Data processing method, device, apparatus, and computer storage medium

Abstract

This application discloses a data processing method, apparatus, device, and computer storage medium. The data processing method includes: acquiring remote sensing data of a target plot over P crop cycles, where the target plot is a plot associated with a credit granting object, and P is an integer greater than 1; determining planting suitability and planting stability based on the remote sensing data; determining a credit limit for the credit granting object based on the planting suitability and planting stability; and performing operations on the credit granting object according to the credit limit. This application's embodiments can reduce the workload of manual on-site inspections in the credit limit determination process, reduce the cumbersomeness of the credit limit determination process, improve the level of intelligence, and at the same time, effectively improve the accuracy and rationality of the determined credit limit.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and in particular relates to a data processing method, apparatus, device and computer storage medium. Background Technology

[0002] Currently, some financial institutions may need to extend credit to entities in the agricultural sector, such as farmers. In related technologies, financial institutions typically rely on manual on-site inspections to obtain information such as the farmers' crop cultivation conditions to determine the credit limit. This results in a cumbersome and unintelligent credit limit determination process, leading to inaccurate credit limit results. Summary of the Invention

[0003] This application provides a data processing method, apparatus, device, and computer storage medium to address the problems in related technologies where the process of determining credit limits for agricultural entities by financial institutions is cumbersome and lacks intelligence, resulting in inaccurate credit limit determinations.

[0004] In a first aspect, embodiments of this application provide a data processing method, including:

[0005] Obtain remote sensing data of the target plot over P crop cycles, where the target plot is the plot associated with the trusted object, and P is an integer greater than 1;

[0006] Based on remote sensing data, determine planting suitability and planting stability;

[0007] Based on planting suitability and stability, determine the credit limit for the credit recipients, and execute operations on the credit recipients according to the credit limit.

[0008] Secondly, embodiments of this application provide a data processing apparatus, the apparatus comprising:

[0009] The acquisition module is used to acquire remote sensing data of the target plot over P crop cycles. The target plot is the plot associated with the trusted object, and P is an integer greater than 1.

[0010] The first determining module is used to determine planting suitability and planting stability based on remote sensing data;

[0011] The execution module is used to determine the credit limit for the credit recipient based on planting suitability and stability, and to perform operations on the credit recipient according to the credit limit.

[0012] Thirdly, embodiments of this application provide an electronic device, the device including: a processor and a memory storing computer program instructions;

[0013] When the processor executes computer program instructions, it implements the data processing method as described in the first aspect.

[0014] Fourthly, embodiments of this application provide a computer storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, they implement the data processing method as shown in the first aspect.

[0015] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the data processing method as described in the first aspect.

[0016] The data processing method provided in this application embodiment acquires remote sensing data of a target plot over multiple crop cycles. The target plot is a plot associated with a credit granting object. Based on the remote sensing data, the suitability and stability of planting are determined. Based on the suitability and stability of planting, the credit limit for the credit granting object is determined, and operations are performed on the credit granting object according to the credit limit. This application embodiment can determine the suitability and stability of planting of a target plot associated with a credit granting object based on remote sensing data, and determine the credit limit for the credit granting object based on the suitability and stability of planting. In this way, the workload of manual on-site inspection in the process of determining the credit limit can be reduced, the cumbersomeness of the credit limit determination process can be reduced, and the level of intelligence can be improved. At the same time, it can also effectively improve the accuracy and rationality of the determined credit limit. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the data processing method provided in an embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a data processing method in a specific application example;

[0020] Figure 3 This is an example graph of the NDVI curves for location A over two years;

[0021] Figure 4 This is an example image of the NDVI curve reconstructed after two years of filtering in location A.

[0022] Figure 5 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application;

[0023] Figure 6This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0024] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0025] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0026] To address the problems of the prior art, embodiments of this application provide a data processing method, apparatus, device, and computer storage medium. The data processing method provided in this application embodiment will be described first below.

[0027] Figure 1 A flowchart illustrating a data processing method provided in one embodiment of this application is shown. Figure 1 As shown, the method includes:

[0028] Step 101: Obtain remote sensing data of the target plot over P crop cycles. The target plot is the plot associated with the trusted object, and P is an integer greater than 1.

