Method and device for identifying information of operating personnel, and computer program product

Abstract

The invention discloses a method and a device for identifying information of operating personnel and a computer program product. Relates to the field of artificial intelligence and big data, and the method comprises the steps: obtaining personnel images, collected by a terminal, of an operator in a preset time period, and obtaining a group of personnel images, the group of personnel images comprising a face image and a clothes image of the operator; first personnel features are extracted from the group of personnel images to obtain a group of first personnel features, the group of first personnel features are input into an image recognition model, a recognition result is output, and the image recognition model comprises a neural network module, an attention module and a fully-connected network module; the identification result is used for indicating whether the clothes of the operator are abnormal; and generating prompt information based on the identification result, and sending the prompt information to a client of the operator. According to the method and the device, the technical problems of low recognition accuracy and low efficiency when the information of the operating personnel is recognized in the prior art are solved.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and big data, and more specifically, to a method, apparatus, and computer program product for identifying information of workers. Background Technology

[0002] With the rapid development of communication technology, communication networks have become a key infrastructure driving social progress and economic development. Communication maintenance personnel, as the backbone of ensuring the stable operation of communication networks, are responsible for daily equipment inspection, maintenance, and troubleshooting. Their work safety is directly related to the quality of communication services and the safety of their lives. Communication base stations and equipment rooms operate in complex environments, often involving high-risk activities such as working at heights and with live electrical connections. Therefore, safety supervision of communication maintenance personnel during their work is indispensable.

[0003] Existing attendance systems and monitoring methods still face challenges and limitations. While biometric technologies such as fingerprint and early facial recognition can prevent proxy attendance to some extent, they are greatly affected by environmental factors, and their recognition rate and stability need improvement. Mobile location-based attendance systems rely on network signals and positioning technology; location drift and data upload failures affect the effectiveness and real-time nature of attendance. For example, paper attendance sheets are easily signed by proxy or missed, lacking data authenticity and traceability. Fixed electronic attendance machines depend on specific locations and are not suitable for dispersed work scenarios. Access control systems and offline attendance terminals are limited by fixed equipment and network coverage, making it difficult to fully cover mobile work areas, and posing risks of data delays and tampering. In addition, communication base stations are mostly located in remote areas, making on-site supervision costly and difficult, and making it difficult to monitor safety protection and behavioral norms during operations in a timely manner, resulting in poor safety risk control.

[0004] There are currently no effective solutions to the technical problems of low accuracy and low efficiency in identifying worker information in related technologies. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, and computer program product for identifying worker information, in order to solve the technical problems of low accuracy and low efficiency in identifying worker information in related technologies.

[0006] To achieve the above objectives, according to one aspect of this application, a method for identifying worker information is provided. The method includes: acquiring worker images collected by a terminal within a preset time period to obtain a set of worker images, wherein the set of worker images includes facial images and clothing images of the worker, and the preset time period includes at least a work start time and a work stop time; extracting first worker features from the set of worker images to obtain a set of first worker features, inputting the set of first worker features into an image recognition model, and outputting a recognition result, wherein the first worker features are used to indicate the worker's clothing features, the image recognition model includes a neural network module, an attention module, and a fully connected network module, the image recognition model processes the first worker features through the neural network module and the attention module, and the fully connected network module outputs the recognition result, the recognition result being used to indicate whether the worker's clothing is abnormal; generating a prompt message based on the recognition result, and sending the prompt message to the worker's client.

[0007] Furthermore, a set of first personnel features is input into the image recognition model, and the output recognition result includes: the neural network module performs scale transformation on the set of first personnel features to obtain a set of processed personnel features, and the processed personnel features are stitched together to obtain image feature data; the image feature data is input into the attention module, and the attention module performs secondary feature extraction on the image feature data to obtain extracted image feature data; the extracted image feature data is input into the fully connected network module; M equipment features are obtained, and the fully connected network module performs recognition on the extracted image feature data based on the M equipment features to obtain the recognition result, where the M equipment features refer to the features of the protective facilities worn by the workers, and M is a positive integer.

[0008] Further, acquiring personnel images of workers within a preset time period collected by the terminal to obtain a set of personnel images includes: sending image acquisition instructions to N terminals in the work area, wherein, when the N terminals receive the image acquisition instructions, initial personnel images of workers in the work area are acquired, where N is a positive integer; receiving a set of initial personnel images sent by the N terminals, and preprocessing each initial personnel image in each set of initial personnel images to obtain a set of personnel images, wherein the preprocessing methods include at least: size normalization processing, noise filtering processing, and data augmentation processing.

[0009] Furthermore, before inputting a set of first personnel features into the image recognition model and outputting the recognition result, the method further includes: receiving a list of workers, determining whether a worker is in the list, and obtaining a determination result, wherein the list of workers includes information on workers who perform work within a preset time period; if the determination result indicates that a worker is in the list, performing the step of inputting a set of first personnel features into the image recognition model; and if the determination result indicates that there are workers who are not in the list, generating an alarm message.

[0010] Furthermore, determining whether a worker is in the worker list includes: extracting a second worker feature from a set of worker images to obtain the second worker feature, wherein the second worker feature includes the worker's facial features and torso features; obtaining the worker's personnel information from the database based on the second worker feature, determining whether the worker information exists in the worker list, and obtaining the determination result.

[0011] Further, extracting first personnel features from each group of personnel images to obtain a set of first personnel features includes: obtaining a task list associated with the list of workers, wherein the task list refers to the task information of workers performing work within a preset time period; determining the task information of workers based on the task list when workers are in the list of workers; determining the clothing standard information of workers based on the task information, and extracting first personnel features from a group of personnel images based on the clothing standard information to obtain a set of first personnel features.

[0012] Furthermore, obtaining the task list associated with the list of operators includes: collecting meeting minutes from historical time periods, generating regional work plans based on the meeting minutes, and sending the regional work plans to the management personnel's client; and generating a task list based on the regional work plans upon receiving the verification approval information returned by the management personnel's client.

