A patrol inspection method and Internet of Things system for smart gas supervision information
Through the smart gas supervision information Internet of Things system, the inspection method is intelligently selected, which solves the problem that unmanned inspection equipment is difficult to operate in uneven or obstacle areas, improves inspection efficiency and accuracy, and reduces resource waste.
Patent Information
- Application Number
- CN202411154883.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-22
AI Technical Summary
Existing unmanned inspection equipment is difficult to operate when the ground in the inspection area is uneven or there are obstacles, and the inspection cost is high, which may lead to invalidity or repeated inspections, increasing labor and time costs.
Design a patrol method and Internet of Things system for smart gas supervision information, obtain patrol routes through the government gas supervision and management platform, process them in segments and determine patrol routes, generate call and collect instructions, and determine based on pipeline and facility supervision information Patrol type parameters, adjust the patrol allocation parameters, and realize the selection of intelligent patrol methods.
It improves the efficiency and accuracy of inspections, reduces resource waste, ensures the effectiveness of inspection data, predicts inspection results and time through machine learning models, and optimizes inspection routes and parameter settings.
Smart Images

Figure CN118674126B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart gas technology, and in particular to a smart gas supervision information inspection method and an Internet of Things system. Background Art
[0002] In order to meet the requirements of intelligent inspection, people are currently more inclined to use unmanned inspection equipment (such as drones, unmanned inspection vehicles, robots, etc.) to replace manual inspection. However, on the one hand, the scope of application of unmanned inspection equipment is relatively limited (for example, when the ground in the inspection area is uneven or there are obstacles, it is difficult for unmanned inspection vehicles to operate); on the other hand, the inspection cost of using unmanned inspection equipment is high, and invalid inspection and repeated inspection problems may occur (for example, the data obtained by the unmanned inspection equipment is unavailable, and manual inspection needs to be arranged again), which increases additional manpower and time costs.
[0003] Therefore, it is necessary to provide a smart gas supervision information inspection method and Internet of Things system, which can judge whether drone inspection, robot inspection or manual inspection is needed based on the relevant information of the inspection route (such as pipeline supervision information, facility supervision information, etc.), to ensure the validity of the inspection data and reduce the waste of resources during the inspection process. Summary of the invention
[0004] In order to solve the problem of how to select a suitable inspection method based on the relevant information of the inspection route and realize intelligent inspection, this manual provides an inspection method and an Internet of Things system for smart gas supervision information.
[0005] The invention content includes a patrol method for smart gas regulatory information, which is implemented based on a smart gas regulatory information Internet of Things system. The method is executed by a government gas regulatory management platform in the smart gas regulatory information Internet of Things system. The method includes: based on a gas company management platform, obtaining a patrol route; segmenting the patrol route, determining multiple patrol routes, and storing the multiple patrol routes in a government gas regulatory object platform; generating a call instruction and sending it to a gas company management platform in the government gas regulatory object platform for execution; generating a collection instruction based on the gas company management platform and sending it to a gas equipment object platform for execution; based on a pipeline regulatory Information and facility supervision information, determine the inspection type parameters of multiple inspection routes; based on the inspection type parameters, determine the inspection allocation parameters; generate inspection instructions, and send them to the gas equipment object platform for execution; during the inspection process, in response to the actual coverage of one or more inspection routes meeting the first preset condition, update the inspection routes to obtain new inspection routes; based on the uncovered routes, adjust the inspection allocation parameters; send the updated inspection allocation parameters to the gas equipment object platform for execution; after the inspection, send the current pipeline inspection results and the pipeline defect information corresponding to the new inspection routes to the gas company management platform in the government gas supervision object platform for storage.
[0006] The invention content includes a smart gas supervision information Internet of Things system, which includes a people's user platform, a citizen cloud service platform, a government gas supervision management platform, a government gas supervision sensor network platform, a government gas supervision object platform, a gas company sensor network platform and a gas equipment object platform; the people's user platform and the citizen cloud service platform interact in both directions; the government gas supervision management platform interacts in both directions with the citizen cloud service platform upward and with the government gas supervision sensor network platform downward, and the government gas supervision management platform is configured to execute the above-mentioned smart gas supervision information inspection method; the government gas supervision sensor network interacts in both directions with the government gas supervision object platform downward; the government gas supervision object platform interacts in both directions with the gas company sensor network platform downward, and the government gas supervision object platform includes a gas company management platform, the gas company management platform is used to store multiple inspection routes and pipeline supervision information, and execute the call instructions issued by the government gas supervision management platform, and obtain the inspection route; the gas company sensor network platform interacts in both directions with the gas equipment object platform downward, and the gas equipment object platform is used to execute the collection instructions and inspection instructions issued by the government gas supervision management platform.
[0007] The invention content includes a smart gas supervision information device, which includes at least one memory and at least one processor, the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement a smart gas supervision information inspection method.
[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 inspection method of smart gas supervision information.
[0009] The beneficial effects brought about by the above invention content include but are not limited to: (1) an information operation closed loop is formed between multiple platforms of the system, and unified coordination and management are achieved through the management platform to realize the informatization and intelligence of regulatory information inspection; (2) the machine learning model can quickly and accurately predict the estimated inspection effect of different inspection type parameters and the estimated inspection time of the object to be inspected, and by jointly training the inspection model and the time model, the accuracy of the inspection model and the time model can be further improved, making the estimation of the inspection time more accurate; (3) based on the pipeline supervision information and facility supervision information, the estimated inspection effect of the inspection type parameters can be accurately predicted, and then the inspection type parameters most suitable for the inspection route can be determined; (4) based on the number of gas accidents and the severity of the inspection route in the historical time period, the inspection route can be accurately determined for the inspection time. The corresponding gas risk value is obtained, and then the second threshold is determined according to the positive correlation, so that the setting of the second threshold is more reasonable; (5) According to the first threshold and the second threshold, the second preset condition can be accurately determined for screening the estimated inspection effect, and according to the density of the gas ancillary facilities of the inspection route, data redundancy or fault correlation, the rationality of the setting of the second threshold can be guaranteed from multiple angles; (6) By obtaining multiple inspection routes and the corresponding pipeline supervision information and facility supervision information, the inspection type parameters of the inspection route are determined, and then the inspection allocation parameters are determined, and adjusted according to the actual coverage during the inspection process. With the help of the interaction between the various platforms of the Internet of Things system, the inspection method of smart gas supervision information is realized, which is conducive to improving the efficiency of smart gas supervision information inspection and reducing manpower and time waste during the inspection process. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 It is a schematic diagram of the platform structure of the smart gas supervision information Internet of Things system shown in some embodiments of this specification;
[0011] Figure 2 is an exemplary flow chart of a method for inspecting smart gas supervision information according to some embodiments of this specification;
[0012] Figure 3 is an exemplary schematic diagram of an inspection model according to some embodiments of this specification;
[0013] Figure 4 is an exemplary flow chart of determining a new target sub-route and an inspection type parameter of the new target sub-route according to some embodiments of this specification;
[0014] Figure 5 is an exemplary flow chart of determining inspection allocation parameters according to some embodiments of this specification;
[0015] Figure 6 is an exemplary schematic diagram of a time model according to some embodiments of the present specification. 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 this specification 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 It is a schematic diagram of the platform structure of the smart gas supervision information Internet of Things system shown in some embodiments of this specification.
[0021] In some embodiments, Figure 1 As shown, the smart gas supervision information Internet of Things system 100 may include a people’s user platform 110, a citizen cloud service platform 120, a government gas supervision management platform 130, a government gas supervision sensor network platform 140, a government gas supervision object platform 150, a gas company sensor network platform 160 and a gas equipment object platform 170.
[0022] The people's user platform 110 refers to a platform for interacting with users. Users refer to all citizens who are related to smart gas (e.g., use smart gas). In some embodiments, the people's user platform 110 can exchange information with users in a two-way manner. For example, users can obtain information or convey requirements through the people's user platform 110. In some embodiments, the people's user platform 110 can be configured as a terminal device. For example, the people's user platform 110 can be a smart phone, a tablet, a laptop, etc., or any combination thereof.
[0023] In some embodiments, the people's user platform 110 can interact bidirectionally with the citizen cloud service platform 120. For example, the citizen cloud service platform 120 can obtain user needs from the people's user platform 110, and upload relevant data corresponding to the user needs to the people's user platform 110.
[0024] The citizen cloud service platform 120 refers to a platform that provides Internet services (such as data computing, control information, etc.) to users. For example, the citizen cloud service platform can provide users with gas query, gas supervision and other related services. In some embodiments, the citizen cloud service platform 120 can be configured as a computer cloud platform.
[0025] The government gas supervision management platform 130 refers to a platform for executing the inspection method of smart gas supervision information. In some embodiments, the government gas supervision management platform 130 can coordinate and coordinate the connection and collaboration between various functional platforms, and gather all the information of the Internet of Things to provide perception management and control management functions for the Internet of Things operation system.
