Smart gas gate station gas monitoring method and Internet of Things system based on safety supervision

Abstract

The present invention relates to the field of gas supervision, and provides a smart gas gate station gas monitoring method and an Internet of Things system based on safety supervision. The method is executed by a smart gas government safety supervision management platform of a smart gas gate station gas monitoring system based on safety supervision, and the method includes: determining the uniformity of the gas based on gas monitoring data; determining the gas component data in response to the uniformity satisfying a first preset condition; determining the component influence coefficient based on the uniformity and environmental data; determining the confidence weight corresponding to the feedback information based on feedback information; determining the monitoring accuracy based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data, and the component influence coefficient. The present invention can evaluate the accuracy of the monitoring data when monitoring the gas components, and timely and targetedly adjust or overhaul the gas monitoring device to ensure the accuracy of gas monitoring.

Description

Technical Field

[0001] This specification relates to the field of gas supervision, and in particular to a smart gas gate station gas monitoring method and Internet of Things system based on safety supervision. Background Art

[0002] In the work of urban gas safety supervision, gas monitoring of gas gate stations by relevant government departments is an important link. At present, gas gate stations mainly monitor gas components through gas monitoring devices, but gas monitoring devices may not be able to guarantee the accuracy and timeliness of monitoring data due to other impurities or pollutants in the gas pipeline, uneven gas entering the gas monitoring device, equipment failure, abnormal influence of the environment where the equipment is located, etc.

[0003] Therefore, it is necessary to provide a smart gas gate station gas monitoring method and Internet of Things system based on safety supervision, which can evaluate the accuracy of monitoring data when monitoring gas components, and make timely and targeted adjustments or repairs to the gas monitoring device to ensure the accuracy of gas monitoring. Summary of the invention

[0004] The invention content includes a smart gas gate station gas monitoring method based on safety supervision, which is executed by a smart gas government safety supervision management platform, and the method includes: obtaining gas monitoring data uploaded by a gas company management platform through a smart gas government safety supervision sensor network platform, and determining the uniformity of the gas based on the gas monitoring data; in response to the uniformity satisfying a first preset condition, controlling a component analysis device of a smart gas equipment object platform to collect target gas and determine gas component data based on the target gas, wherein the component analysis device is deployed on a gas pipeline of a gas gate station; obtaining the gas component data and environmental data uploaded by the gas company management platform through a smart gas government safety supervision sensor network platform; determining a component influence coefficient based on the uniformity and the environmental data; in response to the component influence coefficient satisfying a second preset condition, Preset conditions, generate and send a retrieval instruction to the gas user platform, the retrieval instruction is used to instruct the gas user platform to obtain feedback information uploaded by the gas user according to sampling parameters, the sampling parameters include sampling time point; based on the feedback information, determine the confidence weight corresponding to the feedback information; based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data and the component influence coefficient, determine the monitoring accuracy; and based on the monitoring accuracy, generate and send an adjustment instruction to the smart gas equipment object platform, the adjustment instruction is used to control the smart gas equipment object platform to adjust the component analysis device and / or the pipeline control device deployed in the gas pipeline according to the working parameters, the working parameters include the analysis accuracy of the component analysis device, the calibration cycle and / or the operating parameters of the pipeline control device.

[0005] The invention content includes a smart gas gate station gas monitoring Internet of Things system based on safety supervision, the system includes: a citizen user platform, a smart gas government safety supervision service platform, a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a gas company management platform, a gas company sensor network platform, a smart gas equipment object platform, a gas user service platform and a gas user platform, the smart gas government safety supervision management platform is configured to perform the following operations: obtain the gas monitoring data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform, and determine the uniformity of the gas based on the gas monitoring data; in response to the uniformity satisfying the first preset condition, control the component analysis device of the smart gas equipment object platform to collect the target gas and determine the gas component data based on the target gas, the component analysis device is deployed on the gas pipeline of the gas gate station; obtain the gas through the smart gas government safety supervision sensor network platform The gas component data and environmental data uploaded by the company management platform; based on the uniformity and the environmental data, determining the component influence coefficient; in response to the component influence coefficient satisfying the second preset condition, generating and sending a call instruction to the gas user platform, the call instruction is used to instruct the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters, and the sampling parameters include the sampling time point; based on the feedback information, determining the confidence weight corresponding to the feedback information; based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data and the component influence coefficient, determining the monitoring accuracy; and based on the monitoring accuracy, generating and sending an adjustment instruction to the smart gas equipment object platform, the adjustment instruction is used to control the smart gas equipment object platform to adjust the component analysis device and / or the pipeline control device deployed in the gas pipeline according to the working parameters, the working parameters include the analysis accuracy of the component analysis device, the calibration cycle and / or the operating parameters of the pipeline control device.

[0006] The invention content includes providing a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the smart gas gate station gas monitoring method based on safety supervision described in the above embodiment.

[0007] The beneficial effects of the present invention include but are not limited to: (1) The smart gas gate station gas monitoring Internet of Things system based on safety supervision can form an information operation closed loop between various functional platforms, coordinate and operate regularly, and realize the informatization and intelligence of smart gas gate station gas monitoring; (2) It is judged whether the uniformity meets the first preset condition and then the pipeline control device is adjusted, which can make the gas input to the component analysis device more uniform, and then the result output by the component analysis device is more accurate; (3) Based on the uniformity and environmental data, the degree of influence of environmental factors on the accuracy of the component analysis device can be determined. If the component influence coefficient is large, the monitoring accuracy can be determined and the component analysis device and / or pipeline control device can be adjusted in time based on the monitoring accuracy to ensure the accuracy of gas monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a schematic diagram of the platform structure of a smart gas gate station gas monitoring Internet of Things system based on safety supervision according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a smart gas gate station gas monitoring method based on safety supervision according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart for determining monitoring accuracy according to some embodiments of this specification;

[0012] Figure 4 is an exemplary schematic diagram of an accuracy determination model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] When the operations are performed according to the step description in the embodiments of this specification, unless otherwise specified, the order of the steps is interchangeable, the steps may be omitted, and other steps may be included in the operation process.

[0017] Figure 1 This is a schematic diagram of the platform structure of a smart gas gate station gas monitoring Internet of Things system based on safety supervision according to some embodiments of this specification. Figure 1 As shown, the smart gas gate station gas monitoring Internet of Things system 100 based on safety supervision (hereinafter referred to as the Internet of Things system 100) may include a citizen user platform 110, a smart gas government safety supervision service platform 120, a smart gas government safety supervision management platform 130, a smart gas government safety supervision sensor network platform 140, a smart gas government safety supervision object platform 150, a gas company management platform 151, a gas company sensor network platform 170, a gas user object platform 171, a smart gas equipment object platform 172, a gas user service platform 160 and a gas user platform 161. Each platform in the Internet of Things system 100 is connected through network communication.

[0018] The citizen user platform 110 is a user-oriented platform. For example, the citizen user platform can obtain user needs and provide information feedback to users.

[0019] In some embodiments, the citizen user platform 110 may interact with a government security supervision service platform.

[0020] The smart gas government safety supervision service platform 120 refers to a platform for the government to provide information and services related to gas safety.

[0021] In some embodiments, the smart gas government safety supervision service platform 120 can interact with the citizen user platform 110 and the smart gas government safety supervision management platform 130.

[0022] The smart gas government safety supervision management platform 130 refers to a management platform for the government to manage information related to gas safety.

[0023] In some embodiments, the smart gas government safety supervision management platform 130 may be configured to process and store data of the Internet of Things system 100. In some embodiments, the smart gas government safety supervision management platform 130 may be set on at least one distributed server. The distributed server includes a storage device, which is used to store data of the Internet of Things system 100. In some embodiments, the storage device may store the monitoring device parameters and the location of the component analysis device.

[0024] In some embodiments, the smart gas government safety supervision management platform 130 can be configured to determine the uniformity of the gas based on the gas monitoring data; determine the component influence coefficient based on the uniformity and environmental data; determine the monitoring accuracy based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data and the component influence coefficient; and generate and send adjustment instructions to the smart gas equipment object platform based on the monitoring accuracy.

