Abnormal situation monitoring method, device, equipment and medium based on digital twinning

Abstract

Embodiments of the present application provide an abnormal situation monitoring method and device based on digital twinning, equipment and medium. The method comprises: obtaining current site information of a target site and a digital twin model of the target site; wherein the current site information represents the current environmental information of the target site and the current working state of the device deployed in the target site, and the digital twin model represents a three-dimensional visual virtual target site; updating the digital twin model according to the current site information to obtain an updated digital twin model; predicting the warning level of the target site according to the updated digital twin model, and generating a prompt information, and broadcasting the prompt information; wherein the warning level represents the severity of the abnormality in the target site. The method improves the monitoring accuracy and efficiency of the abnormal situation in the target site, and improves the safety and stability of the target site.

Description

Technical Field

[0001] This application relates to the field of anomaly monitoring technology, and in particular to a method, device, equipment and medium for anomaly monitoring based on digital twins. Background Technology

[0002] The various equipment in a gas station is an important material basis for production activities. As time goes by, the condition of the equipment will change due to its own operation and external conditions, and abnormalities such as corrosion, leakage, and deformation may occur.

[0003] Currently, gas station equipment is often inspected and monitored manually, which is not only time-consuming and labor-intensive, but may also lead to safety accidents in serious cases. Therefore, how to solve the lag in manual inspection and monitor abnormal situations in a timely manner is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a digital twin-based method, apparatus, device, and medium for monitoring abnormal situations, in order to improve the accuracy and efficiency of monitoring abnormal situations in target locations.

[0005] In a first aspect, embodiments of this application provide an anomaly monitoring method based on digital twins, comprising:

[0006] Obtain current location information of the target location and a digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location;

[0007] Based on the current location information, the digital twin model is updated to obtain an updated digital twin model;

[0008] Based on the updated digital twin model, the warning level of the target location is predicted, and a prompt message is generated and broadcast; wherein, the warning level characterizes the severity of the anomaly occurring at the target location.

[0009] In one possible implementation, obtaining the current location information of the target location includes:

[0010] Based on a preset information acquisition device, the current location information of the target location is obtained; wherein, the information acquisition device includes at least one of a camera, a pressure detection sensor, a temperature detection sensor, a humidity detection sensor, a smoke detection sensor, and an ammonia detection sensor.

[0011] In one possible implementation, it also includes:

[0012] Obtain the construction information of the target site; wherein the construction information characterizes the size and layout of the target site;

[0013] A digital twin model of the target location is generated based on the construction information of the target location and the preset initial location information.

[0014] In one possible implementation, the digital twin model is updated based on the current location information to obtain an updated digital twin model, including:

[0015] The current location information is compared with the preset initial location information in the digital twin model;

[0016] If the current location information is inconsistent with the preset initial location information in the digital twin model, the preset initial location information is updated to the current location information to obtain the updated digital twin model.

[0017] In one possible implementation, predicting the warning level of the target location based on the updated digital twin model includes:

[0018] Obtain the current location information from the updated digital twin model;

[0019] Based on a preset range of abnormal information values, the current state of each current location information is determined; wherein, the preset range of abnormal information values ​​represents the range of abnormal values ​​for the current location information, and the current state is either a normal state or an abnormal state.

[0020] Based on the current status of each location, the warning level of the target location is predicted.

[0021] In one possible implementation, predicting the warning level of the target location based on the current state of each current location information includes:

[0022] Based on the current status of each current location information, predict the probability value of an anomaly in each current location information;

[0023] Based on the probability value of anomalies in the current location information, the warning level of the target location is predicted.

[0024] In one possible implementation, predicting the warning level of the target location based on the probability value of anomalies in each current location information includes:

[0025] The probability value of each current location information being abnormal is compared with the corresponding probability threshold to determine the target probability; wherein the target probability is greater than the corresponding probability threshold.

[0026] Based on the number of target probabilities and a preset correlation, the warning level of the target location is determined; wherein, the preset correlation represents the relationship between the number of target probabilities and the warning level, and the warning level includes a level 1 warning, a level 2 warning, and a level 3 warning, wherein the severity of anomalies in a level 1 warning is lower than that in a level 2 warning, and the severity of anomalies in a level 2 warning is lower than that in a level 3 warning.

[0027] In one possible implementation, generating a prompt message and broadcasting the prompt message includes:

[0028] If the warning level is Level 1, then abnormal location information is obtained, and a prompt message containing the abnormal location information is generated and broadcast.

[0029] In one possible implementation, generating a prompt message and broadcasting the prompt message includes:

[0030] If the warning level is Level II, then abnormal location information is obtained, the valves of the devices deployed in the target location are controlled to close, and a prompt message containing the abnormal location information is generated and broadcast.

[0031] In one possible implementation, generating a prompt message and broadcasting the prompt message includes:

[0032] If the warning level is Level 3, then obtain the abnormal location information, control the valves of the devices deployed in the target location to close, generate a prompt message containing the abnormal location information, and broadcast the prompt message;

[0033] Acquire image data of the target location, and determine the number of objects in the target location from the image data;

[0034] If the number of objects is equal to or greater than a preset number threshold, a target path is generated and displayed based on the location information of the objects in the target location; wherein, the target path is used to indicate that the objects in the target location leave the target location.

[0035] Secondly, embodiments of this application provide an anomaly monitoring device based on digital twins, comprising:

[0036] The acquisition module is used to acquire the current location information of the target location and the digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location;

[0037] The update module is used to update the digital twin model based on the current location information to obtain the updated digital twin model.

[0038] The alert module is used to predict the warning level of the target location based on the updated digital twin model, generate alert information, and broadcast the alert information; wherein, the warning level represents the severity of the anomaly occurring at the target location.

