Training method of effusion working condition determination model and effusion working condition determination method and device

Abstract

The invention discloses a training method of an effusion working condition determination model and an effusion working condition determination method and device, and belongs to the technical field of gathering and transportation pipe networks. According to the training method of the effusion working condition determination model, firstly, the characteristic value of the pipe network operation parameter in the sample time period and the sample working condition label corresponding to the sample time node are obtained, the characteristic value of the pipe network operation parameter in the sample time node is obtained based on the characteristic value of the pipe network operation parameter in the sample time period, and the sample working condition label corresponding to the sample working condition label is obtained. And obtaining a correlation coefficient corresponding to the sample time node, and performing model training based on the sample working condition label corresponding to the sample time node, the characteristic value and the correlation coefficient to obtain a hydrops working condition determination model. Therefore, according to the method, the model training is performed based on the real pipe network operation data and the effusion working condition, so that the model obtained by training can accurately determine the effusion working condition of the target pipe network, and the accuracy of determining the effusion working condition is improved.

Description

Technical Field

[0001] The present application relates to the technical field of gathering and transportation pipeline networks, and in particular to a training method for a model for determining a liquid accumulation condition, and a method and device for determining a liquid accumulation condition. Background Art

[0002] When natural gas is transported through a natural gas pipeline network, free water and heavy hydrocarbon components in the natural gas are easily liquefied and precipitated due to the influence of temperature and pressure along the line, and remain in the pipelines with lower terrain, thus forming liquid accumulation. The generation of liquid accumulation will not only increase pipeline transportation energy consumption and reduce pipeline transportation efficiency, but also accelerate the pipeline corrosion rate and pose a risk of gas leakage. Among them, taking pipe cleaning measures can effectively control the liquid accumulation in the pipe, but pipe cleaning measures also have risks and are prone to wear on the inner wall of the pipeline. Therefore, it is necessary to judge the liquid accumulation condition in order to determine the time for pipe cleaning.

[0003] In the related technology, the operating parameters such as the temperature and pressure distribution of the pipeline are simulated mainly through simulation software to obtain the simulated amount of liquid accumulation, and then the liquid accumulation condition is determined based on the simulated amount of liquid accumulation.

[0004] However, the fluid accumulation condition in the related art is determined based on the fluid accumulation simulation quantity, which is not real data and is not accurate enough, which leads to a low accuracy rate of the determined fluid accumulation condition. Summary of the invention

[0005] The embodiment of the present application provides a training method for a fluid accumulation condition determination model, a method and a device for determining a fluid accumulation condition, which can improve the accuracy of the determined fluid accumulation condition. The specific technical solution is as follows:

[0006] In one aspect, a method for training a fluid accumulation condition determination model is provided, the method comprising:

[0007] Acquire multiple sample operating condition labels; wherein the sample operating condition labels are used to indicate whether there is liquid accumulation in the sample pipe network at the sample time node;

[0008] For each sample time node, a plurality of pipe network operation parameters of the sample pipe network within a sample period are obtained; wherein the sample period is located before the sample time node in terms of time sequence;

[0009] For each pipe network operation parameter, obtain a characteristic value of the pipe network operation parameter in the sample period; based on the characteristic value of the pipe network operation parameter in the sample period, obtain a characteristic value of the pipe network operation parameter at the sample time node;

[0010] Obtaining the correlation coefficient corresponding to the sample time node; wherein the correlation coefficient is used to indicate the degree of correlation between any two pipe network operation parameters within the sample period;

[0011] Based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node, model training is performed to obtain a liquid accumulation condition determination model; wherein the liquid accumulation condition determination model is used to determine the liquid accumulation condition of the target pipeline network.

[0012] In another aspect, a method for determining a fluid accumulation condition is provided, the method comprising:

[0013] Obtain multiple pipeline network operation parameters of the target pipeline network within the target period before the current time node;

[0014] For each pipeline network operation parameter, obtain a characteristic value of the pipeline network operation parameter in the target time period; based on the characteristic value of the pipeline network operation parameter in the target time period, obtain a characteristic value of the pipeline network operation parameter at the current time node;

[0015] Obtaining the correlation coefficient corresponding to the current time node;

[0016] Inputting the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain a first fluid accumulation condition;

[0017] Among them, the first fluid accumulation condition is the fluid accumulation condition corresponding to the target pipeline network at the current time node, and the fluid accumulation condition determination model is obtained by training based on the sample condition label, eigenvalue and correlation coefficient corresponding to the sample time node, and the sample condition label is used to indicate whether there is fluid accumulation in the sample pipeline network at the sample time node.

[0018] In another aspect, a training device for a fluid accumulation condition determination model is provided, the device comprising:

[0019] A first acquisition module is used to acquire a plurality of sample operating condition labels; wherein the sample operating condition labels are used to indicate whether there is fluid accumulation in the sample pipe network at the sample time node;

[0020] A second acquisition module is used to acquire, for each sample time node, a plurality of pipe network operation parameters of the sample pipe network within a sample period; wherein the sample period is located before the sample time node in terms of time sequence;

[0021] A third acquisition module is used to acquire, for each pipe network operation parameter, a characteristic value of the pipe network operation parameter in the sample period; based on the characteristic value of the pipe network operation parameter in the sample period, acquire the characteristic value of the pipe network operation parameter at the sample time node;

[0022] A fourth acquisition module is used to acquire the correlation coefficient corresponding to the sample time node; wherein the correlation coefficient is used to represent the degree of correlation between any two pipe network operation parameters within the sample period;

[0023] The training module is used to perform model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a liquid accumulation condition determination model; wherein the liquid accumulation condition determination model is used to determine the liquid accumulation condition of the target pipeline network.

[0024] In a possible implementation, the sample period includes a first sample period and a second sample period, and a boundary value of the first sample period is greater than a boundary value of the second sample period;

[0025] The third acquisition module is used to obtain the mean value of the pipeline network operation parameter in the first sample period to obtain a first mean value feature; obtain the changing trend of the pipeline network operation parameter in the first sample period to obtain a first trend feature; obtain the difference between the pipeline network operation parameter corresponding to the sample time node and the mean value to obtain a first deviation feature; based on the first mean feature, the first trend feature and the first deviation feature, obtain the first characteristic value of the pipeline network operation parameter in the first sample period; obtain the second characteristic value of the pipeline network operation parameter in the second sample period.

[0026] In another possible implementation, the fourth acquisition module is used to obtain the covariance between the first pipeline network operation parameter and the second pipeline network operation parameter within the sample period; wherein the first pipeline network operation parameter and the second pipeline network operation parameter are any two parameters among the multiple pipeline network operation parameters; obtain the first standard deviation and the second standard deviation; wherein the first standard deviation is the standard deviation of the first pipeline network operation parameter within the sample period, and the second standard deviation is the standard deviation of the second pipeline network operation parameter within the sample period; obtain the product of the first standard deviation and the second standard deviation to obtain a first product value; obtain the ratio of the covariance to the first product value to obtain the correlation coefficient between the first pipeline network operation parameter and the second pipeline network operation parameter within the sample period.

[0027] In another possible implementation, the training module is used to determine the type of fluid accumulation corresponding to the sample time node when the sample operating condition label indicates that the sample pipe network has fluid accumulation at the sample time node; and perform model training based on the sample operating condition label, fluid accumulation type, characteristic value and correlation coefficient corresponding to each sample time node to obtain the fluid accumulation condition determination model.

[0028] In another possible implementation, the second acquisition module is used to obtain the gas transmission volume and water transmission volume of the sample pipe network within the sample period; determine the ratio of the water transmission volume to the gas transmission volume to obtain the water-gas ratio; determine the first pressure value and the second pressure value of the sample pipe network, the first pressure value is the pressure value of the sample pipe network at the starting end, and the second pressure value is the pressure value of the sample pipe network at the ending end; determine the difference between the first pressure value and the second pressure value to obtain the transmission pressure difference; wherein the multiple pipe network operation parameters include the gas transmission volume, the water transmission volume, the water-gas ratio and the transmission pressure difference.

[0029] In another aspect, a device for determining a fluid accumulation condition is provided, the device comprising:

[0030] A fifth acquisition module, used to acquire multiple pipe network operation parameters of the target pipe network within a target period before the current time node;

[0031] A sixth acquisition module is used to acquire, for each pipe network operation parameter, a characteristic value of the pipe network operation parameter in the target time period; based on the characteristic value of the pipe network operation parameter in the target time period, acquire the characteristic value of the pipe network operation parameter at the current time node;

[0032] A seventh acquisition module, used to acquire the correlation coefficient corresponding to the current time node;

[0033] A first determination module, configured to input the characteristic value and the correlation coefficient corresponding to the current time node into a fluid accumulation condition determination model to obtain a first fluid accumulation condition;

[0034] Among them, the first fluid accumulation condition is the fluid accumulation condition corresponding to the target pipeline network at the current time node, and the fluid accumulation condition determination model is obtained by training based on the sample condition label, eigenvalue and correlation coefficient corresponding to the sample time node, and the sample condition label is used to indicate whether there is fluid accumulation in the sample pipeline network at the sample time node.

