Personnel detection method and device based on face recognition, equipment and storage medium

By using edge computing and local feature value library encryption identity information database in the face recognition system, the problems of low recognition efficiency and difficulty in information security management in the face recognition system are solved, and fast and secure personnel detection and identity are achieved verify.

CN119091481APending Publication Date: 2024-12-06SHENZHEN SHUZHENGTONG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411000114.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing facial recognition system has problems such as low recognition efficiency and difficulty in managing citizens' information security in the security checkpoint, resulting in a long customs clearance time and high risk of information leakage.

Method used

The edge computing-based method is used to preprocess and feature extraction of face images, and match and update using the local feature value library and encrypted identity information library to reduce the risks of network transmission and data during transmission.

Benefits of technology

It improves identification speed and real-time, enhances data security and system reliability, reduces network bandwidth usage, improves personnel detection efficiency and protects user privacy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091481A_ABST
    Figure CN119091481A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a person detection method and device based on face recognition, equipment and a storage medium. The method comprises the following steps: analyzing a to-be-processed face image based on a preset edge calculation component to obtain a first face feature value; if the first face feature value is successfully matched in a preset local feature value library, obtaining an identity information identifier corresponding to the first face feature value; matching the identity information identifier in a preset encrypted identity information base, determining encrypted identity information, and updating the identity information identifier; and decrypting the encrypted identity information to obtain target identity information. According to the method, face image analysis is performed through the preset edge calculation component, feature value matching and dynamic updating of identity information identification are realized by using the local feature value library and the encrypted identity information library, and the target identity information is obtained through decryption, so that the data security and the system reliability are enhanced, the recognition speed and the real-time performance are improved, and the user experience is improved. And the personnel detection efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for detecting people based on face recognition. Background Art

[0002] The existing access control or security checkpoints with facial feature recognition have one method for processing facial features: the on-site camera takes a photo of the inspected person, and then transmits the image data back to the background processing system. The background processing system performs facial analysis and comparison, and then transmits the comparison results back to the machine at the security checkpoint through the network. Generally speaking, the pictures that need to be extracted for facial features are relatively clear, so the storage space occupied is also relatively large. For the network transmission of large resources, it often takes a long time, which increases the time for the inspected person to pass through the customs and reduces the security inspection efficiency of the entire security checkpoint. Another method is to deploy a machine with a full set of edge computing capabilities, but without isolating the facial feature value extraction and comparison and information identity acquisition functions; some security checkpoints extract feature values ​​from the on-site facial photos, and then match the data with the local database to obtain identity information. Since the security checkpoint has a large citizen information authority, deploying applications in more locations will make citizen information security management difficult and easily cause citizen information leakage. Therefore, how to improve the efficiency of personnel detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of this application is to provide a method, device, equipment and storage medium for personnel detection based on face recognition, aiming to solve the technical problem of how to improve the efficiency of personnel detection.

[0004] To achieve the above objectives, the present application provides a method for detecting people based on face recognition, the method comprising the following steps: Based on the preset edge computing component, the face image to be processed is analyzed to obtain a first face feature value; If the first facial feature value is successfully matched in the preset local feature value library, obtaining the identity information identifier corresponding to the first facial feature value; Matching the identity information identifier in a preset encrypted identity information database, determining the encrypted identity information, and updating the identity information identifier; The encrypted identity information is decrypted to obtain the target identity information.

[0005] In one embodiment, the preset edge computing component and the preset local feature value library are deployed in a first local area network, the preset encrypted identity information library is deployed in a second local area network, and the first local area network and the second local area network communicate data via a preset network transmission protocol.

[0006] In one embodiment, the step of parsing the face image to be processed based on the preset edge computing component to obtain the first face feature value includes: Based on the preset edge computing component, preprocessing the face image to be processed to obtain a preprocessed image, wherein the preprocessing includes one or more of grayscale processing, noise reduction processing and normalization processing; Based on a preset face detection algorithm, extracting a face region in the preprocessed image; Based on a preset feature extraction algorithm, feature extraction is performed on the face area, and the result of the feature extraction is encrypted to obtain the first face feature value.

[0007] In one embodiment, after the step of parsing the face image to be processed based on the preset edge computing component to obtain the first face feature value, the method further includes: Determine a second facial feature value according to preset identity authentication history information, and generate an identity information identifier corresponding to the second facial feature value; The identity information identifier corresponding to the second facial feature value and the second facial feature value are stored in the preset local feature value library; The identity information identifier corresponding to the second facial feature value and the preset identity authentication history information are stored in the preset encrypted identity information library.

[0008] In one embodiment, before the step of obtaining the identity information identifier corresponding to the first facial feature value if the first facial feature value is successfully matched in the preset local feature value library, the step further includes: Traversing the preset local feature value library, and determining whether the identity information identifier corresponding to the first facial feature value exists in the preset local feature value library; If so, determining whether the matching degree between the second facial feature value and the first facial feature value exceeds a preset first matching degree threshold; If it exceeds, it is determined that the first facial feature value is successfully matched in the preset local feature value library; If not, it is determined that the first facial feature value fails to match in the preset local feature value library.

[0009] In one embodiment, the step of matching the identity information identifier in a preset encrypted identity information database, determining the encrypted identity information, and updating the identity information identifier includes: Based on a preset query algorithm, the identity information identifier is used as a query key to perform query matching in the preset encrypted identity information database; Determine whether the matching degree between the query matching result and the query key exceeds a preset second matching degree threshold; If it exceeds, the data corresponding to the query matching result is used as the encrypted identity information, and the identity information identifier is regenerated based on the encrypted identity information. Based on the regenerated identity information identifier, the value of the corresponding identity information identifier in the preset encrypted identity information library and the preset local feature value library is updated.

