Water supply pipeline emergency processing method, system and equipment based on artificial neural network, storage medium and computer program product

Abstract

The invention discloses a water supply pipeline emergency processing method, system and device based on an artificial neural network, a storage medium and a computer program product, and the method comprises the steps: obtaining a water supply pipeline line structure of a target region and current pipeline water flow detection information, and recognizing abnormal sub-regions of different emergency levels of the target region; positioning an abnormal pipeline in each abnormal sub-region, and performing pipeline adjustment processing on each abnormal sub-region to obtain a substitute pipeline corresponding to each abnormal pipeline; collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region, and readjusting the alternative pipeline corresponding to each abnormal pipeline; and when the current emergency level of the abnormal sub-region is greater than a preset level threshold, returning to execute the acquisition step until the current emergency level of the abnormal sub-region is not greater than the preset level threshold, and completing the water supply pipeline emergency processing task. The method can improve the emergency disposal efficiency of the water supply pipeline.

Description

Technical Field

[0001] The present invention belongs to the technical field of emergency treatment of urban water supply pipelines, and specifically relates to an emergency treatment method, system, equipment, storage medium and computer program product for water supply pipelines based on artificial neural networks. Background Art

[0002] Urban water supply pipelines are a core component of municipal public infrastructure and are directly related to the health and quality of life of urban residents. With the acceleration of my country's urbanization process, the construction of urban water supply pipelines has shown a rapid growth trend. At present, urban water supply pipelines have been in use for a long time, and have serious aging and corrosion problems. At the same time, the pipelines are underground, invisible, difficult to operate and maintain, and water supply pipeline network burst accidents occur frequently.

[0003] Traditional emergency treatment of water supply pipelines relies on manual inspection and positioning, which involves large-scale water cut-off and manual inspection of pipeline fault areas, resulting in low efficiency of water supply pipeline inspection and investigation, and failure to solve problems in a timely and accurate manner, which not only affects the production of urban enterprises and the lives of residents, but also causes serious waste of water resources. In view of this, with the needs of the development of urban infrastructure construction, an emergency treatment method and system for water supply pipelines based on artificial neural networks is proposed to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to solve the deficiencies of the above-mentioned background technology and to provide a water supply pipeline emergency treatment method, system, equipment, storage medium and computer program product based on artificial neural network.

[0005] In a first aspect, the present invention provides a water supply pipeline emergency treatment method based on an artificial neural network, comprising the following steps:

[0006] Acquire the water supply pipeline line structure of the target area and the current pipeline water flow detection information, and identify the abnormal sub-areas of different emergency levels of the target area based on the pipeline water flow detection information;

[0007] Based on the water supply pipeline line structure and the pipeline water flow detection information, the abnormal pipeline in each abnormal sub-region is located through the regional positioning strategy, and based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, the pipeline adjustment processing is performed on each abnormal sub-region through an artificial neural network to obtain a replacement pipeline corresponding to each abnormal pipeline;

[0008] Collecting current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-areas, and based on the current pipeline detection information of each of the abnormal pipelines, readjusting the alternative pipeline corresponding to each of the abnormal pipelines through the artificial neural network;

[0009] When the current emergency level of the abnormal sub-area is greater than the preset level domain value, return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, until there is no abnormal sub-area with a current emergency level greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

[0010] Optionally, the identifying abnormal sub-areas of different emergency levels in the target area based on the pipeline water flow detection information includes:

[0011] Based on the pipeline water flow detection information, the pipeline water flow state of each pipeline is identified, and among the pipelines, pipelines with abnormal pipeline water flow states are screened as candidate abnormal pipelines, and clustering processing is performed on the candidate abnormal pipelines to obtain abnormal sub-regions;

[0012] For each abnormal sub-region, identify the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and collect the area range of the abnormal sub-region in the target area;

[0013] Based on the regional range of the abnormal sub-region in the target region, querying the regional criticality of the abnormal sub-region in the regional database, and determining the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region;

[0014] Based on the number of candidate abnormal pipelines in the abnormal sub-area, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-area, the abnormal score value corresponding to the abnormal sub-area is calculated through the abnormal area scoring strategy, and the emergency level of the abnormal sub-area is determined based on the abnormal score value.

[0015] Optionally, the calculating of the abnormal score value corresponding to the abnormal sub-region by an abnormal region scoring strategy based on the number of candidate abnormal pipelines in the abnormal sub-region, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-region includes:

[0016] Based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, a first number of each abnormal level in the abnormal sub-region is identified, and based on the first number of the abnormal sub-region and the second number of each candidate abnormal pipeline in the abnormal sub-region, a first abnormal score value of the abnormal sub-region is queried in a pipeline database;

[0017] The first anomaly score value is weighted and summed by the criticality weight value of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

[0018] Optionally, locating the abnormal pipeline in each abnormal sub-region through a regional positioning strategy based on the water supply pipeline line structure and the pipeline water flow detection information includes:

[0019] For each abnormal sub-region, based on the water supply pipeline line structure, pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region is identified, and based on the pipeline flow direction information of each candidate pipeline, pipeline association information of each candidate abnormal pipeline is identified;

[0020] Based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, the abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is used as the abnormal pipeline of the abnormal sub-area.

[0021] Optionally, based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, performing pipeline adjustment processing on each abnormal sub-region through an artificial neural network to obtain a replacement pipeline corresponding to each abnormal pipeline includes:

[0022] For each abnormal sub-area, based on the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery is identified, and based on the position information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery, and the water supply pipeline line structure, through the route planning layer of the artificial neural network, each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route are calculated;

[0023] Based on each water delivery route of each initial alternative pipeline and the water delivery time of each water delivery route, an initial alternative pipeline including all water flow routes and having the shortest water delivery time of all water delivery routes is selected from each of the initial alternative pipelines as the initial alternative pipeline corresponding to the abnormal pipeline;

[0024] Based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-area and the water delivery routes corresponding to each initial alternative pipeline, the water delivery routes of each initial alternative pipeline are adjusted through the route adjustment layer of the artificial neural network to obtain the alternative pipelines corresponding to each abnormal pipeline.

