Power and environment centralized monitoring method, system, equipment, medium and product

Abstract

The invention discloses a power and environment centralized monitoring method, system and device, a medium and a product, and relates to the field of abnormity monitoring, and the method comprises the steps: obtaining a video image of an inspection scene; preprocessing the video image to obtain a preprocessed image; constructing a machine vision inspection scene AI model; inputting the preprocessed image into a machine vision inspection scene AI model to obtain a machine vision feature detection result; determining whether the inspection result is abnormal or not based on the machine visual feature detection result, a preset threshold value, the permission information and the inspection task; when the inspection result is abnormal, determining an abnormal type and an abnormal result, generating alarm notification information and an intelligent regulation and control instruction, and storing the abnormal information; and when the inspection result is not abnormal, storing the machine visual feature detection result. According to the invention, the problems of low efficiency, high error rate and the like of the existing power and environment centralized monitoring mode can be solved, and the requirements of modern informatization management are met.

Description

Technical Field

[0001] The present application relates to the field of abnormal monitoring, and in particular to a method, system, equipment, medium and product for centralized monitoring of dynamic environments. Background Art

[0002] With the rapid development of information technology, various industries have increasingly higher requirements for the stable operation of key facilities such as computer rooms and data centers. Traditional dynamic environment monitoring systems mainly rely on manual inspections, but this method has problems such as low efficiency and prone to errors, and it is difficult to meet the needs of modern information management. Summary of the invention

[0003] In order to solve the above-mentioned problems existing in the prior art, the present application provides a method, system, equipment, medium and product for centralized monitoring of dynamic environment.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for centralized monitoring of dynamic environments, comprising:

[0006] Acquire video images of inspection scenes;

[0007] Preprocessing the video image to obtain a preprocessed image;

[0008] Constructing a machine vision inspection scene AI model; the machine vision inspection scene AI model is constructed based on a trained neural network model;

[0009] The preprocessed image is input into the machine vision inspection scene AI model to obtain a machine vision feature detection result; the machine vision feature detection result includes one or more of the shape of the equipment in the computer room, the location of the equipment in the computer room, the color of the equipment in the computer room, the texture of the equipment in the computer room, the behavior event, and the operating status of the equipment in the computer room; the behavior event includes one or more of the information of the personnel entering and leaving the equipment, the inspection information, and the construction behavior;

[0010] Determine whether there is an abnormality in the inspection result based on the machine vision feature detection result, the preset threshold, the permission information and the inspection task; the permission information includes one or more of personnel entry permission and construction permission;

[0011] When the inspection result is abnormal, the abnormal type and abnormal result are determined, and alarm notification information and intelligent control instructions are generated, and the abnormal information is stored; the intelligent control instructions are used to generate control operations based on the abnormal type and the abnormal result; the abnormal information includes machine vision feature detection results, abnormal type and abnormal result;

[0012] When there is no abnormality in the inspection result, the machine vision feature detection result is stored.

[0013] Optionally, obtaining a video image of the inspection scene includes:

[0014] The inspection photographic images of the preset positions of the image acquisition device in the inspection scene are acquired at regular intervals to obtain the video images.

[0015] Optionally, preprocessing the video image to obtain a preprocessed image includes:

[0016] The video image is preprocessed using an OpenCV image processing algorithm to obtain the preprocessed image.

[0017] Optionally, build a machine vision inspection scenario AI model, including:

[0018] Acquire historical image data; the historical image data covers a variety of inspection scenarios and a variety of dynamic environment centralized monitoring conditions;

[0019] Annotating the historical image data to obtain annotated samples, and generating training data based on the annotated samples;

[0020] Select at least one neural network model based on the characteristics and requirements of the inspection task;

[0021] Using the training data to train a neural network model, and continuously adjusting the parameters of the neural network model during the training process until the output error of the neural network model is less than a set threshold, thereby obtaining a trained neural network model;

[0022] The trained neural network model is integrated into a unified framework to obtain the machine vision inspection scene AI model.