[0013] To achieve the above objectives, according to another aspect of this application, a device for identifying worker information is provided. The device includes: an acquisition unit, configured to acquire worker images collected by a terminal within a preset time period, obtaining a set of worker images, wherein the set of worker images includes facial images and clothing images of the worker, and the preset time period includes at least a work start time and a work stop time; an extraction unit, configured to extract first worker features from the set of worker images, obtaining a set of first worker features, and input the set of first worker features into an image recognition model, outputting a recognition result, wherein the first worker features are used to indicate the worker's clothing features, the image recognition model includes a neural network module, an attention module, and a fully connected network module, the image recognition model processes the first worker features through the neural network module and the attention module, and the fully connected network module outputs the recognition result, the recognition result being used to indicate whether the worker's clothing is abnormal; and a first generation unit, configured to generate prompt information based on the recognition result and send the prompt information to the worker's client.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the method for identifying the information of any of the above-mentioned operators.

[0015] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory storing an executable program, and the processor for running the program, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-described methods for identifying operator information.

[0016] According to another aspect of the present invention, a computer program product is also provided, the computer program product including a computer program, wherein when the computer program is executed by a processor, it implements the method for identifying the information of any of the above-described operators.

[0017] In this embodiment, the method of identifying worker information involves acquiring worker images collected by a terminal within a preset time period to obtain a set of worker images. Each set of worker images includes facial images and clothing images of the workers. The preset time period includes at least a start-of-work time period and a finish-of-work time period. First worker features are extracted from the set of worker images to obtain a set of first worker features. These first worker features are then input into an image recognition model, which outputs the recognition result. The first worker features are used to indicate the worker's clothing characteristics. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model uses the neural network module and the attention module to identify the first worker's clothing. The features are processed, and the recognition results are output by the fully connected network module. The recognition results are used to indicate whether there are any abnormalities in the clothing of the workers. Based on the recognition results, a prompt message is generated and sent to the worker's client. This solves the technical problems of low accuracy and low efficiency in the identification of worker information in related technologies. By acquiring a set of worker images collected by the terminal within a preset time period, extracting the first set of worker features from the set of worker images, inputting the first set of worker features into the image recognition model, outputting the recognition results, and generating prompt messages based on the recognition results, the technical effect of improving the accuracy of worker information identification is achieved, thereby ensuring the safety of the operation process. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a method for identifying information of operators;

[0020] Figure 2 This is a flowchart of a method for identifying operator information according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the image recognition model processing method provided in the embodiments of this application;

[0022] Figure 4 This is an illustration of an optional method for identifying operator information provided in an embodiment of this application. Figure 1 ;

[0023] Figure 5 This is an illustration of an optional method for identifying operator information provided in an embodiment of this application. Figure 2 ;

[0024] Figure 6 This is a schematic diagram of a device for identifying worker information according to an embodiment of this application;

[0025] Figure 7 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, this system has interfaces with relevant users or organizations to provide users with corresponding operation data for them to choose to agree to or refuse automated decision results. Before obtaining relevant information, a request for obtaining the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained after receiving consent from the aforementioned user or organization; if the user chooses to refuse, the expert decision-making process is initiated. Users can view the purpose of data use in real time through authorization decoding and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.

[0029] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize use or refuse use.

[0030] Example 1

[0031] According to an embodiment of this application, a method embodiment for identifying operator information is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a method for identifying operator information, such as... Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1 The processor 102 (which may include, but is not limited to, a microprocessor MCU (Microcontroller Unit) or a programmable gate array (FPGA)) is illustrated using 102a, 102b, ..., 102n. It also includes a memory 104 for storing data and a transmission device 106 for communication functions. In addition, it may include: a display, an input / output interface (I / O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a keyboard, a cursor control device, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for identifying worker information in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned method for identifying worker information. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) and a network interface, which can be connected to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a radio frequency (RF) module, used for wireless communication with the Internet.

[0036] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0037] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for identifying the information of the operators is shown. Figure 2 This is a flowchart of a method for identifying worker information according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0038] Step S201: Obtain personnel images of workers collected by the terminal within a preset time period to obtain a set of personnel images, wherein the set of personnel images includes facial images and clothing images of workers, and the preset time period includes at least: the work start time period and the work end time period.

[0039] Specifically, the terminal can refer to the smart device carried by the worker, or the terminal of the image acquisition equipment deployed in the work area, capable of acquiring on-site images and transmitting them in real time; the preset time period refers to the pre-set time window for workers to clock in, including the start and end time periods. To achieve worker identity verification, safety protection measures, and safety equipment inspection during maintenance operations, especially in remote work areas, the terminal first acquires facial and full-body clothing images of the workers, resulting in a set of personnel images. These images can be analyzed and confirmed to verify the worker's identity and the wearing status of safety equipment. The facial image is used for real-name verification, while the clothing image is used to check whether personal protective equipment such as safety helmets and vests are worn correctly, and whether necessary safety equipment (such as fire extinguishers and fire blankets) is available on-site.

[0040] Step S202: Extract first personnel features from a set of personnel images to obtain a set of first personnel features, and input the set of first personnel features into an image recognition model to output recognition results. The first personnel features are used to indicate the clothing features of the workers. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model processes the first personnel features through the neural network module and the attention module, and the fully connected network module outputs the recognition results. The recognition results are used to indicate whether there are any abnormalities in the clothing of the workers.

[0041] Specifically, after acquiring a set of personnel images, the primary personnel feature representing the clothing and attire of the workers can be extracted. This feature is then analyzed by an image recognition model composed of a neural network module, an attention module, and a fully connected network module. The model compares the images with standard feature information stored in a database to confirm the correctness of equipment wearing. After analysis, the recognition result is output. The primary personnel feature can include image features of personal protective equipment such as safety helmets, safety vests, insulating gloves, and reflective vests.

