Scene recognition and early warning methods, systems, devices, equipment and storage media

Abstract

This invention discloses a scene recognition and early warning method, system, device, equipment, and storage medium. The method includes: acquiring image acquisition devices and edge nodes related to at least one scene to be identified; generating a configuration file corresponding to each scene to be identified based on the association relationships between each image acquisition device and each edge node and each scene to be identified; determining video image data and a scene model for the corresponding scene to be identified based on the configuration file; determining a scene recognition result for the corresponding scene to be identified based on the video image data and the scene model; and performing early warning processing on the corresponding scene to be identified based on the video image data and the scene recognition result. This invention improves the efficiency and accuracy of scene recognition and early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to a scene recognition and early warning method, system, device, equipment and storage medium. BACKGROUND

[0002] For the analysis of intelligent video of network points, the video data volume involved in the current cloud video data analysis and calculation is large, and the real-time requirement is high, so it is difficult to support large-scale network point scene demand. When solving the problem of processing large-scale scene video, the existing technical solution adopts an analysis platform based on edge computing, but the processing process is not continuous in other aspects, resulting in low quality and efficiency of scene recognition processing. SUMMARY

[0003] The present application provides a scene recognition and early warning method, system, device, equipment and storage medium to improve the efficiency and accuracy of scene recognition and early warning.

[0004] According to one aspect of the present application, a scene recognition and early warning method is provided, the method comprising:

[0005] Obtaining each image acquisition device and each edge node related to at least one scene to be recognized;

[0006] According to the association relationship between each image acquisition device and each edge node and each scene to be recognized, a configuration file corresponding to the corresponding scene to be recognized is generated;

[0007] According to the configuration file, the video image data and the scene model of the corresponding scene to be recognized are determined;

[0008] According to the video image data, the scene recognition result of the corresponding scene to be recognized is determined based on the scene model;

[0009] According to the video image data and the scene recognition result, the corresponding scene to be recognized is processed.

[0010] According to another aspect of the present application, a scene recognition and early warning system is provided, the system comprising:

[0011] An edge device management platform, at least one edge node and a business management system; the edge device management platform is in communication connection with each edge node; each edge node is in communication connection with the business management system;

[0012] The edge device management platform is used to obtain each image acquisition device and each edge node related to at least one scene to be recognized; according to the association relationship between each image acquisition device and each edge node and each scene to be recognized, a configuration file corresponding to the corresponding scene to be recognized is generated;

[0013] Each of the edge nodes is configured to determine video image data and a scene model of a corresponding scene to be identified according to the configuration file, and determine a scene recognition result of the corresponding scene to be identified based on the scene model according to the video image data.

[0014] The business management system is configured to perform early warning processing on the corresponding scene to be identified according to the video image data and the scene recognition result.

[0015] According to another aspect of the present application, there is provided a scene recognition early warning device, which comprises:

[0016] An edge node acquisition module is configured to acquire each image acquisition device and each edge node related to at least one scene to be identified.

[0017] A configuration file generation module is configured to generate a configuration file corresponding to each scene to be identified according to an association relationship between each image acquisition device, each edge node, and each scene to be identified.

[0018] A scene model determination module is configured to determine video image data and a scene model of a corresponding scene to be identified according to the configuration file.

[0019] An identification result determination module is configured to determine a scene recognition result of a corresponding scene to be identified based on the scene model according to the video image data.

[0020] An early warning processing module is configured to perform early warning processing on a corresponding scene to be identified according to the video image data and the scene recognition result.

[0021] According to another aspect of the present application, there is provided an electronic device, which comprises:

[0022] at least one processor; and

[0023] a memory in communication with the at least one processor; wherein

[0024] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the scene recognition early warning method according to any one of the embodiments of the present application.

[0025] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to implement the scene recognition early warning method according to any one of the embodiments of the present application when executed by the processor.

