Method and device for determining equipment layout area, equipment and medium

Abstract

The invention relates to the technical field of environmental monitoring, and provides a method and device for determining an equipment layout area, equipment and a medium. The method comprises the following steps: acquiring water quality monitoring data of each grid region in a target water area; obtaining a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each grid region according to the water quality monitoring data of each grid region; fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid region to obtain a comprehensive evaluation parameter of each grid region; according to the comprehensive evaluation parameters of each grid area, an equipment layout area is determined in the target water area, and the equipment layout area is used for laying water quality monitoring equipment. Based on the scheme of the invention, the reliability of the determined equipment layout area for reflecting the overall water quality condition of the target water area can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and in particular to a method and device for determining a device deployment area, a device and a medium. BACKGROUND

[0002] Water quality monitoring is a basic work for evaluating water environment conditions and preventing and managing pollution. In order to obtain water quality related data, water quality monitoring devices such as hyperspectral monitoring devices need to be deployed in water areas. In order to enable these water quality monitoring devices to effectively reflect the overall water quality conditions of the target water area, it is necessary to reasonably determine the deployment area thereof.

[0003] At present, in related schemes, the determination of the device deployment area is mostly dependent on artificial experience, lacks objective quantitative basis, and may cause the selected grid area to fail to accurately capture the spatial distribution characteristics of water quality, thereby causing a monitoring blind area or data redundancy. Therefore, how to improve the reliability of the water quality monitoring device deployment area has become a technical problem to be solved. SUMMARY

[0004] The embodiments of the present application provide a method and device for determining a device deployment area, and a device and a medium, to solve the technical problem of how to improve the reliability of the water quality monitoring device deployment area.

[0005] In a first aspect, the embodiments of the present application provide a method for determining a device deployment area, comprising: obtaining water quality monitoring data of each grid area in a target water area; obtaining a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each grid area according to the water quality monitoring data of each grid area, the first evaluation parameter being used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid area, the second evaluation parameter being used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid area to the water quality monitoring data of the surrounding grid area, and the third evaluation parameter being used to represent the change intensity of the water quality monitoring data of the corresponding grid area; fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area respectively to obtain a comprehensive evaluation parameter of each grid area; determining a device deployment area in the target water area according to the comprehensive evaluation parameter of each grid area, the device deployment area being used to deploy a water quality monitoring device.

[0006] In combination with the first aspect, in some possible implementation manners, the obtaining of the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area according to the water quality monitoring data of each grid area comprises: perform spatial prediction uncertainty analysis on the water quality monitoring data of each grid region to obtain a first evaluation parameter of each grid region; perform spatial representative analysis on the water quality monitoring data of each grid region to obtain a second evaluation parameter of each grid region; perform change intensity analysis on the water quality monitoring data of each grid region to obtain a third evaluation parameter of each grid region.

[0007] In some possible implementation manners, in combination with the first aspect and the foregoing implementation manners, the spatial prediction uncertainty analysis on the water quality monitoring data of each grid region to obtain the first evaluation parameter of each grid region includes: determining, according to the water quality monitoring data of each grid region, a prediction variance of each grid region by using a preset Kriging interpolation algorithm; determining, according to the prediction variance of each grid region, an information entropy of each grid region; determining, according to the information entropy of each grid region, the first evaluation parameter of each grid region.

[0008] In some possible implementation manners, in combination with the first aspect and the foregoing implementation manners, the spatial representative analysis on the water quality monitoring data of each grid region to obtain the second evaluation parameter of each grid region includes: determining, in the target water area, a surrounding grid region of each grid region; obtaining, according to the water quality monitoring data of each grid region, water quality monitoring estimation data of the surrounding grid region of each grid region; determining, according to the water quality monitoring data and the water quality monitoring estimation data of the surrounding grid region of each grid region, a mean square error of the surrounding grid region of each grid region; determining, according to the mean square error of the surrounding grid region of each grid region, the second evaluation parameter of each grid region.

[0009] In some possible implementation manners, in combination with the first aspect and the foregoing implementation manners, the change intensity analysis on the water quality monitoring data of each grid region to obtain the third evaluation parameter of each grid region includes: determining, according to the water quality monitoring data of each grid region, a time series function of each grid region; performing first-order derivation on the time series function of each grid region respectively and taking absolute values to obtain a first-order derivative absolute value corresponding to the time series function of each grid region; determining, according to the first-order derivative absolute value corresponding to the time series function of each grid region, the third evaluation parameter of each grid region.

[0010] In some possible implementation manners, the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter of each grid region are fused respectively to obtain a comprehensive evaluation parameter of each grid region, including: The first evaluation parameter, the second evaluation parameter, and the third evaluation parameter of each grid region are weighted and summed according to the preset first weight coefficient, the preset second weight coefficient, and the preset third weight coefficient to obtain the comprehensive evaluation parameter of each grid region. The sum of the preset first weight coefficient, the preset second weight coefficient, and the preset third weight coefficient is 1.

[0011] In some possible implementation manners, according to the comprehensive evaluation parameter of each grid region, a device deployment region is determined in the target water area, including: According to the comprehensive evaluation parameter of each grid region, a preset greedy algorithm, and a preset upper limit, a grid region with the largest corresponding comprehensive evaluation parameter is iteratively selected from the grid regions in the target water area to join a device deployment region set until the number of grid regions in the device deployment region set reaches the preset upper limit. The grid regions in the device deployment region set are determined as the device deployment region.

[0012] In a second aspect, an embodiment of the present application provides a device deployment region determination apparatus, including: A first obtaining module is configured to obtain water quality monitoring data of each grid region in a target water area. A second obtaining module is configured to obtain a first evaluation parameter, a second evaluation parameter, and a third evaluation parameter of each grid region according to the water quality monitoring data of each grid region, the first evaluation parameter being used to represent spatial prediction uncertainty of the water quality monitoring data of the corresponding grid region, the second evaluation parameter being used to represent spatial representativeness of the water quality monitoring data of the corresponding grid region to surrounding grid regions, and the third evaluation parameter being used to represent variation intensity of the water quality monitoring data of the corresponding grid region. A parameter fusion module is configured to fuse the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter of each grid region respectively to obtain a comprehensive evaluation parameter of each grid region. A region determination module is configured to determine a device deployment region in the target water area according to the comprehensive evaluation parameter of each grid region, the device deployment region being used to deploy a water quality monitoring device.

[0013] In a third aspect, an embodiment of the present application provides an electronic device including a processor and a memory storing a computer program, the processor implementing the steps of the device deployment region determination method of the first aspect when executing the program.

[0014] In a fourth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the method for determining a device deployment area of the first aspect.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the steps of the method for determining a device deployment area of the first aspect.