[0010] In one embodiment, after the step of decrypting the encrypted identity information to obtain the target identity information, the method further includes: Obtaining real-time behavior data corresponding to the target identity information; Performing the preprocessing on the real-time behavior data to obtain preprocessed behavior data; Extracting behavioral features from the preprocessed behavioral data; Based on the behavior analysis model in the preset edge computing component, identifying the behavior characteristics; If abnormal behavior is identified, the real-time behavior data is recorded and an alarm message is issued.

[0011] In addition, to achieve the above purpose, the present application also proposes a personnel detection device based on face recognition, and the personnel detection device based on face recognition includes: A feature determination module, configured to analyze the face image to be processed based on a preset edge computing component to obtain a first face feature value; an identification acquisition module, configured to acquire an identity information identification corresponding to the first facial feature value if the first facial feature value is successfully matched in a preset local feature value library; The encrypted information determination module matches the identity information identifier in a preset encrypted identity information database, determines the encrypted identity information, and updates the identity information identifier; The target information determination module is used to decrypt the encrypted identity information to obtain the target identity information.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a personnel detection device based on face recognition, the device comprising: a memory, a processor, and a personnel detection program based on face recognition stored on the memory and executable on the processor, the personnel detection program based on face recognition being configured to implement the steps of the personnel detection method based on face recognition as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a personnel detection program based on face recognition is stored. When the personnel detection program based on face recognition is executed by a processor, the steps of the personnel detection method based on face recognition as described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the person detection method based on face recognition as described above.

[0015] This application is based on a preset edge computing component to parse the face image to be processed and obtain the first face feature value; if the first face feature value is successfully matched in the preset local feature value library, the identity information identifier corresponding to the first face feature value is obtained; the identity information identifier is matched in the preset encrypted identity information library, the encrypted identity information is determined, and the identity information identifier is updated; the encrypted identity information is decrypted to obtain the target identity information. This application uses a preset edge computing component to perform face image parsing, uses the local feature value library and the encrypted identity information library to achieve feature value matching and dynamic update of identity information identifiers, and obtains the target identity information through decryption, which enhances data security and system reliability, ensures the accuracy of information and the timeliness of updates, improves recognition speed and real-time performance, reduces network bandwidth usage, and improves personnel detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the first embodiment of the method for detecting people based on face recognition in this application; Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the personnel detection method based on face recognition of the present application; Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the method for detecting people based on face recognition of the present application; Figure 4 This is a schematic diagram of a personnel detection process in an embodiment of a personnel detection method based on face recognition of the present application; Figure 5 This is a schematic diagram of the module structure of a personnel detection device based on face recognition in an embodiment of the present application; Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in the personnel detection method based on face recognition in the embodiment of the present application.

[0017] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0020] It should be noted that the existing access control or security checkpoints with facial feature recognition have one method for processing facial features: the on-site camera takes a photo of the inspected person, and then transmits the image data back to the background processing system. The background processing system performs facial analysis and comparison, and then transmits the comparison results back to the machine at the security checkpoint through the network. Generally speaking, the pictures that need to be extracted for facial features are relatively clear, so the storage space occupied is also relatively large. For network transmission of large resources, it often takes a long time, which increases the time for the inspected person to pass through the customs and reduces the security inspection efficiency of the entire security checkpoint. Another method is to deploy a machine with a full set of edge computing capabilities, but without isolating the facial feature value extraction and comparison and information identity acquisition functions; some security checkpoints extract feature values ​​from the on-site facial photos, and then match the data with the local database to obtain identity information. Since the security checkpoint has a large citizen information authority, deploying applications in more locations will make citizen information security management difficult and easily cause citizen information leakage. Therefore, how to improve the efficiency of personnel detection has become a technical problem that needs to be solved urgently.

[0021] The main solution of this application is: based on the preset edge computing component, the facial image to be processed is analyzed to obtain the first facial feature value; if the first facial feature value is successfully matched in the preset local feature value library, the identity information identifier corresponding to the first facial feature value is obtained; the identity information identifier is matched in the preset encrypted identity information library, the encrypted identity information is determined, and the identity information identifier is updated; the encrypted identity information is decrypted to obtain the target identity information.

[0022] This application performs facial image analysis through a preset edge computing component, uses a local feature value library and an encrypted identity information library to achieve dynamic update of feature value matching and identity information identification, and obtains the target identity information through decryption, thereby enhancing data security and system reliability, ensuring the accuracy of information and the timeliness of updates, improving recognition speed and real-time performance, reducing network bandwidth occupancy, and improving personnel detection efficiency.

[0023] It should be noted that the execution subject of the method of this embodiment can be a computing service device with data processing, network communication and program running functions, or it can be the above-mentioned personnel detection device based on face recognition with the same or similar functions. This embodiment and the following embodiments will be described by taking the personnel detection device based on face recognition as an example.

[0024] Based on this, the first embodiment of the personnel detection method based on face recognition of this application is proposed, please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for detecting people based on face recognition in the present application.

[0025] In this embodiment, the person detection method based on face recognition includes the following steps: S1: Based on the preset edge computing component, the face image to be processed is analyzed to obtain a first face feature value; It should be noted that edge computing refers to a technology that performs computing and data processing at an edge location close to the data source, with the aim of reducing data transmission delays and bandwidth occupancy and improving processing efficiency. Preset edge computing components refer to edge computing hardware and software systems pre-configured on front-end devices, including high-performance processors, dedicated acceleration hardware (such as GPU or TPU), memory, storage devices, and pre-configured algorithms and models. The face image to be processed is image data that needs to be processed for face recognition and is obtained through image acquisition devices such as cameras. The first face feature value refers to a numerical value or vector that describes the face features extracted from the face image to be processed. This feature value is used for matching and identity authentication in the face recognition system.

[0026] Specifically, a front-end camera is used to collect a face image to be processed, and the image data is transmitted to a preset edge computing component. On the edge computing component, the transmitted image is preprocessed to improve the image quality and the accuracy of subsequent processing. The preset face detection algorithm in the edge computing component is used to detect the face area in the preprocessed image. In the detected face area, a preset feature extraction algorithm is used to extract a feature value describing the face features, that is, a first face feature value.