[0029] Step 102: Determine planting suitability and planting stability based on remote sensing data;

[0030] Step 103: Determine the credit limit for the credit recipient based on planting suitability and planting stability, and perform operations on the credit recipient according to the credit limit.

[0031] The data processing method provided in this application embodiment can be applied to an electronic device, wherein the electronic device can be a portable electronic device such as a mobile terminal or tablet computer, or a non-fixed electronic device such as a server or personal computer, and is not specifically limited here.

[0032] In some practical application scenarios, electronic devices can be devices used by financial institutions to extend credit to credit recipients, and correspondingly, the entities executing data processing methods can be financial institutions, etc.

[0033] In step 101, the financial institution can obtain remote sensing data of the land parcel associated with the credit recipient over P crop cycles. The land parcel associated with the credit recipient is the aforementioned target land parcel.

[0034] In some examples, the recipients of the credit line can be natural persons such as farmers who grow crops on the target plot, or legal entities such as enterprises that engage in agricultural production activities on the target plot.

[0035] The target land parcel can be predetermined. For example, financial institutions can use positioning equipment, such as real-time kinematic (RTK) devices, to pinpoint the land parcel specified by the credit applicant, thus obtaining the target land parcel associated with the credit applicant. Alternatively, financial institutions can mark the land parcel specified by the credit applicant on satellite maps to obtain the target land parcel associated with the credit applicant, and so on.

[0036] Financial institutions can obtain remote sensing data of the geographical area where the target land parcel is located, such as satellite remote sensing images. If the target land parcel is identified, its remote sensing data can also be obtained from satellite remote sensing images.

[0037] In this step, financial institutions can obtain remote sensing data of the target plot across multiple crop cycles. It's easy to understand that crops typically have corresponding planting seasons and growth cycles. In some examples, the crop cycle can be determined based on the planting season and growth cycle.

[0038] Step 102: Determine planting suitability and planting stability based on remote sensing data;

[0039] Generally, remote sensing data for different crops will differ. For example, the data may differ at a single point in time, or the patterns of change in the data may differ within a crop cycle. Therefore, based on remote sensing data, the types of crops planted in a target plot during a crop cycle can be determined.

[0040] Generally, different types of crops have different suitable growing environments. For example, some types of crops may be suitable for growing in long-day conditions, while others may be more suitable for growing in acidic soils, and so on.

[0041] The climate and topography of the geographical region where the target plot is located, as well as the soil pH, are factors that influence crop suitability. Data on these factors are usually relatively fixed and can be obtained in advance through appropriate measurement methods. Given the crop type and data on the climate, topography, and soil of the target plot, the suitability of the type of crop to be planted at the target plot can be determined.

[0042] To a certain extent, planting suitability can be defined as the ability of a crop type planted in a target plot to adapt to relevant factors of the target plot (such as climate, soil, topography, and environment). In practical applications, planting suitability can be quantified.

[0043] In various application scenarios, planting suitability usually has a direct impact on crop yield and quality, which in turn affects the economic value of the crop and the repayment ability of the creditor.

[0044] For the target plot, the types of crops planted in different crop cycles may be the same or different. Since the financial institution acquired remote sensing data for multiple crop cycles in step 101, by comparing the remote sensing data of different crop cycles, it can be determined whether the types of crops planted in the target plot have changed. And based on the changes in the types of crops planted in multiple crop cycles, the planting stability of the target plot can be determined.

[0045] Generally, the economic value of the same type of crop varies little across different crop cycles. When planting stability is high, the borrower can be considered to have a relatively stable repayment ability. Conversely, when planting stability is low, the economic benefits the borrower can obtain in each crop cycle are difficult to determine, and their repayment ability is difficult to guarantee.

[0046] From another perspective, high planting stability indicates that the credit recipient has extensive planting experience for certain types of crops, effectively guaranteeing the economic benefits of the crops. Alternatively, planting stability can also reflect the differences in growth of the same type of crop in different crop cycles, thereby determining whether the crop yield is stable.

