Farmer household potential analysis method, device, equipment and medium

Abstract

The invention relates to the technical field of data processing, in particular to a grower potential analysis method, device and equipment and a medium, and the method comprises the steps: firstly screening out a plurality of target crop types according to the historical planting times and the total planting area; determining a first planting proficiency measurement parameter according to the change condition of a plurality of NDVI values corresponding to the same target crop variety in the same period of each planting year, then obtaining a second planting proficiency measurement parameter according to the number of the planting years and the planting area, and carrying out weighted sum calculation to obtain a target planting proficiency, and performing score mapping to obtain a target planting potential score. According to the method, analysis can be carried out from a plurality of dimensions influencing the planting proficiency of the farmer households, so that the more accurate and reliable planting proficiency is obtained, and the planting potential of the farmer households is reflected.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method, device, equipment and medium for analyzing the potential of growers. Background Art

[0002] The Normalized Difference Vegetation Index (NDVI) is an important indicator that reflects the degree of surface vegetation coverage. The vegetation coverage index is closely related to the growth status and distribution density of vegetation. Therefore, it can be used as a measure of the planting proficiency of growers.

[0003] At present, in the task of analyzing the potential of growers, there is no unified judgment standard for the planting proficiency of growers, and the specific planting potential of each grower cannot be known. When allocating growers to large planting areas or allowing them to contract on their own, it is impossible to select growers with high planting proficiency, that is, high planting potential. Therefore, it is necessary to analyze and tap the potential of growers' planting proficiency to improve planting income. However, the current technical methods usually rely on subjective judgment and experience when analyzing the potential of growers, which are easily affected by the personal bias of the evaluator, resulting in low accuracy and reliability of the analysis results. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, equipment and medium for analyzing the planting potential of growers, which can analyze from multiple dimensions that affect the planting proficiency of growers, and then obtain more accurate and reliable planting proficiency to reflect the planting potential of growers.

[0005] According to a first aspect of the present invention, a method for analyzing the potential of growers is provided, comprising the following steps:

[0006] According to the first crop planting information set of the target grower in the past n years, several target crop types are screened out; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type.

[0007] For any target crop type, the target NDVI fluctuation degree corresponding to the target crop type is obtained according to the NDVI values ​​corresponding to several target time points in each year within the historical n years, and the target NDVI fluctuation degree is determined as the first planting proficiency measurement parameter; the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop type.

[0008] According to the number of planting years of the target growers in the historical n years and the planting area corresponding to each planting year, the second planting proficiency measurement parameter is obtained.

[0009] The target planting proficiency is obtained according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter and the corresponding preset parameter weights.

[0010] The target planting proficiency is normalized to obtain a target planting potential score of the target grower corresponding to the target crop type.

[0011] Furthermore, the target crop types are screened through the following steps:

[0012] The crop types in the first planted crop information set whose planting times are less than the first quantity threshold and whose total planting area is less than the second quantity threshold are deleted to obtain a second planted crop information set.

[0013] According to the number of plantings of each crop type and the total planting area of ​​each crop type in the second crop information set, as well as the preset planting weights corresponding to the number of plantings and the total planting area, weighted sums are calculated to obtain the planting priority of each crop type in the second crop information set.

[0014] The crop types in the second crop information set whose corresponding planting priority is greater than a preset priority threshold are determined as target crop types.

[0015] Furthermore, the target NDVI fluctuation degree corresponding to the target crop type is obtained through the following steps:

[0016] According to the number of times the target crop type is planted in the history n, a number of NDVI values ​​corresponding to the target crop type at any target time point is obtained; the number of NDVI values ​​corresponding to the target crop type at any target time point is equal to the number of times the target crop type is planted in the history n.

[0017] According to several NDVI values ​​corresponding to the target crop type at any target time point, the initial NDVI fluctuation degree corresponding to the target crop type at any target time point is obtained.

[0018] The reciprocal of the average value of the m initial NDVI fluctuation degrees of the target crop type at the m target time points is taken as the target NDVI fluctuation degree corresponding to the target crop type.

[0019] Furthermore, the second planting proficiency measurement parameter is obtained through the following steps:

[0020] According to the continuity of the target growers' planting years within the historical n years, the historical n years are divided into several year segments.

[0021] Based on the number of planting years in each year segment, the planting proficiency measurement parameters corresponding to each year segment are obtained according to the arithmetic progression summation method, and the sum of the planting proficiency measurement parameters corresponding to each year segment is used as the first sub-measurement parameter, wherein the first term and tolerance corresponding to the arithmetic progression summation method are both preset parameters.

[0022] Based on the preset planting area benchmark value, the area ratio of the planting area corresponding to each planting year to the planting area benchmark value is obtained, and the sum of the obtained several area ratios is used as the second sub-measurement parameter.

[0023] A weighted sum is calculated for the first sub-measurement parameter and the second sub-measurement parameter, and the calculation result is used as the second planting proficiency measurement parameter.

[0024] Furthermore, the method further comprises the following steps:

[0025] According to the preset maximum planting potential score, the maximum planting potential score is evenly divided into several initial score ranges.