[0042] It should be noted that when the above image recognition model performs feature processing, the neural network module is based on the CenterNet network, which is a deep learning model for object detection. This network can perform CNN feature extraction, extracting multi-scale features from preprocessed images of on-site workers, safety protection measures, and safety materials, and then stitching them together to preserve all feature information of the image. That is, it extracts multi-level feature information from the first set of personnel features to obtain image feature data. The attention module is based on an attention mechanism module built on the Transformer architecture, which can focus on key areas in the image, such as the position of the safety helmet and the pattern of the safety vest, improving the model's recognition accuracy for these features. At the same time, it filters out irrelevant information in the background and outputs the attention calculation results. That is, it uses a multi-head self-attention mechanism to extract the most effective part of the feature information from the multi-scale feature model input, greatly improving the model's learning efficiency and ensuring that the model can obtain the information that most directly affects the judgment result. The fully connected network module is based on a fully connected network (MLP) based on the principle of multi-layer perceptron. The Perceptron module is constructed based on the features selected by the attention module. This module is responsible for the final classification decision, determining whether the safety equipment worn by the workers complies with regulations and whether there are any abnormalities, and outputting the results.

[0043] Step S203: Generate a prompt message based on the recognition result and send the prompt message to the operator's client.

[0044] Specifically, after obtaining the identification results, it is possible to immediately determine whether there are any abnormalities in the workers' safety equipment. If any abnormalities are found, such as not wearing a safety helmet or safety vest, a prompt message can be sent to the workers' client using an instant messaging protocol to remind them to make immediate adjustments. At the same time, the management personnel are notified to take appropriate measures to ensure that the workers are operating under safe conditions.

[0045] The method for identifying worker information provided in this application involves acquiring worker images collected by a terminal within a preset time period to obtain a set of worker images. Each set of worker images includes facial images and clothing images of the workers. The preset time period includes at least a start-of-work time period and a finish-of-work time period. First worker features are extracted from the set of worker images to obtain a set of first worker features. These first worker features are then input into an image recognition model, which outputs a recognition result. The first worker features are used to indicate the workers' clothing characteristics. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model uses the neural network module and the attention module to analyze the first worker features. The system processes the data and outputs the recognition results through a fully connected network module. These results indicate whether the workers' clothing is abnormal. Based on the recognition results, a prompt message is generated and sent to the workers' client. This solves the technical problems of low accuracy and low efficiency in identifying workers' information in related technologies. By acquiring a set of worker images collected by the terminal within a preset time period, extracting first personnel features from the set of images, inputting these first personnel features into an image recognition model, outputting recognition results, and generating prompt messages based on the recognition results, the system achieves the technical effect of improving the accuracy of worker information identification and ensuring safety during the operation.

[0046] Figure 3 This is a schematic diagram of the image recognition model processing method provided in the embodiments of this application, such as... Figure 3 As shown, optionally, in the method for identifying worker information provided in this application embodiment, inputting a set of first worker features into an image recognition model and outputting recognition results includes: scaling the set of first worker features by a neural network module to obtain a set of processed worker features, and stitching the set of processed worker features together to obtain image feature data; inputting the image feature data into an attention module, performing secondary feature extraction on the image feature data by the attention module to obtain extracted image feature data, and inputting the extracted image feature data into a fully connected network module; obtaining M equipment features, and using the fully connected network module to identify the extracted image feature data based on the M equipment features to obtain recognition results, wherein the M equipment features refer to the features of the protective facilities worn by the worker, and M is a positive integer.

[0047] Specifically, after extracting a set of initial personnel features, the image is first processed by a neural network module. This module effectively extracts features at different scales, ensuring the model can recognize safety equipment of various sizes, such as helmets and vests of different sizes. In other words, the neural network module performs scale transformation on the initial personnel features, adjusting feature images of different sizes to the model's expected input size to ensure consistency of input and processing efficiency. After scale transformation, the neural network module stitches the processed personnel features together to form complete image feature data.

[0048] Furthermore, the attention module based on the Transformer architecture performs secondary feature extraction on the aforementioned image feature data. Specifically, it focuses on key regions in the image most relevant to safety equipment, such as the shape of a safety helmet and the pattern of a safety vest, through an attention mechanism. This simultaneously reduces the impact of background noise, improving the model's accuracy and efficiency in identifying safety equipment. The attention module uses multi-head self-attention computation to analyze the complex relationships within the image feature data, identifying the most influential feature information for determining whether safety equipment is worn, and performing deep extraction to form more refined extracted image feature data.

[0049] It should be noted that after the attention module outputs the extracted image features, it can acquire equipment features that indicate the protective equipment worn by workers (such as safety helmets, safety vests, and insulating gloves). These equipment features can include shape, color, and material, and can be compared and analyzed with the extracted image feature data. The fully connected network module identifies the extracted image features based on the equipment features, determines whether the workers have correctly worn all necessary protective equipment as required, and then outputs the identification result, clearly indicating whether the workers' safety equipment meets the safety requirements of the work site.

[0050] This embodiment uses neural network scaling and splicing, secondary feature extraction through attention mechanism, and device feature recognition of fully connected network module to accurately identify the safety equipment wearing status of operators, ensuring personnel safety during operation, avoiding potential risks caused by inadequate safety protection measures, significantly improving the management efficiency of the work site, and reducing the cost of manual supervision.

[0051] Optionally, in the method for identifying worker information provided in this application embodiment, obtaining a set of worker images collected by the terminal within a preset time period includes: sending image acquisition instructions to N terminals in the work area, wherein, when the N terminals receive the image acquisition instructions, initial worker images of the workers in the work area are collected, where N is a positive integer; receiving a set of initial worker images sent by the N terminals, and preprocessing each initial worker image in each set of initial worker images to obtain a set of worker images, wherein the preprocessing method includes at least: size normalization processing, noise filtering processing, and data augmentation processing.

