A smart city restaurant store emergency supervision method and Internet of Things large model system

Abstract

The present invention provides a smart city catering store emergency supervision method and Internet of Things large model system, which relate to the field of emergency supervision. The method includes: based on the emergency supervision object platform, obtaining store gas data from the store monitoring device installed in the store; determining aging data based on the store gas data; the aging data includes the equipment aging degree of the gas-using equipment; based on the equipment aging degree, determining the equipment control parameters and self-test parameters; the equipment control parameters include the opening control value and the power control value, the opening amplitude of the pipeline valve is controlled based on the opening control value, and the operating power of the gas-using equipment is controlled based on the power control value; and the self-test equipment is controlled to start and stop based on the self-test parameters. The system includes an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform. The present invention can achieve supervision and prevention of store risks.

Description

Technical Field

[0001] This specification relates to the field of emergency supervision, and in particular to a smart city catering store emergency supervision method and an Internet of Things large model system. Background Art

[0002] Commercial users typically have high gas demands, often supplied via pipelines or bottled gas to meet their operational needs. However, due to their store layouts and busy operations, some commercial users fail to monitor the aging of their gas storage equipment, some gas appliances, and pipelines, and fail to implement adequate emergency preparedness measures. Frequent emergency inspections often consume a significant amount of commercial users' energy and yield ineffective results. Targeted emergency inspection and prevention strategies for different users and gas facilities are crucial.

[0003] Therefore, it is necessary to provide a smart city catering store emergency supervision method and an Internet of Things large model system to achieve emergency supervision for different users and different gas facilities. Summary of the Invention

[0004] In order to solve the problem of how to apply different emergency supervision solutions to different users and different gas facilities in catering stores in a targeted manner, the present invention provides an emergency supervision method for catering stores in a smart city and an Internet of Things large model system.

[0005] The invention content includes a large-scale IoT model system for emergency supervision of catering stores in a smart city, including an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; the emergency supervision management platform is configured to: based on the emergency supervision object platform, obtain store gas data from a store monitoring device installed in the store; based on the store gas data, determine aging data; the aging data includes the equipment aging degree of gas-using equipment; based on the equipment aging degree, determine equipment control parameters and self-test parameters, and send them to the gas control device and self-test equipment respectively; the equipment control parameters include opening control value and power control value, the opening amplitude of the pipeline valve is controlled based on the opening control value, and the operating power of the gas-using equipment is controlled based on the power control value; the start and stop of the self-test equipment is controlled based on the self-test parameters.

[0006] The invention content includes a smart city catering store emergency supervision method, which is executed by the emergency supervision management platform of the smart city catering store emergency supervision Internet of Things large model system; the method includes: based on the emergency supervision object platform, obtaining store gas data from the store monitoring device installed in the store; based on the store gas data, determining aging data; the aging data includes the equipment aging degree of gas-using equipment; based on the equipment aging degree, determining equipment control parameters and self-test parameters, and sending them to the gas control device and self-test equipment respectively; the equipment control parameters include opening control value and power control value, controlling the opening amplitude of the pipeline valve based on the opening control value, and controlling the operating power of the gas-using equipment based on the power control value; controlling the start and stop of the self-test equipment based on the self-test parameters.

[0007] The beneficial effects brought about by the above invention include but are not limited to: (1) The IoT model for emergency supervision of catering stores in smart cities can form an information operation closed loop between various functional platforms, and operate in a coordinated and regular manner under the unified management of the emergency supervision management platform. By efficiently and accurately monitoring the aging degree of different gas equipment and implementing the control of the operating power and self-inspection start and stop of the gas equipment, the processing efficiency of emergency supervision can be improved; (2) By obtaining the store gas data of commercial stores, the aging degree of the gas equipment used in the store can be effectively monitored, and the equipment can be regulated according to the aging degree, thereby extending the service life of the equipment, reducing the risk of accidents, and providing a good foundation for emergency prevention; (3) By determining the aging degree of the pipeline and further determining the equipment control parameters and self-inspection parameters based on the aging degree of the pipeline, the accuracy of the aging degree judgment of the gas-related devices in the store can be improved, thereby reasonably regulating the devices and better preventing risks; (4) By constructing an aging feature map, various relevant parameters of the equipment and pipelines can be reflected. Based on the aging feature map, the aging data is determined through the model, which can improve the accuracy of the aging data, which is conducive to the emergency supervision management platform to better prevent risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 This is a system structure diagram of the IoT large-scale model system for emergency supervision of catering stores in smart cities according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a method for emergency supervision of catering stores in a smart city according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart for determining device control parameters and self-test parameters according to some embodiments of this specification;

[0012] Figure 4 is an exemplary schematic diagram of an aging determination model according to some embodiments of this specification;

[0013] Figure 5 is an exemplary flow chart for determining device control parameters and self-test parameters according to other embodiments of this specification;

[0014] Figure 6 is an exemplary schematic diagram of a risk estimation model according to some embodiments of this specification. DETAILED DESCRIPTION

[0015] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0016] Figure 1 It is a system structure diagram of the smart city catering store emergency supervision Internet of Things large model system shown in some embodiments of this specification.

[0017] In some embodiments, the smart city catering store emergency supervision IoT model system 100 may include an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140 and an emergency supervision object platform 150.