[0016] The method, device, apparatus and medium provided by the embodiments of the present application for determining a device deployment area first acquire water quality monitoring data of each grid area in a target water area; secondly, based on the water quality monitoring data of each grid area, a first evaluation parameter for representing spatial prediction uncertainty, a second evaluation parameter for representing spatial representativeness of surrounding grid area water quality monitoring data and a third evaluation parameter for representing change intensity are respectively acquired, so as to comprehensively evaluate each grid area from three dimensions of spatial uncertainty, regional representativeness and temporal dynamics; then, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area are fused to obtain a comprehensive evaluation parameter capable of comprehensively reflecting the monitoring value of the grid area; finally, according to the comprehensive evaluation parameter of each grid area, a device deployment area for deploying a water quality monitoring device in the target water area is determined. Through the above scheme, since the three dimensions of spatial prediction uncertainty, spatial representativeness and temporal change intensity of water quality monitoring data are considered and fused, the finally determined device deployment area can cover the area with high water quality information uncertainty to reduce the monitoring blind area, can ensure that the selected area is representative of its surroundings to improve the monitoring efficiency, and can capture the dynamic change trend of the water quality parameter, thereby improving the reliability of the determined device deployment area for reflecting the overall water quality condition of the target water area. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0018] Figure 1 is a flowchart of the method for determining a device deployment area provided by the embodiments of the present application; Figure 2 is a flowchart of determining a plurality of evaluation parameters provided by the embodiments of the present application; Figure 3 is a flowchart of determining a first evaluation parameter provided by the embodiments of the present application; Figure 4 is a flowchart of a process for determining a second evaluation parameter provided by an embodiment of the present application; Figure 5 is a flowchart of a process for determining a third evaluation parameter provided by an embodiment of the present application; Figure 6 is a flowchart of a process for determining a comprehensive evaluation parameter provided by an embodiment of the present application; Figure 7 is a flowchart of a process for determining a device deployment area provided by an embodiment of the present application; Figure 8 is a structural diagram of a device deployment area determination apparatus provided by an embodiment of the present application; Figure 9 is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0020] Water quality monitoring is a basic work for evaluating water environmental conditions, pollution prevention and management. By collecting and analyzing physical, chemical and biological indicators of water samples, the current situation and trend of water environmental quality can be mastered. In order to obtain water quality related data, it is usually necessary to deploy water quality monitoring devices in water areas. For example, the water quality monitoring device can be a hyperspectral monitoring device, which refers to a device that can obtain the reflection or radiation information of water in multiple continuous and narrow spectral bands. Through analysis of these spectral data, various water quality parameters can be retrieved. In addition to the hyperspectral monitoring device, the water quality monitoring device can also be a multi-parameter water quality sensor (for measuring dissolved oxygen, pH value, turbidity, conductivity, etc.), a chemical analyzer (for measuring chemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, etc.), and a biological monitoring device (such as a monitoring device based on changes in aquatic biological community structure). In order to enable these water quality monitoring devices to effectively reflect the overall water quality condition of the target water area, it is necessary to reasonably determine the deployment area thereof.

[0021] In some related solutions, the way adopted is to arrange based on artificial experience. Specifically, the operator selects a representative grid area to arrange the water quality monitoring device according to the understanding of the terrain, hydrological characteristics, and pollution source distribution of the target water area. This method relies on the professional level and experience of the operator, lacks objective and unified quantitative standards, and may result in the selected grid area failing to accurately capture the spatial heterogeneity of water quality, making it difficult for the monitoring data to reflect the overall water quality condition of the target water area.

[0022] In some related solutions, the way adopted is to arrange based on a single water quality index concentration. Specifically, this solution first obtains the data of a certain specific water quality index (such as ammonia nitrogen concentration) in some grid areas of the target water area through preliminary sampling, and then selects the area with the highest or most significant concentration of the water quality index as the arrangement area of the water quality monitoring device. This method only focuses on a single water quality index and ignores the possible influence between different water quality indexes and the comprehensiveness and complexity of water quality conditions. The arrangement area selected based on a single water quality index may result in unsatisfactory monitoring effect.

[0023] In some related solutions, the way adopted is to use a regular grid or random arrangement strategy. Specifically, regular grid arrangement is to divide the target water area into uniform grids and arrange water quality monitoring devices at the center or vertices of each grid; random arrangement is to randomly select several grid areas in the target water area for device deployment. These two methods are simple to operate, but do not consider the actual water quality spatial distribution characteristics of the target water area. In regular grid arrangement, if the water quality distribution is not uniform in space, it may cause waste of monitoring resources in areas with slow changes, and the monitoring accuracy may decrease due to insufficient arrangement density in areas with rapid changes; random arrangement may result in excessive concentration of water quality monitoring devices in some areas, while other areas have monitoring blind spots, which cannot guarantee effective coverage of the overall water quality condition of the target water area.

[0024] It can be seen that the device arrangement area determined by the above related solutions has poor reliability. Therefore, how to improve the reliability of the water quality monitoring device arrangement area has become a technical problem to be solved.

[0025] To solve the above problems, the main scheme provided by the embodiments of the present application includes: first, obtaining water quality monitoring data of each grid area in the target water area; second, based on the water quality monitoring data of each grid area, respectively obtaining a first evaluation parameter for representing spatial prediction uncertainty, a second evaluation parameter for representing spatial representativeness of surrounding grid area water quality monitoring data, and a third evaluation parameter for representing change intensity, thereby comprehensively evaluating each grid area from three dimensions of spatial uncertainty, regional representativeness and temporal dynamics; then, fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area to obtain a comprehensive evaluation parameter that can comprehensively reflect the monitoring value of the grid area; finally, determining a device layout area for laying water quality monitoring devices in the target water area according to the comprehensive evaluation parameter of each grid area. Through the above scheme, since the spatial prediction uncertainty, spatial representativeness and temporal change intensity of the water quality monitoring data are considered at the same time and fused, the finally determined device layout area can cover the area with high water quality information uncertainty to reduce the monitoring blind area, can ensure that the selected area is representative of its surroundings to improve the monitoring efficiency, and can capture the dynamic change trend of the water quality parameter, thereby improving the reliability of the determined device layout area for reflecting the overall water quality condition of the target water area.

[0026] The determination method of the device layout area provided by the embodiments of the present application will be described in detail below.

[0027] Please refer to Figure 1 , Figure 1 The flowchart of the determination method of the device layout area provided by the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the method of the embodiments of the present application can include the following steps S101-S104. Figure 1

[0028] S101, obtaining water quality monitoring data of each grid area in the target water area.

[0029] Specifically, considering that the water quality condition in the target water area is heterogeneous in space, in order to comprehensively and effectively monitor the entire target water area, the embodiments of the present application propose a systematic determination method of the device layout area, which first needs to collect basic data that can reflect the water quality condition of the target water area.

[0030] ​First, in order to construct a multivariate spatial data set that can describe the spatial distribution characteristics of the water quality of the target water area, as the basis for subsequent analysis, it is necessary to obtain water quality monitoring data for each grid area in the target water area. Among them, the target water area refers to any water body that needs to be monitored, such as rivers, lakes, reservoirs or near-sea waters; the grid area refers to the smallest analysis unit with a clear spatial position and boundary divided from the target water area according to the preset rules (such as equal latitude and longitude, equal area); the water quality monitoring data refers to the physical, chemical or biological index data that can represent the water quality, such as dissolved oxygen, ammonia nitrogen, chemical oxygen demand, total phosphorus, total nitrogen, turbidity, chlorophyll a concentration or hyperspectral remote sensing data.

[0031] Regarding this step, in some possible implementations, water quality monitoring data covering each grid area in the target water area can be constructed by spatializing the multi-source data. In some possible implementations, the water quality monitoring data of each grid area in the target water area can be estimated and obtained by spatial interpolation of discrete sampling point data within the target water area.

