Emergency response methods, systems, equipment, storage media, and computer program products for water supply pipelines based on artificial neural networks.

Abstract

This invention discloses a method, system, equipment, storage medium, and computer program product for emergency handling of water supply pipelines based on artificial neural networks. The method includes: acquiring the water supply pipeline structure and current pipeline flow detection information of a target area; identifying abnormal sub-regions of different emergency levels within the target area; locating abnormal pipes in each abnormal sub-region and performing pipeline adjustment processing for each abnormal sub-region to obtain replacement pipes corresponding to each abnormal pipe; collecting current pipeline detection information for each abnormal pipe and the current emergency level of each abnormal sub-region, and readjusting the replacement pipes corresponding to each abnormal pipe; if the current emergency level of an abnormal sub-region is greater than a preset level threshold, returning to the above acquisition steps until no abnormal sub-region has a current emergency level greater than the preset level threshold, thus completing the emergency handling task for the water supply pipeline. This method can improve the efficiency of emergency response for water supply pipelines.

Description

Technical Field

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

[0002] Urban water supply pipelines are a core component of municipal public infrastructure, directly impacting the health and quality of life of urban residents. With the acceleration of urbanization in my country, the construction of urban water supply pipelines has seen rapid growth. Currently, urban water supply pipelines are aging and corroding, and being underground, they are not easily visible, making operation and maintenance difficult and leading to frequent pipe bursts.

[0003] Traditional emergency handling of water supply pipelines relies on manual inspection and location. This involves large-scale water outages followed by manual, piecemeal checks to identify faulty areas. This method is inefficient, failing to address problems promptly and accurately. It not only disrupts urban businesses and residents' lives but also results in significant water waste. Therefore, in light of the evolving needs of urban infrastructure development, this paper proposes an emergency handling method and system for water supply pipelines based on artificial neural networks to address these issues. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the above-mentioned background technology and provide an emergency treatment method, system, equipment, storage medium and computer program product for water supply pipelines based on artificial neural networks.

[0005] In a first aspect, the present invention provides an emergency handling method for water supply pipelines based on artificial neural networks, comprising the following steps:

[0006] The system acquires the water supply pipeline structure and current pipeline water flow detection information of the target area, and identifies abnormal sub-regions of different emergency levels in the target area based on the pipeline water flow detection information.

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

[0008] Collect the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region, and based on the current pipeline detection information of each abnormal pipeline, readjust the alternative pipelines corresponding to each abnormal pipeline through the artificial neural network.

[0009] If the current emergency level of an abnormal sub-region is greater than the preset level threshold, return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region, until the current emergency level of no abnormal sub-region is greater than the preset level threshold, and the emergency handling task of the water supply pipeline is completed.

[0010] Optionally, the step of identifying abnormal sub-regions 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 status of each pipeline is identified, and pipelines with abnormal water flow status are selected as candidate abnormal pipelines. Then, the candidate abnormal pipelines are clustered to obtain each abnormal sub-region.

[0012] For each abnormal sub-region, identify the number of candidate abnormal pipes in the abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and collect the regional range of the abnormal sub-region in the target region;

[0013] Based on the regional range of the abnormal sub-region in the target region, the regional criticality of the abnormal sub-region is queried in the regional database, and the criticality weight value of the abnormal sub-region is determined based on the regional criticality of the abnormal sub-region.

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

[0015] Optionally, the step of calculating the anomaly score value corresponding to the anomaly sub-region based on the number of candidate anomaly pipes in each anomaly sub-region, the anomaly level corresponding to the pipe flow state of each candidate anomaly pipe, and the criticality weight value of the anomaly sub-region, through an anomaly region scoring strategy, includes:

[0016] Based on the anomaly level corresponding to the water flow state of each candidate abnormal pipe, a first number of each anomaly 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 pipe in the abnormal sub-region, a first anomaly score value of the abnormal sub-region is queried in the pipe database.

[0017] The first anomaly score value is weighted and summed using the keyness weight values ​​of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

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

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

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

[0021] Optionally, based on the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipelines corresponding to each of the abnormal sub-regions, the pipeline adjustment process for each of the abnormal sub-regions is performed using an artificial neural network to obtain alternative pipelines corresponding to each of the abnormal pipelines, including:

[0022] For each abnormal sub-region, based on the water supply pipeline structure, the water flow routes of the abnormal pipeline are identified, and based on the location information of each abnormal pipeline in the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure, the route planning layer of the artificial neural network is used to calculate the water flow routes of each initial replacement pipeline and the water flow duration of each water flow route.

[0023] Based on the water transport routes of each initial replacement pipeline and the water transport time of each water transport route, the initial replacement pipeline that includes all water flow routes and has the shortest water transport time among the initial replacement pipelines is selected as the initial replacement pipeline corresponding to the abnormal pipeline.

[0024] Based on the initial replacement pipes corresponding to the abnormal pipes in each of the abnormal sub-regions, and the water transport routes corresponding to each initial replacement pipe, the route adjustment layer of the artificial neural network is used to adjust the water transport routes of each initial replacement pipe to obtain the replacement pipe corresponding to each abnormal pipe.

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

[0026] For each abnormal sub-region, based on the abnormal level corresponding to the water flow status of the abnormal pipe in the abnormal sub-region, the abnormal handling strategy for the abnormal pipe is queried in the strategy database, and the pipe abnormal information template is collected.

[0027] Based on the water flow status of the abnormal pipes in the abnormal sub-region, the target abnormal handling strategy corresponding to the abnormal pipe is matched in each of the abnormal handling strategies, and the water flow status of the abnormal pipe, the abnormal level of the abnormal pipe, and the target abnormal handling strategy of the abnormal pipe are filled into the abnormal information template to obtain the abnormal handling reporting information of the abnormal pipe.