[0035] In one possible implementation, the first determination module is used to input the characteristic value and correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain the second fluid accumulation condition; based on at least one of the third fluid accumulation condition and the fourth fluid accumulation condition, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the target time period includes a first target time period and a second target time period, the third fluid accumulation condition is the fluid accumulation condition corresponding to each time node within the first target time period, and the fourth fluid accumulation condition is the fluid accumulation condition corresponding to each time node within the second target time period.

[0036] In another possible implementation, the first determination module is used to determine at least one of the first quantity and the second quantity when the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node; wherein the first quantity is the quantity of the third fluid accumulation condition indicating the presence of fluid accumulation, and the second quantity is the quantity of the fourth fluid accumulation condition indicating the presence of fluid accumulation; when at least one of the first quantity and the second quantity is greater than a corresponding preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the first fluid accumulation condition indicates that there is fluid accumulation at the current time node.

[0037] In another possible implementation, the first determination module is used to determine a third quantity when the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node; wherein the third quantity is the number of the third fluid accumulation condition or the fourth fluid accumulation condition in which fluid accumulation exists continuously before the current time node; when the third quantity is greater than a first preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the first fluid accumulation condition indicates that there is fluid accumulation at the current time node.

[0038] In another possible implementation, the device further includes:

[0039] An eighth acquisition module, used to acquire effusion types corresponding to multiple time nodes;

[0040] A modification module is used to modify the effusion type corresponding to the current time node to the effusion type corresponding to the previous time node if the effusion type corresponding to the current time node is different from the effusion types corresponding to the previous time node and the next time node, and the effusion types corresponding to the previous time node and the next time node are the same.

[0041] On the other hand, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the training method for determining the effusion condition model or the effusion condition determination method described in any of the above.

[0042] On the other hand, a computer-readable storage medium is provided, in which at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the training method for determining the fluid effusion condition model or the fluid effusion condition determination method described in any of the above.

[0043] On the other hand, a computer program product is provided, in which at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the training method for determining the fluid effusion operating condition model or the fluid effusion operating condition determination method described in any of the above.

[0044] The embodiment of the present application provides a training method for a model for determining a liquid accumulation condition. The method first obtains the characteristic values ​​of the pipe network operation parameters in a sample period and the sample condition labels corresponding to the sample time nodes, obtains the characteristic values ​​of the pipe network operation parameters at the sample time nodes based on the characteristic values ​​of the pipe network operation parameters in the sample period, and obtains the correlation coefficients corresponding to the sample time nodes, and performs model training based on the sample condition labels, characteristic values, and correlation coefficients corresponding to the sample time nodes to obtain a model for determining a liquid accumulation condition. It can be seen that the method performs model training based on real pipe network operation data and liquid accumulation conditions, so the trained model can accurately determine the liquid accumulation conditions of the target pipe network, thereby improving the accuracy of determining the liquid accumulation conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of an implementation environment of a training method for determining a model for a fluid accumulation condition provided in an embodiment of the present application;

[0046] Figure 2 It is a flow chart of a training method for a model for determining a fluid accumulation condition provided in an embodiment of the present application;

[0047] Figure 3 It is a flow chart of a training method for a model for determining a fluid accumulation condition provided in an embodiment of the present application;

[0048] Figure 4 is a flow chart of a method for determining a liquid accumulation condition provided in an embodiment of the present application;

[0049] Figure 5 is a flow chart of a method for determining a liquid accumulation condition provided in an embodiment of the present application;

[0050] Figure 6 is a schematic diagram of determining a liquid accumulation condition provided in an embodiment of the present application;

[0051] Figure 7 It is a structural schematic diagram of a training device for determining a model for a fluid accumulation condition provided in an embodiment of the present application;

[0052] Figure 8 It is a structural schematic diagram of a device for determining a liquid accumulation condition provided in an embodiment of the present application;

[0053] Fig. 9 It is a structural block diagram of a terminal provided in an embodiment of the present application;

[0054] Fig.10 It is a structural block diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the technical solutions and advantages of the present application clearer, the implementation methods of the present application are described in further detail below.

[0056] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0057] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the network operation parameters, characteristic values ​​and correlation coefficients involved in this application are all obtained with full authorization.

[0058] Figure 1 Schematic diagram of an implementation environment of a method for training a model for determining a fluid accumulation condition provided in an embodiment of the present application. Figure 1 The implementation environment includes: an electronic device, which can be provided as a terminal 101, a server 102, or a terminal 101 and a server 102. If the electronic device is provided as a terminal 101 and a server 102, the terminal 101 and the server 102 can be connected via a wireless or wired network. In the embodiments of the present application, the electronic device is not specifically limited.

[0059] If the electronic device is provided as the terminal 101, the terminal 101 performs model training to obtain a liquid accumulation condition determination model. The liquid accumulation condition determination model can be deployed in the terminal 101 or in other terminals, so that the terminal 101 or other terminals can determine the liquid accumulation condition of the target pipe network through the liquid accumulation condition determination model.

[0060] If the electronic device is provided as the server 102, the server 102 performs model training to obtain the liquid accumulation condition determination model. The liquid accumulation condition determination model can be deployed in the terminal 101, so that the terminal 101 can determine the liquid accumulation condition of the target pipe network through the liquid accumulation condition determination model.

[0061] If the electronic device is provided as a terminal 101 and a server 102, the server 102 performs model training to obtain a fluid accumulation condition determination model, and then the fluid accumulation condition determination model is deployed in the terminal 101, so that the terminal 101 can determine the fluid accumulation condition of the target pipeline network through the fluid accumulation condition determination model.

[0062] The terminal 101 is at least one of a mobile phone, a tablet computer, a PC (Personal Computer), an intelligent voice interaction device, a vehicle-mounted terminal, etc. The server 102 can be at least one of a server, a server cluster consisting of multiple servers, a cloud server, a cloud computing platform, and a virtualization center.

[0063] Figure 2 is a flowchart of a training method for a fluid accumulation condition determination model provided in an embodiment of the present application, which is executed by a first electronic device, see Figure 2 , the method comprising:

[0064] Step 201: A first electronic device obtains a plurality of sample operating condition labels.

[0065] The sample operating condition label is used to indicate whether there is liquid accumulation in the sample pipeline network at the sample time node, wherein the sample pipeline network may be a pipeline network for transporting natural gas or a pipeline network for transporting other gases, and there is no specific limitation on this.

[0066] The first electronic device may obtain multiple sample operating condition labels from a sample library, or may obtain multiple sample operating condition labels sent by other devices, which is not specifically limited.

[0067] Step 202: For each sample time node, the first electronic device obtains a plurality of pipe network operation parameters of the sample pipe network within the sample period.

[0068] The sample period is located before the sample time node in terms of time sequence, and the sample period includes one or more periods, which are not specifically limited.

[0069] The multiple pipeline network operation parameters include gas transmission volume, water transmission volume, water-gas ratio and transmission pressure difference. For example, if the sample pipeline network is a pipeline network for transporting natural gas, the gas transmission volume is the amount of natural gas transported by the sample pipeline network, the water transmission volume is the amount of water in the natural gas transported by the sample pipeline network, the water-gas ratio is the proportion of water in the natural gas, and the transmission pressure difference is the pressure difference at both ends of the sample pipeline network. Of course, the pipeline network operation parameters may also include other parameters, which are not specifically limited.

[0070] The first electronic device may obtain multiple pipe network operation parameters of the sample pipe network within the sample period from the sample library, or may obtain multiple pipe network operation parameters of the sample pipe network within the sample period sent by other devices, without specific limitation.

[0071] Step 203: For each pipe network operation parameter, the first electronic device obtains a characteristic value of the pipe network operation parameter within a sample period; based on the characteristic value of the pipe network operation parameter within the sample period, obtains a characteristic value of the pipe network operation parameter at a sample time node.