[0039] Thirdly, embodiments of this application provide an anomaly monitoring device based on digital twins, including: a memory and a processor;

[0040] The memory stores computer-executed instructions;

[0041] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0042] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0043] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0044] This application provides a method, apparatus, device, and medium for monitoring abnormal situations based on digital twins. First, it acquires the current location information and a digital twin model of the target location. The current location information represents the current environmental information and the current operating status of the devices deployed in the target location. The digital twin model represents a three-dimensional, visualized virtual target location. The digital twin model is established based on the acquired initial current location information. Next, the digital twin model is updated based on the current location information to obtain an updated digital twin model. Finally, based on the updated digital twin model, the warning level of the target location is predicted, and a prompt message is generated and broadcast according to the warning level. In this solution, by establishing a digital twin model, abnormal situations in the target location are monitored and warned in a timely manner, improving the accuracy and efficiency of monitoring abnormal situations in the target location and enhancing the security and stability of the target location. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0046] Figure 1 A schematic diagram of the system architecture for an anomaly monitoring method based on digital twins provided in this application;

[0047] Figure 2 A flowchart illustrating an anomaly monitoring method based on digital twins provided in this application;

[0048] Figure 3 A flowchart illustrating an anomaly monitoring method based on digital twins provided in this application;

[0049] Figure 4 A flowchart illustrating an anomaly monitoring method based on digital twins provided in this application;

[0050] Figure 5 A complete flowchart illustrating an anomaly monitoring method based on digital twins provided in this application;

[0051] Figure 6 A schematic diagram of the structure of an abnormal situation monitoring device based on digital twin provided in this application;

[0052] Figure 7 A schematic diagram of the structure of an abnormal situation monitoring device based on digital twin provided in this application;

[0053] Figure 8 This is a schematic diagram of the structure of an anomaly monitoring device based on digital twin, which is provided for this application.

[0054] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0056] The fuel stored at gas stations is flammable and explosive, posing a high potential risk of accidents with serious consequences. Gas station equipment is a crucial material foundation for production activities; however, over time, due to its own operation and external conditions, its technical condition changes, leading to malfunctions such as corrosion, leaks, and deformation. Therefore, the safety management of gas station equipment directly impacts public safety and the normal operation of the petroleum industry.

[0057] As can be seen from the above background technology, the current method of manual inspection is often used for gas station detection and early warning, which is not only time-consuming and labor-intensive, but also has a lag effect and may lead to safety accidents in serious cases.

[0058] This application provides a digital twin-based anomaly monitoring method, which relates to the field of data anomaly monitoring technology, and in particular to a digital twin-based anomaly monitoring method, device, equipment and medium, aiming to solve the above-mentioned technical problems of the prior art.

[0059] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0060] Figure 1 A schematic diagram of the system architecture for an anomaly monitoring method based on digital twins provided in this application is shown below. Figure 1 As shown, the system comprises six parts: a control module, an information acquisition module, a digital twin model construction module, a digital twin model correction module, a digital twin model prediction module, and a hazard warning and planning module. The control module is used for overall system control; the information acquisition module collects actual information data from the gas station; the digital twin model construction module builds a digital twin model of the gas station based on the actual information data; the digital twin model correction module corrects the digital twin model based on real-time actual information data; the digital twin model prediction module predicts the digital twin model based on an expert knowledge base to determine whether anomalies will occur; and the hazard warning and planning module takes appropriate measures for abnormal states at the target location.

[0061] Figure 2 A flowchart illustrating an anomaly monitoring method based on digital twins provided in this application is shown below. Figure 2 As shown, the method includes:

[0062] S201. Obtain the current location information and digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location.

[0063] For example, the current location information represents the current environmental information of the target location and the current operating status of the devices deployed in the target location. These devices can be equipment such as fuel tanks, fuel nozzles, and level gauges at a gas station. The digital twin model represents a three-dimensional, visualized virtual target location. The system has pre-set information acquisition devices to obtain the current location information of the target location. For example, the information acquisition devices can be used to obtain current location information, including temperature, humidity, and pressure. Various information acquisition devices are available, including cameras for capturing image information of the current location; pressure sensors for detecting pressure in fuel tanks and fuel nozzles; temperature sensors for detecting the temperature of the surrounding environment, fuel tanks, and fuel nozzles; humidity sensors for detecting humidity around the gas station; smoke sensors for detecting smoke at the gas station; and ammonia sensors for detecting ammonia leaks at the gas station. Secondly, based on the obtained current location information and combined with the construction information of the target location, a digital twin model of the target location is obtained. The construction information can represent the size and layout of the target location; for example, the construction information can include the installation locations of various devices within the target location.

[0064] A digital twin is a digital technology that uses computers to create virtual models to simulate and monitor objects or systems in the real world, and can reflect the state and changes of real objects in real time.

[0065] The advantage of this setup is that it allows for the creation of a digital twin model based on the actual information of the target location, which helps to increase the model's realism.

[0066] In this embodiment, obtaining the current location information of the target location includes: obtaining the current location information of the target location based on a preset information acquisition device; wherein, the information acquisition device includes at least one of a camera, a pressure detection sensor, a temperature detection sensor, a humidity detection sensor, a smoke detection sensor, and an ammonia detection sensor.

[0067] For example, the system is pre-equipped with information acquisition devices, which include various types. These may include, for instance, cameras, pressure sensors, temperature sensors, humidity sensors, smoke sensors, and ammonia sensors. The camera is used to acquire image information of the target location; the pressure detection module is used to detect the pressure in the fuel tank and fuel nozzle; the temperature detection module is used to detect the temperature of the surrounding environment, the fuel tank, and the fuel nozzle; the humidity detection module is used to detect the humidity of the environment surrounding the gas station; the smoke detection module is used to detect the smoke situation at the gas station; and the ammonia detection module is used to detect ammonia leaks at the gas station. Through these information acquisition devices, the current location information of the target location can be obtained in real time or periodically. That is, the current location information may include the location of the fuel tank in the gas station, the location of safety equipment, the temperature and humidity of the environment in the gas station, and the pressure in the fuel nozzle, etc.

[0068] The advantage of this setup is that by setting up multiple information collection devices, it is easy to collect information from the target location in a comprehensive manner, thereby improving the accuracy of the information and thus enhancing the monitoring precision.

[0069] In this embodiment, the method further includes: acquiring construction information of the target site; wherein the construction information represents the size and layout of the target site; and generating a digital twin model of the target site based on the construction information of the target site and preset initial site information.

