Method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory

Abstract

The invention relates to the technical field of agricultural management, in particular to a method for metering yield per mu based on agricultural machinery operation data and Beidou trajectory, which comprises the following steps: constructing a trajectory continuity index in a space-time operation effectiveness feature set, counting a time interval threshold value of adjacent trajectory points to obtain a continuity level, and incorporating the continuity level into a space-time operation effectiveness comprehensive score, the method is used for overall correction of a subsequent effective operation area, and area errors caused by trajectory point loss / abnormity are inhibited from the source. Constructing a cut width consistency index, further introducing a cut width correction coefficient, correcting a convex hull area, and then linking with a space-time operation effectiveness comprehensive score to obtain a final effective operation area, thereby reducing an accumulative error of cut width fluctuation to an area link; and constructing a correction coefficient based on the whole-cycle soil moisture content mean value and the crop standard soil moisture content, and correcting the basic value of the yield per mu to obtain a final yield per mu value, so that environmental differences are brought into a metering closed loop, and the comparability and interpretability of the yield per mu result are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information processing technology for agricultural production management, and particularly relates to a method for calculating yield per mu based on agricultural machine operation data and Beidou trajectory. BACKGROUND

[0002] In the harvesting operation of agricultural machinery, yield per mu (yield per unit area) is an important indicator for evaluating operation efficiency, yield level and business decision-making. The existing scheme usually obtains the trajectory of agricultural machinery through satellite navigation (Beidou / GNSS); obtains the harvesting amount per unit time through flow / weight sensors; estimates the operation area per unit time by combining the operation speed and the cutting width; and further calculates the area of the operation region through the trajectory, thereby obtaining the yield per mu.

[0003] Disadvantages of the prior art: Many existing methods directly form the operation path or the region boundary using the trajectory points, assuming that the trajectory data is continuous and reliable; when there are communication loss points, positioning drift, and abnormal time stamps, they will still be included in the area calculation, resulting in an overestimation or underestimation of the operation area; the cutting width is affected by crop lodging, driving deviation, and machine state, and if a fixed width is still used or the consistency of the cutting width is not controlled, there will be a structural deviation in the area estimation; the existing technology usually only outputs one yield per mu value, lacks matching verification with historical similar conditions, and makes it difficult to determine whether the result deviates from the reasonable range when the crop changes, the soil condition changes, or the machine condition changes; many existing schemes do not form a quantitative correction link for yield per mu even if the soil condition is collected, so that the yield per mu results under different soil conditions in the same plot lack consistent standards. SUMMARY

[0004] The main purpose of the present application is to provide a method for calculating yield per mu based on agricultural machinery operation data and Beidou trajectory, by constructing a trajectory continuity index in the time-space operation effectiveness feature set, obtaining the continuity level through the time interval threshold of adjacent trajectory points, and incorporating it into the time-space operation effectiveness comprehensive score for the overall correction of the subsequent effective operation area, thereby suppressing the area error caused by trajectory point loss / abnormality from the source; a cutting width consistency index is constructed, and a cutting width correction coefficient is further introduced to correct the convex hull area, and then the final effective operation area is obtained through the linkage of the time-space operation effectiveness comprehensive score, thereby reducing the cumulative error of the area link caused by cutting width fluctuation; by introducing a cross-scene matching degree index and obtaining a historical reference interval, the interval is modified according to the crop type adaptation coefficient and then normalized, so that different crop types have an interpretable reference scale, and the matching degree is used to suppress abnormal deviation, thereby enhancing the cross-scene comparability and self-checking ability; based on the mean value of the whole cycle soil moisture content and the standard soil moisture content of crops, a correction coefficient is constructed to correct the yield per mu basic value to obtain the final yield per mu value, thereby incorporating environmental differences into the measurement closed loop, improving the comparability and interpretability of the yield per mu result, and taking the accurate yield per mu value as the core data support for agricultural production management, providing reliable basis for decision-making scenarios such as plot yield comparison, planting scheme adjustment, agricultural operation efficiency optimization and operating income prediction, and realizing fine management of agricultural production.