[0072] If the sample period includes multiple periods, for example, the sample period includes a first sample period and a second sample period, the first electronic device obtains a characteristic value of the pipe network operation parameter in the first sample period and a characteristic value in the second sample period. The characteristic value of the pipe network operation parameter in the first sample period includes at least one of the mean characteristic, trend characteristic and deviation characteristic of the pipe network operation parameter in the first sample period, and the characteristic value of the pipe network operation parameter in the second sample period includes at least one of the mean characteristic, trend characteristic and deviation characteristic of the pipe network operation parameter in the second sample period. The first electronic device uses the characteristic value of the pipe network operation parameter in the first sample period and the characteristic value of the pipe network operation parameter in the second sample period as the characteristic value of the pipe network operation parameter at the sample time node.

[0073] If the sample period includes one period, the first electronic device obtains a characteristic value of the pipe network operation parameter in the period, and uses the characteristic value of the pipe network operation parameter in the period as the characteristic value of the pipe network operation parameter at the sample time node.

[0074] Step 204: The first electronic device obtains the correlation coefficient corresponding to the sample time node.

[0075] The correlation coefficient is used to represent the correlation between any two pipe network operation parameters within a sample period. In the embodiment of the present application, the first electronic device may represent the correlation between the two pipe network operation parameters by using the Pearson correlation coefficient.

[0076] If the sample period includes a first sample period and a second sample period, the first electronic device obtains the correlation coefficient of any two pipeline network operation parameters in the first sample period and the correlation coefficient in the second sample period, and uses the correlation coefficient of any two pipeline network operation parameters in the first sample period and the correlation coefficient in the second sample period as the correlation coefficient corresponding to the sample time node.

[0077] Step 205: The first electronic device performs model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a fluid accumulation condition determination model.

[0078] The first electronic device uses the sample operating condition label corresponding to each sample time node as a training target, and uses the eigenvalue and correlation coefficient corresponding to each sample time node as training samples to perform model training to obtain a fluid accumulation condition determination model.

[0079] The embodiment of the present application provides a training method for a model for determining a liquid accumulation condition. The method first obtains the characteristic values ​​of the pipe network operation parameters in a sample period and the sample condition labels corresponding to the sample time nodes, obtains the characteristic values ​​of the pipe network operation parameters at the sample time nodes based on the characteristic values ​​of the pipe network operation parameters in the sample period, and obtains the correlation coefficients corresponding to the sample time nodes, and performs model training based on the sample condition labels, characteristic values, and correlation coefficients corresponding to the sample time nodes to obtain a model for determining a liquid accumulation condition. It can be seen that the method performs model training based on real pipe network operation data and liquid accumulation conditions, so the trained model can accurately determine the liquid accumulation conditions of the target pipe network, thereby improving the accuracy of determining the liquid accumulation conditions.

[0080] Figure 2 The figure shows a process of training a fluid effusion condition determination model provided by the present application. The training method of the fluid effusion condition determination model provided by the present application is further elaborated in detail below. Figure 3 is a flowchart of a training method for a fluid accumulation condition determination model provided in an embodiment of the present application, which is executed by a first electronic device, see Figure 3 , the method comprising:

[0081] Step 301: A first electronic device obtains a plurality of sample operating condition labels.

[0082] This step is the same as step 201 and will not be described again here.

[0083] Step 302: For each sample time node, the first electronic device obtains a plurality of pipe network operation parameters of the sample pipe network within the sample period.

[0084] The sample period is located before the sample time node in terms of timing. The sample period includes one or more periods. When the sample period includes multiple periods, the number of multiple periods can be set and changed as needed. In the embodiment of the present application, only the sample period including the first sample period and the second sample period is used as an example for explanation.

[0085] If the sample period includes a first sample period and a second sample period, the boundary value of the first sample period is greater than the boundary value of the second sample period. For example, the sample time node is A, the second sample period is the time period from 7 days before the A time node to the A time node, and the first sample period is the time period from 30 days before the A time node to the A time node.

[0086] If the sample period includes a first sample period and a second sample period, the first electronic device obtains a plurality of pipe network operation parameters of the sample pipe network in the first sample period and a plurality of pipe network operation parameters of the sample pipe network in the second sample period.

[0087] For the first sample period, the first electronic device obtains the gas and water delivery of the sample pipe network within the first sample period; determines the ratio of the water delivery to the gas delivery to obtain the water-gas ratio; determines the difference between the pressure value at the starting end and the pressure value at the ending end of the sample pipe network to obtain the delivery pressure difference. The multiple pipe network operation parameters include gas delivery, water delivery, water-gas ratio and delivery pressure difference.

[0088] The process of the first electronic device acquiring multiple pipe network operating parameters within the second sample period is the same as the process of acquiring multiple pipe network operating parameters within the first sample period, which will not be repeated here.

[0089] If the sample period includes one period, the first electronic device directly obtains the gas and water delivery within the sample period; determines the water-gas ratio according to the gas and water delivery; and determines the pressure difference at both ends of the sample pipe network to obtain the delivery pressure difference.

[0090] One thing that needs to be explained is that after the first electronic device obtains multiple pipeline network operating parameters, it can directly execute step 303, or it can first pre-process the multiple pipeline network operating parameters, for example, eliminate abnormal values, missing values, etc., and execute step 303 based on the pre-processed multiple pipeline network operating parameters.

[0091] Step 303: For each pipe network operation parameter, the first electronic device obtains a first characteristic value of the pipe network operation parameter within a first sample period.

[0092] This step can be achieved by following the steps (1) to (4), including:

[0093] (1) For each pipe network operation parameter, the first electronic device obtains the mean value of the pipe network operation parameter in a first sample period to obtain a first mean value feature.

[0094] For example, if the pipe network operation parameter is the gas transmission volume, the first electronic device determines the gas transmission volume of each day within 30 days before the sample time node, determines the average of the gas transmission volume within these 30 days, and obtains the first average characteristic of the gas transmission volume. If the pipe network operation parameter is the water transmission volume, the first electronic device determines the water transmission volume of each day within 30 days before the sample time node, determines the average of the water transmission volume within these 30 days, and obtains the first average characteristic of the water transmission volume. If the pipe network operation parameter is the water-gas ratio, the first electronic device determines the water-gas ratio of each day within 30 days before the sample time node, determines the average of the water-gas ratio within these 30 days, and obtains the first average characteristic of the water-gas ratio. If the pipe network operation parameter is the transmission pressure difference, the first electronic device determines the transmission pressure difference of each day within 30 days before the sample time node, determines the average of the transmission pressure difference within these 30 days, and obtains the first average characteristic of the transmission pressure difference.

[0095] (2) The first electronic device obtains a change trend of the pipe network operation parameter within a first sample period to obtain a first trend feature.

[0096] The first electronic device determines whether the pipe network operation parameter shows an upward trend or a downward trend within the first sample period. If it shows an upward trend, the first electronic device assigns a first trend characteristic of the pipe network operation parameter to 1; if it shows a downward trend, the first electronic device assigns a first trend characteristic of the pipe network operation parameter to -1.

[0097] For example, if the network operation parameter is gas transmission volume, the first electronic device determines the changing trend of gas transmission volume within 30 days before the sample time node. If it is an upward trend, the first trend characteristic of gas transmission volume is determined to be 1; if it is a downward trend, the first trend characteristic of gas transmission volume is determined to be -1. Similarly, if the network operation parameter is water transmission volume, the first electronic device determines the changing trend of water transmission volume within 30 days before the sample time node, and obtains the first trend characteristic of water transmission volume. If the network operation parameter is water-gas ratio, the first electronic device determines the changing trend of water-gas ratio within 30 days before the sample time node, and obtains the first trend characteristic of water-gas ratio. If the network operation parameter is transmission pressure difference, the first electronic device determines the changing trend of transmission pressure difference within 30 days before the sample time node, and obtains the first trend characteristic of transmission pressure difference.

[0098] (3) The first electronic device obtains the difference between the pipe network operation parameter corresponding to the sample time node and the mean value to obtain a first deviation feature.

[0099] For example, if the network operation parameter is gas transmission volume, the first electronic device obtains the difference between the gas transmission volume corresponding to the sample time node and the mean of the gas transmission volume, and obtains the first deviation characteristic of the gas transmission volume. If the network operation parameter is water transmission volume, the first electronic device obtains the difference between the water transmission volume corresponding to the sample time node and the mean of the water transmission volume, and obtains the first deviation characteristic of the water transmission volume. If the network operation parameter is water-gas ratio, the first electronic device obtains the difference between the water-gas ratio corresponding to the sample time node and the mean of the water-gas ratio, and obtains the first deviation characteristic of the water-gas ratio. If the network operation parameter is pressure difference, the first electronic device obtains the difference between the pressure difference corresponding to the sample time node and the mean of the pressure difference, and obtains the first deviation characteristic of the pressure difference.

[0100] (4) The first electronic device obtains a first feature value based on the first mean feature, the first trend feature, and the first deviation feature.