[0026] The score error probability corresponding to the target planting potential score is calculated based on the target planting potential score and the key score in the target score interval; the target score interval refers to the initial score interval in which the target planting potential score is located; the key score in the target score interval refers to the planting potential score with the largest number of identical scores obtained based on several historical planting potential scores in the target score interval.

[0027] The score error probability is input as a probability parameter into the preset cross entropy loss function, and the output loss value is determined as the random score error.

[0028] The sum of the target planting potential score and the random score error was determined as the final planting potential score.

[0029] According to a second aspect of the present invention, a planter potential analysis device is provided, the device comprising:

[0030] The screening module is used to screen out several target crop types based on the first crop planting information set of the target grower in the past n years; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type.

[0031] The first acquisition module is used to obtain the target NDVI fluctuation degree corresponding to any target crop type according to the NDVI values ​​corresponding to several target time points of each year in the historical n years of the target crop type, and determine the target NDVI fluctuation degree as the first planting proficiency measurement parameter; the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop type.

[0032] The second acquisition module is used to obtain the second planting proficiency measurement parameter according to the number of planting years of the target grower in the historical n years and the planting area corresponding to each planting year.

[0033] The third acquisition module is used to acquire the target planting proficiency according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter and the corresponding preset parameter weights.

[0034] The first calculation module is used to normalize the target planting proficiency to obtain a target planting potential score of the target grower corresponding to the target crop type.

[0035] Furthermore, the screening module includes:

[0036] The deletion module is used to delete the crop types in the first crop information set whose planting times are less than the first quantity threshold and whose total planting area is less than the second quantity threshold, so as to obtain the second crop information set.

[0037] The second calculation module is used to calculate the planting priority of each crop type in the second crop information set by performing weighted sum calculations based on the number of plantings of each crop type and the total planting area of ​​each crop type in the second crop information set, as well as the preset planting weights corresponding to the number of plantings and the total planting area.

[0038] The first determination module is used to determine the crop types in the second crop information set whose corresponding planting priority is greater than a preset priority threshold as target crop types.

[0039] Furthermore, the first acquisition module includes:

[0040] The fourth acquisition module is used to obtain a number of NDVI values ​​corresponding to the target crop type at any target time point according to the number of times the target crop type is planted in the history n; the number of NDVI values ​​corresponding to the target crop type at any target time point is equal to the number of times the target crop type is planted in the history n.

[0041] The fifth acquisition module is used to acquire the initial NDVI fluctuation degree corresponding to the target crop type at any target time point according to a plurality of NDVI values ​​corresponding to the target crop type at any target time point.

[0042] The sixth acquisition module is used to take the reciprocal of the average value of m initial NDVI fluctuation degrees of the target crop type at m target time points as the target NDVI fluctuation degree corresponding to the target crop type.

[0043] Furthermore, the second acquisition module includes:

[0044] The first division module is used to divide the historical n years into several year segments according to the continuity of the planting years of the target growers in the historical n years.

[0045] The seventh acquisition module is used to obtain the planting proficiency measurement parameters corresponding to each year segment based on the number of planting years in each year segment according to the arithmetic progression summation method, and take the sum of the planting proficiency measurement parameters corresponding to each year segment as the first sub-measurement parameter, wherein the first term and tolerance corresponding to the arithmetic progression summation method are both preset parameters.

[0046] The eighth acquisition module is used to obtain the area ratio of the planting area corresponding to each planting year to the planting area benchmark value based on the preset planting area benchmark value, and use the sum of the obtained several area ratios as the second sub-measurement parameter.

[0047] The third calculation module is used to calculate the weighted sum of the first sub-measurement parameter and the second sub-measurement parameter, and use the calculation result as the second planting proficiency measurement parameter.

[0048] Furthermore, a score compensation module is also included, and the score compensation module includes:

[0049] The second division module is used to evenly divide the highest planting potential score into a number of initial score intervals according to a preset highest planting potential score.

[0050] The fourth calculation module is used to calculate the score error probability corresponding to the target planting potential score based on the target planting potential score and the key score in the target score interval; the target score interval refers to the initial score interval in which the target planting potential score is located; the key score in the target score interval refers to the planting potential score with the largest number of identical scores obtained based on several historical planting potential scores in the target score interval.

[0051] The second determination module is used to input the score error probability as a probability parameter into a preset cross entropy loss function, and determine the output loss value as a random score error.

[0052] The third determination module is used to determine the sum of the target planting potential score and the random score error as the final planting potential score.

[0053] According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned grower potential analysis method when executing the computer program.

[0054] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned grower potential analysis method when executed by a processor.

[0055] Compared with the prior art, the present invention has at least the following beneficial effects:

[0056] The method for analyzing the potential of growers described in the present invention first selects several target crop types based on the number of plantings and the total planting area of ​​each crop type in the historical n years, and determines the first planting proficiency measurement parameter based on the changes in several NDVI values ​​corresponding to the same target crop type in the same period of each planting year, and then obtains the second planting proficiency measurement parameter based on the number of planting years and the planting area corresponding to each planting year, and calculates the weighted sum to obtain the target planting proficiency, and finally obtains the target planting potential score after score mapping. It can be seen that the target planting potential score is obtained through the comprehensive influence of three dimensions, namely the target NDVI fluctuation degree, the number of planting years and the planting area corresponding to each planting year. The present invention can analyze from multiple dimensions that affect the planting proficiency of growers, and then obtain more accurate and reliable planting proficiency to reflect the planting potential of growers. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 A flow chart of a method for analyzing the potential of growers provided in Embodiment 1 of the present invention;

