Wearable device-based management method, system, electronic device, and medium

Abstract

The application relates to a wearable device management method and system, an electronic device and a storage medium, the method comprising the following steps: creating a management task through a management platform; when the wearable device receives the management task, starting to collect a video, inputting the collected target video into a trained AI model to detect the device operation and personnel behavior, inputting the generated detection result into an intelligent analysis system to obtain an analysis result, generating an alarm information if the analysis result is abnormal, generating an alarm record when the management platform receives the alarm information, issuing an alarm prompt, statistically analyzing the analysis result and the alarm information, and pushing the statistical analysis result to designated personnel; and the application solves the problems that in the related art, device fault abnormalities or personnel rule violations cannot be managed simultaneously, and the production capacity and safety of an enterprise cannot be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the wearable technology field, in particular to a wearable device-based management method and system, an electronic device and a storage medium. BACKGROUND

[0002] At present, wearable devices such as AR smart glasses or helmets have been applied to many industry scenarios, including power, aviation, rail transit, transportation, fire fighting, infrastructure, semiconductor and other industries. However, the application of wearable devices in enterprise factory equipment inspection and personnel behavior management still has the following shortcomings: on the one hand, the existing AR smart glasses or helmets cannot identify and judge device fault abnormalities or personnel violation behaviors, and cannot handle them immediately when device fault abnormalities or personnel violation behaviors occur, which has poor flexibility and timeliness, cannot guarantee the production safety of the enterprise factory, and cannot help improve the production capacity of the enterprise, causing serious economic losses to the enterprise; on the other hand, the related technology does not establish a complete intelligent management system, and cannot query and trace data of device fault abnormalities or personnel violation behaviors.

[0003] Therefore, the above problems need to be solved. SUMMARY

[0004] The embodiments of the present application provide a wearable device management method, system, electronic device and storage medium to at least solve the problems that related technologies cannot simultaneously manage device fault abnormalities or personnel violation behaviors and cannot help improve the production capacity and safety of enterprises.

[0005] In a first aspect, the embodiments of the present application provide a wearable device management method, which comprises the following steps:

[0006] Creating a management task through a management platform;

[0007] When the wearable device receives the management task, start collecting videos;

[0008] Input the collected target video into a trained AI model to detect the device running condition and personnel behavior, input the generated detection result into an intelligent analysis system to obtain an analysis result;

[0009] If the analysis result is abnormal, generate an alarm information; wherein the target video is obtained by the wearable device worn by the inspection personnel during the enterprise inspection;

[0010] When the management platform receives the alarm information, generate an alarm record, issue an alarm prompt, and statistically analyze the analysis result and the alarm information, and push the result after statistical analysis to designated personnel.

[0011] In some embodiments, after the collected target video is input into the trained AI model to detect the device operation and personnel behavior, the method further comprises:

[0012] If the analysis result is normal, a task result is generated, and the management platform generates a task record based on the task result;

[0013] When receiving a task viewing instruction, a task viewing interface is displayed, wherein the task viewing interface displays at least task progress and task completion.

[0014] In some embodiments, when the management platform receives an alarm information, an alarm record is generated, and an alarm prompt is issued, and the method further comprises:

[0015] An alarm prompt interface is displayed through the management platform, and when the alarm prompt interface receives a click instruction, alarm information is displayed, wherein the alarm information at least includes alarm type, violation content, and recording file at the time of alarm occurrence.

[0016] In some embodiments, when the wearable device has a camera, before the generated detection result is input into the intelligent analysis system to obtain an analysis result, the method further comprises:

[0017] A plurality of analysis rules are configured for the intelligent analysis system; wherein the analysis rules at least include device operation analysis rules and personnel behavior analysis rules.

[0018] In some embodiments, when the wearable device has a microphone, after the wearable device receives the management task and starts collecting video, the method further comprises:

[0019] Audio content is collected through the microphone, and the audio content is converted into text content;

[0020] The text content and the video are merged, and after the merged file is stored to the management platform, the AI model detects the device operation and personnel behavior based on the merged file.