[0052] Specifically, when acquiring images of the workers, an image acquisition command is first sent via the network to multiple terminals deployed in the work area, requesting the terminals to capture images of the workers within a preset time period. The work area refers to the geographical area where maintenance work needs to be performed, such as the area surrounding a communication base station or equipment room. Upon receiving the image acquisition command, these terminals capture and upload raw images containing the real-time status of the workers' faces and full bodies, thus obtaining the initial personnel images.

[0053] After receiving the initial images of people, preprocessing steps are performed on each image to optimize image quality and improve the accuracy of subsequent recognition, thereby obtaining a set of images of people. For example, size normalization (to ensure that the input images have a uniform size), noise filtering (to remove interference factors in the image and improve the accuracy of subsequent processing), and data augmentation (such as increasing data diversity and enhancing the robustness of the model by means of rotation, flipping, brightness adjustment, etc.) can be performed to increase the generalization ability of the model and enable it to maintain high recognition accuracy when facing different types of data.

[0054] This embodiment ensures the uniformity and timeliness of image acquisition by sending standardized image acquisition instructions to intelligent terminals within the work area. Furthermore, through a comprehensive preprocessing procedure, it optimizes image quality, increases data reliability, and improves recognition accuracy, laying a solid foundation for subsequent image recognition and analysis.

[0055] Optionally, in the method for identifying worker information provided in this application embodiment, before inputting a set of first personnel features into an image recognition model and outputting the recognition result, the method further includes: receiving a list of workers, determining whether a worker is in the list of workers, and obtaining a determination result, wherein the list of workers includes information on workers who perform work within a preset time period; if the determination result indicates that a worker is in the list of workers, performing the step of inputting a set of first personnel features into an image recognition model; and if the determination result indicates that there are workers who are not in the list of workers, generating alarm information.

[0056] Specifically, before feature processing by the image recognition model, the identities of the workers need to be verified. This is achieved by first receiving a list of workers compiled by the organization's staff. This list details the information of all personnel scheduled to work within the preset time period, including their names, ID numbers, employee numbers, job responsibilities, insurance information, and special permit information. After collecting and processing the image features of the workers, to verify whether the person clocking in belongs to the list of workers for that day and to ensure the validity of the clocking-in process, the system can determine whether the worker is on the list based on the image features. If the worker's information matches the list, the person is considered authorized to work; otherwise, an anomaly is considered, potentially indicating an unauthorized person attempting to enter the work area.

[0057] If the assessment result indicates that the worker is indeed on the worker list, the image recognition process can continue. This involves processing a set of initial personnel features using a neural network module, an attention module, and a fully connected network module to check if the worker's safety equipment is worn in compliance with regulations. If the assessment result indicates the presence of personnel not on the worker list, an alarm message is generated to notify management that unauthorized personnel are attempting to enter the work area or are performing work, triggering appropriate safety checks and response measures.

[0058] This embodiment effectively verifies the identity of operators, ensuring that only authorized personnel can perform maintenance work within a preset time period. This not only strengthens access control to the work area but also creates the preconditions for subsequent safety equipment wearing inspections and work behavior supervision, preventing potential safety hazards from turning into actual accidents and enhancing the management of the work site.

[0059] Optionally, in the method for identifying worker information provided in this application embodiment, determining whether a worker is in the worker list includes: extracting a second worker feature from a set of worker images to obtain the second worker feature, wherein the second worker feature includes the worker's facial features and torso features; obtaining worker information from the database based on the second worker feature, determining whether worker information exists in the worker list, and obtaining a determination result.

[0060] Specifically, when determining whether workers are permitted to perform their duties, feature extraction is first performed on a set of collected personnel images. This extracts second-level personnel features, including the worker's face and torso, providing raw data for identity verification and safety equipment donning checks. Facial features can include biometric information such as facial contours, eyes, nose, and mouth, while torso features include the shape and position of safety equipment such as safety vests and insulated gloves. The facial features are then compared with personnel identity information stored in the database. Facial recognition technology confirms the worker's identity, providing their personnel information. Simultaneously, by comparing torso features, information about the safety equipment associated with the worker can be obtained, further verifying whether they meet the safety requirements for the day's work.

[0061] Furthermore, by comparing the personnel information obtained from the database with the list of operators, it can be determined whether the operator is on the list, i.e. whether they are the operators scheduled for the day, thus ensuring the safety of the maintenance operation process.

[0062] This embodiment accurately extracts second personnel features, including the face and torso, from personnel images. This not only ensures the authenticity of the on-site workers' identities but also quickly verifies whether they are correctly wearing safety equipment such as helmets and safety vests, meeting the safety requirements before work. It can also immediately detect and prevent any unauthorized personnel from attempting to enter the work area, thereby greatly enhancing the safety supervision of the work site, reducing operational risks, and improving operational efficiency and safety production management.

[0063] Optionally, in the method for identifying worker information provided in this application embodiment, extracting a first set of worker features from each group of worker images to obtain a set of first worker features includes: obtaining a task list associated with the worker list, wherein the task list refers to the task information of workers performing work within a preset time period; determining the worker's task information based on the task list when the worker is in the worker list; determining the worker's clothing standard information based on the task information, and extracting the first set of worker features from a group of worker images based on the clothing standard information to obtain a set of first worker features.

[0064] Specifically, feature extraction first requires obtaining the task list associated with the list of workers. This task list contains the specific work tasks for each worker within a preset time period, such as equipment inspection, troubleshooting, and software upgrades. This allows for the assignment of appropriate tasks based on the worker's identity and provides a basis for determining subsequent safety equipment wearing standards. Once the worker's identity is confirmed, the task list is used to query the current work task details for each worker. Based on different tasks, the corresponding clothing standards can be determined, such as wearing a safety helmet and safety vest for working at heights, and wearing insulated gloves and shoes for working with electricity. Finally, features can be extracted from the image based on this clothing characteristic information to obtain a set of first-level personnel features.