[0026] In some embodiments, the government gas supervision management platform 130 can be used to: obtain inspection routes based on the gas company management platform; segment the inspection routes, determine multiple inspection sub-routes, and store the multiple inspection sub-routes in the government gas supervision object platform; generate a call instruction and send it to the gas company management platform in the government gas supervision object platform for execution; generate a collection instruction based on the gas company management platform and send it to the gas equipment object platform for execution; determine the inspection type parameters of multiple inspection sub-routes based on pipeline supervision information and facility supervision information; determine the inspection allocation parameters based on the inspection type parameters; generate inspection instructions and send them to the gas equipment object platform for execution; during the inspection process, in response to the actual coverage of one or more of the inspection sub-routes meeting the first preset condition, update the inspection sub-routes to obtain new inspection sub-routes; adjust the inspection allocation parameters based on the uncovered sub-routes; send the updated inspection allocation parameters to the gas equipment object platform for execution; after the inspection, send the current pipeline inspection results and the pipeline defect information corresponding to the new inspection sub-routes to the gas company management platform in the government gas supervision object platform for storage.
[0027] In some embodiments, the government gas supervision management platform 130 is further used to: predict the estimated inspection effect of the inspection type parameters based on the pipeline supervision information and the facility supervision information; determine the inspection type parameters of the inspection route based on the estimated inspection effect that meets the second preset condition.
[0028] In some embodiments, the government gas supervision and management platform 130 is further used to: in response to the absence of an estimated inspection effect that meets the second preset condition, determine at least one target sub-route and an adjustment type of the target sub-route; in response to the adjustment type being the first type, adjust the target sub-route based on the estimated inspection effect corresponding to the target sub-route to obtain a new target sub-route.
[0029] In some embodiments, the government gas supervision management platform 130 interacts with the citizen cloud service platform 120 in a two-way manner and interacts with the government gas supervision sensor network platform 140 in a two-way manner. For example, the government gas supervision management platform 130 can obtain user demand information based on the citizen cloud service platform 120. For another example, the government gas supervision management platform 130 can obtain the inspection route through the government gas supervision sensor network platform 140.
[0030] The government gas regulatory sensor network platform 140 refers to a functional platform for managing government sensor communications. In some embodiments, the government gas regulatory sensor network platform 140 can be configured as a communication network or a gateway, etc. In some embodiments, the government gas regulatory sensor network platform 140 can realize the functions of sensing information sensor communication and controlling information sensor communication.
[0031] In some embodiments, the government gas regulatory sensor network platform 140 interacts bidirectionally downward with the government gas regulatory object platform 150. For example, the government gas regulatory sensor network platform 140 can obtain the inspection route from the government gas regulatory object platform 150.
[0032] The government gas supervision object platform 150 refers to an object platform for sensing information generation and controlling information execution. In some embodiments, the government gas supervision object platform can be used to store multiple inspection routes and pipeline supervision information, and execute call instructions issued by the government gas supervision management platform.
[0033] In some embodiments, the government gas supervision object platform 150 may include a gas company management platform 150-1. The gas company management platform 150-1 refers to a comprehensive management platform for relevant information of the gas company. In some embodiments, the gas company management platform 150-1 may be used to obtain inspection routes.
[0034] In some embodiments, the government gas supervision object platform 150 interacts bidirectionally downward with the gas company sensor network platform 160. For example, the government gas supervision object platform 150 may send the received collection instruction to the gas company sensor network platform 160.
[0035] The gas company sensor network platform 160 refers to a comprehensive management platform for sensor information of the gas company. In some embodiments, the gas company sensor network platform can be configured as a communication network or a gateway, etc. In some embodiments, the gas company sensor network platform 160 can realize the functions of sensing information sensor communication and controlling information sensor communication.
[0036] In some embodiments, the gas company sensor network platform 160 interacts bidirectionally downward with the gas equipment object platform 170. For example, the gas company sensor network platform 160 may send the received collection instruction to the gas equipment object platform 170 for execution. After the collection instruction is executed, the gas equipment object platform 170 may upload the acquired facility supervision information to the gas company sensor network platform 160.
[0037] The gas equipment object platform 170 refers to a functional platform for executing control instructions. In some embodiments, the smart gas equipment object platform 170 can be configured as various inspection devices, such as drones, robots, etc.
[0038] In some embodiments, the gas equipment object platform 170 can be used to execute collection instructions and inspection instructions issued by the government gas supervision and management platform.
[0039] For more information about the above platforms, please refer to Figure 2-Figure 6 and related instructions.
[0040] In some embodiments of the present specification, based on the smart gas supervision information Internet of Things system, an information operation closed loop can be formed between the people's user platform, the citizen cloud service platform, the government gas supervision management platform, the government gas supervision sensor network platform, the government gas supervision object platform, the gas company sensor network platform and the gas equipment object platform, and coordinated and operated regularly under the unified management of the government gas supervision management platform, thereby realizing the informatization and intelligence of the inspection of smart gas supervision information.
[0041] It should be noted that the above description of the smart gas supervision information Internet of Things system 100 and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle.
[0042] Figure 2is an exemplary flow chart of the inspection method of smart gas supervision information according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps: In some embodiments, the process 200 may be executed by the government gas supervision management platform 130 .
[0043] Step 210, obtaining the inspection route based on the gas company management platform.
[0044] The inspection route refers to the route formed by the gas pipelines that need to be inspected. For example, the inspection route S can be expressed as "①-②-③-④-⑤-⑥-⑦-⑧-⑨-⑩", which means that the gas pipelines ① to ⑩ are inspected.
[0045] In some embodiments, the government gas supervision and management platform can obtain the inspection route through various methods based on the gas company management platform. For example, the government gas supervision and management platform can obtain all gas pipelines in the area that need to be inspected based on the gas company management platform, and obtain the inspection route by traversing all gas pipelines.
[0046] Step 220, segment the inspection route, determine multiple inspection sub-routes, and store the multiple inspection sub-routes in the government gas supervision object platform.
[0047] The inspection sub-route refers to the sub-route that constitutes the inspection route. For example, the inspection sub-route of the inspection route S may include "①-②-③-④" and "⑤-⑥-⑦-⑧-⑨-⑩".
[0048] In some embodiments, the government gas supervision and management platform can determine multiple inspection sub-routes by segmenting the inspection route. For example, the inspection route may include a main pipeline branch and a bypass pipeline branch. The government gas supervision and management platform may start from the starting point of the main pipeline branch in the inspection route (the starting point of the first gas pipeline of the main pipeline branch), and divide the inspection route into multiple areas along the main pipeline branch according to a preset length, and one area corresponds to one inspection sub-route. The bypass pipeline branch is divided into the inspection sub-route closest to it, and the distance may refer to the midpoint of the bypass pipeline branch and the midpoint of the inspection sub-route. Exemplarily, the inspection route S can be divided into inspection sub-route S1 "①-②-③-④", inspection sub-route S2 "⑤-⑥", and inspection sub-route S3 "⑦-⑧-⑨-⑩" through the above process.
[0049] The main pipeline branch and the bypass pipeline branch can be determined by manual preset. The preset length can be preset manually or by system default, for example, 200 meters, 500 meters, etc.
[0050] In some embodiments, the government gas supervision management platform may send multiple inspection routes to the government gas supervision object platform through the government gas supervision sensor network platform, and the government gas supervision object platform stores them.
[0051] Step 230, generating a call instruction and sending it to the gas company management platform in the government gas supervision object platform for execution.
[0052] The calling instruction refers to an instruction for retrieving pipeline supervision information. In some embodiments, the calling instruction can be used to obtain pipeline supervision information corresponding to multiple inspection routes.
[0053] The pipeline supervision information refers to relevant information obtained from historical inspections of gas pipelines. In some embodiments, the pipeline supervision information may include at least one of pipeline defect information and pipeline inspection results in the first historical time period.
[0054] In some embodiments, the pipeline supervision information obtained in each historical inspection can be automatically stored in the government gas supervision object platform by the government gas supervision management platform through the government gas supervision sensor network platform.
[0055] The pipeline bad information refers to relevant information about the bad condition of the gas pipeline. In some embodiments, the pipeline bad information may include a bad location, such as the location of the area where the gas pipeline is located that is not suitable for the robot to pass through.
[0056] The pipeline inspection result refers to the result of the inspection of the gas pipeline. In some embodiments, the pipeline inspection result may include the inspected gas pipeline, whether the inspected gas pipeline has a fault, and the type of fault (including gas leakage, gas pipeline aging, etc.).
[0057] In some embodiments, the pipeline inspection results may also include facility inspection results of gas ancillary facilities of the gas pipeline. Gas ancillary facilities refer to related monitoring devices attached to the gas pipeline, such as gas metering devices, pressure sensors, temperature sensors, flow rate sensors, gas leak detection devices, etc.
[0058] The inspection results of the facilities refer to the inspection results of the gas ancillary facilities. For example, the inspection results of the facilities may include the inspected gas ancillary facilities, whether the inspected gas ancillary facilities have any faults, and the fault types (including gas ancillary facility damage, gas ancillary facility aging, poor performance of gas ancillary facilities, etc.).
[0059] The first historical time period refers to a period of time in the past. For example, the past year, the first half of a certain year, etc. In some embodiments, the length of the first historical time period is positively correlated with the remaining computing resources of the government gas supervision and management platform. For example, if the remaining computing resources of the government gas supervision and management platform are large (such as not less than 50%), the pipeline inspection results of the past year can be called; if the remaining computing resources are small (less than 50%), the pipeline inspection results of the past six months can be called.
[0060] The remaining computing resources refer to the remaining computing capacity of the government gas supervision and management platform. In some embodiments, the remaining computing resources can be determined based on the average occupancy rate of all central processing units (CPUs) in the government gas supervision and management platform.
[0061] The average occupancy rate refers to the average of multiple occupancy rates of multiple CPUs. The occupancy rate refers to the proportion of resources used by the CPU to perform tasks to the total resources. The occupancy rate can be expressed as a percentage of 0-100%. In some embodiments, the remaining computing resources can be expressed by 1 minus the average occupancy rate.