[0005] The technical scheme of the present application is as follows: A method for calculating yield per mu based on agricultural machinery operation data and Beidou trajectory is proposed, which comprises the following steps: S1, in a preset agricultural machinery operation cycle, real-time acquisition of agricultural machinery trajectory point coordinates, agricultural machinery driving speed, crop flow per unit time, cutting width, agricultural machinery engine speed, agricultural machinery fuel consumption, soil moisture data and field slope and recording of acquisition time nodes, construction of a multi-source data set; S2, based on the multi-source data set, a two-dimensional feature set is constructed, which includes a time-space operation effectiveness feature set and a yield data reliability feature set; the historical reference interval of each type of index in the two-dimensional feature set is obtained, and the historical reference interval of each type of index is modified according to the crop type of the current operation; based on the modified historical reference interval of each type of index, each type of index is standardized; S3, based on the time-space operation effectiveness feature set and the yield data reliability feature set after standardization, the time-space operation effectiveness comprehensive score and the yield data reliability comprehensive score are calculated; S4, based on the multi-source data set, the time-space operation effectiveness comprehensive score and the yield data reliability comprehensive score, the effective operation area is calculated and the total effective yield is calculated to obtain the yield per mu basic value; based on the soil moisture data, the yield per mu basic value is corrected to obtain the final yield per mu value.

[0006] A further improvement of this invention is that the specific content of constructing the multi-source dataset in S1 is as follows: within a preset agricultural machinery operation cycle, the coordinates of agricultural machinery trajectory points, agricultural machinery speed, crop flow rate per unit time, cutting width, agricultural machinery engine speed, agricultural machinery fuel consumption, soil moisture data, and field slope are collected in real time, and the collection time nodes are recorded; the coordinates of agricultural machinery trajectory points are the latitude and longitude coordinates during agricultural machinery operation; the crop flow rate per unit time is the mass of crops harvested by the agricultural machinery per unit time; the cutting width is the width of the crops cut by the agricultural machinery; the agricultural machinery fuel consumption is the fuel consumption of the agricultural machinery per unit time; the soil moisture data is the water content of the soil in the agricultural machinery operation area; and the field slope is the inclination angle of the ground in the agricultural machinery operation area.

[0007] A further improvement of the present invention is that step S2 includes the following specific steps: S21. Construct a feature set for the effectiveness of spatiotemporal operations. This is an index for the continuity of agricultural machinery trajectories, with a value ranging from 0 to 1. The calculation method is as follows: During agricultural machinery operation, the coordinates of adjacent trajectory points are combined into trajectory record pairs according to the recording order. The total number of trajectory record pairs is N-1, where N is the total number of recordings. The number K of trajectory record pairs where the time interval between two adjacent trajectory points is less than a preset time interval is obtained. The coverage index for agricultural machinery operation area is 0-1. It is calculated by dividing the field area into uniform grids and counting the total number of grids. The ratio of the number of grids covered by the coordinates of the agricultural machinery trajectory point to the total number of grids is obtained. This is an index for the stability of agricultural machinery travel speed, with a value ranging from 0 to 1. It is calculated by obtaining the average travel speed of the agricultural machinery. and the standard deviation of agricultural machinery travel speed The cutting width consistency index has a value of 0-1. It is calculated by obtaining the average cutting width and then comparing the standard deviation of the cutting width with the average cutting width. S22. Construct a reliability feature set for production data. This is a data consistency index for flow sensors, with a value ranging from 0 to 1. It is calculated by obtaining the average crop flow rate per unit time. and standard deviation of crop flow per unit time This is an index for the time series rationality of yield data, with a value ranging from 0 to 1. It is calculated as follows: for the crop flow rate per unit time in the i-th record... The moving average was calculated using 20 records as the sliding window length. and ; Calculate crop flow rate per unit time With the corresponding moving average absolute value of deviation Thus, the mean deviation is obtained. The yield data cross-scene matching degree index is calculated in the following manner: first, the average yield per unit area in the whole cycle is calculated represents the recorded i-th agricultural machinery driving speed, represents the recorded i-th cutting width, represents the recorded i-th unit time operation area, and the average yield per unit area of the same crop and historical soil condition is obtained .