[0070] For example, construction information represents the size and layout of the target site. This construction information includes various elements, such as the gas station's geographical location, the capacity of the fuel tanks, the model and number of fuel nozzles, the diameter and material of the pipes, and the configuration of safety equipment such as fire extinguishers and leak detectors. The digital twin model represents a three-dimensional, visualized virtual target site. The preset initial site information is either the initial current site information or the default current site information obtained through an information acquisition device.

[0071] The initial model is a digital twin model generated based on the construction information of the target site and the preset initial site information. First, a virtual 3D visualization model of the target site is created based on its construction information. Then, the 3D visualization model is arranged according to the acquired initial site information, which may include the locations of fuel tanks, safety equipment, ambient temperature and humidity, and pressure in the fuel nozzles. This final virtual model of the target site is then determined, forming the initial model. The system is pre-configured with an information acquisition device and a control module. The control module can acquire construction parameters from the gas station's design documents, construction records, equipment manuals, and sensor data. Combined with the current site information obtained from the information acquisition device—the preset initial site information—a digital twin model of the target site is generated.

[0072] The advantage of this setup is that it allows for the construction of a digital twin model based on the actual construction data of the target site, simulating the real-world conditions of the target site in real time, thus improving the model's realism.

[0073] S202. Based on the current location information, update the digital twin model to obtain the updated digital twin model.

[0074] For example, a digital twin model represents a three-dimensional, visualized virtual target location. Current location information is acquired by the system's information acquisition device, including image information, pressure information, temperature information, humidity information, smoke information, ammonia leak information, etc. Construction information represents the size and layout of the target location. For instance, after acquiring the current location information and construction information of the target location, the system establishes an initial digital twin model based on these information. The acquired location information is the preset initial location information. For example, if the system acquires the current location information of the target location at 9:00 AM, the preset initial location information is the current location information acquired at 9:00 AM. If the system acquires the current location information of the target location again at 10:00 AM, and this information is inconsistent with the information in the model, the current location information needs to be updated in the digital twin model. Therefore, the preset initial location information is the current location information of the target location acquired at 10:00 AM. Meanwhile, the system retrieves the current location information of the target location again according to a preset time period, and determines whether the retrieved current location information of the target location is consistent with the initial location information in the digital twin model. If they are consistent, the digital twin model is not updated. If they are inconsistent, the digital twin model is updated by retrieving the current location information of the target location and updating it to the digital twin model, thus obtaining the updated digital twin model.

[0075] The advantage of this setup is that it makes it easier to ensure that the location information of the digital twin model is consistent with the location information of the target location in real time, thereby improving the accuracy of the model.

[0076] S203. Based on the updated digital twin model, predict the warning level of the target location, generate a prompt message, and broadcast the prompt message; wherein, the warning level characterizes the severity of the anomaly occurring at the target location.

[0077] For example, the digital twin model represents a three-dimensional visualized virtual target location, and the prompt information is used to prompt staff to inspect abnormal locations in the target location. The broadcasting methods include various forms, such as broadcasting through a display screen or broadcasting by sending the prompt information to the staff's terminal device.

[0078] For example, after acquiring the current location information and construction information of the target location, the system generates an updated digital twin model based on this information. Simultaneously, the system acquires the current location information of the target location at preset time intervals and compares it with the current location information in the constructed digital twin model. If they match, no update is performed; otherwise, the acquired location information is updated in real-time to the digital twin model. The system has a pre-set knowledge base containing anomalies of the target location derived from historical data, their causes, and probability values ​​for each anomaly. The probability value represents the number of times an anomaly occurs within a certain period. The updated location information in the digital twin model is then acquired to determine its current state. The current state of the location information includes normal and abnormal values. For example, if the location information is ambient temperature, then the current state of that ambient temperature can be either normal or abnormal. Given the current state of the acquired location information, an anomaly probability value is calculated for each location based on existing probability values ​​in the knowledge base. For example, if the acquired ambient temperature is an anomaly, the anomaly probability value for each of the other locations under this anomaly temperature condition is calculated based on existing probability values ​​in the knowledge base. The anomaly probability value for each location is compared with its corresponding preset probability threshold to determine the target probability. Finally, based on the correlation between the number of target probabilities and the warning level, a warning level is determined, where the target probability refers to the anomaly probability value exceeding the preset probability threshold. A notification is then sent to staff to warn of the anomaly at the target location.

[0079] The advantage of this setup is that it uses a digital twin model to predict and report abnormal situations at the target location, thereby improving the safety and stability of the target location.

[0080] This application provides a method, apparatus, device, and medium for monitoring abnormal situations based on digital twins. First, it acquires the current location information and a digital twin model of the target location. The current location information represents the current environmental information and the current operating status of the devices deployed in the target location. The digital twin model represents a three-dimensional, visualized virtual target location. The digital twin model is established based on the acquired initial current location information. Next, the digital twin model is updated based on the current location information to obtain an updated digital twin model. Finally, based on the updated digital twin model, the warning level of the target location is predicted, and a prompt message is generated and broadcast according to the warning level. In this solution, by establishing a digital twin model, abnormal situations in the target location are monitored and warned in a timely manner, improving the accuracy and efficiency of monitoring abnormal situations in the target location and enhancing the security and stability of the target location.

[0081] Figure 3 A flowchart illustrating an anomaly monitoring method based on digital twins provided in this application is shown below. Figure 2 As shown, the method includes:

[0082] S301. Obtain the current location information and digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location.

[0083] This step can be referred to step S201 above, and will not be repeated here.

[0084] S302. Compare the current location information with the preset initial location information in the digital twin model.