[0062] In some embodiments, the government gas supervision management platform can automatically generate a call instruction based on a manually preset instruction template, and send it to the government gas supervision object platform for execution through the government gas supervision sensor network platform. Based on the call instruction, the government gas supervision object platform retrieves the pipeline supervision information corresponding to the multiple inspection routes stored in the government gas supervision object platform.
[0063] Step 240: Generate a collection instruction based on the gas company management platform and send it to the gas equipment object platform for execution.
[0064] The collection instruction refers to an instruction for obtaining facility supervision information. In some embodiments, the collection instruction can be used to control gas auxiliary facilities deployed on multiple inspection sub-lines to collect and upload facility supervision information. Multiple gas auxiliary facilities can be deployed on one inspection sub-line.
[0065] Facility supervision information refers to information related to gas auxiliary facilities. In some embodiments, the facility supervision information may include the deployment location of the gas auxiliary facilities (e.g., pressure regulating station, gate station, etc.), the facility type of the gas auxiliary facilities (e.g., gas metering device, pressure sensor, etc.), and the facility inspection results of the first historical time period.
[0066] In some embodiments, facility supervision information may be collected and uploaded autonomously by gas-assisted facilities.
[0067] In some embodiments, the government gas supervision management platform can automatically generate collection instructions based on manually preset instruction templates, and send them to the gas equipment object platform for execution through the government gas supervision sensor network platform, the government gas supervision object platform and the gas company sensor network platform. Based on the collection instructions, the gas equipment object platform controls the gas ancillary facilities deployed on multiple inspection sub-lines, collects facility supervision information and uploads it to the government gas supervision management platform.
[0068] Step 250, based on the pipeline supervision information and the facility supervision information, determine the inspection type parameters of the plurality of inspection routes.
[0069] The inspection type parameter refers to the type of subject that performs the inspection work. In some embodiments, the inspection type parameter may include at least one of drone inspection, robot inspection, and manual inspection.
[0070] In some embodiments, each inspection route has a corresponding inspection type parameter. For example, the inspection type parameters of the inspection routes S1, S2, and S3 can be drone inspection, robot inspection, and manual inspection, respectively.
[0071] In some embodiments, the government gas supervision management platform can determine the inspection type parameters of multiple inspection routes in a variety of ways based on the pipeline supervision information and the facility supervision information. For example, the government gas supervision management platform can determine the inspection type parameters based on the pipeline supervision information and the facility supervision information by vector matching.
[0072] In some embodiments, the government gas supervision and management platform can construct a first vector database based on historical data, and the first vector database includes multiple first reference vectors and corresponding reference inspection type parameters and reference inspection coverage. A first reference vector is constructed based on the historical pipeline supervision information and historical facility supervision information of a historical inspection route. Each first reference vector can represent its corresponding historical inspection route. The reference inspection type parameter and the reference inspection coverage can be the corresponding historical actual inspection type parameter and historical actual inspection coverage.
[0073] In some embodiments, the government gas supervision and management platform can construct a first target vector based on pipeline supervision information and facility supervision information. The government gas supervision and management platform can retrieve one or more first reference vectors whose vector distance from the first target vector is less than a distance threshold in the first vector database, and determine the first reference vector with the highest corresponding reference inspection coverage from the one or more first reference vectors, and determine the corresponding reference inspection type parameter as the current inspection type parameter. The vector distance can be any one of Euclidean distance, cosine distance, Mahalanobis distance, etc. The distance threshold can be determined manually based on prior experience or historical data.
[0074] The reference inspection coverage refers to the inspection coverage used for reference. The inspection coverage refers to the coverage of the inspected route. In some embodiments, the inspection coverage can be represented by the ratio of the length of the inspected route to the total length of the inspected sub-route. The total length refers to the sum of the lengths of the main gas pipelines and the secondary gas pipelines included in the inspected sub-route.
[0075] In some embodiments, the government gas supervision management platform can predict the estimated inspection effect of the inspection type parameters based on the pipeline supervision information and the facility supervision information; and determine the inspection type parameters of the inspection routes based on the estimated inspection effect that meets the second preset condition.
[0076] The estimated inspection effect refers to the estimated inspection effect of the gas pipeline based on the inspection type parameters. In some embodiments, the estimated inspection effect may include an estimated accuracy rate and an estimated coverage rate.
[0077] The estimated accuracy rate refers to the estimated inspection accuracy. Inspection accuracy refers to the accuracy of pipeline inspection results. In some embodiments, the estimated accuracy can be represented by the degree of consistency between the estimated pipeline inspection results and the actual pipeline operation results in the future period. The degree of consistency can be determined based on vector distance, similarity, etc.
[0078] The pipeline operation result refers to the actual operation result of the gas pipeline. For example, the pipeline operation result may include whether the gas pipeline and gas ancillary facilities have a fault and the type of fault.
[0079] The future time period refers to a period of time in the future from the current time, for example, the next week.
[0080] The estimated coverage refers to the estimated inspection coverage. In some embodiments, the estimated coverage can be represented by the ratio of the estimated length of the line that can be inspected to the total length of the inspection sub-lines. For an explanation of the inspection coverage, please refer to the above related description.
[0081] Different inspection type parameters may correspond to different estimated inspection effects.
[0082] In some embodiments, the government gas supervision management platform can predict the estimated inspection effect of the inspection type parameters in a variety of ways based on the pipeline supervision information and facility supervision information. For example, for a certain inspection route, it has undergone multiple (assuming m times) manual inspections, and each historical manual inspection corresponds to a historical estimated pipeline inspection result, and the historical actual pipeline operation result of each historical manual inspection can be known based on historical data.
[0083] Count the number of times (assuming it is n) that the historical estimated pipeline inspection results and the historical actual pipeline operation results are inconsistent (for example, there is no fault in the historical estimated pipeline inspection results, but there is a fault in the historical actual pipeline operation results) in m historical manual inspections. The error rate is n / m, and the difference between 1 and the error rate is determined as the estimated accuracy of the manual inspection. Take the union of the inspected gas pipelines in the m historical manual inspections, calculate the total length of the gas pipelines in the union, and determine the ratio of the union to the total length of the inspection route as the estimated coverage of the manual inspection.
[0084] Similarly, the above process can be used to obtain the estimated accuracy and coverage of robot inspections, as well as the estimated accuracy and coverage of drone inspections. If there is no historical data for a certain inspection type parameter (e.g., robot inspection), that is, the inspection route has not been inspected by a robot, the preset value (preset by humans or the system, such as 80%) is used as the estimated accuracy and coverage.
[0085] In some embodiments, the government gas supervision management platform can determine the estimated inspection effect through the inspection model based on the pipeline supervision information, facility supervision information and pipeline distribution.
[0086] The pipeline distribution situation refers to the relevant situation of the distribution location of the gas pipeline. In some embodiments, the pipeline distribution situation can be represented by a vector sequence consisting of the coordinates of the midpoint positions of multiple gas pipelines. For example, {(x1, y1), (x2, y2), ..., (x 10 ,y 10 )}, which means that in the inspection route S, the midpoint position coordinates of the gas pipeline ① are (x1, y1). Similarly, the midpoint position coordinates of the gas pipeline ⑩ are (x 10 ,y 10 ). In some embodiments, the pipeline distribution can also be represented by a graph structure. For example, a graph structure with the starting point and end point of each gas pipeline as nodes and the gas pipeline as an edge.
[0087] In some embodiments, the government gas supervision and management platform can obtain the pipeline distribution of the inspection route based on the gas pipeline distribution map. The gas pipeline distribution map can be manually uploaded to the government gas supervision and management platform in advance.
[0088] The inspection model refers to a model used to determine the estimated inspection effect. In some embodiments, the inspection model can be a machine learning model, such as a neural network (NN).
[0089] In some embodiments, the government gas supervision management platform can input the pipeline supervision information, facility supervision information and pipeline distribution of the inspection route into the inspection model, and output the estimated inspection effects of different inspection type parameters through different output layers of the inspection model. For more information about the inspection model, please refer to Figure 3 Related description.
[0090] In some embodiments of the present specification, the estimated inspection effects of different inspection type parameters can be quickly and accurately predicted through a machine learning model, which is conducive to the subsequent reasonable determination of the inspection type parameters of the inspection routes.
[0091] The second preset condition refers to the condition that the estimated inspection effect must meet when determining the inspection type parameter. In some embodiments, the second preset condition may include the estimated accuracy being greater than the second threshold, and the estimated coverage being greater than the first threshold. The second threshold refers to the minimum critical value of the estimated accuracy when determining the inspection type parameter. For example, 80%.
[0092] In some embodiments, a plurality of inspection sub-routes may correspond to one or more second thresholds, and the second thresholds are positively correlated to the gas risk values corresponding to the inspection sub-routes.
[0093] The gas risk value refers to a numerical value reflecting the gas risk. In some embodiments, the gas risk value can be determined based on the number of gas accidents and the severity of the accidents in the second historical time period of the inspection route. For example, the gas risk value can be the sum of the severity of all gas accidents in the second historical time period. The second historical time period refers to a period of time in the past. In some embodiments, the second historical time period can be manually preset or set by system default. For example, the past two years.
