface and the fingerprint authentication interface until the preset time is reached, and then starting again; the preset time threshold is in negative correlation with the time of restarting; the preset time is positively correlated with the number of restarts.

In this embodiment, when the terminal 102 verifies the unlocking permission of the electric control room door for the user to be verified, the electric control room door of the electric power system is allowed to be unlocked only after the identity card, the face, the voice and the fingerprint are verified, when one verification fails, the terminal 102 may not allow unlocking, and the terminal 102 may be provided with an alarm interface. If the terminal 102 detects that the number of times that the authentication result of the user to be verified fails is greater than the preset number threshold, the terminal 102 may close the started identity card verification interface, the face verification interface, the voice verification interface and the fingerprint verification interface, and restart the terminal after the closing time reaches the preset time. After the startup, the terminal 102 may reacquire the information to be verified input by the user to be verified on each interface, and perform verification again, and if the information still fails, continue to execute the process of closing the interface and then opening the interface, and the preset threshold of the number of times allowed to be input is reduced as the number of times of restarting increases, and the preset time of closing the interface is increased as the number of times of restarting increases.

For example, the identity card, the face, the voice and the fingerprint information may form a password authentication interface, the terminal 102 may edit an alarm program, that is, set the number n of times of inputting the verification password authentication interface, and when the number of times of inputting the password authentication interface is equal to n times and all the times are input incorrectly, the system may be automatically locked and the password authentication interface may not be input again within a certain time t for verification and unlocking; and after the time tmin is reached, the password authentication interface can be input again for verification and unlocking, the number of times n-1 of inputting the verification password authentication interface is reduced, when the number of times of inputting the password authentication interface is equal to n-1 and all the times are input wrongly, the system can be automatically locked and can not input the password again for unlocking within a certain time t +5min, and recursion is carried out in sequence until the number of times of inputting the password is equal to 1 and the input mistake is caused, the system is permanently locked and needs to be returned to the factory for resetting. The n and t may be set according to actual conditions, for example, n is 5, and t is 1. When the verification is wrong, the alarm program can also give an alarm sound, so that related workers are reminded of inputting errors.

Through the embodiment, the terminal 102 can take corresponding alarm and blocking measures when detecting that the authentication fails, so that the safety of the power system can be improved.

In one embodiment, as shown in fig. 3, fig. 3 is a schematic flow chart of a power system unlocking method in another embodiment. The method comprises the following steps: the terminal 102 may perform identification card recognition, face recognition, voice recognition, and fingerprint recognition on the user to be authenticated. The terminal 102 can set an unlocking interface, and obtain the identity card, the face, the voice and the fingerprint of the inputted company staff needing to be verified to form a password authentication interface, the terminal 102 can detect whether the identity card, the face, the voice and the fingerprint simultaneously meet the requirement of being consistent with the information prestored in the system, if so, the terminal 102 can open the lock of a door of an electric control room in the electric system, otherwise, the terminal 102 can also set an alarm interface, when the verification fails and the number of times of mistakes made by the company staff to be verified reaches n times, the terminal 102 can lock the verification program, and the terminal 102 is unlocked after t time, so that the company staff can input the information to be verified again to form the password authentication interface to enable the terminal 102 to be verified.

Through the embodiment, the terminal 102 can be unlocked only by setting four authentication modes, namely the identity card, the human face, the voice and the fingerprint, and if the four authentication modes are correct, the system can be started to lock the program if the password is input for many times, so that the safety of the coded lock is improved, the coded lock cannot be invaded by outsiders, and the serious economic loss and potential safety hazards are avoided. The safety of the power system is improved.

It should be understood that although the various steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps or stages.

In one embodiment, as shown in fig. 4, there is provided a power system unlocking apparatus including: a first acquisition module 500, a second acquisition module 502, a third acquisition module 504, and an authentication module 506, wherein:

the first obtaining module 500 is configured to, in response to an unlocking instruction based on a door of an electric control room in an electric power system, obtain a user identifier input by a user to be authenticated, and start an identity card authentication interface, a face authentication interface, a voice authentication interface, and a fingerprint authentication interface through an authentication device in the electric power system; the authentication device is disposed in a power control room door of a power system.

A second obtaining module 502, configured to query the user database according to the user identifier, and obtain corresponding pre-stored user information; the pre-stored user information comprises pre-stored identity identification, pre-stored face information, pre-stored sound information and pre-stored fingerprint information.

A third obtaining module 504, configured to obtain, based on the identity card verification interface, an identity to be verified of the user to be verified; acquiring static face information to be verified and dynamic face information to be verified of a user to be verified based on a face verification interface; acquiring to-be-verified voice information of a to-be-verified user based on a voice verification interface; and the fingerprint verification interface is used for acquiring the fingerprint information to be verified of the user to be verified.

And the authentication module 506 is configured to perform identity authentication on the user to be authenticated according to a first comparison result of the to-be-authenticated identity identifier and the pre-stored identity identifier, a second comparison result of the to-be-authenticated static face information and the to-be-authenticated dynamic face information respectively with corresponding types of face information in the pre-stored face information, a third comparison result of the to-be-authenticated sound information and the pre-stored sound information, and a fourth comparison result of the to-be-authenticated fingerprint information and the pre-stored fingerprint information, and send a door opening instruction to the authentication device to unlock the door of the power control room when the identity authentication is passed.