[0101] The first electronic device uses the first mean feature, the first trend feature and the first deviation feature as the first feature value, that is, the first feature value includes the first mean feature, the first trend feature and the first deviation feature. Alternatively, the first electronic device uses the sum of the first mean feature, the first trend feature and the first deviation feature as the first feature value. Alternatively, the first electronic device uses the average value of the first mean feature, the first trend feature and the first deviation feature as the first feature value. In the embodiment of the present application, this is not specifically limited.

[0102] Step 304: The first electronic device obtains a second characteristic value of the pipe network operation parameter within a second sample period.

[0103] In a possible implementation, the first electronic device obtains a second mean characteristic, a second trend characteristic, and a second deviation characteristic of the pipeline network operation parameter in a second sample period, and determines a second characteristic value based on the second mean characteristic, the second trend characteristic, and the second deviation characteristic.

[0104] For example, the second sample period is the time period from 7 days before the sample time node to the sample time node, and the pipeline network operation parameter is the gas transmission volume, then the first electronic device obtains the gas transmission volume of each day in the 7 days before the sample time node, determines the average of the gas transmission volume in these 7 days, and obtains the second average characteristic of the gas transmission volume. If the pipeline network operation parameter is the water transmission volume, then the first electronic device obtains the water transmission volume of each day in the 7 days before the sample time node, determines the average of the water transmission volume in these 7 days, and obtains the second average characteristic of the water transmission volume. If the pipeline network operation parameter is the water-gas ratio, then the first electronic device obtains the water-gas ratio of each day in the 7 days before the sample time node, determines the average of the water-gas ratio in these 7 days, and obtains the second average characteristic of the water-gas ratio. If the pipeline network operation parameter is the transmission pressure difference, then the first electronic device obtains the transmission pressure difference of each day in the 7 days before the sample time node, determines the average of the transmission pressure difference in these 7 days, and obtains the second average characteristic of the transmission pressure difference.

[0105] The process of the first electronic device acquiring the second trend feature and the second deviation feature is the same as the process of acquiring the first trend feature and the first deviation feature in step 303, and will not be described again.

[0106] In another possible implementation, the first electronic device obtains a second mean characteristic of the pipeline network operation parameter in a second sample period as the second characteristic value.

[0107] Since the second sample period includes a shorter time period, the change trend and deviation may not be obvious, and therefore, the first electronic device may directly use the second mean feature as the second feature value.

[0108] Step 305: The first electronic device obtains a characteristic value of the pipe network operation parameter at a sample time node based on the first characteristic value and the second characteristic value.

[0109] The first electronic device uses the first characteristic value and the second characteristic value as the characteristic value of the pipe network operation parameter at the sample time node, that is, the characteristic value of the pipe network operation parameter at the sample time node includes the first characteristic value and the second characteristic value.

[0110] Step 306: The first electronic device obtains the correlation coefficient corresponding to the sample time node.

[0111] The correlation coefficient is used to indicate the degree of correlation between any two pipe network operation parameters within a sample period.

[0112] This step can be achieved by following the steps (1) to (4), including:

[0113] (1) The first electronic device obtains the covariance between the first pipe network operation parameter and the second pipe network operation parameter within a sample period.

[0114] The first pipe network operation parameter and the second pipe network operation parameter are any two parameters among a plurality of pipe network operation parameters.

[0115] If the sample period includes a first sample period and a second sample period, the first electronic device respectively obtains the covariance between the first pipe network operation parameter and the second pipe network operation parameter in the first sample period and the covariance between the first pipe network operation parameter and the second pipe network operation parameter in the second sample period.

[0116] In the embodiment of the present application, the manner in which the first electronic device determines the covariance is not specifically limited.

[0117] (2) The first electronic device obtains the first standard deviation and the second standard deviation.

[0118] The first standard deviation is the standard deviation of the first pipe network operation parameter within the sample period, and the second standard deviation is the standard deviation of the second pipe network operation parameter within the sample period.

[0119] If the sample period includes a first sample period and a second sample period, the first standard deviation includes the standard deviation of the first pipeline network operation parameter in the first sample period and the standard deviation in the second sample period, and the second standard deviation includes the standard deviation of the second pipeline network operation parameter in the first sample period and the standard deviation in the second sample period.

[0120] (3) The first electronic device obtains the product of the first standard deviation and the second standard deviation to obtain a first product value.

[0121] If the sample period includes a first sample period and a second sample period, the first electronic device determines the product of the standard deviation of the first pipe network operation parameter in the first sample period and the standard deviation of the second pipe network operation parameter in the first sample period to obtain a second product value; determines the product of the standard deviation of the first pipe network operation parameter in the second sample period and the standard deviation of the second pipe network operation parameter in the second sample period to obtain a third product value, and the first product value includes the second product value and the third product value.

[0122] (4) The first electronic device obtains the ratio of the covariance to the first product value, and obtains the correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter within the sample period.

[0123] If the sample period includes a first sample period and a second sample period, the first electronic device obtains the ratio of the covariance between the first pipe network operation parameter and the second pipe network operation parameter in the first sample period to the second product value, and obtains the correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter in the first sample period. The first electronic device obtains the ratio of the covariance between the first pipe network operation parameter and the second pipe network operation parameter in the second sample period to the third product value, and obtains the correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter in the second sample period. Accordingly, the correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter in the sample period includes the correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter in the first sample period and the correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter in the second sample period.

[0124] For example, the first sample period is a period of time from 30 days before the sample time node to the sample time node, and the second sample period is a period of time from 7 days before the sample time node to the sample time node. The first pipe network operation parameter and the second pipe network operation parameter are the pressure difference and the water delivery volume, respectively. Then, the first electronic device obtains the correlation coefficient of the pressure difference and the water delivery volume within 30 days before the sample time node and the correlation coefficient within 7 days before the sample time node through steps (1) to (4).

[0125] The above is explained by taking the first electronic device obtaining the correlation coefficient of any two pipe network operation parameters within the sample period as an example. In the embodiment of the present application, since the water-gas ratio can reflect the correlation between the water delivery and the gas delivery to a certain extent, the first electronic device can also only obtain the correlation coefficient between the pressure difference and the water delivery within the sample period, the correlation coefficient between the pressure difference and the gas delivery within the sample period, and the correlation coefficient between the pressure difference and the water-gas ratio within the sample period.

[0126] Step 307: The first electronic device performs model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a fluid accumulation condition determination model.

[0127] In one possible implementation, the first electronic device directly performs model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a liquid accumulation condition determination model. The liquid accumulation condition determination model can determine the liquid accumulation condition of the target pipeline network, that is, whether there is liquid accumulation in the target pipeline network at the current time node.

[0128] In another possible implementation, the first electronic device performs model training based on the type of fluid accumulation. The process may be: when the sample operating condition label indicates that fluid accumulation exists in the sample pipe network at the sample time node, the first electronic device determines the type of fluid accumulation corresponding to the sample time node; based on the sample operating condition label, fluid accumulation type, characteristic value and correlation coefficient corresponding to each sample time node, the model is trained to obtain a fluid accumulation condition determination model.

[0129] In this implementation, the liquid accumulation condition determination model can not only determine whether there is liquid accumulation in the target pipe network at the current time node, but also determine the type of liquid accumulation if there is liquid accumulation, for example, whether the liquid accumulation type is temporary liquid accumulation or regular liquid accumulation.

[0130] In the embodiment of the present application, a single machine learning model is prone to overfitting, and the ensemble learning method refers to combining multiple machine learning models to obtain better results, so that the combined model has stronger generalization ability. The XGBoost (Extreme Gradient Boosting) algorithm is one of the Boosting methods in the ensemble method. It has shown a strong influence in the field of machine learning. It is not easy to overfit while having a high accuracy rate. Therefore, the embodiment of the present application can perform model training through the XGBoost algorithm.

[0131] The XGBoost algorithm builds k regression trees so that the predicted value of the tree group is as close to the true value as possible and has the greatest generalization ability. The final prediction function is: in, Indicates the prediction result.

[0132] The objective function can be defined as: The objective function consists of two parts: loss function and regularization term, where i represents the i-th sample. Represents the prediction error of the i-th sample. The smaller the error, the better.

[0133] Ω(f k ) is a function representing the complexity of the tree. The smaller it is, the lower the complexity and the stronger the generalization ability. Among them, T represents the number of nodes in the tree, w j Represents a set of scores for the leaf nodes of the tree, with γ and λ being coefficients.

[0134] In the embodiment of the present application, after the first electronic device obtains the fluid accumulation working condition determination model, the fluid accumulation working condition determination model can be tested, and if the test passes, the fluid accumulation working condition can be determined by the fluid accumulation working condition determination model. In addition, during the use of the model, training samples can be filled regularly or irregularly to update the model, thereby improving the accuracy of the determination of the fluid accumulation working condition.

