Government-regulated smart gas household inspection method, IoT system and media

Abstract

The present invention provides a government-regulated smart gas household inspection method, an Internet of Things system and a medium, which relate to the field of gas inspection. The method includes obtaining gas usage data; determining candidate inspection time periods; determining inspection parameters based on candidate inspection time periods and inspection resource information; generating inspection instructions and sending them to a smart gas inspection personnel object platform. The system includes a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, a smart gas equipment object platform, a smart gas inspection personnel object platform, a government gas supervision object platform, a government gas supervision sensor network platform, a government gas supervision management platform, a government gas supervision service platform, and a citizen user platform. The method can also be run after being read by a computer instruction stored in a computer-readable storage medium. The method can ensure the completion rate of gas inspections, improve inspection efficiency, and reduce inspection costs.

Description

Technical Field

[0001] The present invention relates to the field of gas inspection, and in particular to a government-regulated smart gas household inspection method, system and medium. Background Art

[0002] Gas is a flammable and explosive gas. If there is a leak or failure in the gas pipeline, it may cause serious safety accidents such as fire and explosion. It is necessary to conduct household inspections of gas pipelines to promptly discover potential safety hazards and ensure the reliability and safety of gas supply.

[0003] CN109767513B discloses a pipe network equipment inspection device and method, the pipe network equipment includes multiple pipelines, including terminals, inspection management servers, multiple sets of pipeline operation status monitoring equipment and equipment health status monitoring devices, and can use the enterprise equipment asset data and surrounding geographical environment data and personnel location included in the inspection work to generate inspection recommendation information to improve the pertinence. However, the pipe network equipment only improves the pertinence of gas pipeline inspection, and cannot guarantee the inspection completion rate under the inspection deadline.

[0004] Therefore, a government-regulated smart gas household inspection method, Internet of Things system and medium are provided to improve the inspection efficiency and reduce the inspection cost while ensuring the completion rate of gas inspection. Summary of the invention

[0005] In order to solve the problem of how to improve inspection efficiency and reduce inspection costs while ensuring the completion rate of gas inspections, the present invention provides a government-regulated smart gas household inspection method, Internet of Things system and medium.

[0006] The content of the invention includes a government-regulated smart gas household inspection method. The household inspection method includes: obtaining gas usage data of at least one gas user in the inspection area through a smart gas equipment object platform; for a gas user, the smart gas management platform determines the candidate inspection time period of the gas user based on the gas usage data of the gas user; the smart gas management platform determines the inspection parameters based on the candidate inspection time period and inspection resource information of the at least one gas user, and the inspection parameters include the inspection time period and inspection resource configuration for the household inspection of the at least one gas user; the smart gas management platform sends the inspection parameters to the government gas supervision management platform and the smart gas user platform, and generates an inspection instruction and sends it to the smart gas inspection personnel object platform, so that the inspection personnel can According to the inspection instruction, the household inspection is carried out, and the smart gas inspection personnel object platform is configured as the inspection terminal of the inspection personnel; the government gas supervision and management platform obtains the inspection data of the gas company according to the inspection supervision frequency based on the inspection area and the inspection parameters of the gas company, and determines the inspection completion rate of the gas company based on the inspection data; and in response to the inspection completion rate not meeting the preset progress conditions, the government gas supervision and management platform sends an inspection progress warning to the smart gas management platform based on the inspection completion rate, and adjusts the data acquisition frequency and data storage and cleaning cycle of the gas company based on the inspection completion rate, and cleans the gas data in the memory based on the data storage and cleaning cycle.

[0007] The invention content includes a government-regulated smart gas household inspection Internet of Things system, the system includes a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, a smart gas equipment object platform, a smart gas inspection personnel object platform, a government gas supervision object platform, a government gas supervision sensor network platform, a government gas supervision management platform, a government gas supervision service platform, and a citizen user platform that interact in sequence. The government-regulated smart gas household inspection Internet of Things system is configured to perform the following operations: obtain gas usage data of at least one gas user in the inspection area through the smart gas equipment object platform; for a gas user, the smart gas management platform determines a candidate inspection time period for the gas user based on the gas usage data of the gas user; the smart gas management platform determines inspection parameters based on the candidate inspection time period and inspection resource information of the at least one gas user, and the inspection parameters include inspection of the at least one gas user Inspection time period and inspection resource configuration for household inspection; the smart gas management platform sends the inspection parameters to the government gas supervision and management platform and the smart gas user platform, and generates inspection instructions and sends them to the smart gas inspection personnel object platform, so that the inspection personnel can conduct household inspections based on the inspection instructions, and the smart gas inspection personnel object platform is configured as the inspection terminal of the inspection personnel; the government gas supervision and management platform obtains the inspection data of the gas company according to the inspection supervision frequency based on the inspection area and the inspection parameters of the gas company, and determines the inspection completion rate of the gas company based on the inspection data; and in response to the inspection completion rate not meeting the preset progress conditions, the government gas supervision and management platform sends an inspection progress warning to the smart gas management platform based on the inspection completion rate, and adjusts the data acquisition frequency and data storage and cleaning cycle of the gas company based on the inspection completion rate, and cleans the gas data in the memory based on the data storage and cleaning cycle.

[0008] The invention content includes a computer-readable storage medium, which stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the government-regulated smart gas household inspection method.

[0009] The beneficial effects brought about by the above invention include but are not limited to: (1) By determining the inspection instructions based on the gas usage data of the gas user and conducting home inspections based on the inspection instructions, the problems of low inspection efficiency and low inspection completion rate caused by blind inspections can be avoided, thereby improving the inspection efficiency and inspection completion rate and reducing the inspection cost. (2) By determining the inspection probabilities of different time periods, the candidate inspection time periods can be selected for inspections, and the time periods with higher inspection probabilities can be selected for inspections, thereby optimizing the allocation of inspection resources and improving inspection efficiency. (3) By predicting gas hazards for gas users to be inspected and adjusting the inspection parameters to prioritize inspections, gas users with higher gas hazards can be inspected and checked in a timely and effective manner, thereby avoiding gas safety problems caused by untimely inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present invention 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:

[0011] Figure 1 2 is a schematic diagram of the platform structure of a government-regulated smart gas household inspection Internet of Things system according to some embodiments of the present invention;

[0012] Figure 2 is an exemplary flow chart of government-regulated smart gas household inspection according to some embodiments of the present invention;

[0013] Figure 3 is an exemplary flow chart of determining candidate inspection time periods according to some embodiments of the present invention;

[0014] Figure 4 is an exemplary flow chart of determining inspection parameters according to some embodiments of the present invention;

[0015] Figure 5 It is a schematic diagram of a process for determining key gas users for inspection based on a hidden danger model according to some embodiments of the present invention. DETAILED DESCRIPTION

[0016] The following is a brief introduction to the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0017] 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.

[0018] 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.

[0019] When the operations performed in the embodiments of the present invention are described in steps, unless otherwise specified, the order of the steps is interchangeable, steps may be omitted, and other steps may be included in the operation process.

[0020] Figure 1 1 is a schematic diagram of the platform structure of the government-regulated smart gas household inspection IoT system according to some embodiments of the present invention. The government-regulated smart gas household inspection IoT system involved in the present invention will be described in detail below. It should be noted that the following embodiments are only used to explain the present invention and do not constitute a limitation of the present invention.

[0021] In some embodiments, Figure 1 As shown, the government-regulated smart gas household inspection IoT system 100 may include a smart gas user platform 110, a smart gas service platform 120, a smart gas management platform 130, a smart gas sensor network platform 140, a smart gas equipment object platform 151, a smart gas inspection personnel object platform 152, a government gas supervision object platform 1000, a government gas supervision sensor network platform 190, a government gas supervision management platform 180, a government gas supervision service platform 170 and a citizen user platform 160 that interact in sequence.

[0022] The smart gas user platform 110 may be a platform for interacting with a user. In some embodiments, the smart gas user platform 110 may be configured as a terminal device.

[0023] The smart gas user platform 110 refers to a platform that provides gas users with gas usage related data and gas problem solutions. Gas users refer to users who use gas, such as industrial gas users, commercial gas users, ordinary gas users, etc.