[0025] In some embodiments, the smart gas government safety supervision management platform 130 can be further configured to generate and send an iterative control instruction to the smart gas equipment object platform in response to the uniformity not satisfying the first preset condition.

[0026] In some embodiments, the smart gas government safety supervision management platform 130 can be further configured to determine the uniformity based on the gas monitoring data and monitoring device parameters; and determine the component influence coefficient based on the uniformity, environmental data and gas component data.

[0027] In some embodiments, the smart gas government safety supervision management platform 130 can be further configured to determine the component influence coefficient through a coefficient determination model based on uniformity, environmental data, gas component data, historical component data, and historical maintenance data.

[0028] In some embodiments, the smart gas government safety supervision management platform 130 can be further configured to construct an accuracy characteristic map based on comparative feature data, confidence weights corresponding to feedback information, gas component data, and component influence coefficients; based on the accuracy characteristic map, the monitoring accuracy is determined through an accuracy determination model.

[0029] In some embodiments, the smart gas government safety supervision management platform 130 can be further configured to determine sampling parameters based on component influence coefficients; based on the sampling parameters, generate and send a call instruction to the gas user platform.

[0030] In some embodiments, the smart gas government safety supervision management platform 130 can be further configured to generate and issue adjustment instructions to the smart gas equipment object platform based on the monitoring accuracy in response to the monitoring accuracy satisfying the third preset condition; in response to the smart gas equipment object platform adjusting the component analysis device and / or the pipeline control device according to the working parameters, and the adjusted accuracy still satisfies the third preset condition, generate and send a manual maintenance adjustment order to the gas company management platform; in response to the monitoring accuracy not satisfying the third preset condition but satisfying the fourth preset condition, determine the gas component data based on at least one set of candidate component data and the candidate component influence coefficient corresponding to the candidate component data.

[0031] The smart gas government safety supervision sensor network platform 140 refers to a platform used by the government to manage sensor information related to gas safety.

[0032] In some embodiments, the smart gas government safety supervision sensor network platform 140 can be configured as a communication network or a gateway, etc.

[0033] In some embodiments, the smart gas government safety supervision sensor network platform 140 can interact with the gas company management platform 151 and the smart gas government safety supervision management platform 130.

[0034] The smart gas government safety supervision object platform 150 refers to a platform for generating government supervision information and controlling information execution. In some embodiments, the smart gas government safety supervision object platform 150 may include a gas company management platform 151.

[0035] The gas company management platform 151 refers to a comprehensive management platform for gas company information. In some embodiments, the gas company management platform can be set in a server of the gas company.

[0036] In some embodiments, the gas company management platform 151 may interact with the gas user service platform 160 and the gas company sensor network platform 170 .

[0037] The gas company sensor network platform 170 is a platform for comprehensively managing the sensor information of the gas company. In some embodiments, the gas company sensor network platform 170 can be set on a communication device of the gas company. The communication device is used to communicate with other platforms in the Internet of Things system 100.

[0038] The smart gas equipment object platform 172 refers to a functional platform for sensing information generation and controlling information execution. In some embodiments, the smart gas equipment object platform 172 includes a gas monitoring device, a component analysis device, and a pipeline control device. A gas gate station refers to a site that receives and distributes gas.

[0039] In some embodiments, the smart gas equipment object platform 172 can collect gas monitoring data, environmental data, and gas composition data.

[0040] In some embodiments, the smart gas device object platform 172 can interact with the gas company sensor network platform.

[0041] The gas user service platform 160 is a platform that provides gas services to gas users. In some embodiments, the gas user service platform 160 can interact with the gas company management platform and the gas user platform 161.

[0042] The gas user platform 161 refers to a platform for interacting with users. In some embodiments, the gas user platform 161 includes a device terminal (such as a smart phone, a tablet computer, etc.) used by the user.

[0043] In some embodiments, the IoT system 100 may further include a processor. In some embodiments, the processor may process information and / or data related to the IoT system 100 to perform one or more functions described in this application. As an example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), etc. or any combination thereof. In some embodiments, the processor may interact with multiple platforms included in the IoT system 100.

[0044] For detailed description of the above, please refer to Figures 2 to 4 Related description.

[0045] Based on the Internet of Things system 100, an information operation closed loop can be formed between various functional platforms to coordinate and operate regularly, thereby realizing the informatization and intelligence of gas monitoring at smart gas gate stations.

[0046] Figure 2 is an exemplary flow chart of a smart gas gate station gas monitoring method based on safety supervision according to some embodiments of this specification. In some embodiments, process 200 is executed by a smart gas government safety supervision management platform. Figure 2 As shown, process 200 includes the following steps:

[0047] Step 210, obtain the gas monitoring data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform, and determine the uniformity of the gas based on the gas monitoring data.

[0048] The gas monitoring data refers to data obtained by monitoring the flow of gas in the gas pipeline. In some embodiments, the gas monitoring data may include gas flow rate, gas temperature, gas pressure, etc.

[0049] In some embodiments, the gas monitoring data can be collected by multiple gas monitoring devices arranged at different positions in the gas pipeline of the gas gate station. The gas monitoring device refers to a device used to collect gas monitoring data, such as a gas flow rate meter, a digital thermometer, a digital pressure gauge, etc.

[0050] In some embodiments, multiple gas monitoring devices can send multiple gas monitoring data to the smart gas equipment object platform.

[0051] In some embodiments, the smart gas government safety supervision management platform can obtain the gas monitoring data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform. The gas company management platform can obtain the gas monitoring data uploaded by the smart gas equipment object platform through the gas company sensor network platform. For instructions on each platform, see Figure 1 and its related description.

[0052] The uniformity of the gas can represent the uniformity of the gas flow in the gas pipeline and the uniformity of the gas component distribution. The higher the uniformity of the gas, the higher the uniformity of the gas flow in the gas pipeline and the uniformity of the gas component distribution.

[0053] In some embodiments, the uniformity of the gas may be represented by a numerical value or a grade, wherein the higher the numerical value or the grade, the higher the uniformity of the gas.

[0054] The higher the consistency of the gas monitoring data obtained by the gas monitoring devices at different locations, the higher the uniformity of the gas. In some embodiments, the smart gas government safety supervision and management platform can determine the uniformity of the gas in a variety of ways based on multiple gas monitoring data at different locations. For example, the smart gas government safety supervision and management platform can calculate the variance of multiple gas monitoring data based on multiple gas monitoring data obtained by gas monitoring devices at different locations at consecutive time points, and determine the uniformity of the gas through a first corresponding relationship based on the variance of the multiple gas monitoring data. Among them, the first corresponding relationship may include that the uniformity of the gas is negatively correlated with the variance of multiple gas monitoring data obtained by gas monitoring devices at different locations at consecutive time points, and the larger the variance, the lower the uniformity of the gas.

[0055] In some embodiments, the smart gas government safety supervision and management platform can cluster multiple gas monitoring data to form multiple clusters, each cluster corresponds to a cluster center, each cluster center corresponds to a gas monitoring data, and based on the number of clusters, the uniformity of the gas is determined through a second corresponding relationship. The second corresponding relationship may include that the uniformity of the gas is negatively correlated to the number of clusters, and the more clusters there are, the lower the uniformity of the gas.

[0056] For example, the smart gas government safety supervision and management platform can use the gas flow rate and gas pressure in each gas monitoring data as the clustering feature vector of each gas monitoring data, and perform clustering based on the clustering feature vector to form multiple clusters. Among them, the types of clustering algorithms can include multiple types, for example, the clustering algorithm can include K-Means clustering, hierarchical clustering, etc. The method of determining the cluster center can be any method known to those skilled in the art.

[0057] Step 220 , in response to the uniformity satisfying the first preset condition, controlling the component analysis device of the smart gas equipment object platform to collect the target gas and determine the gas component data based on the target gas.

[0058] The first preset condition refers to a condition for determining whether the uniformity of the gas meets the accuracy requirements of the component analysis device. The component analysis device refers to a device for collecting target gas and determining gas component data based on the target gas, such as a gas detector. The accuracy of the component analysis device is related to the uniformity. The higher the uniformity of the gas collected by the component analysis device, the higher the accuracy of the component analysis device.