[0135] The embodiment of the present application provides a training method for a model for determining a liquid accumulation condition. The method first obtains the characteristic values ​​of the pipe network operation parameters in a sample period and the sample condition labels corresponding to the sample time nodes, obtains the characteristic values ​​of the pipe network operation parameters at the sample time nodes based on the characteristic values ​​of the pipe network operation parameters in the sample period, and obtains the correlation coefficients corresponding to the sample time nodes, and performs model training based on the sample condition labels, characteristic values, and correlation coefficients corresponding to the sample time nodes to obtain a model for determining a liquid accumulation condition. It can be seen that the method performs model training based on real pipe network operation data and liquid accumulation conditions, so the trained model can accurately determine the liquid accumulation conditions of the target pipe network, thereby improving the accuracy of determining the liquid accumulation conditions.

[0136] Furthermore, the model trained by the method provided in this application has high migration reusability and does not require the use of professional software or additional software costs.

[0137] Figure 4 is a flow chart of a method for determining a fluid accumulation condition provided in an embodiment of the present application, which is executed by a second electronic device, wherein the second electronic device and the first electronic device may be the same electronic device or different electronic devices, which is not specifically limited. Figure 4 , the method comprising:

[0138] Step 401: The second electronic device obtains a plurality of pipe network operation parameters of the target pipe network within a target period before the current time node.

[0139] The multiple pipe network operation parameters obtained in this step are the same as the multiple pipe network operation parameters obtained in step 302, and the process of obtaining the multiple pipe network operation parameters is the same as step 302, which will not be repeated here.

[0140] Step 402: For each pipe network operation parameter, the second electronic device obtains a characteristic value of the pipe network operation parameter within a target time period; based on the characteristic value of the pipe network operation parameter within the target time period, obtains a characteristic value of the pipe network operation parameter at a current time node.

[0141] The target period includes one or more periods. When the target period includes one period, the second electronic device obtains the characteristic value of the pipeline network operation parameter in the period, and obtains the characteristic value of the pipeline network operation parameter at the current time node based on the characteristic value of the pipeline network operation parameter in the period.

[0142] When the target period includes multiple periods, the target period includes the first target period and the second target period. If the target period includes the first target period and the second target period, the boundary value of the first target period is greater than the boundary value of the second target period. For example, the second target period is the time period from 7 days before the current time node to the current time node, and the first target period is the time period from 30 days before the current time node to the current time node.

[0143] The second electronic device obtains the characteristic value of the pipeline network operation parameter in the first target period and the characteristic value of the pipeline network operation parameter in the second target period, and obtains the characteristic value of the pipeline network operation parameter at the current time node based on the characteristic value of the pipeline network operation parameter in the first target period and the characteristic value of the pipeline network operation parameter in the second target period.

[0144] Among them, the process of the second electronic device obtaining the characteristic value of the pipeline network operation parameter in the first target time period is the same as step 303, the process of the second electronic device obtaining the characteristic value of the pipeline network operation parameter in the second target time period is the same as step 304, and the process of the second electronic device obtaining the characteristic value of the pipeline network operation parameter at the current time node based on the characteristic value of the pipeline network operation parameter in the first target time period and the characteristic value in the second target time period is the same as step 305, which will not be repeated here.

[0145] Step 403: The second electronic device obtains the correlation coefficient corresponding to the current time node.

[0146] If the target period includes a first target period and a second target period, the second electronic device obtains a correlation coefficient of the first pipe network operation parameter and the second pipe network operation parameter in the first target period and a correlation coefficient in the second target period. The correlation coefficient corresponding to the current time node includes the correlation coefficient of the first pipe network operation parameter and the second pipe network operation parameter in the first target period and a correlation coefficient in the second target period.

[0147] The process of the second electronic device acquiring the correlation coefficient of the first pipe network operation parameter and the second pipe network operation parameter in the first target period and the correlation coefficient in the second target period is the same as step 306 and will not be repeated here.

[0148] Step 404: The second electronic device inputs the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain the first fluid accumulation condition.

[0149] The first liquid accumulation condition is the liquid accumulation condition corresponding to the target pipe network at the current time node. The liquid accumulation condition determination model is obtained by training the method in steps 301 to 307.

[0150] The second electronic device inputs the characteristic value and correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain the first fluid accumulation condition. If the first fluid accumulation condition indicates that there is fluid accumulation in the target pipeline network at the current time node, the fluid accumulation condition determination model will also output the fluid accumulation type.

[0151] The embodiment of the present application provides a method for determining a liquid accumulation condition, which first obtains a characteristic value and a correlation coefficient corresponding to a current time node, and then inputs the characteristic value corresponding to the current time node into a liquid accumulation condition determination model to obtain a first liquid accumulation condition corresponding to the current time node. Since the liquid accumulation condition determination model is obtained based on real pipeline operation data and liquid accumulation condition training, the liquid accumulation condition of the target pipeline network can be accurately determined through the liquid accumulation condition determination model, thereby improving the accuracy of determining the liquid accumulation condition.

[0152] Figure 4 The figure shows a process for determining the liquid accumulation condition provided by the present application. The method for determining the liquid accumulation condition provided by the present application is further elaborated in detail below. Figure 5 is a flow chart of a method for determining a liquid accumulation condition provided in an embodiment of the present application, which is executed by a second electronic device, see Figure 5 , the method comprising:

[0153] Step 501: The second electronic device obtains a plurality of pipe network operation parameters of a target pipe network within a target period before a current time node.

[0154] This step is the same as step 401 and will not be described again here.

[0155] Step 502: For each pipe network operation parameter, the second electronic device obtains a characteristic value of the pipe network operation parameter within a target time period; based on the characteristic value of the pipe network operation parameter within the target time period, obtains a characteristic value of the pipe network operation parameter at a current time node.

[0156] This step is the same as step 402 and will not be described again here.

[0157] Step 503: The second electronic device obtains the correlation coefficient corresponding to the current time node.

[0158] This step is the same as step 403 and will not be described again here.

[0159] Step 504: The second electronic device inputs the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain a second fluid accumulation condition.

[0160] The second electronic device inputs the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation operating condition determination model, and outputs the second fluid accumulation operating condition through the fluid accumulation operating condition determination model.

[0161] For example, the first electronic device and the second electronic device are the same electronic device, see Figure 6 , the second electronic device can perform model training based on the sample data in the sample library to obtain a liquid accumulation condition determination model. Then, for the pipe network whose liquid accumulation condition is to be determined, the liquid accumulation condition of the pipe network is determined by the liquid accumulation condition determination model.

[0162] Step 505: The second electronic device corrects the second liquid accumulation operating condition based on at least one of the third liquid accumulation operating condition and the fourth liquid accumulation operating condition to obtain the first liquid accumulation operating condition.

[0163] The third liquid accumulation condition is the liquid accumulation condition corresponding to each time node in the first target period, and the fourth liquid accumulation condition is the liquid accumulation condition corresponding to each time node in the second target period, and one time node corresponds to one liquid accumulation condition. For example, the third liquid accumulation condition is the liquid accumulation condition corresponding to each day within 30 days before the current time node, and the fourth liquid accumulation condition is the liquid accumulation condition corresponding to each day within 7 days before the current time node.

[0164] In one possible implementation, the second electronic device determines at least one of the first quantity and the second quantity when the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node; and corrects the second fluid accumulation condition to obtain the first fluid accumulation condition when at least one of the first quantity and the second quantity is greater than a corresponding threshold.

[0165] In this implementation, the first number is the number of the third fluid accumulation condition indicating the presence of fluid accumulation, and the second number is the number of the fourth fluid accumulation condition indicating the presence of fluid accumulation.

[0166] When the second liquid accumulation condition indicates that there is no liquid accumulation at the current time node, the second electronic device determines the cumulative number of third liquid accumulation conditions in which liquid accumulation exists within the first target time period, i.e., the first number, and / or determines the cumulative number of fourth liquid accumulation conditions in which liquid accumulation exists within the second target time period, i.e., the second number.

[0167] For example, the second electronic device determines a first quantity and a second quantity, and when the first quantity is greater than a second preset threshold and the second quantity is greater than a third preset threshold, the second liquid accumulation condition is modified to a first liquid accumulation condition, where the first liquid accumulation condition indicates that liquid accumulation exists at the current time node.

[0168] For example, there is no fluid accumulation at the current time node, but the number of third fluid accumulation conditions with fluid accumulation within 30 days before the current time node is 9, and the number of fourth fluid accumulation conditions with fluid accumulation within 7 days before the current time node is 4, both of which are greater than the corresponding preset thresholds. The second electronic device can modify the second fluid accumulation condition corresponding to the current time node to the first fluid accumulation condition.