[0094] The number of gas accidents refers to the number of occurrences of gas accidents, for example, 10 times, 20 times, etc. A gas accident refers to a safety accident related to gas, for example, gas leakage, gas poisoning, gas explosion, etc. In some embodiments, the government gas supervision and management platform can obtain the number of gas accidents in the second historical time period based on historical data.
[0095] The severity of the accident refers to the severity of the gas accident. In some embodiments, the severity of the accident can be determined by a technician based on historical experience and represented by a level of 1 to 10. The higher the level, the more serious the gas accident.
[0096] In some embodiments, the second threshold value may be positively correlated with the gas risk value corresponding to the inspection route. The larger the gas risk value, the higher the second threshold value. The gas risk values corresponding to different inspection routes may be the same or different, and the corresponding second threshold values may be the same or different.
[0097] In some embodiments of the present specification, the gas risk value corresponding to the inspection route can be accurately determined based on the number of gas accidents and the severity of the accidents in the historical time period, and then the second threshold is determined based on the positive correlation, so that the setting of the second threshold is more reasonable.
[0098] The first threshold refers to the minimum critical value of the estimated coverage when determining the inspection type parameter. For example, 80%. In some embodiments, the first threshold can be determined based on at least one of the density of gas auxiliary facilities of the inspection route, data redundancy, or fault correlation.
[0099] For example, the government gas supervision and management platform can determine the first threshold by querying the first preset table based on at least one of density, data redundancy or fault correlation. The first preset table may include a correspondence between at least one of density, data redundancy or fault correlation and the first threshold. The correspondence may include a positive correlation between the first threshold and the density, a negative correlation between the first threshold and the data redundancy, and a negative correlation between the first threshold and the fault correlation. The first preset table can be determined based on prior experience or historical data.
[0100] The density refers to the degree of distribution concentration of gas ancillary facilities. The density can be represented by the number of gas ancillary facilities in a unit length of the gas pipeline. In some embodiments, the density of gas ancillary facilities in the inspection route is positively correlated with the first threshold. The greater the density, the higher the possibility of failure, the greater the inspection coverage required, and the greater the first threshold.
[0101] Data redundancy refers to the degree of overlap of data collected by gas auxiliary facilities. For example, among 10 gas auxiliary facilities, the data collected by 3 gas auxiliary facilities are repeated, and the data redundancy is 30%. In some embodiments, the data redundancy of the gas auxiliary facilities of the inspection route is negatively correlated with the first threshold. The greater the data redundancy, the higher the degree of overlap of the data, the inspection coverage can be appropriately reduced, and the smaller the first threshold.
[0102] Fault correlation refers to the degree of correlation of failures in gas auxiliary facilities. Fault correlation can be represented by the historical frequency of simultaneous failures in gas auxiliary facilities. For example, if 70 out of 100 historical inspections show simultaneous failures in gas auxiliary facilities, the fault correlation is 70%.
[0103] In some embodiments, the fault correlation of the gas auxiliary facilities of the inspection route is negatively correlated with the first threshold. The greater the fault correlation, the higher the accuracy of determining whether other associated gas auxiliary facilities have failed by whether one gas auxiliary facility has failed, and the inspection coverage can be appropriately reduced (only one of the gas auxiliary facilities needs to be inspected), and the smaller the first threshold.
[0104] In some embodiments, the government gas regulatory management platform may determine an estimated inspection effect whose estimated accuracy is greater than a second threshold and whose estimated coverage is greater than a first threshold as an estimated inspection effect that meets a second preset condition.
[0105] In some embodiments of the present specification, based on the first threshold and the second threshold, the second preset condition can be accurately determined for screening the estimated inspection effect, and based on the density of gas ancillary facilities in the inspection route, data redundancy or fault correlation, the rationality of the setting of the second threshold can be guaranteed from multiple angles, which is facilitating the subsequent accurate determination of the inspection type parameters of the inspection route.
[0106] In some embodiments, in response to there being only one estimated inspection effect that meets the second preset condition, the government gas regulatory management platform may determine the inspection type parameter corresponding to the estimated inspection effect as the inspection type parameter of the inspection route. In response to the presence of multiple estimated inspection effects that meet the second preset condition, the government gas regulatory management platform may determine the inspection type parameter corresponding to the estimated inspection effect with the highest estimated accuracy among the multiple estimated inspection effects that meet the second preset condition as the inspection type parameter of the inspection route, or may determine the inspection type parameter with the highest inspection success rate among the multiple estimated inspection effects that meet the second preset condition as the inspection type parameter of the inspection route.
[0107] The inspection success rate refers to the probability that the inspection equipment can successfully pass through the obstacle area (for example, the area blocked by lush plants) and successfully complete the inspection (without getting stuck or damaged in the middle of the inspection). The inspection success rate of robot inspection and drone inspection can be obtained through the inspection model output. For more information about this part, please refer to Figure 3 Related description.
[0108] In some embodiments of the present specification, based on pipeline supervision information and facility supervision information, the estimated inspection effect of the inspection type parameters can be accurately predicted, and then the inspection type parameters most suitable for the inspection route can be determined from the estimated inspection effects that will meet the second preset condition, which is conducive to the effective implementation of subsequent inspection operations.
[0109] Step 260: Determine the inspection allocation parameter based on the inspection type parameter.
[0110] The inspection allocation parameter refers to the allocation combination of inspection equipment or inspectors and inspection sub-routes. In some embodiments, the inspection allocation parameter can be represented by a sequence consisting of matching pairs of inspection equipment or inspectors and inspection sub-routes. For example, the inspection allocation parameter can be {(drone 1, inspection sub-route S1), (robot 1, inspection sub-route S2), (drone 2, inspection sub-route S3), (inspector 1, inspection sub-route S4)}, which means that drone 1, robot 1, drone 2, and inspector 1 are used for the inspection of inspection sub-route S1, inspection sub-route S2, inspection sub-route S3, and inspection sub-route S4, respectively.
[0111] Inspection equipment refers to equipment used to perform inspection operations. In some embodiments, the inspection equipment may include drones and robots. Inspectors refer to personnel used to perform inspection operations.
[0112] In some embodiments, the inspection equipment or inspectors correspond to the inspection type parameters. For example, if the inspection type parameter of the inspection route is drone inspection, the inspection operation of the inspection route is performed by a drone; if the inspection type parameter of the inspection route is robot inspection, the inspection operation of the inspection route is performed by a robot; if the inspection type parameter of the inspection route is manual inspection, the inspection operation of the inspection route is performed by an inspector.
[0113] In some embodiments, the government gas supervision and management platform can determine the inspection allocation parameters in a variety of ways based on the inspection type parameters. For example, the government gas supervision and management platform can randomly assign the corresponding inspection equipment or inspectors to the inspection sub-routes based on the inspection type parameters of the inspection sub-routes, traverse all the inspection sub-routes, and determine the inspection allocation parameters.
[0114] One inspection device or one inspector can be assigned to one or more inspection routes, and different inspection devices or inspectors can be assigned to different inspection routes. If the number of inspection routes with the same inspection type parameter is less than the number of corresponding inspection devices or inspectors (for example, if the inspection type parameter is drone inspection, there are 20 inspection routes and 30 drones), multiple inspection devices or inspectors can be assigned to the same inspection route.
[0115] In some embodiments, the government gas supervision and management platform can divide multiple inspection routes into three categories of objects to be inspected based on the inspection type parameters, determine the candidate allocation parameters of the three categories of objects to be inspected, and then determine the estimated inspection time; based on the estimated inspection time, determine the inspection allocation parameters. For more information about this part, please refer to Figure 5 Related description.
[0116] Step 270: Generate an inspection instruction and send it to the gas equipment object platform for execution.
[0117] The inspection instruction refers to an instruction for executing the inspection allocation parameters. In some embodiments, the inspection instruction can be used to control the inspection equipment and / or the inspector to execute the inspection allocation parameters.
[0118] In some embodiments, the government gas supervision management platform can automatically generate inspection instructions based on manually preset instruction templates, and send them to the gas equipment object platform for execution through the government gas supervision sensor network platform and the gas company sensor network platform. The gas equipment object platform controls the inspection equipment and / or inspectors to execute the inspection allocation parameters based on the call instructions.
[0119] During the inspection process, the government gas supervision and management platform can execute steps 281 to 283.
[0120] Step 281, in response to the actual coverage of one or more inspection sub-routes satisfying the first preset condition, the inspection sub-routes are updated to obtain new inspection sub-routes.
[0121] The actual coverage refers to the actual coverage of the inspection sub-route during the inspection process. In some embodiments, the actual coverage can be represented by the ratio of the length of the line that has actually been inspected to the total length of the inspection sub-route. For example, 70%.
[0122] The first preset condition refers to a condition that the actual coverage must meet when determining whether to update the inspection route. In some embodiments, the first preset requirement may be that the actual coverage is less than a first threshold.
[0123] For more information about the inspection coverage and the first threshold, please refer to the relevant description above.
[0124] The new inspection route refers to the updated inspection route. In some embodiments, the new inspection route may include uncovered routes. The uncovered routes refer to the inspection routes consisting of gas pipelines that have not been inspected.
[0125] In some embodiments, when the actual coverage of the inspection sub-routes meets the first preset condition, the government gas supervision and management platform can re-divide the inspection sub-routes whose actual coverage is less than the first threshold, and determine the uncovered sub-routes based on the gas pipelines that have not been inspected. Other inspection sub-routes that do not meet the first preset condition maintain the original division to obtain new inspection sub-routes.
