Digitized city irrigation district information classification retrieval method

Abstract

The invention relates to the technical field of irrigation district information classification and retrieval, in particular to a digital city irrigation district information classification and retrieval method, which comprises the following steps: acquiring various key data in each irrigation district, calculating the performance excellence of each key data in each irrigation district, and further determining the comprehensive performance excellence of each irrigation district; obtaining the position coordinates of each irrigation area, and determining the performance similarity between every two irrigation areas according to the position coordinates of each irrigation area and the comprehensive performance excellence; clustering the irrigation districts according to the performance similarity, and determining the coordination similarity between the irrigation district to be coordinated and other irrigation districts which are in the same class cluster with the irrigation district to be coordinated; and ranking the coordination similarities from high to low, and marking the irrigation areas corresponding to the coordination similarities ranked in the top preset number as coordinated irrigation areas of the to-be-coordinated irrigation areas. According to the method, all irrigation areas can be finely classified, and the optimal coordinated irrigation area can be accurately matched for each irrigation area.

Description

Technical Field

[0001] The present invention relates to the technical field of irrigation district information classification and retrieval, and in particular to an irrigation district information classification and retrieval method for a digital city. Background Art

[0002] The classification and retrieval method of irrigation district information in digital cities is a new management model developed on the basis of traditional irrigation district management combined with modern information technology. Its core lies in the use of advanced water conservancy, information, control and decision-making technologies to realize the modernization of irrigation district management. This method can not only significantly improve the management level and service capabilities of irrigation districts, but also better serve the needs of irrigation district management and guide irrigation district management practices.

[0003] In the current process of digital city construction, the classification and management of irrigation district information plays a vital role, which is directly related to the effective allocation of water resources, the efficiency of agricultural production and the balance of the ecological environment. Traditionally, the classification of irrigation district information mainly relies on geographical location information, such as division according to administrative divisions, watershed ranges or natural attributes such as topography and landforms. Even if different irrigation districts are geographically close, the operating performance of two irrigation districts may be different due to differences in water source quality, irrigation facilities, etc. Therefore, the existing technology of irrigation district classification by geographical location has certain limitations. Although it is intuitive and easy to implement, it cannot fully reflect the diversity and complexity of irrigation districts, which will lead to insufficiently detailed and comprehensive classification, and directly affect the efficiency and accuracy of subsequent irrigation district information retrieval.

[0004] When it is necessary to quickly locate specific irrigation district information to support decision-making, resource allocation or disaster response, if the classification system cannot provide sufficiently detailed and comprehensive classification labels, users may need to spend more time screening and comparing a large amount of irrelevant information, which not only reduces work efficiency but also may delay the best time to act. In addition, inefficient information retrieval mechanisms will aggravate the irrationality of resource allocation. In irrigation district management, the effective allocation of resources is the key to ensuring agricultural production, promoting water conservation and efficiency, and maintaining ecological balance. If the information classification and retrieval system cannot accurately reflect the actual needs of the irrigation district, it may lead to resource mismatch, such as over-allocating limited water resources to less efficient irrigation districts, while ignoring those more efficient or potential irrigation districts that need support, thereby hindering the sustainable development of the entire irrigation district system. Summary of the invention

[0005] In order to solve the technical problem that the irrigation district classification is not detailed and there is no effective coordination and scheduling method, the purpose of the present invention is to provide a classification and retrieval method for irrigation district information in a digital city. The technical solution adopted is as follows: Obtaining various key data in each irrigation area, and calculating the performance excellence of various key data in each irrigation area; Determine the comprehensive performance excellence of each irrigation area according to the performance excellence of each of the key data in each irrigation area; Acquire the location coordinates of each of the irrigation areas, and determine the performance similarity between any two irrigation areas according to the location coordinates of each of the irrigation areas and the comprehensive performance excellence; Clustering the irrigation areas according to the performance similarity, and determining the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated; The coordination similarities are ranked from high to low, and the irrigation areas corresponding to the coordination similarities ranked in front of a preset number are marked as coordinated irrigation areas of the irrigation areas to be coordinated.

