Abnormal condition identification system and method thereof

Abstract

The invention discloses an abnormal condition identification system and a method thereof. The system comprises a modeling module which constructs a three-dimensional map in a target area; the deployment module deploys an abnormal condition detection model on the edge intelligent equipment according to requirements; the data collection module obtains video monitoring data and geographic position data in a three-dimensional map range; the data processing module processes the video monitoring data and the geographic position data; the human body image frame extraction module extracts human body image frames in the processed video monitoring data and obtains position data of human body key points of the human body image frames; the data analysis module inputs the positions of the human body key points of the continuous human body image frames into an abnormal condition detection model for analysis and identification to obtain an abnormal condition; and the abnormal condition reporting module reports the abnormal condition, the occurrence time of the abnormal condition and the geographic position to an information center when the data analysis module identifies the abnormal condition. And real-time monitoring and accurate identification of abnormal conditions in the target area are realized.

Description

Technical Field

[0001] The present application relates to the technical field of abnormal situation identification, and in particular to an abnormal situation identification system and method thereof. Background Art

[0002] With the rapid development of artificial intelligence technology, edge intelligent devices are playing an increasingly important role in the fields of security protection and health monitoring. Traditional monitoring systems (traditional monitoring devices refer to cameras) mainly rely on manual monitoring or simple motion detection. These methods have limitations in identifying complex behaviors and abnormal situations, such as high false alarm rates. In addition, most of them rely on cloud servers for data processing, which increases network latency, resulting in slow response, and inability to monitor and accurately identify in real time. Therefore, how to monitor and accurately identify abnormal situations in the target area in real time is an urgent problem to be solved. Summary of the invention

[0003] The main purpose of this application is to overcome the shortcomings and deficiencies of the prior art and to provide an abnormal situation identification system and method thereof, which realizes real-time monitoring and accurate identification of abnormal situations in a target area.

[0004] In order to achieve the above objectives, this application adopts the following technical solutions:

[0005] In a first aspect, the present application provides an abnormal situation identification system, comprising:

[0006] A modeling module, used to construct a three-dimensional map of the target area;

[0007] The deployment module is used to deploy the corresponding pre-trained anomaly detection model on the edge smart device according to the needs;

[0008] A data collection module, used to obtain video surveillance data and geographic location data within the range of a three-dimensional map through edge intelligent devices;

[0009] A data processing module, used to process the video surveillance data and the geographic location data to obtain processed video surveillance data and geographic location data;

[0010] A human body image frame extraction module is used to extract the human body image frame in the processed video surveillance data and obtain the position data of the human body key points of the human body image frame;

[0011] A data analysis module, used for inputting the position data of the key points of the human body in the continuous human body image frames into the abnormal situation detection model for analysis, and identifying the abnormal situation according to the analysis result;

[0012] The abnormal situation reporting module is used to report the abnormal situation, the time when the abnormal situation occurred and the geographical location to the information center when the data analysis module identifies an abnormal situation.

[0013] As a preferred technical solution, the edge intelligent device includes a smart camera, an infrared sensor and an ultrasonic sensor.

[0014] As a preferred technical solution, the processing of the video surveillance includes frame extraction, data compression and format conversion.

[0015] As a preferred technical solution, the human body image frame extraction module includes a key point acquisition submodule;

[0016] The key point acquisition submodule is used to identify the positions of the key points of the human body in the continuous human body image frames through a pre-established human body key point model; wherein the positions of the key points of the human body include the positions of the head, neck, shoulders, knees, elbows, wrists and hips.

[0017] As a preferred technical solution, the data analysis module also includes an identification submodule;

[0018] The identification submodule is used to identify a fall if the position of the head and shoulders drops to the position of the knees;

[0019] If the head, neck or shoulder drops to the ground within a preset time, it is identified as falling out of bed.

[0020] As a preferred technical solution, it also includes a review request module;

[0021] The review request module is used to send a review request for the abnormal situation if a suspected abnormal situation is obtained based on the analysis result.

[0022] As a preferred technical solution, when a suspected abnormal situation is obtained, sending a request for abnormal situation review includes:

[0023] The time node when the suspected abnormal situation occurs is recorded, and a suspected abnormal situation review request data frame is sent to multiple nearby edge intelligent devices based on the physical distance; the edge intelligent device retrieves the corresponding data of the time node from the cache area according to the time node when the suspected abnormal situation occurs in the request data frame, inputs the corresponding data of the time node into the pre-trained machine learning model for re-judgment, and outputs the corresponding result.

