Data management system and method based on high-standard farmland construction

Abstract

The invention belongs to the technical field of high-standard farmland construction, and particularly relates to a data management system and method based on high-standard farmland construction. According to the data management method based on high-standard farmland construction, real-time monitoring and priority dynamic adjustment of farmland basic data can be realized, so that the efficiency and accuracy of farmland management are improved, and particularly, by comprehensively evaluating the data attention degree and the data confidence degree, the data management efficiency is improved. According to the method, the key data subsets can obtain higher monitoring priorities, monitoring resources in farmland construction can be reasonably distributed, the farmland can be more effectively managed, in addition, the data monitoring priorities can be dynamically adjusted according to real-time monitoring results, and it is ensured that under different stages and conditions, the monitoring efficiency of the farmland is improved. Farmland management resources can be reasonably distributed and utilized.

Description

Technical Field

[0001] The present invention belongs to the technical field of high-standard farmland construction, and specifically relates to a data management system and method based on high-standard farmland construction. Background Art

[0002] With the advancement of agricultural modernization, the construction of high-standard farmland has become an important means to improve agricultural production efficiency and ensure food security. In the process of high-standard farmland construction, data management is particularly important. Effective data management can ensure the accuracy and efficiency of farmland construction, make rational use of farmland resources, improve the sustainability of agricultural production, and provide strong support for the realization of agricultural modernization.

[0003] Traditional data management methods for farmland construction often lack attention to aspects such as data timeliness and stability. Data management is only based on simple monitoring records, which cannot meet the high requirements of data management for high-standard farmland construction. At the same time, in the process of farmland construction, the relevant data involved in farmland construction also have different levels of importance, such as soil fertility data, irrigation system data, crop growth data, etc., which have an important impact on the decision-making of farmland construction, while some factors that have less impact on farmland construction require less attention, such as farmland surrounding environment data, meteorological data, etc. Therefore, this solution provides a data management method that can comprehensively consider data timeliness, stability and importance to meet the needs of high-standard farmland construction. Summary of the invention

[0004] The purpose of the present invention is to provide a data management system and method based on high-standard farmland construction, which can effectively evaluate and manage farmland construction related data, ensure that the timeliness, stability and importance of the data are reasonably considered, thereby improving the rational allocation of monitoring resources in farmland construction.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A data management method based on high-standard farmland construction, comprising:

[0007] Pre-process all farmland data of the acquired farmland construction projects and output them as farmland basic data;

[0008] According to the preset farmland construction attribute information, the farmland basic data is classified and processed to obtain multiple special data subsets;

[0009] Outputting the data attention of each of the special data subsets according to the access information of each of the special data subsets;

[0010] Outputting the data confidence of each of the special data subsets according to the data change information of each of the special data subsets;

[0011] According to the data attention and data confidence, a comprehensive evaluation is performed on the special data subsets, and then the data monitoring priority of each of the special data subsets is output according to the comprehensive evaluation result;

[0012] The farmland is monitored in real time according to the data monitoring priority, and the data monitoring priority of each of the special data subsets is adjusted according to the comprehensive evaluation results of the basic farmland data in each of the special data subsets under real-time monitoring.

[0013] In a preferred embodiment, the step of preprocessing all farmland data of the acquired farmland construction project and outputting them as farmland basic data includes:

[0014] Obtaining farmland data from multiple sources, including soil quality, irrigation facilities, crop types, planting density, meteorological conditions, and historical yields;

[0015] Performing data cleaning on the farmland data to remove duplicate, missing, abnormal or inconsistent data points;

[0016] The cleaned farmland data are standardized, the farmland data from various sources are converted into a unified format, and the standardized farmland data are recorded as basic farmland data.

[0017] In a preferred embodiment, the step of classifying the farmland basic data according to the preset farmland construction attribute information to obtain multiple special data subsets includes:

[0018] Acquire farmland construction attribute information, wherein the farmland construction attribute information includes a plurality of attribute tags, and the attribute tags include a soil tag, an irrigation facility tag, a crop type tag, and a historical yield tag;

[0019] Defining classification rules based on the soil label, irrigation facility label, crop type label, and historical yield label;

[0020] Matching the farmland basic data according to the classification rules, and outputting the farmland basic data under each classification rule;

[0021] The basic farmland data under the same classification rules are summarized into independent special data subsets.

[0022] In a preferred solution, the step of outputting the data attention of each of the special data subsets according to the access information of each of the special data subsets includes:

[0023] Establishing a monitoring period, and collecting the access information of each of the special data subsets during the monitoring period, wherein the access information includes the number of accesses and the number of data operations during the access period;

[0024] Obtaining the duration of the interval between adjacent review nodes of the same special data subset, and recording the adjacent review duration as a review condition parameter;

[0025] Obtaining a standard review interval duration, and comparing the review condition parameter with the standard review interval duration, and when the review condition parameter is greater than the standard review interval duration, respectively counting the number of reviews of adjacent review points corresponding to the review condition parameter, otherwise, combining and counting the number of reviews of adjacent review points corresponding to the review condition parameter;

[0026] An attention degree calculation function is obtained, and the number of access times and the number of data operations are input into the attention degree calculation function, and the output result of the attention degree calculation function is recorded as the data attention degree.