[0024] The smart gas service platform 120 is a platform for communicating user needs and control information. The smart gas service platform 120 can receive inspection parameters uploaded by the smart gas management platform 130 and upload them to the smart gas user platform 110.

[0025] The smart gas management platform 130 is a platform that coordinates and coordinates the connections and collaborations among various functional platforms, gathers all the information of the Internet of Things, and provides perception management and control management functions for the Internet of Things operation system.

[0026] In some embodiments, the smart gas management platform 130 may include a data processing center 131 and a data storage center 132 .

[0027] The data processing center 131 can be used to manage and process all operating information of the government-regulated smart gas household inspection Internet of Things system 100.

[0028] The data storage center 132 can be used to store all operation information of the government-regulated smart gas household inspection IoT system 100. In some embodiments, the data storage center 132 can be configured as a memory for storing data related to household inspections, such as inspection parameters, inspection instructions, etc.

[0029] In some embodiments, the smart gas management platform 130 can interact bidirectionally with the government gas regulatory sensor network platform 190. For example, the smart gas management platform 130 can send inspection parameters to the government gas regulatory management platform 180 based on the government gas regulatory sensor network platform 190.

[0030] The smart gas sensor network platform 140 refers to a functional platform for managing sensor communication. In some embodiments, the smart gas sensor network platform 140 can realize the functions of sensing information sensor communication and controlling information sensor communication.

[0031] The smart gas equipment object platform 151 refers to a functional platform for sensing information generation and controlling information execution. For example, the smart gas management platform 130 can obtain gas usage data of at least one gas user in the inspection area based on the smart gas equipment object platform 151. In some embodiments, the smart gas equipment object platform 151 can be configured as various gas equipment, various sensors, etc.

[0032] The smart gas inspection personnel object platform 152 refers to a platform that provides gas inspection related data to inspection personnel. In some embodiments, the smart gas inspection personnel object platform 152 can be configured as an inspection terminal for inspection personnel.

[0033] The government gas regulatory object platform 1000 refers to a functional platform for government user perception information generation and control information execution.

[0034] The government gas regulatory sensor network platform 190 refers to a functional platform for government users to manage sensor communications.

[0035] The government gas supervision and management platform 180 is a platform that coordinates the connection and collaboration between various functional platforms for government users, gathers all the information of the Internet of Things, and provides perception management and control management functions for the Internet of Things operation system.

[0036] In some embodiments, the government gas supervision management platform 180 can obtain the gas company's inspection data according to the inspection supervision frequency based on the gas company's inspection area and inspection parameters, and determine the gas company's inspection completion rate based on the inspection data.

[0037] In some embodiments, in response to the inspection completion rate not meeting the preset progress conditions, the government gas regulatory management platform 180 can send an inspection progress warning to the smart gas management platform 130 based on the inspection completion rate, and adjust the data acquisition frequency and data storage and cleaning cycle for the gas company based on the inspection completion rate, and clean up the gas data in the memory based on the data storage and cleaning cycle.

[0038] For more information about inspection personnel, inspection areas, inspection parameters, inspection instructions, inspection supervision frequency, inspection data, inspection completion rate, preset progress conditions, data acquisition frequency, and data storage and cleaning cycle, please refer to Figure 2 and its related description.

[0039] The government gas regulatory service platform 170 refers to a platform for conveying the needs and control information of government users.

[0040] The citizen user platform 160 refers to a platform for interacting with government users.

[0041] In some embodiments of the present invention, the government-regulated smart gas household inspection Internet of Things system 100 can form an information operation closed loop between various platforms, and coordinate and operate regularly under the unified management of the smart gas management platform 130, thereby realizing the informatization and intelligence of household inspections.

[0042] Figure 2 FIG. 1 is an exemplary flow chart of government-regulated smart gas household inspection according to some embodiments of the present invention. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 can be performed by a smart gas household inspection IoT system supervised by the government.

[0043] Step 210: Obtain gas usage data of at least one gas user in the inspection area through the smart gas equipment object platform.

[0044] The inspection area refers to the area where inspections are conducted on gas users.

[0045] In some embodiments, the smart gas management platform can determine the inspection area in a variety of ways. For example, the smart gas management platform can be divided based on the area of ​​different communities or streets to obtain one or more inspection areas. For another example, the smart gas management platform can also be divided based on the management area of ​​a gas subsidiary to obtain one or more inspection areas.

[0046] Gas users refer to users who consume gas. In some embodiments, gas users may include residents, businesses, and enterprises that use gas.

[0047] Gas usage data refers to recorded data reflecting gas consumption. In some embodiments, the gas usage data may include gas usage at different times. In some embodiments, the gas usage data may be represented as a gas usage graph, where the horizontal axis is time and the vertical axis is gas usage at the current time.

[0048] In some embodiments, the smart gas device object platform 151 can obtain the gas usage of the gas user through the corresponding gas equipment (for example, a gas flow meter), and send it to the smart gas management platform via the smart gas sensor network platform 140, thereby determining the gas usage data.

[0049] Step 220: For a gas user, the smart gas management platform determines a candidate inspection period for the gas user based on the gas usage data of the gas user.

[0050] The candidate inspection period refers to the candidate time period for inspecting the gas-related facilities of the gas users.

[0051] In some embodiments, the smart gas management platform can determine the candidate inspection time periods in a variety of ways. For example, the smart gas management platform can determine the gas user's recent gas usage time period based on the gas user's gas usage data, filter out the time period in which gas consumption occurs in the same time period for multiple consecutive days, and determine the filtered time period as the candidate inspection time period. For another example, the smart gas management platform can send the gas user's recent gas usage time period to the gas user via the smart gas user platform, obtain the gas usage time period fed back by the gas user and determine it as the candidate inspection time period. For another example, the smart gas management platform can also directly obtain the time period uploaded by the gas user and determine it as the candidate inspection time period.

[0052] In some embodiments, the smart gas management platform can also determine the gas time characteristics of gas users based on gas usage data; determine the probability of gas users being inspectable at different time periods based on the gas time characteristics; and determine candidate inspection time periods based on the inspection probability. For more information about this section, please refer to Figure 3 and related instructions.

[0053] Step 230: The smart gas management platform determines inspection parameters based on candidate inspection time periods and inspection resource information of at least one gas user.

[0054] Inspection resource information refers to information that can reflect the availability of inspection resources at different time periods. In some embodiments, inspection resources may include inspection personnel and inspection equipment. Among them, inspection personnel refer to relevant personnel who conduct gas household inspections, and inspection equipment refers to equipment used for gas household inspections. For example, pipeline air tightness detectors, gas concentration detectors, etc.

[0055] In some embodiments, the inspection resource information may be represented as the number of inspection personnel that can be dispatched within the inspection area, the available time periods for the inspection personnel, the number of inspection equipment, and the available time periods for the inspection equipment.

[0056] In some embodiments, the smart gas management platform can obtain the inspection personnel schedule and the inspection equipment schedule in the inspection area through the data storage center 132. The inspection personnel / equipment schedule stores the time periods during which each inspection personnel / equipment can perform inspections and the time periods occupied by scheduled inspection operations. The smart gas management platform can determine the idle time periods of each inspection personnel / equipment in the current inspection area based on the inspection personnel / equipment schedule, thereby determining the required inspection resource information.

[0057] Inspection parameters refer to parameter instructions used to guide inspection personnel to conduct inspections. In some embodiments, inspection parameters may include inspection time periods and inspection resource configurations for conducting home inspections on at least one gas user. Inspection resource configurations refer to the number of inspection personnel and inspection equipment required for inspections.

[0058] In some embodiments, the smart gas management platform can determine the maximum number of households that can be inspected in the current time period based on the inspection resource information. Determine the number of gas users that can be inspected in the current time period based on the candidate inspection time periods corresponding to the gas users. If the number of gas users that can be inspected in the current time period is greater than the maximum number of households, the smart gas management platform can sort the gas users from small to large based on the distance between the gas users and the inspection personnel, select the gas users with the largest number of households at the top of the sort, and determine them as the gas users to be inspected in the current time period. If the number of gas users that can be inspected is less than or equal to the maximum number of households, the smart gas management platform can directly determine the number of gas users that can be inspected in the current time period as the gas users to be inspected.