[0026] The embodiment of the present application generates the configuration file corresponding to the corresponding to-be-identified scene according to the association relationship between each image acquisition device, each edge node and each to-be-identified scene; determines the video image data and the scene model of the corresponding to-be-identified scene according to the configuration file; determines the scene identification result of the corresponding to-be-identified scene based on the scene model according to the video image data; and performs early warning processing on the corresponding to-be-identified scene according to the video image data and the scene identification result. The above scheme realizes intelligent analysis and whole-process management of video data through the whole process of video acquisition, generation and issuance of configuration files, algorithm enabling and early warning processing of edge nodes, thereby improving the scene identification and early warning efficiency and accuracy.

[0027] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Figure 1 is a flow chart of a scene identification method provided by the first embodiment of the present application;

[0030] Figure 2A is a structural schematic diagram of a scene identification early warning system provided by the second embodiment of the present application;

[0031] Figure 2B is a structural schematic diagram of a scene identification early warning system provided by the second embodiment of the present application.

[0032] Figure 2C is an interaction schematic diagram of a scene identification method provided by the second embodiment of the present application.

[0033] Figure 3 is a structural schematic diagram of a scene identification device provided by the third embodiment of the present application;

[0034] Figure 4 is a structural schematic diagram of an electronic device for implementing the scene identification method of the embodiment of the present application. DETAILED DESCRIPTION

[0035] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0036] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment one

[0038] Figure 1 A flowchart of a scene recognition early warning method provided by the first embodiment of the present application is provided. The present embodiment can be applicable to the case of identifying and early warning the scene to be identified. The method can be executed by a scene recognition early warning device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in the figure, the method comprises: Figure 1

[0039] S110, acquiring each image acquisition device and each edge node related to at least one scene to be identified.

[0040] The scene to be identified can be a scene to be identified and early warned. For example, the scene to be identified can be a people flow identification scene.

[0041] The image acquisition device can be a device deployed in each scene to be identified for acquiring video image data in the scene to be identified. For example, the image acquisition device can be a camera.

[0042] The edge node can be an edge box for edge computing at the edge. For the scene identification of any scene to be identified, at least one edge box can be used for edge computing. The edge box can be used for analyzing and processing the video image data acquired by the image acquisition device.

[0043] ​Exemplarily, the edge device management platform can acquire the image acquisition device and the edge node related to at least one to-be-identified scene. Optionally, each edge node can be pre-registered in the edge device management platform. Specifically, each edge node can be pre-registered in the edge device management platform based on its device identifier and device address, and its information can be input into the edge device management platform.

[0044] S120, according to the association relationship between each image acquisition device, each edge node, and each to-be-identified scene, a configuration file corresponding to the corresponding to-be-identified scene is generated.

[0045] Exemplarily, the edge device management platform can determine the to-be-identified scene required to be processed by each edge node and the video image data required to be acquired by the to-be-identified scene based on each edge node registered in the platform, so as to determine the image acquisition device required to be interfaced by each edge node. For example, if there are to-be-identified scene A and to-be-identified scene B, there are image acquisition device a, image acquisition device b, and image acquisition device c, there are edge node m and edge node n. If the edge node used for scene identification and early warning of to-be-identified scene A is edge node m, and the video image data required to be acquired for identifying to-be-identified scene A is derived from image acquisition device a and image acquisition device b, there is an association relationship between to-be-identified scene A, edge node m, image acquisition device a, and image acquisition device b. If the edge node used for scene identification and early warning of to-be-identified scene B is edge node n, and the video image data required to be acquired for identifying to-be-identified scene B is derived from image acquisition device c, there is an association relationship between to-be-identified scene B, edge node n, and image acquisition device c.

[0046] Exemplarily, the edge device management platform can generate a configuration file corresponding to the corresponding to-be-identified scene according to the association relationship between each image acquisition device, each edge node, and each to-be-identified scene. It should be noted that for the same to-be-identified scene, the scene configuration parameters in the configuration file are different in different regions or regions. For different to-be-identified scenes, different scene models are required to be used. Therefore, for different to-be-identified scenes, the corresponding configuration files are different. After the edge device management generates the configuration file corresponding to the to-be-identified scene, the configuration file is issued to the edge node corresponding to the to-be-identified scene.