[0027] By parsing and extracting features of facial images on edge computing components, the need to transmit large amounts of image data to remote servers is reduced. The delay of recognition processing is significantly shortened, and high-real-time facial recognition applications are realized, meeting the needs of scenarios that require rapid response, such as security inspection and access control. Direct image preprocessing, detection, and feature extraction on edge computing devices only require the transmission of a small amount of data (such as extracted feature values) rather than the entire image data, which greatly reduces the network bandwidth occupancy, reduces the network transmission burden, and improves the overall operation efficiency of the system. Image processing and feature extraction on local devices reduce the risk of sensitive data transmission on the network, improves data security and privacy protection, and prevents sensitive information from being intercepted or tampered with during transmission. Using edge computing components to share computing loads and reduce dependence on central servers, basic functions can be maintained even in the case of network instability or server failure, enhancing the reliability and stability of the system and ensuring continuous operation capabilities in various complex environments.

[0028] S2: If the first facial feature value is successfully matched in a preset local feature value library, obtaining an identity information identifier corresponding to the first facial feature value; It should be noted that the preset local feature value library refers to a database stored in the local device, which contains the facial feature values ​​of registered persons and is used to match and verify the input facial feature values. The identity information identifier refers to the user's UUID (Universally Unique Identifier) ​​used to identify each user's identity information. UUID is a standardized 128-bit identifier that ensures that each identifier is unique, avoiding duplication and confusion of identity information.

[0029] Specifically, the extracted first facial feature value is compared with the feature value in the preset local feature value library. The preset matching algorithm is used to calculate the similarity between the input feature value and the feature value in the library. It is determined whether the similarity reaches the predetermined matching threshold. If the similarity reaches or exceeds the threshold, the match is considered successful. If the match is successful, the corresponding identity information identifier (UUID) is searched in the feature value library. The identity information identifier (UUID) associated with the successfully matched feature value is extracted from the preset local feature value library. The UUID is used for subsequent identity authentication and information association to ensure that the identity information of each user is unique and accurate.

[0030] By matching feature values ​​in the local feature value library, the feature value matching process is ensured to be fast and accurate. The recognition accuracy of the face recognition system is improved, and the cases of misidentification and missed recognition are reduced. By matching feature values ​​locally, there is no need to transmit data to the remote server, which reduces the delay in the matching process, significantly improves the response speed of the system, and meets the application scenarios with high real-time requirements. The matching process is completed locally, reducing the need for large-scale data transmission. Only a small amount of identity information that is successfully matched needs to be transmitted, which reduces the network bandwidth occupancy, reduces the network transmission burden, and improves the overall efficiency of the system. Local feature value matching reduces the risk of sensitive data transmission on the network, enhances data security, effectively protects user privacy, and prevents sensitive information from being intercepted or leaked during transmission. Relying on the local feature value library for matching reduces dependence on remote servers. Even when the network connection is unstable or the server fails, the system can still operate normally, improving the reliability and stability of the system and ensuring stable operation in various environments.

[0031] S3: matching the identity information identifier in a preset encrypted identity information database, determining the encrypted identity information, and updating the identity information identifier; It should be noted that the preset encrypted identity information database refers to a database that stores user encrypted identity information. The identity information in the database is encrypted to ensure the security of data during storage and transmission.

[0032] Specifically, the identity information identifier (UUID) obtained from the local feature value library is used as the query key to access the preset encrypted identity information library. Use efficient query algorithms (such as hash search, index, etc.) to quickly find the encrypted identity information corresponding to the identity information identifier. Every time a match is successful, the identity information identifier is updated (replaced with a new UUID) and written to the encrypted identity information library. Ensure that the identity information identifiers in the library are always up to date to avoid data obsolescence and confusion.

[0033] By matching the identity information identifier with the records in the encrypted identity information database and encrypting the identity information, the security of data during storage and transmission is ensured, the privacy of users is protected, and sensitive information is prevented from being intercepted or tampered with during transmission and storage. The unique identity information identifier (UUID) is used for matching to ensure the uniqueness and accuracy of identity information, avoid information confusion, improve the recognition accuracy and reliability of the system, and ensure that each match and identity authentication is accurate. The use of efficient query algorithms for matching reduces the time for matching and searching, significantly improves the response speed of the system, and meets application scenarios with high real-time requirements. By updating the identity information identifier after a successful match, it ensures that the identity information in the database is always up to date, avoids data obsolescence, maintains the data consistency and accuracy of the system, and improves the reliability and user experience of the system. By automatically updating the identity information identifier, the workload of manual database maintenance is reduced, the maintenance cost of the system is reduced, and the automation and intelligence level of the system is improved.

[0034] S4: Decrypt the encrypted identity information to obtain target identity information.

[0035] It should be noted that encrypted identity information refers to identity information processed by an encryption algorithm to ensure that it is not illegally accessed or tampered with during storage and transmission. Common encryption algorithms include symmetric encryption (such as AES) and asymmetric encryption (such as RSA). Decryption refers to the process of using a decryption algorithm to restore encrypted information to the original information. Decryption requires the use of the key corresponding to encryption to ensure the security and integrity of the data during the decryption process. The target identity information is the original identity information obtained through decryption, including the user's detailed identity data, such as name, ID number, etc., for further identity authentication and processing.

[0036] Specifically, receive the encrypted identity information that matches the identity information identifier from the encrypted identity information library. Select the corresponding decryption algorithm (such as AES decryption, RSA decryption, etc.) according to the encryption method of the encrypted identity information. Obtain the corresponding decryption key from a secure key management system. Ensure the secure storage and transmission of the decryption key to prevent key leakage. Decrypt the encrypted identity information using the decryption algorithm and decryption key, and restore the encrypted data to the original target identity information. Check whether the decrypted data is complete and correct to ensure that there are no errors in the decryption process. Including verifying the data format, integrity and consistency. Transmit the decrypted target identity information to the module or system that needs to be authenticated for subsequent processing and verification.