[0059] In some embodiments, if the number of gas users that can be inspected in the current period is less than or equal to the maximum number of households, the smart gas management platform can appropriately reduce the corresponding inspection resource configuration to improve the utilization of inspection personnel and inspection equipment. The corresponding relationship between the inspection resource information and the maximum number of households can be preset based on prior experience.

[0060] For example, if the maximum number of households in the current time period is 20, but the number of gas users that can be inspected in the current time period is 30. At this time, the smart gas management platform can give priority to the 20 gas users closest to the inspectors for inspection. The remaining 10 gas users are inspected in other candidate inspection time periods. If the maximum number of households in the current time period is 20, but the number of gas users that can be inspected in the current time period is 10. At this time, the smart gas management platform can appropriately reduce the inspection resource configuration at the current moment and only inspect these 10 gas users.

[0061] In some embodiments, the smart gas management platform can also respond to at least one gas hazard of the inspected gas users meeting the preset hazard condition, and for a gas hazard, predict the gas users to be inspected that have the gas hazard, so as to determine the key gas users to be inspected; and determine the inspection parameters of the subsequent inspection process based on the key gas users to be inspected corresponding to the at least one gas hazard. For more information about this part, please refer to Figure 4 and related instructions.

[0062] In some embodiments, when determining the inspection parameters, the smart gas management platform can determine the maximum number of households that can be inspected in the current time period based on the inspection resource information. Based on the candidate inspection time periods corresponding to the gas users, determine the number of gas users that can be inspected in the current time period. If the number of gas users that can be inspected in the current time period is greater than the maximum number of gas users, the smart gas management platform can sort the gas users from large to small based on the preferred value or comprehensive value, select the gas users with the largest number of households at the top of the ranking, and determine them as the gas users to be inspected in the current time period. If the number of gas users that can be inspected is less than or equal to the maximum number of households, the smart gas management platform 0 can directly determine the number of gas users that can be inspected in the current time period as the gas users to be inspected. Among them, the comprehensive value refers to an indicator that can comprehensively reflect the distance between the gas user and the inspection personnel, as well as the preferred value. For example, the comprehensive value can be a value determined by weighting the distance between the gas user and the inspection personnel and the preferred value, and the comprehensive value is inversely proportional to the above distance and directly proportional to the preferred value.

[0063] In some embodiments of the present invention, by determining the preferred value of the candidate inspection time period and further determining the inspection parameters, it can effectively ensure that relevant work can be carried out in a timely manner after the on-site inspection, reduce unnecessary waiting time in the inspection operation, and improve the inspection efficiency.

[0064] In step 240, the smart gas management platform sends the inspection parameters to the government gas supervision management platform and the smart gas user platform, and generates inspection instructions and sends them to the smart gas inspection personnel object platform, so that the inspection personnel can conduct home inspections based on the inspection instructions.

[0065] In some embodiments, the smart gas management platform can send inspection parameters to the smart gas user platform via the smart gas company service platform, and inform gas users of the home inspection period in advance to avoid home inspection failures or delays caused by gas users being out or using gas.

[0066] Inspection instructions refer to instructions for inspection personnel to perform inspection operations. In some embodiments, the inspection instructions may include gas users to be inspected, corresponding inspection time periods, the number of inspection personnel to be dispatched, and the number of inspection equipment.

[0067] In some embodiments, the smart gas management platform can determine the information included in the inspection parameters, such as the gas users to be inspected, the corresponding inspection time period, the number of inspection personnel, and the number of inspection equipment, as inspection instructions.

[0068] Step 250, the government gas supervision management platform obtains the gas company's inspection data according to the inspection supervision frequency based on the gas company's inspection area and inspection parameters, and determines the gas company's inspection completion rate based on the inspection data.

[0069] The inspection supervision frequency refers to the frequency at which the government gas supervision and management platform 180 supervises and manages the inspection progress of the gas company. In some embodiments, the inspection supervision frequency can be determined based on prior experience. Since the inspection progress of different gas companies is inconsistent, for gas companies with slower inspection progress, the government gas supervision and management platform 180 can supervise and assist accordingly, and appropriately increase the inspection supervision frequency to ensure that the gas companies with slower inspection progress can complete the inspection in time.

[0070] Inspection data refers to the data results obtained after the inspection is completed. In some embodiments, the inspection data may include inspection results, actual inspection time, and inspection delay time.

[0071] The inspection completion rate can reflect the numerical value of the progress of the household inspection completion at the current time point. In some embodiments, the inspection completion rate can be expressed as the ratio of the number of gas users that have been inspected to the number of all gas users that need to be inspected at the current time point. In some embodiments, the smart gas management platform can obtain the number of gas users that have been inspected and the number of all gas users that need to be inspected, and divide the number of gas users that have been inspected by the number of all gas users that need to be inspected to obtain the value obtained as the inspection completion rate. It can be understood that in the process of the government gas supervision management platform 180 obtaining the inspection data of the gas company according to the inspection supervision frequency, each time the inspection data of the gas company is obtained, an inspection completion rate can be determined, and the inspection completion rate can be dynamically changed.

[0072] Step 260, in response to the inspection completion rate not meeting the preset progress conditions, the government gas regulatory management platform sends an inspection progress warning to the smart gas management platform based on the inspection completion rate, and adjusts the data acquisition frequency and data storage and cleaning cycle for the gas company based on the inspection completion rate, and cleans the gas data in the storage based on the data storage and cleaning cycle.

[0073] The preset progress condition refers to a judgment condition for judging whether the inspection completion rate of the gas company is qualified at the current time point. In some embodiments, the preset progress condition may be that the inspection completion rate is greater than the minimum inspection completion rate at the current time point.

[0074] In some embodiments, the minimum inspection completion rate corresponding to different time points may be negatively correlated to the remaining inspection time. The remaining inspection time refers to the time from the current date to the inspection deadline. The corresponding relationship between the minimum inspection completion rate and the remaining inspection time may be determined based on actual conditions.

[0075] For example, for a monthly gas on-site inspection, when there are 20 days, 15 days, and 10 days left before the inspection deadline, the minimum inspection completion rate may be 33%, 50%, and 66%, respectively.

[0076] Inspection progress warning refers to the warning information issued when the inspection progress is at risk of being overdue. In some embodiments, when the smart gas management platform receives the inspection progress warning, it can appropriately increase the number of inspection personnel and inspection equipment to urge the gas company to advance the inspection progress.

[0077] The data acquisition frequency refers to the frequency of acquiring gas usage data. In some embodiments, the data acquisition frequency may be related to the difference between the inspection completion rate at the current time point and the minimum inspection completion rate. For example, the data acquisition frequency may be negatively correlated to the difference between the inspection completion rate at the current time point and the minimum inspection completion rate. The greater the difference between the inspection completion rate at the current time point and the minimum inspection completion rate, the more it is necessary to grasp the current inspection progress in a timely manner to urge the gas company to advance in a timely manner. At this time, the data acquisition frequency can be appropriately increased. When the difference is smaller, the data acquisition frequency can be appropriately reduced to reduce the computing pressure of the server.

[0078] The data storage cleaning cycle refers to the period during which the data storage center 132 cleans up historical data. In order to ensure that the data storage center 132 has sufficient storage space, it is necessary to clean up the relatively old historical gas usage data. In some embodiments, when the number of inspection progress warnings within a preset time range exceeds the warning number threshold, the smart gas management platform can appropriately extend the data storage cleaning cycle to ensure that when problems occur during the inspection process and historical gas usage data needs to be queried, accurate traceability can be performed.

[0079] In some embodiments of the present invention, inspection instructions are determined based on the gas usage data of gas users, and household inspections are performed based on the inspection instructions. This can avoid the problems of low inspection efficiency and low inspection completion rate due to blind inspections, thereby improving the inspection efficiency and inspection completion rate and reducing inspection costs.