[0032] S102, according to the water quality monitoring data of each grid area, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area are obtained, the first evaluation parameter is used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid area, the second evaluation parameter is used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid area to the water quality monitoring data of the surrounding grid area, and the third evaluation parameter is used to represent the change intensity of the water quality monitoring data of the corresponding grid area.

[0033] Specifically, in order to comprehensively evaluate the monitoring value of each grid area from the three dimensions of spatial uncertainty, spatial representativeness and temporal dynamics, it is necessary to obtain the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area according to the water quality monitoring data of each grid area.

[0034] Among them, the first evaluation parameter is used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid area, specifically refers to the error or unreliable degree of the prediction result when the water quality condition of the grid area is spatially predicted, the larger the value, the more difficult the water quality condition of the region is accurately predicted by the surrounding data, which is an information blank or fuzzy area.

[0035] The second evaluation parameter is used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid area to the water quality monitoring data of the surrounding grid area, specifically refers to the ability of the water quality monitoring data of the grid area to reflect or infer the water quality condition of its surrounding area, the larger the value, the more the region can represent the water quality characteristics of its surrounding area, and the equipment can improve the monitoring efficiency at this place.

[0036] The third evaluation parameter is used to represent the change intensity of the water quality monitoring data of the corresponding grid area, specifically refers to the degree of change of the water quality condition of the grid area over time, and the greater the value, the more unstable the water quality state of the region, which is a key area prone to pollution events or water quality changes.

[0037] Regarding this step, in some possible implementation manners, the spatial prediction uncertainty analysis, the spatial representativeness analysis and the change intensity analysis can be respectively performed based on the water quality monitoring data of each grid area, so as to correspondingly obtain the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area. In some possible implementation manners, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area can be calculated simultaneously by using the water quality monitoring data of each grid area through a comprehensive evaluation model.

[0038] S103, respectively, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area are fused to obtain the comprehensive evaluation parameter of each grid area.

[0039] Specifically, in order to perform a single and quantitative comprehensive evaluation on each grid area for global comparison and screening, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area need to be fused to obtain the comprehensive evaluation parameter of each grid area. The comprehensive evaluation parameter refers to a quantitative index for comprehensively reflecting the overall monitoring value of a specific grid area in terms of spatial prediction uncertainty, spatial representativeness and time change intensity.

[0040] Regarding this step, in some possible implementation manners, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area can be fused by means of weighted calculation to obtain the comprehensive evaluation parameter of each grid area. In some possible implementation manners, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area can be processed as input data by using a multi-attribute decision method to obtain the comprehensive evaluation parameter of each grid area.

[0041] S104, according to the comprehensive evaluation parameter of each grid area, a device layout area is determined in the target water area, and the device layout area is used to layout a water quality monitoring device.

[0042] Specifically, in order to achieve the optimal monitoring effect under limited monitoring resources, the position of the monitoring device deployment is scientifically selected, and the device deployment area is determined in the target water area according to the comprehensive evaluation parameter of each grid area. The device deployment area refers to the grid area or the set of grid areas in the target water area that is finally selected for deploying one or more water quality monitoring devices; the device deployment area is used to deploy the water quality monitoring device, specifically referring to physically installing or deploying the water quality monitoring device in the device deployment area to collect water quality data in the area and its surrounding area.

[0043] Regarding this step, in some possible implementation manners, the grid area that meets the preset condition can be selected as the device deployment area in the target water area based on the size of the comprehensive evaluation parameter of each grid area. In some possible implementation manners, the optimal device deployment area can be screened out in the target water area by using an iterative optimization manner according to the comprehensive evaluation parameter of each grid area.

[0044] In this embodiment, first, the water quality monitoring data of each grid area in the target water area is acquired; second, based on the water quality monitoring data of each grid area, the first evaluation parameter for representing spatial prediction uncertainty, the second evaluation parameter for representing spatial representativeness of the surrounding grid area water quality monitoring data, and the third evaluation parameter for representing change intensity are respectively acquired, so as to comprehensively evaluate each grid area from three dimensions of spatial uncertainty, area representativeness, and time dynamics; then, the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter of each grid area are fused to obtain the comprehensive evaluation parameter that can comprehensively reflect the monitoring value of the grid area; finally, the device deployment area for deploying the water quality monitoring device is determined in the target water area according to the comprehensive evaluation parameter of each grid area. Through the above scheme, since the three dimensions of spatial prediction uncertainty, spatial representativeness, and time change intensity of the water quality monitoring data are considered and fused, the finally determined device deployment area can cover the area with high water quality information uncertainty to reduce the monitoring blind area, can ensure that the selected area is representative of its surrounding area to improve the monitoring efficiency, and can capture the dynamic change trend of the water quality parameter, thereby improving the reliability of the determined device deployment area for reflecting the overall water quality condition of the target water area.

[0045] Please refer to Figure 2 A flowchart for determining multiple evaluation parameters is provided for the embodiments of the present application, as shown in Figure 2 The method of the embodiments of the present application can include the following steps S201-S203, which can be further detailed as the above-mentioned step of “acquiring the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter of each grid area according to the water quality monitoring data of each grid area”.

[0046] S201, performing spatial prediction uncertainty analysis on the water quality monitoring data of each grid region to obtain a first evaluation parameter of each grid region; S202, performing spatial representativeness analysis on the water quality monitoring data of each grid region to obtain a second evaluation parameter of each grid region; S203, performing change intensity analysis on the water quality monitoring data of each grid region to obtain a third evaluation parameter of each grid region.

[0047] Specifically, considering that spatial prediction uncertainty, spatial representativeness and change intensity are key indicators for evaluating the monitoring value of a grid region from different dimensions, the embodiment proposes a method for determining each evaluation parameter step by step to realize fine evaluation of each grid region.

[0048] In order to quantify the unknown degree or information entropy of the water quality condition of each grid region in space, so as to identify the region most needing observation by field equipment, it is necessary to perform spatial prediction uncertainty analysis on the water quality monitoring data of each grid region to obtain a first evaluation parameter of each grid region. The spatial prediction uncertainty analysis refers to an analysis process of evaluating the error range or confidence level of the prediction result when predicting the water quality parameter of a specific grid region using existing data.

[0049] Regarding this step, in some possible implementation manners, the water quality monitoring data of each grid region can be analyzed by using statistical methods, the prediction variance of each grid region when performing spatial interpolation is calculated, and the prediction variance is taken as the first evaluation parameter of each grid region. In some possible implementation manners, based on the water quality monitoring data of each grid region, a probability distribution model of the data of the surrounding region of the grid region to its prediction value can be constructed, and the first evaluation parameter of each grid region can be determined according to the dispersion degree of the probability distribution model.

[0050] Further, in order to evaluate the summarization or expression ability of each grid region to the water quality condition of its surrounding region, so as to find a representative grid region with high monitoring efficiency, it is necessary to perform spatial representativeness analysis on the water quality monitoring data of each grid region to obtain a second evaluation parameter of each grid region. The spatial representativeness analysis refers to an analysis process of measuring to what extent the water quality monitoring data of a grid region can reflect or infer the water quality condition of other grid regions in its adjacent spatial range.