[0065] This embodiment achieves accurate matching of operator identity and task, and automatically determines the operator's clothing standard based on the nature of the task, thereby extracting the first personnel characteristics. This avoids safety hazards caused by improper equipment, greatly improves the level of safety supervision of on-site operations, reduces operational risks, and significantly improves the efficiency and compliance of maintenance operations.

[0066] Optionally, in the method for identifying operator information provided in this application embodiment, obtaining the task list associated with the operator list includes: collecting meeting minutes within a historical time period, generating a regional work plan based on the meeting minutes, and sending the regional work plan to the manager's client; and generating a task list based on the regional work plan upon receiving the verification approval information returned by the manager's client.

[0067] Specifically, to obtain the task list, meeting records from historical time periods can be collected first, such as daily safety briefing meeting videos, audio, and text messages. These records can include key elements such as worker identification information, safety training content, work instructions, and risk warnings. By analyzing historical meeting records, the operational needs, personnel allocation, and key safety points for each area can be summarized, generating a detailed regional work plan that provides clear guidance for subsequent work scheduling. The regional work plan is then sent to the management personnel's client, ensuring timely information delivery and effective communication.

[0068] Once the management personnel review and confirm the rationality of the regional work plan through the client, they can receive the verification approval information returned by the client. At this time, they can refine and generate a detailed list of each work task based on the approved regional work plan, including the list of workers, work time, location, task content and safety requirements, which is the task list.

[0069] This embodiment analyzes historical meeting records to generate work plans that meet safety standards and operational requirements. After remote approval by management personnel, the plans are refined into a detailed and feasible task list, ensuring the clarity and safety of the work tasks. This not only reduces human error and operational risks but also improves overall operational efficiency.

[0070] This application also provides a method for identifying operator information. Figure 4 This is an illustration of an optional method for identifying operator information provided in an embodiment of this application. Figure 1 ,like Figure 4 As shown, the method includes:

[0071] 1. Develop work plans: Collect work plans for the designated areas, match them with the assigned personnel, and confirm the work content and workload of the staff.

[0072] 2. Safety Briefing: Work tasks are confirmed through a safety briefing meeting. It should be noted that work tasks can be generated from meeting minutes, which involves identifying attendees and recording the content of the briefing, including images and audio. After the meeting, attendees sign the safety briefing, risk warning card, and emergency response card, and upload them to the management system. The briefing information for the day will be carried out during maintenance work. If no safety briefing was conducted that day, an on-site briefing at the base station is required before any work is carried out.

[0073] 3. Pre-operation check-in: The first check-in before the start of the operation, i.e., before the operation begins, can be determined based on the operation type, risk level, and management requirements, using either joint check-in or self-check-in. Joint check-in refers to a check-in method based on the system's video component, inviting management personnel to participate. During the check-in process, the real names of frontline workers are verified, and it is confirmed whether on-site personnel are wearing safety helmets and vests, and whether on-site safety supplies (fire extinguishers and fire blankets) are complete, ensuring the authenticity and reliability of the check-in. Self-check-in refers to the identification of maintenance personnel's faces, special operation certificates, and safety supplies (safety helmets, safety vests, fire extinguishers, fire blankets), etc., to determine whether the maintenance operation is compliant. The entire check-in process is recorded on video, improving check-in efficiency and reducing safety risks.

[0074] It should be noted that, in accordance with the safety requirements of the construction site, safety protective equipment such as safety helmets, insulated gloves, and reflective vests must be worn. An image recognition model based on YOLOv5 can be used to detect construction workers based on multimedia data such as videos and pictures, and extract the image features of the workers' heads, torsos, and hands. These features are then compared with the stored feature information of gloves, reflective clothing, and helmets to confirm the correct use of safety protective equipment. The entire calculation process is completed by an embedded device NPU (Neural Processing Unit), which is convenient for on-site deployment.

[0075] Specifically, the implementation of on-site check-in includes the following steps: Image acquisition and preprocessing: High-resolution cameras on frontline personnel terminals are used to collect images of workers' faces, safety helmets, safety vests, and safety supplies (fire extinguishers, fire blankets, etc.). Images are preprocessed to improve quality and adaptability. The preprocessing process includes size normalization to ensure input images have uniform dimensions, facilitating consistent feature information during training. Data augmentation is achieved by increasing data diversity through rotation, flipping, and brightness adjustments to enhance model robustness. Simultaneously, noise filtering techniques are used to remove interference factors from the images to some extent, improving the accuracy of subsequent processing. A deep neural network model is constructed for image recognition. It should be noted that during image recognition, the model can be optimized in real-time using a loss function. This loss function is an improvement on the original CenterNet loss function, replacing the traditional YOLOv5 binomial cross-entropy (BCE) loss with a focal loss. Its calculation formula is as follows: FL(P t )=-α(1-P t ) γ logP t Among them, P t : Adjusted predicted probability, α: class weight (balancing positive and negative samples), γ (focusing parameter): controls the degree of weight decay for easy and difficult samples. This loss function forms a quality adjustment factor through the focusing parameter. During model training, for samples that the model has already correctly classified (such as background), their loss contribution is reduced; for samples with low classification probability (such as blurry targets, small objects), high weights are retained to increase their loss contribution. Based on an image recognition model, attendance detection is performed, and the recognition results are output: First, images of workers' faces, safety helmets, safety vests, and safety equipment are acquired through high-resolution camera equipment and preprocessed, including size normalization, data augmentation, and noise filtering, to ensure the quality and adaptability of the input images. The preprocessed images are input into a target detection network based on the Transformer architecture for accurate target localization and recognition. During the detection process, not only are on-site workers identified for real-name verification, but also whether on-site workers are wearing safety helmets and safety vests, and whether on-site safety equipment is complete. Finally, based on the network output, the system combines the dual-check-in system for safe operations to evaluate the check-in status of workers, output the identification results, and ensure that safety protection measures are in place before allowing work to begin.

[0076] 4. In-process safety spot checks: According to management requirements, spot checks will be conducted at a certain ratio; during the spot checks, front-line workers will be connected remotely via video link, and the standardized operation of the work site will be strictly controlled according to the type of work, and a preliminary remote inspection will be carried out on the work content.