[0027] In a preferred solution, the step of outputting the data confidence of each of the special data subsets according to the data change information of each of the special data subsets comprises:

[0028] Obtaining farmland basic data in each of the special data subsets during the monitoring period, and calibrating them as basic condition parameters;

[0029] Performing difference processing on adjacent basic condition parameters to obtain basic fluctuation parameters, and determining the fluctuation interval duration of the basic condition parameters according to the basic fluctuation parameters;

[0030] Determine the timeliness score of the corresponding special data subset according to the fluctuation interval duration, and determine the stability score of the corresponding special data subset according to the basic fluctuation parameter;

[0031] A confidence calculation function is obtained, and the timeliness score and stability score of the special data subset are input into the confidence calculation function together, and the output result of the confidence calculation function is calibrated as data confidence.

[0032] In a preferred solution, the step of determining the timeliness score of the corresponding special data subset according to the fluctuation interval duration, and determining the stability score of the corresponding special data subset according to the basic fluctuation parameter, comprises:

[0033] Acquire the fluctuation interval duration and the timeliness classification interval corresponding to the fluctuation interval duration, wherein a plurality of timeliness classification intervals are provided, and each of the timeliness classification intervals corresponds to a timeliness score;

[0034] Compare the fluctuation interval duration with the timeliness classification interval, and output the timeliness scores of the special data subsets corresponding to the fluctuation interval duration one by one;

[0035] Obtaining the basic fluctuation parameters and arranging them in order of occurrence;

[0036] Obtaining a trend evaluation function, inputting the basic fluctuation parameter into the trend evaluation function, and calibrating the output result of the trend evaluation function as a verification condition parameter;

[0037] Obtain a verification function, and input the adjacent basic parameters and verification condition parameters into the verification function for verification processing, and calibrate the output result of the verification function as a verification bias;

[0038] Obtaining a standard deviation, and performing a difference process between the standard deviation and the calibration deviation to obtain a stability evaluation parameter;

[0039] Obtaining a stability evaluation interval, wherein a plurality of stability evaluation intervals are provided, and each of the stability evaluation intervals corresponds to a stability score;

[0040] The stability evaluation parameter is compared with the stability evaluation interval, and the stability score of the special data subset corresponding to the stability evaluation parameter is output one by one.

[0041] In a preferred solution, the step of comprehensively evaluating the special data subsets according to the data attention and data confidence, and then outputting the data monitoring priority of each of the special data subsets according to the comprehensive evaluation result includes:

[0042] Obtaining data attention and data confidence of each of the special data subsets;

[0043] Obtaining a comprehensive evaluation function, and inputting the data attention and the data confidence into the comprehensive evaluation function together, and calibrating the output result of the comprehensive evaluation function as a comprehensive score;

[0044] Arrange the comprehensive scores of each of the special data subsets in descending order, and assign monitoring priorities to each of the special data subsets one by one according to the sorting results;

[0045] Among them, the larger the value of the comprehensive score is, the higher the monitoring priority corresponding to the comprehensive score is.

[0046] In a preferred solution, the step of adjusting the data monitoring priority of each of the special data subsets according to the comprehensive evaluation results of the farmland basic data in each of the special data subsets under real-time monitoring includes:

[0047] Perform a reverse shift on the current monitoring node to obtain the monitoring period;

[0048] Collecting basic farmland data in each of the special data subsets during the monitoring period and recording them as sample parameters;

[0049] Calculating a comprehensive score of the sample parameters according to the comprehensive evaluation function and recording it as a monitoring score;

[0050] Performing weighted sum processing on the monitoring score and the comprehensive score, and marking the weighted sum result of the monitoring score and the comprehensive score as the ranking score;

[0051] According to the values ​​of the ranking scores, the monitoring priorities of the respective special data subsets are allocated one by one in descending order.

[0052] The present invention also provides a data management system based on high-standard farmland construction, using the above-mentioned data management method based on high-standard farmland construction, including:

[0053] A data collection module, wherein the data collection module is used to pre-process all farmland data of the acquired farmland construction project and output the data as farmland basic data;

[0054] A data classification module, wherein the data classification module is used to classify the farmland basic data according to preset farmland construction attribute information to obtain multiple special data subsets;

[0055] An attention output module, the attention output module is used to output the data attention of each of the special data subsets according to the access information of each of the special data subsets;

[0056] A confidence output module, the confidence output module is used to output the data confidence of each of the special data subsets according to the data change information of each of the special data subsets;

[0057] A comprehensive evaluation module, which is used to perform a comprehensive evaluation on the special data subsets according to the data attention and data confidence, and then output the data monitoring priority of each of the special data subsets according to the comprehensive evaluation result;

[0058] A dynamic adjustment module is used to perform real-time monitoring of farmland according to the data monitoring priority, and adjust the data monitoring priority of each special data subset according to the comprehensive evaluation results of the basic farmland data in each special data subset under real-time monitoring.

[0059] And, an electronic device, the electronic device comprising:

[0060] at least one processor;

[0061] and a memory communicatively coupled to the at least one processor;

[0062] Among them, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned data management method based on high-standard farmland construction.