[0025] Optionally, before collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, the method further includes:

[0026] For each abnormal sub-region, based on the abnormal level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-region, query the abnormal handling strategy of the abnormal pipeline in the strategy database, and collect the pipeline abnormal information template;

[0027] Based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, in each of the abnormal handling strategies, the target abnormal handling strategy corresponding to the abnormal pipeline is matched, and the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target abnormal handling strategy of the abnormal pipeline are filled into the abnormal information template to obtain the abnormal handling reporting information of the abnormal pipeline;

[0028] The exception handling reporting information and the location information of the abnormal pipeline are sent to the staff client.

[0029] Optionally, the readjusting the alternative pipeline corresponding to each abnormal pipeline through the artificial neural network based on the current pipeline detection information of each abnormal pipeline includes:

[0030] Based on the current pipeline detection information of each abnormal pipeline, the current abnormal level and the current pipeline water flow state of the abnormal pipeline are identified, and the pipeline water flow state of each abnormal pipeline is replaced by the current pipeline water flow state of each abnormal pipeline, and the abnormal level of each abnormal pipeline is replaced by the current abnormal level of each abnormal pipeline;

[0031] Return to execute based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, perform pipeline adjustment processing on each abnormal sub-area through an artificial neural network, and obtain the replacement pipeline step corresponding to each abnormal pipeline.

[0032] In a second aspect, the present invention also provides a water supply pipeline emergency treatment system based on an artificial neural network. The system comprises:

[0033] An acquisition module, used to acquire the water supply pipeline line structure of the target area and the current pipeline water flow detection information, and identify abnormal sub-areas of different emergency levels in the target area based on the pipeline water flow detection information;

[0034] An allocation module is used to locate the abnormal pipeline in each abnormal sub-region through a regional positioning strategy based on the line structure of the water supply pipeline and the pipeline water flow detection information, and to adjust the pipeline of each abnormal sub-region through an artificial neural network based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, so as to obtain a replacement pipeline corresponding to each abnormal pipeline;

[0035] an identification module, configured to collect current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-areas, and readjust the alternative pipeline corresponding to each of the abnormal pipelines through the artificial neural network based on the current pipeline detection information of each of the abnormal pipelines;

[0036] The iterative module is used to return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area when the current emergency level of the abnormal sub-area is greater than the preset level domain value, until the current emergency level of the abnormal sub-area is greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

[0037] Optionally, the acquisition module is specifically used to:

[0038] Based on the pipeline water flow detection information, the pipeline water flow state of each pipeline is identified, and among the pipelines, pipelines with abnormal pipeline water flow states are screened as candidate abnormal pipelines, and clustering processing is performed on the candidate abnormal pipelines to obtain abnormal sub-regions;

[0039] For each abnormal sub-region, identify the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and collect the area range of the abnormal sub-region in the target area;

[0040] Based on the regional range of the abnormal sub-region in the target region, querying the regional criticality of the abnormal sub-region in the regional database, and determining the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region;

[0041] Based on the number of candidate abnormal pipelines in the abnormal sub-area, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-area, the abnormal score value corresponding to the abnormal sub-area is calculated through the abnormal area scoring strategy, and the emergency level of the abnormal sub-area is determined based on the abnormal score value.

[0042] Optionally, the acquisition module is specifically used to:

[0043] Based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, a first number of each abnormal level in the abnormal sub-region is identified, and based on the first number of the abnormal sub-region and the second number of each candidate abnormal pipeline in the abnormal sub-region, a first abnormal score value of the abnormal sub-region is queried in a pipeline database;

[0044] The first anomaly score value is weighted and summed by the criticality weight value of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

[0045] Optionally, the allocation module is specifically used to:

[0046] For each abnormal sub-region, based on the water supply pipeline line structure, pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region is identified, and based on the pipeline flow direction information of each candidate pipeline, pipeline association information of each candidate abnormal pipeline is identified;

[0047] Based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, the abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is used as the abnormal pipeline of the abnormal sub-area.

[0048] Optionally, the allocation module is specifically used to:

[0049] For each abnormal sub-area, based on the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery is identified, and based on the position information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery, and the water supply pipeline line structure, through the route planning layer of the artificial neural network, each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route are calculated;

[0050] Based on each water delivery route of each initial alternative pipeline and the water delivery time of each water delivery route, an initial alternative pipeline including all water flow routes and having the shortest water delivery time of all water delivery routes is selected from each of the initial alternative pipelines as the initial alternative pipeline corresponding to the abnormal pipeline;

[0051] Based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-area and the water delivery routes corresponding to each initial alternative pipeline, the water delivery routes of each initial alternative pipeline are adjusted through the route adjustment layer of the artificial neural network to obtain the alternative pipelines corresponding to each abnormal pipeline.

[0052] Optionally, the device further comprises:

[0053] A query module, for querying the abnormal handling strategy of the abnormal pipeline in each abnormal sub-region based on the abnormal level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-region in the strategy database, and collecting the pipeline abnormal information template;

[0054] A filling module is used to match the target exception handling strategy corresponding to the abnormal pipeline in each of the exception handling strategies based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, and fill the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target exception handling strategy of the abnormal pipeline into the exception information template to obtain the exception handling reporting information of the abnormal pipeline;

[0055] The sending module is used to send the exception handling reporting information and the location information of the abnormal pipeline to the staff client.

[0056] Optionally, the identification module is specifically used to:

[0057] Based on the current pipeline detection information of each abnormal pipeline, the current abnormal level and the current pipeline water flow state of the abnormal pipeline are identified, and the pipeline water flow state of each abnormal pipeline is replaced by the current pipeline water flow state of each abnormal pipeline, and the abnormal level of each abnormal pipeline is replaced by the current abnormal level of each abnormal pipeline;

[0058] Return to execute based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, perform pipeline adjustment processing on each abnormal sub-area through an artificial neural network, and obtain the replacement pipeline step corresponding to each abnormal pipeline.