[0006] Furthermore, the calculation of the performance excellence of each of the key data in each of the irrigation areas includes: Acquire at least two data of any of the key data of any of the irrigation areas to form a time series fluctuation curve and calculate the slope value of the time series fluctuation curve; Calculate the difference between two adjacent data in the key data, where the difference is the latter data minus the former data in the two adjacent data; Obtain the number of the difference values ​​having different positive and negative signs from the slope value, and record the number as the difference number; Obtaining the performance excellence of the key data according to the slope value, the number of differences, and the number of difference values; The process of obtaining the performance excellence is repeated to calculate the performance excellence of each of the key data in each irrigation area.

[0007] Further, calculating the slope value of the time series fluctuation curve includes: Obtaining the first data point and the last data point at the beginning and the end of the time series fluctuation curve; The slope of the straight line connecting the head data point and the tail data point is used as the slope value of the time series fluctuation curve.

[0008] Further, obtaining the performance excellence of the key data according to the slope value, the number of differences, and the number of differences includes: After multiplying the slope value by the number of differences, the resultant is divided by the number of differences to obtain a subtrahend; The performance goodness is obtained by subtracting the subtrahend from the slope value.

[0009] Further, determining the comprehensive performance excellence of each irrigation area according to the performance excellence of each key data in each irrigation area includes: Taking the average of the performance excellence of each key data of any irrigation area as the comprehensive performance excellence of any irrigation area; The process of obtaining the comprehensive performance excellence is repeated to determine the comprehensive performance excellence of each irrigation area.

[0010] Further, determining the performance similarity between two irrigation areas according to the location coordinates of each irrigation area and the comprehensive performance excellence includes: Obtaining the first Euclidean distance between the location coordinates of any irrigation area and the location coordinates of another irrigation area; Obtaining an absolute value of a difference between the comprehensive performance excellence of any one irrigation area and the comprehensive performance excellence of another irrigation area; Taking the reciprocal of the first Euclidean distance to obtain a first reciprocal; Add the absolute value to the preset first value and then take the reciprocal to obtain a second reciprocal; The first inverse is multiplied by the second inverse to obtain the performance similarity between any one irrigation area and the other irrigation area.

[0011] Furthermore, clustering the irrigation areas according to the performance similarity includes: The irrigation areas are clustered according to the performance similarities using a K-means algorithm, wherein the number of clusters of the clustering is determined by a silhouette coefficient method.

[0012] Furthermore, the determining of the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated includes: Obtaining a weight value of the jth key data of the irrigation area to be coordinated, a first real-time value of the jth key data of the irrigation area to be coordinated, and a second real-time value of the jth key data of another irrigation area in the same cluster as the irrigation area to be coordinated; Obtaining a second Euclidean distance between the first real-time value and the second real-time value; Add a preset second value to the second Euclidean distance, take the reciprocal, and multiply the result by the weight value to obtain a first product; Repeating the process of obtaining the first product to obtain the first product corresponding to each key data of the irrigation area to be coordinated; A first average value of the first products corresponding to each key data of the irrigation area to be coordinated is obtained as the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated.

[0013] Furthermore, the step of obtaining the weight value of the jth key data of the irrigation area to be coordinated includes: Determine the reference weight values ​​corresponding to different key data according to the scheduling method; Obtaining the performance excellence of the jth key data of the irrigation area to be coordinated and a second average value of the performance excellence of the key data in the irrigation area to be coordinated; The performance excellence of the j-th key data is divided by the second average value and then multiplied by the reference weight value to obtain the weight value of the j-th key data of the irrigation area to be coordinated.

[0014] Further, the determining of reference weight values ​​corresponding to different key data according to the scheduling mode includes: The reference weight value of the key data that matches the preset scheduling mode is set as the first reference value, and the reference weight values ​​of the remaining key data are set as the second reference value.