[0063] The technical effects achieved by the present invention are:

[0064] The present invention, through a data management method based on high-standard farmland construction, can realize real-time monitoring of basic farmland data and dynamic adjustment of priority, thereby improving the efficiency and accuracy of farmland management. Specifically, by comprehensively evaluating data attention and data confidence, the present invention ensures that key data subsets can obtain higher monitoring priorities, so that monitoring resources in farmland construction can be reasonably allocated, thereby achieving more effective management of farmland. In addition, the present invention can also dynamically adjust data monitoring priorities according to real-time monitoring results, ensuring that farmland management resources can be reasonably allocated and utilized under different stages and conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic flow chart of the method of the present invention;

[0066] Figure 2 It is a schematic diagram of the system module of the present invention;

[0067] Figure 3 It is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0068] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0070] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0071] See also Figure 1 As shown, the present invention provides a data management method based on high-standard farmland construction, comprising:

[0072] S1. Preprocess all farmland data of the acquired farmland construction project and output them as farmland basic data;

[0073] S2. Classify and process the basic farmland data according to the preset farmland construction attribute information to obtain multiple special data subsets;

[0074] S3. Output the data attention of each special data subset according to the access information of each special data subset;

[0075] S4. Outputting the data confidence of each special data subset according to the data change information of each special data subset;

[0076] S5. Comprehensively evaluate the special data subsets according to the data attention and data confidence, and then output the data monitoring priority of each special data subset according to the comprehensive evaluation results;

[0077] S6. Carry out real-time monitoring of farmland according to data monitoring priorities, and adjust the data monitoring priorities of each special data subset according to the comprehensive evaluation results of the basic farmland data in each special data subset under real-time monitoring.

[0078] As described in the above steps S1-S6, with the advancement of farmland construction projects, the types and quantities of basic farmland data continue to increase, and the complexity and difficulty of data management are also increasing. In order to ensure efficient management and real-time monitoring of farmland data, this solution further optimizes farmland data management. In this embodiment, all farmland data in the farmland construction project are first collected, and corresponding preprocessing is performed on all farmland data obtained from the farmland construction project. The purpose of data preprocessing is to clean and organize the data to ensure its accuracy and consistency for subsequent analysis and processing. After the preprocessing is completed, the farmland data is output as basic farmland data, and then the basic farmland data will be classified and processed according to the preset farmland construction attribute information, so that the basic farmland data can be decomposed into multiple special data subsets. The multiple special data subsets correspond to various aspects of farmland construction, such as soil quality, irrigation system, crop growth status, etc. In order to facilitate the classification and management of farmland basic data, on the basis of classification processing, the data attention of each special data subset will be output according to the reading information of each special data subset, so as to reflect the importance of each special data subset in the current farmland management. In addition, according to the data change information of each special data subset, the data confidence of each special data subset can also be output. Data confidence refers to the evaluation of data accuracy and reliability, which is used as a basis to judge the credibility of farmland basic data changes. Then, according to the data attention and data confidence, the special data subsets are comprehensively evaluated, so as to assign a comprehensive evaluation result to each special data subset. Based on the comprehensive evaluation result, the data monitoring priority of each special data subset can be output to ensure that the data subset with the highest data monitoring priority can be monitored and managed first. Finally, according to the data monitoring priority, the method monitors the farmland in real time. By continuously tracking the changes in farmland basic data in each special data subset, problems in farmland management can be discovered and solved in a timely manner. At the same time, based on the comprehensive evaluation results of the basic farmland data in each special data subset under real-time monitoring, the data monitoring priority of each special data subset can be dynamically adjusted to ensure the flexibility and adaptability of data monitoring, thereby improving the efficiency and effectiveness of farmland management.

[0079] In a preferred embodiment, the steps of preprocessing all farmland data acquired for the farmland construction project and outputting them as farmland basic data include:

[0080] S101. Obtain farmland data from multiple sources, including soil quality, irrigation facilities, crop types, planting density, meteorological conditions, and historical yields;

[0081] S102. Clean the farmland data to remove duplicate, missing, abnormal or inconsistent data points;

[0082] S103, standardizing the cleaned farmland data, converting the farmland data from various sources into a unified format, and recording the standardized farmland data as basic farmland data.

[0083] As described in the above steps S101-S103, when collecting farmland data, it often involves multiple data sources, and farmland data from multiple sources often have problems with different formats or inconsistencies, so data cleaning and standardization are required. The collected farmland data include but are not limited to detailed indicators of soil quality, such as pH value, organic matter content, content of nutrients such as nitrogen, phosphorus and potassium, details of irrigation facilities, including the type, coverage and operation status of the irrigation system, specific information on crop types, including planted crop varieties, growth cycles and market demand, specific values ​​of planting density, that is, the number of crops planted per unit area, detailed records of meteorological conditions, such as temperature, precipitation, sunshine duration and wind speed, etc., and specific data on historical yields, including yield records and changes over the years. Next, the collected farmland data will be cleaned to remove duplicate data points to avoid data redundancy. At the same time, missing data points will be properly filled or marked to ensure data integrity. Abnormal or inconsistent data points will also be eliminated accordingly to ensure data accuracy and reliability. After the farmland data is cleaned, the cleaned farmland data will be standardized to convert farmland data from different sources into a unified format to ensure data consistency and comparability. For example, standardized data formats and coding systems can be used to format the data so that it can be uniformly managed and analyzed. Finally, the standardized farmland data will be recorded as basic farmland data to provide corresponding pre-data support for subsequent data analysis.