[0169] In another possible implementation, when the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node, the second electronic device determines a third number; when the third number is greater than the first preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition.

[0170] In this implementation, the third number is the number of the third liquid accumulation condition or the fourth liquid accumulation condition in which liquid accumulation exists continuously before the current time node. In the case where the second liquid accumulation condition indicates that there is no liquid accumulation at the current time node, the second electronic device can determine the number of the third liquid accumulation condition in which liquid accumulation exists continuously within the first target period to obtain the third number; or the second electronic device determines the number of the fourth liquid accumulation condition in which liquid accumulation exists continuously within the second target period to obtain the third number. The second electronic device determines whether the third number is greater than the first preset threshold value, and in the case where the third number is greater than the first preset threshold value, the second liquid accumulation condition is modified to the first liquid accumulation condition, and the first liquid accumulation condition indicates that liquid accumulation exists at the current time node.

[0171] For example, if there is no fluid accumulation at the current time node, and the number of third fluid accumulation conditions with continuous fluid accumulation before the current time node is 4, which is greater than the first preset threshold, the second fluid accumulation condition corresponding to the current time node can be modified to the first fluid accumulation condition.

[0172] In an embodiment of the present application, the second electronic device can correct the liquid accumulation condition corresponding to the current time node according to the liquid accumulation condition in the target time period before the current time node, so as to more accurately determine the liquid accumulation condition.

[0173] If the second electronic device is provided as a terminal, or the second electronic device is provided as a terminal and a server, the terminal may display the first fluid accumulation condition on a display interface.

[0174] The second electronic device may display only the first fluid accumulation condition on the display interface, or may display multiple fluid accumulation conditions before the current time node. Moreover, for the fluid accumulation condition with fluid accumulation, the second electronic device may also display the type of fluid accumulation.

[0175] In an embodiment of the present application, the second electronic device can also modify the effusion type at the current time node according to the effusion types at the time nodes before and after the current time node. The process is: the second electronic device obtains the effusion types corresponding to multiple time nodes; for the current time node, if the effusion type corresponding to the current time node is different from the effusion types corresponding to the previous time node and the next time node, and the effusion types corresponding to the previous time node and the next time node are the same, then the effusion type corresponding to the current time node is modified to the effusion type corresponding to the previous time node.

[0176] In this implementation, the second electronic device can determine the effusion type corresponding to multiple time nodes through the effusion working condition determination model, and the multiple time nodes include the current time node, the previous time node of the current time node, and the next time node of the current time node. If the effusion type corresponding to the current time node is different from the effusion type corresponding to the previous and next time nodes, and the effusion type corresponding to the previous and next time nodes is the same, then the effusion type corresponding to the current time node can be modified to the effusion type corresponding to the previous time node or the next time node.

[0177] For example, if the effusion type corresponding to the current time node is temporary effusion, and the effusion types corresponding to the two previous and next time nodes are both regular effusion, the effusion type corresponding to the current time node can be modified to regular effusion.

[0178] The embodiment of the present application provides a method for determining a liquid accumulation condition, which first obtains a characteristic value and a correlation coefficient corresponding to a current time node, and then inputs the characteristic value corresponding to the current time node into a liquid accumulation condition determination model to obtain a first liquid accumulation condition corresponding to the current time node. Since the liquid accumulation condition determination model is obtained based on real pipeline operation data and liquid accumulation condition training, the liquid accumulation condition of the target pipeline network can be accurately determined through the liquid accumulation condition determination model, thereby improving the accuracy of determining the liquid accumulation condition.

[0179] Figure 7 is a structural schematic diagram of a training device for determining a model for a fluid accumulation condition provided in an embodiment of the present application, see Figure 7 , the device comprises:

[0180] The first acquisition module 701 is used to acquire a plurality of sample operating condition labels, wherein the sample operating condition label is used to indicate whether there is liquid accumulation in the sample pipe network at the sample time node;

[0181] The second acquisition module 702 is used to acquire, for each sample time node, a plurality of pipe network operation parameters of the sample pipe network within a sample period; wherein the sample period is located before the sample time node in terms of time sequence;

[0182] The third acquisition module 703 is used to acquire, for each pipe network operation parameter, a characteristic value of the pipe network operation parameter in a sample period; based on the characteristic value of the pipe network operation parameter in the sample period, acquire the characteristic value of the pipe network operation parameter at the sample time node;

[0183] The fourth acquisition module 704 is used to obtain the correlation coefficient corresponding to the sample time node; wherein the correlation coefficient is used to represent the correlation degree between any two pipe network operation parameters within the sample period;

[0184] The training module 705 is used to perform model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a liquid accumulation condition determination model; wherein the liquid accumulation condition determination model is used to determine the liquid accumulation condition of the target pipe network.

[0185] In a possible implementation, the sample period includes a first sample period and a second sample period, and a boundary value of the first sample period is greater than a boundary value of the second sample period;

[0186] The third acquisition module 703 is used to obtain the mean of the pipeline network operation parameters in the first sample period to obtain the first mean feature; obtain the changing trend of the pipeline network operation parameters in the first sample period to obtain the first trend feature; obtain the difference between the pipeline network operation parameters corresponding to the sample time node and the mean to obtain the first deviation feature; based on the first mean feature, the first trend feature and the first deviation feature, obtain the first characteristic value of the pipeline network operation parameters in the first sample period; obtain the second characteristic value of the pipeline network operation parameters in the second sample period.

[0187] In another possible implementation, the fourth acquisition module 704 is used to obtain the covariance between the first pipeline network operation parameter and the second pipeline network operation parameter within the sample period; wherein the first pipeline network operation parameter and the second pipeline network operation parameter are any two parameters among the multiple pipeline network operation parameters; obtain the first standard deviation and the second standard deviation; wherein the first standard deviation is the standard deviation of the first pipeline network operation parameter within the sample period, and the second standard deviation is the standard deviation of the second pipeline network operation parameter within the sample period; obtain the product of the first standard deviation and the second standard deviation to obtain a first product value; obtain the ratio of the covariance to the first product value to obtain the correlation coefficient between the first pipeline network operation parameter and the second pipeline network operation parameter within the sample period.

[0188] In another possible implementation, the training module 705 is used to determine the type of fluid accumulation corresponding to the sample time node when the sample operating condition label indicates that there is fluid accumulation in the sample pipe network at the sample time node; based on the sample operating condition label, fluid accumulation type, characteristic value and correlation coefficient corresponding to each sample time node, model training is performed to obtain a fluid accumulation condition determination model.

[0189] In another possible implementation, the second acquisition module 702 is used to obtain the gas and water delivery of the sample pipeline network within the sample period; determine the ratio of the water delivery to the gas delivery to obtain the water-gas ratio; determine the first pressure value and the second pressure value of the sample pipeline network, the first pressure value is the pressure value of the sample pipeline network at the starting end, and the second pressure value is the pressure value of the sample pipeline network at the ending end; determine the difference between the first pressure value and the second pressure value to obtain the delivery pressure difference; wherein the multiple pipeline network operation parameters include gas delivery, water delivery, water-gas ratio and delivery pressure difference.

[0190] The embodiment of the present application provides a training device for a model for determining a liquid accumulation condition. The device first obtains the characteristic values ​​of the pipe network operation parameters in a sample period and the sample condition labels corresponding to the sample time nodes, obtains the characteristic values ​​of the pipe network operation parameters at the sample time nodes based on the characteristic values ​​of the pipe network operation parameters in the sample period, and obtains the correlation coefficients corresponding to the sample time nodes, performs model training based on the sample condition labels, characteristic values ​​and correlation coefficients corresponding to the sample time nodes, and obtains a model for determining a liquid accumulation condition. It can be seen that the device performs model training based on real pipe network operation data and liquid accumulation conditions, so the trained model can accurately determine the liquid accumulation conditions of the target pipe network, thereby improving the accuracy of determining the liquid accumulation conditions.

[0191] Figure 8 is a schematic diagram of a structure of a device for determining a liquid accumulation condition provided in an embodiment of the present application, see Figure 8 , the device comprises:

[0192] A fifth acquisition module 801 is used to acquire a plurality of pipe network operation parameters of a target pipe network in a target period before a current time node;

[0193] A sixth acquisition module 802 is used to acquire, for each pipe network operation parameter, a characteristic value of the pipe network operation parameter in the target time period; and based on the characteristic value of the pipe network operation parameter in the target time period, acquire the characteristic value of the pipe network operation parameter at the current time node;

[0194] The seventh acquisition module 803 is used to acquire the correlation coefficient corresponding to the current time node;

[0195] The first determination module 804 is used to input the characteristic value and correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain the first fluid accumulation condition; wherein, the first fluid accumulation condition is the fluid accumulation condition corresponding to the target pipeline network at the current time node, and the fluid accumulation condition determination model is trained based on the sample condition label, characteristic value and correlation coefficient corresponding to the sample time node, and the sample condition label is used to indicate whether there is fluid accumulation in the sample pipeline network at the sample time node.