[0051] As to this step, in some possible implementation ways, for each grid region, the grid regions in its surrounding neighborhood can be predicted by using the water quality monitoring data of the grid region, and the reciprocal of the error between the predicted value and the true value can be taken as the second evaluation parameter of the grid region. In some possible implementation ways, the similarity between each grid region and all the grid regions in its surrounding neighborhood can be calculated, and the average of the similarity can be taken as the second evaluation parameter of each grid region.

[0052] Further, in order to identify the regions with the most significant or unstable changes in water quality conditions over time, and thus focus on monitoring potential water quality risks, change intensity analysis needs to be performed according to the water quality monitoring data of each grid region to obtain the third evaluation parameter of each grid region. The change intensity analysis refers to an analysis process of quantifying the change rate or fluctuation intensity of each grid region by analyzing the water quality monitoring data of the grid region over a time sequence.

[0053] As to this step, in some possible implementation ways, a time sequence function can be constructed for the water quality monitoring data of each grid region, a first-order derivative of the time sequence function can be calculated, and the average of the absolute value of the first-order derivative in the time dimension can be taken as the third evaluation parameter of each grid region. In some possible implementation ways, the standard deviation or range of the water quality monitoring data of each grid region within a preset time window can be calculated, and the standard deviation or range can be taken as the third evaluation parameter of each grid region.

[0054] In this embodiment, first, spatial prediction uncertainty analysis is performed according to the water quality monitoring data of each grid region to obtain the first evaluation parameter of each grid region, which quantifies the error in predicting the water quality of the point by using the surrounding data, thereby identifying the regions with unclear information; then, spatial representativeness analysis is performed according to the water quality monitoring data of each grid region to obtain the second evaluation parameter of each grid region, which evaluates the ability of the water quality condition of the point to reflect the characteristics of the surrounding regions, and is used to screen the grid regions with high information coverage efficiency; finally, change intensity analysis is performed according to the water quality monitoring data of each grid region to obtain the third evaluation parameter of each grid region, which characterizes the intensity of the change in water quality over time, so as to locate the key regions with strong dynamics. Through the above scheme, each grid region is quantitatively evaluated from the three dimensions of spatial uncertainty, spatial representativeness, and temporal dynamics, so that the subsequent device deployment can take into account filling the monitoring blind area, improving the monitoring efficiency, and capturing key changes at the same time, thereby optimizing the monitoring benefit under the limited number of devices, and improving the overall performance and reliability of water quality monitoring.

[0055] See Figure 3A flowchart for determining the first evaluation parameter is provided for the embodiments of the present application, as shown in the figure Figure 3 The method of the embodiments of the present application can include steps S301-S303, which can be further detailed for the above-mentioned step of "performing spatial prediction uncertainty analysis on the water quality monitoring data of each grid region to obtain the first evaluation parameter of each grid region".

[0056] S301, determining the prediction variance of each grid region according to the water quality monitoring data of each grid region by using a preset Kriging interpolation algorithm; S302, determining the information entropy of each grid region according to the prediction variance of each grid region; S303, determining the first evaluation parameter of each grid region according to the information entropy of each grid region.

[0057] Specifically, to evaluate the spatial prediction uncertainty, the embodiments propose a method of determining the first evaluation parameter based on the combination of statistics and information theory.

[0058] First, the prediction variance of each grid region needs to be determined according to the water quality monitoring data of each grid region by using a preset Kriging interpolation algorithm. The preset Kriging interpolation algorithm refers to a statistical method based on regionalized variable theory, which uses the autocorrelation of spatial sampling points for optimal and unbiased interpolation estimation. The prediction variance refers to the measurement of the uncertainty of the estimated value itself given by the Kriging interpolation algorithm when estimating the water quality monitoring data of a grid region. The larger the value, the lower the reliability of the prediction at that point.

[0059] Regarding this step, in some possible implementation manners, the water quality monitoring data of known grid regions can be used to fit the autocorrelation structure of the water quality monitoring data in space by constructing a variogram model, and based on the variogram model, the prediction variance of each grid region in the target water area can be calculated by using the preset Kriging interpolation algorithm.

[0060] Further, the information entropy of each grid region is determined according to the prediction variance of each grid region. The information entropy refers to an index for measuring the uncertainty of a random variable, which is used to comprehensively reflect the overall level of the prediction uncertainty of multiple water quality monitoring indicators at a grid region in the embodiments.

[0061] Regarding this step, in some possible implementation manners, the prediction variance of multiple water quality monitoring indicators at each grid region can be taken as input, and the information entropy of each grid region can be calculated by weighted summation, wherein the weight of each water quality monitoring indicator can be set according to the importance of the indicator or its contribution to the comprehensive evaluation of water quality.

[0062] Furthermore, based on the information entropy of each grid region, the first evaluation parameter for each grid region is determined.

[0063] Regarding this step, in some possible implementations, the information entropy of each grid area can be directly used as the first evaluation parameter of that grid area. In this case, the larger the information entropy of the grid area, the larger its first evaluation parameter is, indicating that the water quality of the grid area is more difficult to accurately predict through surrounding data and has higher monitoring value.

[0064] For example, for any grid area in the target water area First, a pre-defined Kriging interpolation algorithm is used, utilizing the known information in its surrounding area. grid areas The Water quality monitoring data To estimate the grid area The Water quality monitoring data values The calculation formula is as follows: ; in These are the weighting coefficients determined by the Kriging interpolation algorithm. The algorithm also provides the prediction variance of this estimate. Then, for this grid area... In summary, all of them Calculate the information entropy based on the predictive uncertainty of each water quality monitoring indicator. The calculation formula is as follows: ; in For the first The weight of each water quality monitoring indicator, To the predicted variance Related uncertainty measures To prevent the use of small constants that are meaningless for several terms, the calculated information entropy is finally... Directly used as the grid area The first evaluation parameter.

[0065] In this embodiment, the prediction variance of each grid region is quantified by using the Kriging interpolation algorithm and further converted into information entropy. Finally, the information entropy is used as the first evaluation parameter, thereby realizing the quantitative assessment of the spatial prediction uncertainty of water quality monitoring data and providing a basis for identifying information gaps or monitoring blind spots.

[0066] Please see Figure 4A flowchart for determining the first evaluation parameter is provided for the embodiments of the present application, as shown in Figure 4 The method of the embodiments of the present application can include the following steps S401-S404, which can be further detailed for the above-mentioned step of "performing spatial representative analysis on the water quality monitoring data of each grid region to obtain the second evaluation parameter of each grid region".

[0067] S401, in the target water area, determine the surrounding grid regions of each grid region; S402, according to the water quality monitoring data of each grid region, obtain the water quality monitoring estimation data of the surrounding grid regions of each grid region; S403, according to the water quality monitoring data and the water quality monitoring estimation data of the surrounding grid regions of each grid region, determine the mean square error of the surrounding grid regions of each grid region; S404, according to the mean square error of the surrounding grid regions of each grid region, determine the second evaluation parameter of each grid region.

[0068] Specifically, considering the need to quantify the representativeness of the grid region to the surrounding region, the embodiments propose a scheme for determining the second evaluation parameter by evaluating the prediction error.