[0059] In a third aspect, the present invention provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0060] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0061] In a fifth aspect, the present invention provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] The present invention discloses an artificial neural network-based water supply pipeline emergency treatment method and system. The method and system obtain the water supply pipeline line structure and current pipeline water flow detection information of the target area, and identify the abnormal sub-areas of different emergency levels of the target area based on the pipeline water flow detection information; locate the abnormal pipeline in each abnormal sub-area based on the water supply pipeline line structure and the pipeline water flow detection information through the regional positioning strategy, and perform pipeline adjustment processing on each abnormal sub-area based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area through the artificial neural network to obtain the replacement pipeline corresponding to each abnormal pipeline; collect the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, and readjust the replacement pipeline corresponding to each abnormal pipeline through the artificial neural network based on the current pipeline detection information of each abnormal pipeline; in the case that the current emergency level of the abnormal sub-area is greater than the preset level threshold value, return to execute the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area until the current emergency level of the abnormal sub-area is greater than the preset level threshold value, and the water supply pipeline emergency treatment task is completed. The present invention uses pipeline water flow detection information and water supply pipeline line structure, divides abnormal sub-areas of different emergency levels, and regional positioning strategies to accurately locate each abnormal pipeline, and then identifies alternative pipelines that can replace the abnormal pipeline through artificial neural networks, thereby avoiding the problem of affecting the normal water supply of the crowd. Finally, by regularly collecting the current pipeline detection information of the abnormal pipeline, the maintenance status of the abnormal pipeline is regularly identified, so that the water delivery status of each pipeline is adjusted in real time based on the pipeline maintenance status, thereby reducing the water supply pressure of each alternative pipeline, so that each water supply pipeline can operate efficiently and normally, so that this solution can avoid affecting the normal water demand of the crowd by intelligently planning alternative tracks and intelligently detecting pipeline status, while improving the emergency disposal efficiency of the water supply pipeline. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic flow chart of a water supply pipeline emergency treatment method based on an artificial neural network in one embodiment;

[0065] Figure 2 is a structural block diagram of a water supply pipeline emergency treatment system based on an artificial neural network in one embodiment;

[0066] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention, and is only used as an example. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other. At the same time, the advantages of the present invention will become clearer and easier to understand by explaining.

[0068] The artificial neural network-based emergency treatment method for water supply pipelines provided in the embodiment of the present application can be applied to the application environment of urban underground water supply pipelines. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. Among them, the terminal accurately locates each abnormal pipeline by dividing the abnormal sub-areas of different emergency levels and the regional positioning strategy through the pipeline water flow detection information and the water supply pipeline line structure, and then identifies the alternative pipeline that can replace the abnormal pipeline through the artificial neural network, so as to avoid affecting the normal water supply of the crowd. Finally, by regularly collecting the current pipeline detection information of the abnormal pipeline, the maintenance status of the abnormal pipeline is regularly identified, so that the water delivery status of each pipeline is adjusted in real time based on the pipeline maintenance status, thereby reducing the water supply pressure of each alternative pipeline, so that each water supply pipeline can be efficiently and normally operated, so that this scheme can avoid affecting the normal water demand of the crowd by intelligently planning the alternative track and intelligently detecting the pipeline status, while improving the emergency disposal efficiency of the water supply pipeline.

[0069] In one embodiment, Figure 1 As shown, a water supply pipeline emergency treatment method based on an artificial neural network is provided, and the method is applied to a terminal as an example for explanation, and includes the following steps:

[0070] Step S101, obtaining the water supply pipeline line structure of the target area and the current pipeline water flow detection information, and identifying abnormal sub-areas of different emergency levels in the target area based on the pipeline water flow detection information.

[0071] In this embodiment, the terminal responds to the pipeline structure transmission operation of the municipal client to obtain the water supply pipeline line structure of the target area, wherein the target area may be, but is not limited to, a municipal administrative area, a provincial administrative area, an urban area, a prosperous urban area, etc. The water supply pipeline line structure includes the connection relationship of each water supply pipeline, the water transmission rate of each water supply pipeline, and the pipeline length of each water supply pipeline. Then, the terminal divides the target area into abnormal sub-areas of different emergency levels, wherein the emergency levels of different abnormal sub-areas may be different or the same, and each abnormal sub-area does not overlap. The emergency level is used to characterize the water supply demand of the abnormal sub-area. The higher the emergency level, the greater the water supply demand of the abnormal sub-area, and the more complex the abnormal pipeline situation; the lower the emergency level, the smaller the drainage and water supply demand of the abnormal sub-area, and the simpler the abnormal pipeline situation. The specific process of identifying the emergency level will be described in detail later. Among them, the current pipeline water flow detection information is the pipe pressure information in the pipeline collected by the water flow sensor set at each position point of the pipeline in the current period, and the water flow velocity information in the pipeline.

[0072] Step S102, based on the water supply pipeline line structure and pipeline water flow detection information, the abnormal pipeline in each abnormal sub-area is located through the regional positioning strategy, and based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, the pipeline adjustment processing is performed on each abnormal sub-area through an artificial neural network to obtain the replacement pipeline corresponding to each abnormal pipeline.

[0073] In this embodiment, the terminal locates the abnormal pipes in each abnormal sub-area based on the line structure of the water supply pipeline and the pipeline water flow detection information through the regional positioning strategy, and based on the emergency level corresponding to each abnormal sub-area and the abnormal pipes corresponding to each abnormal sub-area, the terminal adjusts the pipes of each abnormal sub-area through the artificial neural network to obtain the replacement pipes corresponding to each abnormal pipe. The regional positioning strategy is a strategy corresponding to the neural network with the self-attention mechanism. The specific positioning process will be described in detail later.

[0074] Step S103, collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, and based on the current pipeline detection information of each abnormal pipeline, readjusting the replacement pipeline corresponding to each abnormal pipeline through an artificial neural network.

[0075] In this embodiment, the terminal collects the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, and readjusts the alternative pipeline corresponding to each abnormal pipeline through an artificial neural network based on the current pipeline detection information of each abnormal pipeline. The process of adjusting the alternative pipeline is substantially the same as the process of selecting the alternative pipeline for each abnormal pipeline.