[0047] To a certain extent, planting stability can be understood as the similarity of remote sensing data of target plots in different crop cycles.

[0048] In step 103, financial institutions can determine the credit limit for credit recipients based on planting suitability and planting stability, and perform operations on credit recipients according to the credit limit.

[0049] As shown above, both planting suitability and planting stability can affect the repayment ability of the credit recipient. Therefore, in step 103, the financial institution can determine the credit limit for the credit recipient based on planting suitability and planting stability.

[0050] For example, financial institutions can establish a functional relationship between credit limits and planting suitability and stability, using planting suitability and stability as inputs to calculate credit limits.

[0051] Alternatively, a tabular correspondence can be established between the credit limit granted by financial institutions and the suitability and stability of planting. Once the suitability and stability of planting are determined, the credit limit can be queried through the tabular correspondence.

[0052] Alternatively, financial institutions can determine an initial credit limit for the recipient and then adjust the initial credit limit using planting suitability and planting stability to obtain the final credit limit for the recipient.

[0053] Once a credit limit is determined for a recipient, financial institutions can perform operations on that recipient based on that limit. These operations could include sending the credit limit to the recipient's terminal; investing or financing the recipient based on the credit limit; or linking and storing the recipient's information with the credit limit, etc. Examples are not provided here.

[0054] The data processing method provided in this application embodiment acquires remote sensing data of a target plot over multiple crop cycles. The target plot is a plot associated with a credit granting object. Based on the remote sensing data, the suitability and stability of planting are determined. Based on the suitability and stability of planting, the credit limit for the credit granting object is determined, and operations are performed on the credit granting object according to the credit limit. This application embodiment can determine the suitability and stability of planting of a target plot associated with a credit granting object based on remote sensing data, and determine the credit limit for the credit granting object based on the suitability and stability of planting. In this way, the workload of manual on-site inspection in the process of determining the credit limit can be reduced, the cumbersomeness of the credit limit determination process can be reduced, and the level of intelligence can be improved. At the same time, it can also effectively improve the accuracy and rationality of the determined credit limit.

[0055] Optionally, planting suitability can be determined based on remote sensing data, including:

[0056] Based on remote sensing data, the target planting type is determined, which is the planting type in the target crop cycle within P crop cycles;

[0057] Based on the preset first correspondence, obtain R suitability indicators corresponding to the target planting type. The first correspondence includes the correspondence between the target planting type and the R suitability indicators, where R is an integer greater than 1.

[0058] Obtain measurement data associated with the target plot and corresponding to R suitability indicators, and determine the values ​​of R indicators corresponding to the R suitability indicators based on the measurement data;

[0059] The suitability for planting is determined based on R index values.

[0060] As shown above, the crop planting type can be determined based on remote sensing data. In this embodiment, financial institutions can use remote sensing data of the target plot during the target crop cycle to determine the crop planting type of the target plot during that target crop cycle, i.e., the target planting type mentioned above.

[0061] In some examples, the target crop cycle can be the current crop cycle, that is, the crop cycle corresponding to the point in time when the credit limit is determined. Of course, in practical applications, the target crop cycle can also be the previous crop cycle of the current crop cycle, and so on.

[0062] To simplify the description, the following explanation will mainly use the target crop cycle as the current crop cycle as an example.

[0063] In a specific application example, after identifying a target plot, financial institutions can retrieve the most recent satellite remote sensing spectral imagery, such as multispectral and hyperspectral imagery, for that plot. Based on the spectral characteristics of the satellite remote sensing imagery, and considering the differences in reflectance in the near-infrared band due to differences in crop leaf structure, classification can be performed. Alternatively, classification can be based on the temporal changes in the remote sensing imagery, combined with the phenological characteristics of different types of crops, to obtain the aforementioned target planting type.

[0064] Given a target planting type, R suitability indicators can be determined based on a pre-defined first correspondence.

[0065] For example, if the target planting type indicates that the current crop planted on the target plot is corn, the R suitability indicators determined according to the first correspondence relationship may include average temperature during the growing season, precipitation during the growing season, soil pH value, altitude, and distance from water sources (such as rivers or lakes), etc.