[0080] Figure 3 FIG. 1 is an exemplary flow chart of determining candidate inspection time periods according to some embodiments of the present invention. Figure 3 As shown, process 300 includes the following steps. In some embodiments, process 300 can be executed by a smart gas household inspection IoT system supervised by the government.

[0081] Step 310, determining the gas time characteristics of the gas user based on the gas usage data.

[0082] The gas time characteristics refer to the characteristics of the gas consumption of the gas user over time. For example, the gas time characteristics may be the gas consumption and gas usage duration at different time periods on the same day, and / or the gas consumption and gas usage duration at the same time period for multiple consecutive days.

[0083] In some embodiments, the smart gas management platform divides a day into different time periods, and records and counts the gas usage and gas usage duration for multiple consecutive days according to different time periods, calculates the gas usage and gas usage duration in different time periods of the same day, and / or the gas usage and gas usage duration in the same time period for multiple consecutive days, and determines the gas time characteristics.

[0084] Step 320, based on the gas time characteristics, determine the probability of gas users being inspectable in different time periods.

[0085] The probability of home inspection refers to the probability of home inspection within the preset time period. The preset time period refers to the preset time periods of the day. Since home inspection within the preset time period requires the user to be at home, home inspection cannot be performed if the user is not at home. The probability of home inspection within the preset time period refers to the probability that the user is at home during the time period.

[0086] Different time periods refer to different time periods in a day. For example, different time periods may be 8:00 to 10:00, 11:00 to 13:00, 17:00 to 19:00, 20:00 to 22:00, etc. In some embodiments, different time periods may be preset, and different time periods may include multiple time periods to be evaluated. For more information about the time periods to be evaluated, please refer to the following and related descriptions.

[0087] In some embodiments, the smart gas management platform can calculate the gas usage and gas usage duration for multiple consecutive days in the same period of time for different periods of a day based on the gas time characteristics, and use the proportion of the number of days in which the gas usage in this period exceeds the preset gas usage and the gas usage duration exceeds the preset gas usage duration to the total number of days as the probability of patrollability in this period. In some embodiments, the preset gas usage and the preset gas usage duration can be preset. For example, the smart gas management platform can calculate the gas usage and gas usage duration between 5 pm and 7 pm every day for 10 consecutive days. The number of days in this period that the gas usage exceeds the preset gas usage and the gas usage duration exceeds the preset gas usage duration is 8 days, then the proportion of the above days to the total number of days is 0.8, and the probability of patrollability in this period is 0.8.

[0088] Since the gas usage during this period exceeds the preset gas usage and the gas usage duration exceeds the preset gas usage duration on most days, it means that users basically use gas during this period and are naturally at home, so the probability of inspection is relatively high.

[0089] In some embodiments, the smart gas management platform can determine at least one time period to be evaluated based on the gas time characteristics; for a time period to be evaluated, the inspectability probability of the time period to be evaluated can be determined through an inspectability evaluation model based on the time period to be evaluated, gas user characteristics and gas time characteristics.

[0090] The period to be evaluated refers to the period that needs to be evaluated to see whether it can be used as a candidate inspection period. In some embodiments, the smart gas management platform can use the period with gas usage as the period to be evaluated based on the gas time characteristics. In some embodiments, the duration of each period to be evaluated can be preset. For example, it can be preset based on the duration required for the inspection.

[0091] Gas user characteristics refer to characteristic data related to gas users. For example, gas user characteristics may include the number of people in the gas user's home, age structure, etc. In some embodiments, gas user characteristics may be obtained based on a government platform. It should be noted that the smart gas management platform only obtains the number of people and age structure, and does not involve privacy information.

[0092] The inspectability evaluation model refers to a model that can predict the inspectability probability of the time period to be evaluated. In some embodiments, the inspectability evaluation model can be a machine learning model, such as a deep neural network (Deep-Learning Neural Network, DNN).

[0093] The input of the inspectability assessment model may include gas user characteristics, the time period to be assessed, and gas time characteristics, and the output may include the probability of the gas user being inspectable during the time period to be assessed. For example, the input of the inspectability assessment model may be [a, b, c, d, e], where a represents the number of people in the gas user's home, b represents the age structure, c represents the time period to be assessed, d represents the gas usage, and e represents the duration of gas use.

[0094] In some embodiments, the smart gas management platform can obtain multiple first training samples and first labels, the first training samples include the sample time period to be evaluated, the sample gas user characteristics and the sample gas time characteristics, and the first label is the sample inspectability probability corresponding to the first training sample; based on the multiple first training samples and the first labels, multiple rounds of iterations are performed to train the initial inspectability evaluation model; and the inspectability evaluation model is obtained until the trained inspectability evaluation model meets the preset conditions. Among them, at least one round of iteration includes: selecting one or more first training samples, inputting one or more first training samples into the initial inspectability evaluation model, and obtaining the output of the initial inspectability evaluation model corresponding to one or more first training samples; according to the output of the initial inspectability evaluation model corresponding to one or more first training samples, and the first labels corresponding to one or more first training samples, substitute them into the formula of a predefined loss function to calculate the value of the loss function; according to the value of the loss function, reversely update the model parameters in the initial inspectability evaluation model, and the reverse update can be performed by various methods. For example, it can be updated based on the gradient descent method.

[0095] In some embodiments, the preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc. In some embodiments, the first training sample may be determined based on historical inspection records, and the first training label may be set with a 0-1 label according to whether the user is at home when knocking on the door during the inspection in the historical data. If the user is at home, it is inspectable and the label is 1, otherwise, the label is 0.

[0096] In some embodiments of the present invention, the smart gas management platform determines the inspectability probability of the time period to be evaluated based on the time period to be evaluated, gas user characteristics and gas time characteristics through an inspectability evaluation model, and can efficiently and accurately determine the inspectability probability of the time period to be evaluated.

[0097] In some embodiments, the input of the inspectability assessment model may also include the gas demand level of the gas users in the period to be assessed.

[0098] The degree of gas demand refers to the degree to which the user needs to use gas during the period to be evaluated. If the degree of gas demand is high, it means that the user is likely to be unable to stop using gas immediately for inspection, so the inspection cannot be carried out immediately after entering the house, and it is necessary to wait, and the probability of inspection is reduced. In some embodiments, the smart gas management platform can determine the degree of gas demand based on the gas usage and gas usage duration of the gas user during the period to be evaluated in the historical data. For example, the smart gas management platform can determine the degree of gas demand based on the gas usage and gas usage duration of the gas user during the period to be evaluated in the historical data through the second preset table. Among them, the second preset table may include the correspondence between the degree of gas demand and the gas usage and gas usage duration of the gas user during the period to be evaluated. In some embodiments, the higher the gas usage and the longer the gas usage duration corresponding to the period to be evaluated in the historical data, the higher the degree of gas demand.

[0099] In some embodiments, the smart gas management platform can adjust the first label according to the waiting inspection time during the home inspection in the historical inspection records to determine the second label; and train the initial inspectability assessment model based on multiple first training samples and second labels. If after entering the house, the user is using gas and cannot be inspected immediately, the first label needs to be adjusted according to the waiting inspection time.

[0100] In some embodiments, the smart gas management platform can proportionally reduce the value of the first tag according to the waiting time during the home inspection. For example, if the home inspection starts after waiting for 5 minutes, the first tag is adjusted from 1 to 0.9; if the home inspection starts after waiting for 10 minutes, the first tag is adjusted to 0.8.

[0101] The waiting time for inspection refers to the time the inspector waits to start the inspection after entering the user's home.

[0102] In some embodiments, when the input of the inspectability assessment model may also include the gas demand level of the gas user in the period to be assessed, the first training sample may also include the sample gas demand level. For more information about training the initial inspectability assessment model based on multiple first training samples and second labels, please refer to the relevant description of training the initial inspectability assessment model.

[0103] By inputting the gas demand level in the time period to be evaluated into the inspectability evaluation model, the impact of the user's gas usage time on the inspection can be considered, making the predicted inspectability probability more accurate.

[0104] Step 330: Determine candidate inspection time periods based on the inspection probability.