[0076] Step S104, when the current emergency level of an abnormal sub-area is greater than the preset level domain value, return to execute the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, until the current emergency level of no abnormal sub-area is greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

[0077] In this embodiment, when the current emergency level of an abnormal sub-area is greater than the preset level domain value, the terminal returns to execute the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, until the current emergency level of no abnormal sub-area is greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

[0078] Based on the above scheme, through pipeline water flow detection information and water supply pipeline line structure, by dividing abnormal sub-areas of different emergency levels and regional positioning strategies, each abnormal pipeline can be accurately located, and then, through artificial neural networks, alternative pipelines that can replace the abnormal pipelines can be identified to avoid affecting the normal water supply of the crowd. Finally, by regularly collecting the current pipeline detection information of the abnormal pipeline, the maintenance status of the abnormal pipeline can be regularly identified, so that the water delivery status of each pipeline can be adjusted in real time based on the pipeline maintenance status, thereby reducing the water supply pressure of each alternative pipeline, so that each water supply pipeline can operate efficiently and normally, so that this scheme can avoid affecting the normal water demand of the crowd by intelligently planning alternative tracks and intelligently detecting pipeline status, while improving the emergency response efficiency of water supply pipelines.

[0079] Optionally, based on the pipeline water flow detection information, identifying abnormal sub-regions of different emergency levels in the target area, including: based on the pipeline water flow detection information, identifying the pipeline water flow state of each pipeline, and screening the pipelines with abnormal pipeline water flow states in each pipeline as candidate abnormal pipelines, and clustering the candidate abnormal pipelines to obtain each abnormal sub-region; for each abnormal sub-region, identifying the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and collecting the regional range of the abnormal sub-region in the target area; based on the regional range of the abnormal sub-region in the target area, querying the regional criticality of the abnormal sub-region in the regional database, and determining the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region; based on the number of candidate abnormal pipelines in the abnormal sub-region, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-region, calculating the abnormal score value corresponding to the abnormal sub-region through the abnormal area scoring strategy, and determining the emergency level of the abnormal sub-region based on the abnormal score value.

[0080] In this embodiment, the terminal identifies the pipeline water flow state of each pipeline based on the pipeline water flow detection information, and selects pipelines with abnormal pipeline water flow states from each pipeline as candidate abnormal pipelines, and clusters the candidate abnormal pipelines to obtain abnormal sub-regions. Each abnormal sub-region is a region range including candidate abnormal pipelines and normal pipelines.

[0081] The terminal identifies the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline for each abnormal sub-region, and collects the regional range of the abnormal sub-region in the target region. Then, based on the regional range of the abnormal sub-region in the target region, the terminal queries the regional criticality of the abnormal sub-region in the regional database, and determines the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region. Among them, each target area is divided into regional ranges of different criticalities by range division, wherein the higher the criticality, the higher the water supply urgency of the region, and the lower the criticality, the lower the water supply urgency of the region. For example, the criticality of the bustling central area of ​​the city, the school area, the hospital area, the residential area, and the factory area is high, and the criticality of the abandoned building area and the area with low population density is low. The process of determining the criticality weight by the criticality is to obtain the criticality weight corresponding to each criticality after normalizing the criticality.

[0082] Based on the number of candidate abnormal pipelines in the abnormal sub-region, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-region, the terminal calculates the abnormal score value corresponding to the abnormal sub-region through the abnormal region scoring strategy, and determines the emergency level of the abnormal sub-region based on the abnormal score value. The specific calculation process will be described in detail later.

[0083] Based on the above scheme, the emergency level of the abnormal sub-area is determined by screening different criticality areas, different numbers of candidate abnormal pipelines, and abnormal levels of different abnormal pipelines, thereby improving the accuracy of determining the emergency level of the abnormal sub-area.

[0084] Optionally, based on the number of candidate abnormal pipelines in the abnormal sub-region, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-region, an abnormality score value corresponding to the abnormal sub-region is calculated through an abnormal region scoring strategy, including: based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, identifying a first number of abnormal levels in the abnormal sub-region, and based on the first number of abnormal sub-regions and the second number of candidate abnormal pipelines in the abnormal sub-region, querying a first abnormality score value of the abnormal sub-region in a pipeline database; and performing weighted sum processing on the first abnormal score value through the criticality weight value of the abnormal sub-region to obtain the abnormal score value of the abnormal sub-region.

[0085] In this embodiment, the terminal identifies the first number of each abnormal level in the abnormal sub-region based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and queries the first abnormal score value of the abnormal sub-region in the pipeline database based on the first number of abnormal sub-regions and the second number of each candidate abnormal pipeline in the abnormal sub-region. Then, the terminal performs weighted summation processing on the first abnormal score value by the criticality weight value of the abnormal sub-region to obtain the abnormal score value of the abnormal sub-region.

[0086] Based on the above scheme, the number of abnormal pipelines and the number of each abnormal level of the abnormal pipelines are weighted by the weight value corresponding to the criticality, thereby improving the accuracy of the abnormal score value of the determined abnormal sub-area.

[0087] Optionally, based on the water supply pipeline line structure and the pipeline water flow detection information, the abnormal pipeline in each abnormal sub-region is located through a regional positioning strategy, including: for each abnormal sub-region, based on the water supply pipeline line structure, identifying the pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region, and based on the pipeline flow direction information of each candidate pipeline, identifying the pipeline association information of each candidate abnormal pipeline; based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, identifying the abnormal pipeline in each candidate abnormal pipeline through a self-attention network, and taking the abnormal pipeline as the abnormal pipeline of the abnormal sub-region.

[0088] In this embodiment, for each abnormal sub-region, the terminal identifies the pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region based on the line structure of the water supply pipeline, and identifies the pipeline association information of each candidate abnormal pipeline based on the pipeline flow direction information of each candidate pipeline. The pipeline association information includes the connection information between each pipeline, and the water flow relationship between each adjacent sequence of pipelines in the flow order of water flowing through each pipeline.