[0059] In some embodiments, the first preset condition may include that the uniformity is greater than a uniformity threshold, wherein the uniformity threshold may be preset based on historical experience.

[0060] Target gas refers to the gas for which gas monitoring is desired.

[0061] In some embodiments, the component analysis device may be deployed at a preset point in the gas pipeline of the gas gate station to collect the target gas, wherein the preset point may be pre-set based on historical experience.

[0062] The gas component data refers to data related to the current gas component of the target gas. The gas component data may include the gas component of the target gas and the content of each component. The gas component may include methane, ethylene, isobutane, etc.

[0063] In some embodiments, the smart gas government safety supervision management platform can send instructions to the smart gas equipment object platform via the smart gas government safety supervision sensor network platform, the gas company management platform, and the gas company sensor network platform to control the component analysis device to collect the target gas and determine the gas component data based on the target gas. The component analysis device can automatically analyze and determine the gas component data based on the target gas.

[0064] In some embodiments, in response to the uniformity not satisfying the first preset condition, the smart gas government safety supervision management platform can generate and send iterative control instructions to the smart gas equipment object platform.

[0065] Iterative control instructions refer to instructions used to control the smart gas equipment object platform to adjust the operating parameters of the pipeline control device.

[0066] The pipeline control device refers to a device that controls the flow of gas in the gas pipeline. The pipeline control device may include a gas valve, a pressure regulating valve, etc. The gas valve is used to control the gas flow rate of the gas in the gas pipeline. The pressure regulating valve is used to control the gas pressure of the gas in the gas pipeline. The pipeline control device can be deployed in the gas pipeline of the gas gate station.

[0067] The operating parameters of the pipeline control device may include the gas valve opening and the pressure regulating valve power.

[0068] In some embodiments, the smart gas government safety supervision management platform can obtain the current operating parameters of the pipeline control device uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform, and iteratively adjust the operating parameters based on the preset increase parameters. Among them, the gas company management platform can obtain the operating parameters of the pipeline control device uploaded by the smart gas equipment object platform through the gas company sensor network platform.

[0069] In some embodiments, a round of iterative process in the process of iteratively adjusting the operating parameters includes:

[0070] S1: In the first round of iteration, based on the first operating parameter and the preset increase parameter, the first operating parameter is added to the preset increase parameter to obtain the second operating parameter. The first operating parameter refers to the current operating parameter of the pipeline control device. The second operating parameter is the operating parameter of the current round. Among them, the preset increase parameter refers to the increase value of the gas valve opening and the increase value of the pressure regulating valve power. The preset increase parameter can be pre-set based on historical experience. Increasing the opening of the gas valve and increasing the power of the pressure regulating valve can make the gas flow more uniform.

[0071] S2: Obtain the candidate monitoring data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform, and determine the candidate uniformity corresponding to the candidate monitoring data based on the candidate monitoring data. The candidate monitoring data is the gas monitoring data after the pipeline control device is operated according to the second operating parameters. The process of determining the candidate uniformity corresponding to the candidate monitoring data is similar to the process of determining the uniformity of the gas based on the gas monitoring data, and its implementation method can refer to the implementation method of the process of determining the uniformity of the gas.

[0072] S3: In response to the candidate uniformity not satisfying the first preset condition, taking the second operating parameter as the first operating parameter of the next round of iteration, and continuing the next round of iteration.

[0073] S4: In the next iteration, based on the new first operating parameter and the preset increase parameter, the new first operating parameter is added to the preset increase parameter to obtain a new second operating parameter, and step S2 is repeated to determine the candidate uniformity corresponding to the candidate monitoring data. In response to the candidate uniformity not satisfying the first preset condition, the second operating parameter is used as the first operating parameter of the next iteration, and the next iteration is continued. The value n of the nth iteration is the number threshold.

[0074] S5: In response to the candidate uniformity satisfying the first preset condition or the number of iterations being greater than the number threshold, the iteration is stopped. The number threshold can be preset based on historical experience. The operating parameters after the iteration is stopped are sent as iterative control instructions to the smart gas equipment object platform to control the component analysis device to collect the target gas, and determine the gas component data based on the target gas. For instructions on determining the gas component data, please refer to the relevant description above.

[0075] By adjusting the operating parameters of the pipeline control device, the environment in which the component analysis device collects gas can be made more stable, the collected gas can be more uniform, and more accurate gas composition data can be obtained.

[0076] Step 230, obtaining the gas composition data and environmental data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform.

[0077] Environmental data refers to data related to the environment in which the component analysis device is located. In some embodiments, the environmental data may include the temperature, humidity, etc. of the environment in which the component analysis device is located.

[0078] In some embodiments, the environmental data may be collected by an environmental monitoring device deployed around the component analysis device. The environmental monitoring device may include a thermometer, a hygrometer, etc. The environmental monitoring device may send the environmental data to the smart gas equipment object platform.

[0079] In some embodiments, the smart gas government safety supervision management platform can obtain the gas component data and environmental data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform. The gas company management platform can obtain the gas component data and environmental data uploaded by the smart gas equipment object platform through the gas company sensor network platform.

[0080] Step 240, determining the component influence coefficient based on the uniformity and environmental data.

[0081] The component influence coefficient can represent the degree of influence of the environment in which the component analysis device is located on the accuracy of the component analysis device. The larger the component influence coefficient, the greater the degree of influence of the environment on the accuracy of the component analysis device.

[0082] In some embodiments, the smart gas government safety supervision and management platform can determine the component influence coefficient in a variety of ways based on the uniformity and environmental data. For example, the smart gas government safety supervision and management platform can determine the reference influence coefficient as the component influence coefficient by querying the reference influence coefficient corresponding to the uniformity and environmental data in the preset coefficient table based on the uniformity and environmental data. Among them, the preset coefficient table can be pre-set based on historical data. The preset coefficient table includes multiple groups of uniformity and environmental data and reference influence coefficients corresponding to each group. The reference influence coefficient can be determined by manual annotation.

[0083] In some embodiments, the smart gas government safety supervision and management platform can determine the uniformity based on the gas monitoring data and monitoring device parameters, and determine the component influence coefficient based on the uniformity, environmental data and gas component data.

[0084] Monitoring device parameters refer to data related to the gas monitoring device. In some embodiments, the monitoring device parameters may include the distribution location of the gas monitoring device. The distribution location of the gas monitoring device refers to the location where multiple gas monitoring devices are installed in different gas pipelines.

[0085] In some embodiments, the smart gas government safety supervision and management platform can obtain monitoring device parameters through the storage device. For an explanation of the storage device, see Figure 1 Related description.

[0086] In some embodiments, the smart gas government safety supervision and management platform can divide the area where the gas monitoring device is distributed into multiple sub-areas based on the preset radius range, based on the gas monitoring data and monitoring device parameters, with the location of the component analysis device as the center of the circle, calculate the variance of the gas monitoring data collected by the gas monitoring device in each sub-area, and weighted sum the variance corresponding to each sub-area, and determine the obtained result as the uniformity. Among them, the weights of the preset radius range and the variance corresponding to each sub-area can be pre-set based on historical experience, and the closer the sub-area is to the location of the component analysis device, the higher the weight of the variance corresponding to the sub-area.

[0087] It can be understood that the closer the gas monitoring data collected by the gas monitoring device is to the component analysis device, the more similar it is to the gas monitoring data of the gas pipeline where the component analysis device is located, and thus the corresponding uniformity of the two is also more similar, which is more important when determining the uniformity. Therefore, the closer the sub-region is to the component analysis device, the higher the weight of the variance corresponding to the sub-region.

[0088] Exemplarily, the smart gas government safety supervision and management platform can be based on gas monitoring data and monitoring device parameters, with the position of the component analysis device as the center of the circle, divide the area within a radius of 10 meters into the first sub-area, and divide the area with a radius of 10 to 20 meters into the second sub-area, calculate the variance of the gas monitoring data collected by the gas monitoring devices in the two sub-areas, and weightedly sum the variances corresponding to the two sub-areas, and determine the result as the degree of uniformity.