[0196] In one possible implementation, the first determination module 804 is used to input the characteristic value and correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain the second fluid accumulation condition; based on at least one of the third fluid accumulation condition and the fourth fluid accumulation condition, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the target time period includes a first target time period and a second target time period, the third fluid accumulation condition is the fluid accumulation condition corresponding to each time node within the first target time period, and the fourth fluid accumulation condition is the fluid accumulation condition corresponding to each time node within the second target time period.

[0197] In another possible implementation, the first determination module 804 is used to determine at least one of the first quantity and the second quantity when the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node; wherein the first quantity is the quantity of the third fluid accumulation condition indicating that there is fluid accumulation, and the second quantity is the quantity of the fourth fluid accumulation condition indicating that there is fluid accumulation; when at least one of the first quantity and the second quantity is greater than a corresponding preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the first fluid accumulation condition indicates that there is fluid accumulation at the current time node.

[0198] In another possible implementation, the first determination module 804 is used to determine a third quantity when the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node; wherein the third quantity is the quantity of the third fluid accumulation condition or the fourth fluid accumulation condition in which fluid accumulation exists continuously before the current time node; when the third quantity is greater than a third preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the first fluid accumulation condition indicates that there is fluid accumulation at the current time node.

[0199] In another possible implementation, the device further includes:

[0200] An eighth acquisition module, used to acquire effusion types corresponding to multiple time nodes;

[0201] A modification module is used to modify the effusion type corresponding to the current time node to the effusion type corresponding to the previous time node if the effusion type corresponding to the current time node is different from the effusion types corresponding to the previous time node and the next time node, and the effusion types corresponding to the previous time node and the next time node are the same.

[0202] The embodiment of the present application provides a device for determining a liquid accumulation condition, which first obtains a characteristic value and a correlation coefficient corresponding to a current time node, and then inputs the characteristic value corresponding to the current time node into a liquid accumulation condition determination model to obtain a first liquid accumulation condition corresponding to the current time node. Since the liquid accumulation condition determination model is obtained based on real pipeline operation data and liquid accumulation condition training, the liquid accumulation condition of the target pipeline network can be accurately determined through the liquid accumulation condition determination model, thereby improving the accuracy of determining the liquid accumulation condition.

[0203] If the electronic device is provided as a terminal, refer to Fig. 9 , Fig. 9 The structure block diagram of a terminal 900 provided by an exemplary embodiment of the present application is shown. The terminal 900 may be a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The terminal 900 may also be called a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0204] Typically, the terminal 900 includes a processor 901 and a memory 902 .

[0205] The processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 901 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 901 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0206] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is used to store at least one program code, which is used to be executed by the processor 901 to implement the training method of the effusion condition determination model or the effusion condition determination method provided in the method embodiment of the present application.

[0207] In some embodiments, the terminal 900 may further optionally include: a peripheral device interface 903 and at least one peripheral device. The processor 901, the memory 902 and the peripheral device interface 903 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 903 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 904, a display screen 905, a camera assembly 906, an audio circuit 907 and a power supply 908.

[0208] The peripheral device interface 903 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, the memory 902, and the peripheral device interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902, and the peripheral device interface 903 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0209] The radio frequency circuit 904 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 904 communicates with communication networks and other communication devices through electromagnetic signals. The radio frequency circuit 904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 904 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 904 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 904 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0210] The display screen 905 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 905 is a touch display screen, the display screen 905 also has the ability to collect touch signals on the surface or above the surface of the display screen 905. The touch signal can be input to the processor 901 as a control signal for processing. At this time, the display screen 905 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 905 can be one, set on the front panel of the terminal 900; in other embodiments, the display screen 905 can be at least two, respectively set on different surfaces of the terminal 900 or in a folding design; in other embodiments, the display screen 905 can be a flexible display screen, set on the curved surface or folding surface of the terminal 900. Even, the display screen 905 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 905 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0211] The camera assembly 906 is used to capture images or videos. Optionally, the camera assembly 906 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 906 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0212] The audio circuit 907 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 901 for processing, or input them into the radio frequency circuit 904 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 900. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 907 may also include a headphone jack.

[0213] The power supply 908 is used to power various components in the terminal 900. The power supply 908 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 908 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0214] In some embodiments, the terminal 900 further includes one or more sensors 909 . The one or more sensors 909 include, but are not limited to: an acceleration sensor 910 , a gyroscope sensor 911 , a pressure sensor 912 , an optical sensor 913 , and a proximity sensor 914 .

[0215] The acceleration sensor 910 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 900. For example, the acceleration sensor 910 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 901 can control the display screen 905 to display the user interface in a horizontal view or a vertical view based on the gravity acceleration signal collected by the acceleration sensor 910. The acceleration sensor 910 can also be used for collecting game or user motion data.

[0216] The gyro sensor 911 can detect the body direction and rotation angle of the terminal 900, and the gyro sensor 911 can cooperate with the acceleration sensor 910 to collect the user's 3D actions on the terminal 900. Based on the data collected by the gyro sensor 911, the processor 901 can implement the following functions: motion sensing (such as changing the UI based on the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0217] The pressure sensor 912 can be set in the side frame of the terminal 900 and / or the lower layer of the display screen 905. When the pressure sensor 912 is set in the side frame of the terminal 900, the user's holding signal of the terminal 900 can be detected, and the processor 901 performs left and right hand recognition or shortcut operation based on the holding signal collected by the pressure sensor 912. When the pressure sensor 912 is set in the lower layer of the display screen 905, the processor 901 controls the operability controls on the UI interface based on the user's pressure operation on the display screen 905. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0218] The optical sensor 913 is used to collect the ambient light intensity. In one embodiment, the processor 901 can control the display brightness of the display screen 905 based on the ambient light intensity collected by the optical sensor 913. Specifically, when the ambient light intensity is high, the display brightness of the display screen 905 is increased; when the ambient light intensity is low, the display brightness of the display screen 905 is reduced. In another embodiment, the processor 901 can also dynamically adjust the shooting parameters of the camera component 906 based on the ambient light intensity collected by the optical sensor 913.

[0219] The proximity sensor 914, also called a distance sensor, is usually arranged on the front panel of the terminal 900. The proximity sensor 914 is used to collect the distance between the user and the front of the terminal 900. In one embodiment, when the proximity sensor 914 detects that the distance between the user and the front of the terminal 900 is gradually decreasing, the processor 901 controls the display screen 905 to switch from the screen-on state to the screen-off state; when the proximity sensor 914 detects that the distance between the user and the front of the terminal 900 is gradually increasing, the processor 901 controls the display screen 905 to switch from the screen-off state to the screen-on state.

[0220] Those skilled in the art will understand that Fig. 9 The structure shown in the figure does not constitute a limitation on the terminal 900, and the terminal 900 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0221] If the electronic device is provided as a server, the structural block diagram of the server can be found in Fig.10, the server 1000 may have relatively large differences due to different configurations or performances, and may include a processor (central processing unit, CPU) 1001 and a memory 1002, wherein the memory 1002 stores at least one program code, and the at least one program code is loaded and executed by the processor 1001 to implement the training method of the above-mentioned effusion condition determination model or the effusion condition determination method. Of course, the server 1000 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The server 1000 may also include other components for realizing device functions, which will not be repeated here.

[0222] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the training method of the effusion condition determination model or the effusion condition determination method in the above-mentioned embodiment.

[0223] In an exemplary embodiment, a computer program product is also provided, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the training method of the effusion condition determination model or the effusion condition determination method in the above-mentioned embodiment.

[0224] The above description is only for the purpose of facilitating those skilled in the art to understand the technical solution of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A training method for determining a model for a fluid accumulation condition, characterized in that: The method comprises: Acquire multiple sample operating condition labels; wherein the sample operating condition labels are used to indicate whether there is liquid accumulation in the sample pipe network at the sample time node; For each sample time node, a plurality of pipe network operation parameters of the sample pipe network within a sample period are obtained; wherein the sample period is located before the sample time node in terms of time sequence; For each pipe network operation parameter, obtain a characteristic value of the pipe network operation parameter in the sample period; based on the characteristic value of the pipe network operation parameter in the sample period, obtain a characteristic value of the pipe network operation parameter at the sample time node; Obtaining the correlation coefficient corresponding to the sample time node; wherein the correlation coefficient is used to indicate the degree of correlation between any two pipe network operation parameters within the sample period; Based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node, model training is performed to obtain a liquid accumulation condition determination model; wherein the liquid accumulation condition determination model is used to determine the liquid accumulation condition of the target pipeline network.