In one embodiment, the above apparatus further comprises: the pre-storage module is used for acquiring the identity card number corresponding to the authenticated user as a pre-stored identity mark and acquiring the fingerprint information corresponding to the authenticated user as pre-stored fingerprint information; acquiring sound information emitted by an authenticated user based on a preset verification character as pre-stored sound information, and acquiring image information when the authenticated user emits the pre-stored sound information; acquiring static face information and dynamic face information corresponding to the authenticated user based on the image information, and taking the static face information and the dynamic face information as prestored face information; and forming corresponding pre-stored user information of the authenticated user by the pre-stored identity identification, the pre-stored fingerprint information, the pre-stored sound information and the pre-stored face information, and storing the pre-stored user information into a user database.

In an embodiment, the pre-storage module is specifically configured to obtain, from the image information, an image when the authenticated user does not make a sound as a static face image; and acquiring an image when the authenticated user makes a voice from the image information as a dynamic face image.

In one embodiment, the above apparatus further comprises: the characteristic extraction module is used for carrying out graying processing and normalization processing on the static face information and the dynamic face information to obtain processed static face information and processed dynamic face information; inputting the processed static face information and the plurality of processed dynamic face information into a preset face recognition model, and acquiring static face image characteristics corresponding to the static face information and dynamic face image characteristics corresponding to each piece of processed dynamic face information; extracting mouth feature data in the dynamic human face image features aiming at each dynamic human face image feature; the mouth feature data represents change data of a preset position on the mouth of the face in the dynamic face image features; establishing a coordinate system based on the plurality of mouth feature data, and determining the coordinates of the mouth feature data in the coordinate system according to the acquisition time of the mouth feature data; obtaining a face image function corresponding to the position transformation of the mouth feature data based on the coordinate fitting of the plurality of mouth feature data; and taking the static face image characteristics, the dynamic face image characteristics and the face image function as prestored face information.

In an embodiment, the authentication module 506 is specifically configured to obtain a first similarity between the identity to be verified and a pre-stored identity, as a first comparison result; acquiring second similarity between the static face information to be verified and the dynamic face information to be verified and face information of a corresponding type in the prestored face information respectively as a second comparison result; acquiring a third similarity of the voice information to be verified and the pre-stored voice information as a third comparison result; acquiring a fourth similarity between the fingerprint information to be verified and the prestored fingerprint information as a fourth comparison result; and if the first comparison result is greater than the first similarity threshold, the second comparison result is greater than the second similarity threshold, the third comparison result is greater than the third similarity threshold, and the fourth comparison result is greater than the fourth similarity, determining that the user to be verified passes the identity authentication.

In an embodiment, the authentication module 506 is specifically configured to perform graying processing and normalization processing on the static face information to be verified and the plurality of dynamic face information to be verified, so as to obtain processed static face information to be verified and a plurality of processed dynamic face information; inputting the processed static face information to be verified and the plurality of processed dynamic face information into a preset face recognition model, and acquiring the static face image characteristics to be verified corresponding to the static face information to be verified and the dynamic face image characteristics to be verified corresponding to each processed dynamic face information to be verified; acquiring a first Euclidean distance between a static face image feature to be verified and a static face image feature corresponding to a user identifier, and acquiring a second Euclidean distance between each dynamic face image feature to be verified and a dynamic face image feature corresponding to the user identifier to obtain a plurality of second Euclidean distances; if the first Euclidean distance is smaller than the first distance threshold value and the second Euclidean distances are smaller than the second distance threshold value, extracting feature data of a mouth to be verified in the dynamic human face image features to be verified; and acquiring the function similarity of the plurality of mouth feature data to be verified and the face image function corresponding to the user identification as a second similarity.

In one embodiment, the above apparatus further comprises: the alarm module is used for closing the identity card verification interface, the face verification interface, the voice verification interface and the fingerprint verification interface until reaching the preset time and then starting again if the number of times that the identity authentication result of the user to be verified fails is larger than the preset number threshold; the preset time threshold is in negative correlation with the time of restarting; the preset time is positively correlated with the number of restarts.

For specific limitations of the power system unlocking device, reference may be made to the above limitations of the power system unlocking method, which are not described herein again. The above-mentioned respective modules in the power system unlocking apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a power system unlocking method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the power system unlocking method when executing the computer program.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the power system unlocking method described above.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method of unlocking a power system, the method comprising:

2. The method of claim 1, further comprising:

3. The method according to claim 2, wherein the obtaining of the static face information and the dynamic face information corresponding to the authenticated user based on the image information comprises:

4. The method according to claim 2, wherein after obtaining the static face information and the dynamic face information corresponding to the authenticated user based on the image information, the method further comprises:

5. The method according to claim 4, wherein the authenticating the user to be authenticated according to the first comparison result between the identity to be authenticated and the pre-stored identity, the second comparison result between the static face information to be authenticated and the dynamic face information to be authenticated and the corresponding type of face information in the pre-stored face information, the third comparison result between the voice information to be authenticated and the pre-stored voice information, and the fourth comparison result between the fingerprint information to be authenticated and the pre-stored fingerprint information respectively comprises:

6. The method according to claim 5, wherein the obtaining of the second similarity between the static face information to be verified and the dynamic face information to be verified and the corresponding type of face information in the pre-stored face information respectively comprises:

7. The method of any one of claims 1 to 6, further comprising:

8. An electrical system unlocking device, characterized in that the device comprises:

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.