[0084] In a preferred embodiment, the steps of classifying and processing the farmland basic data according to the preset farmland construction attribute information to obtain multiple special data subsets include:

[0085] S201, obtaining farmland construction attribute information, wherein the farmland construction attribute information includes multiple attribute tags, and the attribute tags include soil tags, irrigation facility tags, crop type tags, and historical yield tags;

[0086] S202, defining classification rules based on soil labels, irrigation facility labels, crop type labels, and historical yield labels;

[0087] S203, matching the farmland basic data according to the classification rules, and outputting the farmland basic data under each classification rule;

[0088] S204, summarizing the basic farmland data under the same classification rule into independent special data subsets.

[0089] As described in the above steps S201-S204, when classifying and processing the basic farmland data, it is first necessary to obtain the farmland construction attribute information related to the farmland construction. The farmland construction attribute information covers multiple key attribute labels, including soil type labels, irrigation facility status labels, planted crop type labels, and past crop yield labels. The attribute labels together constitute the basic framework of the farmland construction attribute information. Based on these attribute labels, a series of classification rules can be defined to ensure that the basic farmland data can be accurately divided according to established standards. For example, farmland can be divided into sandy soil, clay soil and other categories according to different soil types; farmland can be divided into high-efficiency irrigation system, traditional irrigation system and other categories according to the degree of perfection of irrigation facilities; farmland can be divided into food crops, cash crops and other categories according to different crop types; farmland can be divided into high-yield fields and medium-yield fields according to historical yield data. , low-yield fields and other categories. After the classification rules are defined, the classification rules will be used to match the basic farmland data accordingly, so that each basic farmland data can be accurately classified into the corresponding classification rules. For example, the soil type of a piece of farmland is clay, the irrigation facilities are sprinkler systems, the crops planted are wheat, and the historical yield data shows high yield, then the data of this farmland will be classified into the corresponding category. Finally, the basic farmland data under each classification rule will be summarized separately to form an independent special data subset. Each special data subset reflects the basic farmland data under a certain specific classification rule, such as all sandy soil farmland data or all high-yield fields data. In this way, through the form of special data subsets, different categories of farmland can be more conveniently analyzed and managed, thereby providing more accurate data support for farmland construction and agricultural production.

[0090] In a preferred embodiment, the step of outputting the data attention of each special data subset according to the access information of each special data subset includes:

[0091] S301, construct a monitoring period, and collect the access information of each special data subset during the monitoring period, the access information including the number of accesses and the number of data operations during the access period;

[0092] S302, obtaining the interval between adjacent review nodes of the same special data subset, and recording the adjacent review interval as a review condition parameter;

[0093] S303, obtaining the standard access interval duration, and comparing the access condition parameter with the standard access interval duration, and when the access condition parameter is greater than the standard access interval duration, respectively counting the access times of adjacent access points corresponding to the access condition parameter, otherwise, combining and counting the access times of adjacent access points corresponding to the access condition parameter;

[0094] S304, obtaining an attention degree calculation function, and inputting the number of access times and the number of data operations into the attention degree calculation function, and recording the output result of the attention degree calculation function as the data attention degree.

[0095] As described in the above steps S301-S304, after the special data subsets are output, the data attention of each special data subset is output according to the access information of each special data subset. First, it is necessary to construct a monitoring period. The construction of the monitoring period is to track and record the usage of each special data subset within a certain period of time, including the number of accesses and the number of data operations. Then, the access interval between adjacent access nodes of the same special data subset is obtained, and these adjacent access times are recorded as access condition parameters. After obtaining the access condition parameters, it is necessary to obtain the preset standard access interval The standard access interval will be used as a comparison benchmark. By comparing the access condition parameters with the standard access interval, the specific access times of the special data are determined. If the access condition parameters are greater than the standard access interval, the access times of the adjacent access points corresponding to the access condition parameters will be counted separately. On the contrary, if the access condition parameters are less than or equal to the standard access interval, the access times of the adjacent access points corresponding to the access condition parameters will be combined and counted. Then, the attention measurement function is introduced to calculate the data attention of the special data subset. The expression of the correlation measurement function is: R g =αM 1 +βM 2 , where R g represents the data attention, α represents the weight coefficient of the number of accesses, β represents the weight coefficient of the number of data operations, and M 1 Indicates the number of times the special data subset is consulted, M 2 It represents the number of data operations. By taking the number of times the special data subset is accessed and the number of data operations as input parameters and inputting them into the attention measurement function, the data attention of each special data subset can be calculated.