[0047] In an optional embodiment, according to the association between each image acquisition device, each edge node and each scene to be identified, a configuration file corresponding to the corresponding scene to be identified is generated, including: generating scene configuration parameters of the corresponding scene to be identified according to the association between each image acquisition device, each edge node and each scene to be identified; determining a scene model identifier corresponding to each scene to be identified; taking the scene configuration parameters and the scene model identifier of the corresponding scene to be identified as the configuration file corresponding to the corresponding scene to be identified.

[0048] The scene configuration parameters can include time parameters, region parameters, device identifiers of image acquisition devices and a series of parameters used for scene identification.

[0049] The scene model identifier can be used to uniquely represent the scene model of the scene to be identified. The scene models corresponding to different scenes to be identified are different, and are pre-trained by relevant technical personnel for the scene models of different scenes to be identified and stored in an algorithm warehouse of an edge device management platform.

[0050] For example, according to the scene to be identified, a scene model identifier corresponding to a scene model used for early warning identification of the scene to be identified can be determined, and the scene configuration parameters and the scene model identifier of the scene to be identified are taken as the configuration file corresponding to the corresponding scene to be identified, and the configuration file is fed back to the corresponding edge node.

[0051] S130, according to the configuration file, determining video image data and a scene model of the corresponding scene to be identified.

[0052] For example, after the corresponding edge node obtains the configuration file, the configuration file is parsed, and the video image data and the scene model of the corresponding scene to be identified are obtained through the parsed file.

[0053] In an optional embodiment, the scene configuration parameters include device identifiers of image acquisition devices; accordingly, according to the configuration file, determining video image data and a scene model of the corresponding scene to be identified includes: obtaining video image data from the image acquisition device corresponding to the device identifier according to the device identifier; obtaining the scene model identifier from the configuration file, and obtaining the corresponding scene model based on the scene model identifier.

[0054] The device identifier of the image acquisition device is included in the scene configuration parameters, and is used to uniquely represent the image acquisition device.

[0055] Exemplarily, after the edge node obtains the scene configuration parameter, the edge node obtains the device identifier of the image acquisition device from the scene configuration parameter, so as to establish a connection with the image acquisition device corresponding to the device identifier based on the device identifier, and then obtain the video image data collected by the image acquisition device. The edge node can also obtain the scene model identifier from the scene configuration parameter, and based on the scene model identifier, pull the scene model corresponding to the scene model identifier from the algorithm warehouse of the edge device management platform.

[0056] S140, according to the video image data, determining the scene recognition result of the corresponding to-be-recognized scene based on the scene model.

[0057] Exemplarily, the edge node can input the obtained video image data into the scene model, and obtain the scene recognition result of the corresponding to-be-recognized scene output by the scene model.

[0058] In an optional embodiment, the scene configuration parameter includes scene feature parameters corresponding to the to-be-recognized scene; correspondingly, according to the video image data, determining the scene recognition result of the corresponding to-be-recognized scene based on the scene model, includes: inputting the video image data and the scene feature parameters into the scene model to obtain the scene model output result; taking the scene model output result as the scene recognition result of the corresponding to-be-recognized scene.

[0059] Exemplarily, the edge node inputs the video image data and the scene feature parameters into the scene model to obtain the scene model output result, and takes the scene model output result as the scene recognition result of the corresponding to-be-recognized scene. The scene feature parameters can include time parameters, regional parameters, etc.

[0060] For example, for a to-be-recognized scene of human flow, due to external factors, for region A, the human flow is concentrated around 10 o'clock in the morning, so the corresponding scene recognition time can be from 9:00 to 12:00 in the morning; for region B, the human flow is concentrated around 4 o'clock in the afternoon, so the corresponding scene recognition time can be from 15:00 to 18:00 in the afternoon. Therefore, for a to-be-recognized scene of human flow, the corresponding scene feature parameters are different for different regions.

