Artificial Intelligence-Based Groundwater Level Monitoring Method and System

Abstract

The embodiments of this application provide an artificial intelligence-based groundwater level monitoring method and system. By constructing a first groundwater level prediction network including focusing nodes and transfer nodes, and generating multiple second groundwater level prediction networks based on different node association relationships, the diversity and accuracy of groundwater level prediction are significantly improved. Using the basic sample groundwater dynamic monitoring data to perform linkage parameter learning on multiple second groundwater level prediction networks effectively optimizes the network parameters and further improves the prediction accuracy. At the same time, by expanding the water level prediction learning samples of the basic sample data, more abundant and comprehensive target sample groundwater dynamic monitoring data are generated, providing data support for the training of the target groundwater level prediction network. The finally generated target groundwater level prediction network performs excellently in practical applications and can provide accurate and reliable decision-making basis for groundwater management and water resource protection.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology. Specifically, it relates to a groundwater level monitoring method and system based on artificial intelligence. Background Art

[0002] As an important water resource, the accurate monitoring of the groundwater level is of great significance for water resource management, environmental protection, and disaster warning. However, traditional groundwater level monitoring methods, such as manual observation wells and automatic recorders, although they can provide certain monitoring data, have problems such as uneven distribution of monitoring points, untimely data update, and high monitoring costs, and it is difficult to meet the groundwater level monitoring needs on a large scale and long time scale. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a groundwater level monitoring method and system based on artificial intelligence.

[0004] Combined with the first aspect of this application, a groundwater level monitoring method based on artificial intelligence is provided, which is applied to a groundwater level monitoring system based on artificial intelligence. The method includes:

[0005] Obtain a first groundwater level prediction network, where the first groundwater level prediction network includes multiple deep learning nodes, and the deep learning nodes include focusing nodes and transfer nodes;

[0006] Generate multiple second groundwater level prediction networks based on different node association relationships between the focusing nodes and the transfer nodes in each of the deep learning nodes;

[0007] Perform linkage parameter learning on the multiple second groundwater level prediction networks based on basic example groundwater dynamic monitoring data to generate multiple second groundwater level prediction networks that have completed parameter learning;

[0008] Expand the water level prediction learning examples of the basic example groundwater dynamic monitoring data according to the multiple second groundwater level prediction networks that have completed parameter learning to generate target example groundwater dynamic monitoring data;

[0009] Perform water level prediction learning on the first groundwater level prediction network according to the target example groundwater dynamic monitoring data to generate a target groundwater level prediction network.

[0010] In a possible implementation manner of the first aspect, the generating multiple second groundwater level prediction networks based on different node association relationships between the focusing nodes and the transfer nodes in each of the deep learning nodes includes:

[0011] Obtain the scale of the deep learning nodes in the first groundwater level prediction network;

[0012] Determine multiple network model architectures according to the scale of the deep learning nodes, and each of the network model architectures corresponds to a node association relationship between a focus node and a transfer node;

[0013] Generate multiple second groundwater level prediction networks based on the multiple network model architectures.

[0014] In a possible implementation manner of the first aspect, the step of performing linkage parameter learning on the multiple second groundwater level prediction networks based on the basic example groundwater dynamic monitoring data to generate multiple second groundwater level prediction networks that have completed parameter learning includes:

[0015] Obtain basic example groundwater dynamic monitoring data, where the basic example groundwater dynamic monitoring data includes multiple example groundwater dynamic monitoring data and the labeled estimated water level data corresponding to each example groundwater dynamic monitoring data;

[0016] Load any one of the multiple example groundwater dynamic monitoring data, i.e., the target example groundwater dynamic monitoring data, into the multiple second groundwater level prediction networks respectively to generate multiple predicted water level results corresponding to the target example groundwater dynamic monitoring data;

[0017] Optimize the multiple second groundwater level prediction networks based on the error between the multiple predicted water level results and the labeled estimated water level data corresponding to the target example groundwater dynamic monitoring data. The multiple second groundwater level prediction networks share neuron weight information;

[0018] When the multiple second groundwater level prediction networks do not meet the training termination condition, return to execute the step of loading any one of the target example groundwater dynamic monitoring data into the multiple second groundwater level prediction networks respectively, and optimizing the neuron weight information of the multiple second groundwater level prediction networks based on the error between the output multiple predicted water level results and the corresponding labeled estimated water level data;

[0019] When the multiple second groundwater level prediction networks meet the training termination condition, generate multiple second groundwater level prediction networks that have completed parameter learning.