[0096] In a preferred embodiment, the step of outputting the data confidence of each special data subset according to the data change information of each special data subset includes:

[0097] S401, obtaining basic farmland data in each special data subset within the monitoring period, and calibrating them as basic condition parameters;

[0098] S402, performing difference processing on adjacent basic condition parameters to obtain basic fluctuation parameters, and determining the fluctuation interval duration of the basic condition parameters according to the basic fluctuation parameters;

[0099] S403, determining the timeliness score of the corresponding special data subset according to the fluctuation interval duration, and determining the stability score of the corresponding special data subset according to the basic fluctuation parameter;

[0100] S404, obtain a confidence calculation function, and input the timeliness score and stability score of the special data subset into the confidence calculation function, and calibrate the output result of the confidence calculation function as data confidence.

[0101] As described in the above steps S401-S404, after the output of the special data subset, the data confidence of the special data subset will be further calculated. First, it is necessary to collect the basic farmland data in each special data subset within the monitoring period and record it as the basic condition parameters. Then, the adjacent basic condition parameters are subjected to difference processing to obtain the basic fluctuation parameters. The basic fluctuation parameters can reflect the changes in the basic condition parameters in the time series. Based on the basic fluctuation parameters, the fluctuation interval duration of the basic condition parameters can be further determined. The timeliness of the data can be evaluated according to the fluctuation interval duration, and the corresponding timeliness score can be calculated. At the same time, it is also necessary to determine the stability score of each special data subset based on the basic fluctuation parameters. The stability score reflects the degree of fluctuation of the data within a certain time range. Finally, it is necessary to introduce a confidence measurement function. By comprehensively considering the timeliness score and the stability score, a quantitative data confidence can be obtained. The expression of the confidence measurement function is: R z =ω 1 f s +ω 2 f w , where R z represents the confidence score, ω 1 and ω 2 Represent the weight coefficients of timeliness score and stability score, respectively, s and f w They represent the timeliness score and stability score respectively. After the data confidence is output, it can be combined with the data attention to output the comprehensive score of the data special subset.

[0102] In a preferred embodiment, the steps of determining the timeliness score of the corresponding special data subset according to the fluctuation interval duration, and determining the stability score of the corresponding special data subset according to the basic fluctuation parameter include:

[0103] Step 1. Obtain the duration of the fluctuation interval and the timeliness classification interval corresponding to the fluctuation interval. There are multiple timeliness classification intervals, and each timeliness classification interval corresponds to a timeliness score.

[0104] Step 2: Compare the fluctuation interval duration with the timeliness classification interval, and output the timeliness scores of the special data subsets corresponding to the fluctuation interval duration one by one;

[0105] Step 3. Obtain basic fluctuation parameters and arrange them in order of occurrence;

[0106] Step 4, obtain the trend evaluation function, input the basic fluctuation parameter into the trend evaluation function, and calibrate the output result of the trend evaluation function as the verification condition parameter;

[0107] Step 5, obtain the verification function, and input the adjacent basic condition parameters and the verification condition parameters into the verification function for verification processing, and calibrate the output result of the verification function as the verification bias;

[0108] Step 6, obtain the standard deviation, and perform difference processing between the standard deviation and the calibration deviation to obtain the stability evaluation parameter;

[0109] Step 7, obtain the stability evaluation interval. There are multiple stability evaluation intervals, and each stability evaluation interval corresponds to a stability score;

[0110] Step 8. Compare the stability evaluation parameters with the stability evaluation interval, and output the stability scores of the special data subsets corresponding to the stability evaluation parameters one by one.

[0111] As described in the above steps Step 1-Step 8, after the fluctuation interval duration and the basic fluctuation parameters are output, the timeliness classification interval to which it belongs will be determined according to the fluctuation interval duration. The timeliness classification interval is pre-set, and each timeliness classification interval has a specific timeliness score. By comparing the fluctuation interval duration with the timeliness classification interval, the timeliness score of each special data subset can be determined one by one, and then the stability score of the special data subset needs to be calculated. Based on this, the basic fluctuation parameters are first obtained, and the basic fluctuation parameters are arranged in the order of occurrence to ensure the accuracy of the evaluation. Then the trend evaluation function is introduced, and the basic fluctuation parameters are input into the trend evaluation function, where the expression of the trend evaluation function is: In the formula, Q represents the calibration condition parameter, T represents the length of the monitoring period, n represents the number of basic fluctuation parameters, and C i Represents the basic fluctuation parameter. After the verification condition parameter is output, it needs to be input into the verification function. The adjacent basic condition parameters and verification condition parameters are input into the verification function for verification processing. The output result of the verification function is recorded as the verification deviation. The expression of the verification function is: p =C q +Qt-C h , where Cp Indicates the calibration bias, C q represents the basic condition parameter with the highest ranking among the adjacent positions, t represents the sampling interval of the adjacent basic condition parameters, C h It represents the basic condition parameters of the later positions in adjacent positions, and then introduces the preset standard deviation. The standard deviation is set according to historical data and experience. By performing difference processing between the standard deviation and the calibration deviation, the stability evaluation parameter can be obtained. Finally, it is necessary to determine the stability evaluation interval. The stability evaluation interval is pre-set according to the actual situation of data fluctuations. Each stability evaluation interval has a corresponding stability score. By comparing the stability evaluation parameter with the stability evaluation interval, the stability score of each special data subset can be output one by one.