[0089] In some embodiments, the smart gas government safety supervision and management platform can obtain the location of the component analysis device through a storage device.

[0090] In some embodiments, the smart gas government safety supervision and management platform can construct a target feature vector based on uniformity, environmental data, and gas component data, match a first reference vector that satisfies a preset matching condition with the target feature vector in a first vector database, and determine the reference influence coefficient corresponding to the first reference vector that satisfies the preset matching condition as the component influence coefficient. Among them, the target feature vector can be a feature vector constructed based on uniformity, environmental data, gas component data, and mutation parameters. In some embodiments, the preset matching condition can include that the vector distance is less than a distance threshold, and the vector distance can include Euclidean distance, cosine distance, etc., and the distance threshold can be pre-set.

[0091] In some embodiments, the target feature vector may further include a mutation parameter. The mutation parameter may characterize the difference between the current gas component data and the historical component data. The greater the difference between the gas component data and the historical component data, the greater the mutation parameter. The historical component data refers to the gas component data acquired at a first historical time. The first historical time refers to a preset time period past the current time point.

[0092] In some embodiments, the smart gas government safety supervision and management platform may take an average of multiple gas component data acquired at a first historical time, and determine the average as the historical component data.

[0093] In some embodiments, the smart gas government safety supervision and management platform can construct a first vector database based on historical data, and the first vector database may include multiple first reference vectors and reference influence coefficients corresponding to the first reference vectors. Among them, the first reference vector can be a feature vector constructed based on the historical uniformity, historical environmental data, and historical component data in the historical data. The reference influence coefficient can be determined by manual annotation. If the target feature vector includes mutation parameters, the first reference vector also includes historical mutation parameters. The historical mutation parameters in the first reference vector can characterize the difference between the historical component data corresponding to the first reference vector and the first historical component data. The first historical component data refers to the gas component data obtained at the second historical time. The first historical time and the second historical time can be set in advance, and the first historical time is later than the second historical time.

[0094] When determining the uniformity, the importance of gas monitoring data obtained at different locations can be considered to obtain a more realistic uniformity. Since different components in the gas may be affected differently by the environment and uniformity, and may interact with each other under the influence of the environment and uniformity, a more accurate component influence coefficient can be determined based on uniformity, environmental data, gas component data, and mutation parameters.

[0095] In some embodiments, the smart gas government safety supervision and management platform can determine the component influence coefficient through a coefficient determination model based on uniformity, environmental data, gas component data, historical component data, and historical maintenance data.

[0096] The historical maintenance data refers to data related to the maintenance of the component analysis device within the first historical time. In some embodiments, the historical maintenance data may include the maintenance time, etc. The historical maintenance data may be stored in a storage device, and the smart gas government safety supervision management platform may obtain the monitoring device parameters through the storage device.

[0097] In some embodiments, the coefficient determination model refers to a model for determining the component influence coefficient. The coefficient determination model may be a machine learning model. For example, the coefficient determination model may include any one or combination of a recurrent neural network (RNN) model or other custom model structures.

[0098] In some embodiments, the smart gas government safety supervision and management platform can determine the model based on a large number of first training samples with first labels through training coefficients such as gradient descent method. The first training sample can include sample uniformity, sample environmental data, sample gas component data, sample historical component data, and sample historical maintenance data. The first label of the first training sample can be the component influence coefficient corresponding to the sample gas component data. In some embodiments, the first training sample can be obtained based on historical data.

[0099] In some embodiments, the smart gas government safety supervision and management platform can compare the difference between the standard gas component data and the sample gas component data, and determine the component influence coefficient corresponding to the sample gas component data through a third corresponding relationship. The third corresponding relationship may include that the greater the difference between the standard gas component data and the sample gas component data, the higher the component influence coefficient corresponding to the sample gas component data.

[0100] Standard gas component data refers to gas component data obtained under standard monitoring conditions. Standard monitoring conditions refer to the accuracy of the component analysis device meeting the standard for gas monitoring. In some embodiments, the smart gas government safety supervision and management platform can obtain multiple groups of gas component data under standard monitoring conditions for multiple batches of gas, calculate the average value of the multiple groups of gas component data, and determine the average value as the standard gas component data.

[0101] In some embodiments, the coefficient determination model can be trained in the following manner: multiple first training samples with first labels are input into the initial coefficient determination model, a loss function is constructed by the first labels and the prediction results of the initial coefficient determination model, the initial coefficient determination model is updated based on the iteration of the loss function, and the coefficient determination model training is completed when the loss function of the initial coefficient determination model meets the preset loss condition. The preset loss condition can be the convergence of the loss function, the number of iterations reaches a set value, etc.

[0102] By processing the uniformity, environmental data, gas composition data, historical composition data and historical maintenance data through the coefficient determination model, we can utilize the unique advantages of the machine learning model, clarify the correlation between the input content and the output results based on a large amount of complex data, and obtain a more accurate component influence coefficient.

[0103] Step 250, in response to the component influence coefficient satisfying the second preset condition, generating and sending a call instruction to the gas user platform.

[0104] The second preset condition refers to a condition for determining whether it is necessary to evaluate the accuracy of the component analysis device. In some embodiments, the second preset condition may include that the component influence coefficient is greater than an influence threshold value.

[0105] In some embodiments, the impact threshold can be determined based on the historical monitoring accuracy of the component analysis device. The lower the historical monitoring accuracy, the lower the impact threshold. Historical monitoring accuracy refers to the monitoring accuracy in historical data. In some embodiments, the smart gas government safety supervision management platform can average multiple monitoring accuracies within the first historical time and determine the average value as the historical monitoring accuracy. For instructions on determining monitoring accuracy, please refer to the relevant description below.

[0106] The retrieval instruction refers to an instruction used to instruct the gas user platform to obtain feedback information uploaded by the gas user according to the sampling parameters.

[0107] The sampling parameters refer to data related to obtaining feedback information uploaded by gas users. In some embodiments, the sampling parameters may include a sampling time point. The sampling time point refers to the time point at which the feedback information is obtained after the smart gas government safety supervision management platform generates and sends a retrieval instruction to the gas user platform.

[0108] In some embodiments, the smart gas government safety supervision and management platform can calculate the ratio of the delivery distance to the gas flow rate in the gas monitoring data, and determine the obtained ratio as the sampling time point. The delivery distance refers to the distance between the gas user and the component analysis device. In some embodiments, the delivery distance can be stored in a storage device.

[0109] In some embodiments, the gas user platform may obtain instructions for feedback information uploaded by gas users according to sampling parameters.

[0110] Feedback information refers to information related to gas use fed back by different gas users. Feedback information includes but is not limited to pictures, videos, text, audio, etc. For example, feedback information can be a video of gas burning, text indicating that the color of the burning flame is wrong, etc. In some embodiments, gas users may include users who use gas for industrial production.

[0111] In some embodiments, when the feedback information may be in the form of a video, the sampling parameters may also include specific frames of the video. The specific frames of the video may be preset based on historical experience. Only acquiring specific frames of the video may reduce the amount of data that needs to be processed.

[0112] Step 260: Determine the confidence weight corresponding to the feedback information based on the feedback information.

[0113] The confidence weight can represent the confidence level of the feedback information.

[0114] In some embodiments, the confidence weight of the feedback information may be related to the upstream and downstream positions of the gas user corresponding to the feedback information in the gas pipeline network. The smart gas government safety supervision and management platform may determine the confidence weight corresponding to the feedback information through a fourth corresponding relationship based on the position of the gas user corresponding to the feedback information. The fourth corresponding relationship may include that the confidence weight of the feedback information corresponding to the gas user upstream of the gas pipeline network is greater than the confidence weight of the feedback information corresponding to the gas user downstream of the gas pipeline network.