[0020] In a possible implementation manner of the first aspect, the step of optimizing the multiple second groundwater level prediction networks based on the error between the multiple predicted water level results and the labeled estimated water level data corresponding to the target example groundwater dynamic monitoring data, where the multiple second groundwater level prediction networks share neuron weight information, includes:

[0021] Calculate the loss function values between each predicted water level result among the multiple predicted water level results and the labeled estimated water level data corresponding to the target example groundwater dynamic monitoring data, and generate multiple training cost results;

[0022] Calculate the training direction parameters corresponding to each training cost result, and generate multiple training direction parameters;

[0023] Optimize the multiple second groundwater level prediction networks based on the multiple training direction parameters, and the multiple second groundwater level prediction networks share neuron weight information.

[0024] In a possible implementation manner of the first aspect, the expanding the water level prediction learning examples of the basic example groundwater dynamic monitoring data by using the multiple second groundwater level prediction networks that have completed parameter learning to generate the target example groundwater dynamic monitoring data includes:

[0025] Expand the basic example groundwater dynamic monitoring data based on the multiple second groundwater level prediction networks that have completed parameter learning to generate an extended example groundwater dynamic monitoring data sequence;

[0026] Determine multiple target extended example groundwater dynamic monitoring data from the extended example groundwater dynamic monitoring data sequence, and load the multiple target extended example groundwater dynamic monitoring data into the basic example groundwater dynamic monitoring data to generate the target example groundwater dynamic monitoring data.

[0027] In a possible implementation manner of the first aspect, the expanding the basic example groundwater dynamic monitoring data based on the multiple second groundwater level prediction networks that have completed parameter learning to generate an extended example groundwater dynamic monitoring data sequence includes:

[0028] Process each example groundwater dynamic monitoring data in the basic example groundwater dynamic monitoring data based on each second groundwater level prediction network that has completed parameter learning to generate a confidence sequence predicted by each second groundwater level prediction network that has completed parameter learning;

[0029] Determine the extended example groundwater dynamic monitoring data sequence based on the confidence sequences output by each second groundwater level prediction network that has completed parameter learning.

[0030] In a possible implementation manner of the first aspect, the determining the extended example groundwater dynamic monitoring data sequence based on the confidence sequences output by each second groundwater level prediction network that has completed parameter learning includes:

[0031] Determine the maximum confidence in each confidence sequence, and generate the maximum confidence predicted by the second groundwater level prediction network that has completed parameter learning for each;

[0032] Determine the extended example groundwater dynamic monitoring data corresponding to each maximum confidence, and generate multiple extended example groundwater dynamic monitoring data;

[0033] Determine a sequence of extended example groundwater dynamic monitoring data based on the multiple extended example groundwater dynamic monitoring data.

[0034] In a possible implementation manner of the first aspect, the method includes:

[0035] Based on the target groundwater level prediction network, predict any input target groundwater dynamic monitoring data, and generate a water level prediction result of the target groundwater dynamic monitoring data.

[0036] Combined with the second aspect of the present application, there is provided an artificial intelligence-based groundwater level monitoring system, which includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the artificial intelligence-based groundwater level monitoring system implements the foregoing artificial intelligence-based groundwater level monitoring method.

[0037] Combined with the third aspect of the present application, there is provided a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, the foregoing artificial intelligence-based groundwater level monitoring method is implemented.

[0038] Combined with any of the foregoing aspects, in the embodiments of the present application, by constructing a first groundwater level prediction network including focusing nodes and transfer nodes, and generating multiple second groundwater level prediction networks based on different node association relationships, the diversity and accuracy of groundwater level prediction are significantly improved. Using the basic example groundwater dynamic monitoring data to perform linkage parameter learning on multiple second groundwater level prediction networks effectively optimizes the network parameters and further improves the prediction accuracy. At the same time, by expanding the water level prediction learning examples of the basic example data, more abundant and comprehensive target example groundwater dynamic monitoring data is generated, providing data support for the training of the target groundwater level prediction network. The finally generated target groundwater level prediction network performs excellently in practical applications and can provide accurate and reliable decision-making basis for groundwater management and water resource protection. Description of the Drawings

[0039] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained in combination with these drawings.