[0018] The emergency supervision user platform 110 is a platform for users to obtain emergency supervision information and issue emergency supervision requirements and instructions, including a government user sub-platform and a citizen user sub-platform. In some embodiments, the government user sub-platform is an operation connection platform for the superior government emergency supervision department. The superior government emergency supervision department can issue emergency supervision requirements and instructions through the government user sub-platform, and obtain information such as emergency supervision events, status, progress, etc. In some embodiments, the citizen user sub-platform supports citizen users to view emergency information (such as guidance routes, congestion conditions in various areas, etc.) in real time, and allows citizen users to transmit emergency events (such as crowding hazards, safety incidents such as stampedes, gas leaks, etc.). In some embodiments, the emergency supervision user platform 110 can be connected to the emergency supervision service platform 120 through a communication module to transmit user requests. In some embodiments, the emergency supervision user platform 110 may include third-party terminals, such as smart phones, tablet computers, PCs, smart watches, etc.

[0019] The emergency supervision service platform 120 is an intermediate layer between the user and the emergency supervision management platform 130, and is used to process user instructions and forward them to the emergency supervision management platform 130, or send messages from the emergency supervision management platform 130 to the user. In some embodiments, the emergency supervision service platform 120 may include a server, a gateway, and a router.

[0020] The emergency supervision management platform 130 is the control center of the smart city restaurant store emergency supervision IoT large model system 100 and is configured to execute the smart city restaurant store emergency supervision method. Figure 2-Figure 6 Related description.

[0021] In some embodiments, the emergency supervision and management platform 130 may include hardware with computing capabilities, such as a processor, a server, or a server cluster. In some embodiments, the emergency supervision and management platform 130 may also include a data center for storing data. In some embodiments, the emergency supervision and management platform 130 may include multiple emergency sub-platforms, such as a social security incident prevention and monitoring platform. In some embodiments, the data center may be equipped with a memory for storing pipeline maintenance data, pipeline distribution data, and other data; multiple emergency sub-platforms may be communicatively connected to multiple sensor sub-platforms.

[0022] The emergency supervision sensor network platform 140 serves as an intermediate layer between the emergency supervision management platform 130 and the emergency supervision object platform 150, enabling communication between the two. In some embodiments, the emergency supervision sensor network platform 140 may include a communication transmission network and routing devices. In some embodiments, the emergency supervision sensor network platform 140 may include multiple sensor sub-platforms. For example, a sensor sub-platform may be responsible for collecting data for a region and uploading it to the corresponding emergency sub-platform.

[0023] The emergency supervision object platform 150 is a platform for monitoring. In some embodiments, the emergency supervision object platform 150 can be configured with monitoring devices, various sensors, storage devices, and evacuation devices.

[0024] In some embodiments of this specification, the IoT large model for emergency supervision of catering stores in smart cities can form an information operation closed loop between various functional platforms, and operate in a coordinated and regular manner under the unified management of the emergency supervision management platform. By efficiently and accurately monitoring the aging degree of different gas equipment and implementing control of the operating power and self-inspection start and stop of gas equipment, the efficiency of emergency supervision can be improved.

[0025] Figure 2 This is an exemplary flow chart of the emergency supervision method for smart city catering stores according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 may be executed by the emergency supervision management platform 130 .

[0026] Step S210: Based on the emergency supervision object platform, store gas data is obtained from the store monitoring device installed in the store.

[0027] Store gas data refers to data related to gas usage in commercial user stores. In some embodiments, store gas data may include user usage data and device usage data.

[0028] User usage data and device usage data refer to data related to gas usage by users and devices in commercial stores, respectively. For example, user usage data may include the number of gas users, while device usage data may include the number of times gas devices are started and closed, the power consumption of each use, and the duration of gas use.

[0029] In some embodiments, the store monitoring device can obtain store gas data and upload it to the emergency supervision object platform 150; the emergency supervision object platform 150 can upload the store gas data to the emergency supervision management platform 130 for storage via the emergency supervision sensor network platform 140.

[0030] Store monitoring devices are devices that monitor gas usage in commercial stores. These devices can communicate with the emergency supervision platform 150. In some embodiments, these devices may include infrared devices (such as thermal imaging cameras), high-definition cameras, electrical sensors, and the like. The infrared devices and / or high-definition cameras may be equipped with image recognition capabilities.

[0031] In some embodiments, the store monitoring device may be installed at a preset location within a commercial store, and the preset location may be set by a person skilled in the art based on experience.

[0032] Step S220: Determine aging data based on the store gas data.

[0033] The aging data refers to data related to the aging degree of the gas-using equipment. In some embodiments, the aging data includes the aging degree of the gas-using equipment.

[0034] In some embodiments, the emergency management platform 130 can determine the degree of equipment aging through various methods. For example, based on store gas data, the emergency management platform 130 can determine the cumulative number of gas users, gas usage frequency (i.e., cumulative number of starts and stops), cumulative gas usage duration, and average gas power consumption of gas equipment, and then normalize these data to calculate an aging score, which is used as the degree of equipment aging. The normalization method can include Min-Max normalization, Z-score normalization, and other methods.

[0035] As an example only, the aging score can be calculated using the following formula (1).