[0028] The anomaly handling report information and the location information of the anomaly pipeline are sent to the staff client.

[0029] Optionally, the step of readjusting the replacement pipes corresponding to each abnormal pipe based on the current pipe detection information of each abnormal pipe, through the artificial neural network, includes:

[0030] Based on the current pipeline detection information of each abnormal pipeline, the current abnormality level and current pipeline water flow status of each abnormal pipeline are identified, and the current pipeline water flow status of each abnormal pipeline is replaced with the current pipeline water flow status of each abnormal pipeline, and the current abnormality level of each abnormal pipeline is replaced with the abnormality level of each abnormal pipeline.

[0031] The process returns to the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipeline corresponding to each of the abnormal sub-regions. Through artificial neural networks, pipeline adjustment processing is performed on each of the abnormal sub-regions to obtain the alternative pipeline corresponding to each of the abnormal pipelines.

[0032] Secondly, the present invention also provides an emergency response system for water supply pipelines based on artificial neural networks. The system includes:

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

[0034] The allocation module is used to locate the abnormal pipes in each abnormal sub-region based on the water supply pipeline structure and the pipeline water flow detection information, and to perform pipeline adjustment processing on each abnormal sub-region based on the emergency level corresponding to each abnormal sub-region and the abnormal pipes corresponding to each abnormal sub-region through an artificial neural network to obtain the replacement pipes corresponding to each abnormal pipe.

[0035] The identification module is used to collect the current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-regions, and based on the current pipeline detection information of each of the abnormal pipelines, readjust the replacement pipelines corresponding to each of the abnormal pipelines through the artificial neural network.

[0036] The iterative module is used to return to the steps of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region when the current emergency level of an abnormal sub-region is greater than the preset level threshold, until the emergency handling task of the water supply pipeline is completed when the current emergency level of no abnormal sub-region is greater than the preset level threshold.

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

[0038] Based on the pipeline water flow detection information, the pipeline water flow status of each pipeline is identified, and pipelines with abnormal water flow status are selected as candidate abnormal pipelines. Then, the candidate abnormal pipelines are clustered to obtain each abnormal sub-region.

[0039] For each abnormal sub-region, identify the number of candidate abnormal pipes in the abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and collect the regional range of the abnormal sub-region in the target region;

[0040] Based on the regional range of the abnormal sub-region in the target region, the regional criticality of the abnormal sub-region is queried in the regional database, and the criticality weight value of the abnormal sub-region is determined based on the regional criticality of the abnormal sub-region.

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

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

[0043] Based on the anomaly level corresponding to the water flow state of each candidate abnormal pipe, a first number of each anomaly 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 pipe in the abnormal sub-region, a first anomaly score value of the abnormal sub-region is queried in the pipe database.

[0044] The first anomaly score value is weighted and summed using the keyness weight values ​​of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

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

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

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

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

[0049] For each abnormal sub-region, based on the water supply pipeline structure, the water flow routes of the abnormal pipeline are identified, and based on the location information of each abnormal pipeline in the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure, the route planning layer of the artificial neural network is used to calculate the water flow routes of each initial replacement pipeline and the water flow duration of each water flow route.

[0050] Based on the water transport routes of each initial replacement pipeline and the water transport time of each water transport route, the initial replacement pipeline that includes all water flow routes and has the shortest water transport time among the initial replacement pipelines is selected as the initial replacement pipeline corresponding to the abnormal pipeline.

[0051] Based on the initial replacement pipes corresponding to the abnormal pipes in each of the abnormal sub-regions, and the water transport routes corresponding to each initial replacement pipe, the route adjustment layer of the artificial neural network is used to adjust the water transport routes of each initial replacement pipe to obtain the replacement pipe corresponding to each abnormal pipe.

[0052] Optionally, the device further includes:

[0053] The query module is used to query the anomaly handling strategy for each abnormal sub-region based on the anomaly level corresponding to the pipe flow status of the abnormal pipe in the abnormal sub-region, and to collect the pipe anomaly information template.

[0054] The filling module is used to match the target anomaly handling strategy corresponding to the anomaly pipe in each anomaly handling strategy based on the pipe flow status of the anomaly pipe in the anomaly sub-region, and fill the pipe flow status, anomaly level, and target anomaly handling strategy of the anomaly pipe into the anomaly information template to obtain the anomaly handling reporting information of the anomaly pipe.

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

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

[0057] Based on the current pipeline detection information of each abnormal pipeline, the current abnormality level and current pipeline water flow status of each abnormal pipeline are identified, and the current pipeline water flow status of each abnormal pipeline is replaced with the current pipeline water flow status of each abnormal pipeline, and the current abnormality level of each abnormal pipeline is replaced with the abnormality level of each abnormal pipeline.

[0058] The process returns to the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipeline corresponding to each of the abnormal sub-regions. Through artificial neural networks, pipeline adjustment processing is performed on each of the abnormal sub-regions to obtain the alternative pipeline corresponding to each of the abnormal pipelines.