[0069] First, in the target water area, the surrounding grid regions of each grid region need to be determined. The surrounding grid regions of a grid region refer to a set of one or more grid regions that are adjacent to or within a predetermined spatial range of the grid region.

[0070] Regarding this step, in some possible implementation manners, a predetermined spatial neighborhood range (for example, a rectangular or circular window of a specific size containing the grid region) can be set with the grid region as the center, and other grid regions within the spatial neighborhood range can be determined as the surrounding grid regions of the grid region.

[0071] Further, according to the water quality monitoring data of each grid region, the water quality monitoring estimation data of the surrounding grid regions of each grid region is obtained. The water quality monitoring estimation data of the surrounding grid regions of a grid region refers to the data obtained by estimating the water quality monitoring data of the surrounding grid regions of the grid region through a predetermined prediction model using the water quality monitoring data of the grid region.

[0072] Regarding this step, in some possible implementation manners, for each grid region, its water quality monitoring data can be taken as the input, and a predetermined spatial interpolation model or inverse distance weighting model can be used to predict the water quality monitoring data of its surrounding grid regions, thereby obtaining the water quality monitoring estimation data of each surrounding grid region.

[0073] Furthermore, based on the water quality monitoring data and estimated water quality monitoring data of the surrounding grid areas of each grid area, the mean square error of the surrounding grid areas of each grid area is determined. The mean square error of the surrounding grid areas of a grid area refers to the average of the sum of squares of the errors between the estimated water quality monitoring data and the water quality monitoring data of those surrounding grid areas.

[0074] Regarding this step, in some possible implementations, the summation of the squared differences between the estimated water quality monitoring data of the surrounding grid areas of each grid area and the corresponding water quality monitoring data, and then divided by the total number of surrounding grid areas, can be used to obtain the mean squared error of the surrounding grid areas of each grid area.

[0075] Furthermore, based on the mean square error of the surrounding grid regions of each grid region, a second evaluation parameter for each grid region is determined.

[0076] Regarding this step, in some possible implementations, the reciprocal of the mean square error can be used as the second evaluation parameter for the grid area. In this case, the smaller the mean square error of the grid area, the larger its second evaluation parameter, indicating that the water quality monitoring data of the grid area has a stronger predictive ability for its surrounding areas and a higher spatial representativeness.

[0077] For example, for any grid area in the target water area First, determine the set of surrounding grid regions. The set contains A grid area. Then, using this grid area... Water quality monitoring data, through a pre-set prediction model, is used to... Each surrounding grid area within The water quality monitoring data was used to estimate the water quality monitoring data. Next, each surrounding grid area... Water quality monitoring estimation data Compared with actual water quality monitoring data Compare the two, calculate the squared difference between them, sum the squared differences over all surrounding grid areas, and then divide by the total number of surrounding grid areas. The mean square error is then obtained. Finally, based on the calculated mean square error, the grid region is determined. The second evaluation parameter The calculation formula is as follows: ; in, Represents grid-based regions For the surrounding grid area estimated data of water quality monitoring, actual water quality monitoring data of the peripheral grid area. actual water quality monitoring data of the peripheral grid area.

[0078] In this embodiment, by calculating the prediction mean square error of each grid area for its peripheral grid area, and determining the second evaluation parameter based on the mean square error, the quantitative evaluation of the spatial representativeness of the grid area is realized, which provides a basis for screening the area with high information coverage efficiency.

[0079] Please refer to Figure 5 , a flowchart for determining the third evaluation parameter is provided for the embodiments of the present application, as Figure 5 indicated, the method of the embodiments of the present application can include the following steps S501-S503, which can be further refined as the above-mentioned "performing change intensity analysis on the water quality monitoring data of each grid area to obtain the third evaluation parameter of each grid area" step.

[0080] S501, determining a time series function of each grid area according to the water quality monitoring data of each grid area; S502, respectively performing first-order derivation on the time series function of each grid area and taking absolute value to obtain the first-order derivative absolute value corresponding to the time series function of each grid area; S503, determining the third evaluation parameter of each grid area according to the first-order derivative absolute value corresponding to the time series function of each grid area.

[0081] Specifically, considering the need to quantify the degree of change of water quality over time, the embodiments propose a scheme for determining the third evaluation parameter based on time series analysis.

[0082] First, according to the water quality monitoring data of each grid area, the time series function of each grid area needs to be determined. Among them, the time series function of the grid area refers to a mathematical function or model that can describe the change rule of the water quality monitoring data of the grid area over time.

[0083] Regarding this step, in some possible implementation manners, the water quality monitoring data of each grid area at consecutive multiple time points can be taken as input, and a time series fitting scheme such as polynomial fitting, spline interpolation or Fourier transform can be used to construct a time series function that can represent the trend of water quality monitoring data over time.

[0084] Further, the first-order derivative of each grid region's time series function is calculated and the absolute value is taken, to obtain the first-order derivative absolute value corresponding to each grid region's time series function. The first-order derivative absolute value corresponding to the time series function of the grid region refers to the absolute value of the change rate of the time series function at any time point, and is used to represent the instantaneous change rate of the water quality monitoring data at the time point.

[0085] Regarding this step, in some possible implementations, the time series function of each grid region can be differentiated in the time dimension to obtain the first-order derivative function, and then the absolute value of the first-order derivative function is taken to obtain the first-order derivative absolute value corresponding to the time series function of each grid region.

[0086] Further, the third evaluation parameter of each grid region is determined according to the first-order derivative absolute value corresponding to the time series function of each grid region.

[0087] Regarding this step, in some possible implementations, the first-order derivative absolute value corresponding to the time series function of each grid region can be integrated or averaged in a preset time interval, and the obtained result is taken as the third evaluation parameter of the grid region.

[0088] In some possible implementations, the maximum value of the first-order derivative absolute value corresponding to the time series function of each grid region in a preset time interval can also be taken as the third evaluation parameter of the grid region, to capture the peak change strength of the water quality monitoring data.

[0089] For example, for any one grid region in the target water area , the time series function of water quality monitoring indicators is included , where , is time. For each water quality monitoring indicator, the first-order derivative of the time series function is calculated and the absolute value is taken, to obtain the change rate absolute value of the indicator. Then, the change rate absolute values of all water quality monitoring indicators in the grid region are summed and averaged to obtain the third evaluation parameter of the grid region. The calculation formula is: ; wherein represents the time series function of the water quality monitoring indicator, The total number of water quality monitoring indicators. The larger the parameter value, the more intense the water quality condition of the grid area changes over time, and the more it needs to be monitored.

[0090] In this embodiment, by constructing a time series function and calculating the statistical quantity of the absolute value of its first derivative, the quantitative evaluation of the change intensity of water quality monitoring data is realized, which provides a basis for identifying the area with unstable water quality state.

[0091] See Figure 6 A flowchart for determining the comprehensive evaluation parameter is provided for the embodiments of the present application, as shown in Figure 6 The method of the embodiments of the present application can include the following step S601, which can be further refined as the step of "fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area to obtain the comprehensive evaluation parameter of each grid area".

[0092] S601, according to the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area are weighted and summed to obtain the comprehensive evaluation parameter of each grid area; wherein the sum of the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient is 1.