[0036] (1)

[0037] Where S is the aging score; P is the normalized value of the cumulative number of gas users; F is the normalized value of the gas usage frequency of the gas-using equipment; T is the normalized value of the cumulative gas usage time of the gas-using equipment; W is the normalized value of the average gas power of the gas-using equipment; 、 、 and They are respectively the gas user coefficient, gas usage frequency coefficient, gas usage duration coefficient and gas usage power coefficient, which can be set by those skilled in the art based on experience.

[0038] For more information on determining aging data, see the relevant description below.

[0039] In step S230, based on the degree of equipment aging, the equipment control parameters and self-test parameters are determined and sent to the gas control device and the self-test equipment respectively; the equipment control parameters include the opening control value and the power control value, the opening amplitude of the pipeline valve is controlled based on the opening control value, and the operating power of the gas-using equipment is controlled based on the power control value; the start and stop of the self-test equipment is controlled based on the self-test parameters.

[0040] Equipment control parameters refer to parameters related to regulating the operation of gas-using equipment. In some embodiments, the equipment control parameters include the gas-using equipment to be regulated and its corresponding control parameters (such as start-stop, power adjustment, etc.).

[0041] Self-test parameters refer to parameters related to device self-testing. In some embodiments, these parameters include the self-test equipment to be activated and its corresponding control parameters. Self-test equipment is used to test gas-using equipment and may include pipeline pressure monitoring devices, vibration sensors, noise analyzers, and more.

[0042] In some embodiments, the emergency supervision management platform 130 may determine the equipment control parameters and self-test parameters in a variety of ways.

[0043] For example, in response to the aging score of a gas-using device being greater than a preset aging threshold, the emergency supervision and management platform 130 may determine the corresponding gas-using device as an aging device, and set the aging device as the gas-using device that needs to be regulated in the device control parameters. The aging threshold can be set to multiple levels, each level corresponding to a different control parameter. For example, when the aging score is greater than the first aging threshold, the control parameter is to reduce the power, and the adjustment range can be positively correlated with the aging score; when the aging score is greater than the second aging threshold, the control parameter is to shut down the device. For another example, the emergency supervision and management platform 130 may determine the associated pipeline of the aging device as a pipeline to be inspected. Similar to the previous example, in response to the aging score being greater than the preset score threshold, the valve of the pipeline to be inspected is reduced or closed, and the adjustment range is positively correlated with the aging score.

[0044] For more information about associated pipelines, see Figure 3 The relevant description in step S320 in .

[0045] For more information on determining device control parameters and self-test parameters, see the relevant descriptions below.

[0046] The opening control value is used to control the degree of opening of pipeline valves. The power control value is used to adjust the power of equipment. In some embodiments, the emergency supervision and management platform 130 can control the opening amplitude of the valves in the pipeline to be inspected based on the opening control value, and control the operating power of gas-using equipment based on the power control value. In some embodiments, the emergency supervision and management platform 130 controls the start and stop of self-inspection equipment based on self-inspection parameters. The emergency supervision and management platform 130 can identify the self-inspection equipment corresponding to the aging equipment and the pipeline to be inspected as the self-inspection equipment that needs to be activated according to the self-inspection parameters.

[0047] In some embodiments, the emergency supervision and management platform 130 effectively monitors the aging degree of gas equipment used in commercial stores by obtaining store gas data of commercial stores, and can adjust the equipment according to the aging degree, thereby extending the service life of the equipment, reducing the risk of accidents, and providing a good foundation for emergency prevention.

[0048] In some embodiments, the emergency supervision management platform 130 may generate leakage alarm parameters based on the aging data, and send the leakage alarm parameters to the leakage alarm device of the store.

[0049] The leakage alarm parameter is used to control the leakage alarm device. In some embodiments, the leakage alarm parameter controls the leakage alarm device to be triggered based on a leakage alarm threshold. For example, the leakage alarm device is configured to issue an alarm in response to the monitored gas concentration being greater than the leakage alarm threshold.

[0050] In some embodiments, the emergency management platform 130 can lower the leak alarm threshold in response to the presence of aged equipment within the radiation range of the leak alarm device. This radiation range can be preset by technical personnel based on experience. The base value and reduction range of the leak alarm threshold can also be preset by those skilled in the art based on experience, and the reduction range of the leak alarm threshold is positively correlated with the number of aged equipment within the radiation range of the leak alarm device.

[0051] Over the long term, gas-using equipment may experience increased leakage risk due to factors such as seal wear, pipeline corrosion, and sensor aging. Fixed-threshold alarm mechanisms can result in missed or false alarms. Therefore, dynamically adjusting the leak alarm threshold based on equipment aging can improve the accuracy and safety of gas leak monitoring.

[0052] Figure 3 This is an exemplary flow chart for determining device control parameters and self-test parameters according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 may be executed by the emergency supervision management platform 130 .

[0053] Step S310: Based on the emergency supervision object platform, pipeline monitoring data is obtained from the pipeline monitoring device of the gas pipeline.

[0054] Pipeline monitoring data refers to data related to the operating status and environment of a gas pipeline. In some embodiments, pipeline monitoring data includes external and internal pressures of the pipeline, as well as buried environmental data. Buried environmental data includes, for example, pH, humidity, and temperature of the environment surrounding the buried gas pipeline.

[0055] In some embodiments, the pipeline monitoring device can obtain pipeline monitoring data in real time or at regular intervals.