[0023] Optionally, the dynamic environment centralized monitoring method further includes:

[0024] Monitor the operation effect of the machine vision inspection scene AI model in real time to obtain feedback data;

[0025] Based on the feedback data, the structure of the machine vision inspection scenario AI model, the parameters of the machine vision inspection scenario AI model, and the training strategy of the machine vision inspection scenario AI model are continuously adjusted and optimized.

[0026] Optionally, the alarm notification information includes one or more of sound and light alarm information, telephone notification information and text message notification information.

[0027] In a second aspect, the present application provides a dynamic environment centralized monitoring system, including:

[0028] Image acquisition equipment, used to acquire video images of inspection scenes;

[0029] A processing device, connected to the image acquisition device, for implementing the above-mentioned method for centralized monitoring of the dynamic environment, so as to complete the centralized monitoring of the dynamic environment based on the video image;

[0030] A remote device is wirelessly connected to the processing device and is used to display the process information of the centralized monitoring of the dynamic environment; the process information of the centralized monitoring of the dynamic environment includes one or more of the real-time status of each computer room in the inspection scene, historical operation data, machine vision feature detection results, abnormal type, abnormal result, and alarm notification information.

[0031] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-mentioned method for centralized monitoring of dynamic environments.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for centralized monitoring of dynamic environments.

[0033] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for centralized monitoring of dynamic environments.

[0034] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0035] The present application provides a method, system, equipment, medium and product for centralized monitoring of dynamic environment. By automatically processing the acquired video images of the inspection scene as the data basis, it can monitor the inspection scene and equipment status in real time, detect abnormalities in time, and improve the efficiency of dynamic environment monitoring; by preprocessing the acquired video images, it can reduce the impact of image noise and improve data accuracy. By using the machine vision inspection scene AI model to extract the machine vision feature detection results based on the preprocessed image, and then determine whether the inspection results are abnormal based on the machine vision feature detection results, it can improve the accuracy of centralized monitoring of dynamic environment and avoid the misjudgment and omission problems that may occur in manual inspections. When there is an abnormality in the inspection result, by generating alarm notification information and intelligent control instructions, it is convenient to automatically analyze and process the inspection data, and by providing intelligent management suggestions and timely equipment control, it can help operation and maintenance personnel better understand the operation status of the computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 This is an application environment diagram of a dynamic environment centralized monitoring method in one embodiment of the present application;

[0038] Figure 2 A schematic diagram of a flow chart of a method for centralized monitoring of dynamic environments provided in one embodiment of the present application;

[0039] Figure 3 A schematic diagram of functional modules of a dynamic environment centralized monitoring system provided in one embodiment of the present application;

[0040] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0043] The method for centralized monitoring of dynamic environment provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the video image of the inspection scene to the server 104. After the server 104 receives the video image of the inspection scene, the server 104 preprocesses the video image of the inspection scene to obtain a preprocessed image. The preprocessed image is input into the machine vision inspection scene AI model to obtain the machine vision feature detection result. Based on the machine vision feature detection result, the preset threshold, the permission information and the inspection task, it is determined whether the inspection result is abnormal. When the inspection result is abnormal, the abnormal type and abnormal result are determined, and the alarm notification information and intelligent control instructions are generated to store the abnormal information. Among them, the machine vision inspection scene AI model is a network model implanted in the server and constructed based on the trained neural network model. The server 104 can feedback the obtained dynamic ring centralized monitoring results to the terminal 102. In addition, in some embodiments, the method for centralized dynamic environment monitoring can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly perform centralized dynamic environment monitoring processing on the video image of the inspection scene, or the server 104 can obtain the video image of the inspection scene from the data storage system and perform centralized dynamic environment monitoring processing on the video image of the inspection scene.