[0059] Figure 2 A flowchart of step S100 provided in Embodiment 1 of the present invention;

[0060] Figure 3 A flowchart of step S200 provided in the first embodiment of the present invention;

[0061] Figure 4 A flowchart of step S300 provided in the first embodiment of the present invention;

[0062] Figure 5 A flow chart of the steps of determining a final planting potential score provided in the first embodiment of the present invention;

[0063] Figure 6 A schematic diagram of the structure of a planter potential analysis device provided in Embodiment 2 of the present invention;

[0064] Figure 7 A schematic diagram of the structure of the screening module 100 provided in the second embodiment of the present invention;

[0065] Figure 8 A schematic diagram of the structure of the first acquisition module 200 provided in the second embodiment of the present invention;

[0066] Fig. 9 A schematic diagram of the structure of a second acquisition module 300 provided in Embodiment 2 of the present invention;

[0067] Fig.10 This is a schematic diagram of the structure of a score compensation module provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0069] Embodiment 1

[0070] like Figure 1 As shown, this embodiment 1 provides a method for analyzing the potential of growers, comprising the following steps:

[0071] S100, screening out a number of target crop types based on the first crop planting information set of the target grower in the past n years; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type.

[0072] Specifically, the planting frequency of a crop type refers to the number of years in which the crop corresponding to the crop type itself is planted within the past n years. For example, in the past 10 years, the number of years in which tobacco leaves are planted is 7, and the planting frequency is 7.

[0073] Specifically, the total planting area of ​​a crop type refers to the total area of ​​crops corresponding to the crop type itself planted in the historical n years.

[0074] In a specific embodiment, Figure 2 As shown, in step S100, the target crop types are screened through the following steps:

[0075] S101, delete the crop types in the first crop information set whose planting times are less than a first quantity threshold and whose total planting area is less than a second quantity threshold, to obtain a second crop information set. Those skilled in the art can set the first quantity threshold and the second quantity threshold according to actual needs.

[0076] S102, based on the number of plantings of each crop type and the total planting area of ​​each crop type in the second crop information set, as well as the preset planting weights corresponding to the number of plantings and the total planting area, respectively, a weighted sum is calculated to obtain the planting priority of each crop type in the second crop information set; it can be understood as: for any crop type, a weighted sum of the number of plantings of the crop type and the total planting area of ​​the crop type is calculated to obtain the planting priority of the crop type.

[0077] S103: Determine the crop types in the second crop information set whose corresponding planting priority is greater than a preset priority threshold as target crop types.

[0078] As mentioned above, when considering the planting proficiency of the target growers for each type of crop planted, since the crop types with fewer planting times and total planting areas can reflect that the target growers have lower proficiency in this crop type, a first screening is implemented, and then a second screening is performed among the screened crop types, so that the screened target crop types are the crop types with relatively high planting proficiency of the target growers.

[0079] S200, for any target crop type, according to the NDVI values ​​corresponding to several target time points of each year in the historical n years of the target crop type, the target NDVI fluctuation degree corresponding to the target crop type is obtained, and the target NDVI fluctuation degree is determined as the first planting proficiency measurement parameter.

[0080] Specifically, the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop species; it can be understood that: the growth cycle is divided into several time slices, and the connecting time point of each two adjacent time slices is used as the target time point, and each time the crop species is planted, the NDVI values ​​are obtained at several fixed time points; for example, the growth cycle of a random target crop species is January to May, and February 1, March 1, and April 1 of each year can be used as target time points.

[0081] In a specific embodiment, Figure 3 As shown, step S200 includes the following steps:

[0082] S201, according to the number of planting times of the target crop type in the history n, obtain a number of NDVI values ​​corresponding to the target crop type at any target time point; the number of NDVI values ​​corresponding to the target crop type at any target time point is equal to the number of planting times of the target crop type in the history n. For example: if the target crop type is not planted in a certain year, the NDVI value of that year is not considered. If the number of planting times in the history n years is 5, and one of the target time points is February 1, then 5 NDVI values ​​can be obtained at the target time point, that is, one NDVI value can be obtained on February 1 of each planting year.

[0083] S202, obtaining the initial NDVI fluctuation degree corresponding to the target crop type at any target time point according to a number of NDVI values ​​corresponding to the target crop type at any target time point.

[0084] Specifically, the initial NDVI fluctuation degree S of the target crop type at any target time point meets the following conditions:

[0085] S = sqrt(((x 1 -x) 2 +(x 2 -x) 2 +......(x d -x) 2 ) / (d-1)), where d is the number of NDVI values ​​corresponding to the target crop type at any target time point, x d is the dth NDVI value corresponding to the target crop type at any target time point, x is the average of several NDVI values ​​corresponding to the target crop type at any target time point, and sqrt() is the square root function.

[0086] S203, taking the reciprocal of the average value of m initial NDVI fluctuation degrees corresponding to the target crop type at m target time points as the target NDVI fluctuation degree corresponding to the target crop type.