[0008] The further improvement of the application is that the S2 further comprises: S23, obtaining a historical reference interval of each type of index in the two-dimensional feature set is a lower limit value of the historical reference interval of the f-th type of index, is an upper limit value of the historical reference interval of the f-th type of index, and a crop type adaptation coefficient of the current crop type is obtained , the historical reference interval of each type of index is corrected, and the corrected historical reference interval of each type of index is output , wherein, is a lower limit value of the corrected historical reference interval of the f-th type of index, is an upper limit value of the corrected historical reference interval of the f-th type of index, ; S24, based on the corrected historical reference interval of each type of index , each type of index is standardized, when the f-th type of index is a positive index with the larger the numerical value the better, the standardization formula is: ; when the f-th type of index is a negative index with the smaller the numerical value the better, the standardization formula is: ; f^' is the numerical value of the f-th type of index after standardization.

[0009] The further improvement of the application is that the S3 comprises the following specific steps: S31, based on the standardized spatio-temporal operation effectiveness feature set , the spatio-temporal operation effectiveness comprehensive score is calculated ; wherein, is a weight factor of the m-th index in the standardized spatio-temporal operation effectiveness feature set, and m is an index index in the standardized spatio-temporal operation effectiveness feature set; S32, based on the standardized yield data reliability feature set , the yield data reliability comprehensive score is calculated ; wherein, is a weight factor of the n-th index in the standardized yield data reliability feature set, and n is an index index in the standardized yield data reliability feature set.

[0010] The further improvement of the present application is that the S4 comprises the following specific steps: S41, extracting the agricultural machine track point coordinates in the multi-source data set, adopting Graham scanning method to perform convex polygon fitting on the track point coordinates to obtain an initial area of the operation region ; calculating a swath correction coefficient based on the swath consistency index ; combining the time-space operation effectiveness comprehensive score , to calculate the final effective operation region area ; ; S42, calculating the total effective yield in the whole period based on the crop flow per unit time in the multi-source data set and the collection time node is the interval between the time corresponding to the i+1th record and the time corresponding to the ith record ; S43, calculating the total effective yield in the whole period , and the ratio of the effective operation region area to obtain the yield basis value per unit area, and further obtain the yield basis value per mu .

[0011] The further improvement of the present application is that the S4 further comprises: S44, obtaining the mean value of the soil moisture data in the whole period in the multi-source data set , calculating a soil moisture correction coefficient ; wherein, is the standard moisture value of the current operation crop; S45, correcting the yield basis value per mu by the soil moisture correction coefficient to obtain the final yield value per mu .

[0012] The further improvement of the present application is that the value range of the crop type adaptation coefficient in the S23 is: , if the current operation crop is wheat, ; if the current operation crop is corn, ; if the current operation crop is rice, .

[0013] The technical effects of the present application are as follows: A method for calculating yield per mu based on agricultural machinery operation data and Beidou trajectory is constructed. By constructing the trajectory continuity index in the set of spatio-temporal operation effectiveness features, the continuity level is obtained by threshold statistics of the time interval between adjacent trajectory points, and it is included in the comprehensive score of spatio-temporal operation effectiveness for overall correction of the subsequent effective operation area, thereby suppressing the area error caused by trajectory point loss / abnormality from the source; the swath consistency index is constructed, and the swath correction coefficient is further introduced to correct the convex hull area, and then the final effective operation area is obtained by linking with the comprehensive score of spatio-temporal operation effectiveness, thereby reducing the cumulative error of area link caused by swath fluctuation; by introducing the cross-scene matching degree index and obtaining the historical reference interval, the interval is modified according to the crop type adaptation coefficient and then normalized, so that different crop types have an interpretable reference scale, and at the same time, the matching degree is used to suppress abnormal deviation, thereby enhancing the cross-scene comparability and self-checking ability; based on the mean value of the whole cycle soil moisture and the standard soil moisture of crops, the correction coefficient is constructed to correct the yield per mu basic value to obtain the final yield per mu value, thereby including environmental differences in the measurement closed loop, improving the comparability and interpretability of the yield per mu result, and at the same time, taking the accurate yield per mu value as the core data support of agricultural production management, providing reliable basis for decision-making scenarios such as land yield comparison, planting scheme adjustment, agricultural operation efficiency optimization, and operating income prediction, and realizing fine management of agricultural production. BRIEF DESCRIPTION OF DRAWINGS