[0021] In some embodiments, the detection of the device operation and personnel behavior by inputting the collected target video into the trained AI model comprises:

[0022] The device operation in the target video is detected through a built-in device algorithm, wherein the device at least includes one or more of a device with a chain, a device with a transmission belt, a device with a material port, or a zipper machine;

[0023] detecting, by a built-in behavior algorithm, a personnel violation behavior in the target video, wherein the personnel violation behavior at least includes one or more of the following behaviors: not wearing a safety helmet, not wearing a work uniform, not wearing a protective suit, smoking, making a phone call, crossing a boundary, or sleeping.

[0024] In some embodiments, the detecting, by the built-in device algorithm, the device operation in the target video includes:

[0025] When it is detected by the AI model that the device in the target video is a chain, determining, by a built-in chain algorithm corresponding to the chain, a marking point at which a belt on the chain normally conveys materials; comparing a residence time of the belt on the chain in the target video at the marking point with a preset residence time to obtain a comparison result, and generating the detection result based on the comparison result; or,

[0026] When it is detected by the AI model that the device in the target video has a material port, determining, by a built-in material blocking algorithm corresponding to the material port, an average height of material accumulation in the material port, marking an upper limit value of the average height to obtain a marked height, comparing an actual height of material accumulation in the material port in the target video with the marked height to obtain a comparison result, and generating the detection result based on the comparison result.

[0027] In a second aspect, the embodiments of the present application provide a management system based on a wearable device, the system comprising:

[0028] A creating unit configured to create a management task through a management platform;

[0029] A collecting unit configured to start collecting a video when the wearable device receives the management task;

[0030] A detecting unit configured to input a target video collected into a trained AI model to detect a device operation and a personnel behavior;

[0031] An analyzing unit configured to input a generated detection result into an intelligent analysis system to obtain an analysis result;

[0032] An alarming unit configured to generate an alarm information if the analysis result is abnormal; wherein the target video is obtained by a wearable device worn by a patrol personnel during enterprise patrol; when the management platform receives the alarm information, an alarm record is generated, and an alarm prompt is sent out;

[0033] A pushing unit configured to statistically analyze the analysis result and the alarm information, and push a result of the statistical analysis to a designated personnel.

[0034] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the management method of the wearable device according to the first aspect when executing the computer program.

[0035] In a fourth aspect, a storage medium is provided, which stores a computer program executable by a processor to implement the management method of the wearable device according to the first aspect.

[0036] Compared with the related art, in the technical solution of the embodiment, the management platform creates a management task, when the wearable device receives the management task, starts to collect a video, inputs the collected target video into a trained AI model to detect the device operation and the personnel behavior, inputs the generated detection result into an intelligent analysis system to obtain an analysis result, and if the analysis result is abnormal, generates an alarm information to enable the on-site inspection personnel to find the abnormal information, so that corresponding measures can be taken in time. In this way, not only the normal operation of the enterprise production device is ensured and the production efficiency is improved, but also the safety hidden danger caused by the worker's illegal behavior is avoided, the safety is improved, the management platform receives the alarm information, generates an alarm record, issues an alarm prompt, and statistically analyzes the analysis result and the alarm information, and pushes the result after the statistical analysis to the designated personnel. In this way, even if not on site, the management of the identification of the device fault abnormality and the personnel illegal behavior in the enterprise factory device inspection process is realized, the flexibility and timeliness of the management are improved, the economic loss caused by the device fault abnormality and the personnel illegal behavior is reduced, the designated personnel can check at any time, the query and data tracing of the device fault abnormality or the personnel illegal behavior are realized, and the problems that the device fault abnormality or the personnel illegal behavior cannot be managed simultaneously and the production capacity and safety of the enterprise cannot be improved in the related art are solved. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application and illustrate the illustrative embodiments of the present application and the description thereof serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0038] Figure 1 is a first flowchart of the management method of the wearable device according to the embodiment of the present application;

[0039] Figure 2 is a second flowchart of the management method of the wearable device according to the embodiment of the present application;

[0040] Figure 3 is a structural block diagram of the management system based on the wearable device according to the embodiment of the present application;

[0041] Figure 4 FIG. 8 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application and not to limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort fall within the scope of the present application. In addition, it should be understood that, although the efforts made in this development process can be complex and lengthy, some design, manufacture or production changes made on the basis of the technical content disclosed in the present application by those of ordinary skill in the art related to the content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the content disclosed in the present application.