[0044] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0045] Furthermore, in order to solve the problems of low efficiency and easy errors in the existing technology, and to meet the needs of modern information management, a centralized monitoring method for dynamic environment based on machine vision came into being. Machine vision technology originated in the 1960s and was mainly used in the field of industrial automation in the early days. With the rapid development of computer technology and image processing technology, machine vision technology has gradually matured and is widely used in various industries. In the field of computer room monitoring, the application of machine vision technology provides a new solution for centralized monitoring of dynamic environment. Based on this, the centralized monitoring method for dynamic environment based on machine vision provided by this application can mainly utilize hardware and software equipment such as high-definition cameras and image processing software, combined with machine vision technology to achieve real-time monitoring and analysis of the computer room. In actual applications, the system needs to be configured with appropriate video surveillance equipment to collect environmental parameters, equipment status information and personnel behavior event information of the computer room. Through the real-time collection and analysis and processing of this information, the system can detect abnormalities in time and take corresponding treatment measures.

[0046] In an exemplary embodiment, Figure 2 As shown, a method for centralized monitoring of dynamic environment is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps 200 to 206. Among them:

[0047] Step 200: Acquire a video image of an inspection scene.

[0048] Step 201: pre-process the video image to obtain a pre-processed image.

[0049] Step 202: Construct a machine vision inspection scene AI model. The machine vision inspection scene AI model is constructed based on the trained neural network model.

[0050] Step 203: Input the preprocessed image into the machine vision inspection scene AI model to obtain the machine vision feature detection result. The machine vision feature detection result includes one or more of the shape of the equipment in the computer room, the location of the equipment in the computer room, the color of the equipment in the computer room, the texture of the equipment in the computer room, the behavior event, and the operating status of the equipment in the computer room (such as the switch status, the indicator light status, etc.). The behavior event includes one or more of the information of the personnel entering and leaving, the inspection information, and the construction behavior.

[0051] Step 204: Determine whether the inspection result is abnormal based on the machine vision feature detection result, the preset threshold, the permission information and the inspection task. The permission information includes one or more of personnel entry permission and construction permission.

[0052] Step 205: When the inspection result is abnormal, determine the abnormal type and abnormal result, generate alarm notification information and intelligent control instructions, and store the abnormal information. The intelligent control instructions are used to generate control operations based on the abnormal type and abnormal result. The abnormal information includes the machine vision feature detection result, the abnormal type and the abnormal result. The alarm notification information includes one or more of the sound and light alarm information, telephone notification information and SMS notification information.

[0053] Step 206: When there is no abnormality in the inspection result, the machine vision feature detection result is stored.

[0054] Implementing the above steps 200 to 206 can solve the problems of low efficiency and error-proneness in the existing dynamic environment centralized monitoring method, and meet the needs of modern information management. In addition, this application also facilitates automatic analysis and processing of inspection data by generating alarm notification information and intelligent control instructions, and can help operation and maintenance personnel better understand the operation status of the computer room by providing intelligent management suggestions and timely equipment control.

[0055] In another exemplary embodiment of the present application, in order to analyze the real-time video stream image 24 hours a day, monitor the computer room environment and equipment status in real time, find abnormalities in time, and improve the efficiency of dynamic environment monitoring, the method of obtaining the video image of the inspection scene in the above step 200 can be: regularly obtain the inspection photo images of the image acquisition device preset position in the inspection scene to obtain the video image. For example, through a high-definition camera or other image acquisition device, based on the Onvif protocol and the RTSP protocol, real-time video images of key facilities in the computer room are collected, and the camera preset position inspection photo images are collected regularly.

[0056] In another exemplary embodiment of the present application, the OpenCV image processing algorithm can be used to preprocess the video image to obtain a preprocessed image. In the process of preprocessing the video image by the OpenCV image processing algorithm, the video image can be converted into grayscale by denoising to simplify subsequent processing. By using median filtering, Gaussian filtering, etc. to remove noise from the video image through denoising, and using edge detection for the denoised image to detect the outline of equipment or personnel, etc., the image quality can be improved and subsequent analysis can be facilitated.