[0040] Figure 1 Schematic flowchart of the artificial intelligence-based groundwater level monitoring method provided by the embodiments of the present application. Detailed implementation manners

[0041] To enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0042] The terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or terminal that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or terminals.

[0043] Referring to "embodiments" herein means that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0044] Figure 1 The schematic flowchart of the artificial intelligence-based groundwater level monitoring method provided by the embodiments of the present application is shown. It should be understood that in other embodiments, the order of some steps of the artificial intelligence-based groundwater level monitoring method in this embodiment can be shared based on actual needs, or some of the steps can also be omitted or maintained. The details of the artificial intelligence-based groundwater level monitoring method include:

[0045] Step S110: Obtain a first groundwater level prediction network, where the first groundwater level prediction network includes multiple deep learning nodes, and the deep learning nodes include focusing nodes and transmission nodes.

[0046] In this embodiment, when the server performs the groundwater level prediction task, it first needs to obtain the first groundwater level prediction network. This first groundwater level prediction network is the basic architecture for the entire prediction work. For example, the server obtains this first groundwater level prediction network from a pre-constructed model library. The deep learning nodes in this first groundwater level prediction network are the basic units for constructing the network, and the focusing nodes and transmission nodes have their respective functions. The focusing nodes may be responsible for concentrating on specific data features, such as focusing on and processing the seasonal change features in the groundwater level data. The transmission nodes are responsible for transmitting the data processed by the focusing nodes or the original data to other parts of the network to ensure the flow of data and information transfer throughout the network. Just like in a complex logistics network, the focusing nodes are like stations that specially process special goods (specific data features), and the transmission nodes are like transportation lines connecting various stations (nodes) to ensure that the goods (data) can reach different parts of the network. The first groundwater level prediction network obtained by the server may have been preliminarily constructed and designed before, and its structure and node settings are set to adapt to the specific task of groundwater level prediction.

[0047] Step S120: Generate multiple second groundwater level prediction networks based on different node association relationships between the focusing nodes and the transmission nodes in each of the deep learning nodes.

[0048] After obtaining the first groundwater level prediction network, start constructing multiple second groundwater level prediction networks based on the different node association relationships between the focusing nodes and the transmission nodes in the deep learning nodes. First, the server obtains the scale of the deep learning nodes in the first groundwater level prediction network. Assume that the scale of the deep learning nodes in this first network is 100, with 30 focusing nodes and 70 transmission nodes. The server determines multiple network model architectures based on this scale. For example, if the association relationship between the focusing node and the transmission node is a one-to-one connection, a certain network model architecture is determined; if it is an association relationship where one focusing node is connected to multiple transmission nodes, another network model architecture is determined.

[0049] Based on these determined different network model architectures, the server generates multiple second groundwater level prediction networks. For example, when three different node association relationships are determined, the server will generate three different second groundwater level prediction networks. Taking one of the networks as an example, in this network, the association relationship between the focus node and the transfer node is set such that the focus node first processes the long-term trend data in the groundwater level data, and then the transfer node passes the processed data to the next set of nodes for further analysis, such as analyzing the impact of seasonal fluctuations on the water level. This way of generating multiple networks according to different node association relationships can predict the groundwater level from multiple perspectives and structures, increasing the potential for prediction diversity and accuracy.

[0050] Step S130, perform linkage parameter learning on the multiple second groundwater level prediction networks based on the basic sample groundwater dynamic monitoring data, and generate multiple second groundwater level prediction networks that have completed parameter learning.

[0051] The server obtains the basic sample groundwater dynamic monitoring data, which has been pre-collected and sorted for training the second groundwater level prediction network. Assume that the basic sample groundwater dynamic monitoring data contains 1000 sets of groundwater dynamic monitoring data from different regions and different time periods, and for each set of data, there is corresponding labeled estimated water level data.