[0043] Reference to "an embodiment" in this application means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that the embodiments described in this application are merely possible embodiments and that other embodiments can be made and utilized without departing from the scope of the application. In particular, those skilled in the art will recognize that elements from the embodiments can be employed in a modular fashion to construct other embodiments.

[0044] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application means two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The terms “first,” “second,” “third,” etc., used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0045] This application provides a method for managing wearable devices. Figure 1 This is a first flowchart of a wearable device management method according to an embodiment of this application, such as... Figure 1 As shown, in one embodiment of the present invention, the wearable device management method proposed by the present invention includes the following steps:

[0046] Step S101: Create a management task through the management platform; of course, in other embodiments, the management task can also be created through the wearable device after logging in; in addition, in this embodiment, before creating the management task through the management platform, the method further includes: logging into the management platform;

[0047] It should be noted that in other embodiments, this management task may also be referred to as creating a walking management task or something else. Correspondingly, in other embodiments, the management platform may also be referred to as an intelligent AR walking management platform or something else. No specific limitation is made here.

[0048] Step S102: When the wearable device receives the management task, it starts to collect video. The wearable device includes, but is not limited to, AR glasses, AR helmets or other wearable devices. In this embodiment, the wearable device is implemented using AR glasses, which include: a virtual screen, a microphone, a camera, an audio collector, a SIM card module, a wireless protocol, GPS, etc. Since those skilled in the art know the functions of the above components, they will not be described in detail here.

[0049] Step S103, input the collected target video into the trained AI model to detect the device operation and personnel behavior, input the generated detection result into the intelligent analysis system to obtain an analysis result; in this way, the device fault anomaly and personnel irregular behavior can be easily identified in the enterprise factory device inspection process.

[0050] It should be noted that the AI model in the present embodiment can be implemented by using an existing machine learning model or other neural network model. As can be easily understood, the trained AI model is obtained when the loss corresponding to the existing machine learning model converges; for example, the training process can be as follows: first, determine whether the collected video has a device fault anomaly or personnel irregular behavior by artificial research and judgment, and label the above-mentioned video, then input the labeled video into the machine learning model for training to iteratively enhance the identification and analysis capability of the intelligent analysis system, until the trained AI model is obtained when the loss corresponding to the machine learning model converges. Since those skilled in the art know the specific process and implementation steps of training the AI model, they will not be described here. In addition, those skilled in the art know that the intelligent analysis system can use an existing AI analysis algorithm or software program to analyze the generated detection result and obtain an analysis result, so this will not be described here.

[0051] Step S104, if the analysis result is abnormal, generate an alarm information; wherein the alarm information can be device fault anomaly alarm information or personnel irregular behavior alarm information, which is not limited here; in addition, the wearable device can prompt by text or voice when generating the alarm information, so that the on-site inspection personnel can find abnormal information and take corresponding measures in time, so as to not only ensure the normal operation of the enterprise production device and improve the production efficiency, but also avoid the safety hazards caused by the irregular behavior of workers and improve the safety; wherein the target video is obtained by the wearable device worn by the inspection personnel during the enterprise inspection;

[0052] Step S105, when the management platform receives the alarm information, generate an alarm record, issue an alarm prompt, and statistically analyze the analysis result and the alarm information, and push the statistical analysis result to the designated personnel. In this way, even if not on site, the identification of device fault anomaly and personnel irregular behavior in the enterprise factory device inspection process can be managed, the flexibility and timeliness of management are improved, the economic loss caused by device fault anomaly and personnel irregular behavior is reduced, and the designated personnel can check at any time to realize the query and data traceability of device fault anomaly or personnel irregular behavior.