[0014] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the accompanying drawings: Figure 1 The flowchart of the method for calculating yield per mu based on agricultural machinery operation data and Beidou trajectory of embodiment 1 of the application is shown. DETAILED DESCRIPTION

[0015] Embodiment 1: This embodiment proposes a method for calculating yield per mu based on agricultural machinery operation data and Beidou trajectory. By constructing a trajectory continuity index in the time-space operation effectiveness feature set, the continuity level is obtained by statistical analysis of the time interval threshold of adjacent trajectory points, and it is included in the comprehensive score of time-space operation effectiveness for overall correction of the subsequent effective operation area, thereby suppressing the area error caused by trajectory point loss / abnormality from the source; a cutting width consistency index is constructed, and a cutting width correction coefficient is further introduced to correct the convex hull area, and then the final effective operation area is obtained through the linkage of the comprehensive score of time-space operation effectiveness, thereby reducing the cumulative error of the area link caused by cutting width fluctuation; by introducing a cross-scene matching degree index and obtaining a historical reference interval, the interval is modified according to the crop type adaptation coefficient and then normalized, so that different crop types have an interpretable reference scale, and the matching degree is used to suppress abnormal deviation, thereby enhancing the cross-scene comparability and self-checking ability; based on the mean value of the whole cycle soil moisture and the standard soil moisture of crops, a correction coefficient is constructed to correct the yield per mu basic value to obtain the final yield per mu value, thereby including environmental differences in the measurement closed loop, improving the comparability and interpretability of the yield per mu result, and taking the accurate yield per mu value as the core data support for agricultural production management, providing a reliable basis for decision-making scenarios such as plot yield comparison, planting scheme adjustment, agricultural operation efficiency optimization, and operating income prediction, and realizing fine management of agricultural production. Specifically, as shown in Figure 1 The method for calculating yield per mu based on agricultural machinery operation data and Beidou trajectory proposed in this embodiment includes the following specific steps: S1, in a preset agricultural machinery operation cycle, real-time acquisition of agricultural machinery trajectory point coordinates, agricultural machinery driving speed, crop flow per unit time, cutting width, agricultural machinery engine speed, agricultural machinery fuel consumption, soil moisture data and field slope and recording the acquisition time node, constructing a multi-source data set; S2, based on the multi-source data set, a two-dimensional feature set is constructed, which includes a time-space operation effectiveness feature set and a yield data reliability feature set; the historical reference interval of each type of index in the two-dimensional feature set is obtained, and the historical reference interval of each type of index is modified according to the crop type of the current operation; based on the modified historical reference interval of each type of index, each type of index is standardized; S3, based on the standardized time-space operation effectiveness feature set and the yield data reliability feature set, the comprehensive score of time-space operation effectiveness and the comprehensive score of yield data reliability are calculated; S4, based on the multi-source data set, the comprehensive score of time-space operation effectiveness and the comprehensive score of yield data reliability, the effective operation area is calculated and the total effective yield is calculated to obtain the yield per mu basic value; based on the soil moisture data, the yield per mu basic value is corrected to obtain the final yield per mu value.

[0016] In the embodiment, the specific content of constructing the multi-source data set in S1 is: in a preset agricultural machine operation period, real-time collection of agricultural machine track point coordinates, agricultural machine travel speed, crop flow per unit time, cutting width, agricultural machine engine speed, agricultural machine fuel consumption, soil moisture data, and field slope and recording of collection time nodes; the agricultural machine track point coordinates are longitude and latitude coordinates in the agricultural machine operation process; the crop flow per unit time is the mass of the harvested crops per unit time; the cutting width is the width of the cut crops; the agricultural machine fuel consumption is the fuel consumption per unit time; the soil moisture data is the water content of the soil in the agricultural machine operation area; and the field slope is the inclination angle of the ground in the agricultural machine operation area.