[0066] Of course, in practical applications, the first correspondence can also record the correspondence between crop types other than corn and suitability indicators, which will not be illustrated here.

[0067] For each suitability indicator, the target plot can have corresponding measurement data. For example, the average temperature and precipitation during the growing season can be obtained based on the measurement and statistics of climate data from previous years, while the soil pH value can be measured using soil pH measurement equipment, and so on.

[0068] From the perspective of financial institutions, the aforementioned measurement data can be obtained from relevant databases or based on user data input operations, etc.

[0069] Taking the average temperature during the growing season as an example of suitability index, generally speaking, for a type of crop, there can be an optimal range of average temperature during the growing season, a suboptimal range of average temperature during the growing season, and an unsuitable range of average temperature during the growing season.

[0070] When the measured average temperature during the growing season of the target plot indicates that it falls within the optimal range for growth, a higher score can be assigned to this suitability indicator. If the measured average temperature during the growing season of the target plot falls within the suboptimal range, a moderate score can be assigned. And if the measured average temperature during the growing season of the target plot falls within the unsuitable range, a lower score can be assigned.

[0071] In the examples above, the scores assigned to the suitability indicators can be the corresponding indicator values. Of course, in practical applications, the suitability indicators mentioned above are not limited to the average temperature during the reproductive period shown in the examples; they can also be other types of suitability indicators.

[0072] In some specific applications, suitability indicators can be crop growth indicators. For different suitability indicators, different fuzzy membership functions can be used to dimensionlessly and normallyize the input values, constructing a single-factor model of suitability.

[0073] For example, single-factor models can be either small-scale or large-scale function models (i.e., the smaller or larger the index value, the higher the suitability) or intermediate function models (i.e., the higher the suitability value when the index value is in a certain range).

[0074] Then, based on the mean and standard deviation of the suitability index, combined with the optimal value of the suitability index and its impact on crop growth, a linear, parabolic, or semi-parabolic function is selected to complete the construction of the single-factor model for suitability. Subsequently, the measured values ​​of the suitability index can be used as inputs to calculate the corresponding index values ​​for each suitability index using the single-factor model.

[0075] Given R suitability indicators and their corresponding R indicator values, financial institutions can determine planting suitability based on these R indicator values.

[0076] For example, financial institutions can add up these indicator values, or perform a weighted summation, or use other calculation methods to calculate planting suitability.

[0077] This embodiment determines the target planting type for the target plot within the target crop cycle, identifies R suitability indicators corresponding to the target planting type, determines R indicator values ​​based on measurement data, and finally determines the planting suitability based on these R indicator values. This approach helps to fully consider all factors affecting crop planting suitability, improving the accuracy and rationality of the planting suitability determination results.

[0078] Optionally, planting suitability is determined based on R index values, including:

[0079] Obtain the weight values ​​of R indicators corresponding to R suitability indicators, where the weight values ​​of the indicators corresponding to the suitability indicators are positively correlated with the importance of the suitability indicators to the growth of the target planting type;

[0080] The planting suitability is obtained by summing the weighted values ​​of the R indicators.

[0081] Based on the example above, if the current crop planted on the target plot is corn, the R suitability indicators can include average temperature during the growing season, precipitation during the growing season, soil pH value, altitude, and distance from water sources (such as rivers or lakes), etc.

[0082] In practical applications, the importance of various suitability indicators to maize growth may vary. For example, climate-related indicators such as average temperature and precipitation during the growing season may have a more significant impact on maize growth than indicators such as distance from water sources.

[0083] Of course, this is just an example illustrating the relative importance of suitability indicators that affect crop planting. In practical applications, the relative importance of each suitability indicator can be determined based on empirical data and other factors.

[0084] To reflect the relative importance of suitability indicators, this embodiment can obtain the indicator weight values ​​corresponding to each suitability indicator. These indicator weight values ​​can be obtained based on empirical data, or they can be obtained by combining other mathematical calculation models, etc., without specific limitations here.