[0053] Through steps S101 to S105 above, in the technical solution of this embodiment, a management task is created through the management platform. When the wearable device receives the management task, it begins to collect video. The collected target video is input into a trained AI model to detect the equipment operation and personnel behavior. The generated detection results are input into the intelligent analysis system to obtain the analysis results. If the analysis results are abnormal, an alarm message is generated so that the on-site inspection personnel can discover the abnormal information and take corresponding measures in a timely manner. In this way, not only is the normal operation of the enterprise's production equipment guaranteed and production efficiency is improved, but safety hazards caused by workers' violations can also be avoided, thus improving safety. When the management platform receives the alarm message, it generates an alarm record, issues an alarm prompt, and performs statistical analysis on the analysis results and alarm information, and pushes the statistical analysis results to designated personnel. In this way, even when not on-site, it is possible to manage the identification of equipment malfunctions and personnel violations during the inspection of factory equipment, improving the flexibility and timeliness of management, reducing economic losses caused by equipment malfunctions and personnel violations, and allowing designated personnel to view the data at any time, enabling querying and tracing of equipment malfunctions or personnel violations. This solves the problem that related technologies cannot simultaneously manage equipment malfunctions or personnel violations and cannot help improve the production capacity and safety of enterprises.

[0054] Figure 2 This is a second flowchart of a wearable device management method according to an embodiment of this application, such as... Figure 2 As shown, to facilitate personnel inspection of factory equipment and management of personnel behavior, in some embodiments, after inputting the collected target video into a trained AI model to detect equipment operation and personnel behavior, the method further includes the following steps:

[0055] If the analysis results are normal, the task results are generated, and the management platform generates task records based on these results.

[0056] When a task viewing command is received, a task viewing interface is displayed. This interface shows at least the task progress and completion status, providing data support for user management decisions.

[0057] To facilitate the reconstruction of alarm scenarios, in one optional embodiment, when the management platform receives alarm information, it generates an alarm record and issues an alarm notification. Simultaneously, the method further includes the following steps:

[0058] The management platform displays an alarm notification interface. When the alarm notification interface receives a click command, it displays alarm information, which includes at least the alarm type, the content of the violation, and a recording file of the time the alarm occurred.

[0059] In order to improve the accuracy of the intelligent analysis system, in some embodiments, when the wearable device has a camera, before the generated detection result is input into the intelligent analysis system to obtain an analysis result, the method further includes the following steps:

[0060] A plurality of analysis rules are configured for the intelligent analysis system; wherein the analysis rules at least include device operation analysis rules and personnel behavior analysis rules. It is easy to understand that only after the intelligent analysis system is configured with a plurality of analysis rules, the intelligent analysis system can receive the generated detection result, and based on each of the plurality of analysis rules, the corresponding analysis result is obtained; in addition, each analysis rule is set according to the actual needs of the user, which is not limited here.

[0061] In the application scenario, during the process of the inspection personnel wearing the wearable device to walk in the indoor or outdoor scene, not only video content can be collected, but sometimes audio content can also be collected. In order to improve the detection effect, in some embodiments, when the wearable device has a microphone, after the wearable device starts collecting video when receiving the management task, the method further includes the following steps:

[0062] Audio content is collected through the microphone, and the audio content is converted into text content;

[0063] The text content is merged with the video, and after the merged file is stored to the management platform, when the AI model receives the merged file, the device operation and the personnel behavior are detected based on the merged file.

[0064] In order to facilitate the detection of device fault abnormalities and personnel irregular behaviors, in some embodiments, the steps of inputting the collected target video into the trained AI model to detect the device operation and the personnel behavior include the following steps:

[0065] The device operation in the target video is detected by a built-in device algorithm, wherein the device at least includes one or more of a device with a chain, a device with a transmission belt, a device with a material port, or a zipper machine; of course, in other embodiments, the device can also be other, which is not limited here, as long as the management method of the wearable device corresponding to the present application is used, it is within the protection scope of the present application.