[0017] In the embodiment, S2 includes the following specific steps: S21, constructing a time-space operation effectiveness feature set is an agricultural machine track continuity index, with a value of 0-1, and the calculation method is: adjacent track point coordinates in the agricultural machine operation process are combined into track record pairs in the recording order, the total number of track record pairs is N-1, N is the total number of records, the number K of track record pairs corresponding to two adjacent track points with a collection time interval less than a preset time interval is obtained, is an agricultural machine operation area coverage index, with a value of 0-1, and the calculation method is: the field area is divided into grids with uniform areas and the total number of grids is counted, and the ratio of the number of grids covered by the agricultural machine track point coordinates to the total number of grids is obtained; is an agricultural machine travel speed stability index, with a value of 0-1, and the calculation method is: the average value of the agricultural machine travel speed and the standard deviation of the agricultural machine travel speed is a cutting width consistency index, with a value of 0-1, and the calculation method is: the average value of the cutting width is obtained, and the ratio of the standard deviation of the cutting width to the average value of the cutting width is obtained; S22, constructing a yield data reliability feature set is a flow sensor data consistency index, with a value of 0-1, and the calculation method is: the average value of the crop flow per unit time and the standard deviation of the crop flow per unit time is a yield data time sequence rationality index, with a value of 0-1, and the calculation method is: for the crop flow per unit time of the i-th record , the sliding average value is calculated with 20 records as the sliding window length and ; the deviation absolute value of the crop flow per unit time from the corresponding sliding average value is calculated, and then the average deviation The yield data cross-scene matching degree index is calculated in the following manner: first, the average yield per unit area in the whole cycle is calculated represents the i-th recorded agricultural machinery driving speed, represents the i-th recorded cutting width, represents the i-th recorded unit time operation area, and the average yield per unit area of the same crop and soil condition history is obtained .

[0018] In this embodiment, the S2 further includes: S23, obtaining the historical reference interval of each type of index in the two-dimensional feature set is the lower limit value of the historical reference interval of the f-th type of index, is the upper limit value of the historical reference interval of the f-th type of index, and the crop type adaptation coefficient of the current crop type is obtained , the historical reference interval of each type of index is corrected, and the corrected historical reference interval of each type of index is output , wherein, is the lower limit value of the corrected historical reference interval of the f-th type of index, is the upper limit value of the corrected historical reference interval of the f-th type of index, ; S24, based on the corrected historical reference interval of each type of index , each type of index is standardized, when the f-th type of index is a positive index with the larger the numerical value the better, the standardization formula is: ; when the f-th type of index is a negative index with the smaller the numerical value the better, the standardization formula is: ; f' is the numerical value of the f-th type of index after standardization.

[0019] In this embodiment, the S3 includes the following specific steps: S31, based on the standardized spatio-temporal operation effectiveness feature set , the spatio-temporal operation effectiveness comprehensive score is calculated ; wherein, is the weight factor of the m-th index in the standardized spatio-temporal operation effectiveness feature set, and m is the index index in the standardized spatio-temporal operation effectiveness feature set; S32, based on the standardized yield data reliability feature set , the yield data reliability comprehensive score is calculated ; wherein, is the weight factor of the n-th index in the standardized yield data reliability feature set, and n is the index index in the standardized yield data reliability feature set.

[0020] In this embodiment, step S4 includes the following specific steps: S41. Extract the coordinates of agricultural machinery trajectory points from the multi-source dataset, and use the Graham scan method to fit the trajectory point coordinates to a convex hull polygon to obtain the initial area of ​​the working area. Based on the consistency index of cutting width Calculate the cutting width correction coefficient A comprehensive evaluation combining the effectiveness of spatiotemporal operations. Calculate the final effective working area. ; S42. Calculate the total effective yield over the entire cycle based on the crop flow per unit time and the data collection time nodes in the multi-source dataset. The time corresponding to the (i+1)th record The time corresponding to the i-th record The interval; S43. Calculate the total effective output over the entire cycle. and effective working area The ratio is used to obtain the basic value of yield per unit area, and then the basic value of yield per mu (unit of land area). .

[0021] In this embodiment, S4 further includes: S44. Obtain the average value of soil moisture data for the entire period from multiple sources. Calculate the soil moisture correction factor ;in, This represents the standard soil moisture value for the current crop being cultivated. S45. The baseline yield per mu is precisely corrected using the soil moisture correction coefficient to obtain the final yield per mu. .

[0022] In this embodiment, the crop type adaptation coefficient in S23 The range of values ​​for is: If the current crop is wheat, If the current crop is corn, If the current crop is rice, .

[0023] The threshold and weight settings can be based on the default settings of this invention, or they can be set by the operator.

[0024] Example 2: This example provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory by calling the computer program stored in the memory.