[0105] In some embodiments, the smart gas management platform may use the time period when the probability of inspection exceeds the probability threshold as a candidate inspection time period, wherein the probability threshold may be preset according to demand.

[0106] By determining the probability of inspection at different time periods, candidate inspection time periods can be selected, and inspections can be performed during time periods with higher inspection probabilities, thereby optimizing the allocation of inspection resources and improving inspection efficiency.

[0107] The embodiments of the present invention are only for illustration and description, and do not limit the applicable scope of the present invention. For those skilled in the art, various modifications and changes that can be made under the guidance of the present invention are still within the scope of the present invention.

[0108] Figure 4 FIG. 1 is an exemplary flow chart of determining inspection parameters according to some embodiments of the present invention. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 can be executed by a smart gas household inspection IoT system supervised by the government.

[0109] Step 410: Generate at least one set of inspection parameters to be optimized based on candidate inspection time periods and inspection resource information of at least one gas user.

[0110] The inspection parameters to be optimized refer to the generated inspection parameters that have not yet been optimized by iterative optimization or other optimization operations.

[0111] In some embodiments, the smart gas management platform can generate inspection parameters to be optimized in a variety of ways. For example, the smart gas management platform can determine the maximum number of households that can be inspected in different time periods based on the inspection resource information, and determine the number of gas users that can be inspected in different time periods based on the candidate inspection time periods of different gas users. If the number of gas users that can be inspected is less than or equal to the maximum number of households that can be inspected, all gas users that can be inspected in that time period are determined as gas users to be inspected. If the number of gas users that can be inspected is greater than the maximum number of households that can be inspected, the smart gas management platform can randomly select a coordinate from the inspection area as the center coordinate, sort the other gas users from near to far according to their distance from the center coordinate, and select the gas users with the maximum number of households that can be inspected that are ranked at the top, and determine them as the gas users to be inspected in that time period. The smart gas management platform can repeat the above steps to obtain at least one set of inspection parameters to be optimized.

[0112] Step 420: based on the inspection cost of at least one set of inspection parameters to be optimized, iteratively optimize at least one set of inspection parameters to be optimized until an iteration condition is met, thereby obtaining inspection parameters.

[0113] The inspection cost may reflect the cost consumed in the inspection task. In some embodiments, the inspection cost may include at least one of the inspection resource cost and the inspection time cost. Among them, the inspection resource cost may include the number of inspection personnel and the number of inspection equipment required for the inspection. The inspection time cost may include the actual time consumed for the inspection.

[0114] In some embodiments, the smart gas management platform can determine the inspection cost of the inspection parameters to be optimized in a variety of ways. For example, the smart gas management platform can obtain the historical inspection efficiency of each inspection personnel and the historical inspection efficiency of each inspection equipment based on the data storage center 132, determine the number of inspection personnel and the number of inspection equipment required for the inspection based on the inspection parameters to be optimized, and determine the corresponding inspection time cost by querying the second preset relationship table based on the historical inspection efficiency of each inspection personnel, the historical inspection efficiency of each inspection equipment, the number of inspection personnel and the number of inspection equipment required for the inspection.

[0115] The third preset table may include the historical inspection efficiency of the inspection personnel, the historical inspection efficiency of each inspection device, the number of inspection personnel required for inspection, and the corresponding relationship between the number of inspection devices and the inspection time cost. The third preset table may be constructed based on a large amount of historical data. For example, the corresponding relationship may be that the inspection time cost is negatively correlated with the historical inspection efficiency of each inspection personnel, the historical inspection efficiency of each inspection device, the number of inspection personnel required for inspection, and the number of inspection devices.

[0116] In some embodiments, for a set of inspection parameters to be optimized, the smart gas management platform can also plan at least one inspection route based on the inspection time periods, inspection resource information, and gas user locations of different gas users in the inspection parameters to be optimized; and determine the inspection time cost based on at least one inspection route, gas user location, and inspection reference duration.

[0117] The inspection route refers to the mobile route that the inspection personnel use for on-site inspections. In some embodiments, the smart gas management platform can group the inspection personnel and inspection equipment according to the inspection resource information to obtain several inspection teams, and each inspection team can complete the inspection task independently according to the inspection route.

[0118] In some embodiments, the smart gas management platform can group the inspection personnel and inspection equipment in the inspection area to obtain several inspection teams. Among them, the inspection team is the smallest inspection unit that can conduct independent inspections. The smart gas management platform can determine the maximum number of groups that can be grouped for the inspection team based on the inspection resource information, the minimum number of inspection personnel for each inspection team, and the minimum number of inspection equipment. The above maximum number of groups that can be grouped is determined as the number of groups of the inspection team. Among them, the minimum number of inspection personnel and the minimum number of inspection equipment for each inspection team can be determined based on prior experience.

[0119] In some embodiments, the smart gas management platform can divide the gas users with the same candidate inspection period according to their locations to obtain gas groups containing a number of gas users with the same number of groups as the inspection group. The grouping method may include grid division, street division, etc.

[0120] In some embodiments, the gas group corresponds to the inspection group one by one. The smart gas management platform can determine the inspection group closest to the gas group that has not yet been assigned a gas group as the corresponding inspection group.

[0121] In some embodiments, the smart gas management platform can construct a gas user vector corresponding to the gas user. For example, the elements of the gas user vector may include the location coordinates of the gas user and the candidate inspection period. For example, if the location coordinates of the gas user are A and the candidate inspection period is B, the corresponding gas user vector is [A, B].

[0122] The smart gas management platform can cluster gas user vectors through a clustering algorithm to obtain a number of clusters. Each cluster contains several gas user vectors corresponding to gas users. Among them, in order to ensure that the number of gas users contained in each cluster is relatively close, the variance of the number of vectors contained in different clusters should be less than the preset variance threshold. There can be many types of clustering algorithms. For example, clustering algorithms can include K-Means clustering, density-based clustering method (DBSCAN), etc. There is no restriction on the type of clustering algorithm.

[0123] In some embodiments, the smart gas management platform may determine the clusters obtained after clustering as gas groups, thereby obtaining a grouping number of gas groups.

[0124] In some embodiments, the smart gas management platform can be based on A The inspection route of each inspection team relative to the corresponding gas team is determined by using a method such as a Dijkstra algorithm. There is no restriction on the type of inspection route determination algorithm.

[0125] The reference inspection time refers to the estimated theoretical time required for a home inspection.

[0126] In some embodiments, the smart gas management platform can determine the inspection reference duration in a variety of ways. The smart gas management platform can obtain several groups of historical inspection actual durations based on historical data, and determine the statistical value of the historical inspection actual duration as the inspection reference duration. The statistical value may include a mean, a median, etc.

[0127] In some embodiments, the smart gas management platform can also determine the inspection delay risk based on the probability of at least one gas user being inspectable during the candidate inspection period. Based on the inspection delay risk, determine the duration tolerance coefficient; and based on the duration tolerance coefficient, adjust the initial inspection reference duration to determine the inspection reference duration.

[0128] Inspection delay risk refers to the probability that the inspection duration during home inspection exceeds the inspection reference duration. In some embodiments, the smart gas management platform can determine the inspection delay risk based on the inspection probability. In some embodiments, the inspection delay risk is negatively correlated with the inspection probability. The smart gas management platform can construct a corresponding relationship between the inspection delay risk and the inspection probability based on prior experience.

[0129] In some embodiments, the inspection delay risk can be calculated by the following formula (1):

[0130] (1)

[0131] in, Indicates the risk of inspection delay. represents the probability of inspection, is the coefficient. It can be set based on experience or by system default.

[0132] The duration tolerance coefficient refers to a coefficient used to adjust the reference duration of the initial inspection. In some embodiments, the smart gas management platform can determine the duration tolerance coefficient based on the inspection delay risk.

[0133] In some embodiments, the duration tolerance coefficient may be positively correlated with the inspection delay risk. The greater the inspection delay risk, the greater the possibility of delay in the current inspection step, and the longer inspection time needs to be arranged, so the duration tolerance coefficient may be appropriately increased.

[0134] In some embodiments, the duration tolerance coefficient can be calculated using the following formula (2):

[0135] (2)

[0136] in, Represents the duration tolerance coefficient, Indicates the risk of inspection delay. is the coefficient. It can be set based on experience or by system default.