[0059] Thirdly, the present invention provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0060] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0061] Fifthly, the present invention provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

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

[0063] This invention relates to an emergency handling method and system for water supply pipelines based on artificial neural networks. The method involves acquiring the water supply pipeline structure and current water flow detection information of a target area, and identifying abnormal sub-regions with different emergency levels within the target area based on the water flow detection information. Using a regional positioning strategy, the method locates abnormal pipes within each abnormal sub-region based on the pipeline structure and the water flow detection information. Then, using an artificial neural network, it adjusts the pipelines in each abnormal sub-region according to their corresponding emergency level and the abnormal pipe, obtaining alternative pipes for each abnormal pipe. The method collects current pipeline detection information for each abnormal pipe and the current emergency level of each abnormal sub-region, and uses the artificial neural network to readjust the alternative pipes for each abnormal pipe. If the current emergency level of an abnormal sub-region exceeds a preset threshold, the method returns to the previous steps of collecting current pipeline detection information and the current emergency level of each abnormal sub-region until no abnormal sub-region has a current emergency level exceeding the preset threshold, thus completing the emergency handling task for the water supply pipeline. This invention utilizes pipeline flow detection information and water supply pipeline structure, dividing abnormal sub-regions into different emergency levels and employing regional positioning strategies to accurately locate each abnormal pipeline. Then, through an artificial neural network, it identifies alternative pipelines that can replace the abnormal ones, thus avoiding disruption to the normal water supply for the population. Finally, by periodically collecting current pipeline detection information of the abnormal pipelines, it periodically identifies the maintenance status of these pipelines, allowing for real-time adjustments to the water delivery status of each pipeline based on the maintenance situation. This reduces the water supply pressure on alternative pipelines, ensuring the efficient and normal operation of all water supply pipelines. This solution, through intelligent planning of alternative routes and intelligent detection of pipeline status, avoids impacting the normal water demand of the population while improving the emergency response efficiency of the water supply pipeline. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating an emergency response method for water supply pipelines based on artificial neural networks in one embodiment.

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

[0066] Figure 3 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0067] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. It should be noted that these descriptions are for the purpose of aiding understanding the present invention and do not constitute a limitation thereof; they are merely examples. Furthermore, 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 them.

[0068] The emergency handling method for water supply pipelines based on artificial neural networks provided in this application embodiment can be applied to the application environment of urban underground water supply pipelines. This method can be applied to terminals, servers, or systems including both terminals and servers, and is implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, tablets, etc. The terminals, through pipeline water flow detection information and the water supply pipeline structure, accurately locate each abnormal pipeline by dividing abnormal sub-regions of different emergency levels and using regional positioning strategies. Then, through artificial neural networks, alternative pipelines that can replace the abnormal pipeline are identified, thereby avoiding disruption to the normal water supply to the population. Finally, by periodically collecting the current pipeline detection information of the abnormal pipelines, the maintenance status of the abnormal pipelines is periodically identified, allowing for real-time adjustment of the water delivery status of each pipeline based on the pipeline maintenance status. This reduces the water supply pressure of each alternative pipeline, enabling each water supply pipeline to operate efficiently and normally. This solution, through intelligent planning of alternative routes and intelligent detection of pipeline status, avoids affecting the normal water demand of the population while improving the emergency handling efficiency of water supply pipelines.

[0069] In one embodiment, such as Figure 1 As shown, an emergency handling method for water supply pipelines based on artificial neural networks is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0070] Step S101: Obtain the water supply pipeline structure and current pipeline water flow detection information of the target area, and identify 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 and obtains the water supply pipeline structure of the target area. This target area can be, but is not limited to, a municipal administrative area, a provincial administrative area, an urban area, or a bustling urban area. The water supply pipeline structure includes the connection relationships of each water supply pipeline, the water delivery rate of each pipeline, and the length of each pipeline. Then, the terminal divides the target area into abnormal sub-regions with different emergency levels. The emergency levels of different abnormal sub-regions may be different or the same, and each abnormal sub-region does not overlap. The emergency level is used to characterize the water supply demand of the abnormal sub-region. The higher the emergency level, the greater the water supply demand and the more complex the abnormal pipeline situation; the lower the emergency level, the smaller the water supply demand and the simpler the abnormal pipeline situation. The specific process of identifying the emergency level will be explained in detail later. The current pipeline water flow detection information includes the pipe pressure information and water flow velocity information collected by water flow sensors set at various locations on the pipeline during the current time period.

[0072] Step S102: Based on the water supply pipeline structure and pipeline water flow detection information, the abnormal pipeline in each abnormal sub-region is located through a regional positioning strategy. Based on the emergency level and the abnormal pipeline corresponding to each abnormal sub-region, the pipeline adjustment process is carried out in each abnormal sub-region through an artificial neural network to obtain the replacement pipeline corresponding to each abnormal pipeline.

[0073] In this embodiment, the terminal, based on the water supply pipeline structure and pipeline flow detection information, locates the abnormal pipelines in each abnormal sub-region using a regional positioning strategy. Then, based on the emergency level and the corresponding abnormal pipelines in each abnormal sub-region, an artificial neural network is used to adjust the pipelines in each sub-region to obtain alternative pipelines for each abnormal pipeline. The regional positioning strategy is a neural network strategy based on a self-attention mechanism. The specific positioning process will be explained in detail later.

[0074] Step S103: Collect the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region, and based on the current pipeline detection information of each abnormal pipeline, readjust the alternative pipelines 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-region. Based on the current pipeline detection information of each abnormal pipeline, it readjusts the corresponding alternative pipelines for each abnormal pipeline through an artificial neural network. The process of adjusting the alternative pipelines is essentially the same as the process of selecting alternative pipelines for each abnormal pipeline.

[0076] Step S104: If the current emergency level of an abnormal sub-region is greater than the preset level threshold, return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region until the current emergency level of no abnormal sub-region is greater than the preset level threshold, and the emergency handling task of the water supply pipeline is completed.

[0077] In this embodiment, if the current emergency level of an abnormal sub-region is greater than the preset level threshold, the terminal returns to the steps of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region until the current emergency level of no abnormal sub-region is greater than the preset level threshold, thus completing the emergency handling task for the water supply pipeline.