[0087] As mentioned above, by analyzing the changes in NDVI values ​​of target crop types in the same period of each planting year, the differences in growth status of target crop types can be grasped. When the growth status differences of target crop types in the same period are large, it can reflect that the planting proficiency of the target growers is low. Taking into account unexpected situations in the growth cycle, the inverse of the average value of the NDVI fluctuation degree is used as the target NDVI fluctuation degree, which can accurately and reliably reflect the planting proficiency of the target growers to a certain extent.

[0088] S300, obtaining a second planting proficiency measurement parameter according to the number of planting years of the target grower in the historical n years and the planting area corresponding to each planting year.

[0089] In a specific embodiment, Figure 4 As shown, step S300 includes the following steps:

[0090] S301, according to the continuity of the planting years of the target growers in the past n years, the historical n years are divided into a number of year segments. For example, in the past 10 years, the target crop type was planted in the 1st, 2nd, 3rd, 6th, 7th, 9th, and 10th years from the most recent to the most distant, and the year segments divided are 1-3 years, 6-7 years, and 9-10 years.

[0091] S302, based on the number of planting years in each year segment, obtain the planting proficiency measurement parameter corresponding to each year segment according to the arithmetic progression summation method, and use the sum of the planting proficiency measurement parameters corresponding to each year segment as the first sub-measurement parameter, wherein the first term and the tolerance corresponding to the arithmetic progression summation method are both preset parameters. Generally, the first term is 1, and the tolerance is not greater than 1. For example, for the year segments divided as described above, the first term can be set to 1, the tolerance can be set to 1, the planting proficiency measurement parameter corresponding to the first year segment is 1+2+3, and the final first sub-measurement parameter is (1+2+3)+(1+2)+(1+2)=12.

[0092] S303, based on the preset planting area benchmark value, obtain the area ratio of the planting area corresponding to each planting year to the planting area benchmark value, and use the sum of the obtained area ratios as the second sub-measurement parameter. For example, if the planting area benchmark value is set to 10 mu, when the planting area is 5 mu, the corresponding area ratio is 0.5, and when the planting area is 15 mu, the corresponding area ratio is 1.5.

[0093] S304, calculating the weighted sum of the first sub-measurement parameter and the second sub-measurement parameter, and using the calculation result as the second planting proficiency measurement parameter; it can be understood as: calculating the weighted sum of the first sub-measurement parameter and the second sub-measurement parameter according to the first preset weight corresponding to the number of planting years and the second preset weight corresponding to the planting area.

[0094] Specifically, the second planting proficiency measurement parameter L meets the following conditions:

[0095] L=W 1 ×(∑ g h＝1 A h )+W 2 ×(∑ d e＝1 (B e / B)), where A h is the planting proficiency measurement parameter corresponding to the h-th year segment, g is the number of year segments, Be is the planting area corresponding to the e-th planting year, B is the preset planting area benchmark value, d is the number of planting years in the history of n years, W 1 is the first parameter weight corresponding to the first sub-measurement parameter, W 2 is the second parameter weight corresponding to the second sub-measurement parameter.

[0096] As mentioned above, considering that the accumulation of planting years will have a positive impact on planting proficiency, and that not planting a certain type of crop in the middle will lead to unfamiliarity, and the size of the annual planting area will also affect the planting proficiency, the comprehensive consideration of the number of planting years and the planting area can further reflect the planting proficiency of the target growers.

[0097] S400: Obtain a target planting proficiency according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter, and the corresponding preset parameter weights.

[0098] Specifically, the target planting proficiency Z meets the following conditions:

[0099] Z=W 3 ×K+W 4 ×L, where K is the first planting proficiency measurement parameter, W 3 is the preset parameter weight corresponding to the first planting proficiency measurement parameter, W 4 The preset parameter weights corresponding to the second planting proficiency measurement parameters.

[0100] S500, normalizing the target planting proficiency to obtain a target planting potential score of the target grower corresponding to the target crop type.

[0101] Specifically, the target planting potential score Y meets the following conditions:

[0102] Y=R / (1+exp(-z)), wherein R is the preset maximum planting potential score; it can be understood that: R represents the R point system, for example, when the percentage system is set, R=100, and when the ten-point system is set, R=10.

[0103] As mentioned above, considering that with the gradual increase of planting years and the increase of total planting area, the planting proficiency of target growers will not increase significantly all the time, but will increase more and more slowly and approach the peak value, the above normalization method is used to obtain a more reasonable and reliable target planting potential score to reflect the planting potential of the target growers.

[0104] In a specific embodiment, Figure 5 As shown, the method further comprises the following steps:

[0105] S10, according to the preset maximum planting potential score, the maximum planting potential score is evenly divided into a number of initial score intervals. For example, when R=100, it can be divided into 5 initial score intervals, namely [0-20] points, (20-40] points, (40-60] points, (60-80] points, and (80-100] points.

[0106] S20, calculate the score error probability corresponding to the target planting potential score based on the target planting potential score and the key score in the target score interval; the target score interval refers to the initial score interval in which the target planting potential score is located; the key score in the target score interval refers to the planting potential score with the largest number of identical scores obtained based on several historical planting potential scores in the target score interval.

[0107] Specifically, the score error probability P corresponding to the planting potential score meets the following conditions:

[0108] P=|(YY 0 )| / r, where Y 0 is the key score in the target score range, and r is the upper limit of the target score range.