[0056] A pipeline monitoring device is a device that monitors the internal and external environment of a gas pipeline. For example, a pipeline monitoring device may include a pressure sensor, a corrosion-resistant pH electrode, a temperature sensor, and a humidity sensor.

[0057] Step S320: Determine the degree of pipeline aging based on pipeline monitoring data, store gas data, and operation efficiency data.

[0058] For more information about store gas data, please refer to the relevant description in step S210.

[0059] Operational efficiency data refers to data related to the operating efficiency of gas-using equipment. In some embodiments, this operational efficiency data includes historical temperature data or temperature change data during the operation of the gas-using equipment, as well as historical gas usage (e.g., gas usage over a past week). The emergency monitoring and management platform 130 can access this operational efficiency data from the data center.

[0060] In some embodiments, the aging data also includes the aging degree of the store's pipeline system. The store's pipeline system refers to the store's corresponding gas pipeline system, including through-wall pipelines, buried pipelines, etc. The pipeline aging degree is used to assess the aging degree of the gas pipeline.

[0061] In some embodiments, the emergency supervision management platform 130 may determine the pipeline aging rate based on pipeline monitoring data, store gas data, and operation efficiency data; and determine the degree of pipeline aging based on the pipeline aging rate.

[0062] The pipeline aging rate is used to evaluate the aging rate of the gas pipeline. In some embodiments, the emergency supervision management platform 130 can construct an aging feature vector by taking the mean of the pipeline monitoring data at multiple time points, the mean of the equipment usage data of the gas-using equipment connected to the gas pipeline at multiple time points, and the mean of the operating efficiency data of the gas-using equipment at multiple time points; query the first vector database based on the aging feature vector, and use the reference aging feature vector that meets the preset requirements and corresponds to the reference pipeline aging rate as the pipeline aging rate. For more information about equipment usage data, see Figure 2 In the relevant description of step S210, the preset requirement may include one of the following: the vector similarity between the aging feature vector and the reference aging feature vector is greater than a similarity threshold, the vector distance is less than a distance threshold, etc. The similarity threshold and the distance threshold can be set by those skilled in the art based on experience.

[0063] Among them, the first vector database may include one of Milvus, Faiss, etc. The first vector database contains multiple reference feature vectors and their corresponding reference pipeline aging rates. The first vector database can be pre-constructed based on experimental data or historical data, and the construction steps include: constructing a reference aging feature vector based on the mean of the actual pipeline monitoring data at the reference time point in the experimental data or historical data, the mean of the actual equipment usage data of the gas-using equipment connected to the gas pipeline at the reference time point, and the mean of the actual operating efficiency data of the gas-using equipment at the reference time point; and recording the reference aging rate in the subsequent preset time period; obtaining multiple reference feature vectors and their corresponding reference pipeline aging rates in the above manner, and placing them into the first vector database.

[0064] In some embodiments, the reference aging rate is the rate of change of the pipeline aging degree per unit time.

[0065] In some embodiments, the emergency supervision and management platform 130 can determine the degree of pipeline aging based on the pipeline aging rate and the pipeline usage time. As an example, the degree of pipeline aging can be the product of the pipeline aging rate and the pipeline usage time. The pipeline usage time can be determined from the time the gas pipeline was actually put into use to the current time. The time the gas pipeline was actually put into use can be determined based on filed construction records.

[0066] In some embodiments, the emergency supervision management platform 130 may also determine the aging degree of the gas-using equipment based on the aging degree of pipelines associated with the gas-using equipment.

[0067] In some embodiments, the emergency supervision and management platform 130 may identify gas pipelines whose path distance from gas-consuming equipment is less than a preset threshold as associated pipelines. The preset threshold is positively correlated with the aging impact data of the gas-consuming equipment. For more information on aging impact data, see the relevant description below.

[0068] Path distance is used to quantify the topological connection hierarchical relationship between gas-consuming equipment and gas pipeline nodes. For example, the path distance of the gas pipeline directly connected to the gas-consuming equipment is 0, and the path distance between the upstream gas pipeline and the gas-consuming equipment is 1.

[0069] In some embodiments, the emergency supervision management platform 130 may appropriately increase the weight of the gas usage duration coefficient in formula (1) based on the degree of pipeline aging. The magnitude of the increase may be preset.

[0070] Since pipeline aging may cause more impurities to enter the gas, thereby affecting the aging of gas-using equipment, considering the aging degree of the pipeline when determining the aging degree of the equipment can improve the accuracy of the aging degree assessment.

[0071] Step S330: Determine equipment control parameters and self-test parameters based on the pipeline aging degree and the equipment aging degree.

[0072] In some embodiments, in response to the pipeline aging degree of the gas pipeline being greater than the pipeline aging threshold, the emergency supervision management platform 130 may determine the equipment control parameters and self-test parameters in a manner similar to step S230 .

[0073] By determining the degree of pipeline aging and further determining equipment control parameters and self-test parameters based on the degree of pipeline aging, the accuracy of judging the aging degree of gas-related devices in stores can be improved, thereby rationally regulating the devices and better preventing risks.

[0074] In some embodiments, the emergency supervision management platform 130 can also determine aging impact data based on store gas data and gas storage location data; determine a judgment threshold based on the aging impact data; and determine equipment control parameters and self-test parameters based on the judgment threshold and aging data.