[0037] Through the encryption and decryption mechanism, the security of identity information during storage and transmission is ensured, and sensitive identity information is effectively prevented from being intercepted, tampered or leaked, thereby improving the security of the system and user privacy protection. The decryption process ensures that the data is restored from the encrypted state to the original state, maintains the integrity and accuracy of the data, ensures that the target identity information after decryption is consistent with the data before encryption, and improves the reliability and accuracy of identity authentication. Use encryption algorithms to protect data, and verify the decryption results during the decryption process to prevent data tampering and forgery, improve the system's protection against data tampering and forgery, and enhance the overall security and protection capabilities of the system. The use of standardized encryption and decryption algorithms can flexibly adapt to different security requirements and application scenarios. The system can select appropriate encryption and decryption algorithms according to different security requirements to improve the flexibility and adaptability of the system. Through a fast and accurate decryption process, it ensures that the user's identity information can be verified and processed in a timely and effective manner, improves the system's response speed and user experience, and meets the needs of high real-time application scenarios.

[0038] This embodiment is based on a preset edge computing component to parse the face image to be processed and obtain the first face feature value; if the first face feature value is successfully matched in the preset local feature value library, the identity information identifier corresponding to the first face feature value is obtained; the identity information identifier is matched in the preset encrypted identity information library, the encrypted identity information is determined, and the identity information identifier is updated; the encrypted identity information is decrypted to obtain the target identity information. This embodiment uses a preset edge computing component to perform face image parsing, uses the local feature value library and the encrypted identity information library to achieve feature value matching and dynamic update of identity information identifiers, and obtains the target identity information through decryption, which enhances data security and system reliability, ensures the accuracy of information and the timeliness of updates, improves recognition speed and real-time performance, reduces network bandwidth usage, and improves personnel detection efficiency.

[0039] Based on the above first embodiment, a second embodiment of the personnel detection method based on face recognition is proposed. Figure 2 , Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the personnel detection method based on face recognition of the present application.

[0040] like Figure 2 As shown, in this embodiment, step S1 includes: S11: Based on the preset edge computing component, preprocess the face image to be processed to obtain a preprocessed image, wherein the preprocessing includes one or more of grayscale processing, noise reduction processing and normalization processing; S12: extracting a face region in the preprocessed image based on a preset face detection algorithm; S13: Based on a preset feature extraction algorithm, extract features from the face area, and encrypt the feature extraction result to obtain the first face feature value.

[0041] Specifically, a front-end camera is used to collect the facial image to be processed, and the image data is transmitted to the preset edge computing component. This camera can be a device deployed at a security checkpoint, access control system, etc., to capture the facial images of people passing by in real time. On the edge computing component, the transmitted image is preprocessed to improve the image quality and the accuracy of subsequent processing. The preprocessing process includes the following steps: Grayscale processing: converting the color image into a grayscale image. The color image contains three channels (red, green, and blue). Grayscale processing reduces the amount of calculation and improves the processing speed; Noise reduction processing: Use a filter to remove noise from the image. For example, a Gaussian filter can smooth the image and reduce the impact of random noise on feature extraction; Normalization processing: Adjust the pixel value of the image to a standard range (for example, 0 to 1 or -1 to 1). Standardization processing helps eliminate the impact of illumination changes on image processing.

[0042] Furthermore, the face area is detected in the preprocessed image using the preset face detection algorithm in the edge computing component. The face detection algorithm includes the following steps: Image scanning: The algorithm scans the image block by block to locate the area that may contain the face; Feature matching: Use the face detection algorithm (such as Haar feature detection or deep learning model) to match the face features in the preprocessed image to determine the location of the face; Bounding box generation: Generate a bounding box at the detected face location to mark the face area. In the detected face area, the preset feature extraction algorithm is used to extract the feature values ​​that describe the face features. The feature extraction process includes the following steps: Feature point detection: Detect key points in the image, which are usually located in prominent parts such as eyes, nose, and mouth; Feature description: Use an algorithm (such as LBP, SIFT, or deep learning model) to describe the detected feature points and generate feature vectors. These feature vectors highly summarize the unique features of the face. The extracted feature values ​​are encrypted. The encryption process includes the following steps: Select encryption algorithm: Select an appropriate encryption algorithm (such as AES or RSA) to encrypt the feature value; Encryption operation: Use the encryption algorithm and key to encrypt the feature value to generate the encrypted first face feature value. Encryption ensures the security of the feature value during storage and transmission.

[0043] By performing image preprocessing, detection, and feature extraction on edge computing components, the need to transmit large amounts of image data to remote servers is reduced, the delay in recognition processing is significantly shortened, and high-real-time face recognition applications are realized, meeting the needs of scenarios that require rapid response, such as security inspection and access control. Direct image preprocessing, detection, and feature extraction on edge computing devices only require the transmission of a small amount of data (such as encrypted feature values) rather than the entire image data, which greatly reduces the network bandwidth occupancy, reduces the network transmission burden, and improves the overall operating efficiency of the system. Performing image processing and feature extraction on local devices and encrypting feature values ​​reduces the risk of sensitive data transmission on the network, improves data security and privacy protection, and prevents sensitive information from being intercepted or tampered with during transmission. Using edge computing components to share computing loads and reduce dependence on central servers, basic functions can be maintained even in the case of network instability or server failure, enhancing the reliability and stability of the system and ensuring continuous operation capabilities in various complex environments.

[0044] Based on the above-mentioned first embodiment, in this embodiment, the preset edge computing component and the preset local feature value library are deployed in the first local area network, the preset encrypted identity information library is deployed in the second local area network, and the first local area network and the second local area network communicate data through a preset network transmission protocol.