[0109] S30, inputting the score error probability as a probability parameter into a preset cross entropy loss function, and determining the output loss value as a random score error.

[0110] Specifically, the random score error C meets the following conditions:

[0111] C = ±log(P), where YY 0 <0, C=-log(P), when YY 0 When >0, C=log(P).

[0112] It should be noted that in a special case, YY 0 When =0, the random score error is 0.

[0113] S40, determining the sum of the target planting potential score and the random score error as the final planting potential score.

[0114] As mentioned above, since the calculated target planting potential score, that is, the corresponding target planting proficiency may be different from the actual planting proficiency, it is necessary to compensate for it. Based on the target planting potential score and several historical planting potential scores, the score error probability is calculated, and then the random score error is obtained. The random score error is compensated for the target planting potential score to eliminate certain error influences, which can improve the accuracy of the obtained planting proficiency of the target growers.

[0115] Embodiment 2

[0116] like Figure 6 As shown, this embodiment 2 provides a planter potential analysis device, the device comprising:

[0117] The screening module 100 is used to screen out several target crop types based on the first crop planting information set of the target grower in the past n years; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type.

[0118] Specifically, the planting frequency of a crop type refers to the number of years in which the crop corresponding to the crop type itself is planted within the past n years. For example, in the past 10 years, the number of years in which tobacco leaves are planted is 7, and the planting frequency is 7.

[0119] Specifically, the total planting area of ​​a crop type refers to the total area of ​​crops corresponding to the crop type itself planted in the historical n years.

[0120] In a specific embodiment, Figure 7 As shown, the screening module 100 includes:

[0121] The deletion module 101 is used to delete the crop types in the first crop information set whose planting times are less than the first quantity threshold and whose total planting area is less than the second quantity threshold, to obtain a second crop information set. Those skilled in the art can set the first quantity threshold and the second quantity threshold according to actual needs.

[0122] The second calculation module 102 is used to calculate the planting priority of each crop type in the second crop information set by performing weighted sum calculation based on the number of plantings of each crop type and the total planting area of ​​each crop type in the second crop information set, as well as the preset planting weights corresponding to the number of plantings and the total planting area; it can be understood that: for any crop type, the weighted sum of the number of plantings of the crop type and the total planting area of ​​the crop type is calculated to obtain the planting priority of the crop type.

[0123] The first determination module 103 is used to determine the crop types in the second crop information set whose corresponding planting priority is greater than a preset priority threshold as target crop types.

[0124] As mentioned above, when considering the planting proficiency of the target growers for each type of crop planted, since the crop types with fewer planting times and total planting areas can reflect that the target growers have lower proficiency in this crop type, a first screening is implemented, and then a second screening is performed among the screened crop types, so that the screened target crop types are the crop types with relatively high planting proficiency of the target growers.

[0125] The first acquisition module 200 is used to obtain the target NDVI fluctuation degree corresponding to any target crop type according to the NDVI values ​​corresponding to several target time points of each year in the historical n years, and determine the target NDVI fluctuation degree as the first planting proficiency measurement parameter.

[0126] Specifically, the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop species; it can be understood that: the growth cycle is divided into several time slices, and the connecting time point of each two adjacent time slices is used as the target time point, and each time the crop species is planted, the NDVI values ​​are obtained at several fixed time points; for example, the growth cycle of a random target crop species is January to May, and February 1, March 1, and April 1 of each year can be used as target time points.

[0127] In a specific embodiment, Figure 8 As shown, the first acquisition module 200 includes:

[0128] The fourth acquisition module 201 is used to obtain a number of NDVI values ​​corresponding to the target crop type at any target time point according to the number of planting times of the target crop type in the history n; the number of NDVI values ​​corresponding to the target crop type at any target time point is equal to the number of planting times of the target crop type in the history n. For example: if the target crop type is not planted in a certain year, the NDVI value of that year is not considered. If the number of planting times in the history n years is 5, and one of the target time points is February 1, then 5 NDVI values ​​can be obtained at the target time point, that is, one NDVI value can be obtained on February 1 of each planting year.

[0129] The fifth acquisition module 202 is used to acquire the initial NDVI fluctuation degree corresponding to the target crop type at any target time point according to a number of NDVI values ​​corresponding to the target crop type at any target time point.

[0130] Specifically, the initial NDVI fluctuation degree S of the target crop type at any target time point meets the following conditions:

[0131] S = sqrt(((x 1 -x) 2 +(x 2 -x) 2 +......(x d -x) 2 ) / (d-1)), where d is the number of NDVI values ​​corresponding to the target crop type at any target time point, x dis the dth NDVI value corresponding to the target crop type at any target time point, x is the average of several NDVI values ​​corresponding to the target crop type at any target time point, and sqrt() is the square root function.

[0132] The sixth acquisition module 203 is used to take the reciprocal of the average value of m initial NDVI fluctuation degrees corresponding to the target crop type at m target time points as the target NDVI fluctuation degree corresponding to the target crop type.