[0052] The server loads any one of the 1000 sets of sample groundwater dynamic monitoring data, i.e., the target sample groundwater dynamic monitoring data, into the multiple second groundwater level prediction networks respectively. For example, select one set of data from a specific region and a certain time period and load it into each of the second groundwater level prediction networks. Each network processes the data according to its own structure and algorithm, thereby generating multiple predicted water level results corresponding to the target sample groundwater dynamic monitoring data.

[0053] Then, the server optimizes the multiple second groundwater level prediction networks based on the error between these predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data. Since these second groundwater level prediction networks share neuron weight information, the optimization is linkage. Specifically, the server calculates the loss function values between each of the predicted water level results in the multiple predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data respectively, generating multiple training cost results. For example, calculate the gap between each predicted result and the true labeled value through a loss function such as the mean squared error (MSE).

[0054] Next, calculate the training direction parameters corresponding to each training cost result to generate multiple training direction parameters. These training direction parameters indicate the direction and amplitude in which the network parameters should be adjusted. Optimize multiple second groundwater level prediction networks based on these training direction parameters. If, during this process, the multiple second groundwater level prediction networks do not meet the training termination conditions, for example, the preset number of training rounds has not been completed or the prediction error has not reached the predetermined threshold, then the server will return to execute the step of loading any target example groundwater dynamic monitoring data into the multiple second groundwater level prediction networks respectively and optimizing the neuron weight information of the multiple second groundwater level prediction networks based on the error between the multiple predicted water level results and the corresponding labeled estimated water level data.

[0055] When the multiple second groundwater level prediction networks meet the training termination conditions, for example, after 1000 rounds of training, the prediction error has been reduced to an acceptable range, the server generates multiple second groundwater level prediction networks that have completed parameter learning. These networks have adjusted their own parameters by learning the basic example groundwater dynamic monitoring data and have the ability to more accurately predict the groundwater level.

[0056] Step S140, based on the multiple second groundwater level prediction networks that have completed parameter learning, perform water level prediction learning example expansion on the basic example groundwater dynamic monitoring data to generate target example groundwater dynamic monitoring data.

[0057] The server expands the basic example groundwater dynamic monitoring data based on the multiple second groundwater level prediction networks that have completed parameter learning. First, the server processes each example groundwater dynamic monitoring data in the basic example groundwater dynamic monitoring data based on each second groundwater level prediction network that has completed parameter learning to generate a confidence sequence predicted by each second groundwater level prediction network that has completed parameter learning. For example, for a certain set of groundwater dynamic monitoring data in the basic example, each second groundwater level prediction network that has completed parameter learning will give a prediction result and the confidence of this result. Assuming there are 1000 sets of basic example data, each network will generate 1000 confidence values, and these values form the confidence sequence.

[0058] Then, the server determines the extended example groundwater dynamic monitoring data sequence based on the confidence sequences output by each second groundwater level prediction network that has completed parameter learning. Specifically, the server determines the maximum confidence in each confidence sequence to generate the maximum confidence predicted by each second groundwater level prediction network that has completed parameter learning. For example, in the confidence sequence of a certain network, the prediction confidence of the 500th set of data is the highest, so this highest confidence is the maximum confidence of this network for this set of data.

[0059] Next, determine the extended example groundwater dynamic monitoring data corresponding to each maximum confidence level, and generate multiple sets of extended example groundwater dynamic monitoring data. For example, find the set of data corresponding to the maximum confidence level and use it as the extended example groundwater dynamic monitoring data. Finally, determine the extended example groundwater dynamic monitoring data sequence based on these multiple sets of extended example groundwater dynamic monitoring data.

[0060] Determine multiple target extended example groundwater dynamic monitoring data from this extended example groundwater dynamic monitoring data sequence. Suppose 100 sets of data are selected from the extended example data sequence, and then these 100 sets of target extended example groundwater dynamic monitoring data are loaded into the basic example groundwater dynamic monitoring data to generate the target example groundwater dynamic monitoring data. These target example groundwater dynamic monitoring data contain more valuable information and can provide richer data support for the subsequent learning of the first groundwater level prediction network.

[0061] Step S150: Perform water level prediction learning on the first groundwater level prediction network according to the target example groundwater dynamic monitoring data to generate a target groundwater level prediction network.