[0112] In a preferred embodiment, the steps of comprehensively evaluating the special data subsets according to the data attention and the data confidence, and then outputting the data monitoring priority of each special data subset according to the comprehensive evaluation result include:

[0113] S501, obtaining data attention and data confidence of each special data subset;

[0114] S502, obtaining a comprehensive evaluation function, and inputting the data attention and the data confidence into the comprehensive evaluation function, and marking the output result of the comprehensive evaluation function as a comprehensive score;

[0115] S503, arranging the comprehensive scores of each special data subset in descending order, and assigning a monitoring priority to each special data subset one by one according to the sorting result;

[0116] Among them, the larger the value of the comprehensive score is, the higher the monitoring priority corresponding to the comprehensive score is.

[0117] As described in the above steps S501-S503, in order to ensure the efficiency and accuracy of data monitoring, it is necessary to conduct a comprehensive evaluation of each special data subset, which specifically involves an in-depth analysis of the data attention and data confidence. Specifically, a comprehensive evaluation function is used to calculate the comprehensive score of the special data subset, where the expression of the comprehensive evaluation function is: μ = η 1 R g +η 2 R z , where μ represents the comprehensive score, η 1 and η 2They represent the weight factors of data attention and data confidence respectively. The comprehensive score is a quantitative indicator of the overall performance of each special data subset, which can reflect the comprehensive value of the data subset in data management. After obtaining the comprehensive score, it is necessary to sort the comprehensive scores of all special data subsets. Specifically, they are arranged in order from high to low according to the comprehensive score, so that the more prominent special data subsets can be intuitively seen. Then, according to the sorting results, a data monitoring priority is assigned to each special data subset. The principle of priority allocation is: the higher the comprehensive score of the data subset, the higher its monitoring priority, thereby optimizing the process and effect of data monitoring and ensuring that monitoring resources can be more reasonably allocated to the most critical special data subsets.

[0118] In a preferred embodiment, the step of adjusting the data monitoring priority of each special data subset according to the comprehensive evaluation results of the farmland basic data in each special data subset under real-time monitoring includes:

[0119] S601, reversely shift the current monitoring node to obtain a monitoring period;

[0120] S602, collecting basic farmland data in each special data subset during the monitoring period, and recording it as sample parameters;

[0121] S603, calculating the comprehensive score of the sample parameters according to the comprehensive evaluation function, and recording it as the monitoring score;

[0122] S604: Perform weighted sum processing on the monitoring score and the comprehensive score, and mark the weighted sum result of the monitoring score and the comprehensive score as the ranking score;

[0123] S605. According to the values ​​of the ranking scores, the monitoring priority of each special data subset is assigned one by one in descending order.

[0124] As described in the above steps S601-S605, during the real-time monitoring process, it is necessary to conduct a comprehensive evaluation of the basic farmland data in each special data subset in order to adjust the data monitoring priority of the basic farmland data in the special data subset. First, the current monitoring node needs to be reversed. In this way, a monitoring period can be determined. The monitoring period can help understand the changes in the basic farmland data within a specific time. Then, the basic farmland data in each special data subset will be collected during this monitoring period and recorded as sample parameters. After the sample parameters are collected, the preset comprehensive evaluation function will be used to calculate the comprehensive score of the sample parameters. The expression of the comprehensive evaluation function is: υ=k 1 R′ g +k 2 R z ′, where υ represents the comprehensive score, k1 Indicates the weight coefficient of sample parameters corresponding to data attention, k 2 Represents the weight coefficient of the sample parameter corresponding to the data confidence, R′ g and R z ′ respectively represent the data attention and data confidence of the sample parameters. The determination process is consistent with the analysis process of the above-mentioned special data subsets and will not be repeated here. Based on the above, the performance of each special data subset in the current monitoring period can be determined. After obtaining the monitoring score, it is necessary to perform weighted summation processing with the comprehensive score to comprehensively consider the immediate performance and long-term performance of the special data subset in the monitoring period. In this way, a more comprehensive evaluation result can be obtained, which will be calibrated as a ranking score. The ranking score is the basis for dynamically adjusting the data monitoring priority of each special data subset, ensuring that the monitoring of basic farmland data can be dynamically adjusted to provide more reasonable data support for agricultural production.

[0125] See also Figure 2 A data management system based on high-standard farmland construction, using the above-mentioned data management method based on high-standard farmland construction, comprising:

[0126] The data collection module is used to pre-process all the farmland data of the farmland construction project and output them as basic farmland data;

[0127] The data classification module is used to classify the basic farmland data according to the preset farmland construction attribute information to obtain multiple special data subsets;

[0128] The attention output module is used to output the data attention of each special data subset according to the reading information of each special data subset;

[0129] A confidence output module, which is used to output the data confidence of each special data subset based on the data change information of each special data subset;

[0130] Comprehensive evaluation module: The comprehensive evaluation module is used to conduct a comprehensive evaluation on the special data subsets according to the data attention and data confidence, and then output the data monitoring priority of each special data subset according to the comprehensive evaluation results;

[0131] The dynamic adjustment module is used to monitor farmland in real time according to the data monitoring priority, and adjust the data monitoring priority of each special data subset according to the comprehensive evaluation results of the basic farmland data in each special data subset under real-time monitoring.