[0089] Based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, the terminal identifies the abnormal pipeline in each candidate abnormal pipeline through the self-attention network, and uses the abnormal pipeline as the abnormal pipeline of the abnormal sub-region. Among them, the abnormal level of the abnormal pipeline is low, and the abnormal level of the water flow through the pipeline after the abnormal pipeline should be gradually higher. For example, if the water pipe of pipeline A is broken, the abnormal level of pipeline A is A1. Since the subsequent pipelines receive less water flow, the water flow rate of the subsequent pipelines is slower and the pipeline pressure is smaller, so the abnormal level of the subsequent pipelines should be greater than A1.

[0090] Based on the above solution, the abnormal pipelines in the candidate abnormal pipelines are identified by considering the pipeline flow direction and pipeline association information, thereby improving the accuracy of identifying the abnormal pipelines.

[0091] Optionally, based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, an artificial neural network is used to perform pipeline adjustment processing on each abnormal sub-area to obtain an alternative pipeline corresponding to each abnormal pipeline, including: for each abnormal sub-area, based on the water supply pipeline line structure, identifying each water flow route of the abnormal pipeline water supply, and based on the position information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water supply, and the water supply pipeline line structure, calculating each water supply route of each initial alternative pipeline and the water supply time of each water supply route through the route planning layer of the artificial neural network; based on each water supply route of each initial alternative pipeline and the water supply time of each water supply route, selecting an initial alternative pipeline containing all water flow routes and having the shortest water supply time of all water supply routes from each initial alternative pipeline as the initial alternative pipeline corresponding to the abnormal pipeline; based on the initial alternative pipeline corresponding to the abnormal pipeline in each abnormal sub-area and each water supply route corresponding to each initial alternative pipeline, adjusting each water supply route of each initial alternative pipeline through the route adjustment layer of the artificial neural network to obtain an alternative pipeline corresponding to each abnormal pipeline.

[0092] In this embodiment, for each abnormal sub-area, the terminal identifies each water flow route of the abnormal pipeline water delivery based on the water supply pipeline line structure, and calculates each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route through the route planning layer of the artificial neural network based on the location information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery, and the water supply pipeline line structure. Then, based on each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route, the terminal selects the initial replacement pipeline that contains all water flow routes and has the shortest water delivery time of all water delivery routes from each initial replacement pipeline as the initial replacement pipeline corresponding to the abnormal pipeline. For each abnormal sub-area, based on the line structure of the water supply pipeline, each water flow route of the abnormal pipeline water supply is identified, and based on the position information of each abnormal pipeline in the line structure of the water supply pipeline, each water flow route of the abnormal pipeline water supply, and the line structure of the water supply pipeline, the route planning layer of the artificial neural network is used to calculate each water supply route of each initial alternative pipeline and the water supply time of each water supply route; based on each water supply route of each initial alternative pipeline and the water supply time of each water supply route, in each initial alternative pipeline, the initial alternative pipeline containing all water flow routes and with the shortest water supply time of all water supply routes is selected as the initial alternative pipeline corresponding to the abnormal pipeline; based on the initial alternative pipeline corresponding to the abnormal pipeline in each abnormal sub-area and each water supply route corresponding to each initial alternative pipeline, the route adjustment layer of the artificial neural network is used to adjust each water supply route of each initial alternative pipeline to obtain the alternative pipeline corresponding to each abnormal pipeline.

[0093] Then, based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-area and the water delivery routes corresponding to each initial alternative pipeline, the terminal adjusts the water delivery routes of each initial alternative pipeline through the route adjustment layer of the artificial neural network to obtain the alternative pipelines corresponding to each abnormal pipeline. Among them, the route planning layer is a reinforcement learning neural network composed of multiple neurons. Among them, the route adjustment layer is the same as the neural network corresponding to the route planning layer.

[0094] Based on the above scheme, by screening each initial alternative pipeline and adjusting the water delivery route of each initial alternative pipeline, the pipelines of each pipeline can operate normally within the saturated operating range, thereby improving the water delivery efficiency of each alternative pipeline.

[0095] Optionally, before collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, it also includes: for each abnormal sub-area, based on the abnormal level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, querying the abnormal pipeline exception handling strategy in the policy database, and collecting the pipeline exception information template; based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, matching the target exception handling strategy corresponding to the abnormal pipeline in each exception handling strategy, and filling the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target exception handling strategy of the abnormal pipeline into the exception information template to obtain the exception handling reporting information of the abnormal pipeline; sending the exception handling reporting information and the location information of the abnormal pipeline to the staff client.

[0096] In this embodiment, for each abnormal sub-area, the terminal queries the abnormal pipeline abnormality handling strategy in the strategy database based on the abnormality level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, and collects the pipeline abnormality information template. Among them, the abnormality handling strategy is the processing strategy corresponding to different abnormality levels, and the processing strategy includes the required maintenance replacement materials, maintenance personnel experience, maintenance methods, maintenance time, and tools required for maintenance.

[0097] Based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, the terminal matches the target abnormal handling strategy corresponding to the abnormal pipeline in each abnormal handling strategy, and fills the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target abnormal handling strategy of the abnormal pipeline into the abnormal information template to obtain the abnormal handling report information of the abnormal pipeline. Finally, the terminal sends the abnormal handling report information and the location information of the abnormal pipeline to the staff client.

[0098] Based on the above solution, the staff's maintenance efficiency for each abnormal pipeline is improved by filtering the exception handling strategy and sending it to the staff client.

[0099] Optionally, based on the current pipeline detection information of each abnormal pipeline, the alternative pipeline corresponding to each abnormal pipeline is readjusted through an artificial neural network, including: based on the current pipeline detection information of each abnormal pipeline, the current abnormal level of the abnormal pipeline and the current pipeline water flow state are identified, and the current pipeline water flow state of each abnormal pipeline is replaced with the pipeline water flow state of each abnormal pipeline, and the current abnormal level of each abnormal pipeline is replaced with the abnormal level of each abnormal pipeline; return to execute based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, and perform pipeline adjustment processing on each abnormal sub-area through an artificial neural network to obtain the alternative pipeline step corresponding to each abnormal pipeline.