[0061] S150, according to the video image data and the scene recognition result, performing early warning processing on the corresponding to-be-recognized scene.

[0062] Exemplarily, each edge node can send the video image data and the scene recognition result corresponding to the video image data to the business management system, and the business management system can make early warning processing on the scene recognition result, and send the video image data and the scene recognition result corresponding to the video image data to the model algorithm training platform through the business management system, to optimize the corresponding scene model.

[0063] In an optional embodiment, according to the video image data and the scene recognition result, a pre-warning process is performed on the corresponding to-be-recognized scene, including: if the scene recognition result meets a preset pre-warning rule, a scene pre-warning is performed on the corresponding to-be-recognized scene; and according to the video image data and the scene recognition result, a model update is performed on a scene model corresponding to the corresponding to-be-recognized scene.

[0064] The pre-warning rule can be preset by a relevant technical personnel. For example, for a people flow scene, the corresponding pre-warning rule can be that the people flow recognized by the scene recognition result is greater than a preset people flow threshold.

[0065] For example, after the business management system obtains the scene recognition result, the corresponding to-be-recognized scene can be pre-warned based on the corresponding pre-warning rule. Different to-be-recognized scenes can correspond to different pre-warning rules. At the same time, according to the video image data and the scene recognition result, a model update can be performed on a scene model corresponding to the corresponding to-be-recognized scene. Optionally, the business management system can also send the video image data and the scene recognition result to a model algorithm training platform, and the model algorithm training platform can perform a model update on the scene model corresponding to the corresponding to-be-recognized scene, so as to store the updated scene model.

[0066] In an optional embodiment, the edge node includes a node device identifier and a node device address; after the pre-warning process is performed on the corresponding to-be-recognized scene, the method further includes: according to the node device identifier and the node device address, real-time monitoring is performed on each edge node.

[0067] For example, the edge device management platform can pre-store the device identifier and the node device address corresponding to the edge node, which can be pre-registered in the edge device management platform by each edge node. Each edge node can synchronize the running information to the edge device management platform, and the edge device management platform can perform real-time monitoring on each edge node according to the node device identifier and the node device address, so as to determine whether there is a malfunctioning or error edge node, and further to quickly process the abnormal edge node.

[0068] The embodiment of the present application generates a configuration file corresponding to a corresponding to-be-identified scene according to the association relationship between each image acquisition device, each edge node and each to-be-identified scene; determines video image data and a scene model of the corresponding to-be-identified scene according to the configuration file; determines a scene recognition result of the corresponding to-be-identified scene based on the scene model according to the video image data; and performs early warning processing on the corresponding to-be-identified scene according to the video image data and the scene recognition result. The above scheme realizes intelligent analysis and whole-process management of video data through the whole process of video acquisition, configuration file generation, algorithm enabling and early warning processing of edge nodes, thereby improving the scene recognition and early warning efficiency and accuracy.

[0069] Embodiment two

[0070] The embodiment further provides a scene identification and early warning system for implementing the scene identification and early warning method of the above embodiment, as shown in a structural schematic diagram of a scene identification and early warning system. Figure 2A The scene identification and early warning system comprises an edge device management platform 201, at least one edge node 202 and a business management system 203. The edge device management platform 201 is in communication connection with each edge node 202, and each edge node 202 is in communication connection with the business management system 203.

[0071] The edge device management platform 201 is configured to acquire each image acquisition device and each edge node related to at least one to-be-identified scene, and generate a configuration file corresponding to a corresponding to-be-identified scene according to the association relationship between each image acquisition device, each edge node and each to-be-identified scene.

[0072] Each edge node 202 is configured to determine video image data and a scene model of a corresponding to-be-identified scene according to the configuration file, and determine a scene recognition result of the corresponding to-be-identified scene based on the scene model according to the video image data.

[0073] The business management system 203 is configured to perform early warning processing on the corresponding to-be-identified scene according to the video image data and the scene recognition result.