[0133] As mentioned above, by analyzing the changes in NDVI values ​​of target crop types in the same period of each planting year, the differences in growth status of target crop types can be grasped. When the growth status differences of target crop types in the same period are large, it can reflect that the planting proficiency of the target growers is low. Taking into account unexpected situations in the growth cycle, the average value of NDVI fluctuation degree is used as the target NDVI fluctuation degree, which can accurately and reliably reflect the planting proficiency of the target growers to a certain extent.

[0134] The second acquisition module 300 is used to acquire a second planting proficiency measurement parameter according to the number of planting years of the target grower in the historical n years and the planting area corresponding to each planting year.

[0135] In a specific embodiment, Fig. 9 As shown, the second acquisition module 300 includes:

[0136] The first division module 301 is used to divide the historical n years into a number of year segments according to the continuity of the planting years of the target growers in the historical n years. For example, in the historical 10 years, the target crop type was planted in the 1st, 2nd, 3rd, 6th, 7th, 9th, and 10th years from the recent to the distant, and the divided year segments are 1-3 years, 6-7 years, and 9-10 years.

[0137] The seventh acquisition module 302 is used to obtain the planting proficiency measurement parameter corresponding to each year segment according to the arithmetic progression summation method based on the number of planting years in each year segment, and take the sum of the planting proficiency measurement parameters corresponding to each year segment as the first sub-measurement parameter, wherein the first term and the tolerance corresponding to the arithmetic progression summation method are both preset parameters. Generally, the first term is 1, and the tolerance is not greater than 1. For example, for the year segments divided as described above, the first term can be set to 1, the tolerance can be set to 1, the planting proficiency measurement parameter corresponding to the first year segment is 1+2+3, and the final first sub-measurement parameter is (1+2+3)+(1+2)+(1+2)=12.

[0138] The eighth acquisition module 303 is used to obtain the area ratio of the planting area corresponding to each planting year to the planting area benchmark value based on the preset planting area benchmark value, and use the sum of the obtained area ratios as the second sub-measurement parameter. For example, if the planting area benchmark value is set to 10 mu, when the planting area is 5 mu, the corresponding area ratio is 0.5, and when the planting area is 15 mu, the corresponding area ratio is 1.5.

[0139] The third calculation module 304 is used to calculate the weighted sum of the first sub-measurement parameter and the second sub-measurement parameter, and use the calculation result as the second planting proficiency measurement parameter; it can be understood as: according to the first preset weight corresponding to the number of planting years and the second preset weight corresponding to the planting area, the weighted sum of the first sub-measurement parameter and the second sub-measurement parameter is calculated.

[0140] Specifically, the second planting proficiency measurement parameter L meets the following conditions:

[0141] L=W 1 ×(∑ g h＝1 A h )+W 2 ×(∑ d e＝1 (B e / B)), where A h is the planting proficiency measurement parameter corresponding to the h-th year segment, g is the number of year segments, B e is the planting area corresponding to the e-th planting year, B is the preset planting area benchmark value, d is the number of planting years in the history of n years, W 1 is the first parameter weight corresponding to the first sub-measurement parameter, W 2 is the second parameter weight corresponding to the second sub-measurement parameter.

[0142] As mentioned above, considering that the accumulation of planting years will have a positive impact on planting proficiency, and that not planting a certain type of crop in the middle will lead to unfamiliarity, and the size of the annual planting area will also affect the planting proficiency, the comprehensive consideration of the number of planting years and the planting area can further reflect the planting proficiency of the target growers.

[0143] The third acquisition module 400 is used to acquire the target planting proficiency according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter and the corresponding preset parameter weights.

[0144] Specifically, the target planting proficiency Z meets the following conditions:

[0145] Z=W 3 ×K+W 4×L, where K is the first planting proficiency measurement parameter, W 3 is the preset parameter weight corresponding to the first planting proficiency measurement parameter, W 4 The preset parameter weights corresponding to the second planting proficiency measurement parameters.

[0146] The first calculation module 500 is used to normalize the target planting proficiency to obtain a target planting potential score of the target grower corresponding to the target crop type.

[0147] Specifically, the target planting potential score Y meets the following conditions:

[0148] Y=R / (1+exp(-z)), wherein R is the preset maximum planting potential score; it can be understood that: R represents the R point system, for example, when the percentage system is set, R=100, and when the ten-point system is set, R=10.

[0149] As mentioned above, considering that with the gradual increase of planting years and the increase of total planting area, the planting proficiency of target growers will not increase significantly all the time, but will increase more and more slowly and approach the peak value, the above normalization method is used to obtain a more reasonable and reliable target planting potential score to reflect the planting potential of the target growers.

[0150] In a specific embodiment, Fig.10 As shown, the device further includes a score compensation module, and the score compensation module includes:

[0151] The second division module 10 is used to evenly divide the highest planting potential score into a number of initial score intervals according to a preset highest planting potential score.

[0152] For example, when R=100, it can be divided into five initial score intervals, namely [0-20] points, (20-40] points, (40-60] points, (60-80] points, and (80-100] points.

[0153] The fourth calculation module 20 is used to calculate the score error probability corresponding to the target planting potential score based on the target planting potential score and the key score in the target score interval; the target score interval refers to the initial score interval in which the target planting potential score is located; the key score in the target score interval refers to the planting potential score with the largest number of identical scores obtained based on several historical planting potential scores in the target score interval.