[0085] For example, the current location information may include the location of the fuel tanks in the gas station, the location of safety equipment, the temperature and humidity of the gas station environment, and the pressure in the fuel nozzle. The preset initial location information is the initial current location information of the target location obtained through the information acquisition device or the default current location information. The digital twin model represents a three-dimensional visualized virtual target location, and the construction information represents the size and layout of the target location. For example, a digital twin model is first constructed based on the obtained current location information and construction information of the target location. At this time, the obtained current location information is the initial location information. Meanwhile, the system acquires the location information of the target location according to a preset time period. For example, at 9 o'clock, the system acquires the location information of the target location, i.e., the initial location information, and constructs a digital twin model based on this location information. At 10 o'clock, the system acquires the location information of the target location again and compares the location information acquired at 10 o'clock with the initial location information. If they match, the digital twin model is not updated. If they do not match, the location information of the target location acquired at 10 o'clock is updated into the digital twin model. At this time, the location information of the target location updated into the digital twin model becomes the initial location information. When the system acquires the location information of the target location again at 11 o'clock, the initial location information is compared with the newly acquired location information again.

[0086] The advantage of this setup is that it facilitates updating the digital twin model with real-time data from the target location, thereby improving the model's accuracy.

[0087] S303. If the current location information and the preset initial location information in the digital twin model are inconsistent, the preset initial location information is updated to the current location information to obtain the updated digital twin model.

[0088] For example, the current location information may include the location of the fuel tanks in the gas station, the location of safety equipment, the temperature and humidity of the gas station environment, and the pressure in the fuel nozzle. The preset initial location information is the initial current location information of the target location obtained through the information acquisition device or the default current location information. The digital twin model represents a three-dimensional visualized virtual target location. First, the system acquires the location information and construction information of the target location, where the construction information represents the size and layout of the target location. A digital twin model is built based on the acquired location information and construction information of the target location. The location information of the target location acquired at this time is the initial location information. At the same time, the system acquires the location information of the target location again according to a preset time period. The consistency of the currently acquired location information of the target location is compared with the initial location information in the digital twin model. If they are consistent, the digital twin model is not updated. If they are inconsistent, the newly acquired current location information of the target location is updated into the digital twin model to obtain the updated digital twin model.

[0089] The advantage of this setup is that it allows for regular updates to the digital twin model, which helps improve the model's accuracy.

[0090] This application provides a method, apparatus, device, and medium for monitoring abnormal situations based on digital twins. First, it acquires the current location information and a digital twin model of the target location. The current location information represents the current environmental information and the current operating status of the devices deployed in the target location. The digital twin model represents a three-dimensional, visualized virtual target location. The digital twin model is established based on the acquired initial current location information. Next, the digital twin model is updated based on the current location information to obtain an updated digital twin model. Finally, based on the updated digital twin model, the warning level of the target location is predicted, and a prompt message is generated and broadcast according to the warning level. In this solution, by establishing a digital twin model, abnormal situations in the target location are monitored and warned in a timely manner, improving the accuracy and efficiency of monitoring abnormal situations in the target location and enhancing the security and stability of the target location.

[0091] Figure 4 A flowchart illustrating an anomaly monitoring method based on digital twins provided in this application is shown below. Figure 3 As shown, the method includes:

[0092] S401. Obtain the current location information and digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location.

[0093] This step can be referred to step S301 above, and will not be repeated here.

[0094] S402. Update the digital twin model based on the current location information to obtain the updated digital twin model.

[0095] This step can be referred to step S302 above, and will not be repeated here.

[0096] S403. Obtain the current location information from the updated digital twin model.

[0097] For example, a digital twin model represents a three-dimensional, visualized virtual target location. The system acquires current location information and construction information of the target location using preset information acquisition devices, which may include cameras, pressure sensors, temperature sensors, humidity sensors, smoke sensors, ammonia sensors, etc. The current location information may include the location of fuel tanks in a gas station, the location of safety equipment, the temperature and humidity of the gas station environment, and the pressure in the fuel nozzles. The construction information represents the size and layout of the target location and may include the geographical location of the gas station, the capacity of fuel tanks, the model and number of fuel nozzles, the diameter and material of pipes, and the configuration of safety equipment such as fire extinguishers and leak detectors. Based on the acquired current location information and construction information, a digital twin model is constructed. Simultaneously, the system acquires location information of the target location at preset time intervals and compares this location information with the location information in the digital twin model. If there is a discrepancy, the location information is updated in the digital twin model, and the updated current location information is acquired from the digital twin model.

[0098] The advantage of this setup is that it facilitates providing the accuracy of the model.

[0099] S404. Determine the current state of each current location information according to the preset information anomaly value range; wherein, the preset information anomaly value range represents the range of current location information that is anomaly value, and the current state is a normal value state or an anomaly value state.

[0100] For example, the preset information anomaly range represents the range of anomalies in the current location information. The current state is divided into two types: normal state and anomaly state. The system has a preset knowledge base that stores the information anomaly ranges. For instance, if the current location information obtained from the updated digital twin model is an oil tank temperature of 35 degrees Celsius, and the knowledge base stores an anomaly range of 30-100 degrees Celsius for this oil tank temperature, then the oil tank temperature state is determined to be an anomaly state. If the oil tank temperature is 28 degrees Celsius, then the oil tank temperature state is determined to be a normal state.

[0101] The advantage of this setting is that by defining the range of outliers, it is easier to determine the current status of the current location information and improve the security of the target location.

[0102] S405. Based on the current status of each location's information, predict the warning level of the target location.

[0103] For example, the warning levels include Level 1 warning, Level 2 warning and Level 3 warning. The severity of the anomaly in Level 1 warning is lower than that in Level 2 warning, and the severity of the anomaly in Level 2 warning is lower than that in Level 3 warning. The system has a pre-set knowledge base containing the range of information anomaly values ​​and the probability value of each state of the current location information calculated based on historical data.

[0104] For example, to acquire the current location information of a target location in the updated digital twin model, the system has a pre-set knowledge base containing a range of outlier values. This outlier range represents the range of outliers in the current location information. The system compares the acquired current location information with the outlier ranges in the knowledge base to determine the current state of the location information, which includes both normal and abnormal states. The knowledge base contains information on abnormal situations, their causes, and probability values ​​for each abnormal situation, derived from historical data. The probability value represents the frequency of an abnormal situation occurring within a certain period. Given the current state of the location information, the system calculates the probability value for each location based on the existing probability values ​​in the knowledge base. This probability value is then compared with its corresponding preset probability threshold. The warning level is determined based on the number of outlier probabilities exceeding the preset threshold. For example, based on the existing probability values ​​in the knowledge base, three categories of outlier probabilities are calculated: temperature, humidity, and pressure. A Level 1 warning is issued when the abnormal probability value of temperature is greater than its corresponding preset probability threshold, while the abnormal probability values ​​of humidity and pressure are both less than their corresponding preset probability thresholds. A Level 2 warning is issued when the abnormal probability values ​​of temperature and humidity are both greater than their respective preset probability thresholds, while the abnormal probability value of pressure is less than its preset probability threshold. A Level 3 warning is issued when the abnormal probability values ​​of temperature, humidity, and pressure are all greater than their respective preset probability thresholds.