[0074] In another optional embodiment, the scene identification and early warning system can further comprise an image acquisition device 204 and a model algorithm training platform 205. As shown in a structural schematic diagram of a scene identification and early warning system. Figure 2B The image acquisition device 204 can be a camera and is configured to acquire video image data of each to-be-identified scene. The model algorithm training platform is configured to perform model training and model optimization on a scene model corresponding to each to-be-identified scene.

[0075] In a specific embodiment, as shown in a structural schematic diagram of a scene identification and early warning system. Figure 2CThis diagram illustrates an interaction of a scene recognition method. User login is performed on the edge device management platform. For example, authorized personnel can log in on the edge device management platform. Video image data is acquired by an image acquisition device and sent to edge nodes. Edge nodes enter and register information on the edge device management platform. The edge device management platform selects a scene model from its algorithm repository and generates a configuration file. The edge device management platform distributes the configuration file to the edge nodes. The edge nodes parse the configuration file to obtain the model identifier of the corresponding scene model, and based on this identifier, retrieve the scene model from the algorithm repository of the edge device management platform and start the scene model. Based on the video image data and the scene model, the edge nodes determine the scene recognition result of the corresponding scene to be recognized and feed it back to the business management system, which then issues an alert regarding the scene recognition result. The business management system feeds back the video image data and scene recognition result information to the model algorithm training platform, where the scene model is optimized. Furthermore, each edge node synchronizes its own device information to the edge device management platform, which then monitors the devices of each edge node.

[0076] This embodiment proposes a cloud-edge-device collaborative scene recognition system based on edge computing. It achieves cloud-based management of edge node devices, meaning that the network's edge computing nodes and image acquisition are integrated with the edge device management platform to form a cloud architecture, constructed using resource virtualization. Through system integration, it realizes intelligent video analytics management across the entire process, from algorithm training, video acquisition, configuration file generation and distribution, edge device algorithm activation, to business system processing and early warning, and device monitoring. The process achieves loose coupling, high availability, hierarchical deployment, and unified parameterized configuration management for the network environment. Simultaneously, by utilizing the edge device management platform, it connects the network's camera video acquisition terminals, deployed edge nodes, and the cloud-based model algorithm training platform, solving the problem of insufficient cloud-based video analytics computing power. This enhances the network's intelligent management capabilities across the entire process.

[0077] Example 3

[0078] Figure 3 This is a schematic diagram of the structure of a scene recognition and early warning device provided in Embodiment 2 of the present invention. The scene recognition and early warning device provided in this embodiment of the present invention is applicable to situations where a scene to be recognized is identified and an early warning is issued. This scene recognition and early warning device can be implemented in hardware and / or software, such as... Figure 3 As shown, the device specifically includes: an edge node acquisition module 301, a configuration file generation module 302, a scene model determination module 303, a recognition result determination module 304, and an early warning processing module 305. Among them,

[0079] The edge node acquisition module 301 is configured to acquire each image acquisition device and each edge node related to at least one to-be-identified scene;

[0080] The configuration file generation module 302 is configured to generate a configuration file corresponding to a corresponding to-be-identified scene according to the association between each image acquisition device and each edge node and each to-be-identified scene.

[0081] The scene model determination module 303 is configured to determine video image data and a scene model of a corresponding to-be-identified scene according to the configuration file.

[0082] The recognition result determination module 304 is configured to determine a scene recognition result of a corresponding to-be-identified scene based on the scene model according to the video image data.

[0083] The early warning processing module 305 is configured to perform early warning processing on a corresponding to-be-identified scene according to the video image data and the scene recognition result.

[0084] The embodiment of the present application generates a configuration file corresponding to a corresponding to-be-identified scene according to the association between each image acquisition device and each edge node and each to-be-identified scene, determines video image data and a scene model of a corresponding to-be-identified scene according to the configuration file, determines a scene recognition result of a corresponding to-be-identified scene based on the scene model according to the video image data, and performs early warning processing on a corresponding to-be-identified scene according to the video image data and the scene recognition result. The above scheme realizes intelligent analysis and full-process management of video data and improves the scene recognition and early warning efficiency and accuracy through the entire process of video acquisition, generation and issuance of a configuration file, algorithm activation by an edge node, and early warning processing.