[0045] Specifically, the preset edge computing components and the local feature value library are deployed in the first local area network. This means that these components and the database are located in the same physical location, and data processing and matching can be performed quickly. The preset encrypted identity information library is deployed in the second local area network. The local area network may be located in another physical location, such as a data center or a cloud server, and is used to store and manage encrypted identity information. The first local area network and the second local area network communicate data through a preset network transmission protocol (such as TCP / IP protocol) to ensure the integrity and security of data during transmission. The protocol provides an error detection and correction mechanism to ensure the reliability of data transmission.

[0046] Furthermore, when face recognition is performed in the first local area network, the successfully matched identity information identifier needs to be sent to the encrypted identity information database in the second local area network for matching and verification, and data communication is performed through a preset network transmission protocol to ensure the security and integrity of the identity information identifier and encrypted identity information during transmission and prevent data loss or tampering.

[0047] Deploying the preset edge computing components and the local feature value library in the same LAN can achieve fast data processing and matching without transmitting a large amount of data across the network, significantly improving the processing efficiency and response speed of the face recognition system and meeting application scenarios with high real-time requirements. By deploying the encrypted identity information library in an independent second LAN and using the preset network transmission protocol for data communication, the security of data during transmission is ensured, the security of identity information is improved, sensitive information is prevented from being intercepted or tampered with during network transmission, and user privacy is protected. Local processing in the first LAN reduces dependence on remote servers. Even if the second LAN fails, the system can still perform preliminary processing and matching locally, enhancing the reliability and stability of the system and ensuring that the system can operate stably in various complex environments. A large amount of data processing and matching is performed in the first LAN, and data is sent to the second LAN for verification only when necessary, reducing the amount of data transmission across networks, reducing the occupancy of network bandwidth, and improving the operating efficiency of the overall system. Distributing processing tasks in different LANs, taking advantage of edge computing and centralized storage, optimizing resource utilization and processing capabilities, the system can process large amounts of data more flexibly and efficiently, and improving overall performance.

[0048] Based on the first embodiment above, in this embodiment, after step S1, the following steps are further included: S1a: Determine a second facial feature value according to preset identity authentication history information, and generate an identity information identifier corresponding to the second facial feature value; S1b: storing the identity information identifier corresponding to the second facial feature value and the second facial feature value in the preset local feature value library; S1c: Save the identity information identifier corresponding to the second facial feature value and the preset identity authentication history information in the preset encrypted identity information database.

[0049] It should be noted that the preset identity authentication history information refers to the historical identity authentication records saved in the system, including previous identity authentication data, feature values ​​and corresponding identity information identifiers. This information is used to assist in the generation and verification of new identity feature values. The second facial feature value refers to a new numerical value or vector describing facial features generated based on the preset identity authentication history information, which is used for matching and identity authentication in the system.

[0050] Specifically, the preset identity authentication history information is analyzed to extract the feature values ​​and corresponding identity information identifiers in the historical verification records. A new second facial feature value is generated by combining the historical authentication information with the preset algorithm. This process may include feature value fusion, weighted averaging, or re-extraction to improve the accuracy and reliability of the new feature value. A unique identity information identifier (such as UUID) is generated for the new second facial feature value to ensure the uniqueness and traceability of the new feature value in the system.

[0051] Furthermore, the new second facial feature value and its corresponding identity information identifier are saved in the local feature value library, and the local database is updated to include the latest feature value and identity information. The identity information identifier corresponding to the new second facial feature value and the related preset identity authentication history information are saved in the encrypted identity information library to ensure that the information is encrypted to protect its security and privacy.

[0052] By combining historical identity authentication information to generate new second face feature values, the stability and reliability of historical data can be used to improve the accuracy and consistency of new feature values, improve the recognition accuracy and credibility of the system, and reduce the occurrence of misidentification and missed recognition. Continuously learning and accumulating identity authentication historical information, by generating new feature values ​​and identity information identifiers, the adaptability and intelligence level of the system are enhanced, and it can better cope with the identity authentication needs in different scenarios and complex environments, and improve the overall performance. By saving the identity information identifier and the identity authentication historical information in the encrypted identity information library and encrypting them, the security of the data during storage and transmission is ensured, the user's privacy is effectively protected, sensitive information is prevented from being intercepted or tampered with, and data security is enhanced. Saving new feature values ​​and identity information identifiers in the local feature value library reduces the need for frequent access to remote databases, improves the efficiency of local matching and verification, significantly improves the response speed of the system, and meets the application scenario requirements with high real-time requirements. Through the accumulation and management of preset identity authentication historical information, the system can continuously optimize and update the feature value library and identity information library, keep the data up-to-date and effective, enhance the maintainability and scalability of the system, facilitate subsequent updates and expansions, and improve the long-term use value of the system.

[0053] This embodiment is based on a preset edge computing component to parse the face image to be processed and obtain the first face feature value; if the first face feature value is successfully matched in the preset local feature value library, the identity information identifier corresponding to the first face feature value is obtained; the identity information identifier is matched in the preset encrypted identity information library, the encrypted identity information is determined, and the identity information identifier is updated; the encrypted identity information is decrypted to obtain the target identity information. This embodiment uses a preset edge computing component to perform face image parsing, uses the local feature value library and the encrypted identity information library to achieve feature value matching and dynamic update of identity information identifiers, and obtains the target identity information through decryption, which enhances data security and system reliability, ensures the accuracy of information and the timeliness of updates, improves recognition speed and real-time performance, reduces network bandwidth usage, and improves personnel detection efficiency.

[0054] Based on the above second embodiment, a third embodiment of the personnel detection method based on face recognition is proposed. Figure 3 , Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the personnel detection method based on face recognition of the present application.

[0055] like Figure 3 As shown, in this embodiment, before step S2, the following is further included: S2a: traverse the preset local feature value library to determine whether the identity information identifier corresponding to the first facial feature value exists in the preset local feature value library; S2b: If yes, determine whether the matching degree between the second facial feature value and the first facial feature value exceeds a preset first matching degree threshold; S2c: If the match exceeds the limit, it is determined that the first facial feature value is successfully matched in the preset local feature value library; S2d: If not, it is determined that the first facial feature value fails to match in the preset local feature value library.