[0132] In the above, the system includes a data acquisition module, a data classification module, an attention output module, a confidence output module, a comprehensive evaluation module and a dynamic adjustment module. The data acquisition module is responsible for collecting and organizing all relevant farmland data generated in the farmland construction project. The farmland data includes but is not limited to soil type, crop planting conditions, irrigation system, fertilization records, etc. The collected farmland data is further pre-processed to ensure its accuracy and consistency, and finally forms the farmland basic data. The data classification module performs detailed classification processing on the farmland basic data according to the pre-set farmland construction attribute information. Through this process, the farmland basic data is divided into multiple specialized The module outputs data subsets of special data, such as soil quality data subset, crop growth data subset, water resource management data subset, etc. Each special data subset corresponds to various aspects of farmland construction, which is convenient for subsequent analysis and management. The attention output module focuses on analyzing the frequency and importance of each special data subset, so as to evaluate the data attention of each special data subset. The confidence output module focuses on the reliability and accuracy of the data. It evaluates and outputs the data confidence of each special data subset according to the data changes of each special data subset. The comprehensive evaluation module comprehensively considers the data attention and data confidence, and conducts a comprehensive evaluation of each special data subset. Based on the evaluation results, the data monitoring priority of each special data subset can be determined, so as to guide the subsequent data monitoring and management activities. The dynamic adjustment module is responsible for real-time monitoring of farmland according to the data monitoring priority. It uses the latest monitoring data and combines the comprehensive evaluation results of each special data subset to dynamically adjust the data monitoring priority, ensuring the flexibility and adaptability of farmland management and being able to respond to various changes in the farmland construction process in a timely manner.

[0133] See also Figure 3 , an electronic device, the electronic device comprising:

[0134] at least one processor;

[0135] and a memory communicatively coupled to the at least one processor;

[0136] Among them, the memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned data management method based on high-standard farmland construction.

[0137] In the above, the processor of the electronic device can be a central processing unit (CPU) or a graphics processing unit (GPU), which is responsible for executing the computer program stored in the memory to implement the various steps of the data management method. The memory can be a random access memory (RAM), a read-only memory (ROM) or other forms of non-volatile storage devices, such as a solid-state drive (SSD) or a hard disk drive (HDD), for storing computer programs and related data. The electronic device also includes an arithmetic unit, an input device and an output device. The arithmetic unit is responsible for executing the instructions issued by the processor to perform data processing and calculation work. The input device allows the user to interact with the electronic device and input necessary instructions and data, such as a keyboard, a mouse, a touch screen, etc. The output device is used to display the processing results, such as a display, a printer, etc.

[0138] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0139] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A data management method based on high-standard farmland construction, characterized by: include: Pre-process all farmland data of the acquired farmland construction projects and output them as farmland basic data; According to the preset farmland construction attribute information, the farmland basic data is classified and processed to obtain multiple special data subsets; Outputting the data attention of each of the special data subsets according to the access information of each of the special data subsets; Outputting the data confidence of each of the special data subsets according to the data change information of each of the special data subsets; According to the data attention and data confidence, a comprehensive evaluation is performed on the special data subsets, and then the data monitoring priority of each of the special data subsets is output according to the comprehensive evaluation result; The farmland is monitored in real time according to the data monitoring priority, and the data monitoring priority of each of the special data subsets is adjusted according to the comprehensive evaluation results of the basic farmland data in each of the special data subsets under real-time monitoring.

2. According to claim 1, a data management method based on high-standard farmland construction is characterized in that: The step of preprocessing all the farmland data of the acquired farmland construction project and outputting them as farmland basic data includes: Obtaining farmland data from multiple sources, including soil quality, irrigation facilities, crop types, planting density, meteorological conditions, and historical yields; Performing data cleaning on the farmland data to remove duplicate, missing, abnormal or inconsistent data points; The cleaned farmland data are standardized, the farmland data from various sources are converted into a unified format, and the standardized farmland data are recorded as basic farmland data.

3. According to claim 1, a data management method based on high-standard farmland construction is characterized in that: The step of classifying the farmland basic data according to the preset farmland construction attribute information to obtain multiple special data subsets includes: Acquire farmland construction attribute information, wherein the farmland construction attribute information includes a plurality of attribute tags, and the attribute tags include a soil tag, an irrigation facility tag, a crop type tag, and a historical yield tag; Defining classification rules based on the soil label, irrigation facility label, crop type label, and historical yield label; Matching the farmland basic data according to the classification rules, and outputting the farmland basic data under each classification rule; The basic farmland data under the same classification rules are summarized into independent special data subsets.

4. The data management method based on high-standard farmland construction according to claim 1 is characterized in that: The step of outputting the data attention of each of the special data subsets according to the access information of each of the special data subsets comprises: Establishing a monitoring period, and collecting the access information of each of the special data subsets during the monitoring period, wherein the access information includes the number of accesses and the number of data operations during the access period; Obtaining the duration of the interval between adjacent review nodes of the same special data subset, and recording the adjacent review duration as a review condition parameter; Obtaining a standard review interval duration, and comparing the review condition parameter with the standard review interval duration, and when the review condition parameter is greater than the standard review interval duration, respectively counting the number of reviews of adjacent review points corresponding to the review condition parameter, otherwise, combining and counting the number of reviews of adjacent review points corresponding to the review condition parameter; Obtain an attention degree calculation function, input the number of access times and the number of data operations into the attention degree calculation function, and record the output result of the attention degree calculation function as data attention degree.