[0062] The server uses the generated target example groundwater dynamic monitoring data to perform water level prediction learning on the first groundwater level prediction network. Each set of data in the target example groundwater dynamic monitoring data contains rich groundwater dynamic information and the corresponding water level information. The first groundwater level prediction network adjusts its own parameters by learning these data to improve its prediction ability for the groundwater level.

[0063] During the learning process, the focusing nodes and transfer nodes in the network work together. The focusing nodes extract and analyze the key features in the target example data. For example, they focus on processing the relationships between the groundwater level and factors such as rainfall and surrounding land use types. The transfer nodes then transfer the processed data to other parts of the network, enabling the entire network to adjust parameters such as the connection weights between neurons based on these data.

[0064] With continuous learning of the target sample groundwater dynamic monitoring data, the prediction ability of the first groundwater level prediction network gradually improves. When the learning process reaches a predetermined condition, such as the prediction error is reduced to a very low level or the number of learning rounds reaches a certain amount, the server will use this learned first groundwater level prediction network as the target groundwater level prediction network. This target groundwater level prediction network has undergone multiple rounds of learning and optimization and has the ability to accurately predict the groundwater level. It can be used to predict any input target groundwater dynamic monitoring data and generate the water level prediction result of the target groundwater dynamic monitoring data. For example, when receiving new groundwater dynamic monitoring data of a certain area, this target groundwater level prediction network can accurately predict the groundwater level situation in this area according to the knowledge and rules learned before.

[0065] Based on the above steps, in the embodiment of the present application, by constructing the first groundwater level prediction network including a focusing node and a transfer node and generating multiple second groundwater level prediction networks based on different node association relationships, the diversity and accuracy of groundwater level prediction are significantly improved. Using the basic sample groundwater dynamic monitoring data to perform joint parameter learning on multiple second groundwater level prediction networks effectively optimizes the network parameters and further improves the prediction accuracy. At the same time, by expanding the water level prediction learning samples of the basic sample data, richer and more comprehensive target sample groundwater dynamic monitoring data are generated, providing data support for the training of the target groundwater level prediction network. The finally generated target groundwater level prediction network performs excellently in practical applications and can provide accurate and reliable decision-making basis for groundwater management and water resource protection.

[0066] In a possible implementation manner, the generating multiple second groundwater level prediction networks based on different node association relationships between the focusing node and the transfer node in each of the deep learning nodes includes:

[0067] Obtain the scale of the deep learning nodes in the first groundwater level prediction network.

[0068] Determine multiple network model architectures according to the scale of the deep learning nodes, and each of the network model architectures corresponds to a node association relationship between the focusing node and the transfer node.

[0069] Generate multiple second groundwater level prediction networks based on the multiple network model architectures.

[0070] In a possible implementation manner, the performing joint parameter learning on the multiple second groundwater level prediction networks based on the basic sample groundwater dynamic monitoring data to generate multiple second groundwater level prediction networks with completed parameter learning includes:

[0071] Obtain basic sample groundwater dynamic monitoring data, where the basic sample groundwater dynamic monitoring data includes multiple sample groundwater dynamic monitoring data and the corresponding labeled estimated water level data for each sample groundwater dynamic monitoring data.

[0072] Load any one of the multiple sample groundwater dynamic monitoring data, i.e., the target sample groundwater dynamic monitoring data, into the multiple second groundwater level prediction networks respectively, and generate multiple predicted water level results corresponding to the target sample groundwater dynamic monitoring data.

[0073] Optimize the multiple second groundwater level prediction networks based on the error between the multiple predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data. The multiple second groundwater level prediction networks share neuron weight information.

[0074] When the multiple second groundwater level prediction networks do not meet the training termination condition, return to execute the step of loading any one of the target sample groundwater dynamic monitoring data into the multiple second groundwater level prediction networks respectively, and optimizing the neuron weight information of the multiple second groundwater level prediction networks based on the error between the output multiple predicted water level results and the corresponding labeled estimated water level data.

[0075] When the multiple second groundwater level prediction networks meet the training termination condition, generate multiple second groundwater level prediction networks that have completed parameter learning.