[0075] Gas storage location data refers to data related to the location of gas storage. For example, gas storage location data includes gas storage locations (e.g., the location of a gas storage room or gas storage warehouse). In some embodiments, the emergency management platform 130 can determine the gas storage location data from construction drawings of the gas system.

[0076] Aging impact data is used to characterize the impact of gas-using equipment and / or gas pipelines on leakage due to aging. In some embodiments, the aging impact data may include equipment impact data and pipeline impact data, which are used to characterize the impact of gas-using equipment and gas pipelines on leakage due to aging, respectively.

[0077] In some embodiments, the device impact data is positively correlated with the number of people within a first range of the gas-using device and negatively correlated with the distance between the gas-using device and a gas storage location that meets pre-set rules. The emergency supervision management platform 130 can query a first pre-set table to determine the device impact data based on the location of the gas-using device.

[0078] The number of users can be obtained through statistics, and the preset rule may include that the distance between the gas-using device and the gas storage location is less than a threshold. The distance threshold, the first range, and the first preset table can be preset based on experience. The first preset table includes the number of people within the first range of multiple reference gas-using devices, the distances between the reference gas-using devices and reference gas storage locations that meet the preset rule, and the corresponding device impact data.

[0079] In some embodiments, the pipeline impact data is positively correlated with the number of gas users within the second range of the gas pipeline, negatively correlated with the distance between the gas pipeline and a gas storage location that meets preset rules, and positively correlated with the frequency of use of gas-using equipment connected to the gas pipeline. The emergency supervision management platform 130 can determine the pipeline impact data based on the location of the gas pipeline by querying the second preset table.

[0080] The number of users can be obtained through statistics, and the second range and the second preset table can be pre-set based on experience. The second preset table includes the number of people within the second range of multiple reference gas pipelines, the distance between the reference gas pipelines and a reference gas storage location that meets preset rules, the usage frequency of gas-using equipment connected to the reference gas pipelines, and corresponding pipeline impact data.

[0081] The judgment threshold includes an aging threshold and a pipeline aging threshold. In some embodiments, the aging impact data is negatively correlated with the judgment threshold. For example, the larger the aging impact data, the smaller the judgment threshold.

[0082] In some embodiments, in response to the aging data being greater than the judgment threshold adjusted based on the aging impact data, the emergency supervision management platform 130 may determine the equipment control parameters and self-test parameters in a manner similar to step S230 .

[0083] Gas equipment and pipelines age over time, potentially reducing their sealing and structural integrity, increasing the risk of gas leaks. When these aging gas equipment and pipelines are located in densely populated areas or near gas storage, a leak could cause a serious safety incident, resulting in widespread personal injury and property damage. Therefore, incorporating aging impact data to strengthen monitoring and maintenance can mitigate potential risks. Furthermore, by dynamically adjusting judgment thresholds based on aging impact data, the degree of aging can be more accurately assessed.

[0084] In some embodiments, the emergency supervision management platform 130 can also obtain pipeline distribution data from the data center; construct an aging feature map based on the pipeline distribution data, pipeline monitoring data, store gas data and pipeline characteristic data; and determine aging data based on the aging feature map. For more information about the data center, see Figure 1 Related description in .

[0085] Pipeline distribution data is used to characterize the spatial distribution of gas pipelines. For example, pipeline distribution data may include the locations of multiple gas pipelines, connection nodes between gas pipelines, and so on.

[0086] The pipeline characteristic data is used to characterize the structural characteristics of the gas pipeline. For example, the pipeline characteristic data may include the material, length, diameter, thickness, etc. of the gas pipeline. The emergency supervision management platform 130 can read the pipeline distribution data and pipeline characteristic data from the data center.

[0087] The aging characteristic map is used to characterize the spatial distribution and aging characteristics of the gas pipeline. In some embodiments, the aging characteristic map may include nodes and edges, and the nodes include connection nodes and device nodes.

[0088] The connection node is used to characterize the connection between gas pipelines. In some embodiments, the connection node may include connection node features. For example, the connection node features may include the type of connector at one or more time points.

[0089] Device nodes are used to represent gas-using equipment. In some embodiments, device nodes may include device node characteristics. For example, device node characteristics may include device usage data at one or more time points, device characteristic data (such as device type and device installation time), and operational efficiency data. The emergency supervision and management platform 130 can read device characteristic data from the data center. For more information on device usage data, see the relevant description in step S210; for more information on operational efficiency data, see the relevant description in step S320.

[0090] The above connection node characteristics and device node characteristics constitute node characteristics.

[0091] Edges are used to represent gas pipelines. In some embodiments, edges may include edge features. For example, edge features may include pipeline monitoring data or pipeline feature data at one or more time points. For more information about pipeline monitoring data, see the description of step S310.

[0092] In some embodiments, the node features of a node and the edge features correspond to different time features. The time feature refers to the time point or time period corresponding to the node features and the edge features.

[0093] In some embodiments, the time characteristics of the node features and edge features are respectively positively correlated with the aging degree and aging impact data of their corresponding gas-using equipment and pipelines.

[0094] By associating the temporal characteristics of node and edge features with the aging degree and aging impact data of equipment and pipelines, we can more accurately reflect the changes in the status of equipment and pipelines over different time periods. As the aging degree and aging impact data of equipment or pipelines change, the temporal characteristics can be dynamically adjusted. For example, for equipment or pipelines with a high degree of aging, they may include more corresponding historical data. This historical data of these high-risk objects can be more fully utilized, helping the emergency supervision and management platform to detect potential problems earlier.