[0085] Generally, the suitability index's weight value should be positively correlated with its importance to the growth of the target crop type. In other words, the higher the importance of the suitability index to the growth of the target crop type, the larger its weight value can be.

[0086] The suitability for planting can be obtained by summing the weighted values ​​of the R indicators.

[0087] For example, if we denote the value of the i-th suitability indicator as w... i Let k be the weight value of the i-th suitability indicator. i The suitability for planting can be represented by a numerical value K, which can be calculated as follows:

[0088]

[0089] In this embodiment, based on the importance of each suitability indicator to the growth of the target planting type, corresponding indicator weight values ​​are assigned to the suitability indicators. Combining the indicator weight values ​​to determine the suitability indicators helps to further improve the accuracy and rationality of the planting suitability determination results.

[0090] Optionally, the R suitability indicators belong to at least one criterion;

[0091] Obtain the weight values ​​of the R indicators corresponding to the R suitability indicators, including:

[0092] Obtain the criterion weight value of the target criterion, and all S suitability indicators belonging to the target criterion, wherein the target criterion is any one of at least one criteria;

[0093] When S is an integer greater than 1, a weight judgment matrix is ​​established for the S suitability indicators. The value of the element in the i-th row and j-th column of the weight judgment matrix represents the relative growth importance between the i-th suitability indicator and the j-th suitability indicator. i and j are both positive integers less than or equal to S.

[0094] Normalize the eigenvectors of the weight judgment matrix to obtain the weight vector;

[0095] Based on the criterion weight values ​​and weight vectors, determine the weight value of each of the S suitability indicators.

[0096] Taking maize as an example, the R suitability indicators can include average temperature during the growing season, precipitation during the growing season, soil pH, altitude, and distance from water sources, etc. Among them, average temperature and precipitation during the growing season can be attributed to the climate criterion, soil pH can be attributed to the soil criterion, altitude can be attributed to the topography criterion, and distance from water sources can be attributed to the surrounding environment criterion.

[0097] Of course, in practical applications, the affiliation between suitability indicators and criteria can be set according to actual needs. Furthermore, for various crop types, corresponding criteria and suitability indicators belonging to those criteria can be established.

[0098] Each criterion can have a corresponding criterion weight value. In some examples, similar to indicator weight values, criterion weight values ​​can also be determined based on the relative importance of each criterion to crop growth.

[0099] The target criterion can be any one of the criteria to which the above R suitability indicators belong. Under the target criterion, there can be S suitability indicators.

[0100] When S is an integer greater than 1, a weight judgment matrix can be established for the S suitability indicators. The value of the element in the i-th row and j-th column of the weight judgment matrix represents the relative growth importance between the i-th suitability indicator and the j-th suitability indicator, where i and j are both positive integers less than or equal to S.

[0101] For ease of understanding, the weight judgment matrix can be denoted as A, where:

[0102]

[0103] In matrix A, the element in the i-th row and j-th column can be denoted as a. ij , representing the relative growth importance between the i-th fitness index and the j-th fitness index. Accordingly, a ji This represents the relative growth importance between the j-th fitness index and the i-th fitness index. Therefore, a ij With a ji They can be reciprocals of each other, that is, a ij =1 / a ji As for a ii This indicates the importance of the i-th fitness index relative to its own growth, and can generally be equal to 1. Based on the above explanation, the weight judgment matrix A can be a positive reciprocal matrix.

[0104] The relative importance of growth among the various fitness indicators can be determined based on empirical data, and will not be explained in detail here.

[0105] Let V be the eigenvector of the weight judgment matrix. Then, the following relationship generally holds: λV = AV, where λ is the eigenvalue of the weight judgment matrix. V can be expressed as:

[0106] V = [v1, ..., v s ] T

[0107] Normalizing the eigenvectors of the weight judgment matrix yields the weight vector, denoted as W, which can be specifically expressed as:

[0108] W = [w′1,…,w′] S ] T

[0109] Based on the criterion weight values ​​and weight vectors, the weight value of each of the S suitability indicators can be determined. For example, for the first suitability indicator among the S suitability indicators, the corresponding weight value can be the product of the criterion weight value of the target criterion and w′1. The calculation method for the weight values ​​of other suitability indicators is similar, and will not be explained in detail here.