[0078] Based on the above solution, by utilizing pipeline flow detection information and the water supply pipeline structure, and by dividing abnormal sub-regions into different emergency levels and employing regional positioning strategies, each abnormal pipeline can be accurately located. Then, an artificial neural network is used to identify alternative pipelines that can replace the abnormal ones, thereby avoiding disruption to the normal water supply for the population. Finally, by periodically collecting current pipeline detection information of the abnormal pipelines, the maintenance status of the abnormal pipelines can be identified in real time. This allows for real-time adjustments to the water delivery status of each pipeline based on the maintenance status, thereby reducing the water supply pressure on the alternative pipelines and ensuring the efficient and normal operation of all water supply pipelines. This solution, through intelligent planning of alternative routes and intelligent detection of pipeline status, avoids affecting the normal water demand of the population while improving the emergency response efficiency of the water supply pipeline.

[0079] Optionally, based on pipeline flow detection information, abnormal sub-regions of different emergency levels within the target area are identified, including: identifying the pipeline flow state of each pipeline based on the pipeline flow detection information, selecting pipelines with abnormal flow states as candidate abnormal pipelines, and clustering each candidate abnormal pipeline to obtain each abnormal sub-region; for each abnormal sub-region, identifying the number of candidate abnormal pipelines and the abnormal level corresponding to the pipeline flow state of each candidate abnormal pipeline, and collecting the regional range of the abnormal sub-region within the target area; based on the regional range of the abnormal sub-region within 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 each abnormal sub-region, the abnormal level corresponding to the pipeline 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 an abnormal region 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 water flow status of each pipe based on the pipe flow detection information, and filters out pipes with abnormal water flow status as candidate abnormal pipes. Then, it performs clustering processing on each candidate abnormal pipe to obtain abnormal sub-regions. Each abnormal sub-region includes both candidate abnormal pipes and normal pipes.

[0081] For each abnormal sub-region, the terminal identifies the number of candidate abnormal pipes and the corresponding abnormality level of the water flow status of each candidate abnormal pipe, and collects the regional range of the abnormal sub-region within the target region. Then, based on the regional range of the abnormal sub-region within 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. Each target region is divided into regional ranges with different criticalities through a range division method. Higher criticality indicates a higher water supply urgency in the region, and lower criticality indicates a lower water supply urgency. For example, urban bustling centers, school areas, hospital areas, residential areas, and factory areas have high criticality, while abandoned building areas and areas with low population density have low criticality. The process of determining the criticality weight value involves normalizing the criticality to obtain the corresponding criticality weight value for each criticality level.

[0082] The terminal calculates the anomaly score for each anomaly sub-region based on the number of candidate anomaly pipes in each sub-region, the anomaly level corresponding to the water flow status of each candidate anomaly pipe, and the criticality weight value of the anomaly sub-region, using an anomaly region scoring strategy. Based on the anomaly score, the terminal determines the emergency response level for the anomaly sub-region. The specific calculation process will be explained in detail later.

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

[0084] Optionally, based on the number of candidate abnormal pipes in each abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, 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. This includes: identifying the first number of each abnormality level in the abnormal sub-region based on the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe; querying the first abnormality score value of the abnormal sub-region in the pipe database based on the first number of abnormal sub-regions and the second number of candidate abnormal pipes in the abnormal sub-region; and performing weighted summation on the first abnormality score value using the criticality weight value of the abnormal sub-region to obtain the abnormality score value of the abnormal sub-region.

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

[0086] Based on the above scheme, the number of abnormal channels and the number of each abnormal level of abnormal channels are weighted by the weight value corresponding to the criticality, which improves the accuracy of the abnormal score value of the determined abnormal sub-region.

[0087] Optionally, based on the water supply pipeline structure and pipeline flow detection information, an abnormal pipeline in each abnormal sub-region is located using a regional positioning strategy. This includes: for each abnormal sub-region, identifying the pipeline flow direction information of each candidate abnormal pipeline in the abnormal sub-region based on the water supply pipeline structure, and identifying the pipeline association information of each candidate abnormal pipeline based on the pipeline flow direction information; and identifying the abnormal pipeline in each candidate abnormal pipeline using a self-attention network based on the abnormality level and pipeline association information of each candidate abnormal pipeline, and identifying the abnormal pipeline as the abnormal pipeline in 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 water supply pipeline line structure, and identifies the pipeline association information of each candidate abnormal pipeline based on the pipeline flow direction information. The pipeline association information includes the connection information between each pipeline, and the water flow relationship between each adjacent pipeline in the water flow sequence.

[0089] Based on the anomaly level and pipeline association information of each candidate abnormal pipeline, the terminal uses a self-attention network to identify abnormal pipelines among the candidate abnormal pipelines and classifies them as abnormal pipelines in abnormal sub-regions. The abnormal pipeline has a lower anomaly level, and the anomaly level of the pipelines flowing through it should gradually increase. For example, if pipeline A is ruptured, its anomaly level is A1. Subsequent pipelines, receiving less water, will have slower flow rates and lower pressures, thus their anomaly levels should be greater than A1.

[0090] Based on the above scheme, by considering the pipeline flow direction and pipeline association information, the accuracy of identifying abnormal pipelines among candidate abnormal pipelines is improved.

[0091] Optionally, based on the emergency level corresponding to each abnormal sub-region and the abnormal pipeline corresponding to each abnormal sub-region, an artificial neural network is used to adjust the pipelines in each abnormal sub-region to obtain the alternative pipelines corresponding to each abnormal pipeline. This includes: for each abnormal sub-region, based on the water supply pipeline structure, identifying the water flow routes of the abnormal pipeline, and based on the location information of each abnormal pipeline in the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure, using the route planning layer of the artificial neural network to calculate the water flow routes and the water flow duration of each initial alternative pipeline; based on the water flow routes and the water flow duration of each initial alternative pipeline, selecting the initial alternative pipeline that includes all water flow routes and has the shortest water flow duration among the initial alternative pipelines, as the initial alternative pipeline corresponding to the abnormal pipeline; and based on the initial alternative pipelines corresponding to the abnormal pipelines in each abnormal sub-region and the water flow routes corresponding to each initial alternative pipeline, using the route adjustment layer of the artificial neural network to adjust the water flow routes of each initial alternative pipeline to obtain the alternative pipeline corresponding to each abnormal pipeline.