[0093] Specifically, considering the need for quantitative comprehensive of multi-dimensional indicators, the embodiments propose a weighted summation method to determine the comprehensive evaluation parameter.

[0094] First, according to the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient, the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area are weighted and summed to obtain the comprehensive evaluation parameter of each grid area. Among them, the preset first weight coefficient refers to the weight value set for the first evaluation parameter, which is used to represent the importance of spatial prediction uncertainty in comprehensive evaluation; the preset second weight coefficient refers to the weight value set for the second evaluation parameter, which is used to represent the importance of spatial representativeness in comprehensive evaluation; the preset third weight coefficient refers to the weight value set for the third evaluation parameter, which is used to represent the importance of change intensity in comprehensive evaluation.

[0095] Regarding this step, in some possible implementation manners, the first evaluation parameter of each grid area can be multiplied by the preset first weight coefficient, the second evaluation parameter can be multiplied by the preset second weight coefficient, and the third evaluation parameter can be multiplied by the preset third weight coefficient. Then the result of multiplying the three is summed to obtain the comprehensive evaluation parameter of each grid area.

[0096] In some possible implementations, the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient can be determined according to the monitoring target's emphasis on the spatial coverage, representativeness and dynamic change capture by using the analytic hierarchy process or expert scoring method, and then the specific values of the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient are used for weighted summation calculation.

[0097] Exemplarily, for any one grid region in the target water area , the first evaluation parameter , the second evaluation parameter and the third evaluation parameter of the grid region are weighted and summed to obtain the comprehensive evaluation parameter of the grid region. The calculation formula is as follows: ; wherein, the first evaluation parameter of the grid region is , the second evaluation parameter of the grid region is , and the third evaluation parameter of the grid region is . The preset first weight coefficient is , the preset second weight coefficient is , and the preset third weight coefficient is , and the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient satisfy . For example, different weight values can be set according to the monitoring target's emphasis on the spatial coverage, representativeness and dynamic change capture, such as

[0098] In this embodiment, by setting the weights of the evaluation parameters of different dimensions and performing weighted summation, the comprehensive quantitative evaluation of the grid region monitoring value is realized, and a unified and comparable decision basis is provided for subsequent region selection.

[0099] Please refer to Figure 7 , which provides a flowchart for determining a device layout region, as shown in Figure 7 , the method of the embodiment of the present application can include the following steps S701-S702, and the steps S701-S702 can be further refined as the step of "determining a device layout region in the target water area according to the comprehensive evaluation parameter of each grid region".

[0100] S701, according to the comprehensive evaluation parameter of each grid region, the preset greedy algorithm and the preset upper limit number, iteratively select the grid region with the largest comprehensive evaluation parameter in the grid region of the target water area to join the device layout region set until the number of grid regions in the device layout region set reaches the preset upper limit number; S702, determine the grid regions in the device deployment region set as device deployment regions.

[0101] Specifically, considering the demand for achieving a better region selection under limited resources, the embodiment proposes a scheme for determining device deployment regions based on an iterative optimization strategy.

[0102] First, according to the comprehensive evaluation parameter of each grid region, the preset greedy algorithm and the preset upper limit, the grid region with the maximum comprehensive evaluation parameter is selected from the grid regions of the target water area to join the device deployment region set in an iterative manner, until the number of grid regions in the device deployment region set reaches the preset upper limit. The preset greedy algorithm refers to an algorithm that selects the best or optimal choice in the current state at each step, so as to expect to result in a globally best or optimal result. The preset upper limit refers to the maximum number of water quality monitoring devices allowed to be deployed, that is, the total number of finally selected device deployment regions. The device deployment region set refers to a set for storing grid regions selected as device deployment locations.

[0103] Regarding this step, in some possible implementation manners, an empty device deployment region set can be initialized, and then the selection operation is repeatedly performed until the number of grid regions in the device deployment region set reaches the preset upper limit, wherein each selection operation includes selecting a grid region with the maximum comprehensive evaluation parameter from the grid regions in the target water area that have not been selected into the device deployment region set, and adding it to the device deployment region set.

[0104] In some possible implementation manners, after each grid region with the maximum comprehensive evaluation parameter is selected to join the device deployment region set, the comprehensive evaluation parameters of the unselected grid regions in the neighborhood of the selected grid region can be updated to reduce the probability of re-selection of the regions near the newly selected grid region, so as to avoid excessive concentration of deployment points in the iterative process and improve the rationality of spatial distribution.

[0105] Further, the grid regions in the device deployment region set are determined as device deployment regions.

[0106] Regarding this step, in some possible implementation manners, after the iterative selection process is completed, all the grid regions contained in the finally obtained device deployment region set can be collectively determined as the final device deployment regions.

[0107] Exemplarily, it is assumed that the target water area contains grid regions, each grid region has a comprehensive evaluation parameter , the preset upper limit is , and First, an empty set of device deployment areas is initialized , i.e. Then, the first iteration selection is performed. From all grid areas, the grid area with the maximum comprehensive evaluation parameter is selected, denoted as , and added to the set of device deployment areas , at this time After adding , according to the preset spatial influence rule, the comprehensive evaluation parameters of the unselected grid areas in the neighborhood of are updated, for example, for any unselected grid area in the neighborhood of , the comprehensive evaluation parameter thereof is updated to , where is a decay coefficient, which can be dynamically adjusted according to the spatial distance between and , so as to reduce the probability of the area near being selected again in the subsequent iterations. Next, the second iteration selection is performed. From the remaining unselected grid areas, the grid area with the maximum updated comprehensive evaluation parameter is selected, denoted as , and added to the set of device deployment areas , at this time Similarly, the comprehensive evaluation parameters of the unselected grid areas in the neighborhood of are updated. The iteration selection and updating process is repeated, each time the grid area with the maximum current comprehensive evaluation parameter is selected from the unselected grid areas and added to the set of device deployment areas , and the comprehensive evaluation parameters of the neighborhood thereof are updated. When the number of grid areas in the set of device deployment areas reaches the preset upper limit , i.e. , the iteration process ends. Finally, the grid areas contained in the set of device deployment areas are the determined device deployment areas.

[0108] In this embodiment, the greedy algorithm is used for iteration selection, which can efficiently filter out a grid area combination with high comprehensive value from a large number of candidate grid areas, and ensure that the monitoring efficiency is improved under the condition of limited device quantity.

[0109] In an embodiment, after determining the device deployment area in the target water area, in each determined device deployment area, a suitable installation point is selected according to the actual situation. Then, the water quality monitoring device is deployed at the installation point. The deployment method can be selected according to the specific scene, for example, for lakes or reservoirs, an anchor buoy type deployment can be used; for rivers or near sewage outlets, a fixed pile foundation type deployment can be used. After completing the physical installation, the water quality monitoring device is initially configured, including inputting the unique identification code of the device deployment area, setting the device operation parameters, and calibrating the sensor module. At the same time, the geographic coordinates of the water quality monitoring device are recorded and stored as the basis for subsequent data space location association.