[0126] For example, the inspection route S is divided into inspection sub-route S1 "①-②-③-④", inspection sub-route S2 "⑤-⑥", and inspection sub-route S3 "⑦-⑧-⑨-⑩". Among them, the actual coverage of the inspection sub-route S1 is 70%, which is less than the first threshold 80%. If the first preset condition is met, the inspection sub-route S1 is divided again, and the gas pipelines ① and ② that have not been inspected are divided into an uncovered sub-route S 11 "①-②", divide the inspected gas pipelines ③ and ④ into a new inspection route S 12 "③-④", that is, S1 is divided into S 11 and S 12 The actual coverage of the inspection route S2 and the inspection route S3 are 90% and 85% respectively, which are greater than the first threshold 80% and do not meet the first preset condition, so the original division is maintained. 11 and S 12 .
[0127] Step 282: Adjust inspection allocation parameters based on uncovered sub-routes.
[0128] In some embodiments, the government gas supervision and management platform can adjust the inspection allocation parameters based on the uncovered sub-routes in a variety of ways. For example, the government gas supervision and management platform can directly assign inspectors to inspect the uncovered sub-routes. For example, the original inspection allocation parameters {(drone 1, inspection sub-route S1), (robot 1, inspection sub-route S2), (drone 2, inspection sub-route S3)}, S1 is further divided into S 11 and S 12 , S 11 If the route is not covered, the inspection allocation parameters can be adjusted to {(Inspector 1, New Inspection Route S 11 ), (UAV 1, new inspection route S 12 ), (Robot 1, inspection route S2), (UAV 2, inspection route S3)}. For more information on how to adjust inspection allocation parameters, see Figure 5 Related description in .
[0129] Step 283: Send the updated inspection allocation parameters to the gas equipment object platform for execution.
[0130] In some embodiments, the government gas supervision management platform can send the updated inspection allocation parameters to the gas equipment object platform through the government gas supervision sensor network platform and the gas company sensor network platform for execution. The gas equipment object platform controls the inspection equipment and / or inspectors to perform inspection operations based on the updated inspection allocation parameters.
[0131] Step 290, after the inspection is completed, the current pipeline inspection results and the pipeline defect information corresponding to the new inspection route are sent to the gas company management platform in the government gas supervision object platform for storage.
[0132] In some embodiments, the pipeline defect information corresponding to the new inspection route may include the defective position corresponding to the new inspection route, and the original inspection type parameters corresponding to the new inspection route need to be indicated (i.e., whether it is a robot or a drone that cannot reach the defective position corresponding to the new inspection route).
[0133] In some embodiments, the government gas supervision management platform can send the current pipeline inspection results and pipeline defect information corresponding to the new inspection route to the gas company management platform in the government gas supervision object platform for storage through the government gas supervision sensor network platform.
[0134] In some embodiments of the present specification, by acquiring multiple inspection routes and their corresponding pipeline supervision information and facility supervision information, the inspection type parameters of the inspection routes are determined, and then the inspection allocation parameters are determined, and adjusted according to the actual coverage during the inspection process. With the help of the interaction between various platforms of the Internet of Things system, a method for inspecting smart gas supervision information is implemented, which is beneficial to improving the efficiency of the inspection of smart gas supervision information and reducing manpower and time waste during the inspection process.
[0135] The embodiments in this specification are only for illustration and description, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes that can be made under the guidance of this specification are still within the scope of this specification.
[0136] Figure 3 It is an exemplary schematic diagram of the inspection model shown in some embodiments of this specification.
[0137] In some embodiments, Figure 3 As shown, the inspection model 320 may include a feature extraction layer 320 - 1 , a drone output layer 320 - 2 , a robot output layer 320 - 3 , and a manual output layer 320 - 4 .
[0138] For more information about the inspection model, see Figure 2 Related description.
[0139] The feature extraction layer 320-1 refers to a model used to determine feature vectors. In some embodiments, the feature extraction layer can be a machine learning model, such as a deep neural network (DNN) model. In some embodiments, Figure 3As shown, the input of the feature extraction layer may include pipeline distribution 310-1, pipeline supervision information 310-2 and facility supervision information 310-3 of the inspection route, and the output may include feature vector 330. For more information about pipeline distribution, pipeline supervision information and facility supervision information, please refer to Figure 2 Related description.
[0140] The feature vector is a vector that characterizes the features of the inspection route. In some embodiments, the feature vector may refer to a vector composed of pipeline distribution, pipeline supervision information, and facility supervision information.
[0141] The drone output layer 320-2 refers to a model used to determine the estimated inspection effect of the drone inspection. In some embodiments, the drone output layer can be a machine learning model, such as a convolutional neural network. In some embodiments, such as Figure 3 As shown, the input of the drone output layer 320 - 2 may include a feature vector 330 , and the output may include an estimated accuracy 340 - 1 of the drone inspection and an estimated coverage 340 - 2 of the drone inspection.
[0142] The estimated accuracy (or estimated coverage) of drone inspection refers to the estimated accuracy (or estimated coverage) obtained for an inspection route using the inspection type parameters of drone inspection.
[0143] The robot output layer 320-3 refers to a model used to determine the estimated inspection effect of the robot inspection. In some embodiments, the robot output layer can be a machine learning model, such as a convolutional neural network. Figure 3 As shown, the input of the robot output layer 320 - 3 may include a feature vector 330 , and the output may include an estimated accuracy 350 - 1 of the robot inspection and an estimated coverage 350 - 2 of the robot inspection.
[0144] The estimated accuracy (or estimated coverage) of robot inspection refers to the estimated accuracy (or estimated coverage) obtained for an inspection route using the inspection type parameters of robot inspection.
[0145] The artificial output layer 320 - 4 refers to a model used to determine the estimated inspection effect of the manual inspection. In some embodiments, the artificial output layer can be a machine learning model, such as a convolutional neural network (Convolutional Neural Networks).
[0146] In some embodiments, Figure 3As shown, the input of the manual output layer 320 - 4 may include a feature vector 330 , and the output may include an estimated accuracy 360 - 1 of manual inspection and an estimated coverage 360 - 2 of manual inspection.
[0147] The estimated accuracy (or estimated coverage) of manual inspection refers to the estimated accuracy (or estimated coverage) obtained for a patrol route using the patrol type parameters of manual inspection. For more information about drone inspection, robot inspection, manual inspection, patrol type parameters, estimated accuracy and estimated coverage, please refer to Figure 2 Related description.
[0148] In some embodiments, Figure 3 As shown, the output of the drone output layer 320-2 may also include an estimated success rate 340-3 of the drone inspection, and the output of the robot output layer 320-3 may also include an estimated success rate 350-3 of the robot inspection.
[0149] The estimated success rate refers to the estimated inspection success rate. The estimated success rate of robot inspection (or drone inspection) refers to the estimated success rate obtained by using the inspection type parameters of robot inspection (or drone inspection) for an inspection route. For more information about inspection success rate, please refer to Figure 2 Related description.
[0150] In some embodiments of the present specification, the drone output layer and the robot output layer can accurately determine the estimated success rate of the drone inspection and the robot inspection, which is conducive to the reasonable selection of the inspection type parameters of the subsequent inspection routes.
[0151] In some embodiments, the government gas supervision and management platform can train the inspection model based on multiple first training samples with first labels. The first training sample may include sample pipeline distribution of sample inspection sub-lines, sample pipeline supervision information, and sample facility supervision information. The first label may be the actual inspection accuracy and actual inspection coverage corresponding to the first training sample. The first training sample and the first label may be obtained through historical data.
[0152] The first training samples can be divided into first-category training samples, second-category training samples, and third-category training samples. Among them, the first-category training samples refer to first training samples that only contain inspection type parameters of drone inspection. The second-category training samples refer to first training samples that only contain inspection type parameters of robot inspection. The third-category training samples refer to first training samples that only contain inspection type parameters of manual inspection.
[0153] The first labels can be divided into first-category labels, second-category labels and third-category labels, which are the labels corresponding to the first-category training samples, the second-category training samples and the third-category training samples, respectively, that is, the actual inspection accuracy and actual inspection coverage of drone inspection, robot inspection and manual inspection, respectively.
[0154] In some embodiments, the government gas supervision and management platform can use the first type of training samples to jointly train the feature extraction layer and the drone output layer, input the sample pipeline distribution of the sample inspection route, the sample pipeline supervision information and the sample facility supervision information into the initial feature extraction layer, and input the feature vector output by the initial feature extraction layer into the initial drone output layer, and construct a loss term (denoted as loss term 1) through the results of the first type of labels and the initial drone output layer.
[0155] Similarly, the government gas regulatory management platform can use the second type of training samples to jointly train the feature extraction layer and the robot output layer, and construct another loss term (referred to as loss term 2) through the second type of labels and the results of the initial robot output layer. The government gas regulatory management platform can use the third type of training samples to jointly train the feature extraction layer and the manual output layer, and construct another loss term (referred to as loss term 3) through the results of the third type of labels and the initial manual output layer.
[0156] In some embodiments, the government gas supervision and management platform can jointly train the feature extraction layer, the drone output layer, the robot output layer, and the manual output layer. The government gas supervision and management platform can construct a first loss function based on loss term 1, loss term 2, and loss term 3 in a variety of ways (such as weighted summation, etc.), and iteratively update the parameters of the feature extraction layer, the drone output layer, the robot output layer, and the manual output layer based on the first loss function by gradient descent or other methods. When the preset conditions are met, the training is completed, and the trained feature extraction layer, drone output layer, robot output layer, and manual output layer are obtained. Among them, the preset conditions can be that the first loss function converges, the number of iterations reaches a threshold, etc.