5. A data management method based on high-standard farmland construction according to claim 4, characterized in that: The step of outputting the data confidence of each of the special data subsets according to the data change information of each of the special data subsets comprises: Obtaining farmland basic data in each of the special data subsets during the monitoring period, and calibrating them as basic condition parameters; Performing difference processing on adjacent basic condition parameters to obtain basic fluctuation parameters, and determining the fluctuation interval duration of the basic condition parameters according to the basic fluctuation parameters; Determine the timeliness score of the corresponding special data subset according to the fluctuation interval duration, and determine the stability score of the corresponding special data subset according to the basic fluctuation parameter; A confidence calculation function is obtained, and the timeliness score and stability score of the special data subset are input into the confidence calculation function together, and the output result of the confidence calculation function is calibrated as data confidence.

6. A data management method based on high-standard farmland construction according to claim 5, characterized in that: The step of determining the timeliness score of the corresponding special data subset according to the fluctuation interval duration, and determining the stability score of the corresponding special data subset according to the basic fluctuation parameter, comprises: Acquire the fluctuation interval duration and the timeliness classification interval corresponding to the fluctuation interval duration, wherein a plurality of timeliness classification intervals are provided, and each of the timeliness classification intervals corresponds to a timeliness score; Compare the fluctuation interval duration with the timeliness classification interval, and output the timeliness scores of the special data subsets corresponding to the fluctuation interval duration one by one; Obtaining the basic fluctuation parameters and arranging them in order of occurrence; Obtaining a trend evaluation function, inputting the basic fluctuation parameter into the trend evaluation function, and calibrating the output result of the trend evaluation function as a verification condition parameter; Obtain a verification function, and input the adjacent basic parameters and verification condition parameters into the verification function for verification processing, and calibrate the output result of the verification function as a verification bias; Obtaining a standard deviation, and performing a difference process between the standard deviation and the calibration deviation to obtain a stability evaluation parameter; Obtaining a stability evaluation interval, wherein a plurality of stability evaluation intervals are provided, and each of the stability evaluation intervals corresponds to a stability score; The stability evaluation parameter is compared with the stability evaluation interval, and the stability score of the special data subset corresponding to the stability evaluation parameter is output one by one.

7. The data management method based on high-standard farmland construction according to claim 1 is characterized in that: The step of comprehensively evaluating the special data subsets according to the data attention and the data confidence, and then outputting the data monitoring priority of each of the special data subsets according to the comprehensive evaluation result, includes: Obtaining data attention and data confidence of each of the special data subsets; Obtaining a comprehensive evaluation function, and inputting the data attention and the data confidence into the comprehensive evaluation function together, and calibrating the output result of the comprehensive evaluation function as a comprehensive score; Arrange the comprehensive scores of each of the special data subsets in descending order, and assign monitoring priorities to each of the special data subsets one by one according to the sorting results; Among them, the larger the value of the comprehensive score is, the higher the monitoring priority corresponding to the comprehensive score is.

8. The data management method based on high-standard farmland construction according to claim 7 is characterized in that: The step of adjusting the data monitoring priority of each of the special data subsets according to the comprehensive evaluation results of the farmland basic data in each of the special data subsets under real-time monitoring includes: Perform a reverse shift on the current monitoring node to obtain the monitoring period; Collecting basic farmland data in each of the special data subsets during the monitoring period and recording them as sample parameters; Calculating a comprehensive score of the sample parameters according to the comprehensive evaluation function and recording it as a monitoring score; Performing weighted sum processing on the monitoring score and the comprehensive score, and marking the weighted sum result of the monitoring score and the comprehensive score as the ranking score; According to the values ​​of the ranking scores, the monitoring priorities of the respective special data subsets are allocated one by one in descending order.

9. A data management system based on high-standard farmland construction, characterized by: The data management method based on high-standard farmland construction according to any one of claims 1 to 8 comprises: A data collection module, wherein the data collection module is used to pre-process all farmland data of the acquired farmland construction project and output the data as farmland basic data; A data classification module, wherein the data classification module is used to classify the farmland basic data according to preset farmland construction attribute information to obtain multiple special data subsets; An attention output module, the attention output module is used to output the data attention of each of the special data subsets according to the access information of each of the special data subsets; A confidence output module, the confidence output module is used to output the data confidence of each of the special data subsets according to the data change information of each of the special data subsets; A comprehensive evaluation module, which is used to perform a comprehensive evaluation on the special data subsets according to the data attention and data confidence, and then output the data monitoring priority of each of the special data subsets according to the comprehensive evaluation result; A dynamic adjustment module is used to perform real-time monitoring of farmland according to the data monitoring priority, and adjust the data monitoring priority of each special data subset according to the comprehensive evaluation results of the basic farmland data in each special data subset under real-time monitoring.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; In which, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data management method based on high-standard farmland construction as described in any one of claims 1 to 8.

Images