[0110] After initial configuration is completed, the water quality monitoring device enters an automatic working mode. The sensor module built-in the device measures the water environment at its location in situ according to the preset collection frequency, for example, once an hour, thereby obtaining raw water quality monitoring data. The raw water quality monitoring data can include multiple water quality parameters, such as dissolved oxygen, pH value, turbidity, conductivity, chemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, and chlorophyll a concentration. After each data collection is completed, the main control module of the device automatically adds an accurate time stamp for the batch of data and binds it with the recorded geographic coordinates, generating a water quality monitoring data stream with clear spatio-temporal attributes. To ensure the safety and integrity of the data before transmission, the device can locally compress and cache store the data within a certain time window, for example, 24 hours of data.

[0111] The water quality monitoring device transmits the locally cached water quality monitoring data to the remote data center or cloud platform regularly or in real time through the integrated communication module. The data transmission protocol can be selected according to the network conditions on site, for example, TCP / IP protocol can be used in areas with good 4G / 5G network coverage, and satellite communication or low-power wide-area network technology can be used in remote water areas. During data transmission, the device will encrypt the data packets to ensure the safety of the data during public network transmission. In addition, the device can also receive remote instructions from the data center, such as adjusting the collection frequency, updating the firmware program, or performing an immediate state self-check, thereby realizing the remote centralized management of distributed water quality monitoring devices.

[0112] The remote data center or cloud platform receives the water quality monitoring data, first performs data analysis and decryption, and restores the original data stream with space-time tags. Subsequently, the system performs a series of verification operations on the received data, including checking the integrity of the data packet, verifying the validity of the time stamp and geographic coordinates, and identifying abnormal values caused by sensor failure or environmental interference. The verified data will be cleaned, formatted, and stored in a time series database or a spatial database according to the preset data model, integrated with historical water quality data, geographic information data, and pollution source distribution data of the target water area, providing standardized and high-quality data sets for subsequent water quality spatio-temporal dynamic analysis, pollution source tracing, and early warning model construction.

[0113] The following will be combined Figure 8 The device layout area determination device 800 provided by the embodiments of the present application will be described in detail. The device layout area determination device 800 can be mutually corresponding to the device layout area determination method described above. It should be noted that Figure 8 The device layout area determination device 800 in the method provided by the embodiments of the present application is used to execute the method of the embodiments of the present application Figure 1 Figure 7 The method of the embodiments shown in the embodiments is only shown with the parts related to the embodiments of the present application for the convenience of description, and the specific technical details not disclosed are please refer to the embodiments shown in the embodiments of the present application. Specifically, the device layout area determination device 800 can include a first acquisition module 810, a second acquisition module 820, a parameter fusion module 830, and a region determination module 840, as follows: Figure 1 Figure 7 The device layout area determination device 800 can include a first acquisition module 810, a second acquisition module 820, a parameter fusion module 830, and a region determination module 840, as follows: The first acquisition module 810 is configured to acquire water quality monitoring data of each grid region in the target water area. The second acquisition module 820 is configured to acquire a first evaluation parameter, a second evaluation parameter, and a third evaluation parameter of each grid region according to the water quality monitoring data of each grid region. The first evaluation parameter is used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid region. The second evaluation parameter is used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid region to the water quality monitoring data of the surrounding grid region. The third evaluation parameter is used to represent the change intensity of the water quality monitoring data of the corresponding grid region. The parameter fusion module 830 is configured to fuse the first evaluation parameter, the second evaluation parameter, and the third evaluation parameter of each grid region, respectively, to obtain a comprehensive evaluation parameter of each grid region. The region determination module 840 is configured to determine a device layout area in the target water area according to the comprehensive evaluation parameter of each grid region. The device layout area is used to layout a water quality monitoring device.

[0114] Optionally, in some embodiments, the second acquisition module 820 is further configured to:​​ performing spatial prediction uncertainty analysis on the water quality monitoring data of each grid region to obtain a first evaluation parameter of each grid region; performing spatial representative analysis on the water quality monitoring data of each grid region to obtain a second evaluation parameter of each grid region; performing change intensity analysis on the water quality monitoring data of each grid region to obtain a third evaluation parameter of each grid region.

[0115] Optionally, in some embodiments, the second acquisition module 820 is further configured to: determining, according to the water quality monitoring data of each grid region, a prediction variance of each grid region by using a preset Kriging interpolation algorithm; determining, according to the prediction variance of each grid region, an information entropy of each grid region; determining, according to the information entropy of each grid region, the first evaluation parameter of each grid region.

[0116] Optionally, in some embodiments, the second acquisition module 820 is further configured to: determining, in the target water area, a surrounding grid region of each grid region; acquiring, according to the water quality monitoring data of each grid region, water quality monitoring estimation data of the surrounding grid region of each grid region; determining, according to the water quality monitoring data and the water quality monitoring estimation data of the surrounding grid region of each grid region, a mean square error of the surrounding grid region of each grid region; determining, according to the mean square error of the surrounding grid region of each grid region, the second evaluation parameter of each grid region.

[0117] Optionally, in some embodiments, the second acquisition module 820 is further configured to: determining, according to the water quality monitoring data of each grid region, a time series function of each grid region; performing first-order derivation on the time series function of each grid region respectively and taking absolute values to obtain a first-order derivative absolute value corresponding to the time series function of each grid region; determining, according to the first-order derivative absolute value corresponding to the time series function of each grid region, the third evaluation parameter of each grid region.

[0118] Optionally, in some embodiments, the parameter fusion module 830 is further configured to: performing weighted summation on the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid region respectively according to a preset first weight coefficient, a preset second weight coefficient and a preset third weight coefficient to obtain a comprehensive evaluation parameter of each grid region; The sum of the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient is 1.

[0119] Optionally, in some embodiments, the region determination module 840 is further configured to: According to the comprehensive evaluation parameter of each grid region, a preset greedy algorithm and a preset upper limit number, iteratively select a grid region with the largest comprehensive evaluation parameter in the grid regions of the target water area to add to the device layout region set until the number of grid regions in the device layout region set reaches the preset upper limit number. Determine the grid regions in the device layout region set as the device layout regions.

[0120] The effects that can be achieved by the present embodiment are described in the related embodiments of the device layout region determination method above, which will not be repeated here.

[0121] Figure 9 An example of a schematic diagram of the physical structure of an electronic device is shown in FIG. 8. Figure 9 As shown in FIG. 8, the electronic device can include a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902 and the memory 903 can communicate with each other through the communication bus 904. The processor 901 can invoke the computer program in the memory 903 to execute the steps of the device layout region determination method, for example, including: Obtain water quality monitoring data of each grid region in the target water area; According to the water quality monitoring data of each grid region, obtain a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each grid region, the first evaluation parameter being used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid region, the second evaluation parameter being used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid region to the water quality monitoring data of the surrounding grid regions, and the third evaluation parameter being used to represent the change intensity of the water quality monitoring data of the corresponding grid region; Fuse the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid region respectively to obtain a comprehensive evaluation parameter of each grid region; According to the comprehensive evaluation parameter of each grid region, determine a device layout region in the target water area, the device layout region being used to layout a water quality monitoring device.