[0085] Optionally, the configuration file generation module 302 comprises:

[0086] The configuration parameter generation unit is configured to generate scene configuration parameters of a corresponding to-be-identified scene according to the association between each image acquisition device and each edge node and each to-be-identified scene.

[0087] The model identifier determination unit is configured to determine a scene model identifier corresponding to each to-be-identified scene.

[0088] The configuration file generation unit is configured to take the scene configuration parameters and the scene model identifier of a corresponding to-be-identified scene as a configuration file corresponding to the corresponding to-be-identified scene.

[0089] Optionally, the scene configuration parameters comprise a device identifier of an image acquisition device.

[0090] Correspondingly, the scene model determination module 303 comprises:

[0091] a video image data acquisition unit, configured to acquire video image data from an image acquisition device corresponding to the device identifier according to the device identifier;

[0092] a scene model determination unit, configured to acquire a scene model identifier from the configuration file, and acquire a corresponding scene model based on the scene model identifier.

[0093] Optionally, the scene configuration parameter comprises a scene feature parameter corresponding to the scene to be identified.

[0094] Correspondingly, the identification result determination module 304 comprises:

[0095] an output result determination unit, configured to input the video image data and the scene feature parameter into the scene model to obtain a scene model output result.

[0096] an identification result determination unit, configured to take the scene model output result as a scene identification result of the corresponding scene to be identified.

[0097] Optionally, the early warning processing module 305 comprises:

[0098] a scene early warning unit, configured to perform scene early warning on the corresponding scene to be identified if the scene identification result meets a preset early warning rule; and

[0099] a model updating unit, configured to perform model updating on the scene model corresponding to the corresponding scene to be identified according to the video image data and the scene identification result.

[0100] Optionally, the edge node comprises a node device identifier and a node device address.

[0101] The apparatus further comprises:

[0102] a real-time monitoring module, configured to perform real-time monitoring on each edge node according to the node device identifier and the node device address after the early warning processing on the corresponding scene to be identified.

[0103] The scene identification and early warning apparatus provided in the embodiments of the present application can execute the scene identification and early warning method provided in any of the embodiments of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0104] Embodiment Four

[0105] Figure 4A structural diagram of an electronic device 40 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0106] As shown, the electronic device 40 includes at least one processor 41, and memory, such as read-only memory (ROM) 42, random access memory (RAM) 43, etc., that is communicatively coupled with the at least one processor 41, where the memory stores computer programs that are executable by the at least one processor. The processor 41 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 42 or loaded into the random access memory (RAM) 43 from the storage unit 48. Various programs and data required for the operation of the electronic device 40 can also be stored in the RAM 43. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44. Figure 4

[0107] Various components in the electronic device 40 are connected to the I / O interface 45, including an input unit 46, such as a keyboard, a mouse, etc., an output unit 47, such as various types of displays, speakers, etc., a storage unit 48, such as a magnetic disk, an optical disk, etc., and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0108] The processor 41 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 performs various methods and processes described above, such as the scene recognition pre-warning method.

[0109] ​In some embodiments, the scene recognition warning method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 48. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 40 via, e.g., ROM 42 and / or communication unit 49. When the computer program is loaded onto RAM 43 and executed by processor 41, one or more steps of the scene recognition warning method described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the scene recognition warning method by way of other means, e.g., with the aid of firmware.