[0015] The present invention has the following beneficial effects: First, the comprehensive performance of each irrigation area is determined according to the performance of each of the key data in each irrigation area. The comprehensive performance is used to compare the similarity between different irrigation areas. That is, the more consistent the comprehensive performance of two irrigation areas is, the more similar they are. Secondly, the location coordinates of each irrigation area are obtained, and the performance similarity between two irrigation areas is determined according to the location coordinates of each irrigation area and the comprehensive performance. The performance similarity between two irrigation areas is obtained for subsequent classification, and irrigation areas with high performance similarity can be classified into one category. Furthermore, the irrigation areas are clustered according to the performance similarity to determine the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated. Here, all irrigation areas are divided into several clusters according to the performance similarity. When the irrigation areas need to be coordinated and scheduled in the future, only the irrigation areas in the same cluster need to be searched. In each cluster, the possibility of another tank area that can be coordinated with a certain irrigation area in resource allocation and scheduling is selected. That is, the higher the coordination similarity, the greater the possibility. Finally, the coordination similarity is ranked from high to low, and the irrigation areas corresponding to the preset number of coordination similarities ranked in the front are marked as the coordination irrigation areas of the irrigation areas to be coordinated. The irrigation areas corresponding to the coordination similarities ranked in the top are selected as the coordination irrigation areas, and the coordination irrigation areas are the irrigation areas that can be coordinated with the irrigation areas to be coordinated in terms of resource allocation and scheduling. In summary, the present application can achieve a refined classification of all irrigation areas based on a number of key data and location coordinates of each irrigation area, ensure accurate classification, and avoid general divisions. In addition, in the process of coordinated scheduling between irrigation areas, the present application can also accurately match the optimal coordination irrigation area for each irrigation area, thereby significantly improving the operating efficiency and overall effectiveness of the irrigation area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of a method for classifying and retrieving irrigation district information in a digital city provided by the first embodiment of the present invention; Figure 2 A flowchart of a performance excellence acquisition process provided by the second embodiment of the present invention; Figure 3 A flowchart of a performance similarity acquisition process provided by the third embodiment of the present invention; Figure 4 A flowchart of a coordination similarity acquisition process provided by a fourth embodiment of the present invention; Figure 5 This is a flow chart of obtaining the weight value of the j-th key data of the irrigation area to be coordinated provided by the fifth embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a digital city irrigation area information classification retrieval method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the irrigation area information classification and retrieval method for a digital city provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of a method for classified retrieval of irrigation district information in a digital city provided by an embodiment of the present invention, the method comprising: S101. Acquire various key data in each irrigation area, and calculate the performance excellence of each key data in each irrigation area.

[0022] An irrigation area refers to the beneficiary area of ​​a water conservancy and irrigation project. It is usually an area that draws water from one or several water sources and has a complete water transmission, distribution, irrigation and drainage engineering system. It can provide irrigation and drainage services according to the needs of crops and taking into account the carrying capacity of water resources and the environment.

[0023] The key data include but are not limited to: location coordinates, water quality conditions, crop planting conditions, and irrigation water consumption.

[0024] The performance excellence acquisition process will be described in detail in the second embodiment and will not be repeated here.

[0025] Since each irrigation area will have changes in key data due to climate change, changes in agricultural production patterns, etc., the key data of each irrigation area is constantly changing with time. Therefore, firstly, the performance change of each irrigation area is determined based on the changes in key data obtained at different statistical times for each irrigation area.

[0026] S102. Determine the comprehensive performance excellence of each irrigation area according to the performance excellence of each of the key data in each irrigation area.

[0027] Specifically, determining the comprehensive performance excellence of each irrigation area according to the performance excellence of each key data in each irrigation area includes: Taking the average of the performance excellence of each key data of any irrigation area as the comprehensive performance excellence of any irrigation area; The process of obtaining the comprehensive performance excellence is repeated to determine the comprehensive performance excellence of each irrigation area.

[0028] The comprehensive performance can be expressed by the formula: ; Among them, the represents the comprehensive performance excellence, N represents the number of key data, represents the performance excellence of the nth key data, and m represents the mth irrigation area.

[0029] S103. Obtain the location coordinates of each of the irrigation areas, and determine the performance similarity between any two irrigation areas according to the location coordinates of each of the irrigation areas and the comprehensive performance excellence.

[0030] The performance similarity acquisition process will be described in detail in the third embodiment and will not be repeated here.

[0031] S104. Clustering the irrigation areas according to the performance similarity, and determining the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated.

[0032] Specifically, clustering the irrigation areas according to the performance similarity includes: The irrigation areas are clustered according to the performance similarities using a K-means algorithm, wherein the number of clusters of the clustering is determined by a silhouette coefficient method.

