A land information surveying and mapping system based on the Internet of Things
Through the Internet of Things system, real-time collection and analysis of agricultural regional data, using cluster analysis to divide regions and generate management demand indexes, the problems of resource waste and imbalance in traditional agricultural management are solved, and refined resource regulation and efficient agricultural production are achieved. .
Patent Information
- Application Number
- CN202411219455.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-09-02
AI Technical Summary
Regional division and management in existing agricultural production rely on traditional experience, ignoring differences in land characteristics, resulting in the singularity and inaccuracy of management strategies, resulting in waste of resources and imbalance in crop yields.
The land information surveying and mapping system based on the Internet of Things collects soil and plant growth status information in real time through sensor networks, divides areas using cluster analysis, generates management demand indexes, and achieves refined resource regulation and management decisions.
The rational allocation and utilization of resources is achieved, the waste of water and fertilizer is avoided, crop yield and quality are improved, the efficiency and benefits of agricultural production are enhanced, and the accuracy of full consideration and management of differences in characteristics of each region is ensured.
Smart Images

Figure CN118733696B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of Internet of Things, and in particular to a land information surveying and mapping system based on the Internet of Things. Background Art
[0002] As a crucial component of today's information technology, the Internet of Things (IoT) is rapidly transforming traditional agricultural management models. By connecting various sensors, devices, and systems, the IoT enables real-time information collection, transmission, and processing, significantly improving the intelligence of agricultural production. IoT-based land mapping uses sensor networks deployed across diverse regions to collect key data such as soil conditions and plant growth status in real time. This data is transmitted and processed through the IoT, creating a comprehensive land information map.
[0003] Currently, regional division and management in agricultural production still rely on traditional experience and unified management strategies. This approach ignores the differences in land characteristics between different regions, such as soil composition, terrain slope, and light intensity, resulting in a single and inaccurate management strategy. For example, within a farmland, different areas may require different water and fertilizer management plans, and the existing unified fertilization, irrigation, or spraying methods are difficult to meet these differentiated needs. This "one-size-fits-all" management approach often results in a waste of resources, such as excessive water leading to soil erosion, or too little fertilizer affecting crop growth. At the same time, the inability to perform differentiated operations based on the actual conditions of specific regions may also lead to imbalances in crop yield and quality. Crop yields in some areas are low, making it difficult to maximize overall agricultural benefits. Summary of the Invention
[0004] In view of the shortcomings of the existing technology, the present invention provides a land information surveying and mapping system based on the Internet of Things, which solves the problems mentioned in the background technology.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a land information surveying and mapping system based on the Internet of Things, including a sensor network module, a data analysis module, a region division module, a management decision module, a feedback optimization module and a visualization module;
[0006] The sensor network module deploys IoT network sensors in several areas of the land, collects soil status information and plant growth status information through the deployed network sensors, and forms an IoT collection data group;
[0007] The data analysis module obtains the soil salt content factor by analyzing the IoT collected data group , plant growth status factors and soil active factors , which constitutes the feature vector of region i ;
[0008] The region division module is based on the acquired feature vector Use the cluster analysis method to divide the similarity and divide the regional feature vector Normalize the feature values and use the Euclidean distance to calculate the similarity distance between regions , obtain the set and cluster type of similar feature areas to form cluster data cm;
[0009] The management decision module analyzes the mean and standard deviation of the characteristics of the received cluster data cm and obtains the mean of the characteristics of the cluster data cm and characteristic standard deviation , and then get the management demand index after fitting ;
[0010] The feedback optimization module manages the demand index Notify and remind relevant personnel and implement management demand index Then perform real-time detection of the feature vector of region i And analyze to obtain feedback control index , according to the feedback control index Adaptive notification and prompt management demand index Adjustment results;
[0011] The visualization module is used to generate a comprehensive report visualization page for land management, and to display the status of the region and the status of the adjustment results in a visual manner, including using map and chart visualization tools to display the region division and generate a report on the region.