[0066] The personnel irregular behavior in the target video is detected by a built-in behavior algorithm, wherein the personnel irregular behavior at least includes one or more of the following behaviors: not wearing a safety helmet, not wearing a work uniform, not wearing a protective suit, smoking, making a phone call, crossing the boundary, or sleeping. Of course, in other embodiments, the personnel irregular behavior can also be other, which is not limited here, as long as the management method of the wearable device corresponding to the present application is used, it is within the protection scope of the present application.

[0067] It should be noted that the built-in behavior algorithm and the built-in device algorithm can be realized by existing software programs or algorithms, and the specific software programs or algorithms are not limited here.

[0068] In a preferred embodiment, the detection of the device operation in the target video by the built-in device algorithm includes the following steps:

[0069] When the device in the target video is detected by the AI model as a chain, the built-in chain algorithm corresponding to the chain is used to determine the marking point when the belt on the chain normally conveys the material, the residence time of the belt on the chain in the target video passing through the marking point is compared with the preset residence time to obtain a comparison result, and a detection result is generated based on the comparison result; or,

[0070] When the device in the target video is detected by the AI model as having a material port, the built-in material blocking algorithm corresponding to the material port is used to determine the average height of the material accumulation in the material port, the upper limit value of the average height is marked to obtain a marking height, the actual height of the material accumulation in the material port in the target video is compared with the marking height to obtain a comparison result, and a detection result is generated based on the comparison result.

[0071] In another preferred embodiment, inputting the collected target video into the trained AI model to detect the device operation and the personnel behavior further includes the following steps:

[0072] When the personnel behavior is detected by the AI model, the built-in safety helmet detection algorithm is used to determine whether the personnel in the video wear a safety helmet, and output the corresponding detection result; for example, the built-in safety helmet detection algorithm is used to mark according to the size and shape of the safety helmet, combined with the human body shape, and compare whether the human body shape head part of the on-site collected video picture frame conforms to the marked safety helmet feature track, so that the intelligent analysis system receives the detection result and reminds the relevant personnel of the notification system.

[0073] When the built-in phone call detection algorithm is used to determine that the personnel in the video are making a phone call, the corresponding detection result is output; for example, the built-in phone call detection algorithm is used to mark according to the average size and shape of the mobile phone, combined with the human body shape, and compare whether the human body shape and the mobile phone combined part of the on-site collected video picture frame conforms to the marked phone call feature track, so that the intelligent analysis system receives the detection result and reminds the relevant personnel of the notification system.

[0074] When the built-in non-workwear algorithm is used to determine that the personnel in the video do not wear workwear, the corresponding detection result is output.

[0075] When the built-in non-protection clothing algorithm is used to determine that the personnel in the video do not wear protection clothing, the corresponding detection result is output.

[0076] When it is determined through the built-in smoking detection algorithm that the personnel in the video are smoking, a corresponding detection result is outputted;

[0077] When it is determined through the built-in sleeping detection algorithm that the personnel in the video are sleeping, a corresponding detection result is outputted. Since those skilled in the art can easily realize the functions of the above-mentioned built-in safety helmet detection algorithm, built-in work clothes algorithm, built-in smoking detection algorithm and built-in phone call detection algorithm through existing software algorithms and programs, they will not be described here.

[0078] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that described here.

[0079] The embodiment also provides a wearable device-based management system for implementing the above-mentioned embodiments and preferred embodiments, which have been described and will not be described here. As used below, the terms "module", "unit", "sub-unit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware or a combination of software and hardware can also be implemented and conceived.