[0056] It should be noted that the matching degree refers to the similarity measure between feature values, indicating how similar two feature values ​​are. A matching degree exceeding a preset threshold indicates that the two feature values ​​are considered to be the same or sufficiently similar. The preset first matching degree threshold is a pre-set value used to determine whether two feature values ​​match. If the matching degree between the feature values ​​exceeds the threshold, the match is considered successful.

[0057] Specifically, all records in the local feature value library are traversed, and the identity information identifier in each record is checked one by one to see whether it is the same as the identity information identifier corresponding to the first facial feature value. If the identity information identifier corresponding to the first facial feature value is found in the local feature value library, the next step of judgment is entered. The matching degree between the second facial feature value and the first facial feature value is calculated. The matching degree is usually determined by calculating the similarity between the feature value vectors, such as Euclidean distance, cosine similarity, etc. The calculated matching degree is compared with a preset first matching degree threshold. If the matching degree exceeds the preset matching degree threshold, it is considered that the two feature values ​​are matched successfully. If the matching degree exceeds the preset first matching degree threshold, it is determined that the first facial feature value is matched successfully in the local feature value library, indicating that the feature value is consistent with the record in the library. If the matching degree fails to exceed the preset first matching degree threshold, it is determined that the first facial feature value fails to match in the local feature value library, indicating that the feature value is inconsistent with the record in the library.

[0058] Through strict matching degree calculation and threshold judgment, only highly similar feature values ​​are judged as matching successfully, reducing the cases of misidentification and missed identification, and improving the recognition accuracy and credibility of the face recognition system. Multiple verification steps (including traversing the library, calculating matching degree and threshold judgment) ensure that only truly matching feature values ​​can pass the verification, improving the security of the system, preventing identity impersonation and fraud, and protecting user privacy. By performing fast matching and judgment in the local feature value library, the time for data transmission and remote processing is reduced, the response speed of the system is significantly improved, and the requirements of high real-time application scenarios are met. Matching and judgment are performed locally, reducing the dependence on remote server resources, reducing the computing and communication burden of the system, optimizing the utilization of system resources, and improving the overall system operation efficiency. The fast and accurate matching and identity authentication process improves the user experience during use, enhances the user's trust and satisfaction with the system, and improves the application value of the system.

[0059] Based on the above second embodiment, in this embodiment, step S3 includes: S31: Based on a preset query algorithm, use the identity information identifier as a query key to perform query matching in the preset encrypted identity information database; S32: Determine whether the matching degree between the query matching result and the query key exceeds a preset second matching degree threshold; S33: If it exceeds, the data corresponding to the result of the query matching is used as the encrypted identity information, and the identity information identifier is regenerated based on the encrypted identity information. Based on the regenerated identity information identifier, the value of the corresponding identity information identifier in the preset encrypted identity information library and the preset local feature value library is updated.

[0060] It should be noted that the preset query algorithm is an algorithm for finding matching records in the database, which is preset and optimized to improve query efficiency and accuracy. The preset second matching degree threshold is a preset value used to determine whether the query matching result is similar enough to the query key. Exceeding this threshold indicates a successful match.

[0061] Specifically, a preset query algorithm is used, and the input identity information identifier is used as a query key to search in the preset encrypted identity information database, trying to find a record that matches the query key. The matching degree between the query matching result and the input identity information identifier is calculated. The matching degree measures the similarity between two values, and common methods include hash matching, cosine similarity, etc. The calculated matching degree is compared with a preset second matching degree threshold. If the matching degree exceeds the preset threshold, the query match is considered successful. If the matching degree exceeds the preset second matching degree threshold, the query matching result is determined as the corresponding encrypted identity information.

[0062] Furthermore, based on the encrypted identity information obtained through query matching, a new identity information identifier (such as a new UUID) is regenerated to ensure the uniqueness and update of the identity information. The regenerated identity information identifier is used together with the corresponding encrypted identity information to update the records in the preset encrypted identity information database to ensure that the information in the database is up to date. At the same time, the regenerated identity information identifier is updated to the preset local feature value database to ensure that the identity information identifier in the local feature value database is consistent with the encrypted identity information database.

[0063] Use the preset query algorithm and matching degree calculation to ensure the accuracy of the match between the identity information and the encrypted identity information, improve the recognition accuracy and credibility, and reduce the cases of misidentification and missed identification. Ensure the security of data during storage and transmission by querying and matching the encrypted identity information. Regenerate and update the identity information to maintain the consistency of database information, protect user privacy, prevent sensitive information from being intercepted or tampered with, and ensure the consistency and integrity of system data. Through efficient query algorithms and matching degree judgments, quickly find matching encrypted identity information and update related records, improve the response speed of the system, and meet the needs of application scenarios with high real-time requirements. Automatically update the identity information to reduce the workload of manual database maintenance, ensure that the data in the system is always up to date, enhance the maintainability and scalability of the system, facilitate subsequent updates and expansions, and enhance the long-term use value of the system. Through a fast and accurate matching and update process, ensure that the user's identity information can be verified and processed in a timely and effective manner, improve user trust and satisfaction, and enhance the application value.

[0064] Based on the above second embodiment, in this embodiment, after step S4, the following is further included: S4a: Acquire real-time behavior data corresponding to the target identity information; S4b: performing the preprocessing on the real-time behavior data to obtain preprocessed behavior data; S4c: extracting behavioral features from the preprocessed behavioral data; S4d: Identify the behavior feature based on the behavior analysis model in the preset edge computing component; S4e: If abnormal behavior is identified, the real-time behavior data is recorded and an alarm message is issued.

[0065] It should be noted that real-time behavior data refers to the real-time data corresponding to the target identity information, including the user's behavior records in the system. Behavioral features are feature values ​​or vectors extracted from preprocessed behavioral data that can describe the user's behavior pattern. The behavior analysis model is based on the model in the preset edge computing component, which is used to identify and analyze behavioral features and determine whether the user behavior is abnormal. The model may be based on machine learning or rule matching.