[0154] Specifically, the score error probability P corresponding to the planting potential score meets the following conditions:

[0155] P=|(YY 0 )| / r, where Y 0is the key score in the target score range, and r is the upper limit of the target score range.

[0156] The second determination module 30 is used to input the score error probability as a probability parameter into a preset cross entropy loss function, and determine the output loss value as a random score error.

[0157] Specifically, the random score error C meets the following conditions:

[0158] C = ±log(P), where YY 0 <0, C=-log(P), when YY 0 When >0, C=log(P).

[0159] It should be noted that in a special case, YY 0 When =0, the random score error is 0.

[0160] The third determination module 40 is used to determine the sum of the target planting potential score and the random score error as the final planting potential score.

[0161] As mentioned above, since the calculated target planting potential score, that is, the corresponding target planting proficiency may be different from the actual planting proficiency, it is necessary to compensate for it. Based on the target planting potential score and several historical planting potential scores, the score error probability is calculated, and then the random score error is obtained. The random score error is compensated for the target planting potential score to eliminate certain error influences, which can improve the accuracy of the obtained planting proficiency of the target growers.

[0162] Embodiment 3

[0163] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0164] According to the first crop planting information set of the target grower in the past n years, several target crop types are screened out; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type.

[0165] For any target crop type, the target NDVI fluctuation degree corresponding to the target crop type is obtained according to the NDVI values ​​corresponding to several target time points in each year within the historical n years, and the target NDVI fluctuation degree is determined as the first planting proficiency measurement parameter; the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop type.

[0166] According to the number of planting years of the target growers in the historical n years and the planting area corresponding to each planting year, the second planting proficiency measurement parameter is obtained.

[0167] The target planting proficiency is obtained according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter and the corresponding preset parameter weights.

[0168] The target planting proficiency is normalized to obtain a target planting potential score of the target grower corresponding to the target crop type.

[0169] Embodiment 4

[0170] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0171] According to the first crop planting information set of the target grower in the past n years, several target crop types are screened out; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type.

[0172] For any target crop type, the target NDVI fluctuation degree corresponding to the target crop type is obtained according to the NDVI values ​​corresponding to several target time points in each year within the historical n years, and the target NDVI fluctuation degree is determined as the first planting proficiency measurement parameter; the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop type.

[0173] According to the number of planting years of the target growers in the historical n years and the planting area corresponding to each planting year, the second planting proficiency measurement parameter is obtained.

[0174] The target planting proficiency is obtained according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter and the corresponding preset parameter weights.

[0175] The target planting proficiency is normalized to obtain a target planting potential score of the target grower corresponding to the target crop type.

[0176] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0177] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0178] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for analyzing the potential of growers, characterized in that: The following steps are involved: According to the first crop planting information set of the target grower in the past n years, a number of target crop types are screened out; the first crop planting information set includes the planting times of each crop type and the total planting area of ​​each crop type; For any target crop type, the target NDVI fluctuation degree corresponding to the target crop type is obtained according to the NDVI values ​​corresponding to several target time points of each year in the historical n years, and the target NDVI fluctuation degree is determined as the first planting proficiency measurement parameter; the several target time points refer to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop type; According to the number of planting years of the target growers in the past n years and the planting area corresponding to each planting year, the second planting proficiency measurement parameter is obtained; Obtaining a target planting proficiency according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter, and the corresponding preset parameter weights; The target planting proficiency is normalized to obtain a target planting potential score of the target grower corresponding to the target crop type.

2. The method for analyzing the potential of growers according to claim 1, characterized in that: Screen target crop species through the following steps: The crop types whose planting times are less than the first quantity threshold and whose total planting area is less than the second quantity threshold in the first planting crop information set are deleted to obtain a second planting crop information set; According to the planting times of each crop type and the total planting area of ​​each crop type in the second planting crop information set, as well as the preset planting weights corresponding to the planting times and the total planting area, respectively, a weighted sum is calculated to obtain the planting priority of each crop type in the second planting crop information set; The crop types in the second crop information set whose corresponding planting priority is greater than a preset priority threshold are determined as target crop types.

3. The method for analyzing the potential of growers according to claim 1, characterized in that: The target NDVI fluctuation degree corresponding to the target crop type is obtained through the following steps: According to the number of times the target crop type is planted in the history n, a number of NDVI values ​​corresponding to the target crop type at any target time point is obtained; the number of NDVI values ​​corresponding to the target crop type at any target time point is equal to the number of times the target crop type is planted in the history n; According to a number of NDVI values ​​corresponding to the target crop type at any target time point, the initial NDVI fluctuation degree corresponding to the target crop type at any target time point is obtained; The reciprocal of the average value of the m initial NDVI fluctuation degrees of the target crop type at the m target time points is taken as the target NDVI fluctuation degree corresponding to the target crop type.

4. The method for analyzing the potential of growers according to claim 1, characterized in that: The second planting proficiency measurement parameters are obtained through the following steps: According to the continuity of the planting years of the target growers in the past n years, the historical n years are divided into several year segments; Based on the number of planting years in each year segment, the planting proficiency measurement parameter corresponding to each year segment is obtained according to the arithmetic progression summation method, and the sum of the planting proficiency measurement parameters corresponding to each year segment is used as the first sub-measurement parameter, wherein the first term and the tolerance corresponding to the arithmetic progression summation method are both preset parameters; Based on the preset planting area benchmark value, the area ratio of the planting area corresponding to each planting year to the planting area benchmark value is obtained, and the sum of the obtained several area ratios is used as the second sub-measurement parameter; A weighted sum is calculated for the first sub-measurement parameter and the second sub-measurement parameter, and the calculation result is used as the second planting proficiency measurement parameter.