[0077] 5. Post-operation check-in: After the operation is completed, a "second" check-in is conducted to inspect the site environment, safety facilities and materials one by one to ensure that the environment is clean and orderly and materials are properly cleaned up, thus ending the safety supervision process.

[0078] The above method can be applied to a dual attendance system. Figure 5 This is an illustration of an optional method for identifying operator information provided in an embodiment of this application. Figure 2 ,like Figure 5 As shown, the dual attendance system can include a presentation layer, an application layer, a service layer, and a data layer. The presentation layer is associated with multiple clients. The application layer includes an operations and maintenance application, an operations and maintenance monitoring system, and a personnel management system. The operations and maintenance application can perform work order retrieval, on-site attendance, in-process spot checks, off-site attendance, image recognition, material recognition, and manual assisted recognition. The operations and maintenance monitoring system can perform qualification management, meeting management, plan management, work order dispatch, in-process spot checks, assisted recognition, and data visualization. The personnel management system can perform account management, personnel information management, face management, qualification management, image recognition, permission management, and data visualization. The service layer can perform image recognition analysis, big data processing, caching, load balancing, and cloud clustering. The data layer is associated with non-relational databases, relational databases, and distributed service clusters, and can perform data cleaning, data filtering, and data transformation operations.

[0079] This embodiment acquires a set of personnel images collected by the terminal within a preset time period, extracts a first personnel feature from the set of personnel images, inputs the first personnel feature into an image recognition model, outputs the recognition result, and generates prompt information based on the recognition result. This achieves the technical effect of improving the accuracy of identifying personnel information and ensuring safety during the operation.

[0080] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0081] Example 2

[0082] This application also provides a device for identifying worker information. It should be noted that this device can be used to execute the worker information identification method provided in this application. The worker information identification device provided in this application is described below.

[0083] According to an embodiment of this application, an apparatus for implementing the above-described method for identifying the information of operators is also provided. Figure 6 This is a schematic diagram of a device for identifying worker information according to an embodiment of this application, such as... Figure 6 As shown, the device includes: an acquisition unit 60, an extraction unit 61, and a first generation unit 62.

[0084] The acquisition unit 60 is used to acquire personnel images of workers collected by the terminal within a preset time period to obtain a set of personnel images, wherein the set of personnel images includes facial images and clothing images of the workers, and the preset time period includes at least: the work start time period and the work end time period.

[0085] Extraction unit 61 is used to extract first personnel features from a set of personnel images to obtain a set of first personnel features, and input the set of first personnel features into an image recognition model to output recognition results. The first personnel features are used to indicate the clothing features of the workers. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model processes the first personnel features through the neural network module and the attention module, and the fully connected network module outputs the recognition results. The recognition results are used to indicate whether there are any abnormalities in the clothing of the workers.

[0086] The first generation unit 62 is used to generate prompt information based on the recognition results and send the prompt information to the operator's client.

[0087] The worker information identification device provided in this application embodiment acquires worker images collected by a terminal within a preset time period through an acquisition unit 60, obtaining a set of worker images. The set of worker images includes facial images and clothing images of the workers. The preset time period includes at least a work start time and a work stop time. An extraction unit 61 extracts first worker features from the set of worker images, obtaining a set of first worker features, and inputs the set of first worker features into an image recognition model, outputting a recognition result. The first worker features are used to indicate the worker's clothing features. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model uses the neural network module and the attention module to analyze the first worker's clothing. The features are processed, and the recognition result is output by the fully connected network module. The recognition result is used to indicate whether there is any abnormality in the clothing of the workers. The first generation unit 62 generates a prompt message based on the recognition result and sends the prompt message to the client of the workers. This solves the technical problems of low recognition accuracy and low efficiency in the recognition of workers' information in related technologies. By acquiring a set of images of workers collected by the terminal within a preset time period, extracting the first personnel features from the set of personnel images, inputting the set of first personnel features into the image recognition model, outputting the recognition result, and generating a prompt message based on the recognition result, the technical effect of improving the accuracy of recognizing workers' information is achieved, thereby ensuring the safety of the operation process.

[0088] Optionally, in the identification device for worker information provided in this application embodiment, the extraction unit 61 includes: a transformation module, used to perform scale transformation on a set of first personnel features by a neural network module to obtain a set of processed personnel features, and to stitch together the set of processed personnel features to obtain image feature data; an input module, used to input the image feature data into an attention module, where the attention module performs secondary feature extraction on the image feature data to obtain extracted image feature data, and inputs the extracted image feature data into a fully connected network module; and a first acquisition module, used to acquire M equipment features, where the fully connected network module identifies the extracted image feature data based on the M equipment features to obtain an identification result, wherein the M equipment features refer to the features of the protective facilities worn by the worker, and M is a positive integer.

[0089] Optionally, in the identification device for worker information provided in this application embodiment, the acquisition unit 60 includes: a sending unit, used to send image acquisition instructions to N terminals in the work area, wherein when the N terminals receive the image acquisition instructions, initial worker images of the workers in the work area are acquired, where N is a positive integer; and a receiving module, used to receive a set of initial worker images sent by the N terminals, and preprocess each initial worker image in each set of initial worker images to obtain a set of worker images, wherein the preprocessing method includes at least: size normalization processing, noise filtering processing, and data augmentation processing.

[0090] Optionally, in the personnel information identification device provided in this application embodiment, the device further includes: a receiving unit, configured to receive a list of personnel, determine whether a personnel is in the list of personnel, and obtain a determination result before inputting a set of first personnel features into an image recognition model and outputting a recognition result, wherein the list of personnel includes information on personnel performing work within a preset time period; an execution unit, configured to execute the step of inputting a set of first personnel features into an image recognition model when the determination result indicates that a personnel is in the list of personnel; and a second generation unit, configured to generate alarm information when the determination result indicates that there are personnel among the personnel who are not in the list of personnel.