[0137] In some embodiments, the smart gas management platform can adjust the initial inspection reference duration based on the duration tolerance coefficient to determine the inspection reference duration.

[0138] The initial inspection reference duration refers to the inspection reference duration in the initial state that has not been adjusted. In some embodiments, the initial inspection reference duration may be an inspection reference duration determined based on the statistics of the actual time consumed by historical inspections.

[0139] In some embodiments, the inspection reference duration may be positively correlated to the initial inspection reference duration and the duration fault tolerance coefficient. The longer the initial inspection reference duration and the greater the duration fault tolerance coefficient, the longer the inspection reference duration.

[0140] In some embodiments, the inspection reference duration can be calculated using the following formula (3):

[0141] (3)

[0142] in, Indicates the inspection reference duration. Represents the duration tolerance coefficient, Indicates the reference duration of the initial inspection. is the coefficient. It can be set based on experience or by system default.

[0143] In some embodiments of the present invention, the initial inspection reference duration is dynamically adjusted through the time tolerance coefficient to ensure that the inspection personnel can complete the inspection within the inspection reference duration, thereby avoiding the problem of delaying subsequent inspection steps due to insufficient inspection time and improving the inspection efficiency and success rate.

[0144] In some embodiments, the smart gas management platform can determine the inspection time cost based on at least one inspection route, the location of the gas user, and the inspection reference time. For example, for an inspection team, the smart gas management platform can determine the traffic distance based on the initial location of the inspection team, the inspection route, and the location of the gas user, and query the preset traffic speed table based on the traffic distance to determine the traffic time for the inspection team to visit all gas users included in the corresponding gas team. Add the traffic time to the inspection reference time, and determine the result of the addition as the estimated inspection time of the group. Calculate the estimated inspection time of all inspection teams, and determine the result with the longest estimated inspection time as the inspection time cost of the group of inspection parameters to be optimized. Among them, the traffic speed table contains the estimated speed of the inspection personnel when using different modes of transportation (for example, bus, subway, walking).

[0145] In some embodiments of the present invention, when the inspection parameters to be optimized are unreasonable, the inspection personnel often need to travel back and forth between gas users that are far apart during the on-site inspection process, resulting in unnecessary waste of time. Therefore, when determining the inspection time cost of the inspection parameters to be optimized, the impact of the inspection route must also be considered comprehensively to ensure that the inspection parameters to be optimized can meet the actual needs of the inspection personnel.

[0146] Iterative optimization refers to the process of optimizing the inspection parameters to be optimized. In some embodiments, the inspection resource cost can interact with the inspection time cost. For example, when the number of inspection personnel and the number of inspection equipment in the inspection resource cost are increased, the number of gas users that can be inspected per unit time will also increase, thereby reducing the time required to complete the inspection and reducing the inspection time cost. When the number of inspection personnel and the number of inspection equipment in the inspection resource cost are reduced, the number of gas users that can be inspected per unit time will also decrease, thereby increasing the time required to complete the inspection and increasing the inspection time cost.

[0147] In some embodiments, in order to reduce the waste of manpower and material resources, while ensuring that the inspection can be completed within the inspection period, the inspection resource cost should be reduced as much as possible.

[0148] In some embodiments, the smart gas management platform can use the inspection parameters to be optimized that have not yet been iteratively optimized as parent parameters. During iteration, the smart gas management platform can perform crossover, mutation and other operations on the parent parameters based on the inspection time cost of the inspection parameters to be optimized, under the constraints of candidate household inspection time periods, and available inspection personnel and equipment in different time periods, to obtain child parameters.

[0149] Crossover refers to the operation of selecting two parent parameters for exchange and combination to obtain child parameters with excellent characteristics. In some embodiments, the smart gas management platform can select two initial inspection parameters to be optimized from a number of initial inspection parameters to be optimized as parent parameters and cross them to generate new inspection parameters to be optimized as child parameters. Among them, the crossover probability refers to the probability of two individuals crossing over. Exemplarily, the crossover probability can be determined based on prior experience. In some embodiments, the types of crossovers can also include: single-point crossover, multi-point crossover, uniform crossover and other one or more crossover methods.

[0150] Mutation refers to the operation of changing the data of the offspring. In some embodiments, the smart gas management platform can mutate the inspection parameters to be optimized as offspring parameters according to the mutation probability, and change the data of the inspection parameters to be optimized. Among them, the mutation probability can be determined based on prior experience. In some embodiments, the types of mutations can also include: basic bit mutation, uniform mutation, non-uniform mutation and other one or more crossover methods.

[0151] In some embodiments, after obtaining the child parameters, the smart gas management platform can determine whether the child parameters meet the iteration conditions. If the iteration conditions are met, the child parameters that meet the iteration conditions are determined as inspection parameters. If the iteration conditions are not met, the child parameters of the current iteration are determined as the parent parameters of the next iteration and iterated until the iteration conditions are met.

[0152] The iteration condition refers to the judgment condition for determining whether the iteration is terminated. In some embodiments, the iteration condition can be any one of the following: the inspection time cost meets the inspection deadline, and the number of iterations reaches the iteration number threshold, the inspection resource cost drops to a preset expected value, or the inspection resource cost difference between two iterations is lower than a preset difference threshold. Among them, the iteration number threshold, the preset expected value, the preset number of iterations, and the preset difference threshold can be set according to various methods such as manual experience and historical data.

[0153] In some embodiments of the present invention, since all inspection parameters to be optimized are listed by permutation and combination, the number is usually large, and then calculating the inspection costs of a large number of inspection parameters to be inspected will consume a lot of computing power and corresponding time costs. By iterating the inspection parameters to be optimized, the inspection parameters that meet the iteration requirements are finally determined. A balance can be maintained between inspection efficiency and computing power consumption, so that ideal inspection parameters can be obtained at a lower cost.

[0154] In some embodiments, during the inspection process, the smart gas management platform can dynamically adjust the inspection parameters through steps 430-440.

[0155] Step 430, during the inspection process, in response to at least one gas hazard of the inspected gas users satisfying a preset hazard condition, for one gas hazard, predicting gas users to be inspected that have gas hazards, so as to determine key gas users to be inspected.

[0156] Gas hazards refer to safety hazards related to gas discovered during home inspections. Gas hazards may include multiple types, such as low gas pressure, high gas pressure, gas leakage, gas alarm failure, etc. In some embodiments, the smart gas management platform can obtain gas hazards of gas users based on inspection data.

[0157] The preset hidden danger condition refers to the judgment condition for determining whether a certain gas hidden danger is universal. In some embodiments, the preset hidden danger condition may be: the proportion of the same gas hidden danger among the inspected gas users is higher than the preset proportion threshold. The preset proportion thresholds corresponding to different gas hidden dangers may be determined based on prior experience. The proportion of the same gas hidden danger among the inspected gas users refers to the proportion of the inspected gas users with the same gas hidden danger among all the inspected gas users in the inspection results.

[0158] Key gas users to be inspected refer to gas users to be inspected with higher priority during home inspections. In some embodiments, the smart gas management platform can determine key gas users to be inspected in a variety of ways. In some embodiments, the smart gas management platform can predict gas users to be inspected with the same gas hazards based on gas usage data and user gas characteristics to determine key gas users to be inspected.

[0159] User gas characteristics refer to indicators that can reflect the gas usage characteristics of gas users. In some embodiments, user gas characteristics may include but are not limited to the number of residents of the gas user, gas usage time period, gas equipment type, gas equipment factory batch, and gas equipment usage time. The smart gas management platform can obtain user gas characteristics based on the data storage center 132.

[0160] In some embodiments, the smart gas management platform can build a vector database based on the user gas characteristics of inspected gas users, and determine the gas users to be inspected who have the same gas hazards based on vector retrieval.

[0161] In some embodiments, for a gas user, the smart gas management platform can construct a target feature vector based on the number of residents of the gas user to be inspected, the gas usage period, the type of gas equipment, the factory batch of the gas equipment, and the length of time the gas equipment has been used. There are many ways to construct the target feature vector. For example, the target feature vector is constructed by TF-IDF (TermFrequency-Inverse Document Frequency), One-Hot, Word2Vec and other methods.