[0105] The advantage of this setup is that it allows for the classification of early warning levels for target locations, which facilitates improved accuracy and efficiency in monitoring abnormal situations within those locations.

[0106] This application provides a method, apparatus, device, and medium for monitoring abnormal situations based on digital twins. First, it acquires the current location information and a digital twin model of the target location. The current location information represents the current environmental information and the current operating status of the devices deployed in the target location. The digital twin model represents a three-dimensional, visualized virtual target location. The digital twin model is established based on the acquired initial current location information. Next, the digital twin model is updated based on the current location information to obtain an updated digital twin model. Finally, based on the updated digital twin model, the warning level of the target location is predicted, and a prompt message is generated and broadcast according to the warning level. In this solution, by establishing a digital twin model, abnormal situations in the target location are monitored and warned in a timely manner, improving the accuracy and efficiency of monitoring abnormal situations in the target location and enhancing the security and stability of the target location.

[0107] In this embodiment, predicting the warning level of the target location based on the current state of each current location information includes: predicting the probability value of an anomaly in each current location information based on the current state of each current location information; and predicting the warning level of the target location based on the probability value of an anomaly in each current location information.

[0108] For example, the warning levels include Level 1, Level 2, and Level 3 warnings. The severity of anomalies in Level 1 warnings is lower than that in Level 2 warnings, and the severity of anomalies in Level 2 warnings is lower than that in Level 3 warnings. The system has a pre-set knowledge base containing information anomaly value ranges and probability values ​​for each state of the current location information calculated based on historical data. The knowledge base contains information anomaly value ranges, where the information anomaly value range represents the range of anomalies in the current location information. For example, the current location information includes three types: temperature, humidity, and pressure. Upon obtaining the current location information of the target location, the current state of the current location information is determined, which is divided into normal value state and abnormal value state. For example, if the obtained current location information of the target location is an oil tank temperature of 35 degrees Celsius, firstly, based on the information anomaly value range of 30-100 degrees Celsius in the knowledge base, the oil tank temperature of 35 degrees Celsius is determined to be an anomaly state. Under this abnormal oil tank temperature state, the anomaly probability value for each location information is calculated based on the existing probability values ​​in the knowledge base. The existing probability values ​​in the knowledge base are calculated based on historical data, and the probability value represents the number of times an anomaly occurs within a certain period. The abnormal probability value of each location information is compared with its corresponding preset probability threshold. The warning level of the target location is classified according to the number of abnormal probability values ​​that are greater than the preset probability threshold.

[0109] The advantage of this setup is that it allows for the calculation of anomaly probability values ​​for each location's information, making it easier to classify warning levels and thus making warnings more accurate.

[0110] In this embodiment, predicting the warning level of the target location based on the probability value of anomalies in each current location information includes: comparing the probability value of anomalies in each current location information with the corresponding probability threshold to determine the target probability; wherein the target probability is greater than the corresponding probability threshold; and determining the warning level of the target location based on the number of target probabilities and a preset correlation relationship; wherein the preset correlation relationship represents the correlation between the number of target probabilities and the warning level, and the warning levels include Level 1 warning, Level 2 warning, and Level 3 warning, wherein the severity of anomalies in Level 1 warning is lower than that in Level 2 warning, and the severity of anomalies in Level 2 warning is lower than that in Level 3 warning.

[0111] For example, if the target probability is greater than the corresponding probability threshold, a preset correlation represents the relationship between the number of target probabilities and the warning level. Warning levels include Level 1, Level 2, and Level 3 warnings, with Level 1 warnings indicating a lower severity of anomalies than Level 2 warnings, and Level 2 warnings indicating a lower severity of anomalies than Level 3 warnings. For instance, to acquire current location information from an updated digital twin model, the system has a preset knowledge base containing information anomaly ranges, where the information anomaly range represents the range of current location information that is anomaly. Based on the information anomaly ranges in the knowledge base, the current state of each acquired current location information is determined, where the current state is either a normal state or an anomaly state. The anomaly probability value for each location information is calculated based on existing probability values ​​in the knowledge base, where existing probability values ​​are calculated from historical data, and the probability value represents the number of times an anomaly occurs within a certain period. The calculated anomaly probability value for each location information is compared with its corresponding preset probability threshold. If the anomaly probability value is greater than the probability threshold, then the anomaly probability value is determined as the target probability. Based on the number of target probabilities and the preset correlation, the warning level is determined. For example, when the number of target probabilities is 3, it is determined as a Level 1 warning; when the number of target probabilities is 5, it is determined as a Level 2 warning; and when the number of target probabilities is 7, it is determined as a Level 3 warning.

[0112] The advantage of this setting is that by setting a probability threshold, the warning level can be divided according to the correlation between the number of target probabilities and the warning level, which helps to improve the accuracy of the system.

[0113] In this embodiment, generating and broadcasting a prompt message includes: if the warning level is the Level 1 warning, obtaining abnormal location information, generating a prompt message containing the abnormal location information, and broadcasting the prompt message.

[0114] For example, the warning levels include Level 1, Level 2, and Level 3 warnings. The severity of the anomaly in Level 1 warnings is lower than that in Level 2 warnings, and the severity of the anomaly in Level 2 warnings is lower than that in Level 3 warnings. The warning information is used to remind staff to inspect the abnormal location. There are multiple ways to broadcast the information. For example, if the staff's terminal device is bound to the system, the system can broadcast the anomaly information by sending it to the staff's terminal device. Alternatively, the anomaly information can be broadcast by displaying it on a screen.