[0092] In this embodiment, for each abnormal sub-region, the terminal identifies the water flow routes of the abnormal pipeline based on the water supply pipeline structure. Based on the location information of each abnormal pipeline within the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure itself, the terminal uses a route planning layer of an artificial neural network to calculate the water flow routes and duration of each initial replacement pipeline. Then, based on the water flow routes and duration of each initial replacement pipeline, the terminal selects the initial replacement pipeline that includes all water flow routes and has the shortest total water flow duration from among all initial replacement pipelines, and uses this as the initial replacement pipeline corresponding to the abnormal pipeline. For each anomalous sub-region, based on the water supply pipeline structure, the water flow routes of the anomalous pipeline are identified. Based on the location information of each anomalous pipeline within the water supply pipeline structure, the water flow routes of the anomalous pipeline, and the water supply pipeline structure itself, a route planning layer of an artificial neural network calculates the water flow routes and durations of each initial replacement pipeline. Based on the water flow routes and durations of each initial replacement pipeline, the initial replacement pipeline that includes all flow routes and has the shortest total water flow duration is selected from among the initial replacement pipelines and designated as the initial replacement pipeline corresponding to the anomalous pipeline. Based on the initial replacement pipelines corresponding to the anomalous pipelines in each anomalous sub-region and the water flow routes corresponding to each initial replacement pipeline, a route adjustment layer of the artificial neural network adjusts the water flow routes of each initial replacement pipeline to obtain the replacement pipeline corresponding to each anomalous pipeline.

[0093] Next, based on the initial replacement pipes corresponding to the abnormal pipes in each abnormal sub-region, and the water transmission routes corresponding to each initial replacement pipe, the terminal adjusts the water transmission routes of each initial replacement pipe through the route adjustment layer of an artificial neural network to obtain the replacement pipe corresponding to each abnormal pipe. The route planning layer is a reinforcement learning neural network composed of multiple neurons. The neural network corresponding to the route adjustment layer is the same as that 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 can operate normally within the saturation 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-region, the process includes: for each abnormal sub-region, based on the abnormal level corresponding to the pipeline flow status of the abnormal pipeline in the abnormal sub-region, querying the abnormal handling strategy for the abnormal pipeline in the strategy database, and collecting the pipeline abnormal information template; based on the pipeline flow status of the abnormal pipeline in the abnormal sub-region, matching the target abnormal handling strategy corresponding to the abnormal pipeline in each abnormal handling strategy, and filling the abnormal information template with the pipeline flow status, abnormal level, and target abnormal handling strategy of the abnormal pipeline to obtain the abnormal pipeline abnormal handling reporting information; and sending the abnormal handling reporting information and the location information of the abnormal pipeline to the staff client.

[0096] In this embodiment, for each abnormal sub-region, the terminal queries the strategy database for the abnormal handling strategy of the abnormal pipeline based on the abnormal level corresponding to the water flow status of the abnormal pipeline in the abnormal sub-region, and collects the pipeline abnormal information template. The abnormal handling strategy is a handling strategy corresponding to different abnormal levels, which includes the required replacement repair materials, repair personnel experience, repair methods, repair time, and repair tools, etc.

[0097] Based on the water flow status of the abnormal pipes in the abnormal sub-region, the terminal matches the target abnormal handling strategy corresponding to the abnormal pipe among various abnormal handling strategies, and fills the abnormal information template with the water flow status, abnormal level, and target abnormal handling strategy of the abnormal pipe to obtain the abnormal pipe's abnormal handling reporting information. Finally, the terminal sends the abnormal handling reporting information and the location information of the abnormal pipe to the staff's client.

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

[0099] Optionally, based on the current pipeline detection information of each abnormal pipeline, an artificial neural network is used to readjust the corresponding alternative pipelines for each abnormal pipeline. This includes: identifying the current abnormality level and current pipeline flow state of each abnormal pipeline based on the current pipeline detection information, replacing the current pipeline flow state of each abnormal pipeline with the current pipeline flow state of each abnormal pipeline, and replacing the current abnormality level of each abnormal pipeline with the current abnormality level of each abnormal pipeline; returning to execute the step of adjusting the pipelines in each abnormal sub-region based on the emergency level and the abnormal pipelines in each abnormal sub-region, using an artificial neural network, to obtain the corresponding alternative pipelines for each abnormal pipeline.

[0100] In this embodiment, the terminal identifies the current anomaly level and current water flow status of each abnormal pipe based on the current pipe detection information. It then replaces the current water flow status of each abnormal pipe with its own current anomaly level, and replaces its own anomaly level with its own current anomaly level. Next, the terminal returns to execute the pipe adjustment process based on the emergency level and the abnormal pipes corresponding to each abnormal sub-region, using an artificial neural network to obtain the replacement pipes for each abnormal pipe.

[0101] Based on the above scheme, by periodically collecting the current pipeline detection information of abnormal pipelines, the maintenance status of the abnormal pipelines can be identified in a timely manner. This allows for real-time adjustment of the water supply status of each pipeline based on the pipeline maintenance status, thereby reducing the water supply pressure of each alternative pipeline and enabling each water supply pipeline to operate efficiently and normally.

[0102] Based on the above scheme, by adjusting the current maximum water delivery rate of each abnormal alternative pipeline according to the current sewage discharge level of the abnormal alternative pipeline, a new water supply pipeline structure is obtained, which improves the ability to ensure that the new alternative pipeline corresponding to each abnormal pipeline can achieve the optimal sewage discharge rate when abnormal alternative pipelines exist.