[0057] In another exemplary embodiment of the present application, in order to accurately obtain the equipment status and environmental parameters and avoid possible misjudgments and omissions in manual inspections, a pre-built machine vision inspection scene AI model is used to extract and detect features from images after noise reduction and edge detection. Through feature extraction and detection, automatic recognition of equipment in the computer room, status judgment, and judgment of in and out personnel, inspections, and construction behaviors are achieved. Among them, the construction process of the machine vision inspection scene AI model includes:

[0058] (1) Obtain historical image data. The historical image data covers a variety of inspection scenarios and a variety of dynamic environment centralized monitoring conditions.

[0059] (2) Label the historical image data to obtain labeled samples, and generate training data based on the labeled samples. This step mainly involves collecting and labeling training images. For example, a large amount of high-quality image data covering various inspection scenes and conditions is labeled. The labeled information includes information such as the location, type, and attributes of the target object.

[0060] (3) Based on the characteristics and requirements of the inspection task, select at least one appropriate neural network model, such as a convolutional neural network (CNN).

[0061] (4) Using the training data to train the neural network model, the parameters of the neural network model are continuously adjusted during the training process until the output error of the neural network model is less than the set threshold, thereby obtaining a trained neural network model.

[0062] In the actual application process, after the model is selected in step (3), the model code is written using a programming language (such as Python) and a deep learning framework PyTorch, and the neural network model is trained using training data. The model training process requires a large amount of GPU computing resources and time.

[0063] During the training process, the model identifies and locates target objects in the image, realizing the detection and classification of inspection objects.

[0064] (5) Integrate the trained neural network model into a unified framework to obtain the machine vision inspection scene AI model and prepare for fusion, which can improve the performance and robustness of the model.

[0065] In actual application, the trained model needs to be deployed to the inspection system and run in the actual environment.

[0066] Furthermore, before performing step (1), a visual inspection scenario definition may be performed, for example, the inspection target and environment may be clarified, and the types of objects to be detected and identified may be determined. Specific requirements of the inspection task may be defined, such as accuracy, speed, and reliability.

[0067] In another exemplary embodiment of the present application, in order to adapt to new inspection scenarios and improve performance, the dynamic environment centralized monitoring method provided by the present application can also monitor the operation effect of the machine vision inspection scenario AI model in real time during the actual process, and collect feedback data to evaluate the model performance. Based on the feedback data, the structure of the machine vision inspection scenario AI model, the parameters of the machine vision inspection scenario AI model, and the training strategy of the machine vision inspection scenario AI model are continuously adjusted and optimized, and the training image samples are continuously supplemented and annotated for application, and the model is iteratively trained and optimized.

[0068] Based on the above description, the construction process of the machine vision inspection scene AI model in step 202 can be summarized as 10 processes, including visual inspection scene definition, training image collection and annotation, AI model selection, AI model programming, AI model training, AI model target detection and recognition, AI model integration, AI model deployment, real-time monitoring and feedback of AI model effects, and continuous iteration and optimization of AI models.

[0069] In the process of building the AI ​​model for the entire machine vision inspection scenario, the key factors that need to be considered are: 1) Data quality: Ensure the diversity and representativeness of the training image data to improve the generalization ability of the model. 2) Model generalization: The model should be able to handle unseen data and new scenarios. 3) Real-time: The model needs to respond quickly to meet the needs of real-time monitoring. 4) Accuracy: The detection and recognition accuracy of the model should meet the requirements of the inspection task. 5) Maintainability: The model should be easy to maintain and update to adapt to the ever-changing environment and needs.