[0110] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0111] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0112] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0114] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0115] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0116] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0117] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A scene recognition early warning method, characterized in that, The method comprises the following steps: acquiring image acquisition devices and edge nodes related to at least one scene to be identified; generating a configuration file corresponding to each scene to be identified according to the association between each image acquisition device, each edge node and each scene to be identified; determining video image data and a scene model of each scene to be identified according to the configuration file; determining a scene recognition result of each scene to be identified according to the video image data and the scene model; performing early warning processing on each scene to be identified according to the video image data and the scene recognition result; The method comprises the following steps: generating scene configuration parameters of each scene to be identified according to the association between each image acquisition device, each edge node and each scene to be identified; determining a scene model identifier corresponding to each scene to be identified; regarding the scene configuration parameters and the scene model identifier of each scene to be identified as the configuration file corresponding to each scene to be identified; The method comprises the following steps: if the scene recognition result meets a preset early warning rule, performing scene early warning on each scene to be identified; and updating a scene model corresponding to each scene to be identified according to the video image data and the scene recognition result; different scenes to be identified correspond to different early warning rules.

2. The method of claim 1, wherein, The scene configuration parameters comprise device identifiers of image acquisition devices; Accordingly, the method comprises the following steps: acquiring video image data from the image acquisition devices corresponding to the device identifiers according to the device identifiers; acquiring a scene model identifier from the configuration file and acquiring a corresponding scene model based on the scene model identifier.

3. The method of claim 1, wherein, The scene configuration parameters comprise scene feature parameters corresponding to each scene to be identified; Accordingly, the method comprises the following steps: inputting the video image data and the scene feature parameters into the scene model to obtain a scene model output result; regarding the scene model output result as the scene recognition result of each scene to be identified.

4. The method according to any one of claims 1 to 3, characterized in that, The edge nodes comprise node device identifiers and node device addresses; After the early warning processing on each scene to be identified, the method further comprises the following steps: performing real-time monitoring on each edge node according to the node device identifiers and the node device addresses.

5. A scene recognition early warning system characterized by, The method for implementing any one of claims 1-4 comprises the following steps: an edge device management platform, at least one edge node and a business management system; the edge device management platform is in communication connection with each edge node; each edge node is in communication connection with the business management system; The edge device management platform is configured to acquire each image acquisition device and each edge node related to at least one to-be-identified scene; and generate a configuration file corresponding to a corresponding to-be-identified scene according to an association relationship between each image acquisition device, each edge node, and each to-be-identified scene. Each edge node is configured to determine video image data and a scene model of a corresponding to-be-identified scene according to the configuration file; and determine a scene recognition result of the corresponding to-be-identified scene based on the scene model according to the video image data. The business management system is configured to perform early warning processing on the corresponding to-be-identified scene according to the video image data and the scene recognition result.

6. A scene recognition early warning device, characterized in that, The edge node acquisition module is configured to acquire each image acquisition device and each edge node related to at least one to-be-identified scene. The configuration file generation module is configured to generate a configuration file corresponding to a corresponding to-be-identified scene according to an association relationship between each image acquisition device, each edge node, and each to-be-identified scene. The scene model determination module is configured to determine video image data and a scene model of a corresponding to-be-identified scene according to the configuration file. The recognition result determination module is configured to determine a scene recognition result of the corresponding to-be-identified scene based on the scene model according to the video image data. The early warning processing module is configured to perform early warning processing on the corresponding to-be-identified scene according to the video image data and the scene recognition result. The configuration file generation module includes: The configuration parameter generation unit is configured to generate scene configuration parameters of a corresponding to-be-identified scene according to an association relationship between each image acquisition device, each edge node, and each to-be-identified scene. The model identification determination unit is configured to determine a scene model identification corresponding to each to-be-identified scene. The configuration file generation unit is configured to take the scene configuration parameters and the scene model identification of the corresponding to-be-identified scene as a configuration file corresponding to the corresponding to-be-identified scene. The early warning processing module includes: The scene early warning unit is configured to perform scene early warning on a corresponding to-be-identified scene if the scene recognition result meets a preset early warning rule. The model update unit is configured to perform model update on a scene model corresponding to a corresponding to-be-identified scene according to the video image data and the scene recognition result. The electronic device includes:

7. An electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the scene recognition and early warning method in any one of claims 1-5. The computer readable storage medium stores computer instructions for enabling the processor to execute the scene recognition and early warning method in any one of claims 1-5 when executed.

8. A computer-readable storage medium, characterized in that, ​

Images