[0095] In some embodiments, the emergency supervision management platform 130 may determine aging data based on the aging characteristic map and an aging determination model.

[0096] In some embodiments, the aging determination model may be a machine learning model, such as a graph neural network (GNN) model, or a combination of one or more other custom models.

[0097] Figure 4 is an exemplary schematic diagram of an aging determination model according to some embodiments of this specification.

[0098] In some embodiments, as Figure 4 As shown, the input of the aging determination model 460 may include an aging characteristic map 450, and the output may include aging data 470. The aging characteristic map 450 may be constructed based on the pipeline distribution data 410, the pipeline monitoring data 420, the store gas data 430, and the pipeline characteristic data 440.

[0099] In some embodiments, the aging determination model can be trained using a plurality of first training samples with first labels. The first training samples include a sample aging feature map constructed based on sample pipeline distribution data, sample pipeline monitoring data, sample store gas data, sample equipment efficiency data, sample equipment feature data, and sample pipeline feature data. The first labels are aging data obtained through actual testing of the samples.

[0100] In some embodiments, the training of the aging determination model can be performed by the emergency supervision management platform 130 or an external server. For example, the emergency supervision management platform 130 performs multiple rounds of iterations, and at least one round of iteration includes: selecting one or more first training samples, inputting one or more first training samples into the initial aging determination model, and obtaining the model prediction output corresponding to the one or more first training samples; according to the model prediction output corresponding to the one or more first training samples, and the first label of the one or more first training samples, substitute into the formula of the predefined loss function to calculate the value of the loss function; according to the value of the loss function, reversely update the model parameters in the initial aging determination model; this step can be performed using various methods. For example, it can be updated based on the gradient descent method. When the iteration end condition is met, the iteration ends and the trained aging determination model is obtained.

[0101] By constructing an aging characteristic map, various relevant parameters of equipment and pipelines can be reflected. Determining aging data through a model based on the aging characteristic map can improve the accuracy of aging data determination, which is conducive to the emergency supervision and management platform to better prevent risks.

[0102] In some embodiments, the emergency supervision management platform 130 may determine pressure alarm parameters based on aging data, pipeline characteristic data, and pipeline monitoring data, and send the pressure alarm parameters to the store's pressure alarm device.

[0103] The pressure alarm parameter is used to control the pressure alarm device to be triggered based on the safety pressure threshold. The pressure alarm device is configured to issue an alarm in response to the pressure of the pipeline of the store pipeline system being greater than the safety pressure threshold.

[0104] In some embodiments, the emergency supervision management platform 130 may determine the safety pressure threshold in a variety of ways.

[0105] For example, based on the age and thickness of the gas pipeline, a corresponding safety pressure threshold is determined by querying a third preset table. This third preset table can be constructed based on historical data or through experiments. The third preset table contains the age and thickness of multiple reference gas pipelines, as well as the corresponding reference safety pressure thresholds. The higher the age and the smaller the thickness of the reference gas pipeline, the lower the reference safety pressure threshold.

[0106] For another example, a pressure feature vector is constructed based on the pipeline aging degree and pipeline characteristic data; based on the pressure feature vector, a second vector database is queried to determine a safe pressure threshold.

[0107] The second vector database includes a plurality of reference pressure feature vectors and their corresponding reference safety thresholds. The construction method of the second vector database is similar to that of the first vector database, which can be referred to above.

[0108] In some embodiments, the emergency supervision and management platform 130 may also use a pressure sensor to measure the pressure fluctuation amplitude of the gas pipeline over a preset period of time and adaptively adjust the safety pressure threshold based on the pressure fluctuation amplitude. For example, if the pressure fluctuation amplitude is large, the safety pressure threshold may be adjusted downward. The adjustment amplitude of the safety pressure threshold can be preset by those skilled in the art based on experience. For more information on pressure sensors, internal pressure, and external pressure, please refer to the relevant description of step S310.

[0109] Over the long term, gas pipelines may experience a decrease in their pressure resistance due to factors such as seal wear, pipeline corrosion, and fatigue damage. Fixed threshold alarm mechanisms can result in missed or false alarms. Therefore, dynamically adjusting the safety pressure threshold based on pipeline aging can improve the accuracy and safety of gas leak detection.

[0110] Figure 5 This is an exemplary flow chart for determining device control parameters and self-test parameters according to other embodiments of this specification. In some embodiments, process 500 may be executed by the emergency supervision management platform 130.

[0111] Step S510: Acquire multiple candidate device control parameters.

[0112] Candidate device control parameters refer to the device control parameters that are candidates for use. For details about device control parameters, see Figure 2 In some embodiments, the emergency supervision object platform 150 may randomly select to shut down or reduce the gas pipeline and / or gas-using equipment to generate candidate equipment control parameters and upload them to the emergency supervision management platform 130.

[0113] Step S520: estimating future store gas data based on current and historical store gas data.

[0114] Future store gas data can represent the store gas data that commercial stores are expected to reach in the future. For more information about store gas data, see Figure 2 In some embodiments, the emergency management platform 130 may use the current and historical store gas data as future store gas data at the same time point in the next month (or next few months).