2. The method according to claim 1, characterized in that: The sample period includes a first sample period and a second sample period, and a boundary value of the first sample period is greater than a boundary value of the second sample period; The obtaining of the characteristic value of the pipe network operation parameter within the sample period includes: Obtaining a mean value of the pipe network operation parameter in the first sample period to obtain a first mean value feature; Obtaining a change trend of the pipe network operation parameter within the first sample period to obtain a first trend feature; Obtaining the difference between the pipe network operation parameter corresponding to the sample time node and the mean value to obtain a first deviation feature; Based on the first mean feature, the first trend feature and the first deviation feature, obtaining a first feature value of the pipeline network operation parameter within the first sample period; A second characteristic value of the pipeline network operation parameter in the second sample time period is obtained.

3. The method according to claim 1, characterized in that The obtaining the correlation coefficient corresponding to the sample time node includes: Obtaining the covariance between the first pipe network operation parameter and the second pipe network operation parameter within the sample period; wherein the first pipe network operation parameter and the second pipe network operation parameter are any two parameters among the multiple pipe network operation parameters; Obtaining a first standard deviation and a second standard deviation; wherein the first standard deviation is the standard deviation of the first pipe network operation parameter within the sample period, and the second standard deviation is the standard deviation of the second pipe network operation parameter within the sample period; Obtaining the product of the first standard deviation and the second standard deviation to obtain a first product value; The ratio of the covariance to the first product value is obtained to obtain a correlation coefficient between the first pipe network operation parameter and the second pipe network operation parameter within the sample period.

4. The method according to claim 1, characterized in that: The method of performing model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a fluid accumulation operating condition determination model includes: When the sample operating condition label indicates that there is fluid accumulation in the sample pipe network at the sample time node, determining the type of fluid accumulation corresponding to the sample time node; Based on the sample operating condition label, effusion type, characteristic value and correlation coefficient corresponding to each sample time node, model training is performed to obtain the effusion operating condition determination model.

5. The method according to claim 1, characterized in that The obtaining of a plurality of pipe network operation parameters of the sample pipe network within a sample period includes: Obtaining the gas and water delivery of the sample pipe network during the sample period; Determine the ratio of the water delivery amount to the gas delivery amount to obtain a water-gas ratio; Determine a first pressure value and a second pressure value of the sample pipe network, wherein the first pressure value is a pressure value of the sample pipe network at a starting end, and the second pressure value is a pressure value of the sample pipe network at a terminating end; Determine the difference between the first pressure value and the second pressure value to obtain a pressure difference; Among them, the multiple pipeline network operation parameters include the gas transmission volume, the water transmission volume, the water-gas ratio and the transmission pressure difference.

6. A method for determining a liquid accumulation condition, characterized in that: The method comprises: Obtain multiple pipeline network operation parameters of the target pipeline network within the target period before the current time node; For each pipeline network operation parameter, obtain a characteristic value of the pipeline network operation parameter in the target time period; based on the characteristic value of the pipeline network operation parameter in the target time period, obtain a characteristic value of the pipeline network operation parameter at the current time node; Obtaining the correlation coefficient corresponding to the current time node; Inputting the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain a first fluid accumulation condition; Among them, the first fluid accumulation condition is the fluid accumulation condition corresponding to the target pipeline network at the current time node, and the fluid accumulation condition determination model is obtained by training based on the sample condition label, eigenvalue and correlation coefficient corresponding to the sample time node, and the sample condition label is used to indicate whether there is fluid accumulation in the sample pipeline network at the sample time node.

7. The method according to claim 6, characterized in that The step of inputting the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation condition determination model to obtain the first fluid accumulation condition includes: Inputting the characteristic value and the correlation coefficient corresponding to the current time node into the fluid accumulation working condition determination model to obtain a second fluid accumulation working condition; Based on at least one of the third fluid accumulation operating condition and the fourth fluid accumulation operating condition, the second fluid accumulation operating condition is corrected to obtain the first fluid accumulation operating condition; wherein, the target time period includes a first target time period and a second target time period, the third fluid accumulation operating condition is the fluid accumulation operating condition corresponding to each time node within the first target time period, and the fourth fluid accumulation operating condition is the fluid accumulation operating condition corresponding to each time node within the second target time period.

8. The method according to claim 7, characterized in that The step of correcting the second fluid accumulation operating condition based on at least one of the third fluid accumulation operating condition and the fourth fluid accumulation operating condition to obtain the first fluid accumulation operating condition includes: In the case where the second fluid accumulation condition indicates that there is no fluid accumulation at the current time node, determining at least one of a first quantity and a second quantity; wherein the first quantity is the quantity of a third fluid accumulation condition indicating that there is fluid accumulation, and the second quantity is the quantity of a fourth fluid accumulation condition indicating that there is fluid accumulation; When at least one of the first number and the second number is greater than a corresponding preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein, the first fluid accumulation condition indicates that fluid accumulation exists at the current time node.

9. The method according to claim 7, characterized in that: The step of correcting the second fluid accumulation operating condition based on at least one of the third fluid accumulation operating condition and the fourth fluid accumulation operating condition to obtain the first fluid accumulation operating condition includes: When the second liquid accumulation condition indicates that there is no liquid accumulation at the current time node, determining a third number; wherein the third number is the number of the third liquid accumulation condition or the fourth liquid accumulation condition in which there is liquid accumulation continuously before the current time node; When the third number is greater than the first preset threshold, the second fluid accumulation condition is corrected to obtain the first fluid accumulation condition; wherein the first fluid accumulation condition indicates that fluid accumulation exists at the current time node.

10. The method according to claim 6, characterized in that The method further comprises: Get the effusion types corresponding to multiple time nodes; For the current time node, if the effusion type corresponding to the current time node is different from the effusion type corresponding to the previous time node and the next time node, and the effusion type corresponding to the previous time node and the next time node are the same, then the effusion type corresponding to the current time node is modified to the effusion type corresponding to the previous time node.

11. A training device for determining a model for a fluid accumulation condition, characterized in that: The device comprises: A first acquisition module is used to acquire a plurality of sample operating condition labels; wherein the sample operating condition labels are used to indicate whether there is fluid accumulation in the sample pipe network at the sample time node; A second acquisition module is used to acquire, for each sample time node, a plurality of pipe network operation parameters of the sample pipe network within a sample period; wherein the sample period is located before the sample time node in terms of time sequence; A third acquisition module is used to acquire, for each pipe network operation parameter, a characteristic value of the pipe network operation parameter in the sample period; based on the characteristic value of the pipe network operation parameter in the sample period, acquire the characteristic value of the pipe network operation parameter at the sample time node; A fourth acquisition module is used to acquire the correlation coefficient corresponding to the sample time node; wherein the correlation coefficient is used to represent the degree of correlation between any two pipe network operation parameters within the sample period; The training module is used to perform model training based on the sample operating condition label, characteristic value and correlation coefficient corresponding to each sample time node to obtain a liquid accumulation condition determination model; wherein the liquid accumulation condition determination model is used to determine the liquid accumulation condition of the target pipeline network.

12. A device for determining a liquid accumulation condition, characterized in that: The device comprises: A fifth acquisition module, used to acquire multiple pipe network operation parameters of the target pipe network within a target period before the current time node; A sixth acquisition module is used to acquire, for each pipe network operation parameter, a characteristic value of the pipe network operation parameter in the target time period; based on the characteristic value of the pipe network operation parameter in the target time period, acquire the characteristic value of the pipe network operation parameter at the current time node; A seventh acquisition module, used to acquire the correlation coefficient corresponding to the current time node; A first determination module, configured to input the characteristic value and the correlation coefficient corresponding to the current time node into a fluid accumulation condition determination model to obtain a first fluid accumulation condition; Among them, the first fluid accumulation condition is the fluid accumulation condition corresponding to the target pipeline network at the current time node, and the fluid accumulation condition determination model is obtained by training based on the sample condition label, eigenvalue and correlation coefficient corresponding to the sample time node, and the sample condition label is used to indicate whether there is fluid accumulation in the sample pipeline network at the sample time node.

13. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the method according to any one of claims 1 to 5 or 6 to 10.

14. A computer-readable storage medium, characterized in that: At least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by the processor to implement the method according to any one of claims 1 to 5 or 6 to 10.

Images