[0115] When the updated digital twin model's current location information is obtained, the current state of the current location information is first determined. This current state is categorized into anomaly and normal states. The system has a pre-set knowledge base. Given the current state of the current location information, an anomaly probability value is calculated for each piece of information based on pre-set probability values ​​in the knowledge base. These pre-set probability values ​​are calculated from historical data and represent the number of times an anomaly occurs within a given period. The anomaly probability value for each piece of information is compared to its corresponding pre-set probability threshold. If the anomaly probability value is greater than the pre-set threshold, it is determined as a target probability. Based on the correlation between the number of target probabilities and the warning level, the warning level is determined, where the target probability is greater than the corresponding probability threshold. If the warning level is determined to be Level 1, the anomaly location information is obtained and sent to a display screen for display and broadcast, or to staff terminals to remind staff to check and repair the situation.

[0116] The beneficial effect of this setup is that it provides early warnings of abnormal information, facilitates the elimination of potential dangers in the target location, and improves the safety and stability of the target location.

[0117] In this embodiment, generating and broadcasting a prompt message includes: if the warning level is the Level 2 warning, obtaining abnormal location information, controlling the valves of the devices deployed in the target location to close, generating a prompt message containing the abnormal location information, and broadcasting the prompt message.

[0118] For example, the warning levels include Level 1, Level 2, and Level 3 warnings. The severity of the anomaly in Level 1 warnings is lower than that in Level 2 warnings, and the severity of the anomaly in Level 2 warnings is lower than that in Level 3 warnings. The warning information is used to remind staff to check and repair the anomaly. There are multiple ways to broadcast the information. For example, if the staff's terminal device is bound to the system, the system can broadcast the anomaly information by sending it to the staff's terminal device. Alternatively, the system can display the anomaly information on the screen and broadcast it.

[0119] For example, based on the number of target probabilities and the correlation between these probabilities and the warning level, the warning level is determined. The target probability refers to the value at which the probability of an anomaly in the current location exceeds a preset probability threshold. This anomaly probability is derived from existing probability values ​​in a preset knowledge base and represents the number of times an anomaly occurs within a given period. If the warning level is determined to be a Level 2 warning, the abnormal location information is first acquired. Simultaneously, all valves of the devices deployed in the target location are closed, and power is cut off. These valves include various types, such as fuel tank valves and fuel nozzle valves. A prompt message containing the abnormal location information is generated and displayed and broadcast on a screen or broadcast through staff's terminal devices to remind staff to check and repair the abnormal location.

[0120] The advantage of this setup is that closing the valves of the equipment at the target location and stopping the power supply helps improve the safety and stability of the target location.

[0121] In this embodiment, generating and broadcasting a prompt message includes: if the warning level is the third-level warning, acquiring abnormal location information, controlling the valves of the devices deployed in the target location to close, generating a prompt message containing the abnormal location information, and broadcasting the prompt message; acquiring image data of the target location, determining the number of objects in the target location from the image data; if the number of objects is equal to or greater than a preset number threshold, generating and displaying a target path based on the location information of the objects in the target location; wherein, the target path is used to indicate that the objects in the target location leave the target location.

[0122] For example, the prompt message is used to remind staff to check for abnormal information in the target area and to inspect the abnormal location. The prompt message can be broadcast through a display screen or staff terminal device. The image data is obtained through a camera to determine the number of vehicles and people in the target area. The target path is used to instruct objects in the target area to leave the target area.

[0123] For example, when the system predicts abnormal location information at a target location, if the warning level is determined to be Level 3, it first acquires the abnormal location information, closes the valves of the devices deployed at the target location, and cuts off the power supply. The abnormal location information is then displayed and broadcast on a screen or a notification is sent to staff terminals. Next, the system uses cameras in the information acquisition device to obtain information about vehicles and personnel at the target location. If the number of vehicles and personnel is less than a preset threshold, no route planning is performed for the corresponding vehicles and personnel; only the abnormal location information is broadcast and displayed on the screen, reminding vehicles and personnel to leave the target location normally. If the number of vehicles and personnel at the target location is greater than or equal to the preset threshold, route planning is performed for the corresponding vehicles and personnel. This route planning is done using a pre-built route planning model. When the number of vehicles and personnel at the target location is greater than or equal to the preset threshold, the system inputs the image or video information acquired by the cameras into the preset route planning model to perform route planning for the vehicles and personnel at the target location, generate an evacuation plan, and display the generated evacuation plan on the screen.

[0124] The advantage of this setup is that it allows for route planning for people in the target area, which facilitates the protection of people in the target area and improves the overall security of the target area.

[0125] Figure 5 A complete flowchart illustrating an anomaly monitoring method based on digital twins, as provided in this application, is shown below. Figure 5 As shown, the method specifically includes the following steps:

[0126] S501. Collect actual data from gas stations based on the information collection module.

[0127] For example, the system is pre-installed with an information acquisition module, which includes a camera, a pressure detection module, a temperature detection module, a humidity detection module, a smoke detection module, and an ammonia detection module. The camera is used to acquire image information of the gas station, the pressure detection module is used to detect the pressure information in the fuel tank and fuel nozzle, the temperature detection module is used to detect the temperature information of the surrounding environment, the fuel tank and fuel nozzle, the humidity detection module is used to detect the humidity information of the surrounding environment of the gas station, the smoke detection module is used to detect the smoke situation of the gas station, and the ammonia detection module is used to detect the ammonia leakage situation of the gas station.

[0128] The advantage of this setup is that it allows for the collection of actual data from gas stations, making the constructed digital twin model more accurate.

[0129] S502, Based on the digital twin model construction module, a digital twin model of the gas station is built according to the actual information of the gas station.

[0130] S503, a digital twin model correction module, corrects the digital twin model of the gas station based on real-time actual information.