[0091] Optionally, in the identification device for worker information provided in this application embodiment, the acquisition unit 60 includes: an extraction module, used to extract a second worker feature from a set of worker images to obtain the second worker feature, wherein the second worker feature includes the worker's facial features and torso features; and a second acquisition module, used to obtain worker information from the database based on the second worker feature, determine whether worker information exists in the worker list, and obtain a determination result.

[0092] Optionally, in the identification device for worker information provided in this application embodiment, the extraction unit 61 includes: a third acquisition module, used to acquire a task list associated with the worker list, wherein the task list refers to the task information of workers performing work within a preset time period; a first determination module, used to determine the task information of workers based on the task list when the workers are in the worker list; and a second determination module, used to determine the clothing standard information of workers based on the task information, and extract a first set of first personnel features from a set of personnel images based on the clothing standard information.

[0093] Optionally, in the identification device for operator information provided in this application embodiment, the extraction unit 61 includes: a collection module, used to collect meeting records within a historical time period, generate a regional work plan based on the meeting records, and send the regional work plan to the manager's client; and a generation module, used to generate a task list based on the regional work plan upon receiving the verification approval information returned by the manager's client.

[0094] It should be noted that the acquisition unit 60, extraction unit 61, and first generation unit 62 mentioned above correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the above units and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0095] Example 3

[0096] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced with a mobile terminal or an electronic device, etc.

[0097] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0098] In this embodiment, the computer terminal described above can execute the program code for the following steps in the method for identifying worker information: acquiring worker images collected by the terminal within a preset time period to obtain a set of worker images, wherein the set of worker images includes facial images and clothing images of the worker, and the preset time period includes at least: the start time period and the end time period; extracting first worker features from the set of worker images to obtain a set of first worker features, and inputting the set of first worker features into an image recognition model to output a recognition result, wherein the first worker features are used to indicate the worker's clothing features, the image recognition model includes a neural network module, an attention module, and a fully connected network module, the image recognition model processes the first worker features through the neural network module and the attention module, and the fully connected network module outputs the recognition result, the recognition result is used to indicate whether the worker's clothing is abnormal; generating prompt information based on the recognition result, and sending the prompt information to the worker's client.

[0099] Optionally, the computer terminal described above can execute the following steps in the method for identifying the information of the workers: the neural network module performs a scaling transformation on a set of first personnel features to obtain a set of processed personnel features, and then concatenates the set of processed personnel features to obtain image feature data; the image feature data is input into the attention module, which performs secondary feature extraction on the image feature data to obtain extracted image feature data, and the extracted image feature data is input into the fully connected network module; M equipment features are obtained, and the fully connected network module identifies the extracted image feature data based on the M equipment features to obtain the identification result, wherein the M equipment features refer to the features of the protective facilities worn by the workers, and M is a positive integer.

[0100] Optionally, the computer terminal described above can execute the program code for the following steps in the method for identifying the information of the workers: sending image acquisition instructions to N terminals in the work area, wherein, when the N terminals receive the image acquisition instructions, initial personnel images of the workers in the work area are acquired, where N is a positive integer; receiving a set of initial personnel images sent by the N terminals, and preprocessing each initial personnel image in each set of initial personnel images to obtain a set of personnel images, wherein the preprocessing method includes at least: size normalization processing, noise filtering processing, and data augmentation processing.

[0101] Optionally, the computer terminal described above can execute the program code for the following steps in the method for identifying operator information: receiving a list of operators, determining whether an operator is in the list of operators, and obtaining a determination result, wherein the list of operators includes operator information for operators performing work within a preset time period; if the determination result indicates that an operator is in the list of operators, performing the step of inputting a set of first personnel features into an image recognition model; if the determination result indicates that there are operators who are not in the list of operators, generating alarm information.

[0102] Optionally, the computer terminal described above can execute the program code for the following steps in the method for identifying the information of operators: extracting a second personnel feature for each operator from a set of personnel images to obtain the second personnel feature, wherein the second personnel feature includes the operator's facial features and torso features; obtaining the operator's personnel information from the database based on the second personnel feature, determining whether the personnel information exists in the operator's list, and obtaining the determination result.

[0103] Optionally, the computer terminal described above can execute the program code for the following steps in the method for identifying the information of operators: obtaining a task list associated with the operator list, wherein the task list refers to the task information of operators performing operations within a preset time period; when an operator is in the operator list, determining the operator's task information based on the task list; determining the operator's clothing standard information based on the task information, and extracting a first set of first personnel features from a set of personnel images based on the clothing standard information.

[0104] Optionally, the aforementioned computer terminal can execute the program code for the following steps in the method for identifying operator information: collecting meeting minutes within a historical time period, generating a regional work plan based on the meeting minutes, and sending the regional work plan to the manager's client; upon receiving the verification approval information returned by the manager's client, generating a task list based on the regional work plan.

[0105] Optionally, Figure 7 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 7 As shown, the electronic device may include: one or more ( Figure 7 Only one of the following is shown: processor 702, memory 704, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module, and display.

[0106] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and apparatus for identifying worker information in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned method for identifying worker information. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0107] The processor can access the information and application programs stored in the memory via the transmission device to execute the steps described above in the method for identifying the information of the operators.

[0108] This application provides a scheme for identifying worker information. By acquiring worker images collected by a terminal within a preset time period, a set of worker images is obtained. This set of images includes facial images and clothing images of the workers. The preset time period includes at least a start-of-work time period and a finish-of-work time period. First worker features are extracted from the set of worker images to obtain a set of first worker features. These first worker features are then input into an image recognition model, and the recognition result is output. The first worker features are used to indicate the worker's clothing characteristics. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model processes the first worker features through the neural network module and the attention module, and outputs the recognition result through the fully connected network. The network module outputs recognition results, which are used to indicate whether there are any abnormalities in the clothing of the workers. Based on the recognition results, a prompt message is generated and sent to the worker's client. This solves the technical problems of low accuracy and low efficiency in the identification of worker information in related technologies. By acquiring a set of worker images collected by the terminal within a preset time period, extracting the first person feature from the set of images, inputting the first person feature into the image recognition model, outputting the recognition result, and generating a prompt message based on the recognition result, the technical effect of improving the accuracy of worker information identification is achieved, thereby ensuring the safety of the operation process.