[0080] Figure 3 is a structural block diagram of a wearable device-based management system according to the embodiments of the present application, as shown in Figure 3 The system comprises:

[0081] The creating unit 31 is configured to create a management task through the management platform;

[0082] The collecting unit 32 is configured to start collecting a video when the wearable device receives the management task;

[0083] The detection unit 33 is configured to input the collected target video into the trained AI model to detect the device operation and personnel behavior;

[0084] The analysis unit 34 is configured to input the generated detection result into an intelligent analysis system to obtain an analysis result;

[0085] The alarm unit 35 is configured to generate an alarm information if the analysis result is abnormal; wherein the target video is obtained by a wearable device worn by a patrol personnel during enterprise patrol; when the management platform receives the alarm information, an alarm record is generated and an alarm prompt is sent out;

[0086] The push unit 36 is configured to statistically analyze the analysis result and the alarm information, and push the analyzed result to a designated person. In the system, a management task is created by the management platform, when the wearable device receives the management task, the wearable device starts to collect videos, and the collected target videos are input into the trained AI model to detect the device operation and the personnel behavior, the generated detection result is input into the intelligent analysis system to obtain an analysis result, if the analysis result is abnormal, an alarm information is generated, so that the on-site inspection personnel can find abnormal information, and corresponding measures can be taken in time. In this way, not only the normal operation of the enterprise production device is ensured, and the production efficiency is improved, but also the safety hidden danger caused by the worker's illegal behavior is avoided, and the safety is improved. When the management platform receives the alarm information, an alarm record is generated, an alarm prompt is sent, and the analysis result and the alarm information are statistically analyzed, and the analyzed result is pushed to the designated person. In this way, even if the designated person is not on site, the management of the device fault abnormality and the personnel illegal behavior in the enterprise factory equipment inspection process can be realized, the flexibility and timeliness of the management are improved, the economic loss caused by the device fault abnormality and the personnel illegal behavior is reduced, and the designated person can check at any time, the device fault abnormality or the personnel illegal behavior is queried and data is traced back, and the problems that the device fault abnormality or the personnel illegal behavior cannot be managed simultaneously and the production capacity and the safety of the enterprise cannot be improved in the related technologies are solved.

[0087] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented by software or hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor, or each of the above modules can be located in different processors in any combination.

[0088] The application further provides an electronic device including a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the management method of the wearable device.

[0089] Optionally, the electronic device can further include a transmission device and an input and output device, wherein the transmission device is connected with the processor, and the input and output device is connected with the processor.

[0090] Optionally, in the embodiment, the processor can be configured to execute the following steps by the computer program:

[0091] Step S101, creating a management task by a management platform;

[0092] Step S102, when the wearable device receives the management task, starting to collect videos;

[0093] Step S103, input the collected target video into the trained AI model to detect the equipment operation and personnel behavior, input the generated detection result into the intelligent analysis system to obtain an analysis result;

[0094] Step S104, if the analysis result is abnormal, generate an alarm information; wherein, the target video is obtained by a wearable device worn by a patrol personnel in the process of enterprise patrol;

[0095] Step S105, when the management platform receives the alarm information, generate an alarm record, issue an alarm prompt, and statistically analyze the analysis result and the alarm information, and push the statistical analysis result to a designated personnel.

[0096] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and this embodiment will not be repeated here.

[0097] In addition, in combination with the wearable device management method in the above embodiments, the application embodiment can provide a storage medium for implementation. The storage medium has a computer program stored thereon; the computer program is executed by a processor to implement any one of the wearable device management methods in the above embodiments.

[0098] In one embodiment, a computer device is provided, which can be a terminal. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a wearable device management method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0099] In one embodiment, Figure 4 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the application, as Figure 4 shown, an electronic device is provided, which can be a server, and the internal structure diagram of the electronic device can be as Figure 4As shown. The electronic device includes a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with external terminals through network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program, the computer program is executed by the processor to implement a wearable device management method, and the database is used to store data.

[0100] Those skilled in the art can understand that, Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0101] Those skilled in the art should understand that each technical feature of the above-mentioned embodiments can be combined arbitrarily, and in order to make the description concise, each technical feature in the above-mentioned embodiments is not described in all possible combinations, however, as long as the combination of technical features does not exist contradictory, it should be considered as the scope of the present application.

[0102] The above-mentioned embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.