[0162] The vector database may include multiple reference vectors and corresponding historical gas hazards. Each reference vector may be constructed based on the historical number of residents of the inspected gas users, historical gas usage periods, historical gas equipment types, historical gas equipment factory batches, and historical gas equipment usage duration. The construction method of the reference vector is similar to that of the target feature vector.

[0163] In some embodiments, the smart gas management platform can determine the key gas users to be inspected based on the similarity between the target feature vector and multiple reference vectors in the vector database. For example, at least one reference vector whose similarity with the target feature vector meets the preset conditions is used as the key vector, and at least one gas user corresponding to the key vector is used as the key gas user to be inspected. The preset conditions can be set according to the situation. For example, the similarity is maximum, or the similarity is greater than a threshold, etc. For another example, the vector distance is minimum.

[0164] Step 440, based on the key gas users to be inspected corresponding to at least one gas hazard, determine the inspection parameters of the subsequent inspection process. For example, when determining the inspection route, priority can be given to on-site inspection of key gas users to be inspected, so as to eliminate the gas hazard in a timely manner. For more information on determining the inspection route, please refer to the relevant content above.

[0165] In some embodiments of the present invention, by predicting gas hazards for gas users to be inspected and adjusting inspection parameters to prioritize inspections, gas users with higher gas hazards can be inspected and checked in a timely and effective manner, thereby avoiding gas safety problems caused by untimely inspections.

[0166] Figure 5 It is a schematic diagram of a process for determining key gas users for inspection based on a hidden danger model according to some embodiments of the present invention.

[0167] In some embodiments, for a gas user to be inspected, the smart gas management platform can determine whether the gas user to be inspected has a gas hazard 560 based on the gas hazard 522, the first gas usage data 511, the first user's gas characteristics 512, the second gas usage data 551, and the second gas usage characteristics 552 through the hazard model 530, where the hazard model 530 is a machine learning model. Then, the smart gas management platform can determine the gas user to be inspected with a gas hazard as a key gas user to be inspected 570.

[0168] The hidden danger model 530 is a prediction model for determining key gas users to be inspected. In some embodiments, the hidden danger model is a machine learning model.

[0169] In some embodiments, the hidden danger model 530 may include an embedding layer 531 and a prediction layer 532. The embedding layer 531 may be a recurrent neural network (RNN) model, and the prediction layer 532 may be a DNN model.

[0170] In some embodiments, the input of the embedding layer 531 includes the first gas usage data 511, the first user gas feature 512, and the gas hidden danger 522 of the inspected gas user, and the output includes the hidden danger association feature 540. The input of the prediction layer 532 includes the hidden danger association feature 540, the second gas usage data 551, and the second gas usage feature 552, and the output includes whether the gas user to be inspected has a gas hidden danger 560.

[0171] In some embodiments, the first user gas feature 512 and the first gas usage data 511 may be input into the hidden danger model 530 in the form of feature vectors.

[0172] The feature vector 521 refers to a vector used to represent the first user gas feature 512 and the first gas usage data 511. In some embodiments, the feature vector 521 can be determined based on a preset number of sample center moments and sample origin moments of the inspected gas user's gas usage data and user gas features.

[0173] In some embodiments, the smart gas management platform can represent the first gas usage data 511 and the first user gas feature 512 of the gas hazard through the gas usage vector. Based on the gas usage vector, the sample center moment and sample origin moment of the preset number K of gas usage vectors are calculated.

[0174] In some embodiments, the preset number K of sample central moments may include sample origin moments of order 1 to order K; the preset number K of sample central moments may include sample central moments of order 1 to order K.

[0175] The sample origin moment can reflect the distance of each point in the data distribution relative to the origin.

[0176] In some embodiments, the smart gas management platform can calculate the K-order sample origin moment by the following formula (4):

[0177] (4)

[0178] in, represents the K-order sample origin moment, Represents the total number of gas usage vectors, Represents the Kth power of the ith gas usage vector.

[0179] The sample central moment can reflect the deviation of each point in the data distribution relative to the mean.

[0180] In some embodiments, the smart gas management platform can calculate the K-order sample central moment by the following formula (5):

[0181] (5)

[0182] in, represents the K-order sample central moment, Represents the total number of gas usage vectors, represents the i-th gas usage vector, Represents the mean of the gas usage vector.

[0183] In some embodiments, when the value of the preset number K is larger, the more information is included in the feature vector 521, the more representative the feature vector 521 is, and the more computing power is consumed.

[0184] In some embodiments, the preset number K may be related to the variance of the user gas characteristics of the inspected personnel who have the gas hazard. For example, the preset number K may be positively correlated to the variance of the user gas characteristics of the inspected personnel who have the gas hazard. When the variance is larger, it means that the correlation between the inspected personnel who have the gas hazard is worse, so the preset number K may be appropriately increased to increase the information contained in the feature vector 521.

[0185] In some embodiments, the smart gas management platform can concatenate a preset number K of sample central moments and sample origin moments into [(1st-order sample origin moment + 1st-order sample central moment), (2nd-order sample origin moment + 2nd-order sample central moment)...(Kth-order sample origin moment + Kth-order sample central moment)] as the feature vector 521 of the inspected personnel who have the gas hazard, and as the input of the hazard model.

[0186] In some embodiments of the present invention, by merging the gas usage data and user gas characteristics of several inspected personnel with the gas hazard into a representative feature vector, the amount of data can be reduced while retaining relevant data features, which helps to improve the calculation speed and training speed of the hazard model.

[0187] In some embodiments, the output of the embedding layer 531 can be used as the input of the prediction layer 532. The embedding layer 531 and the prediction layer 532 can be obtained through joint training.

[0188] In some embodiments, the second training sample of the joint training includes several groups of training data, each group of training data corresponds to several sample inspected gas users and one sample gas user to be inspected, each group of training data includes: sample first gas usage data, sample first user gas characteristics, sample gas hidden dangers, sample second gas usage data and sample second gas usage characteristics, and the second label corresponding to the second training sample is whether the sample gas user to be inspected has a gas hidden danger.

[0189] In some embodiments, the second training sample can be obtained based on historical inspection records, and the second label can be determined by manual annotation. For example, the smart gas management platform can randomly select several historically inspected gas users with the same gas hazards and determine them as sample inspected gas users, construct the historical gas usage data and historical gas features of the sample inspected gas users into sample first gas usage data and sample first gas usage features, and further construct a sample feature vector; construct the same gas hazards of the sample inspected gas users as sample gas hazards; randomly select a historically inspected gas user to be determined as a sample gas user to be inspected. The historical gas usage data and historical gas features of the sample gas user to be inspected are constructed as sample second gas usage data and sample second gas usage features. The smart gas management platform can repeat the above steps of randomly selecting and determining sample inspected gas users and sample inspected gas users to obtain several groups of training data.

[0190] The smart gas management platform 130 can obtain the historical gas hazards of the sample gas users to be inspected. When the historical gas hazards of the sample gas users to be inspected include the sample gas hazards, the label of whether the sample gas users to be inspected have gas hazards is 1, otherwise the above label is 0.

[0191] Exemplarily, the joint training process of the embedding layer and the prediction layer includes: inputting the sample feature vector of the inspected personnel with the gas hazard included in the second training sample and the sample gas hazard into the initial embedding layer to obtain the hazard association features output by the initial embedding layer; using the hazard association features as the input of the initial prediction layer, and inputting them into the initial prediction layer together with the sample gas usage data and sample gas usage features of the gas users to be inspected included in the second training sample, to obtain the key gas users to be inspected output by the initial prediction layer. A loss function is constructed based on the key gas users to be inspected output by the prediction layer and the second label, and the model parameters of the initial embedding layer and the prediction layer are updated. When the loss function meets the preset conditions, the training is completed, and a trained hazard model is obtained. The preset conditions may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0192] In some embodiments of the present invention, by using a hidden danger model to determine key gas users to be inspected, the data processing and analysis capabilities of the machine learning model can be effectively utilized to quickly and accurately determine the required key gas users to be inspected.