[0115] Step S530 : determining an estimated damage risk corresponding to each of the plurality of candidate equipment control parameters based on the plurality of candidate equipment control parameters, future store gas data, and aging data.

[0116] The estimated damage risk represents the probability of damage to each gas pipeline and each gas-using device at a specific point in the future. The estimated damage risk can be expressed as a value between 0 and 1.

[0117] In some embodiments, the emergency supervision management platform 130 can determine the estimated damage risk at multiple future time points through a risk prediction model based on candidate equipment control parameters, future store gas data, aging data, operating efficiency data, pipeline characteristic data and equipment characteristic data.

[0118] Figure 6 is an exemplary schematic diagram of a risk estimation model according to some embodiments of this specification.

[0119] In some embodiments, the risk prediction model may be a machine learning model, such as a recurrent neural network (RNN) or a combination of one or more other custom models.

[0120] In some embodiments, as Figure 6 As shown, the input of the risk prediction model 660 may include candidate equipment control parameters 610, future store gas data 620, aging data 630, operating efficiency data 640, pipeline characteristic data 440 and equipment characteristic data 650, and the output of the risk prediction model 660 may include estimated damage risk 670.

[0121] In some embodiments, the risk prediction model can be obtained by training multiple second training samples with second labels. The second training samples may include sample candidate equipment control parameters, sample future store gas data, sample aging data, sample operating efficiency data, sample pipeline feature data, and sample equipment feature data collected at the first historical time point. The second label may include the actual estimated damage risk collected at the second historical time point. The second historical time point is after the first historical time point. The second label can be obtained by manual annotation. For example, if the gas pipeline and / or gas-using equipment at the second historical time point is damaged, the label is recorded as 1, otherwise it is 0.

[0122] The training of the risk estimation model is the same as that of the aging determination model, which can be seen in the previous article.

[0123] The damage risk is estimated through the risk prediction model, which improves the accuracy of the damage risk estimation. At the same time, the data processing efficiency is high and the degree of intelligence is high.

[0124] Step S540 : determining a device control parameter and a self-test parameter based on the estimated damage risk corresponding to each of the plurality of candidate device control parameters.

[0125] In some embodiments, the emergency supervision management platform 130 can determine a comprehensive risk score based on the estimated damage risk of candidate equipment control parameters at multiple future time points; determine equipment control parameters based on the comprehensive risk score; and determine self-test parameters based on the equipment control parameters.

[0126] The comprehensive risk score is used to evaluate the comprehensive damage probability of gas pipelines / gas-using equipment at multiple future time points based on a candidate equipment control parameter. As an example only, the comprehensive risk score of the candidate equipment control parameter can be calculated using the following formula (2):

[0127] (2)

[0128] Where, A comprehensive risk score for the candidate device's control parameters; is the time point risk at the jth future time point The risk factor of > >… > ; is the time point risk at the jth future time point; m is the total number of future time points; 1≤j≤m, and the smaller the value of j is, the closer the future time point is to the current time point.

[0129] Among them, the time point risk refers to the sum of the correction values ​​of the estimated damage risks corresponding to multiple gas pipelines and gas-using equipment at a certain future time point. In some embodiments, the emergency supervision and management platform 130 can perform risk classification and correction on the estimated damage risks of multiple gas pipelines and gas-using equipment of a candidate equipment control parameter at a certain future time point. For example, the emergency supervision and management platform 130 can classify multiple estimated damage risks into low risk, medium risk and high risk. Among them, low risk includes an estimated damage risk greater than 0 and less than or equal to the first threshold, and its corresponding correction value is 0; medium risk includes an estimated damage risk greater than the first threshold and less than or equal to the second threshold, and its corresponding correction value is a preset value between the first threshold and the second threshold; high risk includes an estimated damage risk greater than the second threshold and less than or equal to 1, and its corresponding correction value is the estimated damage risk. The first threshold and the second threshold can be set by those skilled in the art based on experience, and the first threshold is less than the second threshold.

[0130] Using formula (2), the emergency supervision and management platform 130 calculates the risk comprehensive scores corresponding to multiple candidate equipment control parameters, and uses the candidate equipment control parameter corresponding to the minimum risk comprehensive score as the equipment control parameter, and uses the self-test devices in the gas pipeline and associated pipelines of the gas-using equipment involved in the equipment control parameter as the self-test parameters. For example, if the equipment control parameter is {Close gas pipeline 1 and gas-using equipment 3}, then the corresponding self-test parameter is {Open gas pipeline 1 and the self-test devices in the associated pipelines of gas-using equipment 3}.

[0131] By estimating future store gas data and damage risks, determining equipment control parameters and self-test parameters, and taking possible future situations into consideration, the accuracy of determining equipment control parameters and self-test parameters is improved, and the effectiveness of risk prevention is enhanced.

[0132] In some embodiments, the emergency supervision management platform 130 can also determine a compensation coefficient based on the aging impact data corresponding to each of multiple candidate equipment control parameters; determine the time point risk based on the compensation coefficient and the estimated damage risk; determine the comprehensive risk score based on the time point risk; and determine the equipment control parameters and self-test parameters based on the comprehensive risk score.