[0024] In a second aspect, the present application provides an abnormal situation identification system, which is applied to the abnormal situation identification method, and comprises the following steps:

[0025] Construct a three-dimensional map of the target area;

[0026] Deploy the corresponding pre-trained anomaly detection model on the edge smart device as needed;

[0027] Obtain video surveillance data and geographic location data within the three-dimensional map range through edge intelligent devices;

[0028] Processing the video surveillance data and the geographic location data to obtain processed video surveillance data and geographic location data;

[0029] Extracting a human body image frame from the processed video surveillance data, and acquiring position data of human body key points of the human body image frame;

[0030] Inputting the position data of the key points of the human body in the continuous human body image frames into the abnormal situation detection model for analysis, and identifying the abnormal situation according to the analysis results;

[0031] When an abnormal situation is identified, the abnormal situation, the time when the abnormal situation occurred, and the geographical location are reported to the information center.

[0032] In a third aspect, the present application provides an electronic device, the electronic device comprising:

[0033] at least one processor; and,

[0034] a memory communicatively connected to the at least one processor; wherein,

[0035] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor to enable the at least one processor to perform the abnormal situation identification method.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the method for identifying an abnormal situation.

[0037] In summary, compared with the prior art, the effective effects brought about by the technical solution provided by this application include at least:

[0038] The present application proposes an abnormal situation recognition system, wherein the modeling module constructs a three-dimensional map within the target area; the deployment module deploys the corresponding pre-trained abnormal situation detection model on the edge intelligent device according to the demand; the data collection module obtains the video surveillance data and geographic location data within the three-dimensional map range through the edge intelligent device; the data processing module processes the video surveillance data and geographic location data to obtain the processed video surveillance data and geographic location data; the human image frame extraction module extracts the human image frame in the processed video surveillance data and obtains the position data of the human key points of the human image frame; the data analysis module inputs the position of the human key points of the continuous human image frame into the abnormal situation detection model for analysis, and identifies the abnormal situation according to the analysis result; the abnormal situation reporting module reports the abnormal situation, the time when the abnormal situation occurs, and the geographic location to the information center when the data analysis module identifies the abnormal situation. The present application can realize the real-time monitoring and accurate identification of human activities and possible abnormal events by directly deploying or running a specific algorithm model on the edge intelligent device; this localized intelligent processing avoids the delay that may occur in the process of transmitting data to a remote server or cloud platform, thereby ensuring that a quick response can be made in an emergency and improving the timeliness of processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of 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 creative work.

[0040] Figure 1 A block diagram of an abnormal situation identification system provided for one embodiment of the present application;

[0041] Figure 2 A flowchart of an abnormal situation identification method provided for one embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0043] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0044] Example:

[0045] See also Figure 1 In one embodiment of the present application, a system for identifying an abnormal situation is provided, comprising:

[0046] A modeling module, used to construct a three-dimensional map of the target area;

[0047] The deployment module is used to deploy the corresponding pre-trained anomaly detection model on the edge smart device according to the needs;

[0048] A data collection module, used to obtain video surveillance data and geographic location data within the range of a three-dimensional map through edge intelligent devices;

[0049] A data processing module, used to process the video surveillance data and the geographic location data to obtain processed video surveillance data and geographic location data;

[0050] A human body image frame extraction module is used to extract the human body image frame in the processed video surveillance data and obtain the position data of the human body key points of the human body image frame;

[0051] A data analysis module, used for inputting the position data of the key points of the human body in the continuous human body image frames into the abnormal situation detection model for analysis, and identifying the abnormal situation according to the analysis result;

[0052] The abnormal situation reporting module is used to report the abnormal situation, the time when the abnormal situation occurred and the geographical location to the information center when the data analysis module identifies an abnormal situation.