[0066] Specifically, the real-time behavior data corresponding to the target identity information is extracted from the storage, and these data reflect the user's current behavior in real time. The acquired real-time behavior data is preprocessed, and the steps may include: cleaning: removing irrelevant or noise data; formatting: converting the data into a unified format for subsequent processing; normalization: normalizing the numerical data to ensure that the data is within the same scale range.

[0067] Furthermore, features that can describe user behavior patterns are extracted from the preprocessed behavior data. The extracted behavior features are identified and analyzed using a preset behavior analysis model. The behavior analysis model can be based on a machine learning algorithm (such as a classifier, a clustering algorithm) or rule matching (such as anomaly detection rules). The behavior analysis model is used to determine whether the user behavior is abnormal. If abnormal behavior is identified (such as frequent access to sensitive data, abnormal login time, etc.), the system will record the relevant data. The detected abnormal behavior data is recorded and an alarm message is generated. The alarm information includes a specific description of the abnormal behavior, time, user identity, etc. An alarm notification is issued to alert relevant personnel to facilitate further investigation and processing.

[0068] By real-time monitoring and analysis of user behavior, abnormal behavior can be detected and responded to in a timely manner, potential security threats can be prevented, data leakage, unauthorized access and other security incidents can be effectively prevented, and the overall security and stability of the system can be improved. It can continuously monitor user behavior, extract and analyze behavioral characteristics, establish user behavior patterns, enhance the system's monitoring and management capabilities of user behavior, and better identify and prevent potential illegal operations. By presetting edge computing components to analyze behavioral characteristics in real time, abnormal behavior can be quickly identified and issued alarms, which improves the response speed and processing efficiency of abnormal behavior and reduces human intervention and processing time. Through automated behavior analysis and alarm mechanisms, problems can be discovered and solved in a timely manner, potential threats to users can be reduced, user trust and satisfaction can be improved, and the overall user experience can be optimized. The behavior analysis model can be continuously optimized and updated to adapt to new security requirements and application scenarios, and its behavior recognition and anomaly detection capabilities can be continuously improved.

[0069] This embodiment is based on a preset edge computing component to parse the face image to be processed and obtain the first face feature value; if the first face feature value is successfully matched in the preset local feature value library, the identity information identifier corresponding to the first face feature value is obtained; the identity information identifier is matched in the preset encrypted identity information library, the encrypted identity information is determined, and the identity information identifier is updated; the encrypted identity information is decrypted to obtain the target identity information. This embodiment uses a preset edge computing component to perform face image parsing, uses the local feature value library and the encrypted identity information library to achieve feature value matching and dynamic update of identity information identifiers, and obtains the target identity information through decryption, which enhances data security and system reliability, ensures the accuracy of information and the timeliness of updates, improves recognition speed and real-time performance, reduces network bandwidth usage, and improves personnel detection efficiency.

[0070] For example, in order to help understand the technical concept or technical principle of the two-dimensional code generation method of the above embodiment, please refer to Figure 4 , Figure 4 This is a schematic diagram of the personnel detection process in an embodiment of the personnel detection method based on face recognition of the present application.

[0071] like Figure 4 As shown in the figure, the security edge computing component includes a camera and a machine with edge computing capabilities. The camera and the machine with edge computing capabilities share a storage space. After the passenger arrives at the security checkpoint, the camera takes a photo to obtain the passenger's face photo. The machine with edge computing capabilities reads the photo, extracts the feature value, compares it with the local feature value library (the feature value is encrypted by the algorithm and the specific meaning cannot be directly read out), obtains the UUID of the passenger who reaches the face score threshold, and finally transmits the UUID to the background. The background obtains the UUID transmitted by the edge computing system, matches the database to obtain the passenger's citizen identity information, and then encrypts the citizen identity information and transmits it to the security edge component. The security edge component uses the key to decrypt the encrypted string to obtain the identity information of the passenger, and decides whether to release the passenger based on this information.

[0072] The present application also provides a person detection device based on face recognition, please refer to Figure 5 , Figure 5 This is a schematic diagram of the module structure of a personnel detection device based on face recognition according to an embodiment of the present application. The personnel detection device based on face recognition includes: A feature determination module 501 is used to analyze the face image to be processed based on a preset edge computing component to obtain a first face feature value; The identification acquisition module 502 is used to obtain the identity information identification corresponding to the first facial feature value if the first facial feature value is successfully matched in the preset local feature value library; The encrypted information determination module 503 matches the identity information identifier in a preset encrypted identity information database, determines the encrypted identity information, and updates the identity information identifier; The target information determination module 504 is used to decrypt the encrypted identity information to obtain the target identity information.

[0073] The personnel detection device based on face recognition provided in the embodiment of the present application adopts the personnel detection method based on face recognition in the above embodiment, which can solve the technical problem of how to improve the efficiency of personnel detection. Compared with the prior art, the beneficial effects of the personnel detection device based on face recognition provided in the embodiment of the present application are the same as the beneficial effects of the personnel detection method based on face recognition provided in the above embodiment, and other technical features in the personnel detection device based on face recognition are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0074] The present application provides a personnel detection device based on face recognition, and the personnel detection device based on face recognition includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the personnel detection method based on face recognition in the above-mentioned embodiment.

[0075] Reference below Figure 6 , which shows a schematic diagram of the structure of a person detection device based on face recognition suitable for implementing the embodiment of the present application. The person detection device based on face recognition in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The illustrated human detection device based on face recognition is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0076] like Figure 6As shown, the personnel detection device based on face recognition may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the personnel detection device based on face recognition are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the personnel detection device based on face recognition to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a personnel detection device based on face recognition with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0077] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0078] The personnel detection device based on face recognition provided by the present application adopts the personnel detection method based on face recognition in the above embodiment, which can solve the technical problem of how to improve the efficiency of personnel detection. Compared with the prior art, the beneficial effects of the personnel detection device based on face recognition provided by the present application are the same as the beneficial effects of the personnel detection method based on face recognition provided by the above embodiment, and the other technical features in the personnel detection device based on face recognition are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0079] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0080] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0081] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the personnel detection method based on face recognition in the above-mentioned embodiment.