[0115] It is understandable that the gas used by upstream gas users is closer to the effective feedback information of upstream users and is closer to the target gas. The gas used by downstream gas users may pass through other gas stations and gas pipelines due to the longer transmission distance. The gas may be mixed with more impurities and thus differ greatly from the target gas. Therefore, the confidence weight of the feedback information corresponding to the gas users upstream of the gas pipeline network is greater than the confidence weight of the feedback information corresponding to the gas users downstream of the gas pipeline network.

[0116] In some embodiments, the location of the gas user may be stored in a storage device.

[0117] In some embodiments, the confidence weight may be related to the historical monitoring difference, and the smart gas government safety supervision management platform may determine the confidence weight corresponding to the feedback information based on the historical monitoring difference. Figure 3 and its related description.

[0118] Step 270, determining the monitoring accuracy based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data and the component influence coefficient.

[0119] Monitoring accuracy can characterize the accuracy of gas composition data.

[0120] In some embodiments, the smart gas government safety supervision and management platform can determine the monitoring accuracy in a variety of ways based on the feedback information, the confidence weights corresponding to the feedback information, the gas component data, and the component influence coefficients. For example, the smart gas government safety supervision and management platform can determine the monitoring accuracy as the reference accuracy by querying the reference accuracy corresponding to the feedback information, the confidence weights corresponding to the feedback information, the gas component data, and the component influence coefficients in the preset table based on the feedback information, the confidence weights corresponding to the feedback information, the gas component data, and the component influence coefficients. Among them, the preset coefficient table can be pre-set based on historical data. The preset coefficient table includes multiple groups of feedback information, confidence weights corresponding to the feedback information, gas component data, component influence coefficients, and reference accuracy corresponding to each group. The reference accuracy can be determined by manual marking.

[0121] In some embodiments, the smart gas government safety supervision and management platform can determine the monitoring accuracy based on the comparison of feature data, confidence weights corresponding to feedback information, gas component data, and component influence coefficients. For more information about this part, please refer to Figure 3 and its related description.

[0122] Step 280, based on the monitoring accuracy, generate and send adjustment instructions to the smart gas equipment object platform.

[0123] The adjustment instruction is used to control the smart gas equipment object platform to adjust the component analysis device and / or pipeline control device according to the working parameters.

[0124] Working parameters refer to parameters related to the operation of the component analysis device and / or the pipeline control device. In some embodiments, the working parameters may include the accuracy of the component analysis device, the calibration cycle and / or the operating parameters of the pipeline control device. The calibration cycle refers to the time interval for calibrating the component analysis device. For more information about the operating parameters, please refer to the relevant description above.

[0125] In some embodiments, after receiving the adjustment instruction, the smart gas equipment object platform can send the calibration cycle to the maintenance personnel, and the maintenance personnel can calibrate the component analysis device based on the calibration cycle.

[0126] In some embodiments, the smart gas government safety supervision and management platform can determine adjustment instructions in a variety of ways based on monitoring accuracy. For example, the smart gas government safety supervision and management platform can determine the working parameters based on the monitoring accuracy through the fifth correspondence, and generate adjustment instructions based on the working parameters. Among them, the fifth correspondence may include that the accuracy of the component analysis device and the operating parameters of the pipeline control device are negatively correlated with the monitoring accuracy. The lower the monitoring accuracy, the greater the increase in accuracy and the greater the increase in operating parameters; the calibration period is positively correlated with the monitoring accuracy. The lower the monitoring accuracy, the shorter the calibration period.

[0127] In some embodiments, in response to the monitoring accuracy satisfying the third preset condition, the smart gas government safety supervision and management platform can generate and send an adjustment instruction to the smart gas equipment object platform based on the monitoring accuracy; in response to the smart gas equipment object platform adjusting the component analysis device and / or the pipeline control device according to the working parameters, the adjusted monitoring accuracy still satisfies the third preset condition, the smart gas government safety supervision and management platform can generate and send a manual maintenance adjustment order to the gas company management platform; in response to the monitoring accuracy not satisfying the third preset condition and satisfying the fourth preset condition, the smart gas government safety supervision and management platform can determine the gas component data based on at least one set of candidate component data and the candidate component influence coefficient corresponding to the candidate component data. For instructions on adjusting the component analysis device and / or the pipeline control device, please refer to the relevant description above.

[0128] In some embodiments, the third preset condition may include that the monitoring accuracy is lower than the second accuracy threshold. The fourth preset condition may include that the monitoring accuracy is higher than the second accuracy threshold and lower than the first accuracy threshold. The first accuracy threshold is greater than the second accuracy threshold.

[0129] In some embodiments, the first accuracy threshold and the second accuracy threshold may be related to the abnormal frequency, inspection interval, gas flow rate, and average monitoring difference. The higher the abnormal frequency, the longer the inspection interval, the larger the gas flow rate, and the larger the average monitoring difference, the higher the first accuracy threshold and the second accuracy threshold. The larger the gas flow rate, the more important the gas pipeline is. The larger the average monitoring difference, the greater the difference between the historical feedback monitoring data and the historical component data, and the gas pipeline needs to be regulated.

[0130] Abnormal frequency refers to the frequency at which the monitoring accuracy is lower than the second accuracy threshold. Inspection interval refers to the time interval since the last maintenance of the component analysis device. Average monitoring difference refers to the average value of historical monitoring differences. For an explanation of historical monitoring differences, see Figure 3 and its related description.

[0131] In some embodiments, the smart gas government safety supervision management platform can count the frequency of the monitoring accuracy being lower than the second accuracy threshold within the first historical time; obtain the time of the last maintenance of the component analysis device through the gas company management platform, and calculate the time interval from the last maintenance of the component analysis device, and use the time interval; calculate the average value of the historical monitoring differences as the average monitoring difference.

[0132] Based on the abnormal frequency, inspection interval, gas flow and average monitoring difference, a more reasonable first accuracy threshold and second accuracy threshold can be determined, which is conducive to accurately selecting subsequent operations, timely generating and sending adjustment instructions or manual maintenance orders, or changing the way of determining gas component data.

[0133] In some embodiments, in response to the smart gas equipment object platform adjusting the component analysis device and / or the pipeline control device according to the working parameters, the smart gas government safety supervision and management platform can obtain the gas component data and determine the monitoring accuracy corresponding to the gas component data. If the monitoring accuracy still meets the third preset condition, the smart gas government safety supervision and management platform can generate and send a manual maintenance order to the gas company management platform.

[0134] Manual maintenance dispatch orders refer to instructions used to control the gas company management platform to assign maintenance personnel to repair the component analysis device.

[0135] In some embodiments, in response to the monitoring accuracy not satisfying the third preset condition and satisfying the fourth preset condition, the smart gas government safety supervision and management platform may change the way of determining the gas component data. For example, the smart gas government safety supervision and management platform may weight and sum at least one set of candidate component data based on at least one set of candidate component data and the component influence coefficient corresponding to the candidate component data, and determine the obtained result as the gas component data. The weight of each set of candidate component data may be negatively correlated to the component influence coefficient corresponding to each set of candidate component data, and the larger the component influence coefficient corresponding to the candidate component data, the smaller the weight of the candidate component data.

[0136] The at least one set of candidate component data refers to at least one set of fuel gas component data collected multiple times by the component analysis device.

[0137] In some embodiments, in response to the monitoring accuracy not meeting the third preset condition and the fourth preset condition, but the component influence coefficient is high, the smart gas government safety supervision management platform can control the component analysis device through the smart gas equipment object platform to re-collect the target gas and determine the gas component data based on the target gas.

[0138] By judging whether the monitoring accuracy meets the third preset condition, when the monitoring accuracy is low, an adjustment instruction or a manual maintenance order can be generated and sent in time to adjust or repair the component analysis device and / or the pipeline control device, so as to avoid obtaining a large amount of inaccurate gas component data; by judging whether the monitoring accuracy meets the fourth preset condition, when the monitoring accuracy is moderate, the method of determining the gas component data can be changed to improve the accuracy of the gas component data.