[0157] In some embodiments of the present specification, through different output layers of the inspection model, the estimated accuracy and estimated coverage corresponding to different inspection type parameters can be accurately and efficiently predicted, which is conducive to the reasonable selection of inspection type parameters for subsequent inspection routes, so as to ensure the smooth progress of the inspection operation to the greatest extent.
[0158] Figure 4 FIG. 1 is an exemplary flow chart of determining a new target branch route and an inspection type parameter of the new target branch route according to some embodiments of this specification. Figure 4 As shown, the process 400 may include step 410 and step 420. In some embodiments, the process 400 may be executed by the government gas supervision management platform 130.
[0159] Step 410 : In response to the absence of an estimated inspection effect that satisfies a second preset condition, determining at least one target sub-route and an adjustment type of the target sub-route.
[0160] The target sub-route refers to the inspection sub-route that needs to be re-divided or the inspection type parameters need to be adjusted. In some embodiments, in response to the fact that an inspection sub-route does not have an estimated inspection effect that meets the second preset condition (i.e., for an inspection sub-route, the estimated inspection effects of all inspection type parameters do not meet the second preset condition), the government gas supervision and management platform can determine the inspection sub-route as the target sub-route.
[0161] The adjustment type refers to the type of way to adjust the target branch route. In some embodiments, the adjustment type may include a first type corresponding to an estimated coverage less than a first threshold, and a second type corresponding to an estimated accuracy less than a second threshold.
[0162] In some embodiments, for the target sub-route whose estimated inspection effect does not meet the second preset condition (i.e., the estimated accuracy is greater than the second threshold and the estimated coverage is greater than the first threshold), as long as the estimated coverage corresponding to the target sub-route is less than the first threshold, the government gas supervision and management platform can determine that the corresponding adjustment type is the first type; if the estimated coverage corresponding to the target sub-route is greater than the first threshold and the estimated accuracy is less than the second threshold, the government gas supervision and management platform can determine that the corresponding adjustment type is the second type.
[0163] Since the estimated coverage of the inspection sub-route corresponding to the first type is less than the first threshold, the estimated coverage less than the first threshold means that some areas or positions of the inspection sub-route are not suitable for automatic inspection by the inspection equipment, and manual inspection is considered at this time. Therefore, the first type can refer to direct manual inspection of the target sub-route.
[0164] Since the estimated accuracy of the second type corresponding to the inspection route is less than the second threshold, the estimated accuracy less than the second threshold means that the current inspection type parameter of the inspection route is not suitable, but the current inspection type parameter is the inspection type parameter with the highest inspection accuracy. At this time, consider using multiple inspection type parameters to inspect at the same time to improve the inspection accuracy. Therefore, the second type can refer to using multiple inspection type parameters to inspect the target route at the same time (for example, using drone inspection and robot inspection at the same time).
[0165] For more information about the second preset condition, the first threshold, the second threshold, the estimated accuracy, the estimated coverage, the inspection type parameter, the estimated inspection effect and other related parameters, please refer to Figure 2 Related description.
[0166] Step 420 , in response to the adjustment type being the first type, adjusting the target sub-route based on the estimated inspection effect corresponding to the target sub-route to obtain a new target sub-route.
[0167] The new target sub-route refers to the adjusted target sub-route. In some embodiments, in response to the adjustment type being the first type (i.e., the estimated coverage of the target sub-route is less than the first threshold), the government gas regulatory management platform can separate the gas pipelines with inconvenient roads or remote geographical locations in the target sub-route according to the pipeline distribution and pipeline defect information to obtain the new target sub-route. In the estimated inspection effect corresponding to the target sub-route, the smaller the estimated coverage, the more detailed the re-division of the target sub-route can be, that is, the more new target sub-route can be obtained by re-division.
[0168] For example, the target route S 1 "①-②-③-④-⑤-⑥", its estimated coverage is 70%, which is less than the first threshold of 80%, so its adjustment type is the first type. Among them, the geographical locations of gas pipelines ① and ③ are remote, so gas pipelines ① and ③ can be divided into a new target branch route S 11 "①-③", direct manual inspection is adopted, and gas pipelines ②, ④, ⑤, ⑥ are divided into another new target sub-route S 12 "②-④-⑤-⑥", the previous inspection type parameters are used; segmentation processing can also be performed according to the main pipeline branches and bypass pipeline branches to adjust the target branch route to obtain a new target branch route. For more information about segmentation processing according to the main pipeline branches and bypass pipeline branches, please refer to Figure 2 Related description.
[0169] In some embodiments of the present specification, when the estimated inspection effects of all inspection type parameters do not meet the preset requirements, the inspection sub-route is regarded as a target sub-route that needs to be re-divided, and for the target sub-route with an estimated coverage less than a first threshold, it is readjusted according to the estimated inspection effect, and manual inspection is directly adopted for new target sub-routes with inconvenient roads or remote geographical locations, which is conducive to improving the final inspection coverage.
[0170] In some embodiments, Figure 4 As shown, the process 400 may further include step 430. Step 430 may be performed by the government gas supervision management platform 130.
[0171] Step 430 , in response to the adjustment type being the second type, updating the inspection type parameter of the target sub-route based on the estimated inspection effect corresponding to the target sub-route.
[0172] In some embodiments, in response to the adjustment type being the second type (i.e., the estimated accuracy of the target sub-route is less than the second threshold), the government gas regulatory management platform can select the two inspection type parameters with the highest estimated accuracy based on the estimated inspection results corresponding to the target sub-route, and execute the two inspection type parameters on the target sub-route at the same time.
[0173] In some embodiments of the present specification, when the estimated accuracy of the target sub-route is less than the second threshold, two inspection type parameters with the highest estimated accuracy are simultaneously executed on the target sub-route, which is beneficial to improving the final inspection accuracy.
[0174] In some embodiments, Figure 4 As shown, the process 400 may further include step 440. Step 440 may be performed by the government gas supervision management platform 130.
[0175] Step 440 , in response to the number of target sub-routes of the second adjustment type exceeding a quantity threshold, determine new target sub-routes and estimated inspection effects of the new target sub-routes based on pipeline distribution of the target sub-routes.
[0176] The quantity threshold refers to the maximum critical value of the number of target sub-routes whose adjustment type is the second type when the target sub-routes need to be updated, and can be preset manually. In some embodiments, when the number of target sub-routes whose adjustment type is the second type exceeds the quantity threshold, the government gas regulatory management platform or manual work can segment the target sub-routes whose adjustment type is the second type based on the pipeline distribution of the target sub-routes, re-divide them to obtain multiple new target sub-routes, and predict the estimated inspection effects of the corresponding inspection sub-routes. One division method obtains a group of new target sub-routes, and different division methods obtain multiple groups of new target sub-routes. For more information on determining the estimated inspection effect, please refer to Figure 2 Related description.
[0177] In some embodiments, if the multiple groups of new target sub-routes corresponding to all division methods cannot ensure that the estimated inspection effects of all inspection sub-routes meet the second preset condition, the division method with the least number of inspection sub-routes whose estimated inspection effects do not meet the second preset condition is selected to re-divide the target sub-routes.
[0178] In some embodiments, the government gas supervision and management platform can determine the estimated inspection effect of the new target sub-route through the inspection model. For more information about this part, please refer to Figure 4 Related description.
[0179] In some embodiments of the present specification, when there are a large number of target sub-routes whose estimated accuracy is less than the second threshold, the target sub-routes are re-divided according to the pipeline distribution to obtain new target sub-routes and corresponding estimated inspection effects, which is beneficial to ensure that the final inspection sub-routes have a high inspection accuracy.
[0180] Figure 5 FIG. 1 is an exemplary flow chart of determining inspection allocation parameters according to some embodiments of this specification. Figure 5 As shown, the process 500 may include steps 510 to 530. In some embodiments, the process 500 may be executed by the government gas supervision management platform 130.
[0181] Step 510: Based on the inspection type parameter, multiple inspection routes are divided into three types of objects to be inspected, and candidate allocation parameters of the objects to be inspected are determined.
[0182] The objects to be inspected refer to the categories of the inspection routes classified according to the inspection type parameters. In some embodiments, the three types of objects to be inspected can be drone inspection routes, robot inspection routes, and manual inspection routes.
[0183] In some embodiments, the government gas supervision and management platform can traverse all inspection routes, divide the inspection routes of drone inspections into drone inspection routes, divide the inspection routes of robot inspections into robot inspection routes, and divide the inspection routes of manual inspections into manual inspection routes, so as to complete the division of inspection routes into three categories of objects to be inspected.
[0184] Candidate allocation parameters refer to parameters used for candidate inspection allocation parameters. Each type of object to be inspected has multiple candidate allocation parameters corresponding to it. In some embodiments, the candidate allocation parameters can be represented by a sequence consisting of matching pairs of inspection equipment or inspectors and corresponding initial inspection routes. For example, taking the object to be inspected as a drone inspection route as an example, the drone inspection route includes inspection routes S1-S1. 10 , the drones include drone 1-drone 4, then the candidate allocation parameters can be {(drone 1, initial inspection route S1), (drone 2, initial inspection route S3), (drone 3, initial inspection route S6), (drone 4, initial inspection route S 10 )}, which means that drone 1, drone 2, drone 3, and drone 4 are respectively from the initial inspection route S1, the initial inspection route S3, the initial inspection route S6, and the initial inspection route S 10 Begin inspection work.