[0053] Furthermore, when the modeling module constructs a three-dimensional map of the target area, the staff uses a tool with SLAM technology to scan the designated area, obtains various types of raw data in the hospital through sensors, and performs data preprocessing, feature extraction, data fusion and other processing based on the various types of raw data obtained in the above process, and uses SLAM technology to construct a three-dimensional map of the hospital scene. Among them, the tool with SLAM technology can be a smart car with infrared ranging and obstacle avoidance functions, a handheld scanner with SLAM function, a drone, a mobile robot, etc.; various types of raw data scanning data, video image data, point cloud data, etc.

[0054] Furthermore, data preprocessing includes data cleaning, data denoising, normalization, etc. Feature extraction refers to extracting the three-dimensional coordinates of key data points, functional areas, traffic areas, and extracting spatial features from three-dimensional maps, such as room size, shape, channel width, staircase location, etc. Extract spatial distribution features from point cloud data, such as the height, volume, and shape of objects.

[0055] In the above-constructed three-dimensional map, various attribute parameters of the edge intelligent device are input, and the k-means algorithm is used to calculate the location suitable for installing the edge intelligent device. The steps include:

[0056] (1) Define attributes for different types of edge smart devices, including range, monitoring capabilities, energy consumption, etc.

[0057] (2) Collect key data points in the hospital's three-dimensional map, such as important areas within the hospital, high-traffic areas, key passages, privacy areas, etc.

[0058] (3) Determine the features that can be used for clustering algorithms. These features include three-dimensional coordinates (X, Y, Z), traffic flow, and area functions such as wards, operating rooms, emergency rooms, and key channels.

[0059] (4) Use the elbow rule to determine the optimal number of clusters so that the coverage of edge smart devices is maximized and the overlap is minimized.

[0060] (5) When assigning key data points to clusters, the range of the edge smart device must be considered to ensure that each point in the cluster can be covered by the corresponding edge smart device. If some areas or data points in the cluster are not within the range of the edge smart device, it is necessary to adjust the device location or increase the number of devices.

[0061] (6) Simulate the coverage effect of edge smart devices on the three-dimensional hospital map to verify whether each cluster is covered by at least one edge smart device and the coverage overlap is minimized.

[0062] (7) According to the simulation results and verification results, adjust the position of the edge intelligent device and rerun the k-means algorithm; repeat the above steps (5) to (7) until the optimal edge intelligent device placement solution is found.

[0063] In this embodiment, a deep learning model such as a convolutional neural network can also be used to predict the coverage effect under a given camera layout, and optimize the position of the edge smart device through iterative learning.

[0064] The edge intelligent devices include multiple ones; the edge intelligent devices include: smart cameras, infrared sensors, ultrasonic sensors, etc.

[0065] As one of the implementation methods, the deployment module deploys the corresponding pre-trained abnormal situation detection model on the edge smart device according to the needs, and the needs may be human fall detection, bed fall detection, body temperature monitoring, etc. The abnormal situation detection model is a lightweight model that is pre-trained, processed by pruning, quantization and other technologies and can be deployed in the edge smart device to run. This model can be used to identify abnormal situations of human activities, such as falls, bed falls, medical equipment failures, respiratory arrest, etc. The abnormal situation of respiratory arrest is monitored by a wristband worn by the patient that monitors human health data, and the wristband also has an intranet interconnection function.

[0066] Furthermore, the time for the edge intelligent device to collect data is set to thirty seconds. The edge intelligent device stores the collected data inside the device every thirty seconds, and defines this part of the data as data in the first data cache area. The edge intelligent device automatically stores the data in the first data cache area in another space inside the device after frame extraction, data compression, format conversion and other operations, and defines this part of the processed data as data in the second data cache area. At the same time, the data in the first data cache area is transmitted to the central data processing system or cloud platform as a backup through TCP / IP or MQTT protocol. When the edge intelligent device completes the processing of the data in the first data cache area and uploads the backup, the data in the first data cache area is deleted, and the memory occupied by this part of the data is cleared. When the data in the second data cache area reaches the system default buffer size, the earliest generated part of the data in the second data cache area is deleted, and the latest data processed in the first data cache area is stored in the second data cache area; so as to continuously process and update the data.

[0067] As one of the implementation modes, the human body image frame extraction module includes a key point acquisition submodule; the key point acquisition submodule is used to identify the positions of human body key points in the continuous human body image frames through a pre-established human body key point model; wherein the positions of the human body key points include the head, neck, shoulders, knees, elbows, wrists, hips and ankles, etc.