[0139] By judging whether the uniformity meets the first preset condition and then adjusting the pipeline control device, the gas input to the component analysis device can be made more uniform, and the result output by the component analysis device can be made more accurate; based on the uniformity and environmental data, the degree of influence of environmental factors on the accuracy of the component analysis device can be determined. If the component influence coefficient is large, the monitoring accuracy can be determined and the component analysis device and / or pipeline control device can be adjusted in time based on the monitoring accuracy to ensure the accuracy of fuel gas monitoring.

[0140] It should be noted that the above description of process 200 is only for illustration and description, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process hand-eye calibration under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0141] Figure 3is an exemplary flow chart for determining monitoring accuracy according to some embodiments of this specification. In some embodiments, process 300 is executed by a smart gas government safety supervision and management platform. Figure 3 As shown, process 300 includes the following steps:

[0142] Step 310: Determine effective feedback information based on the feedback information.

[0143] In some embodiments, the sampling parameters may also include sampling user information. The smart gas government safety supervision and management platform may determine the sampling parameters based on the component influence coefficient; based on the sampling parameters, generate and send a call instruction to the gas user platform to control the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters. For instructions on generating and sending a call instruction to the gas user platform to control the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters, please refer to Figure 2 and its related description.

[0144] The sampled user information refers to information related to the gas users who upload feedback information. In some embodiments, the sampled user information may include the number of sampled users, the range of sampled users, etc. The number of sampled users refers to the number of gas users who upload feedback information. The sampled user range refers to the range of gas users who upload feedback information.

[0145] In some embodiments, the smart gas government safety supervision and management platform can determine the sampling parameters in a variety of ways based on the component influence coefficient. For example, the smart gas government safety supervision and management platform can calculate the absolute value of the difference between the component influence coefficient and the coefficient threshold based on the component influence coefficient, and determine the sampling parameters through a preset relationship based on the absolute value. Among them, the preset relationship includes that the sampling parameter is negatively correlated with the absolute value of the difference between the component influence coefficient and the coefficient threshold. The smaller the absolute value, the more sampled users and the larger the range of sampled users. The coefficient threshold can be preset based on historical experience.

[0146] It is understandable that the larger the absolute value of the difference between the component influence coefficient and the coefficient threshold, the less accurate the gas component data is, and only a small amount of data needs to be analyzed to determine the monitoring accuracy. Conversely, the smaller the absolute value, the higher the accuracy of the gas component data is, but not absolute accuracy, and a large amount of data needs to be analyzed to determine the monitoring accuracy.

[0147] In some embodiments, the smart gas government safety supervision and management platform can construct a call feature vector based on the component influence coefficient, the current time point, the user usage characteristics, and the historical feedback quality, match the second reference vector that meets the preset matching conditions with the call feature vector in the second vector database, and determine the reference sampling parameters corresponding to the second reference vector that meets the preset matching conditions as the sampling parameters. Among them, the call feature vector can be a feature vector constructed based on the component influence coefficient, the current time point, the user usage characteristics, and the historical feedback quality. For an explanation of the preset matching conditions, see Figure 2 Related description.

[0148] User usage characteristics can characterize the characteristics of gas users when using gas, such as the form of feedback information, the time and amount of gas used, etc. In some embodiments, the gas user platform can count user usage characteristics and upload them to the smart gas government safety supervision and management platform.

[0149] The quality of historical feedback refers to the quality of feedback information uploaded by gas users in the first historical time. The quality of historical feedback can be determined by manual annotation. For example, the higher the proportion of effective feedback information in the feedback information in the first historical time, the greater the amount of information, and the higher the accuracy of the wording, the higher the quality of historical feedback.

[0150] In some embodiments, the smart gas government safety supervision and management platform can construct a second vector database based on historical data, and the second vector database may include multiple second reference vectors and reference sampling parameters corresponding to the second reference vectors. Among them, the second reference vector can be a feature vector constructed based on the historical component influence coefficient, historical time point, historical user usage characteristics, and historical feedback quality in the historical data. The reference sampling parameters can be determined by manual annotation. The historical feedback quality in the second reference vector refers to the quality of feedback information uploaded by gas users within the second historical time. For instructions on the first historical time and the second historical time, please refer to Figure 2 and its related description.

[0151] By determining the sampling parameters based on the component influence coefficient, feedback information within an appropriate amount and range can be obtained, reducing the amount of calculation; at the same time, the characteristics of gas users' use of gas and the quality of feedback information can be considered when determining the sampling parameters, so that more reasonable sampling parameters can be determined.

[0152] Effective feedback information refers to feedback information that excludes useless information.

[0153] In some embodiments, the smart gas government safety supervision and management platform can determine effective feedback information based on the feedback information in a variety of ways. For example, for feedback information in the form of text or voice, the smart gas government safety supervision and management platform can match the feedback information with the keyword library for keywords, and exclude feedback information that does not include keywords to obtain effective feedback information. For feedback information in the form of pictures and videos, the smart gas government safety supervision and management platform can identify key features in the feedback information through a preset recognition method, and exclude feedback information that does not include key features to obtain effective feedback information. Among them, the preset recognition method may include image recognition algorithms and models for image recognition. Image recognition algorithms include support vector machines, principal component analysis, and the like. Models for image recognition include YOLO models, Faster R-CNN models, U-Net models, and the like. The keyword library can be pre-set based on historical experience, including a large number of keywords.

[0154] Keywords refer to descriptions related to gas use, such as the size of the flame when the gas burns, the amount of smoke produced, etc.

[0155] Key features refer to feature images related to gas use, such as images of gas stoves or gas pipes, gas flame color images, smoke images, etc.

[0156] In some embodiments, the smart gas government safety supervision and management platform can convert keywords and key features in the effective feedback information into key feature vectors through a preset conversion algorithm, and find abnormal feature vectors through an outlier detection algorithm to exclude the effective feedback information corresponding to the abnormal feature vector. Among them, the preset conversion algorithms include Bag of Words, TF-IDF model, word embedding (Word2Vec, GloVe) or BERT embedding, etc. Outlier detection algorithms include Isolation Forest, Local Outlier Factor (LOF), etc.

[0157] An abnormal feature vector refers to a key feature vector that is significantly different from the other key feature vectors.

[0158] It is understandable that if a certain valid feedback information is significantly different from the rest of the valid feedback information, it means that the valid feedback information may be wrong, and excluding the valid feedback information can obtain more accurate monitoring accuracy. For example, if the keyword in the valid feedback information of the upstream gas user is abnormal combustion, but the keyword in the valid feedback information of multiple downstream gas users is normal combustion, it may be that there is a problem with the gas equipment of the upstream gas user, which has nothing to do with the monitoring accuracy.

[0159] Step 320: Determine comparative feature data based on the effective feedback information.

[0160] The comparative feature data may characterize the key features of the effective feedback information. In some embodiments, the smart gas government safety supervision and management platform may use the keywords, key features, or key feature vectors corresponding to the effective feedback information as the comparative feature data corresponding to the effective feedback information.

[0161] Step 330: Determine the confidence weight corresponding to the feedback information based on the feedback information.

[0162] In some embodiments, the smart gas government safety supervision and management platform can determine the confidence weight corresponding to the feedback information based on the feedback information. Figure 2 and its related description.

[0163] In some embodiments, the confidence weight may be related to the historical monitoring difference. The historical monitoring difference may characterize the degree of difference between the historical feedback monitoring data and the historical component data. In some embodiments, the historical monitoring difference may be represented by a numerical value or a percentage. The larger the numerical value or percentage, the higher the historical monitoring difference. For an explanation of the historical component data, see Figure 2 and its related description.

[0164] The historical feedback monitoring data refers to the feedback monitoring data within the first historical time. The feedback monitoring data refers to the gas composition data uploaded by the gas branch sites around the gas user. In some embodiments, the feedback monitoring data can be obtained by a component analysis device deployed at the gas branch site.

[0165] In some embodiments, the smart gas government safety supervision management platform can construct a first vector based on historical component data, construct a second vector based on historical feedback monitoring data, calculate the vector distance between the first vector and the second vector, and determine the historical monitoring difference based on the vector distance. The smaller the vector distance, the greater the historical monitoring difference. The vector distance can include Euclidean distance, cosine distance, etc.