[0110] In this embodiment, by establishing a weight judgment matrix, the eigenvectors of the weight judgment matrix are normalized to obtain a weight vector. Based on the weight vector and the criterion weight value, the index weight value corresponding to each suitability index is determined. This helps to make the index weight value more accurately reflect the relative importance of each suitability index to crop growth, thereby helping to improve the rationality of the index weight value.

[0111] Optionally, before normalizing the eigenvectors of the weight judgment matrix to obtain the weight vector, the method further includes:

[0112] When S is an integer greater than 2, check the consistency of the weight judgment matrix;

[0113] Normalize the eigenvectors of the weight judgment matrix to obtain the weight vector, which includes:

[0114] If the consistency check of the weight judgment matrix passes, the eigenvectors of the weight judgment matrix are normalized to obtain the weight vector.

[0115] As shown above, in the weight judgment matrix, each element reflects the relative importance of two suitability indicators to crop growth. However, when there are many suitability indicators, there may be estimation errors between the pairwise comparison results of the suitability indicators, which will cause deviations in the calculation results of the feature vector and the weight vector.

[0116] Therefore, in this embodiment, the consistency of the weight judgment matrix can be checked before normalizing the eigenvectors of the weight judgment matrix. When the consistency of the weight judgment matrix is ​​high (corresponding to the consistency check of the weight judgment matrix passing), it indicates that the pairwise comparison results of the relative growth importance of the suitability index to the crop have small errors. Furthermore, the eigenvectors and weight vectors can be further determined based on the weight judgment matrix to improve the accuracy of the index weight values.

[0117] Conversely, if the consistency test of the weight judgment matrix fails, the values ​​of the elements in the weight judgment matrix can be adjusted. For example, the relative importance of one or more suitability indicators to crop growth can be adjusted until the consistency test of the adjusted weight judgment matrix passes.

[0118] In some implementations, when S=1 or 2, there is usually no consistency problem with the weight judgment matrix. In this case, the consistency check of the weight judgment matrix can be directly considered to have passed.

[0119] In some implementations, the range of values ​​for each element in the weighting matrix can be restricted, for example, by limiting the range to [1 / 9, 9]. Of course, the range of values ​​for each element in the weighting matrix can also be adjusted according to actual needs.

[0120] Optionally, the consistency of the weight judgment matrix is ​​checked, including:

[0121] Obtain the largest eigenvalue of the weight judgment matrix;

[0122] Based on the largest eigenvalue and the order of the weight judgment matrix, the consistency index of the weight judgment matrix is ​​determined. Based on the order of the weight judgment matrix and the correspondence between the preset order and the average consistency index, the average consistency index of the weight judgment matrix is ​​determined.

[0123] The consistency of the weight judgment matrix is ​​tested based on the ratio of the consistency index to the average consistency index.

[0124] Among them, the consistency test of the weight judgment matrix is ​​passed when the ratio of the consistency index to the average consistency index is less than the preset ratio.

[0125] As shown above, the weight judgment matrix A and its eigenvector V have the following relationship with the eigenvalue λ: λV = AV. For the weight judgment matrix A, it may have multiple eigenvalues ​​λ. In this embodiment, the eigenvalue used to verify the consistency of the weight judgment matrix can be the largest eigenvalue of the weight judgment matrix, denoted as λ. max .

[0126] For ease of understanding, the consistency index of the weight judgment matrix will be denoted as CI, and the average consistency index of the weight judgment matrix will be denoted as RI. The ratio of CI to RI is denoted as CR, i.e.:

[0127] CR = CI / RI

[0128] CR can be used to indicate the consistency of the weight judgment matrix.

[0129] The consistency index (CI) can be calculated as follows:

[0130] CI=(λ max -S) / (S-1)

[0131] Where S is the total number of suitability indicators in the target criteria, or it can be the order of the weight judgment matrix determined for the target criteria.

[0132] The average consistency index (RI) can be preset, and it can correspond to the order of the weight judgment matrix. For example, the correspondence between the order of the weight judgment matrix, the preset order, and the average consistency index can be shown in the table below.