[0068] As one embodiment, the data analysis module also includes an identification submodule; the identification submodule is used to identify a sign of falling if the position of the head and shoulders drops to the position of the knees; if the head, neck or shoulders drops to the ground within a preset time, it is used to identify a sign of falling out of bed.

[0069] Specifically, if the abnormal situation detection model performs analysis, if the analysis result is normal, no processing is performed and this stage ends.

[0070] As one implementation mode, it further includes a review request module; the review request module is used to obtain a suspected abnormal situation according to the analysis result (the abnormal situation detection model performs analysis, and if the analysis result is between normal and abnormal, it is marked as a suspected abnormal situation), and then send an abnormal situation review request, the steps of which include:

[0071] Record the time node when the suspected abnormal situation occurs, and send a suspected abnormal situation review request data frame to multiple nearby edge intelligent devices based on the physical distance; the edge intelligent device retrieves the corresponding data of the time node from the second data cache area according to the time node when the suspected abnormal situation occurs in the request data frame, and inputs the corresponding data of the time node into the pre-trained machine learning model for re-judgment. If the review result is normal, the result of the review as normal is returned to the edge intelligent device that sent the abnormal situation review request data frame, and this stage ends. If the review result is an abnormal situation, the time node when the abnormal situation occurs and the data information of the time node stored in the second data cache area are reported to the server of the hospital information center.

[0072] When the data analysis module identifies an abnormal situation, it reports the abnormal situation, the time when the abnormal situation occurred, and the geographical location to the information center. It also includes starting a collaborative processing mechanism to integrate data from different edge intelligent devices to form a unified data set, which includes video data, sensor data, medical device status and other information. The integrated data is cleaned, standardized and normalized to eliminate the differences between different data sources. Then, a collaborative learning algorithm is used to allow multiple edge intelligent devices to share knowledge while keeping their models updated and learning. Through data enhancement, transfer learning and other technologies, the algorithm model of each edge intelligent device is optimized to improve monitoring capabilities. Finally, the analysis results and optimization suggestions are fed back to the relevant edge intelligent devices. The edge intelligent device adjusts the local model and strategy based on the feedback results to adapt to new data and environmental changes.

[0073] This embodiment can utilize multiple edge intelligent devices to perform data alignment and fusion operations, and through collaborative processing technology, effectively integrate the data and analysis capabilities of different devices; this distributed intelligence enhances the system's ability to judge complex situations, significantly improves the accuracy of human body status recognition, reduces the occurrence of false alarms, and makes the system more reliable.

[0074] When the data analysis module identifies an abnormal situation, it reports the abnormal situation, the time when the abnormal situation occurred, and the geographical location to the information center. After receiving the abnormal situation, the information center immediately notifies the relevant medical staff and management personnel so that they can respond quickly and provide necessary assistance. In addition, the abnormal situation reporting module will record the detailed information of the abnormal situation, including the timestamp, location, personnel involved, and handling process of the event, for review and analysis; it can also automatically adjust the sensitivity and priority of the monitoring system according to the nature and severity of the abnormal situation to improve the recognition and response speed of similar events.

[0075] See also Figure 2 In another embodiment of the present application, a method for identifying an abnormal situation is provided, comprising the following steps:

[0076] Construct a three-dimensional map of the target area;

[0077] Deploy the corresponding pre-trained anomaly detection model on the edge smart device as needed;

[0078] Obtain video surveillance data and geographic location data within the three-dimensional map range through edge intelligent devices;

[0079] Processing the video surveillance data and the geographic location data to obtain processed video surveillance data and geographic location data;

[0080] Extracting a human body image frame from the processed video surveillance data, and acquiring position data of human body key points of the human body image frame;

[0081] Inputting the position data of the key points of the human body in the continuous human body image frames into the abnormal situation detection model for analysis, and identifying the abnormal situation according to the analysis results;

[0082] When an abnormal situation is identified, the abnormal situation, the time when the abnormal situation occurred, and the geographical location are reported to the information center.

[0083] It should be noted that, for the sake of convenience of description, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously.

[0084] It should be noted that an abnormal situation identification method of the present application corresponds one-to-one to an abnormal situation identification system of the present application. The technical features and beneficial effects described in the embodiment of the above-mentioned abnormal situation identification system are applicable to the embodiment of an abnormal situation identification method. For specific contents, please refer to the description in the embodiment of the method of the present application. It will not be repeated here. This is hereby declared.