[0166] In some embodiments, the smart gas government safety supervision and management platform can update the confidence weight corresponding to the feedback information based on the historical monitoring difference and the confidence weight corresponding to the feedback information. For example, the smart gas government safety supervision and management platform can normalize and sum the historical monitoring difference and the confidence weight corresponding to the feedback information, and determine the summed result as the updated confidence weight.

[0167] Taking historical monitoring differences into account when determining the confidence weight of feedback information can determine a more reasonable confidence weight.

[0168] Step 340, constructing an accuracy characteristic map based on the comparison characteristic data, the confidence weight corresponding to the feedback information, the gas component data, and the component influence coefficient.

[0169] Figure 4 is an exemplary schematic diagram of an accuracy determination model according to some embodiments of this specification. The accuracy feature map 420 refers to a graph structure containing association information between gas users and gas pipelines. The graph structure is a data structure composed of nodes and edges, where the edges connect the nodes, and the nodes and edges may have features. Among them, the edges are directed edges, indicating the direction of gas flow.

[0170] In some embodiments, the smart gas government safety supervision and management platform can construct an accuracy feature map 420 based on the comparison feature data 411, the confidence weight 412 corresponding to the feedback information, the gas component data 413, and the component influence coefficient 414. The nodes of the accuracy feature map 420 include user nodes, ordinary pipeline nodes, and target pipeline nodes (for example, user nodes 423, ordinary pipeline nodes 422, target pipeline nodes 421, etc.). Among them, the user node refers to a node representing a gas user. The target pipeline node refers to a node representing a gas pipeline where the target gas is located. The ordinary pipeline node refers to a node representing a gas pipeline in a gas gate station except for the target pipeline node.

[0171] In some embodiments, the node feature of the user node in the accuracy feature map 420 is the confidence weight corresponding to the comparison feature data and the feedback information, the node feature of the common pipeline node is the gas monitoring data corresponding to the common pipeline, and the node feature of the target pipeline node is the gas monitoring data, gas component data, component influence coefficient and historical component data corresponding to the target pipeline. The edge feature is the direction of gas flow. Among them, the gas monitoring data corresponding to the common pipeline node can be obtained by the gas monitoring device deployed in the common pipeline.

[0172] In some embodiments, the node characteristics of the user node may include feedback monitoring data, etc. The node characteristics of the common node may also include component influence coefficients and monitoring accuracy corresponding to common pipelines, etc.

[0173] In some embodiments, the smart gas government safety supervision and management platform can determine the component influence coefficient and monitoring accuracy corresponding to the ordinary pipeline based on the gas component data corresponding to the ordinary pipeline. The process of determining the component influence coefficient and monitoring accuracy corresponding to the ordinary pipeline is similar to the process of determining the component influence coefficient and monitoring accuracy, and its implementation method can refer to the implementation method of the process of determining the component influence coefficient and monitoring accuracy. Among them, the gas component data corresponding to the ordinary pipeline can be collected and obtained by the component analysis device deployed in the ordinary pipeline.

[0174] In some embodiments, when the node characteristics of the user node include feedback monitoring data, and the node characteristics of the common node include the component influence coefficient and monitoring accuracy corresponding to the common pipeline, the node characteristics of the user node in the sample accuracy feature map also include sample feedback monitoring data, and the node characteristics of the common node include the sample component influence coefficient and sample monitoring accuracy corresponding to the common pipeline.

[0175] Step 350, based on the accuracy characteristic map, determine the monitoring accuracy through the accuracy determination model.

[0176] In some embodiments, the smart gas government safety supervision and management platform can input the accuracy characteristic map 420 into the accuracy determination model 430 to obtain the monitoring accuracy 440.

[0177] The accuracy determination model 430 refers to a model for determining monitoring accuracy. In some embodiments, the accuracy determination model 430 may be a machine learning model. For example, the accuracy determination model may include any one or combination of a Graph Neural Network (GNN) model or other custom model structures.

[0178] In some embodiments, the smart gas government safety supervision and management platform can train the accuracy determination model 430 based on the training set by gradient descent method, etc., and the training set includes a large number of second training samples with second labels. The second training samples may include a sample accuracy feature map, and the second label of the second training sample may be the actual monitoring accuracy corresponding to the sample gas component data. In some embodiments, the sample accuracy feature map may include a historical accuracy feature map determined based on historical data, and the nodes and features, edges and features of the historical accuracy feature map are similar to the above description.

[0179] In some embodiments, the smart gas government safety supervision and management platform can compare the difference between the standard gas component data and the sample gas component data in the sample accuracy characteristic map, and determine the actual monitoring accuracy corresponding to the sample gas component data through a preset corresponding relationship. Among them, the preset corresponding relationship may include that the larger the difference between the standard gas component data and the sample gas component data, the lower the actual monitoring accuracy corresponding to the sample gas component data. For more information about standard gas component data, please refer to Figure 2 and its related description.

[0180] The training process of the accuracy determination model 430 is similar to the training process of the coefficient determination model, and reference may be made to the training process of the coefficient determination model.

[0181] The node characteristics of the user node may include feedback monitoring data, and the node characteristics of the common node may also include the component influence coefficient and monitoring accuracy corresponding to the common pipeline, so that an accuracy characteristic map that can better reflect the characteristics of the node can be obtained.

[0182] In some embodiments, the variance of the global confidence of each sample accuracy feature map in the training set of the training accuracy determination model satisfies a preset confidence condition.

[0183] The global confidence can reflect the confidence level of the sample accuracy feature map. The higher the variance of the global confidence, the more diverse the sample accuracy feature maps in the training set.

[0184] In some embodiments, the smart gas government safety supervision and management platform can weighted sum the data amounts of multiple sample effective feedback information based on the data amounts of sample comparison feature data corresponding to multiple user nodes in the sample accuracy feature map and the weights of the sample effective feedback information, and determine the weighted summation result as the global confidence of the sample accuracy feature map. The weight corresponding to the sample effective feedback information can be preset based on the type of the sample effective feedback information.

[0185] In some embodiments, the smart gas government safety supervision and management platform can determine the data volume of sample effective feedback information in a variety of ways. For example, the smart gas government safety supervision and management platform can determine the data volume of sample effective feedback information in text form by keyword counting method. For another example, the smart gas government safety supervision and management platform can determine the data volume of sample effective feedback information in picture form by pixel area method and key frame extraction. For another example, the smart gas government safety supervision and management platform can determine the data volume of sample effective feedback information in video form by duration method and key feature counting.

[0186] In some embodiments, the smart gas government safety supervision and management platform can normalize the data volume of effective feedback information of samples in different forms.

[0187] The preset confidence condition refers to a condition for determining whether the training set of the training accuracy determination model meets the training requirements. In some embodiments, the preset confidence condition may include that the variance is greater than a discrete threshold.

[0188] In some embodiments, the discrete threshold may be negatively correlated to the number of samples and the quality of samples in the training set. The more samples there are and the better the sample quality is, the lower the discrete threshold is. The sample quality may be manually determined based on completeness, noise, and other aspects.

[0189] In some embodiments of the present specification, the variance of the global confidence of each sample accuracy feature map in the training set satisfies a preset confidence condition, thereby ensuring the diversity of the sample accuracy feature maps in the training set, thereby improving the versatility of the accuracy determination model.

[0190] By constructing an accuracy feature map, various scattered and large data can be effectively organized, which helps to quickly and efficiently obtain the correlation between gas users and gas pipelines and their respective characteristics from the accuracy feature map; by processing the accuracy feature map through the accuracy determination model, the self-learning ability of the machine learning model can be used to find patterns from large amounts of data, thereby improving the accuracy and efficiency of determining monitoring accuracy.

[0191] It should be noted that the above description of process 300 is only for illustration and description, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process hand-eye calibration under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0192] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the smart gas gate station gas monitoring method based on safety supervision as described in any of the above embodiments.