[0076] In a possible implementation manner, the optimizing the multiple second groundwater level prediction networks based on the error between the multiple predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data, where the multiple second groundwater level prediction networks share neuron weight information, includes:

[0077] Calculate the loss function values between each of the multiple predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data respectively, and generate multiple training cost results.

[0078] Calculate the training direction parameters corresponding to each of the training cost results, and generate multiple training direction parameters.

[0079] Optimize the multiple second groundwater level prediction networks based on the multiple training direction parameters. The multiple second groundwater level prediction networks share neuron weight information.

[0080] In a possible implementation, the multiple second groundwater level prediction networks that learn according to the completion parameters perform water level prediction learning example expansion on the basic example groundwater dynamic monitoring data to generate target example groundwater dynamic monitoring data, including:

[0081] The multiple second groundwater level prediction networks that learn according to the completion parameters expand the basic example groundwater dynamic monitoring data to generate a sequence of expanded example groundwater dynamic monitoring data.

[0082] Determine multiple target expanded example groundwater dynamic monitoring data from the sequence of expanded example groundwater dynamic monitoring data, and load the multiple target expanded example groundwater dynamic monitoring data into the basic example groundwater dynamic monitoring data to generate target example groundwater dynamic monitoring data.

[0083] In a possible implementation, the multiple second groundwater level prediction networks that learn according to the completion parameters expand the basic example groundwater dynamic monitoring data to generate a sequence of expanded example groundwater dynamic monitoring data, including:

[0084] The second groundwater level prediction networks that learn according to each completion parameter process each example groundwater dynamic monitoring data in the basic example groundwater dynamic monitoring data to generate a confidence sequence predicted by the second groundwater level prediction networks that learn according to each completion parameter.

[0085] Determine a sequence of expanded example groundwater dynamic monitoring data based on the confidence sequences output by the second groundwater level prediction networks that learn according to each completion parameter.

[0086] In a possible implementation, the determining a sequence of expanded example groundwater dynamic monitoring data based on the confidence sequences output by the second groundwater level prediction networks that learn according to each completion parameter includes:

[0087] Determine the maximum confidence in each confidence sequence to generate the maximum confidence predicted by the second groundwater level prediction networks that learn according to each completion parameter.

[0088] Determine the expanded example groundwater dynamic monitoring data corresponding to each maximum confidence to generate multiple expanded example groundwater dynamic monitoring data.

[0089] Determine a sequence of expanded example groundwater dynamic monitoring data based on the multiple expanded example groundwater dynamic monitoring data.

[0090] In a possible implementation, the method includes:

[0091] Based on the target groundwater level prediction network, the target groundwater dynamic monitoring data input arbitrarily is predicted to generate the water level prediction result of the target groundwater dynamic monitoring data.

[0092] In the above embodiments, the artificial intelligence-based groundwater level monitoring system for implementing the above method embodiments has at least one processor, a control module (chipset) coupled to at least one of the (at least one) processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one load-to / output device coupled to the control module, and a network interface coupled to the control module.

[0093] The processor may include at least one single-core or multi-core processor, and the processor may include any combination of a general-purpose processor or a dedicated processor (such as a graphics processor, an application processor, a baseband processor, etc.). For some alternative embodiments, the artificial intelligence-based groundwater level monitoring system can be used as an electronic device such as the gateway described in the embodiments of the present application.

[0094] For some alternative embodiments, the artificial intelligence-based groundwater level monitoring system may include at least one computer-readable medium having instructions (e.g., a memory or an NVM / storage device) and at least one processor integrated with the at least one computer-readable medium and configured to execute the instructions to implement a module to perform the actions described in the present disclosure.

[0095] For one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the (at least one) processors and / or any suitable device or component communicating with the control module.

[0096] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0097] The memory may be used, for example, to load and store data and / or instructions for the artificial intelligence-based groundwater level monitoring system. For one embodiment, the memory may include any suitable volatile memory, e.g., a suitable DRAM.

[0098] For one embodiment, the control module may include at least one load-to / output controller to provide an interface to the NVM / storage device and the at least one load-to / output device.

[0099] For example, an NVM / storage device can be used to store data and / or instructions. The NVM / storage device can include any suitable non-volatile memory (e.g., flash memory) and / or can include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one compact disc (CD) drive, and / or at least one digital versatile disc (DVD) drive).