[0193] Some embodiments of the present invention provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the government-regulated smart gas household inspection method described in any one of the present invention.

[0194] Furthermore, certain features, structures or characteristics in one or more embodiments of the present invention may be appropriately combined.

[0195] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present invention are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0196] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the referenced materials of this invention and the contents of this invention, the descriptions, definitions, and / or usage of terms in this invention shall prevail.

Claims

1. A government-supervised smart gas household inspection method, characterized in that: The method is performed by a government-regulated smart gas household inspection IoT system, and includes: Obtain gas usage data of at least one gas user in the inspection area through the smart gas equipment object platform; For a gas user, the smart gas management platform determines a candidate inspection period for the gas user based on the gas usage data of the gas user, including: Based on the gas usage data, determining a gas time characteristic of the gas user; Based on the gas time characteristics, determining at least one time period to be evaluated; For a time period to be evaluated, based on the time period to be evaluated, gas user characteristics and gas time characteristics, the inspectability probability of the time period to be evaluated is determined by an inspectability evaluation model, wherein the inspectability evaluation model is a machine learning model, and the training process of the inspectability evaluation model includes: Acquire a plurality of first training samples and first labels, wherein the first training samples include a sample evaluation period, a sample gas user feature, and a sample gas time feature, and the first label is a sample inspection probability corresponding to the first training sample; Based on the plurality of first training samples and the first labels, training an initial inspectability assessment model; Acquire the inspectability assessment model until the trained inspectability assessment model meets preset conditions; Based on the inspection probability, determining the candidate inspection period; The smart gas management platform determines inspection parameters based on the candidate inspection period and inspection resource information of the at least one gas user, wherein the inspection parameters include the inspection period and inspection resource configuration for conducting home inspections on the at least one gas user; wherein the inspection resources include inspection personnel and inspection equipment; The smart gas management platform sends the inspection parameters to the government gas supervision management platform and the smart gas user platform, and generates an inspection instruction and sends it to the smart gas inspection personnel object platform, so that the inspection personnel can conduct household inspections based on the inspection instructions. The smart gas inspection personnel object platform is configured as the inspection terminal of the inspection personnel; The government gas supervision management platform obtains the inspection data of the gas company according to the inspection supervision frequency based on the inspection area and the inspection parameters of the gas company, and determines the inspection completion rate of the gas company based on the inspection data; In response to the inspection completion rate not meeting the preset progress conditions, the government gas regulatory management platform sends an inspection progress warning to the smart gas management platform based on the inspection completion rate, and adjusts the data acquisition frequency and data storage and cleaning cycle of the gas company based on the inspection completion rate, and cleans the gas data in the memory based on the data storage and cleaning cycle.

2. The method according to claim 1, characterized in that The input of the patrolability assessment model also includes the gas demand degree of the gas user in the period to be assessed, and the gas demand degree is determined based on the gas consumption and gas usage duration of the gas user in the period to be assessed in historical data; The training of the initial inspectability evaluation model based on the plurality of first training samples and the first labels comprises: According to the waiting inspection time during the home inspection in the historical inspection records, the first tag is adjusted to determine the second tag; And based on the plurality of first training samples and the second labels, an initial inspectability assessment model is trained.

3. The method according to claim 1, characterized in that The determining of inspection parameters based on the candidate inspection period and inspection resource information of the at least one gas user includes: Determine the optimal value of the candidate inspection period based on the inspection delay risk in the historical inspection records; And determining the inspection parameters based on the candidate inspection time period of the at least one gas user, the preferred value and the inspection resource information.

4. The method according to claim 1, characterized in that: The determining of inspection parameters based on the candidate inspection period and inspection resource information of the at least one gas user includes: Based on the candidate inspection period and the inspection resource information of the at least one gas user, generating at least one set of inspection parameters to be optimized; And based on the inspection cost of the at least one group of inspection parameters to be optimized, the at least one group of inspection parameters to be optimized is iteratively optimized until the iteration condition is met to obtain the inspection parameters, wherein the inspection cost includes at least one of the inspection resource cost and the inspection time cost.

5. The method according to claim 4, characterized in that The determining of inspection parameters based on the candidate inspection period and inspection resource information of the at least one gas user further includes: During the inspection process, in response to at least one gas hazard of the inspected gas user meeting the preset hazard condition, For a gas hidden danger, predict the gas users to be inspected that have the gas hidden danger, so as to determine the key gas users to be inspected; And based on the key gas users to be inspected corresponding to the at least one gas hazard, the inspection parameters of the subsequent inspection process are determined.

6. A government-regulated smart gas household inspection Internet of Things system, characterized in that: The system includes a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, a smart gas equipment object platform, a smart gas inspection personnel object platform, a government gas supervision object platform, a government gas supervision sensor network platform, a government gas supervision management platform, a government gas supervision service platform, and a citizen user platform that interact in sequence; the smart gas service platform refers to a platform for conveying user needs and control information, the smart gas service platform receives the inspection parameters uploaded by the smart gas management platform, and uploads them to the smart gas user platform; the smart gas sensor network platform refers to a functional platform for managing sensor communications, and the smart gas sensor The network platform realizes the functions of sensing information sensor communication and controlling the information sensor communication; the government gas supervision object platform refers to the functional platform for the government user to generate the sensing information and execute the control information; the government gas supervision sensor network platform refers to the functional platform for the government user to manage the sensor communication, and the smart gas management platform interacts with the government gas supervision sensor network platform in a two-way manner; the government gas supervision service platform refers to a platform for conveying the needs of the government user and the control information; the citizen user platform refers to a platform for interacting with the government user; the government-regulated smart gas household inspection Internet of Things system is configured to perform the following operations: Obtaining gas usage data of at least one gas user in the inspection area through the smart gas equipment object platform; For a gas user, the smart gas management platform determines a candidate inspection period for the gas user based on the gas usage data of the gas user, including: Based on the gas usage data, determining a gas time characteristic of the gas user; Based on the gas time characteristics, determining at least one time period to be evaluated; For a time period to be evaluated, based on the time period to be evaluated, gas user characteristics and gas time characteristics, the inspectability probability of the time period to be evaluated is determined by an inspectability evaluation model, wherein the inspectability evaluation model is a machine learning model, and the training process of the inspectability evaluation model includes: Acquire a plurality of first training samples and first labels, wherein the first training samples include a sample evaluation period, a sample gas user feature, and a sample gas time feature, and the first label is a sample inspection probability corresponding to the first training sample; Based on the plurality of first training samples and the first labels, training an initial inspectability assessment model; Acquire the inspectability assessment model until the trained inspectability assessment model meets preset conditions; Based on the inspection probability, determining the candidate inspection period; The smart gas management platform determines inspection parameters based on the candidate inspection period and inspection resource information of the at least one gas user, wherein the inspection parameters include the inspection period and inspection resource configuration for conducting home inspections on the at least one gas user; wherein the inspection resources include inspection personnel and inspection equipment; The smart gas management platform sends the inspection parameters to the government gas supervision management platform and the smart gas user platform, and generates an inspection instruction and sends it to the smart gas inspection personnel object platform, so that the inspection personnel can conduct household inspections based on the inspection instructions. The smart gas inspection personnel object platform is configured as the inspection terminal of the inspection personnel; The government gas supervision management platform obtains the inspection data of the gas company according to the inspection supervision frequency based on the inspection area and the inspection parameters of the gas company, and determines the inspection completion rate of the gas company based on the inspection data; In response to the inspection completion rate not meeting the preset progress conditions, the government gas regulatory management platform sends an inspection progress warning to the smart gas management platform based on the inspection completion rate, and adjusts the data acquisition frequency and data storage and cleaning cycle of the gas company based on the inspection completion rate, and cleans the gas data in the memory based on the data storage and cleaning cycle.

7. The Internet of Things system according to claim 6, characterized in that: The smart gas management platform interacts bidirectionally with the government gas regulatory sensor network platform.

8. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the government-regulated smart gas household inspection method as described in claim 1.

Images