[0193] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

Claims

1. A smart gas gate station gas monitoring method based on safety supervision, characterized in that: The method is executed by a smart gas government safety supervision management platform based on a smart gas gate station gas monitoring system for safety supervision, and the method includes: Obtain the gas monitoring data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform, and determine the uniformity of the gas based on the gas monitoring data; In response to the uniformity satisfying the first preset condition, controlling the component analysis device of the smart gas equipment object platform to collect target gas and determine gas component data based on the target gas, wherein the component analysis device is deployed on the gas pipeline of the gas gate station; Acquire the gas composition data and environmental data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform; Determining a component influence coefficient based on the uniformity and the environmental data; In response to the component influence coefficient satisfying the second preset condition, generating and sending a retrieval instruction to the gas user platform, the retrieval instruction is used to instruct the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters, and the sampling parameters include the sampling time point; Based on the feedback information, determining a confidence weight corresponding to the feedback information; Determining monitoring accuracy based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data, and the component influence coefficient; and, Based on the monitoring accuracy, generating and sending an adjustment instruction to the smart gas equipment object platform includes: In response to the monitoring accuracy satisfying a third preset condition, generating and sending an adjustment instruction to the smart gas equipment object platform based on the monitoring accuracy; In response to the smart gas equipment object platform adjusting the component analysis device and / or pipeline control device according to the working parameters, if the monitoring accuracy after adjustment still meets the third preset condition, a manual maintenance adjustment order is generated and sent to the gas company management platform; and In response to the monitoring accuracy not satisfying the third preset condition and satisfying the fourth preset condition, the gas component data is determined based on at least one set of candidate component data and the component influence coefficients corresponding to the candidate component data, and the adjustment instruction is used to control the smart gas equipment object platform to adjust the component analysis device and / or the pipeline control device deployed in the gas pipeline according to the working parameters, and the working parameters include the analysis accuracy of the component analysis device, the calibration cycle and / or the operating parameters of the pipeline control device.

2. The method according to claim 1, characterized in that Determining the component influence coefficient based on the uniformity and the environmental data includes: determining the uniformity based on the gas monitoring data and monitoring device parameters, wherein the monitoring device parameters include distribution positions of gas monitoring devices used to obtain the gas monitoring data; and The component influence coefficient is determined based on the uniformity, the environmental data and the fuel gas component data.

3. The method according to claim 1, characterized in that The second preset condition includes that the component influence coefficient is greater than an influence threshold, the influence threshold is determined based on historical monitoring accuracy, and the determination of monitoring accuracy includes: Based on the feedback information, determining effective feedback information; Determining comparative feature data based on the effective feedback information; Based on the feedback information, determining a confidence weight corresponding to the feedback information; constructing an accuracy characteristic map based on the comparison characteristic data, the confidence weight corresponding to the feedback information, the gas component data, and the component influence coefficient; and, Based on the accuracy feature map, the monitoring accuracy is determined by an accuracy determination model, and the accuracy determination model is a machine learning model.

4. The method according to claim 3, characterized in that The sampling parameters also include sampling user information, and the sampling user information includes the number of sampled users and the range of sampled users. The method further includes: determining the sampling parameters based on the component influence coefficients; and, Based on the sampling parameters, the retrieval instruction is generated and sent to the gas user platform to control the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters.

5. The smart gas gate station gas monitoring Internet of Things system based on safety supervision is characterized by: The system includes a citizen user platform, a smart gas government safety supervision service platform, a smart gas government safety supervision management platform, a smart gas government safety supervision sensor network platform, a smart gas government safety supervision object platform, a gas company management platform, a gas company sensor network platform, a gas user object platform, a smart gas equipment object platform, a gas user service platform and a gas user platform, wherein the citizen user platform refers to a user-dominated platform, the smart gas government safety supervision service platform refers to a platform for the government to provide information and services related to gas safety, the smart gas government safety supervision management platform refers to a management platform for the government to manage information related to gas safety, the smart gas government safety supervision sensor network platform refers to a platform for the government to manage sensor information related to gas safety, the smart gas government safety supervision object platform refers to a platform for the government to generate supervision information and control information execution, and the smart gas government safety supervision object platform includes The gas company management platform includes the gas company management platform, the gas company management platform refers to a comprehensive management platform for gas company information, the gas company sensor network platform refers to a platform for comprehensive management of gas company sensor information, the smart gas equipment object platform refers to a functional platform for sensing information generation and control information execution, the gas user service platform refers to a platform that provides gas services to gas users, the gas user platform refers to a platform for interacting with users, the gas company sensor network platform refers to a platform for comprehensive management of gas company sensor information, the citizen user platform interacts with the smart gas government safety supervision service platform, the smart gas government safety supervision service platform interacts with the citizen user platform and the smart gas government safety supervision management platform, the gas company management platform interacts with the gas user service platform and the gas company sensor network platform, and the gas user object platform and the smart gas equipment object platform interact with the gas company sensor network platform; The smart gas government safety supervision and management platform is configured to perform the following operations: Obtaining the gas monitoring data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform, and determining the uniformity of the gas based on the gas monitoring data; In response to the uniformity satisfying the first preset condition, controlling the component analysis device of the smart gas equipment object platform to collect target gas and determine gas component data based on the target gas, wherein the component analysis device is deployed on the gas pipeline of the gas gate station; Acquire the gas composition data and environmental data uploaded by the gas company management platform through the smart gas government safety supervision sensor network platform; Determining a component influence coefficient based on the uniformity and the environmental data; In response to the component influence coefficient satisfying the second preset condition, generating and sending a retrieval instruction to the gas user platform, the retrieval instruction is used to instruct the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters, and the sampling parameters include the sampling time point; Based on the feedback information, determining a confidence weight corresponding to the feedback information; Determining monitoring accuracy based on the feedback information, the confidence weight corresponding to the feedback information, the gas component data, and the component influence coefficient; and, Based on the monitoring accuracy, generating and sending an adjustment instruction to the smart gas equipment object platform includes: In response to the monitoring accuracy satisfying a third preset condition, generating and sending an adjustment instruction to the smart gas equipment object platform based on the monitoring accuracy; In response to the smart gas equipment object platform adjusting the component analysis device and / or pipeline control device according to the working parameters, if the monitoring accuracy after adjustment still meets the third preset condition, a manual maintenance adjustment order is generated and sent to the gas company management platform; and In response to the monitoring accuracy not satisfying the third preset condition and satisfying the fourth preset condition, the gas component data is determined based on at least one set of candidate component data and the component influence coefficients corresponding to the candidate component data, and the adjustment instruction is used to control the smart gas equipment object platform to adjust the component analysis device and / or the pipeline control device deployed in the gas pipeline according to the working parameters, and the working parameters include the analysis accuracy of the component analysis device, the calibration cycle and / or the operating parameters of the pipeline control device.

6. The Internet of Things system according to claim 5, characterized in that: The smart gas government safety supervision and management platform is further configured as follows: determining the uniformity based on the gas monitoring data and monitoring device parameters, wherein the monitoring device parameters include distribution positions of gas monitoring devices used to obtain the gas monitoring data; and The component influence coefficient is determined based on the uniformity, the environmental data and the fuel gas component data.

7. The Internet of Things system according to claim 5, characterized in that: The second preset condition includes that the component influence coefficient is greater than the influence threshold, and the smart gas government safety supervision and management platform is further configured as follows: Based on the feedback information, determining effective feedback information; Determining comparative feature data based on the effective feedback information; Based on the feedback information, determining a confidence weight corresponding to the feedback information; Constructing an accuracy characteristic map based on the comparison characteristic data, the confidence weight corresponding to the feedback information, the gas component data, and the component influence coefficient; as well as, Based on the accuracy feature map, the monitoring accuracy is determined by an accuracy determination model, and the accuracy determination model is a machine learning model.

8. The Internet of Things system according to claim 7, characterized in that: The sampling parameters also include sampling user information, and the sampling user information includes the number of sampling users and the range of sampling users. The smart gas government safety supervision and management platform is further configured as follows: determining the sampling parameters based on the component influence coefficients; and, Based on the sampling parameters, the retrieval instruction is generated and sent to the gas user platform to control the gas user platform to obtain the feedback information uploaded by the gas user according to the sampling parameters.

Images