[0033] The performance of irrigation districts in each cluster is relatively similar, which means that multiple irrigation districts in the cluster may share the same water source or the surrounding ecological environment is relatively similar. Therefore, these multiple irrigation districts can be coordinated in the subsequent water resource allocation and scheduling.

[0034] Among them, the K-means algorithm and the silhouette coefficient method are both existing technologies and will not be described in detail here.

[0035] The coordination similarity acquisition process will be described in detail in the fourth embodiment and will not be repeated here.

[0036] After all irrigation areas are classified according to performance similarity, when different irrigation areas need to be coordinated and allocated in the future, the irrigation area information needs to be retrieved and scheduled. For example, if water resources need to be coordinated and scheduled for the bth irrigation area, when retrieving the irrigation area information, the information of other irrigation areas in the cluster where the bth irrigation area is located is retrieved, and the operation status of various key data of other irrigation areas at this time is analyzed to coordinate and schedule.

[0037] S105. Rank the coordination similarities from high to low, and mark the irrigation areas corresponding to the coordination similarities that rank in front of a preset number as the coordinated irrigation areas of the irrigation areas to be coordinated.

[0038] The preset number can be set independently and is not limited here, and is preferably 3.

[0039] The coordinated irrigation areas can be recommended to search personnel as search results, and the search personnel select the coordinated irrigation areas for coordinated scheduling based on the recommended results.

[0040] Figure 2 The flowchart of the performance excellence acquisition process provided by one embodiment of the present invention, wherein the calculation of the performance excellence of each of the key data in each irrigation area includes: S201. Obtain at least two data of any of the key data of any of the irrigation areas to form a time series fluctuation curve and calculate the slope value of the time series fluctuation curve.

[0041] Specifically, calculating the slope value of the time series fluctuation curve includes: Obtaining the first data point and the last data point at the beginning and the end of the time series fluctuation curve; The slope of the straight line connecting the head data point and the tail data point is used as the slope value of the time series fluctuation curve.

[0042] In addition, the average value of the slopes of the data points in the time series fluctuation curve may be used as the slope value of the time series fluctuation curve.

[0043] When the time series fluctuation curve is the time series fluctuation curve corresponding to the key data being the water quality condition, the slope of the time series fluctuation curve indicates whether the water quality condition is developing in a better direction or a worse direction. When the slope is positive, it indicates that the water quality of the irrigation area is developing in a better direction, and when the slope is negative, it indicates that the water quality of the irrigation area is developing in a worse direction.

[0044] S202. Calculate the difference between two adjacent data in the key data, where the difference is the value of the latter data minus the former data in the two adjacent data.

[0045] The number of data in the key data is R, and the number of differences is R-1.

[0046] S203. Obtain the number of the difference values ​​that have different positive and negative signs from the slope value, and record the number as the difference number.

[0047] S204. Obtain the performance excellence of the key data according to the slope value, the number of differences, and the number of difference values.

[0048] Specifically, obtaining the performance excellence of the key data according to the slope value, the number of differences, and the number of difference values ​​includes: After multiplying the slope value by the number of differences, the resultant is divided by the number of differences to obtain a subtrahend; The performance goodness is obtained by subtracting the subtrahend from the slope value.

[0049] The performance excellence can be expressed as: ; Among them, the represents the performance excellence of the nth key data, m represents the mth irrigation area, R represents the number of data in the key data, R-1 represents the number of differences, The slope value is the slope value corresponding to the nth key data of the mth irrigation area. Indicates the number of differences.

[0050] When the time series fluctuation curve is the time series fluctuation curve corresponding to the key data being the water quality condition, the The larger the value of is, the more drastic the fluctuation of the water quality in the mth irrigation area is, and the smaller the water quality performance of the corresponding mth irrigation area is. The larger the value of , the better the water quality of the mth irrigation area.

[0051] S205. Repeat the process of obtaining the performance excellence to calculate the performance excellence of each of the key data in each irrigation area.

[0052] That is to say, each key data of each irrigation area corresponds to a performance excellence.