[0185] The initial inspection route refers to the first inspection route that the inspection equipment or inspectors start to inspect during the inspection. In some embodiments, if the number of inspection equipment (or inspectors) is less than the number of inspection routes, after the inspection equipment (or inspectors) completes the inspection of the initial inspection route, the inspection equipment (or inspectors) can continue to be assigned to the inspection route that is closest to the inspection equipment (or inspectors) and has not been inspected. Furthermore, if there is only one inspection route left to be inspected and the inspection of the other inspection routes has been completed, the idle inspection equipment (or inspectors) can also be assigned to the inspection route.
[0186] Continuing with the above example, if after drone 1 completes the inspection of the initial inspection route S1, the drone is closest to the inspection route S2 that has not been inspected, drone 1 will continue to be assigned to inspection route S2, and the same goes for the remaining drones. Furthermore, if drone 3 completes inspection route S7 and finds that only inspection route S8 is being inspected by drone 4, drone 3 can also be assigned to inspection route S8, until all inspection routes are inspected. The candidate allocation parameters can be {(drone 1, inspection route S1-inspection route S2), (drone 2, inspection route S3-inspection route S4-inspection route S5), (drone 3, inspection route S6-inspection route S7-inspection route S8), (drone 4, inspection route S 10 -Inspection route S9-Inspection route S8)}.
[0187] In some embodiments, the government gas supervision and management platform can calculate the location distance between the inspection equipment or inspector and the starting and ending locations of each inspection route that has not been inspected based on the location of the inspection equipment or inspector, the starting and ending locations of the inspection routes, and select the inspection route with the smallest location distance as the next inspection route of the inspection equipment or inspector. The location of the inspection equipment or inspector can be spontaneously obtained and uploaded to the government gas supervision and management platform by a positioning device (such as a GPS locator, etc.) carried by the inspection equipment or inspector. The starting and ending locations of the inspection routes can be obtained based on the pipeline distribution.
[0188] In some embodiments, the government gas supervision and management platform can randomly select inspection routes as initial inspection routes and randomly assign them to inspection equipment (or inspectors), thereby randomly generating multiple candidate allocation parameters.
[0189] For more information about inspection type parameters, inspection equipment, inspectors, pipeline distribution and other related parameters, please refer to Figure 2 Related description.
[0190] Step 520, determining an estimated inspection time based on the candidate allocation parameters.
[0191] The estimated inspection time refers to the estimated inspection time. The inspection time refers to the time required to inspect all objects of a category to be inspected. For example, 6 hours, 10 hours, etc. Each category of objects to be inspected has a plurality of candidate allocation parameters corresponding to each category, and each candidate allocation parameter corresponds to an estimated inspection time. In some embodiments, the government gas regulatory management platform can determine the estimated inspection time in a variety of ways based on the candidate allocation parameters. For example, the government gas regulatory management platform can determine the estimated inspection time by vector matching.
[0192] In some embodiments, for a class of objects to be inspected, the government gas supervision and management platform can construct a second vector database based on historical data, and the second vector database includes multiple second reference vectors and corresponding reference inspection times. A second reference vector can be obtained based on the historical data of the class of objects to be inspected, and a second reference vector can be constructed by the number of historical inspection routes, historical pipeline distribution, historical pipeline supervision information and historical facility supervision information of the class of objects to be inspected, and the historical inspection allocation parameters of the class of objects to be inspected. The reference inspection time can be the corresponding historical actual inspection time.
[0193] For a class of objects to be inspected, the government gas supervision and management platform can construct a second target vector based on the number of current inspection routes, pipeline distribution, pipeline supervision information and facility supervision information in the class of objects to be inspected, as well as the candidate allocation parameters of the class of objects to be inspected.
[0194] In some embodiments, the government gas regulatory management platform can retrieve one or more second reference vectors whose vector distance from the second target vector is less than a distance threshold from the second vector database, average the one or more reference inspection times corresponding to the one or more second reference vectors, and determine the average value as the estimated inspection time.
[0195] The vector distance may be any one of Euclidean distance, cosine distance, Mahalanobis distance, etc. The distance threshold may be determined manually based on prior experience or historical data.
[0196] In some embodiments, for a type of object to be inspected, the government gas supervision management platform can determine the estimated inspection time through a time model based on candidate allocation parameters, object type, pipeline distribution of inspection routes, pipeline supervision information and facility supervision information.
[0197] Object type refers to the category of the object to be inspected. In some embodiments, the object type may include drones, robots, and manual inspections, corresponding to drone inspection routes, robot inspection routes, and manual inspection routes, respectively. Time model refers to a model used to determine the estimated inspection time. In some embodiments, the time model may be a machine learning model, such as a neural network (NN). One type of object to be inspected has a corresponding time model. Three types of objects to be inspected correspond to three time models.
[0198] In some embodiments, Figure 6 As shown, the input of the time model 630 may include candidate allocation parameters 610 , object type 620 , and pipeline distribution 310 - 1 of the inspection route, pipeline supervision information 310 - 2 , and facility supervision information 310 - 3 , and the output may be an estimated inspection time 640 .
[0199] In some embodiments, Figure 6 As shown, the input of the time model 630 may also include the estimated coverage 650 corresponding to the inspection route. For more information about pipeline distribution, pipeline supervision information, facility supervision information and estimated coverage, please refer to Figure 2 Related description.
[0200] In some embodiments of the present specification, adding the estimated coverage corresponding to the inspection route as the input of the time model can make the prediction of the estimated inspection time more accurate.
[0201] In some embodiments, for a class of objects to be inspected, the government gas supervision management platform can train the time model corresponding to the class of objects to be inspected based on multiple second training samples with second labels. The second training samples may include sample inspection allocation parameters, sample object types, and sample pipeline distribution of sample inspection routes, sample pipeline supervision information, sample facility supervision information, and sample inspection coverage. The second label may be the actual inspection time corresponding to the second training sample. The second training sample and the second label may be obtained through historical data.
[0202] In some embodiments, the government gas supervision and management platform can use the second training sample to train the time model, input the sample inspection allocation parameters, sample object type, sample pipeline distribution of the sample inspection route, sample pipeline supervision information, sample facility supervision information and sample inspection coverage into the initial time model, construct the second loss function through the second label and the result of the initial time model, and iteratively update the parameters of the time model based on the second loss function through gradient descent or other methods. When the preset conditions are met, the time model training is completed. Among them, the preset conditions can be that the second loss function converges, the number of iterations reaches a threshold, etc.
[0203] In some embodiments, the inspection model and the temporal model may be trained jointly.
[0204] In some embodiments, the government gas supervision and management platform can jointly train the inspection model and the time model based on multiple third training samples with third labels. The third training samples may include sample inspection allocation parameters, sample object types, and sample pipeline distribution of sample inspection routes, sample pipeline supervision information, and sample facility supervision information. The third label may be the actual inspection time, actual inspection accuracy, and actual inspection success rate corresponding to the third training sample. The third training sample and the third label can be obtained through historical data.
[0205] For the drone inspection routes, the third training samples can be sample inspection allocation parameters, sample object types and first-category training samples; for the robot inspection routes, the third training samples can be sample inspection allocation parameters, sample object types and second-category training samples; for the manual inspection routes, the third training samples can be sample inspection allocation parameters, sample object types and third-category training samples, which are respectively used for the joint training of three time models and inspection models applicable to the three types of objects to be inspected.
[0206] In some embodiments, for a type of object to be inspected (e.g., drone inspection routes), the government gas supervision and management platform can use the corresponding third training samples to jointly train the inspection model and the time model, and input the sample pipeline distribution, sample pipeline supervision information, and sample facility supervision information of the sample inspection routes into the inspection model. The output layer corresponding to the inspection model (e.g., drone output layer) outputs the corresponding estimated coverage, estimated accuracy, and estimated success rate. The estimated coverage output by the inspection model and the third training samples are input into the time model to output the estimated inspection time.
[0207] The first loss term is constructed by the actual inspection accuracy and the actual inspection success rate (third label), and the estimated accuracy and the estimated success rate (output result) output by the inspection model; the second loss term is constructed by the actual inspection time (third label) and the estimated inspection time (output result) output by the inspection model. In some embodiments, the loss function of the joint training can be determined based on the weighted sum of the first loss term and the second loss term. Among them, the sum of the weight of the first loss term and the weight of the second loss term is 1. In some embodiments, the weight of the first loss term can be determined based on at least one of the inspection scale and the amount of negative user feedback. For example, the government gas supervision and management platform can determine the weight of the first loss term based on a preset corresponding relationship. The preset corresponding relationship can be preset manually. For example, the inspection scale is negatively correlated with the weight of the first loss term, and the amount of negative user feedback is positively correlated with the weight of the first loss term.
[0208] Among them, the inspection scale refers to the scale of the inspection operation. For example, the inspection scale can be represented by the size of the inspection area, the total length of the inspection route, etc. The amount of user negative feedback refers to the number of user negative feedback. For example, the amount of user negative feedback can be represented by the number of users' negative reviews, etc.
[0209] In some embodiments of the present specification, the loss function of the joint training is determined based on the weighted sum of the first loss term and the second loss term, and the weight is determined based on the inspection scale or the amount of negative user feedback. This can make the loss function of the joint training more accurate and facilitate dynamic determination of the loss function based on actual conditions.