[0103] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0104] Based on the same inventive concept, this application also provides an artificial neural network-based emergency response system for water supply pipelines, which implements the aforementioned artificial neural network-based emergency response method for water supply pipelines. The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the artificial neural network-based emergency response system for water supply pipelines provided below can be found in the limitations of the artificial neural network-based emergency response method for water supply pipelines described above, and will not be repeated here.

[0105] In one embodiment, such as Figure 2 As shown, an emergency response system for water supply pipelines based on artificial neural networks is provided, including: 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 structure of the target area and the current pipeline water flow detection information, and based on the pipeline water flow detection information, identify abnormal sub-regions of different emergency levels in the target area.

[0107] The allocation module 220 is used to locate the abnormal pipes in each abnormal sub-region based on the water supply pipeline line structure and the pipeline water flow detection information, and to perform pipeline adjustment processing on each abnormal sub-region based on the emergency level corresponding to each abnormal sub-region and the abnormal pipes corresponding to each abnormal sub-region through an artificial neural network to obtain the alternative pipes corresponding to each abnormal pipe.

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

[0109] The 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-region when the current emergency level of an abnormal sub-region is greater than the preset level threshold, until the current emergency level of no abnormal sub-region is greater than the preset level threshold, and then complete the emergency handling task of the water supply pipeline.

[0110] Optionally, the acquisition module 210 is specifically used for:

[0111] Based on the pipeline water flow detection information, the pipeline water flow status of each pipeline is identified, and pipelines with abnormal water flow status are selected as candidate abnormal pipelines. Then, the candidate abnormal pipelines are clustered to obtain each abnormal sub-region.

[0112] For each abnormal sub-region, identify the number of candidate abnormal pipes in the abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and collect the regional range of the abnormal sub-region in the target region;

[0113] Based on the regional range of the abnormal sub-region in the target region, the regional criticality of the abnormal sub-region is queried in the regional database, and the criticality weight value of the abnormal sub-region is determined based on the regional criticality of the abnormal sub-region.

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

[0115] Optionally, the acquisition module 210 is specifically used for:

[0116] Based on the anomaly level corresponding to the water flow state of each candidate abnormal pipe, a first number of each anomaly 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 pipe in the abnormal sub-region, a first anomaly score value of the abnormal sub-region is queried in the pipe database.

[0117] The first anomaly score value is weighted and summed using the keyness weight values ​​of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

[0118] Optionally, the allocation module 220 is specifically used for:

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

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

[0121] Optionally, the allocation module 220 is specifically used for:

[0122] For each abnormal sub-region, based on the water supply pipeline structure, the water flow routes of the abnormal pipeline are identified, and based on the location information of each abnormal pipeline in the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure, the route planning layer of the artificial neural network is used to calculate the water flow routes of each initial replacement pipeline and the water flow duration of each water flow route.

[0123] Based on the water transport routes of each initial replacement pipeline and the water transport time of each water transport route, the initial replacement pipeline that includes all water flow routes and has the shortest water transport time among the initial replacement pipelines is selected as the initial replacement pipeline corresponding to the abnormal pipeline.

[0124] Based on the initial replacement pipes corresponding to the abnormal pipes in each of the abnormal sub-regions, and the water transport routes corresponding to each initial replacement pipe, the route adjustment layer of the artificial neural network is used to adjust the water transport routes of each initial replacement pipe to obtain the replacement pipe corresponding to each abnormal pipe.

[0125] Optionally, the device further includes:

[0126] The query module is used to query the anomaly handling strategy for each abnormal sub-region based on the anomaly level corresponding to the pipe flow status of the abnormal pipe in the abnormal sub-region, and to collect the pipe anomaly information template.

[0127] The filling module is used to match the target anomaly handling strategy corresponding to the anomaly pipe in each anomaly handling strategy based on the pipe flow status of the anomaly pipe in the anomaly sub-region, and fill the pipe flow status, anomaly level, and target anomaly handling strategy of the anomaly pipe into the anomaly information template to obtain the anomaly handling reporting information of the anomaly pipe.

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

[0129] Optionally, the identification module 230 is specifically used for:

[0130] Based on the current pipeline detection information of each abnormal pipeline, the current abnormality level and current pipeline water flow status of each abnormal pipeline are identified, and the current pipeline water flow status of each abnormal pipeline is replaced with the current pipeline water flow status of each abnormal pipeline, and the current abnormality level of each abnormal pipeline is replaced with the abnormality level of each abnormal pipeline.

[0131] The process returns to the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipeline corresponding to each of the abnormal sub-regions. Through artificial neural networks, pipeline adjustment processing is performed on each of the abnormal sub-regions to obtain the alternative pipeline corresponding to each of the abnormal pipelines.

[0132] The modules in the aforementioned emergency water supply pipeline system based on artificial neural networks can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0133] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, communication interface, display screen, and input system connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an emergency handling method for water supply pipelines based on artificial neural networks. The display screen can be an LCD screen or an e-ink screen. The input system can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

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

[0135] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.

[0136] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0137] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[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, data stored, data displayed, 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 will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0140] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this invention should be included within the protection scope of this invention. Contents not described in detail in this specification are prior art known to those skilled in the art.