[0070] In another exemplary embodiment of the present application, the implementation process of step 205 can be to perform abnormal detection on the status of the equipment in the computer room, and determine the compliance of personnel entry and exit, inspection and construction behavior based on the extracted features and preset thresholds, personnel entry and exit permissions, inspection tasks and construction permits. Once an abnormality is detected, such as equipment failure, temperature abnormality, water leakage, unauthorized entry, irregular inspection behavior and unreported construction behavior, the alarm mechanism is immediately triggered, and the abnormal information is promptly notified to the operation and maintenance personnel through various methods such as sound and light alarms, telephone notifications, and text message notifications. At the same time, the abnormal information is recorded in the database for subsequent analysis and processing. A detailed abnormal analysis report can also be further generated, including information such as abnormal type, location, time, event and personnel.

[0071] The implementation process of the control operation can be to automatically perform a series of basic control operations according to the type and degree of recorded abnormalities, such as adjusting the air conditioning temperature, shutting down faulty equipment, sending warning voice, etc., to reduce the impact of abnormalities on the operation of the computer room. For complex abnormal situations, the system can provide processing suggestions or guide operation and maintenance personnel to handle them.

[0072] In summary, compared with the prior art, the dynamic environment centralized monitoring method provided by this application has the following advantages:

[0073] 1. Timeliness and efficiency: The centralized dynamic environment monitoring method based on machine vision inspection provided in this application can analyze real-time video stream images 24 hours a day, monitor the computer room environment and equipment status in real time, detect abnormalities in time, and improve the efficiency of dynamic environment monitoring.

[0074] 2. Data accuracy and reliability: This application can accurately obtain the equipment status and environmental parameters of the computer room, avoiding misjudgments and omissions that may occur during manual inspections.

[0075] 3. Reduce labor costs: Traditional inspection methods require a lot of human resources, but this application can automatically complete inspection tasks through machine vision inspection, reducing manpower investment.

[0076] 4. Improve work safety: In some dangerous environments, manual inspections have certain safety risks. The dynamic environment centralized monitoring method based on machine vision inspection provided by this application can replace manual inspections and reduce work risks.

[0077] 5. Intelligent management: This application builds a machine learning model to automatically analyze and process inspection data, provide intelligent management suggestions and timely equipment control, and help operation and maintenance personnel better understand the operation status of the computer room.

[0078] Based on the same inventive concept, the embodiment of the present application also provides a dynamic environment centralized monitoring system for implementing the dynamic environment centralized monitoring method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more dynamic environment centralized monitoring system embodiments provided below can refer to the limitations of the dynamic environment centralized monitoring method above, and will not be repeated here.

[0079] In an exemplary embodiment, Figure 3 As shown, a dynamic environment centralized monitoring system is provided, including: an image acquisition device 300, a processing device 301 and a remote device 302.

[0080] The image acquisition device 300 is used to acquire video images of inspection scenes.

[0081] The processing device 301 is connected to the image acquisition device 300, and is mainly used to implement the above-mentioned dynamic environment centralized monitoring method to complete the dynamic environment centralized monitoring based on video images.

[0082] The remote device 302 is wirelessly connected to the processing device 301, and is mainly used to display the process information of the dynamic environment centralized monitoring. The process information of the dynamic environment centralized monitoring includes one or more of the real-time status of each machine room in the inspection scene, historical operation data, machine vision feature detection results, abnormal type, abnormal result, and alarm notification information.

[0083] As an optional implementation, a dynamic environment centralized monitoring platform may be embedded in the remote device 302. The dynamic environment centralized monitoring platform realizes centralized monitoring and management of a large number of computer rooms in various places. For example, the real-time status, historical data, alarm information, etc. of each computer room can be displayed through a unified dynamic environment centralized monitoring platform, which facilitates operation and maintenance personnel to fully understand the operation status of the computer room.

[0084] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store dynamic environment centralized monitoring processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for centralized monitoring of dynamic environments is implemented.