Claims

1. A management method based on wearable devices, characterized in that, The method includes: Create management tasks through the management platform; When the wearable device receives the management task, it begins to collect video. The collected target video is input into the trained AI model to detect the equipment operation and personnel behavior. The generated detection results are then input into the intelligent analysis system to obtain the analysis results. If the analysis results are abnormal, an alarm message is generated; wherein, the target video is captured by the wearable device worn by the inspection personnel during the enterprise inspection. When the management platform receives alarm information, it generates an alarm record, issues an alarm prompt, performs statistical analysis on the analysis results and the alarm information, and pushes the results of the statistical analysis to designated personnel. The wearable device has a microphone, which collects audio content and converts the audio content into text content. The text content is then merged with the video, and the merged file is stored in the management platform. When the AI ​​model receives the merged file, it detects the device's operating status and personnel behavior based on the merged file.

2. The method according to claim 1, characterized in that, After inputting the collected target video into the trained AI model to detect equipment operation and personnel behavior, the method further includes: If the analysis results are normal, a task result is generated, and the management platform generates a task record based on the task result. When a task viewing instruction is received, a task viewing interface is displayed, wherein the content displayed on the task viewing interface includes at least the task progress and task completion status.

3. The method according to claim 1, characterized in that, When the management platform receives alarm information, it generates an alarm record and issues an alarm notification. Simultaneously, the method also includes: The management platform displays an alarm notification interface. When the alarm notification interface receives a click command, it displays alarm information, which includes at least the alarm type, the content of the violation, and a recording file of the time the alarm occurred.

4. The method according to claim 1, characterized in that, In the case that the wearable device has a camera, before inputting the generated detection results into the intelligent analysis system to obtain the analysis results, the method further includes: The intelligent analysis system is configured with several analysis rules; wherein the analysis rules include at least equipment operation analysis rules and personnel behavior analysis rules.

5. The method according to claim 1, characterized in that, The step of inputting the acquired target video into the trained AI model to detect equipment operation and personnel behavior includes: The device operation status in the target video is detected by the built-in device algorithm, wherein the device includes at least one or more of the following: a device with a chain, a device with a drive belt, a device with a feed port, or a zipper machine; The built-in behavior algorithm detects violations by personnel in the target video. The violations include at least one or more of the following: not wearing a safety helmet, not wearing work clothes, not wearing protective clothing, smoking, making a phone call, crossing boundaries, or sleeping.

6. The method according to claim 5, characterized in that, The detection of device operation status in the target video using a built-in device algorithm includes: When the AI ​​model detects that the device in the target video is a chain, the built-in chain algorithm corresponding to that chain determines the marker point where the belt on the chain normally transports materials; the dwell time of the belt on the chain at the marker point in the target video is compared with a preset dwell time to obtain a comparison result, and the detection result is generated based on the comparison result; or... When the AI ​​model detects that the device in the target video has a material inlet, the average height of the material accumulation in the material inlet is determined by the built-in material blockage algorithm corresponding to the material inlet. The upper limit of the average height is marked to obtain the marked height. The actual height of the material accumulation in the material inlet in the target video is compared with the marked height to obtain the comparison result. The detection result is generated based on the comparison result.

7. A management system based on wearable devices, characterized in that, The system includes: Create a unit, used to create management tasks through the management platform; The acquisition unit is used to start acquiring video when the wearable device receives the management task; The detection unit is used to input the acquired target video into the trained AI model to detect the equipment operation status and personnel behavior; The analysis unit is used to input the generated detection results into the intelligent analysis system to obtain the analysis results. An alarm unit is used to generate alarm information if the analysis results are abnormal; wherein, the target video is captured by the wearable device worn by the inspection personnel during the enterprise inspection; when the management platform receives the alarm information, it generates an alarm record and issues an alarm prompt. The push unit is used to perform statistical analysis on the analysis results and the alarm information, and push the results of the statistical analysis to designated personnel. The wearable device has a microphone, which collects audio content and converts the audio content into text content. The text content is then merged with the video, and the merged file is stored in the management platform. When the AI ​​model receives the merged file, it detects the device's operating status and personnel behavior based on the merged file.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the management method based on a wearable device as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the management method based on any one of claims 1 to 6 when it runs.

Images