[0133] In some embodiments, the emergency management platform 130 may calculate a weighted sum of the revised values ​​of the estimated damage risks corresponding to multiple gas pipelines and gas-consuming equipment at the future time point, and use the weighted sum as the risk at that point in time. The weights corresponding to the revised values ​​of the estimated damage risks serve as compensation coefficients for the gas pipelines and gas-consuming equipment.

[0134] In some embodiments, the emergency supervision management platform 130 may use the pipeline impact data and the equipment impact data as compensation coefficients for the corresponding gas pipelines and gas-using equipment.

[0135] For instructions on determining the comprehensive risk score and determining the control parameters and self-check parameters, please refer to the relevant description in step S540.

[0136] In step S540, the point-in-time risk is the sum of the corrected values ​​for the estimated damage risk of each gas pipeline and each gas-consuming device. This means that each gas pipeline and each gas-consuming device is assumed to have the same impact on the overall risk. However, different gas pipelines and gas-consuming devices may age at different levels. Severely aged gas pipelines and gas-consuming devices have a higher probability of leakage and more serious accident consequences, and their impact on the overall risk is far greater than that of other gas pipelines and gas-consuming devices. Therefore, by introducing a compensation factor to determine the impact of the ageing of gas pipelines and gas-consuming devices on the point-in-time risk, a more accurate assessment of the point-in-time risk can be achieved.

[0137] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

Claims

1. A large-scale IoT model system for emergency supervision of restaurant stores in smart cities, characterized by: It includes an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; the emergency supervision management platform is configured to: Based on the emergency supervision object platform, store gas data is obtained from store monitoring devices installed in the store; Obtain pipeline distribution data from the government regulatory comprehensive database; Based on the emergency supervision object platform, pipeline monitoring data is obtained from a pipeline monitoring device of the gas pipeline; Constructing an aging characteristic map based on the pipeline distribution data, the pipeline monitoring data, the store gas data, and the pipeline characteristic data; determining aging data based on the aging characteristic map; the aging data including the aging degree of the gas-using equipment and the aging degree of the pipelines in the store pipeline system; Determining the degree of aging of the pipeline based on the pipeline monitoring data, the store gas data, and the operating efficiency data; Based on the aging degree of the pipeline and the aging degree of the equipment, the equipment control parameters and self-test parameters are determined and sent to the gas control device and the self-test equipment respectively; the equipment control parameters include an opening control value and a power control value, the opening amplitude of the pipeline valve is controlled based on the opening control value, and the operating power of the gas-using equipment is controlled based on the power control value; the start and stop of the self-test equipment is controlled based on the self-test parameters.

2. The system according to claim 1, wherein The emergency supervision management platform is further configured to: Based on the aging data, leakage alarm parameters are generated and sent to the leakage alarm device of the store; the leakage alarm parameters control the leakage alarm device to be triggered based on a leakage alarm threshold, and the leakage alarm device is configured to issue an alarm in response to the monitored gas concentration being greater than the leakage alarm threshold.

3. The system according to claim 1, wherein: The emergency supervision management platform is further configured to: Obtain control parameters of multiple candidate devices; Based on the current and historical store gas data, estimate future store gas data; Determining an estimated damage risk corresponding to each of the plurality of candidate device control parameters based on the plurality of candidate device control parameters, the future store gas data, and the aging data; The device control parameter and the self-test parameter are determined based on the estimated damage risk corresponding to each of the plurality of candidate device control parameters.

4. A smart city restaurant store emergency supervision method, characterized in that: The method is executed by the emergency supervision management platform of the smart city catering store emergency supervision Internet of Things large model system; the method includes: Based on the emergency supervision object platform, store gas data is obtained from the store monitoring devices installed in the store; Obtain pipeline distribution data from the government regulatory comprehensive database; Based on the emergency supervision object platform, pipeline monitoring data is obtained from a pipeline monitoring device of the gas pipeline; Constructing an aging characteristic map based on the pipeline distribution data, the pipeline monitoring data, the store gas data, and the pipeline characteristic data; determining aging data based on the aging characteristic map; the aging data including the aging degree of the gas-using equipment and the aging degree of the pipelines in the store pipeline system; Determining the degree of aging of the pipeline based on the pipeline monitoring data, the store gas data, and the operating efficiency data; Based on the aging degree of the pipeline and the aging degree of the equipment, the equipment control parameters and self-test parameters are determined and sent to the gas control device and the self-test equipment respectively; the equipment control parameters include an opening control value and a power control value, the opening amplitude of the pipeline valve is controlled based on the opening control value, and the operating power of the gas-using equipment is controlled based on the power control value; the start and stop of the self-test equipment is controlled based on the self-test parameters.

5. The method according to claim 4, wherein The method further comprises: Based on the aging data, leakage alarm parameters are generated and sent to the leakage alarm device of the store; the leakage alarm parameters control the leakage alarm device to be triggered based on a leakage alarm threshold, and the leakage alarm device is configured to issue an alarm in response to the monitored gas concentration being greater than the leakage alarm threshold.

6. The method according to claim 4, wherein The method further comprises: Obtain control parameters of multiple candidate devices; Based on the current and historical store gas data, estimate future store gas data; Determining an estimated damage risk corresponding to each of the plurality of candidate device control parameters based on the plurality of candidate device control parameters, the future store gas data, and the aging data; The device control parameter and the self-test parameter are determined based on the estimated damage risk corresponding to each of the plurality of candidate device control parameters.

Images