[0131] For example, the twin model represents a virtual target location visualized in three dimensions. After the actual information of the gas station is obtained through the information acquisition module, the digital twin model construction module constructs a digital twin model based on the actual information. The digital twin model correction module collects the actual information of the gas station according to a preset time period and compares the collected actual information of the gas station with the actual information of the gas station in the digital twin model. If they are consistent, the digital twin model is not corrected. If they are inconsistent, the actual information of the gas station collected by the digital twin correction module is updated into the digital twin model.

[0132] The advantage of this setup is that it makes it easier to keep the actual information in the digital twin model consistent with the actual information at the gas station, thereby improving the accuracy of monitoring the target location.

[0133] S504. The digital twin model prediction module predicts the digital twin model of the gas station based on the expert knowledge base to determine whether any anomalies have occurred.

[0134] For example, the system has a pre-set expert knowledge base containing probability values ​​for location information of each target location. These probability values ​​are calculated using a Bayesian network based on historical data. First, the updated digital twin model of the gas station location information is acquired, and its current state is determined. The current state is categorized as either normal or abnormal. The acquired location information is then input into the Bayesian network. Based on the existing probability values ​​in the knowledge base, the abnormal probability value for each gas station location in its current state is calculated. If the obtained abnormal probability value exceeds a preset probability threshold, the situation is considered abnormal. Furthermore, based on the correlation between the obtained abnormal probability value and the warning level, the warning level is classified, and a warning is issued according to the classified warning level.

[0135] The advantage of this setup is that it facilitates the detection of abnormal situations at gas stations, thereby improving the safety and stability of gas stations.

[0136] S505. Based on the hazard warning planning module, take corresponding measures according to the abnormal state.

[0137] For example, the system has a pre-set hazard warning planning module. When the system predicts an abnormal situation, it takes different measures according to the warning level. For a Level 1 warning, the hazard warning planning module obtains the abnormal location information through the control module and displays and broadcasts this information on the screen, or sends it to the staff's terminal device to remind them to go for repairs. For a Level 2 warning, the hazard warning planning module controls the closure of all valves in the gas station and stops the power supply through the control module. These valves may include valves on the fuel tank, fuel nozzles, etc. It also obtains the abnormal location information and sends a prompt to remind staff to go for repairs. For a Level 3 warning, the hazard warning planning module controls the closure of all valves in the gas station and stops the power supply through the control module. The hazard warning planning module obtains images or videos captured by the camera and identifies vehicle and personnel location information through these images or videos. If the number of vehicles and personnel in the gas station is less than a preset threshold, no route planning is performed for vehicles and personnel; instead, a prompt is broadcast to the screen or staff's terminal device. If the number of vehicles and personnel at the gas station is greater than or equal to a preset threshold, the system will plan routes for the corresponding vehicles and personnel based on a preset route planning model and acquired image or video information. The system will then remind the vehicles and personnel to drive out of the gas station according to the planned route. The route planning for vehicles and personnel can be broadcast through the early warning broadcast module, and the corresponding route can be displayed on the screen or sent to the staff's terminal device for easy viewing.

[0138] The advantage of this setup is that it allows for route planning for vehicles and personnel at gas stations, which helps ensure their safety and improves the safety and stability of the gas station.

[0139] Figure 6 A schematic diagram of an anomaly monitoring device based on digital twins provided in this application is shown below. Figure 6 As shown, the abnormal situation monitoring device 600 based on digital twin provided in this embodiment includes:

[0140] The acquisition module 601 is used to acquire the current location information of the target location and the digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location;

[0141] The update module 602 is used to update the digital twin model according to the current location information to obtain the updated digital twin model;

[0142] The prompting module 603 is used to predict the warning level of the target location based on the updated digital twin model, generate prompt information, and broadcast the prompt information; wherein, the warning level represents the severity of the anomaly occurring at the target location.

[0143] Figure 7 A schematic diagram of an anomaly monitoring device based on digital twins provided in this application is shown below. Figure 7 As shown, the device 700 includes an acquisition module 701, an update module 702, and a prompting module 703. The acquisition module 701 includes a first acquisition unit 7011, a second acquisition unit 7012, and a generation unit 7013. The update module 702 includes a comparison unit 7021 and an update unit 7022. The prompting module 703 includes a third acquisition unit 7031, a first determination unit 7032, a prediction unit 7033, a first broadcast unit 7034, a second broadcast unit 7035, a third broadcast unit 7036, a second determination unit 7037, and a display unit 7038.

[0144] In one example, module 701 is retrieved, including:

[0145] The first acquisition unit 7011 is used to acquire the current location information of the target location based on a preset information acquisition device; wherein, the information acquisition device includes at least one of a camera, a pressure detection sensor, a temperature detection sensor, a humidity detection sensor, a smoke detection sensor, and an ammonia detection sensor.

[0146] In one example, module 701 also includes:

[0147] The second acquisition unit 7012 is used to acquire the construction information of the target site; wherein the construction information characterizes the size and layout of the target site;

[0148] The generation unit 7013 is used to generate a digital twin model of the target site based on the construction information of the target site and the preset initial site information.

[0149] In one example, module 702 is updated, including:

[0150] The comparison unit 7021 is used to compare the current location information with the preset initial location information in the digital twin model;

[0151] The update unit 7022 is used to update the preset initial location information to the current location information if the current location information and the preset initial location information in the digital twin model are inconsistent, so as to obtain the updated digital twin model.

[0152] In one example, prompt module 703 includes:

[0153] The third acquisition unit 7031 is used for the current location information in the updated digital twin model;

[0154] The first determining unit 7032 is used to determine the current state of each current location information according to a preset information anomaly value range; wherein, the preset information anomaly value range represents the range of current location information as anomalies, and the current state is a normal value state or an anomaly value state;

[0155] The prediction unit 7033 is used to predict the warning level of the target location based on the current status of each current location information.

[0156] In one example, prediction unit 7033 includes:

[0157] The first prediction subunit is used to predict the probability value of an anomaly in each current location information based on the current state of each current location information.

[0158] The second prediction subunit predicts the warning level of the target location based on the probability value of anomalies in each current location information.