[0012] Preferably, the sensor network module includes an area division unit and a data acquisition and transmission unit;
[0013] The area division unit deploys relevant IoT sensors in each divided area to monitor and collect soil status information and plant growth status information in real time, including soil moisture sensors, laser ranging sensors, photosynthesis meters, temperature sensors, conductivity sensors, light sensors, and camera sensors;
[0014] The data acquisition and transmission unit collects soil status information and plant growth status information from the deployed network sensors to form an Internet of Things collection data group, including soil moisture , conductivity , soil temperature , concentration value , average plant height , plant leaf area and plant density .
[0015] Preferably, the data analysis module includes a vector analysis unit;
[0016] The vector analysis unit obtains the soil salt content factor by analyzing the IoT collected data group , plant growth status factors and soil active factors , which constitutes the feature vector of region i ;
[0017] Among them, the eigenvector of region i Specifically ={ , , }.
[0018] Preferably, the soil salt content factor Ssalt is obtained by the following calculation formula:
[0019] ;
[0020] Where, represents the conductivity, Indicates the soil temperature value, represents the temperature correction constant, and exp represents the exponential function;
[0021] The plant growth status factor Obtained through the following calculation formula:
[0022] ;
[0023] Where, Indicates concentration value Change value, represents the average height of plants, △H represents the peak value of plant height difference, represents the plant leaf area, T represents the fixed test period, Indicates plant density;
[0024] The soil active factor Obtained through the following calculation formula:
[0025] ;
[0026] Where, represents soil moisture, Eh represents redox potential, Correction constant for redox potential.
[0027] Preferably, the region division module includes a standardization unit and a cluster analysis unit;
[0028] The normalization unit obtains the feature vectors of all regions according to Use the cluster analysis method to divide the similarity and divide the feature vector of the region Perform eigenvalue standardization;
[0029] Among them, the eigenvalue normalization is processed by the following calculation formula:
[0030] ;
[0031] Where, represents the kth eigenvalue of region i after normalization, Represents the original eigenvalue, specifically the kth unstandardized eigenvalue of region i, represents the mean of the kth eigenvalue, represents the standard deviation of the kth eigenvalue;
[0032] The cluster analysis unit calculates the similarity distance between regions by using the Euclidean distance , by obtaining the similarity distance between each region Fill in the distance matrix elements to form the distance matrix D[i, j] of region i and region j, perform bubble sort on all distance matrices D[i, j] to obtain adjacent distance matrices D[i, j] and mark them as the cluster type of similar feature regions, specifically the cluster type of eigenvalue k type, to form cluster data cm, specifically cm=[ck, ck+1, ..., cm].
[0033] Preferably, the similarity distance Calculated using the following formula:
[0034] ;
[0035] Where, Represents the similarity distance, specifically the Euclidean distance between region i and region j, n represents the length of the feature vector, specifically the total number of eigenvalues included in the feature vector, k represents the feature factor index, the kth eigenvalue, represents the kth eigenvalue of region j after normalization.
[0036] Preferably, the management decision module includes a cluster processing unit and a management index unit;
[0037] The cluster processing unit analyzes the mean and standard deviation of the features according to the received cluster data cm to obtain the feature mean of the cluster data C and characteristic standard deviation ;
[0038] Among them, the characteristic mean Obtained through the following calculation formula:
[0039] ;
[0040] Where, It represents the feature mean of the mth set cluster type in the cluster data, specifically the mean of the kth feature in the cluster data cm, |cm| represents the total number of cluster data, specifically the length of the distance matrix that constitutes the cluster data cm, represents the kth eigenvalue of region i;
[0041] characteristic standard deviation Obtained through the following calculation formula:
[0042] ;
[0043] Where, Represents the characteristic standard deviation, specifically the characteristic standard deviation of the mth cluster type in the cluster data ;
[0044] The management index unit obtains the cluster data cm feature mean feature mean and characteristic standard deviation , and then get the management demand index after fitting .
[0045] Preferably, the management demand index Obtained through the following calculation formula:
[0046] ;
[0047] Where, Represents the management demand index, specifically the management demand of cluster data cm, including fertilization control, pesticide control and water control, Represents the feature mean The preset weight value of Represents the characteristic standard deviation The preset weight value of .