[0085] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0086] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0087] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0089] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0090] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0091] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0092] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for centralized monitoring of dynamic environment, characterized in that: The dynamic environment centralized monitoring method comprises: Acquire video images of inspection scenes; Preprocessing the video image to obtain a preprocessed image; Constructing a machine vision inspection scene AI model; the machine vision inspection scene AI model is constructed based on a trained neural network model; The preprocessed image is input into the machine vision inspection scene AI model to obtain a machine vision feature detection result; the machine vision feature detection result includes one or more of the shape of the equipment in the computer room, the location of the equipment in the computer room, the color of the equipment in the computer room, the texture of the equipment in the computer room, the behavior event, and the operating status of the equipment in the computer room; the behavior event includes one or more of the information of the personnel entering and leaving the equipment, the inspection information, and the construction behavior; Determine whether there is an abnormality in the inspection result based on the machine vision feature detection result, the preset threshold, the permission information and the inspection task; the permission information includes one or more of personnel entry permission and construction permission; When the inspection result is abnormal, the abnormal type and abnormal result are determined, and alarm notification information and intelligent control instructions are generated, and the abnormal information is stored; the intelligent control instructions are used to generate control operations based on the abnormal type and the abnormal result; the abnormal information includes machine vision feature detection results, abnormal type and abnormal result; When there is no abnormality in the inspection result, the machine vision feature detection result is stored.

2. The method for centralized monitoring of dynamic environment according to claim 1, characterized in that: Obtain video images of inspection scenes, including: The inspection photographic images of the preset positions of the image acquisition device in the inspection scene are acquired at regular intervals to obtain the video images.

3. The method for centralized monitoring of dynamic environment according to claim 1, characterized in that: Preprocessing the video image to obtain a preprocessed image includes: The video image is preprocessed using an OpenCV image processing algorithm to obtain the preprocessed image.

4. The method for centralized monitoring of dynamic environment according to claim 1, characterized in that: Build an AI model for machine vision inspection scenarios, including: Acquire historical image data; the historical image data covers a variety of inspection scenarios and a variety of dynamic environment centralized monitoring conditions; Annotating the historical image data to obtain annotated samples, and generating training data based on the annotated samples; Select at least one neural network model based on the characteristics and requirements of the inspection task; Using the training data to train a neural network model, and continuously adjusting the parameters of the neural network model during the training process until the output error of the neural network model is less than a set threshold, thereby obtaining a trained neural network model; The trained neural network model is integrated into a unified framework to obtain the machine vision inspection scene AI model.

5. The method for centralized monitoring of dynamic environment according to claim 1, characterized in that: The dynamic environment centralized monitoring method also includes: Monitor the operation effect of the machine vision inspection scene AI model in real time to obtain feedback data; Based on the feedback data, the structure of the machine vision inspection scenario AI model, the parameters of the machine vision inspection scenario AI model, and the training strategy of the machine vision inspection scenario AI model are continuously adjusted and optimized.

6. The method for centralized monitoring of dynamic environment according to claim 1, characterized in that: The alarm notification information includes one or more of sound and light alarm information, telephone notification information and text message notification information.

7. A dynamic environment centralized monitoring system, characterized in that: The dynamic environment centralized monitoring system comprises: Image acquisition equipment, used to acquire video images of inspection scenes; A processing device, connected to the image acquisition device, for implementing the method for centralized monitoring of the dynamic environment according to any one of claims 1 to 6, so as to complete the centralized monitoring of the dynamic environment based on the video image; A remote device is wirelessly connected to the processing device and is used to display the process information of the centralized monitoring of the dynamic environment; the process information of the centralized monitoring of the dynamic environment includes one or more of the real-time status of each computer room in the inspection scene, historical operation data, machine vision feature detection results, abnormal type, abnormal result, and alarm notification information.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for centralized monitoring of dynamic environments as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for centralized monitoring of dynamic environments described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for centralized monitoring of dynamic environments described in any one of claims 1 to 6 is implemented.

Images