[0100] In this embodiment, the terminal identifies the current abnormal level of the abnormal pipeline and the current pipeline water flow state based on the current pipeline detection information of each abnormal pipeline, and replaces the pipeline water flow state of each abnormal pipeline with the current pipeline water flow state of each abnormal pipeline, and replaces the abnormal level of each abnormal pipeline with the current abnormal level of each abnormal pipeline. Then, the terminal returns to execute the pipeline adjustment processing for each abnormal sub-area based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area through the artificial neural network, and obtains the replacement pipeline step corresponding to each abnormal pipeline.

[0101] Based on the above scheme, by regularly collecting the current pipeline detection information of the abnormal pipeline, the maintenance status of the abnormal pipeline can be regularly identified, so that the water supply status of each pipeline can be adjusted in real time based on the pipeline maintenance status, thereby reducing the water supply pressure of each alternative pipeline, so that each water supply pipeline can operate efficiently and normally.

[0102] Based on the above scheme, the current maximum water delivery rate of each abnormal alternative pipeline is adjusted according to the current sewage discharge degree of the abnormal alternative pipeline to obtain the new water supply pipeline line structure, which improves the situation in which abnormal alternative pipelines exist. The new alternative pipelines corresponding to each abnormal pipeline can achieve the optimal sewage discharge rate.

[0103] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0104] Based on the same inventive concept, the embodiment of the present application also provides an artificial neural network-based water supply pipeline emergency treatment system for implementing the artificial neural network-based water supply pipeline emergency treatment method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the artificial neural network-based water supply pipeline emergency treatment system provided below can refer to the limitations of the artificial neural network-based water supply pipeline emergency treatment method above, and will not be repeated here.

[0105] In one embodiment, Figure 2 As shown, a water supply pipeline emergency treatment system based on artificial neural network is provided, comprising: an acquisition module 210, an allocation module 220, an identification module 230 and an iteration module 240, wherein:

[0106] The acquisition module 210 is used to acquire the water supply pipeline line structure of the target area and the current pipeline water flow detection information, and identify the abnormal sub-areas of different emergency levels of the target area based on the pipeline water flow detection information;

[0107] The allocation module 220 is used to locate the abnormal pipeline in each abnormal sub-region through the regional positioning strategy based on the line structure of the water supply pipeline and the pipeline water flow detection information, and to adjust the pipeline of each abnormal sub-region through an artificial neural network based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, so as to obtain the replacement pipeline corresponding to each abnormal pipeline;

[0108] The identification module 230 is used to collect the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, and readjust the alternative pipeline corresponding to each abnormal pipeline through the artificial neural network based on the current pipeline detection information of each abnormal pipeline;

[0109] Iteration module 240 is used to return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area when the current emergency level of the abnormal sub-area is greater than the preset level domain value, until the current emergency level of the abnormal sub-area is greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

[0110] Optionally, the acquisition module 210 is specifically configured to:

[0111] Based on the pipeline water flow detection information, the pipeline water flow state of each pipeline is identified, and among the pipelines, pipelines with abnormal pipeline water flow states are screened as candidate abnormal pipelines, and clustering processing is performed on the candidate abnormal pipelines to obtain abnormal sub-regions;

[0112] For each abnormal sub-region, identify the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and collect the area range of the abnormal sub-region in the target area;

[0113] Based on the regional range of the abnormal sub-region in the target region, querying the regional criticality of the abnormal sub-region in the regional database, and determining the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region;

[0114] Based on the number of candidate abnormal pipelines in the abnormal sub-area, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-area, the abnormal score value corresponding to the abnormal sub-area is calculated through the abnormal area scoring strategy, and the emergency level of the abnormal sub-area is determined based on the abnormal score value.

[0115] Optionally, the acquisition module 210 is specifically configured to:

[0116] Based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, a first number of each abnormal level in the abnormal sub-region is identified, and based on the first number of the abnormal sub-region and the second number of each candidate abnormal pipeline in the abnormal sub-region, a first abnormal score value of the abnormal sub-region is queried in a pipeline database;

[0117] The first anomaly score value is weighted and summed by the criticality weight value of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

[0118] Optionally, the allocation module 220 is specifically configured to:

[0119] For each abnormal sub-region, based on the water supply pipeline line structure, pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region is identified, and based on the pipeline flow direction information of each candidate pipeline, pipeline association information of each candidate abnormal pipeline is identified;

[0120] Based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, the abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is used as the abnormal pipeline of the abnormal sub-area.

[0121] Optionally, the allocation module 220 is specifically configured to:

[0122] For each abnormal sub-area, based on the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery is identified, and based on the position information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery, and the water supply pipeline line structure, through the route planning layer of the artificial neural network, each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route are calculated;

[0123] Based on each water delivery route of each initial alternative pipeline and the water delivery time of each water delivery route, an initial alternative pipeline including all water flow routes and having the shortest water delivery time of all water delivery routes is selected from each of the initial alternative pipelines as the initial alternative pipeline corresponding to the abnormal pipeline;

[0124] Based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-area and the water delivery routes corresponding to each initial alternative pipeline, the water delivery routes of each initial alternative pipeline are adjusted through the route adjustment layer of the artificial neural network to obtain the alternative pipelines corresponding to each abnormal pipeline.

[0125] Optionally, the device further comprises:

[0126] A query module, for querying the abnormal handling strategy of the abnormal pipeline in each abnormal sub-region based on the abnormal level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-region in the strategy database, and collecting the pipeline abnormal information template;

[0127] A filling module is used to match the target exception handling strategy corresponding to the abnormal pipeline in each of the exception handling strategies based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, and fill the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target exception handling strategy of the abnormal pipeline into the exception information template to obtain the exception handling reporting information of the abnormal pipeline;

[0128] The sending module is used to send the exception handling reporting information and the location information of the abnormal pipeline to the staff client.