[0048] Preferably, the feedback optimization module includes a feedback notification unit and a feedback detection unit;
[0049] The feedback notification unit is based on the management demand index Matches with the preset management demand notification threshold XQ, obtains the management demand notification result, and notifies and prompts relevant personnel based on the management demand notification result. The notification includes mobile phone text messages, preset voice prompts, and interactive page pop-up prompts;
[0050] The management requirement notification result is obtained through the following matching method:
[0051] Management Demand Index <Management demand notification threshold XQ, obtain the management demand notification sending result;
[0052] Management Demand Index ≥ Management demand notification threshold XQ, no result is sent when obtaining management demand notification;
[0053] The feedback detection unit performs management demand index Then perform real-time detection of the feature vector of region i And analyze to obtain feedback control index , according to the feedback control index Management Demand Index pass Calculation formula for adaptive notification and prompt management demand index Adjustment results;
[0054] Feedback Regulation Index Obtained through the following calculation formula:
[0055] ;
[0056] Where, Executive Management Demand Index The feature vector of region i recorded later , Executive Management Demand Index Feature vector of region i recorded previously , Indicates the preset weight value for regulation.
[0057] Preferably, the visualization module includes a visualization unit;
[0058] The visualization unit is used to generate a visualization page of a comprehensive report on land management, and to display the status of the area and the adjustment result status in a visual manner, including using map and chart visualization tools to display regional division and generate regional reports, including using map drawing tools and chart drawing tools to dynamically display regional land information and plant growth status information.
[0059] The present invention provides a land information surveying and mapping system based on the Internet of Things, which has the following beneficial effects:
[0060] (1) When the system is running, the sensor network module collects real-time information on soil and plant growth status in different areas, and conducts in-depth analysis of these data to obtain the soil salt content factor , plant growth status factors and soil active factors , thereby accurately defining regional characteristics. Then, through advanced cluster analysis algorithms, the system can scientifically divide different areas according to similarities and generate management units with consistent characteristics. This refined land area division and mapping method allows each area to receive a customized management plan to ensure the rational allocation and utilization of resources, avoiding water and fertilizer waste and excessive use of resources. In addition, the feedback optimization module can also monitor and adjust management measures in real time to ensure that crops can obtain optimal resource allocation during their growth process. Finally, through the visual reports generated by the system, managers can clearly see the land mapping and division status and adjustment effects of each area, thereby improving the efficiency and benefits of agricultural production, solving the problems of uneven yield and resource waste caused by differences in regional characteristics, and ultimately achieving the goal of accurately reflecting the land characteristics of different regions through land information mapping.
[0061] (2) Through standardization units and cluster analysis units, the land characteristics of different regions are standardized in a refined manner, and the similarity distance between regions is calculated. , thus achieving accurate division of regions, ensuring that the characteristic differences of each region are fully considered, and also providing reliable basic data for further management decisions through the optimized cluster data cm, accurately calculating the characteristic mean of each region and characteristic standard deviation , and accordingly fit the specific management demand index It realizes the intelligent management of fertilization, pesticide application and water regulation, avoids the waste of resources and imbalance in traditional agricultural management as much as possible, and provides a more visual and controllable means of regulation for land mapping, greatly improving crop yield and quality.