[0122] Moreover, the logic instructions in the memory described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the method of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0123] In another aspect, the embodiments of the present application also provide a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the steps of the device layout area determination method provided by the above-mentioned embodiments, for example, including: obtaining water quality monitoring data of each grid area in a target water area; According to the water quality monitoring data of each grid area, obtaining a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each grid area, the first evaluation parameter is used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid area, the second evaluation parameter is used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid area to the surrounding grid area, and the third evaluation parameter is used to represent the change intensity of the water quality monitoring data of the corresponding grid area; Fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area respectively, to obtain a comprehensive evaluation parameter of each grid area; According to the comprehensive evaluation parameter of each grid area, determining a device layout area in the target water area, and the device layout area is used to layout a water quality monitoring device.

[0124] In another aspect, the embodiments of the present application also provide a processor readable storage medium, which stores a computer program, and the computer program is used to make the processor execute the steps of the method provided by the above-mentioned embodiments, for example, including: obtaining water quality monitoring data of each grid area in a target water area; According to the water quality monitoring data of each grid area, a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each grid area are obtained, the first evaluation parameter is used to represent the spatial prediction uncertainty of the water quality monitoring data of the corresponding grid area, the second evaluation parameter is used to represent the spatial representativeness of the water quality monitoring data of the corresponding grid area to the water quality monitoring data of the surrounding grid area, and the third evaluation parameter is used to represent the change intensity of the water quality monitoring data of the corresponding grid area; The first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area are fused respectively to obtain a comprehensive evaluation parameter of each grid area. According to the comprehensive evaluation parameter of each grid area, a device layout area is determined in the target water area, and the device layout area is used to layout a water quality monitoring device.

[0125] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to a magnetic memory (such as a floppy disk, a hard disk, a magnetic tape, a magneto-optical disk (MO), etc.), an optical memory (such as a CD, a DVD, a BD, a HVD, etc.), and a semiconductor memory (such as a ROM, an EPROM, an EEPROM, a non-volatile memory (NAND FLASH), a solid state disk (SSD)), etc.

[0126] The device embodiments described above are only schematic, wherein the units illustrated as separate components can or can not be physically separated, and the components illustrated as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments. Those skilled in the art can understand and implement without creative labor.

[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software plus necessary general hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of the embodiments or some parts of the embodiments.

[0128] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for 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 embodiments of the present application.

Claims

1. A method for determining an equipment deployment area, characterized in that, The method comprises the following steps: acquiring water quality monitoring data of each grid area in a target water area; acquiring a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each grid area according to the water quality monitoring data of each grid area, the first evaluation parameter being used to represent spatial prediction uncertainty of the water quality monitoring data of the corresponding grid area, the second evaluation parameter being used to represent spatial representativeness of the water quality monitoring data of the corresponding grid area to the water quality monitoring data of the surrounding grid areas, and the third evaluation parameter being used to represent variation intensity of the water quality monitoring data of the corresponding grid area; fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area respectively to obtain a comprehensive evaluation parameter of each grid area; determining a device layout area in the target water area according to the comprehensive evaluation parameter of each grid area, the device layout area being used to layout a water quality monitoring device.

2. The method of claim 1, wherein, The step of acquiring the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each grid area according to the water quality monitoring data of each grid area comprises the following steps: performing spatial prediction uncertainty analysis according to the water quality monitoring data of each grid area to obtain the first evaluation parameter of each grid area; performing spatial representativeness analysis according to the water quality monitoring data of each grid area to obtain the second evaluation parameter of each grid area; performing variation intensity analysis according to the water quality monitoring data of each grid area to obtain the third evaluation parameter of each grid area.

3. The method of claim 2, wherein, The step of performing spatial prediction uncertainty analysis according to the water quality monitoring data of each grid area to obtain the first evaluation parameter of each grid area comprises the following steps: determining a prediction variance of each grid area by using a preset Kriging interpolation algorithm according to the water quality monitoring data of each grid area; determining an information entropy of each grid area according to the prediction variance of each grid area; determining the first evaluation parameter of each grid area according to the information entropy of each grid area.

4. The method of claim 2, wherein, The step of performing spatial representativeness analysis according to the water quality monitoring data of each grid area to obtain the second evaluation parameter of each grid area comprises the following steps: determining surrounding grid areas of each grid area in the target water area; acquiring water quality monitoring estimation data of the surrounding grid areas of each grid area according to the water quality monitoring data of each grid area; determining a mean square error of the surrounding grid areas of each grid area according to the water quality monitoring data and the water quality monitoring estimation data of the surrounding grid areas of each grid area; determining the second evaluation parameter of each grid area according to the mean square error of the surrounding grid areas of each grid area.

5. The method of claim 2, wherein, The step of performing variation intensity analysis according to the water quality monitoring data of each grid area to obtain the third evaluation parameter of each grid area comprises the following steps: determining a time series function of each grid area according to the water quality monitoring data of each grid area; respectively, to each of the grid regions, and taking absolute values, to obtain a first-order derivative absolute value corresponding to a time series function of each of the grid regions; determine a third evaluation parameter of each of the grid regions according to the first-order derivative absolute value corresponding to the time series function of each of the grid regions.

6. The method of claim 1, wherein, The step of fusing the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each of the grid regions respectively to obtain a comprehensive evaluation parameter of each of the grid regions comprises: perform weighted summation on the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each of the grid regions respectively according to a preset first weight coefficient, a preset second weight coefficient and a preset third weight coefficient, to obtain the comprehensive evaluation parameter of each of the grid regions; wherein the sum of the preset first weight coefficient, the preset second weight coefficient and the preset third weight coefficient is 1.

7. The method of claim 1, wherein, The step of determining the equipment deployment region in the target water area according to the comprehensive evaluation parameter of each of the grid regions comprises: iteratively select a grid region with the largest corresponding comprehensive evaluation parameter in the grid regions of the target water area to add to a set of equipment deployment regions according to the comprehensive evaluation parameter of each of the grid regions, a preset greedy algorithm and a preset upper limit number, until the number of grid regions in the set of equipment deployment regions reaches the preset upper limit number; determine the grid regions in the set of equipment deployment regions as the equipment deployment region.

8. An apparatus for determining a device deployment area, the apparatus comprising: a device deployment area determination module configured to determine a device deployment area based on a device location and a device orientation. comprise: a first acquisition module configured to acquire water quality monitoring data of each grid region in a target water area; a second acquisition module configured to acquire a first evaluation parameter, a second evaluation parameter and a third evaluation parameter of each of the grid regions according to the water quality monitoring data of each of the grid regions, the first evaluation parameter being used to represent spatial prediction uncertainty of the water quality monitoring data of the corresponding grid region, the second evaluation parameter being used to represent spatial representativeness of the water quality monitoring data of the corresponding grid region to the water quality monitoring data of the surrounding grid regions, and the third evaluation parameter being used to represent variation intensity of the water quality monitoring data of the corresponding grid region; a parameter fusion module configured to fuse the first evaluation parameter, the second evaluation parameter and the third evaluation parameter of each of the grid regions respectively to obtain a comprehensive evaluation parameter of each of the grid regions; a region determination module configured to determine an equipment deployment region in the target water area according to the comprehensive evaluation parameter of each of the grid regions, the equipment deployment region being used to deploy a water quality monitoring device.

9. An electronic device comprising a processor and a memory having a computer program stored therein, characterized in that, The processor executes the computer program to implement the steps of the method for determining the equipment deployment region according to any one of claims 1 to 7. 10.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method for determining the equipment deployment region according to any one of claims 1 to 7.

Images