[0025] The electronic device can have great differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the hectare yield metering method based on agricultural machinery operation data and Beidou track provided by the above method embodiments. The electronic device can also include other components for realizing device functions, for example, the electronic device can also have wired or wireless network interfaces and input and output interfaces and the like to input and output data. This embodiment will not be described here.

[0026] Those skilled in the art understand that the present application can be implemented as a system, a method or a computer program product. Therefore, the present disclosure can be embodied in the form of a complete hardware, a complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present application can also be implemented as a computer program product in one or more computer readable media, which contains computer readable program code.

[0027] Any combination of one or more computer readable medium can be used. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fibers, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus.

[0028] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flows and blocks in the block diagrams. Figure 1 one or more functions specified in the flowchart or flows and blocks in the block diagrams. Figure 1 one or more functions specified in the flowchart or flows and blocks in the block diagrams.

[0029] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flows and blocks in the block diagrams. Figure 1 one or more functions specified in the flowchart or flows and blocks in the block diagrams. Figure 1 one or more functions specified in the flowchart or flows and blocks in the block diagrams.

[0030] The embodiments of the present application described above are merely intended to illustrate the present application, but not to limit the present application. The above-described embodiments are merely illustrative, but not limiting, and any person skilled in the art can make many modifications without departing from the spirit and scope of the present application, and these modifications are also within the scope of the present application.

Claims

1. A method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory, characterized by: The specific steps include the following: S1. Within the preset agricultural machinery operation cycle, collect real-time data on agricultural machinery trajectory point coordinates, agricultural machinery driving speed, crop flow rate per unit time, cutting width, agricultural machinery engine speed, agricultural machinery fuel consumption, soil moisture data, and field slope, and record the collection time nodes to construct a multi-source dataset. S2. Construct a two-dimensional feature set based on multi-source datasets. The two-dimensional feature set includes a spatiotemporal operation effectiveness feature set and a yield data credibility feature set. Obtain the historical reference interval of each type of indicator in the two-dimensional feature set, and correct the historical reference interval of each type of indicator according to the crop type of the current operation. Based on the corrected historical reference interval of each type of indicator, perform standardization processing on each type of indicator. S3. Based on the standardized spatiotemporal operation effectiveness feature set and output data credibility feature set, calculate the comprehensive score of spatiotemporal operation effectiveness and the comprehensive score of output data credibility. S4. Based on multi-source datasets, comprehensive scores of spatiotemporal operation effectiveness and yield data credibility, complete the calculation of effective operation area and total effective yield to obtain the basic yield per mu; based on soil moisture data, perform accuracy correction on the basic yield per mu to obtain the final yield per mu.

2. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 1, characterized in that: The specific content of constructing the multi-source dataset in S1 is as follows: within a preset agricultural machinery operation cycle, real-time collection of agricultural machinery trajectory point coordinates, agricultural machinery driving speed, crop flow rate per unit time, cutting width, agricultural machinery engine speed, agricultural machinery fuel consumption, soil moisture data, and field slope is recorded, and the collection time nodes are recorded; the agricultural machinery trajectory point coordinates are the latitude and longitude coordinates during agricultural machinery operation; the crop flow rate per unit time is the mass of crops harvested by the agricultural machinery per unit time; the cutting width is the width of the crops cut by the agricultural machinery; the agricultural machinery fuel consumption is the fuel consumption of the agricultural machinery per unit time; the soil moisture data is the soil moisture content of the agricultural machinery operation area; and the field slope is the tilt angle of the ground in the agricultural machinery operation area.

3. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 2, characterized in that: S2 includes the following specific steps: S21. Construct a feature set for the effectiveness of spatiotemporal operations. This is an index for the continuity of agricultural machinery trajectories, with a value ranging from 0 to 1. The calculation method is as follows: During agricultural machinery operation, the coordinates of adjacent trajectory points are combined into trajectory record pairs according to the recording order. The total number of trajectory record pairs is N-1, where N is the total number of recordings. The number K of trajectory record pairs where the time interval between two adjacent trajectory points is less than a preset time interval is obtained. The coverage index for agricultural machinery operation area is 0-1. It is calculated by dividing the field area into uniform grids and counting the total number of grids. The ratio of the number of grids covered by the coordinates of the agricultural machinery trajectory point to the total number of grids is obtained. This is an index for the stability of agricultural machinery travel speed, with a value ranging from 0 to 1. It is calculated by obtaining the average travel speed of the agricultural machinery. and the standard deviation of agricultural machinery travel speed The cutting width consistency index has a value of 0-1. It is calculated by obtaining the average cutting width and then comparing the standard deviation of the cutting width with the average cutting width. S22. Construct a reliability feature set for production data. This is a data consistency index for flow sensors, with a value ranging from 0 to 1. It is calculated by obtaining the average crop flow rate per unit time. and standard deviation of crop flow per unit time This is an index for the time series rationality of yield data, with a value ranging from 0 to 1. It is calculated as follows: for the crop flow rate per unit time in the i-th record... The moving average was calculated using 20 records as the sliding window length. and ; Calculate crop flow per unit time With the corresponding moving average absolute value of deviation Thus, the mean deviation is obtained. The cross-scenario matching index for production data is calculated as follows: first, calculate the average yield per unit area over the entire cycle. This represents the speed of the agricultural machinery recorded in the i-th instance. This represents the width of the cut in the i-th record. This represents the area worked per unit time in the i-th record, and the average yield per unit area for the same crop under the same soil moisture conditions is obtained historically. .

4. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 3, characterized in that: S2 further includes: S23. Obtain the historical reference interval for each type of indicator in the two-dimensional feature set. This is the lower limit of the historical reference range for the f-th type of indicator. Given the upper limit of the historical reference interval for the f-th index, obtain the crop type fit coefficient for the current crop type. The historical reference interval for each type of indicator is adjusted, and the adjusted historical reference interval for each type of indicator is output. ,in, This is the lower limit of the historical reference range after correction for the f-th type of indicator. This represents the upper limit of the historical reference range after correction for the f-th type of indicator. ; S24. Historical reference intervals adjusted based on each type of indicator. For each type of indicator, standardization is performed. When the f-th type of indicator is a positive indicator where a larger value is better, the standardization formula is: When the f-th type of indicator is a negative indicator where smaller values ​​are better, the standardization formula is: f^' represents the standardized value of the f-th type of index.

5. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 4, characterized in that: S3 includes the following specific steps: S31. Feature set of spatiotemporal operation effectiveness based on standardized processing Calculate the comprehensive score of the effectiveness of spatiotemporal operations. ;in, , is the weight factor of the m-th indicator in the standardized spatiotemporal operation effectiveness feature set, where m is the index of the indicator in the standardized spatiotemporal operation effectiveness feature set; S32. Reliability Feature Set Based on Standardized Production Data Calculate the overall reliability score of production data. in, is the weight factor of the nth indicator in the standardized production data credibility feature set, where n is the index of the indicator in the standardized production data credibility feature set.

6. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 5, characterized in that: S4 includes the following specific steps: S41. Extract the coordinates of agricultural machinery trajectory points from the multi-source dataset, and use the Graham scan method to fit the trajectory point coordinates to a convex hull polygon to obtain the initial area of ​​the working area. Based on the consistency index of cutting width Calculate the cutting width correction coefficient A comprehensive evaluation combining the effectiveness of spatiotemporal operations. Calculate the final effective working area. ; S42. Calculate the total effective yield over the entire cycle based on the crop flow per unit time and the data collection time nodes in the multi-source dataset. The time corresponding to the (i+1)th record The time corresponding to the i-th record The interval; S43. Calculate the total effective output over the entire cycle. and effective working area The ratio is used to obtain the basic value of yield per unit area, and then the basic value of yield per mu (unit of land area). .

7. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 6, characterized in that: S4 further includes: S44. Obtain the average value of soil moisture data for the entire period from multiple sources. Calculate the soil moisture correction factor ;in, This represents the standard soil moisture value for the current crop being cultivated. S45. The baseline yield per mu is precisely corrected using the soil moisture correction coefficient to obtain the final yield per mu. .

8. The method for measuring yield per mu based on agricultural machinery operation data and Beidou trajectory according to claim 4, characterized in that: The crop type matching coefficient in S23 The range of values ​​for is: If the current crop is wheat, If the current crop is corn, If the current crop is rice, .

Images