[0062] (3) Based on the management demand index The system accurately sends or does not send management demand notifications based on the matching results with the preset management demand notification threshold XQ, ensuring the accuracy and timeliness of the notifications. Subsequently, the feedback detection unit performs real-time detection and analysis of the regional feature vectors after the execution of the management demand index. The system can dynamically obtain the feedback control index and adjust the management strategy accordingly. This mechanism not only improves the accuracy of management decisions, but also makes the land mapping process more flexible and controllable, reducing resource waste and the occurrence of erroneous decisions. The visualization module uses maps and charts to intuitively display various information from the land mapping management process, allowing managers to clearly understand the regional status and adjustment results, improving the transparency and operability of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] Figure 1 This is a block diagram and flow chart of a land information surveying and mapping system based on the Internet of Things of the present invention. DETAILED DESCRIPTION
[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0065] Example 1
[0066] The present invention provides a land information surveying and mapping system based on the Internet of Things. Figure 1 , including sensor network module, data analysis module, area division module, management decision module, feedback optimization module and visualization module;
[0067] The sensor network module deploys IoT network sensors in several areas of the land, collects soil status information and plant growth status information through the deployed network sensors, and forms an IoT collection data group;
[0068] The data analysis module obtains the soil salt content factor by analyzing the IoT collected data group , plant growth status factors and soil active factors , which constitutes the feature vector of region i ;
[0069] The region division module is based on the acquired feature vector Use the cluster analysis method to divide the similarity and divide the regional feature vector Normalize the feature values and use the Euclidean distance to calculate the similarity distance between regions , obtain the set and cluster type of similar feature areas to form cluster data cm;
[0070] The management decision module analyzes the mean and standard deviation of the characteristics of the received cluster data cm and obtains the mean of the characteristics of the cluster data cm and characteristic standard deviation , and then get the management demand index after fitting ;
[0071] The feedback optimization module manages the demand index Notify and remind relevant personnel and implement management demand index Then perform real-time detection of the feature vector of region i And analyze to obtain feedback control index , according to the feedback control index Adaptive notification and prompt management demand index Adjustment results;
[0072] The visualization module is used to generate a comprehensive report visualization page for land management, and to display the status of the region and the status of the adjustment results in a visual manner, including using map and chart visualization tools to display the region division and generate a report on the region.
[0073] In this embodiment, the sensor network module collects soil and plant growth status information in different areas in real time, and conducts in-depth analysis of these data to obtain the soil salt content factor. , plant growth status factors and soil active factors , thereby accurately defining regional characteristics. Then, through advanced cluster analysis algorithms, the system can scientifically divide different areas according to similarities and generate management units with consistent characteristics. This refined regional division method allows each area to receive a customized management plan to ensure the rational allocation and utilization of resources, avoiding water and fertilizer waste and excessive use of resources. In addition, the feedback optimization module can also monitor and adjust management measures in real time to ensure that crops can obtain optimal resource allocation during the growth process. Finally, through the visual reports generated by the system, managers can clearly see the status and adjustment effects of each area, improve the efficiency and benefits of agricultural production, and solve the problems of uneven yield and resource waste caused by differences in regional characteristics.
[0074] Example 2
[0075] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the sensor network module includes an area division unit and a data acquisition and transmission unit;
[0076] The area division unit deploys relevant IoT sensors in each divided area to monitor and collect soil status information and plant growth status information in real time, including soil moisture sensors, laser ranging sensors, photosynthesis meters, temperature sensors, conductivity sensors, light sensors, and camera sensors;
[0077] The data acquisition and transmission unit collects soil status information and plant growth status information from the deployed network sensors to form an Internet of Things collection data group, including soil moisture , conductivity , soil temperature , concentration value , average plant height , plant leaf area and plant density .
[0078] The data analysis module includes a vector analysis unit;
[0079] The vector analysis unit obtains the soil salt content factor by analyzing the IoT collected data group , plant growth status factors and soil active factors , which constitutes the feature vector of region i ;
[0080] Among them, the eigenvector of region i Specifically ={ , , }.
[0081] The soil salt content factor Ssalt is obtained by the following calculation formula:
[0082] ;
[0083] Where, represents the conductivity, Indicates the soil temperature value, represents the temperature correction constant, and exp represents the exponential function;
[0084] The plant growth status factor Obtained through the following calculation formula:
[0085] ;
[0086] Where, Indicates concentration value Change value, represents the average height of plants, △H represents the peak value of plant height difference, represents the plant leaf area, T represents the fixed test period, Indicates plant density;
[0087] The soil active factor Obtained through the following calculation formula:
[0088] ;
[0089] Where, represents soil moisture, Eh represents redox potential, Correction constant for redox potential.