[0085] In another embodiment, an electronic device for implementing an abnormal situation identification method is provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; when the processor executes the computer program, an abnormal situation identification method of any embodiment of the present application is implemented.

[0086] Exemplarily, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more module elements may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the device.

[0087] The device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0088] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0089] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; in addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0090] Accordingly, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute an abnormal situation identification method as described in any one of the above embodiments.

[0091] Those skilled 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 program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] 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.

[0093] The above embodiments are preferred implementation modes of the present application, but the implementation modes of the present application are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present application should be equivalent replacement methods and are included in the protection scope of the present application.

Claims

1. An abnormal situation identification system, characterized in that: include: A modeling module, used to construct a three-dimensional map of the target area; The deployment module is used to deploy the corresponding pre-trained anomaly detection model on the edge smart device according to the needs; A data collection module, used to obtain video surveillance data and geographic location data within the range of a three-dimensional map through edge intelligent devices; A data processing module, used to process the video surveillance data and the geographic location data to obtain processed video surveillance data and geographic location data; A human body image frame extraction module is used to extract the human body image frame in the processed video surveillance data and obtain the position data of the human body key points of the human body image frame; A data analysis module, used for inputting the position data of the key points of the human body in the continuous human body image frames into the abnormal situation detection model for analysis, and identifying the abnormal situation according to the analysis result; The abnormal situation reporting module is used to report the abnormal situation, the time when the abnormal situation occurred and the geographical location to the information center when the data analysis module identifies an abnormal situation.

2. The abnormal situation identification system according to claim 1, characterized in that: The edge intelligent device includes a smart camera, an infrared sensor and an ultrasonic sensor.

3. The abnormal situation identification system according to claim 1, characterized in that: The processing of the video surveillance includes frame extraction, data compression and format conversion.

4. The abnormal situation identification system according to claim 1, characterized in that: The human body image frame extraction module includes a key point acquisition submodule; The key point acquisition submodule is used to identify the positions of the key points of the human body in the continuous human body image frames through a pre-established human body key point model; wherein the positions of the key points of the human body include the positions of the head, neck, shoulders, knees, elbows, wrists and hips.

5. The abnormal situation identification system according to claim 4, characterized in that: The data analysis module also includes an identification submodule; The identification submodule is used to identify a fall if the position of the head and shoulders drops to the position of the knees; If the head, neck or shoulder drops to the ground within a preset time, it is identified as falling out of bed.

6. The abnormal situation identification system according to claim 1, characterized in that: Also includes a review request module; The review request module is used to send a review request for the abnormal situation if a suspected abnormal situation is obtained based on the analysis result.

7. The abnormal situation identification system according to claim 6, characterized in that: If a suspected abnormal situation is obtained, a request for abnormal situation review is sent, including: The time node when the suspected abnormal situation occurs is recorded, and a suspected abnormal situation review request data frame is sent to multiple nearby edge intelligent devices based on the physical distance; the edge intelligent device retrieves the corresponding data of the time node from the cache area according to the time node when the suspected abnormal situation occurs in the request data frame, inputs the corresponding data of the time node into the pre-trained machine learning model for re-judgment, and outputs the corresponding result.

8. A method for identifying abnormal situations, characterized in that: An abnormal situation identification system applied to any one of claims 1 to 7 comprises the following steps: Construct a three-dimensional map of the target area; Deploy the corresponding pre-trained anomaly detection model on the edge smart device as needed; Obtain video surveillance data and geographic location data within the three-dimensional map range through edge intelligent devices; Processing the video surveillance data and the geographic location data to obtain processed video surveillance data and geographic location data; Extracting a human body image frame from the processed video surveillance data, and acquiring position data of human body key points of the human body image frame; Inputting the position data of the key points of the human body in the continuous human body image frames into the abnormal situation detection model for analysis, and identifying the abnormal situation according to the analysis results; When an abnormal situation is identified, the abnormal situation, the time when the abnormal situation occurred, and the geographical location are reported to the information center.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor to enable the at least one processor to perform the basic abnormal situation identification method according to claim 8.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, an abnormal situation identification method as described in any one of claim 8 is implemented.

Images