Claims

1. An emergency handling method for water supply pipelines based on artificial neural networks, characterized in that: Includes the following steps: The system acquires the water supply pipeline structure and current pipeline water flow detection information of the target area, and identifies abnormal sub-regions of different emergency levels in the target area based on the pipeline water flow detection information. Based on the water supply pipeline structure and the pipeline water flow detection information, the abnormal pipeline in each abnormal sub-region is located through a regional positioning strategy. Based on the emergency level and the abnormal pipeline corresponding to each abnormal sub-region, the pipeline adjustment process is performed on each abnormal sub-region through an artificial neural network to obtain the alternative 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-region, and based on the current pipeline detection information of each abnormal pipeline, readjust the alternative pipelines corresponding to each abnormal pipeline through the artificial neural network. If the current emergency level of an abnormal sub-region is greater than the preset level threshold, return to the step of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region until the current emergency level of no abnormal sub-region is greater than the preset level threshold, and the emergency handling task of the water supply pipeline is completed. The step of identifying abnormal sub-regions of different emergency levels in the target area based on the pipeline water flow detection information includes: Based on the pipeline water flow detection information, the pipeline water flow status of each pipeline is identified, and pipelines with abnormal water flow status are selected as candidate abnormal pipelines. Then, the candidate abnormal pipelines are clustered to obtain each abnormal sub-region. For each abnormal sub-region, identify the number of candidate abnormal pipes in the abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and collect the regional range of the abnormal sub-region in the target region; Based on the regional range of the abnormal sub-region in the target region, the regional criticality of the abnormal sub-region is queried in the regional database, and the criticality weight value of the abnormal sub-region is determined based on the regional criticality of the abnormal sub-region. Based on the number of candidate abnormal pipes in each abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and the criticality weight value of the abnormal sub-region, the abnormality score value corresponding to the abnormal sub-region is calculated through the abnormal region scoring strategy, and the emergency level of the abnormal sub-region is determined based on the abnormality score value.

2. The emergency handling method for water supply pipelines based on artificial neural networks according to claim 1, characterized in that: The method involves calculating the anomaly score value corresponding to each anomaly sub-region based on the number of candidate anomaly pipes in each anomaly sub-region, the anomaly level corresponding to the pipe flow state of each candidate anomaly pipe, and the criticality weight value of the anomaly sub-region, using an anomaly region scoring strategy. This includes: Based on the anomaly level corresponding to the water flow state of each candidate abnormal pipe, a first number of each anomaly 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 pipe in the abnormal sub-region, a first anomaly score value of the abnormal sub-region is queried in the pipe database. The first anomaly score value is weighted and summed using the keyness weight values ​​of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

3. The emergency handling method for water supply pipelines based on artificial neural networks according to claim 2, characterized in that: The method of locating abnormal pipes in each abnormal sub-region based on the water supply pipeline structure and the pipeline water flow detection information, using a regional positioning strategy, includes: For each abnormal sub-region, based on the water supply pipeline line structure, the 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 abnormal pipeline, the pipeline association information of each candidate abnormal pipeline is identified. Based on the anomaly level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, an abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is regarded as the abnormal pipeline of the abnormal sub-region.

4. The emergency handling method for water supply pipelines based on artificial neural networks according to claim 3, characterized in that: Based on the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipelines corresponding to each of the abnormal sub-regions, the process of adjusting the pipelines in each of the abnormal sub-regions using an artificial neural network to obtain alternative pipelines for each of the abnormal pipelines includes: For each abnormal sub-region, based on the water supply pipeline structure, the water flow routes of the abnormal pipeline are identified, and based on the location information of each abnormal pipeline in the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure, the route planning layer of the artificial neural network is used to calculate the water flow routes of each initial replacement pipeline and the water flow duration of each water flow route. Based on the water transport routes of each initial replacement pipeline and the water transport time of each water transport route, the initial replacement pipeline that includes all water flow routes and has the shortest water transport time among the initial replacement pipelines is selected as the initial replacement pipeline corresponding to the abnormal pipeline. Based on the initial replacement pipes corresponding to the abnormal pipes in each of the abnormal sub-regions, and the water transport routes corresponding to each initial replacement pipe, the route adjustment layer of the artificial neural network is used to adjust the water transport routes of each initial replacement pipe to obtain the replacement pipe corresponding to each abnormal pipe.

5. The emergency handling method for water supply pipelines based on artificial neural networks according to claim 4, characterized in that: Before collecting the current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-regions, the process also includes: For each abnormal sub-region, based on the abnormal level corresponding to the water flow status of the abnormal pipe in the abnormal sub-region, the abnormal handling strategy for the abnormal pipe is queried in the strategy database, and the pipe abnormal information template is collected. Based on the water flow status of the abnormal pipes in the abnormal sub-region, the target abnormal handling strategy corresponding to the abnormal pipe is matched in each of the abnormal handling strategies, and the water flow status of the abnormal pipe, the abnormal level of the abnormal pipe, and the target abnormal handling strategy of the abnormal pipe are filled into the abnormal information template to obtain the abnormal handling reporting information of the abnormal pipe. The anomaly handling report information and the location information of the anomaly pipeline are sent to the staff client.

6. The emergency handling method for water supply pipelines based on artificial neural networks according to claim 5, characterized in that: The step of readjusting the replacement pipes corresponding to each abnormal pipe based on the current pipe detection information of each abnormal pipe, through the artificial neural network, includes: Based on the current pipeline detection information of each abnormal pipeline, the current abnormality level and current pipeline water flow status of each abnormal pipeline are identified, and the current pipeline water flow status of each abnormal pipeline is replaced with the current pipeline water flow status of each abnormal pipeline, and the current abnormality level of each abnormal pipeline is replaced with the abnormality level of each abnormal pipeline. The process returns to the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipeline corresponding to each of the abnormal sub-regions. Through artificial neural networks, pipeline adjustment processing is performed on each of the abnormal sub-regions to obtain the alternative pipeline corresponding to each of the abnormal pipelines.