[0129] Optionally, the identification module 230 is specifically configured to:

[0130] Based on the current pipeline detection information of each abnormal pipeline, the current abnormal level and the current pipeline water flow state of the abnormal pipeline are identified, and the pipeline water flow state of each abnormal pipeline is replaced by the current pipeline water flow state of each abnormal pipeline, and the abnormal level of each abnormal pipeline is replaced by the current abnormal level of each abnormal pipeline;

[0131] Return to execute based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, perform pipeline adjustment processing on each abnormal sub-area through an artificial neural network, and obtain the replacement pipeline step corresponding to each abnormal pipeline.

[0132] Each module in the water supply pipeline emergency treatment system based on artificial neural network can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0133] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a water supply pipeline emergency treatment method based on an artificial neural network is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse, etc.

[0134] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0136] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0137] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0139] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0140] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0141] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Any changes or substitutions that can be easily thought of by a person of ordinary skill in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field.

Claims

1. A water supply pipeline emergency treatment method based on artificial neural network, characterized in that: The steps include: Acquire the water supply pipeline line structure of the target area and the current pipeline water flow detection information, and identify the abnormal sub-areas of different emergency levels of the target area based on the pipeline water flow detection information; Based on the water supply pipeline line structure and the pipeline water flow detection information, the abnormal pipeline in each abnormal sub-region is located through the regional positioning strategy, and based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, the pipeline adjustment processing is performed on each abnormal sub-region through an artificial neural network to obtain a replacement pipeline corresponding to each abnormal pipeline; Collecting current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-areas, and based on the current pipeline detection information of each of the abnormal pipelines, readjusting the alternative pipeline corresponding to each of the abnormal pipelines through the artificial neural network; When the current emergency level of the abnormal sub-area is greater than the preset level domain value, return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, until there is no abnormal sub-area with a current emergency level greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

2. The water supply pipeline emergency treatment method based on artificial neural network according to claim 1 is characterized in that: The identifying, based on the pipeline water flow detection information, abnormal sub-areas of different emergency levels in the target area includes: Based on the pipeline water flow detection information, the pipeline water flow state of each pipeline is identified, and among the pipelines, pipelines with abnormal pipeline water flow states are screened as candidate abnormal pipelines, and clustering processing is performed on the candidate abnormal pipelines to obtain abnormal sub-regions; For each abnormal sub-region, identify the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and collect the area range of the abnormal sub-region in the target area; Based on the regional range of the abnormal sub-region in the target region, querying the regional criticality of the abnormal sub-region in the regional database, and determining the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region; Based on the number of candidate abnormal pipelines in the abnormal sub-area, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-area, the abnormal score value corresponding to the abnormal sub-area is calculated through the abnormal area scoring strategy, and the emergency level of the abnormal sub-area is determined based on the abnormal score value.

3. The water supply pipeline emergency treatment method based on artificial neural network according to claim 2 is characterized in that: The method of calculating the abnormal score value corresponding to the abnormal sub-region based on the number of candidate abnormal pipelines in the abnormal sub-region, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-region through the abnormal region scoring strategy includes: Based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, a first number of each abnormal level in the abnormal sub-region is identified, and based on the first number of the abnormal sub-region and the second number of each candidate abnormal pipeline in the abnormal sub-region, a first abnormal score value of the abnormal sub-region is queried in a pipeline database; The first anomaly score value is weighted and summed by the criticality weight value of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

4. The water supply pipeline emergency treatment method based on artificial neural network according to claim 3 is characterized in that: The method of locating the abnormal pipeline in each abnormal sub-region based on the water supply pipeline line structure and the pipeline water flow detection information through a regional positioning strategy includes: For each abnormal sub-region, based on the water supply pipeline line structure, pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region is identified, and based on the pipeline flow direction information of each candidate pipeline, pipeline association information of each candidate abnormal pipeline is identified; Based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, the abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is used as the abnormal pipeline of the abnormal sub-area.

5. The water supply pipeline emergency treatment method based on artificial neural network according to claim 4 is characterized in that: Based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, the pipeline adjustment processing is performed on each abnormal sub-region through an artificial neural network to obtain a replacement pipeline corresponding to each abnormal pipeline, including: For each abnormal sub-area, based on the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery is identified, and based on the position information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery, and the water supply pipeline line structure, through the route planning layer of the artificial neural network, each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route are calculated; Based on each water delivery route of each initial alternative pipeline and the water delivery time of each water delivery route, an initial alternative pipeline including all water flow routes and having the shortest water delivery time of all water delivery routes is selected from each of the initial alternative pipelines as the initial alternative pipeline corresponding to the abnormal pipeline; Based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-area and the water delivery routes corresponding to each initial alternative pipeline, the water delivery routes of each initial alternative pipeline are adjusted through the route adjustment layer of the artificial neural network to obtain the alternative pipelines corresponding to each abnormal pipeline.

6. The water supply pipeline emergency treatment method based on artificial neural network according to claim 5 is characterized in that: Before collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area, the method further includes: For each abnormal sub-region, based on the abnormal level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-region, query the abnormal handling strategy of the abnormal pipeline in the strategy database, and collect the pipeline abnormal information template; Based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, in each of the abnormal handling strategies, the target abnormal handling strategy corresponding to the abnormal pipeline is matched, and the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target abnormal handling strategy of the abnormal pipeline are filled into the abnormal information template to obtain the abnormal handling reporting information of the abnormal pipeline; The exception handling reporting information and the location information of the abnormal pipeline are sent to the staff client.

7. The water supply pipeline emergency treatment method based on artificial neural network according to claim 6 is characterized by: The step of re-adjusting the alternative pipelines corresponding to the abnormal pipelines based on the current pipeline detection information of the abnormal pipelines through the artificial neural network includes: Based on the current pipeline detection information of each abnormal pipeline, the current abnormal level and the current pipeline water flow state of the abnormal pipeline are identified, and the pipeline water flow state of each abnormal pipeline is replaced by the current pipeline water flow state of each abnormal pipeline, and the abnormal level of each abnormal pipeline is replaced by the current abnormal level of each abnormal pipeline; Return to execute based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, perform pipeline adjustment processing on each abnormal sub-area through an artificial neural network, and obtain the replacement pipeline step corresponding to each abnormal pipeline.