[0090] Example 3
[0091] This embodiment is explained in Example 2, please refer to Figure 1 ,Specifically: the region division module includes a standardization unit and a cluster analysis unit;
[0092] The normalization unit obtains the feature vectors of all regions according to Use the cluster analysis method to divide the similarity and divide the feature vector of the region Perform eigenvalue standardization;
[0093] Among them, the eigenvalue normalization is processed by the following calculation formula:
[0094] ;
[0095] Where, represents the kth eigenvalue of region i after normalization, Represents the original eigenvalue, specifically the kth unstandardized eigenvalue of region i, represents the mean of the kth eigenvalue, represents the standard deviation of the kth eigenvalue;
[0096] The cluster analysis unit calculates the similarity distance between regions by using the Euclidean distance , by obtaining the similarity distance between each region Fill in the distance matrix elements to form the distance matrix D[i, j] of region i and region j, perform bubble sort on all distance matrices D[i, j] to obtain adjacent distance matrices D[i, j] and mark them as the cluster type of similar feature regions, specifically the cluster type of eigenvalue k type, to form cluster data cm, specifically cm=[ck, ck+1, ..., cm].
[0097] The similarity distance Calculated using the following formula:
[0098] ;
[0099] Where, Represents the similarity distance, specifically the Euclidean distance between region i and region j, n represents the length of the feature vector, specifically the total number of eigenvalues included in the feature vector, k represents the feature factor index, the kth eigenvalue, represents the kth eigenvalue of region j after normalization.
[0100] The management decision module includes a cluster processing unit and a management index unit;
[0101] The cluster processing unit analyzes the mean and standard deviation of the features according to the received cluster data cm to obtain the feature mean of the cluster data C and characteristic standard deviation ;
[0102] Among them, the characteristic mean Obtained through the following calculation formula:
[0103] ;
[0104] Where, It represents the feature mean of the mth set cluster type in the cluster data, specifically the mean of the kth feature in the cluster data cm, |cm| represents the total number of cluster data, specifically the length of the distance matrix that constitutes the cluster data cm, represents the kth eigenvalue of region i;
[0105] characteristic standard deviation Obtained through the following calculation formula:
[0106] ;
[0107] Where, Represents the characteristic standard deviation, specifically the characteristic standard deviation of the mth cluster type in the cluster data ;
[0108] The management index unit obtains the cluster data cm feature mean feature mean and characteristic standard deviation , and then get the management demand index after fitting .
[0109] The Management Demand Index Obtained through the following calculation formula:
[0110] ;
[0111] Where, Represents the management demand index, specifically the management demand of cluster data cm, including fertilization control, pesticide control and water control, Represents the feature mean The preset weight value of Represents the characteristic standard deviation The preset weight value of .
[0112] In this embodiment, the land characteristics of different regions are standardized in a refined manner through the standardization unit and the cluster analysis unit, and the similarity distance between regions is calculated. , thus achieving accurate division of regions, ensuring that the characteristic differences of each region are fully considered, and also providing reliable basic data for further management decisions through the optimized cluster data cm, accurately calculating the characteristic mean of each region and characteristic standard deviation , and accordingly fit the specific management demand index It realizes the intelligent management of fertilization, pesticide application and water regulation, avoids the waste of resources and imbalance in traditional agricultural management as much as possible, and provides a more visual and controllable means of regulation for land mapping, greatly improving crop yield and quality.
[0113] Example 4
[0114] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the feedback optimization module includes a feedback notification unit and a feedback detection unit;
[0115] The feedback notification unit is based on the management demand index Matches with the preset management demand notification threshold XQ, obtains the management demand notification result, and notifies and prompts relevant personnel based on the management demand notification result. The notification includes mobile phone text messages, preset voice prompts, and interactive page pop-up prompts;
[0116] The management requirement notification result is obtained through the following matching method:
[0117] Management Demand Index <Management demand notification threshold XQ, obtain the management demand notification sending result;
[0118] Management Demand Index ≥ Management demand notification threshold XQ, no result is sent when obtaining management demand notification;
[0119] The feedback detection unit performs management demand index Then perform real-time detection of the feature vector of region i And analyze to obtain feedback control index , according to the feedback control index Management Demand Index pass Calculation formula for adaptive notification and prompt management demand index Adjustment results;
[0120] Feedback Regulation Index Obtained through the following calculation formula:
[0121] ;
[0122] Where, Executive Management Demand Index The feature vector of region i recorded later , Executive Management Demand Index Feature vector of region i recorded previously , Indicates the preset weight value for regulation.