[0100] The NVM / storage device can include storage resources that are physically part of the device on which the artificial intelligence-based groundwater level monitoring system is installed, or it can be accessed by the device without necessarily being part of the device. For example, the NVM / storage device can be accessed via a (at least one) loading / to-output device based on a network.

[0101] The (at least one) loading / to-output device can provide an interface for the artificial intelligence-based groundwater level monitoring system to communicate with any other suitable device. The loading / to-output device can include communication components, phonetic components, sensor components, etc. The network interface can provide an interface for the artificial intelligence-based groundwater level monitoring system to communicate based on at least one network. The artificial intelligence-based groundwater level monitoring system can wirelessly communicate with at least one component of the wireless network based on any prior and / or protocol in at least one wireless network prior and / or protocol, such as accessing a wireless network based on a communication prior.

[0102] For one embodiment, at least one of the (at least one) processors can be logically loaded together with at least one controller of the control module (e.g., a memory controller module). For one embodiment, at least one of the (at least one) processors can be logically loaded together with at least one controller of the control module to form a system-level load. For one embodiment, at least one of the (at least one) processors can be logically integrated with at least one controller of the control module on the same die. For one embodiment, at least one of the (at least one) processors can be logically integrated with at least one controller of the control module on the same die to form a system-on-chip (SoC).

[0103] The embodiments of the present application have been introduced in detail above. Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, based on the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

[0104] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the artificial intelligence-based groundwater level monitoring method described in the foregoing embodiments.

[0105] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the artificial intelligence-based groundwater level monitoring method described in the foregoing embodiments.

[0106] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0107] Through the specific descriptions of the above embodiments, those skilled in the art can clearly understand that each implementation can be realized by means of software plus a necessary general hardware platform, and of course also by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used for a computer to have or store data.

[0108] Finally, it should be noted that what is disclosed above is only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A groundwater level monitoring method based on artificial intelligence, characterized in that: The method comprises: obtaining a first groundwater level prediction network, wherein the first groundwater level prediction network comprises a plurality of deep learning nodes, wherein the deep learning nodes comprise a focus node and a transmission node; generating a plurality of second groundwater level prediction networks based on different node association relationships between the focus node and the transmission node in each of the deep learning nodes; performing linkage parameter learning on the plurality of second groundwater level prediction networks based on basic sample groundwater dynamic monitoring data to generate a plurality of second groundwater level prediction networks that have completed parameter learning; performing water level prediction learning sample expansion on the basic sample groundwater dynamic monitoring data based on the plurality of second groundwater level prediction networks that have completed parameter learning to generate a target sample groundwater level prediction network; The target sample groundwater dynamic monitoring data; the first groundwater level prediction network is subjected to water level prediction learning according to the target sample groundwater dynamic monitoring data to generate a target groundwater level prediction network; during the learning process, the focusing nodes and the transmission nodes in the network work together, the focusing nodes process the key features in the target sample data, and the transmission nodes transmit the processed data to other parts of the network to ensure the flow of data and information transmission in the entire network; the second groundwater level prediction network is generated based on the different node association relationships between the focusing nodes and the transmission nodes in each of the deep learning nodes, including: obtaining the deep learning nodes in the first groundwater level prediction network The scale of the deep learning node is as follows: a plurality of network model architectures are determined according to the scale of the deep learning node, each of the network model architectures corresponds to a node association relationship between a focusing node and a transmission node; there are a plurality of different node association relationships between the focusing node and the transmission node, each network model architecture corresponds to a node association relationship, and the node association relationship refers to the node connection relationship between the focusing node and the transmission node; a plurality of second groundwater level prediction networks are generated based on the plurality of network model architectures; the plurality of second groundwater level prediction networks are linked to parameter learning based on the basic sample groundwater dynamic monitoring data to generate a plurality of second groundwater level prediction networks that have completed parameter learning, including: obtaining a basic sample groundwater Dynamic monitoring data, the basic sample groundwater dynamic monitoring data includes multiple sample groundwater dynamic monitoring data and annotated estimated water level data corresponding to each sample groundwater dynamic monitoring data; any target sample groundwater dynamic monitoring data among the multiple sample groundwater dynamic monitoring data are loaded into the multiple second groundwater level prediction networks respectively, and multiple predicted water level results corresponding to the target sample groundwater dynamic monitoring data are generated; the multiple second groundwater level prediction networks are optimized based on the errors between the multiple predicted water level results and the annotated estimated water level data corresponding to the target sample groundwater dynamic monitoring data, and the multiple second groundwater level prediction networks share neuron weight information;When the multiple second groundwater level prediction networks do not meet the training termination conditions, return to the step of loading any target sample groundwater dynamic monitoring data into the multiple second groundwater level prediction networks, and optimizing the neuron weight information of the multiple second groundwater level prediction networks based on the error between the output multiple predicted water level results and the corresponding labeled estimated water level data; when the multiple second groundwater level prediction networks meet the training termination conditions, generate multiple second groundwater level prediction networks that have completed parameter learning. ; 2. The groundwater level monitoring method based on artificial intelligence according to claim 1 is characterized in that: The multiple second groundwater level prediction networks are optimized based on the errors between the multiple predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data, and the multiple second groundwater level prediction networks share neuron weight information, including: respectively calculating the loss function value between each predicted water level result in the multiple predicted water level results and the labeled estimated water level data corresponding to the target sample groundwater dynamic monitoring data, and generating multiple training cost results; calculating the training direction parameters corresponding to each training cost result, and generating multiple training direction parameters; optimizing the multiple second groundwater level prediction networks based on the multiple training direction parameters, and the multiple second groundwater level prediction networks share neuron weight information.