[0159] In one example, the second prediction subunit is specifically used to compare the probability value of anomalies in each current location information with the corresponding probability threshold to determine the target probability; wherein the target probability is greater than the corresponding probability threshold; based on the number of target probabilities and a preset correlation relationship, the warning level of the target location is determined; wherein the preset correlation relationship represents the correlation between the number of target probabilities and the warning level, and the warning level includes a level 1 warning, a level 2 warning, and a level 3 warning, wherein the severity of anomalies in a level 1 warning is lower than that in a level 2 warning, and the severity of anomalies in a level 2 warning is lower than that in a level 3 warning.

[0160] In one example, prompt module 703 includes:

[0161] The first broadcasting unit 7034 is used to acquire abnormal location information and generate a prompt message containing the abnormal location information if the warning level is the first-level warning, and broadcast the prompt message.

[0162] In one example, prompt module 703 includes:

[0163] The second broadcasting unit 7035 is used to, if the warning level is the Level II warning, acquire abnormal location information, control the valves of the devices deployed in the target location to close, generate a prompt message containing the abnormal location information, and broadcast the prompt message.

[0164] In one example, prompt module 703 includes:

[0165] The third broadcasting unit 7036 is used to, if the warning level is the third-level warning, acquire abnormal location information, control the valves of the devices deployed in the target location to close, generate a prompt message containing abnormal location information, and broadcast the prompt message.

[0166] The second determining unit 7037 is used to acquire image data of the target location and determine the number of objects in the target location from the image data;

[0167] The display unit 7038 is used to generate a target path and display it based on the location information of the objects in the target location if the number of objects is equal to or greater than a preset number threshold; wherein the target path is used to indicate that the objects in the target location leave the target location.

[0168] The abnormal situation monitoring device based on digital twin provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0169] Figure 8 This is a schematic diagram of the structure of an anomaly monitoring device based on digital twins, provided in this application. Figure 8 As shown, the electronic device 800 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the device 800 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0170] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0171] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0172] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0173] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0174] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0175] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0176] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0177] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0178] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0179] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0180] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0181] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0182] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0183] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0184] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for monitoring abnormal situations based on digital twins, characterized in that, include: Obtain current location information of the target location and a digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location; Based on the current location information, the digital twin model is updated to obtain an updated digital twin model; Based on the updated digital twin model, the warning level of the target location is predicted, and a prompt message is generated and broadcast; wherein, the warning level characterizes the severity of the anomaly occurring at the target location.

2. The method according to claim 1, characterized in that, The step of obtaining the current location information of the target location includes: Based on a preset information acquisition device, the current location information of the target location is obtained; wherein, the information acquisition device includes at least one of a camera, a pressure detection sensor, a temperature detection sensor, a humidity detection sensor, a smoke detection sensor, and an ammonia detection sensor.

3. The method according to claim 1, characterized in that, Also includes: Obtain the construction information of the target site; wherein the construction information characterizes the size and layout of the target site; A digital twin model of the target location is generated based on the construction information of the target location and the preset initial location information.

4. The method according to claim 1, characterized in that, Based on the current location information, the digital twin model is updated to obtain an updated digital twin model, including: The current location information is compared with the preset initial location information in the digital twin model; If the current location information is inconsistent with the preset initial location information in the digital twin model, the preset initial location information is updated to the current location information to obtain the updated digital twin model.

5. The method according to claim 1, characterized in that, Based on the updated digital twin model, the warning level of the target location is predicted, including: Obtain the current location information from the updated digital twin model; Based on a preset range of abnormal information values, the current state of each current location information is determined; wherein, the preset range of abnormal information values ​​represents the range of abnormal values ​​for the current location information, and the current state is either a normal state or an abnormal state. Based on the current status of each location, the warning level of the target location is predicted.

6. The method according to claim 5, characterized in that, Based on the current status of each location, predict the warning level of the target location, including: Based on the current status of each current location information, predict the probability value of an anomaly in each current location information; Based on the probability value of anomalies in the current location information, the warning level of the target location is predicted.

7. The method according to claim 6, characterized in that, Based on the probability value of anomalies in the current location information, the warning level of the target location is predicted, including: The probability value of each current location information being abnormal is compared with the corresponding probability threshold to determine the target probability; wherein the target probability is greater than the corresponding probability threshold. Based on the number of target probabilities and a preset correlation, the warning level of the target location is determined; wherein, the preset correlation represents the relationship between the number of target probabilities and the warning level, and the warning level includes a level 1 warning, a level 2 warning, and a level 3 warning, wherein the severity of anomalies in a level 1 warning is lower than that in a level 2 warning, and the severity of anomalies in a level 2 warning is lower than that in a level 3 warning.

8. The method according to claim 7, characterized in that, Generate a prompt message and broadcast the prompt message, including: If the warning level is Level 1, then abnormal location information is obtained, and a prompt message containing the abnormal location information is generated and broadcast.

9. The method according to claim 8, characterized in that, Generate a prompt message and broadcast the prompt message, including: If the warning level is Level II, then abnormal location information is obtained, the valves of the devices deployed in the target location are controlled to close, and a prompt message containing the abnormal location information is generated and broadcast.

10. The method according to claim 9, characterized in that, Generate a prompt message and broadcast the prompt message, including: If the warning level is Level 3, then obtain the abnormal location information, control the valves of the devices deployed in the target location to close, generate a prompt message containing the abnormal location information, and broadcast the prompt message; Acquire image data of the target location, and determine the number of objects in the target location from the image data; If the number of objects is equal to or greater than a preset number threshold, a target path is generated and displayed based on the location information of the objects in the target location; wherein, the target path is used to indicate that the objects in the target location leave the target location.

11. An anomaly monitoring device based on digital twins, characterized in that, include: The acquisition module is used to acquire the current location information of the target location and the digital twin model of the target location; wherein, the current location information represents the current environmental information of the target location and the current working status of the devices deployed in the target location, and the digital twin model represents a three-dimensional visualized virtual target location; The update module is used to update the digital twin model based on the current location information to obtain the updated digital twin model. The alert module is used to predict the warning level of the target location based on the updated digital twin model, generate alert information, and broadcast the alert information; wherein, the warning level represents the severity of the anomaly occurring at the target location.

12. An anomaly monitoring device based on digital twins, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-10.

Images