[0082] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0083] The computer-readable storage medium may be included in a person detection device based on face recognition; or may exist independently without being assembled into a person detection device based on face recognition.

[0084] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a personnel detection device based on face recognition, the personnel detection device based on face recognition: based on a preset edge computing component, the face image to be processed is analyzed to obtain a first face feature value; if the first face feature value is successfully matched in a preset local feature value library, the identity information identifier corresponding to the first face feature value is obtained; the identity information identifier is matched in a preset encrypted identity information library, the encrypted identity information is determined, and the identity information identifier is updated; the encrypted identity information is decrypted to obtain the target identity information. The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, and the programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0085] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0086] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0087] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned personnel detection method based on face recognition, and can solve the technical problem of how to improve the efficiency of personnel detection. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the personnel detection method based on face recognition provided in the above-mentioned embodiment, and will not be elaborated here.

[0088] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned person detection method based on face recognition.

[0089] The computer program product provided in this application can solve the technical problem of how to improve the efficiency of personnel detection. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the personnel detection method based on face recognition provided in the above embodiment, which will not be repeated here.

[0090] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A person detection method based on face recognition, It is characterized in that The method comprises: Based on the preset edge computing component, the face image to be processed is analyzed to obtain a first face feature value; If the first facial feature value is successfully matched in the preset local feature value library, obtaining the identity information identifier corresponding to the first facial feature value; Matching the identity information identifier in a preset encrypted identity information database, determining the encrypted identity information, and updating the identity information identifier; The encrypted identity information is decrypted to obtain the target identity information.

2. The method according to claim 1, It is characterized in that The preset edge computing component and the preset local feature value library are deployed in a first local area network; The preset encrypted identity information database is deployed in the second local area network; The first local area network and the second local area network perform data communication via a preset network transmission protocol.

3. The method according to claim 1, It is characterized in that The step of parsing the face image to be processed based on the preset edge computing component to obtain the first face feature value includes: Based on the preset edge computing component, preprocessing the face image to be processed to obtain a preprocessed image, wherein the preprocessing includes one or more of grayscale processing, noise reduction processing and normalization processing; Based on a preset face detection algorithm, extracting a face region in the preprocessed image; Based on a preset feature extraction algorithm, feature extraction is performed on the face area, and the result of the feature extraction is encrypted to obtain the first face feature value.

4. The method according to claim 1, It is characterized in that After the step of parsing the face image to be processed based on the preset edge computing component to obtain the first face feature value, the method further includes: Determine a second facial feature value according to preset identity authentication history information, and generate an identity information identifier corresponding to the second facial feature value; The identity information identifier corresponding to the second facial feature value and the second facial feature value are stored in the preset local feature value library; The identity information identifier corresponding to the second facial feature value and the preset identity authentication history information are stored in the preset encrypted identity information library.

5. The method according to claim 4, It is characterized in that Before the step of obtaining the identity information identifier corresponding to the first facial feature value if the first facial feature value is successfully matched in the preset local feature value library, the method further includes: Traversing the preset local feature value library, and determining whether the identity information identifier corresponding to the first facial feature value exists in the preset local feature value library; If so, determining whether the matching degree between the second facial feature value and the first facial feature value exceeds a preset first matching degree threshold; If it exceeds, it is determined that the first facial feature value is successfully matched in the preset local feature value library; If not, it is determined that the first facial feature value fails to match in the preset local feature value library.

6. The method according to claim 1, It is characterized in that The step of matching the identity information identifier in a preset encrypted identity information database, determining the encrypted identity information, and updating the identity information identifier includes: Based on a preset query algorithm, the identity information identifier is used as a query key to perform query matching in the preset encrypted identity information database; Determine whether the matching degree between the query matching result and the query key exceeds a preset second matching degree threshold; If it exceeds, the data corresponding to the query matching result is used as the encrypted identity information, and the identity information identifier is regenerated based on the encrypted identity information. Based on the regenerated identity information identifier, the value of the corresponding identity information identifier in the preset encrypted identity information library and the preset local feature value library is updated.

7. The method according to claim 3, It is characterized in that After the step of decrypting the encrypted identity information to obtain the target identity information, the method further includes: Obtaining real-time behavior data corresponding to the target identity information; Performing the preprocessing on the real-time behavior data to obtain preprocessed behavior data; Extracting behavioral features from the preprocessed behavioral data; Based on the behavior analysis model in the preset edge computing component, identifying the behavior characteristics; If abnormal behavior is identified, the real-time behavior data is recorded and an alarm message is issued.

8. A person detection device based on face recognition, It is characterized in that The device comprises: A feature determination module, configured to analyze the face image to be processed based on a preset edge computing component to obtain a first face feature value; an identification acquisition module, configured to acquire an identity information identification corresponding to the first facial feature value if the first facial feature value is successfully matched in a preset local feature value library; The encrypted information determination module matches the identity information identifier in a preset encrypted identity information database, determines the encrypted identity information, and updates the identity information identifier; The target information determination module is used to decrypt the encrypted identity information to obtain the target identity information.

9. A computer device, It is characterized in that The device comprises: a memory, a processor, and a personnel detection program based on face recognition stored in the memory and executable on the processor, wherein the personnel detection program based on face recognition is configured to implement the steps of the personnel detection method based on face recognition as described in any one of claims 1 to 7.

10. A storage medium, It is characterized in that The storage medium stores a personnel detection program based on face recognition, and when the personnel detection program based on face recognition is executed by the processor, the steps of the personnel detection method based on face recognition as described in any one of claims 1 to 7 are implemented.