3. The groundwater level monitoring method based on artificial intelligence according to claim 1 is characterized in that: The method of performing water level prediction learning sample expansion on the basic sample groundwater dynamic monitoring data based on the multiple second groundwater level prediction networks that have completed parameter learning to generate target sample groundwater dynamic monitoring data includes: expanding the basic sample groundwater dynamic monitoring data based on the multiple second groundwater level prediction networks that have completed parameter learning to generate an extended sample groundwater dynamic monitoring data sequence; determining multiple target extended sample groundwater dynamic monitoring data from the extended sample groundwater dynamic monitoring data sequence, and loading the multiple target extended sample groundwater dynamic monitoring data into the basic sample groundwater dynamic monitoring data to generate target sample groundwater dynamic monitoring data.

4. The groundwater level monitoring method based on artificial intelligence according to claim 3 is characterized in that: The multiple second groundwater level prediction networks based on the completed parameter learning expand the basic sample groundwater dynamic monitoring data to generate an extended sample groundwater dynamic monitoring data sequence, including: processing each sample groundwater dynamic monitoring data in the basic sample groundwater dynamic monitoring data based on each second groundwater level prediction network that has completed parameter learning to generate a confidence sequence predicted by each second groundwater level prediction network that has completed parameter learning; determining an extended sample groundwater dynamic monitoring data sequence based on the confidence sequence output by each second groundwater level prediction network that has completed parameter learning.

5. The groundwater level monitoring method based on artificial intelligence according to claim 4 is characterized in that: The method determines an extended sample groundwater dynamic monitoring data sequence based on the confidence sequence output by the second groundwater level prediction network that has completed parameter learning, including: determining the maximum confidence in each confidence sequence, generating the maximum confidence predicted by each second groundwater level prediction network that has completed parameter learning; determining the extended sample groundwater dynamic monitoring data corresponding to each maximum confidence, generating multiple extended sample groundwater dynamic monitoring data; and determining the extended sample groundwater dynamic monitoring data sequence based on the multiple extended sample groundwater dynamic monitoring data.

6. The groundwater level monitoring method based on artificial intelligence according to claim 1 is characterized in that: The method comprises: predicting any input target groundwater dynamic monitoring data based on the target groundwater level prediction network, and generating a water level prediction result of the target groundwater dynamic monitoring data.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the groundwater level monitoring method based on artificial intelligence described in any one of claims 1 to 6 is implemented.

8. A groundwater level monitoring system based on artificial intelligence, characterized in that: It includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the artificial intelligence-based groundwater level monitoring method described in any one of claims 1 to 6 is implemented.

Images