7. An emergency response system for water supply pipelines based on artificial neural networks, characterized in that: include The acquisition module is used to acquire the water supply pipeline structure of the target area and the current pipeline water flow detection information, and based on the pipeline water flow detection information, identify abnormal sub-regions of different emergency levels in the target area; The allocation module is used to locate the abnormal pipes in each abnormal sub-region based on the water supply pipeline structure and the pipeline water flow detection information, and to perform pipeline adjustment processing on each abnormal sub-region based on the emergency level corresponding to each abnormal sub-region and the abnormal pipes corresponding to each abnormal sub-region through an artificial neural network to obtain the replacement pipes corresponding to each abnormal pipe. The identification module is used to collect the current pipeline detection information of each of the abnormal pipelines and the current emergency level of each of the abnormal sub-regions, and based on the current pipeline detection information of each of the abnormal pipelines, readjust the replacement pipelines corresponding to each of the abnormal pipelines through the artificial neural network. The iterative module is used to return to the steps of collecting the current pipeline detection information of each abnormal pipeline and the current emergency level of each abnormal sub-region when the current emergency level of an abnormal sub-region is greater than the preset level threshold, until the emergency handling task of the water supply pipeline is completed when the current emergency level of no abnormal sub-region is greater than the preset level threshold.

8. The emergency response system for water supply pipelines based on artificial neural networks according to claim 7, characterized in that: The acquisition module is specifically used for: Based on the pipeline water flow detection information, the pipeline water flow status of each pipeline is identified, and pipelines with abnormal water flow status are selected as candidate abnormal pipelines. Then, the candidate abnormal pipelines are clustered to obtain each abnormal sub-region. For each abnormal sub-region, identify the number of candidate abnormal pipes in the abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and collect the regional range of the abnormal sub-region in the target region; Based on the regional range of the abnormal sub-region in the target region, the regional criticality of the abnormal sub-region is queried in the regional database, and the criticality weight value of the abnormal sub-region is determined based on the regional criticality of the abnormal sub-region. Based on the number of candidate abnormal pipes in each abnormal sub-region, the abnormality level corresponding to the pipe flow state of each candidate abnormal pipe, and the criticality weight value of the abnormal sub-region, the abnormality score value corresponding to the abnormal sub-region is calculated through the abnormal region scoring strategy, and the emergency level of the abnormal sub-region is determined based on the abnormality score value.

9. The emergency response system for water supply pipelines based on artificial neural networks according to claim 8, characterized in that: The acquisition module is specifically used for: Based on the anomaly level corresponding to the water flow state of each candidate abnormal pipe, a first number of each anomaly 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 pipe in the abnormal sub-region, a first anomaly score value of the abnormal sub-region is queried in the pipe database. The first anomaly score value is weighted and summed using the keyness weight values ​​of the anomaly sub-region to obtain the anomaly score value of the anomaly sub-region.

10. The emergency response system for water supply pipelines based on artificial neural networks according to claim 9, characterized in that: The allocation module is specifically used for: For each abnormal sub-region, based on the water supply pipeline line structure, the 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 abnormal pipeline, the pipeline association information of each candidate abnormal pipeline is identified. Based on the anomaly level of each candidate abnormal pipeline and the pipeline association information of each candidate abnormal pipeline, an abnormal pipeline in each candidate abnormal pipeline is identified through a self-attention network, and the abnormal pipeline is regarded as the abnormal pipeline of the abnormal sub-region.

11. The emergency response system for water supply pipelines based on artificial neural networks 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 structure, the water flow routes of the abnormal pipeline are identified, and based on the location information of each abnormal pipeline in the water supply pipeline structure, the water flow routes of the abnormal pipeline, and the water supply pipeline structure, the route planning layer of the artificial neural network is used to calculate the water flow routes of each initial replacement pipeline and the water flow duration of each water flow route. Based on the water transport routes of each initial replacement pipeline and the water transport time of each water transport route, the initial replacement pipeline that includes all water flow routes and has the shortest water transport time among the initial replacement pipelines is selected as the initial replacement pipeline corresponding to the abnormal pipeline. Based on the initial replacement pipes corresponding to the abnormal pipes in each of the abnormal sub-regions, and the water transport routes corresponding to each initial replacement pipe, the route adjustment layer of the artificial neural network is used to adjust the water transport routes of each initial replacement pipe to obtain the replacement pipe corresponding to each abnormal pipe.

12. The emergency response system for water supply pipelines based on artificial neural networks according to claim 11, characterized in that: The identification module is specifically used for: Based on the current pipeline detection information of each abnormal pipeline, the current abnormality level and current pipeline water flow status of each abnormal pipeline are identified, and the current pipeline water flow status of each abnormal pipeline is replaced with the current pipeline water flow status of each abnormal pipeline, and the current abnormality level of each abnormal pipeline is replaced with the abnormality level of each abnormal pipeline. The process returns to the emergency level corresponding to each of the abnormal sub-regions and the abnormal pipeline corresponding to each of the abnormal sub-regions. Through artificial neural networks, pipeline adjustment processing is performed on each of the abnormal sub-regions to obtain the alternative pipeline corresponding to each of the abnormal pipelines.

13. The emergency response system for water supply pipelines based on artificial neural networks according to claim 12, characterized in that: Also includes: The query module is used to query the anomaly handling strategy for each abnormal sub-region based on the anomaly level corresponding to the pipe flow status of the abnormal pipe in the abnormal sub-region, and to collect the pipe anomaly information template. The filling module is used to match the target anomaly handling strategy corresponding to the anomaly pipe in each anomaly handling strategy based on the pipe flow status of the anomaly pipe in the anomaly sub-region, and fill the pipe flow status, anomaly level, and target anomaly handling strategy of the anomaly pipe into the anomaly information template to obtain the anomaly handling reporting information of the anomaly pipe. The sending module is used to send the anomaly handling reporting information and the location information of the anomaly pipeline to the staff client.

14. A computer device, characterized in that: The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 6.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1 to 6.

16. A computer program product, characterized in that: The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1 to 6.

Images