[0123] The visualization module includes a visualization unit;
[0124] The visualization unit is used to generate a visualization page of a comprehensive report on land management, and to display the status of the area and the adjustment result status in a visual manner, including using map and chart visualization tools to display regional division and generate regional reports, including using map drawing tools and chart drawing tools to dynamically display regional land information and plant growth status information.
[0125] In this implementation, according to the management demand index The system accurately sends or does not send management demand notifications based on the matching results with the preset management demand notification threshold XQ, ensuring the accuracy and timeliness of the notifications. Subsequently, the feedback detection unit performs real-time detection and analysis of the regional feature vectors after the execution of the management demand index. The system can dynamically obtain the feedback control index and adjust the management strategy accordingly. This mechanism not only improves the accuracy of management decisions, but also makes the land mapping process more flexible and controllable, reducing resource waste and the occurrence of erroneous decisions. The visualization module uses maps and charts to intuitively display various information from the land mapping management process, allowing managers to clearly understand the regional status and adjustment results, improving the transparency and operability of decision-making.
[0126] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.
Claims
1. A land information surveying and mapping system based on the Internet of Things, characterized by: It includes sensor network module, data analysis module, area division module, management decision module, feedback optimization module and visualization module; The sensor network module deploys IoT network sensors in several areas of the land, collects soil status information and plant growth status information through the deployed network sensors, and forms an IoT collection data group; The data analysis module obtains the soil salt content factor by analyzing the IoT collected data group , plant growth status factor and soil active factors , which constitutes the feature vector of region i ; The region division module is based on the acquired feature vector The regional feature vectors are divided into Normalize the feature values and use the Euclidean distance to calculate the similarity distance between regions. , obtain the set and cluster type of similar feature areas to form cluster data cm; The management decision module analyzes the mean and standard deviation of the features according to the received cluster data cm, and obtains the feature mean of the cluster data cm and characteristic standard deviation , and then get the management demand index after fitting ; The feedback optimization module manages the demand index Notify and remind relevant personnel to implement management demand index Then perform real-time detection of the feature vector of area i And analyze to obtain feedback regulation index , according to the feedback control index Adaptive notification and reminder management demand index The adjustment results; The visualization module is used to generate a comprehensive report visualization page for land management, and to display the status of the region and the status of the adjustment results in a visual manner, including using map and chart visualization tools to display regional divisions and generate regional reports.
2. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The sensor network module includes a region division unit and a data acquisition and transmission unit; The area division unit deploys relevant IoT sensors in each divided area to monitor and collect soil status information and plant growth status information in real time, including soil moisture sensors, laser ranging sensors, photosynthesis meters, temperature sensors, conductivity sensors, light sensors and camera sensors; The data acquisition and transmission unit collects soil status information and plant growth status information from the deployed network sensors to form an Internet of Things collection data group, including soil moisture , conductivity , soil temperature , concentration value , average plant height , plant leaf area and plant density .
3. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The data analysis module includes a vector analysis unit; The vector analysis unit obtains the soil salt content factor by analyzing the IoT collected data group , plant growth status factor and soil active factors , which constitutes the feature vector of region i ; Among them, the eigenvector of region i Specifically ={ , , }.
4. The land information surveying and mapping system based on the Internet of Things according to claim 3 is characterized in that: The soil salt content factor Ssalt is obtained by the following calculation formula: ; In the formula, represents the conductivity, Indicates the soil temperature value. represents the temperature correction constant, exp represents the exponential function; The plant growth status factor Obtained through the following calculation formula: ; In the formula, Indicates concentration value Change value, represents the average height of plants, △H represents the peak value of plant height difference, represents the plant leaf area, T represents the fixed test cycle duration, Indicates plant density; The soil active factor Obtained through the following calculation formula: ; In the formula, represents soil moisture, Eh represents redox potential, Correction constant for the redox potential.
5. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The region division module includes a standardization unit and a cluster analysis unit; The standardization unit obtains the feature vectors of all regions according to The method based on cluster analysis is used to divide the similarity and divide the feature vector of the region Perform feature value standardization; Among them, the eigenvalue standardization is processed by the following calculation formula: ; In the formula, represents the kth eigenvalue of region i after normalization, represents the original eigenvalue, specifically the kth unstandardized eigenvalue of region i, represents the mean of the kth eigenvalue, represents the standard deviation of the kth eigenvalue; The cluster analysis unit calculates the similarity distance between regions by using the Euclidean distance , by obtaining the similarity distance between each region Fill the distance matrix elements to form the distance matrix D[i, j] of region i and region j, perform bubble sort on all distance matrices D[i, j] to obtain adjacent distance matrices D[i, j], mark them as the set cluster type of similar feature regions, specifically the set cluster type of eigenvalue k type, and form cluster data cm, specifically cm=[ck, ck+1, ..., cm].
6. The land information surveying and mapping system based on the Internet of Things according to claim 5 is characterized in that: The similarity distance Calculated by the following formula: ; In the formula, represents the similarity distance, specifically the Euclidean distance between region i and region j, n represents the length of the feature vector, specifically the total number of eigenvalues included in the feature vector, k represents the feature factor index, the kth eigenvalue, represents the kth eigenvalue of region j after normalization.
7. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The management decision module includes a cluster processing unit and a management index unit; The cluster processing unit analyzes the mean and standard deviation of the features according to the received cluster data cm to obtain the feature mean of the cluster data C. and characteristic standard deviation ; Among them, the feature mean Obtained through the following calculation formula: ; In the formula, represents the feature mean of the mth set cluster type in the cluster data, specifically the mean of the kth feature in the cluster data cm, |cm| represents the total number of cluster data, specifically the length of the distance matrix that constitutes the cluster data cm, represents the kth eigenvalue of region i; Characteristic standard deviation Obtained through the following calculation formula: ; In the formula, Represents the characteristic standard deviation, specifically the characteristic standard deviation of the mth cluster type in the cluster data ; The management index unit obtains the cluster data cm feature mean feature mean and characteristic standard deviation , and then get the management demand index after fitting .
8. The land information surveying and mapping system based on the Internet of Things according to claim 7 is characterized in that: The Management Needs Index Obtained through the following calculation formula: ; In the formula, Represents the management demand index, specifically the management demand of cluster data cm, including fertilizer regulation, pesticide regulation and water regulation. Represents the feature mean The preset weight value of Represents the characteristic standard deviation The preset weight value of .
9. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The feedback optimization module includes a feedback notification unit and a feedback detection unit; The feedback notification unit manages the demand index Match with the preset management demand notification threshold XQ, obtain the management demand notification result, and notify and prompt relevant personnel according to the management demand notification result. The notification includes mobile phone text messages, preset voice prompts and interactive page pop-up prompts; The management requirement notification result is obtained by the following matching method: Management Demand Index <Management demand notification threshold XQ, obtain the management demand notification sending result; Management Demand Index ≥ Management demand notification threshold XQ, no result is sent when obtaining management demand notification; The feedback detection unit performs a management demand index Then perform real-time detection of the feature vector of area i And analyze to obtain feedback regulation index , according to the feedback control index Management Demand Index pass Calculation formula for adaptive notification and reminder management demand index The adjustment results; Feedback Regulation Index Obtained through the following calculation formula: ; In the formula, Executive Management Demand Index The feature vector of region i recorded later , Executive Management Demand Index Feature vector of region i recorded previously , Indicates the preset weight value for regulation.
10. The land information surveying and mapping system based on the Internet of Things according to claim 1, characterized in that: The visualization module includes a visualization unit; The visualization unit is used to generate a visualization page of a comprehensive report on land management, and to display the status of the area and the status of the adjustment results in a visual manner, including using map and chart visualization tools to display regional division and generate regional reports, including using map drawing tools and chart drawing tools to dynamically display regional land information and plant growth status information.