[0053] Figure 3 A flowchart of a performance similarity acquisition process provided by an embodiment of the present invention, wherein determining the performance similarity between two irrigation areas according to the location coordinates of each irrigation area and the comprehensive performance excellence includes: S301. Obtain a first Euclidean distance between the location coordinates of any irrigation area and the location coordinates of another irrigation area.

[0054] The first Euclidean distance can be expressed as: ; Among them, the represents the location coordinates of the pth irrigation area, i.e., the irrigation area to be coordinated, represents the position coordinates of the qth irrigation area, i.e., the other irrigation area, represents the Euclidean distance function.

[0055] S302. Obtain the absolute value of the difference between the comprehensive performance excellence of any one irrigation area and the comprehensive performance excellence of another irrigation area.

[0056] The absolute value can be expressed as: ; Among them, the represents the comprehensive performance excellence of the pth irrigation area, i.e., any of the irrigation areas, represents the comprehensive performance excellence of the qth irrigation area, i.e., the other irrigation area, represents the absolute value function.

[0057] S303. Take the reciprocal of the first Euclidean distance to obtain a first reciprocal.

[0058] The first reciprocal can be expressed as: ; S304. Add a preset first value to the absolute value and then take the reciprocal to obtain a second reciprocal.

[0059] The second reciprocal can be expressed as: ; Said Represents the first value, preferably 1, and the purpose of setting is to exclude the case where the denominator is equal to 0.

[0060] S305. Multiply the first inverse by the second inverse to obtain the performance similarity between any one irrigation area and the other irrigation area.

[0061] The performance similarity can be expressed as: ; Among them, the represents the performance similarity between the p-th irrigation area, i.e., any one irrigation area, and the q-th irrigation area, i.e., another irrigation area.

[0062] Figure 4 A flowchart of a coordination similarity acquisition process provided by an embodiment of the present invention, wherein determining the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated comprises: S401. Obtain a weight value of the jth key data of the irrigation area to be coordinated, a first real-time value of the jth key data of the irrigation area to be coordinated, and a second real-time value of the jth key data of another irrigation area in the same cluster as the irrigation area to be coordinated.

[0063] The process of obtaining the weight value will be described in detail in the fifth embodiment and will not be repeated here.

[0064] S402. Obtain a second Euclidean distance between the first real-time value and the second real-time value.

[0065] The second Euclidean distance can be expressed as follows: ; in, It represents the real-time value of the jth key data in the bth irrigation area, i.e. the irrigation area to be coordinated. Similarly, it represents the real-time value of the jth key data of the yth irrigation area in the same cluster as the bth irrigation area, i.e., the irrigation area to be coordinated. represents the Euclidean distance function.

[0066] S403. Add a preset second value to the second Euclidean distance, take the reciprocal, and then multiply the result by the weight value to obtain a first product.

[0067] The first product can be expressed as: ; Among them, the represents the weight value of the jth key data in the bth irrigation area, i.e., the irrigation area to be coordinated. Represents the first value, preferably 1, and the purpose of setting is to exclude the case where the denominator is equal to 0.

[0068] S404. Repeat the process of obtaining the first product to obtain the first product corresponding to each key data of the irrigation area to be coordinated.

[0069] S405. Obtain a first average value of the first products corresponding to the key data of the irrigation area to be coordinated as the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated.

[0070] The coordination similarity can be expressed as: ; Among them, the represents the coordination similarity, the Indicates the number of key data.

[0071] According to the above method, the performance quality of each key data in the bth irrigation area can be calculated, and then the weight value of each key data can be determined according to the performance quality of each key data. The greater the performance quality of the key data, the more stable the key data is and the more it can represent the performance of the current irrigation area, and the corresponding weight value of the key data should be greater. Figure 5 The flowchart of obtaining the weight value of the j-th key data of the irrigation area to be coordinated provided in the fifth embodiment of the present invention includes: S501. Determine the reference weight values ​​corresponding to the different key data according to the scheduling method.

[0072] Specifically, determining the reference weight values ​​corresponding to different key data according to the scheduling mode includes: The reference weight value of the key data that matches the preset scheduling mode is set as the first reference value, and the reference weight values ​​of the remaining key data are set as the second reference value.