5. The method for analyzing the potential of growers according to claim 1, characterized in that: The method further comprises the steps of: According to the preset maximum planting potential score, the maximum planting potential score is evenly divided into a number of initial score ranges; The score error probability corresponding to the target planting potential score is calculated according to the target planting potential score and the key score in the target score interval; the target score interval refers to the initial score interval in which the target planting potential score is located; the key score in the target score interval refers to the planting potential score with the largest number of identical scores obtained based on several historical planting potential scores in the target score interval; The score error probability is input as a probability parameter into the preset cross entropy loss function, and the output loss value is determined as the random score error; The sum of the target planting potential score and the random score error was determined as the final planting potential score.

6. A planter potential analysis device, characterized in that: The device comprises: A screening module is used to screen out a number of target crop types according to a first crop planting information set of the target grower in the past n years; the first crop planting information set includes the number of planting times of each crop type and the total planting area of ​​each crop type; The first acquisition module is used to obtain the target NDVI fluctuation degree corresponding to any target crop type according to the NDVI values ​​corresponding to a number of target time points of each year in the historical n years, and determine the target NDVI fluctuation degree as the first planting proficiency measurement parameter; the number of target time points refers to m fixed time points with time intervals determined in the growth cycle of the corresponding target crop type; The second acquisition module is used to obtain the second planting proficiency measurement parameter according to the number of planting years of the target grower in the past n years and the planting area corresponding to each planting year; A third acquisition module is used to acquire the target planting proficiency according to the first planting proficiency measurement parameter, the second planting proficiency measurement parameter and the corresponding preset parameter weights; The first calculation module is used to normalize the target planting proficiency to obtain a target planting potential score of the target grower corresponding to the target crop type.

7. The planter potential analysis device according to claim 6, characterized in that: The screening module comprises: A deletion module, used for deleting the crop types in the first crop information set whose planting times are less than a first quantity threshold and whose total planting area is less than a second quantity threshold, to obtain a second crop information set; A second calculation module is used to calculate the planting priority of each crop type in the second crop information set by performing weighted sum calculations according to the planting times of each crop type and the total planting area of ​​each crop type in the second crop information set, as well as preset planting weights corresponding to the planting times and the total planting area respectively; The first determination module is used to determine the crop types in the second crop information set whose corresponding planting priority is greater than a preset priority threshold as target crop types.

8. The planter potential analysis device according to claim 6, characterized in that: The first acquisition module includes: A fourth acquisition module is used to acquire a number of NDVI values ​​corresponding to the target crop type at any target time point according to the number of planting times of the target crop type in the history n; the number of NDVI values ​​corresponding to the target crop type at any target time point is equal to the number of planting times of the target crop type in the history n; A fifth acquisition module is used to acquire the initial NDVI fluctuation degree corresponding to the target crop type at any target time point according to a number of NDVI values ​​corresponding to the target crop type at any target time point; The sixth acquisition module is used to take the reciprocal of the average value of m initial NDVI fluctuation degrees of the target crop type at m target time points as the target NDVI fluctuation degree corresponding to the target crop type.

9. The planter potential analysis device according to claim 6, characterized in that: The second acquisition module includes: The first division module is used to divide the historical n years into several year segments according to the continuity of the planting years of the target growers in the historical n years; A seventh acquisition module is used to obtain the planting proficiency measurement parameter corresponding to each year segment according to the arithmetic progression summation method based on the number of planting years in each year segment, and use the sum of the planting proficiency measurement parameters corresponding to each year segment as the first sub-measurement parameter, wherein the first term and the tolerance corresponding to the arithmetic progression summation method are both preset parameters; An eighth acquisition module is used to acquire the area ratio of the planting area corresponding to each planting year to the planting area benchmark value based on the preset planting area benchmark value, and use the sum of the acquired area ratios as the second sub-measurement parameter; The third calculation module is used to calculate the weighted sum of the first sub-measurement parameter and the second sub-measurement parameter, and use the calculation result as the second planting proficiency measurement parameter.

10. The planter potential analysis device according to claim 6, characterized in that: It also includes a score compensation module, the score compensation module including: The second division module is used to evenly divide the highest planting potential score into a number of initial score intervals according to the preset highest planting potential score; A fourth calculation module is used to calculate the score error probability corresponding to the target planting potential score according to the target planting potential score and the key score in the target score interval; the target score interval refers to the initial score interval in which the target planting potential score is located; the key score in the target score interval refers to the planting potential score with the largest number of identical scores obtained based on several historical planting potential scores in the target score interval; A second determination module is used to input the score error probability as a probability parameter into a preset cross entropy loss function, and determine the output loss value as a random score error; The third determination module is used to determine the sum of the target planting potential score and the random score error as the final planting potential score.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the grower potential analysis method as described in any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the grower potential analysis method as described in any one of claims 1 to 5 is implemented.

Images