[0210] In some embodiments, the government gas supervision and management platform can iteratively update the parameters of the inspection model and the time model based on the loss function of the joint training by gradient descent or other methods. When the preset conditions are met, the training is completed and the trained inspection model and time model are obtained. The preset conditions may be that the loss function of the joint training converges, the number of iterations reaches a threshold, etc.
[0211] In some embodiments of the present specification, by jointly training the inspection model and the time model, the accuracy of the inspection model and the time model can be further improved, making the estimation of the inspection time more accurate.
[0212] In some embodiments of the present specification, the estimated inspection time of the object to be inspected can be determined quickly and accurately through a machine learning model, which is conducive to the reasonable selection of inspection type parameters for subsequent inspection routes.
[0213] Step 530: Determine inspection allocation parameters based on the estimated inspection time.
[0214] In some embodiments, the government gas regulatory management platform may determine the candidate allocation parameter with the shortest estimated inspection time as the inspection allocation parameter.
[0215] In some embodiments of the present specification, candidate allocation parameters for each type of inspection object are determined based on the inspection type parameters, and then the estimated inspection time of each candidate allocation parameter is determined, and the inspection allocation parameter with the shortest inspection time is further selected, which is beneficial to reducing time consumption during the inspection process and improving inspection efficiency.
[0216] One or more embodiments of this specification provide a smart gas supervision information device. The device includes at least one memory and at least one processor, the at least one memory is used to store computer instructions, and the at least one processor executes the computer instructions or part of the instructions to implement a smart gas supervision information inspection method.
[0217] One or more embodiments of the present specification provide a computer-readable storage medium. The storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes a method for inspecting smart gas supervision information.
[0218] Certain features, structures or characteristics of one or more embodiments of this specification may be appropriately combined.
[0219] 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 this specification are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.
[0220] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.
Claims
1. A method for inspecting smart gas supervision information, characterized in that: The method is implemented based on a smart gas supervision information Internet of Things system, which includes a people's user platform, a citizen cloud service platform, a government gas supervision management platform, a government gas supervision sensor network platform, a government gas supervision object platform, a gas company sensor network platform, and a gas equipment object platform. The government gas supervision object platform includes a gas company management platform. The method is executed by the government gas supervision management platform, and the method includes: Based on the gas company management platform, obtain the inspection route; Segmenting the inspection route to determine a plurality of inspection sub-routes, and storing the plurality of inspection sub-routes in the government gas supervision object platform; Generate a call instruction and send it to the gas company management platform in the government gas supervision object platform for execution, wherein the call instruction is used to obtain pipeline supervision information corresponding to the multiple inspection routes, wherein the pipeline supervision information includes at least one of pipeline defect information and pipeline inspection results in the first historical time period; Generate a collection instruction based on the gas company management platform and send it to the gas equipment object platform for execution, wherein the collection instruction is used to control the gas auxiliary facilities deployed on the multiple inspection sub-lines to collect and upload facility supervision information; Determine inspection type parameters of the multiple inspection sub-routes based on the pipeline supervision information and the facility supervision information, wherein the inspection type parameters include at least one of drone inspection, robot inspection, and manual inspection; Determining inspection allocation parameters based on the inspection type parameters; Generate an inspection instruction and send it to the gas equipment object platform for execution, wherein the inspection instruction is used to control the inspection equipment and / or inspectors to execute the inspection allocation parameters; During the inspection process, In response to the actual coverage of one or more of the inspection sub-routes satisfying the first preset condition, updating the inspection sub-routes to obtain new inspection sub-routes, wherein the new inspection sub-routes include uncovered sub-routes; Adjusting the inspection allocation parameters based on the uncovered branch routes; Sending the updated inspection allocation parameters to the gas equipment object platform for execution; After the inspection is completed, the current pipeline inspection results and the pipeline defect information corresponding to the new inspection route are sent to the gas company management platform in the government gas supervision object platform for storage.
2. The method according to claim 1, characterized in that The determining, based on the pipeline supervision information and the facility supervision information, the inspection type parameters of the multiple inspection sub-routes includes: Through the government gas regulatory management platform: Based on the pipeline supervision information and the facility supervision information, predict the estimated inspection effect of the inspection type parameter, wherein the estimated inspection effect includes an estimated accuracy and an estimated coverage; Based on the estimated inspection effect that meets the second preset condition, the inspection type parameter of the inspection route is determined.
3. The method according to claim 2, characterized in that The method further comprises: Through the government gas regulatory management platform: In response to the absence of the estimated inspection effect that satisfies the second preset condition, at least one target sub-route and an adjustment type of the target sub-route are determined, the adjustment type comprising a first type corresponding to the estimated coverage being less than a first threshold, and a second type corresponding to the estimated accuracy being less than a second threshold; the first threshold is determined based on at least one of the density of the gas ancillary facilities of the inspection sub-route, data redundancy or fault correlation; the second threshold is positively correlated to the gas risk value corresponding to the inspection sub-route; In response to the adjustment type being the first type, the target sub-route is adjusted based on the estimated inspection effect corresponding to the target sub-route to obtain a new target sub-route.
4. The method according to claim 3, characterized in that The method further comprises: Through the government gas regulatory management platform: In response to the adjustment type being the second type, the inspection type parameter of the target sub-route is updated based on the estimated inspection effect corresponding to the target sub-route.
5. The method according to claim 1, characterized in that The determining of the inspection allocation parameter based on the inspection type parameter includes: Through the government gas regulatory management platform: Based on the inspection type parameter, the multiple inspection routes are divided into three types of objects to be inspected, and candidate allocation parameters of the objects to be inspected are determined; Determining an estimated inspection time based on the candidate allocation parameters; Based on the estimated inspection time, the inspection allocation parameter is determined.
6. A smart gas supervision information Internet of Things system, characterized in that: The smart gas supervision information IoT system includes a people's user platform, a citizen cloud service platform, a government gas supervision management platform, a government gas supervision sensor network platform, a government gas supervision object platform, a gas company sensor network platform and a gas equipment object platform; The people user platform and the citizen cloud service platform interact in a two-way manner; The government gas supervision and management platform interacts with the citizen cloud service platform in a two-way manner upwards and interacts with the government gas supervision sensor network platform in a two-way manner downwards. The government gas supervision and management platform is used to: Obtain inspection routes based on the gas company management platform; Segmenting the inspection route to determine a plurality of inspection sub-routes, and storing the plurality of inspection sub-routes in the government gas supervision object platform; Generate a call instruction and send it to the gas company management platform in the government gas supervision object platform for execution, wherein the call instruction is used to obtain pipeline supervision information corresponding to the multiple inspection routes, wherein the pipeline supervision information includes at least one of pipeline defect information and pipeline inspection results in the first historical time period; Generate a collection instruction based on the gas company management platform and send it to the gas equipment object platform for execution, wherein the collection instruction is used to control the gas auxiliary facilities deployed on the multiple inspection sub-lines to collect and upload facility supervision information; Determine inspection type parameters of the multiple inspection sub-routes based on the pipeline supervision information and the facility supervision information, wherein the inspection type parameters include at least one of drone inspection, robot inspection, and manual inspection; Determining inspection allocation parameters based on the inspection type parameters; Generate an inspection instruction and send it to the gas equipment object platform for execution, wherein the inspection instruction is used to control the inspection equipment and / or inspectors to execute the inspection allocation parameters; During the inspection process, In response to the actual coverage of one or more of the inspection sub-routes satisfying the first preset condition, updating the inspection sub-routes to obtain new inspection sub-routes, wherein the new inspection sub-routes include uncovered sub-routes; Adjusting the inspection allocation parameters based on the uncovered branch routes; Sending the updated inspection allocation parameters to the gas equipment object platform for execution; After the inspection is completed, the current pipeline inspection result and the pipeline defect information corresponding to the new inspection route are sent to the gas company management platform in the government gas supervision object platform for storage; The government gas regulatory sensor network interacts downward with the government gas regulatory object platform in a two-way manner; The government gas supervision object platform interacts bidirectionally downward with the gas company sensor network platform. The government gas supervision object platform includes a gas company management platform. The government gas supervision object platform is used to store the multiple inspection routes and the pipeline supervision information, and execute the call instruction issued by the government gas supervision management platform. The gas company management platform is used to obtain the inspection route; The gas company sensor network platform interacts downward with the gas equipment object platform in a two-way manner, and the gas equipment object platform is used to execute the collection instructions and the inspection instructions issued by the government gas supervision and management platform.
7. The Internet of Things system according to claim 6, characterized in that: The government gas supervision and management platform is further used for: Based on the pipeline supervision information and the facility supervision information, predict the estimated inspection effect of the inspection type parameter, wherein the estimated inspection effect includes an estimated accuracy and an estimated coverage; Based on the estimated inspection effect that meets the second preset condition, the inspection type parameter of the inspection route is determined.
8. The Internet of Things system according to claim 7, characterized in that: The government gas supervision and management platform is further used for: In response to the absence of the estimated inspection effect that satisfies the second preset condition, at least one target sub-route and an adjustment type of the target sub-route are determined, the adjustment type comprising a first type corresponding to the estimated coverage being less than a first threshold, and a second type corresponding to the estimated accuracy being less than a second threshold; the first threshold is determined based on at least one of the density of the gas ancillary facilities of the inspection sub-route, data redundancy or fault correlation; the second threshold is positively correlated to the gas risk value corresponding to the inspection sub-route; In response to the adjustment type being the first type, the target sub-route is adjusted based on the estimated inspection effect corresponding to the target sub-route to obtain a new target sub-route.