[0073] The scheduling methods include but are not limited to water scheduling methods, water quality scheduling methods, and ecological scheduling methods. The key data preset for each scheduling method is different. For example, when the scheduling method is water scheduling, the key data preset for matching may be water volume data, water level data, etc. When the scheduling method is ecological scheduling, the key data preset for matching may be location coordinates, soil quality data, etc.

[0074] Therefore, firstly, the key data required in each scheduling method are counted according to the previous knowledge, and then when the b-th irrigation area, i.e., the irrigation area to be coordinated, needs coordinated scheduling, the scheduling method required by the b-th irrigation area is first determined, and then the reference weight value of the key data preset to match the scheduling method is set as the first reference value, preferably , the reference weight value of other key data is set to the second reference value, preferably .

[0075] S502. Obtain the performance excellence of the j-th key data of the irrigation area to be coordinated and a second average value of the performance excellence of the key data in the irrigation area to be coordinated.

[0076] The second average value can be expressed as: ; Among them, the represents the performance excellence of the xth key data in the bth irrigation area, i.e., the irrigation area to be coordinated, Indicates the number of key data.

[0077] S503. After dividing the performance excellence of the j-th key data by the second average value, multiply the result by the reference weight value to obtain the weight value of the j-th key data of the irrigation area to be coordinated.

[0078] The weight value can be expressed as: ; Among them, the represents the weight value of the jth key data in the bth irrigation area, i.e., the irrigation area to be coordinated. represents the benchmark weight value of the jth key data, Indicates the performance quality of the jth key data of the bth irrigation area.

[0079] Said The larger the value of , the better the performance of the jth key data in the bth irrigation area is compared with other key data, and the corresponding weight value of the jth key data in the bth irrigation area should also be larger.

[0080] The present invention has the following beneficial effects: First, the comprehensive performance of each irrigation area is determined according to the performance of each of the key data in each irrigation area. The comprehensive performance is used to compare the similarity between different irrigation areas. That is, the more consistent the comprehensive performance of two irrigation areas is, the more similar they are. Secondly, the location coordinates of each irrigation area are obtained, and the performance similarity between two irrigation areas is determined according to the location coordinates of each irrigation area and the comprehensive performance. The performance similarity between two irrigation areas is obtained for subsequent classification, and irrigation areas with high performance similarity can be classified into one category. Furthermore, the irrigation areas are clustered according to the performance similarity to determine the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated. Here, all irrigation areas are divided into several clusters according to the performance similarity. When the irrigation areas need to be coordinated and scheduled in the future, only the irrigation areas in the same cluster need to be searched. In each cluster, the possibility of another tank area that can be coordinated with a certain irrigation area in resource allocation and scheduling is selected. That is, the higher the coordination similarity, the greater the possibility. Finally, the coordination similarity is ranked from high to low, and the irrigation areas corresponding to the preset number of coordination similarities ranked in the front are marked as the coordination irrigation areas of the irrigation areas to be coordinated. The irrigation areas corresponding to the coordination similarities ranked in the top are selected as the coordination irrigation areas, and the coordination irrigation areas are the irrigation areas that can be coordinated with the irrigation areas to be coordinated in terms of resource allocation and scheduling. In summary, the present application can achieve a refined classification of all irrigation areas based on a number of key data and location coordinates of each irrigation area, ensure accurate classification, and avoid general divisions. In addition, in the process of coordinated scheduling between irrigation areas, the present application can also accurately match the optimal coordination irrigation area for each irrigation area, thereby significantly improving the operating efficiency and overall effectiveness of the irrigation area.

[0081] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A classification and retrieval method for irrigation area information of a digital city, characterized in that: The method comprises: Obtaining various key data in each irrigation area, and calculating the performance excellence of various key data in each irrigation area; Determine the comprehensive performance excellence of each irrigation area according to the performance excellence of each of the key data in each irrigation area; Acquire the location coordinates of each of the irrigation areas, and determine the performance similarity between any two irrigation areas according to the location coordinates of each of the irrigation areas and the comprehensive performance excellence; Clustering the irrigation areas according to the performance similarity, and determining the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated; The coordination similarities are ranked from high to low, and the irrigation areas corresponding to the coordination similarities ranked in front of a preset number are marked as coordinated irrigation areas of the irrigation areas to be coordinated.

2. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 1, characterized in that: The calculation of the performance excellence of each of the key data in each of the irrigation areas includes: Acquire at least two data of any of the key data of any of the irrigation areas to form a time series fluctuation curve and calculate the slope value of the time series fluctuation curve; Calculate the difference between two adjacent data in the key data, where the difference is the latter data minus the former data in the two adjacent data; Obtain the number of the difference values ​​having different positive and negative signs from the slope value, and record the number as the difference number; Obtaining the performance excellence of the key data according to the slope value, the number of differences, and the number of difference values; The process of obtaining the performance excellence is repeated to calculate the performance excellence of each of the key data in each irrigation area.

3. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 2, characterized in that: Calculating the slope value of the time series fluctuation curve includes: Obtaining the first data point and the last data point at the beginning and the end of the time series fluctuation curve; The slope of the straight line connecting the head data point and the tail data point is used as the slope value of the time series fluctuation curve.

4. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 2, characterized in that: Acquiring the performance excellence of the key data according to the slope value, the number of differences, and the number of difference values ​​includes: After multiplying the slope value by the number of differences, the resultant is divided by the number of differences to obtain a subtrahend; The performance goodness is obtained by subtracting the subtrahend from the slope value.

5. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 1, characterized in that: The comprehensive performance of each irrigation area is determined based on the performance of each key data in each irrigation area, including: Taking the average of the performance excellence of each key data of any irrigation area as the comprehensive performance excellence of any irrigation area; The process of obtaining the comprehensive performance excellence is repeated to determine the comprehensive performance excellence of each irrigation area.

6. The method for classifying and retrieving irrigation district information of a digital city according to claim 1, characterized in that: Determining the performance similarity between two irrigation areas according to the location coordinates of each irrigation area and the comprehensive performance excellence includes: Obtaining the first Euclidean distance between the location coordinates of any irrigation area and the location coordinates of another irrigation area; Obtaining an absolute value of a difference between the comprehensive performance excellence of any one irrigation area and the comprehensive performance excellence of another irrigation area; Taking the reciprocal of the first Euclidean distance to obtain a first reciprocal; Add the absolute value to the preset first value and then take the reciprocal to obtain a second reciprocal; The first inverse is multiplied by the second inverse to obtain the performance similarity between any one irrigation area and the other irrigation area.

7. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 1, characterized in that: Clustering the irrigation areas according to the performance similarity includes: The irrigation areas are clustered according to the performance similarities using a K-means algorithm, wherein the number of clusters of the clustering is determined by a silhouette coefficient method.

8. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 1, characterized in that: The step of determining the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated comprises: Obtaining a weight value of the jth key data of the irrigation area to be coordinated, a first real-time value of the jth key data of the irrigation area to be coordinated, and a second real-time value of the jth key data of another irrigation area in the same cluster as the irrigation area to be coordinated; Obtaining a second Euclidean distance between the first real-time value and the second real-time value; Add a preset second value to the second Euclidean distance, take the reciprocal, and multiply the result by the weight value to obtain a first product; Repeating the process of obtaining the first product to obtain the first product corresponding to each key data of the irrigation area to be coordinated; A first average value of the first products corresponding to each key data of the irrigation area to be coordinated is obtained as the coordination similarity between the irrigation area to be coordinated and other irrigation areas in the same cluster as the irrigation area to be coordinated.

9. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 8, characterized in that: The step of obtaining the weight value of the jth key data of the irrigation area to be coordinated includes: Determine the reference weight values ​​corresponding to different key data according to the scheduling method; Obtaining the performance excellence of the jth key data of the irrigation area to be coordinated and a second average value of the performance excellence of the key data in the irrigation area to be coordinated; The performance excellence of the j-th key data is divided by the second average value and then multiplied by the reference weight value to obtain the weight value of the j-th key data of the irrigation area to be coordinated.

10. The method for classifying and retrieving irrigation district information of a digital city as claimed in claim 9, characterized in that: Determining the reference weight values ​​corresponding to different key data according to the scheduling method includes: The reference weight value of the key data that matches the preset scheduling mode is set as the first reference value, and the reference weight values ​​of the remaining key data are set as the second reference value.

Images