[0109] Those skilled in the art will understand that Figure 7 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 7 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 7 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 7 The different configurations shown.

[0110] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0111] Example 4

[0112] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for identifying operator information provided in Embodiment 1.

[0113] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0114] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring personnel images of workers collected by the terminal within a preset time period to obtain a set of personnel images, wherein the set of personnel images includes facial images and clothing images of the workers, and the preset time period includes at least: the start time period and the end time period; extracting first personnel features from the set of personnel images to obtain a set of first personnel features, and inputting the set of first personnel features into an image recognition model to output a recognition result, wherein the first personnel features are used to indicate the clothing features of the workers, the image recognition model includes a neural network module, an attention module, and a fully connected network module, the image recognition model processes the first personnel features through the neural network module and the attention module, and the fully connected network module outputs the recognition result, the recognition result is used to indicate whether there is any abnormality in the clothing of the workers; generating prompt information based on the recognition result, and sending the prompt information to the client of the workers.

[0115] This application also provides a computer program product, which, when executed on a data processing device, is suitable for performing steps of a method for identifying information of operators.

[0116] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0117] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0121] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0122] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for identifying information about workers, characterized in that, include: The system acquires images of workers collected by the terminal within a preset time period to obtain a set of worker images, wherein the set of worker images includes facial images and clothing images of the workers, and the preset time period includes at least: the start time period and the end time period. First personnel features are extracted from the set of personnel images to obtain a set of first personnel features. The set of first personnel features is then input into an image recognition model to output a recognition result. The first personnel features are used to indicate the clothing features of the workers. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model processes the first personnel features through the neural network module and the attention module, and the fully connected network module outputs the recognition result. The recognition result is used to indicate whether there is any abnormality in the clothing of the workers. Based on the recognition results, a prompt message is generated and sent to the operator's client.

2. The method according to claim 1, characterized in that, The first set of personnel features is input into the image recognition model, and the output recognition results include: The neural network module performs a scale transformation on the first set of personnel features to obtain a set of processed personnel features, and then concatenates the set of processed personnel features to obtain image feature data; The image feature data is input into the attention module, which performs secondary feature extraction on the image feature data to obtain the extracted image feature data. The extracted image feature data is then input into the fully connected network module. M device features are obtained, and the fully connected network module identifies the extracted image feature data based on the M device features to obtain the identification result. The M device features refer to the features of the protective equipment worn by the operator, and M is a positive integer.

3. The method according to claim 1, characterized in that, The system acquires personnel images collected by the terminal within a preset time period, resulting in a set of personnel images including: Image acquisition instructions are sent to N terminals in the work area. Upon receiving the image acquisition instructions, initial personnel images of the workers within the work area are acquired. N is a positive integer; The system receives a set of initial personnel images sent by the N terminals, and preprocesses each initial personnel image in each set of initial personnel images to obtain the set of personnel images. The preprocessing methods include at least: size normalization processing, noise filtering processing, and data augmentation processing.

4. The method according to claim 1, characterized in that, Before inputting the first set of person features into the image recognition model and outputting the recognition result, the method further includes: Receive a list of workers, determine whether the workers are in the list, and obtain a determination result, wherein the list of workers includes information on workers who performed work within the preset time period; If the judgment result indicates that the operator is in the operator list, the step of inputting the first set of personnel features into the image recognition model is performed; If the judgment result indicates that there are workers who are not on the list of workers, an alarm message is generated.

5. The method according to claim 4, characterized in that, Determining whether the operator is in the operator list includes: The second personnel feature is extracted from each worker in the set of personnel images to obtain the second personnel feature, wherein the second personnel feature includes the worker's facial features and torso features; Based on the second personnel characteristics, the personnel information of the operators is obtained from the database, and it is determined whether the personnel information exists in the list of operators, thus obtaining the determination result.

6. The method according to claim 1, characterized in that, Extract the first person feature from each group of people images to obtain a first person feature set including: Obtain the task list associated with the list of workers, wherein the task list refers to the task information of the workers who will be performing the work within the preset time period; If the operator is in the operator list, the operator's task information is determined based on the task list; Based on the task information, the clothing standard information of the workers is determined, and the first personnel feature is extracted from the group of personnel images according to the clothing standard information to obtain the first personnel feature.

7. The method according to claim 6, characterized in that, The task list associated with the list of operators includes: Collect meeting minutes from a historical time period, generate regional work plans based on the meeting minutes, and send the regional work plans to the administrator's client. Upon receiving the verification approval information returned by the administrator's client, the task list is generated according to the regional work plan.

8. A device for identifying worker information, characterized in that, include: The acquisition unit is used to acquire personnel images of workers collected by the terminal within a preset time period to obtain a set of personnel images, wherein the set of personnel images includes facial images and clothing images of the workers, and the preset time period includes at least: the work start time period and the work end time period. An extraction unit is configured to extract a first set of personnel features from the set of personnel images, obtain a set of first personnel features, input the set of first personnel features into an image recognition model, and output a recognition result. The first personnel features are used to indicate the clothing features of the workers. The image recognition model includes a neural network module, an attention module, and a fully connected network module. The image recognition model processes the first personnel features through the neural network module and the attention module, and the fully connected network module outputs the recognition result. The recognition result is used to indicate whether there is any abnormality in the clothing of the workers. The first generation unit is used to generate prompt information based on the recognition result and send the prompt information to the operator's client.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the method for identifying the information of the operator as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for identifying information of operators as described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method for identifying the information of the operator as described in any one of claims 1 to 7.

Images