8. A water supply pipeline emergency treatment system based on artificial neural network, characterized in that: include An acquisition module, used to acquire the water supply pipeline line structure of the target area and the current pipeline water flow detection information, and identify abnormal sub-areas of different emergency levels in the target area based on the pipeline water flow detection information; An allocation module is used to locate the abnormal pipeline in each abnormal sub-region through a regional positioning strategy based on the line structure of the water supply pipeline and the pipeline water flow detection information, and to adjust the pipeline of each abnormal sub-region through an artificial neural network based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, so as to obtain a replacement pipeline corresponding to each abnormal pipeline; an identification module, configured to collect current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-areas, and readjust the alternative pipeline corresponding to each of the abnormal pipelines through the artificial neural network based on the current pipeline detection information of each of the abnormal pipelines; The iterative module is used to return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-area when the current emergency level of the abnormal sub-area is greater than the preset level domain value, until the current emergency level of the abnormal sub-area is greater than the preset level domain value, and the water supply pipeline emergency processing task is completed.

9. The water supply pipeline emergency treatment system based on artificial neural network according to claim 8 is characterized in that: The acquisition module is specifically used for: Based on the pipeline water flow detection information, the pipeline water flow state of each pipeline is identified, and among the pipelines, pipelines with abnormal pipeline water flow states are screened as candidate abnormal pipelines, and clustering processing is performed on the candidate abnormal pipelines to obtain abnormal sub-regions; For each abnormal sub-region, identify the number of candidate abnormal pipelines in the abnormal sub-region and the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and collect the area range of the abnormal sub-region in the target area; Based on the regional range of the abnormal sub-region in the target region, querying the regional criticality of the abnormal sub-region in the regional database, and determining the criticality weight value of the abnormal sub-region based on the regional criticality of the abnormal sub-region; Based on the number of candidate abnormal pipelines in the abnormal sub-area, the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, and the criticality weight value of the abnormal sub-area, the abnormal score value corresponding to the abnormal sub-area is calculated through the abnormal area scoring strategy, and the emergency level of the abnormal sub-area is determined based on the abnormal score value.

10. The water supply pipeline emergency treatment system based on artificial neural network according to claim 9, characterized in that: The acquisition module is specifically used for: Based on the abnormal level corresponding to the pipeline water flow state of each candidate abnormal pipeline, a first number of each abnormal level in the abnormal sub-region is identified, and based on the first number of the abnormal sub-region and the second number of each candidate abnormal pipeline in the abnormal sub-region, a first abnormal score value of the abnormal sub-region is queried in a pipeline database; The first anomaly score value is weighted and summed by the criticality weight value of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

11. The water supply pipeline emergency treatment system based on artificial neural network according to claim 10, characterized in that: The allocation module is specifically used for: For each abnormal sub-region, based on the water supply pipeline line structure, pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region is identified, and based on the pipeline flow direction information of each candidate pipeline, pipeline association information of each candidate abnormal pipeline is identified; Based on the abnormal level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, the abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is used as the abnormal pipeline of the abnormal sub-area.

12. The water supply pipeline emergency treatment system based on artificial neural network according to claim 11, characterized in that: The allocation module is specifically used for: For each abnormal sub-area, based on the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery is identified, and based on the position information of each abnormal pipeline in the water supply pipeline line structure, each water flow route of the abnormal pipeline water delivery, and the water supply pipeline line structure, through the route planning layer of the artificial neural network, each water delivery route of each initial replacement pipeline and the water delivery time of each water delivery route are calculated; Based on each water delivery route of each initial alternative pipeline and the water delivery time of each water delivery route, an initial alternative pipeline including all water flow routes and having the shortest water delivery time of all water delivery routes is selected from each of the initial alternative pipelines as the initial alternative pipeline corresponding to the abnormal pipeline; Based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-area and the water delivery routes corresponding to each initial alternative pipeline, the water delivery routes of each initial alternative pipeline are adjusted through the route adjustment layer of the artificial neural network to obtain the alternative pipelines corresponding to each abnormal pipeline.

13. The water supply pipeline emergency treatment system based on artificial neural network according to claim 12, characterized in that: The identification module is specifically used for: Based on the current pipeline detection information of each abnormal pipeline, the current abnormal level and the current pipeline water flow state of the abnormal pipeline are identified, and the pipeline water flow state of each abnormal pipeline is replaced by the current pipeline water flow state of each abnormal pipeline, and the abnormal level of each abnormal pipeline is replaced by the current abnormal level of each abnormal pipeline; Return to execute based on the emergency level corresponding to each abnormal sub-area and the abnormal pipeline corresponding to each abnormal sub-area, perform pipeline adjustment processing on each abnormal sub-area through an artificial neural network, and obtain the replacement pipeline step corresponding to each abnormal pipeline.

14. The water supply pipeline emergency treatment system based on artificial neural network according to claim 13, characterized in that: Also includes: A query module, for querying the abnormal handling strategy of the abnormal pipeline in each abnormal sub-region based on the abnormal level corresponding to the pipeline water flow state of the abnormal pipeline in the abnormal sub-region in the strategy database, and collecting the pipeline abnormal information template; A filling module is used to match the target exception handling strategy corresponding to the abnormal pipeline in each of the exception handling strategies based on the pipeline water flow state of the abnormal pipeline in the abnormal sub-area, and fill the pipeline water flow state of the abnormal pipeline, the abnormal level of the abnormal pipeline, and the target exception handling strategy of the abnormal pipeline into the exception information template to obtain the exception handling reporting information of the abnormal pipeline; The sending module is used to send the exception handling reporting information and the location information of the abnormal pipeline to the staff client.

15. A computer device, characterized in that: The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

17. A computer program product, characterized in that: The computer program product comprises a computer program, which implements the steps of the method according to any one of claims 1 to 7 when executed by a processor.

Images