[0133]

[0134] When the order of the weight judgment matrix is ​​1 or 2, it is not necessary to calculate CR; the consistency check of the weight judgment matrix can be directly determined to be passed.

[0135] When the order of the weight judgment matrix is ​​an integer greater than 2, the calculated CR can be compared with the preset ratio. When the CR is less than the preset ratio, the consistency check of the weight judgment matrix is ​​considered to have passed.

[0136] In some feasible implementations, the consistency of the weight judgment matrix can also be checked solely based on the value of CI mentioned above.

[0137] In some implementations, the criterion weights of each criterion can also be determined in a manner similar to that used for determining index weights. That is, based on the relative importance of each criterion to crop growth, a weight judgment matrix of order can be established, and the eigenvectors of this weight judgment matrix can be obtained and normalized to yield a weight vector for each criterion. The value of each element in this weight vector can then be used as the criterion weight for the corresponding criterion.

[0138] Optionally, planting stability can be determined based on remote sensing data, including:

[0139] Based on remote sensing data, P Normalized Difference Vegetation Index (NDVI) streams of the target plot are obtained in P crop cycles. Each NDVI stream includes NDVI at multiple preset sampling time points in the corresponding crop cycle.

[0140] Planting stability is determined based on P NDVI flows.

[0141] To facilitate understanding of the NDVI stream acquisition process, this embodiment will be described below with reference to a specific application scenario.

[0142] For the target plot, financial institutions can access remote sensing data (mainly multispectral and hyperspectral remote sensing data) over the past five years of crop cycles, ensuring that the temporal resolution of the remote sensing data is no less than 16 days. It's easy to understand that this five-year crop cycle corresponds to P crop cycles.

[0143] By analyzing spectral data, the NDVI of the target plot at each sampling time point in each crop cycle of the remote sensing image can be calculated. Generally, NDVI can be defined as the ratio of the difference between the Near Infrared (NIR) value and the sum of the values ​​in the visible red band (RED), i.e.:

[0144] NDVI = (NIR - RED) / (NIR - RED)

[0145] Since the temporal resolution of remote sensing data is no less than 16 days within each crop cycle, the number of sampling time points in each crop cycle can be multiple, denoted as t, which is an integer greater than 1. The NDVI stream acquired in a crop cycle can be denoted as NDVI_t. T Then we have:

[0146] NDVI T ={ndvi1,…,ndvi t}

[0147] For any two crop cycles, the similarity between NDVI flows can be calculated to determine whether the types of crops planted in the target plots in these two crop cycles are consistent, or whether the growth of the planted crops is similar, which helps to determine the planting stability of the target plots.

[0148] Of course, in practical applications, NDVI flows from three or more crop cycles can be combined to determine the planting stability of the target plot.

[0149] In this embodiment, planting stability is determined by using multiple NDVI streams obtained from multiple crop cycles. This helps to reduce the impact of factors such as remote sensing data errors or the early or late growth period of crops in a single year, and improves the accuracy of the planting stability determination results.

[0150] Optionally, planting stability is determined based on P NDVI flows, including:

[0151] Acquire the first NDVI stream and the second NDVI stream, which are any two NDVI streams that are adjacent in the crop cycle;

[0152] Determine the similarity between the first NDVI stream and the second NDVI stream;

[0153] Planting stability is determined based on similarity.

[0154] In one example, the Pearson correlation coefficient between the first NDVI stream and the second NDVI stream can be calculated as a measure of the similarity between the two NDVI streams.

[0155] Of course, the similarity between NDVI streams can also be determined by methods such as calculating the cosine distance of the included angle, but these will not be illustrated here.

[0156] The similarity between the first NDVI stream and the second NDVI stream can be used to determine planting stability. For example, the similarity can be used as a value for planting stability, or the similarity can be converted into a value for planting stability through a preset function transformation relationship, and so on.

[0157] As shown above, NDVI flows from three or more crop cycles can be combined to determine the planting stability of a target plot. For example, financial institutions can calculate the NDVI flow similarity between two adjacent crop cycles and use the average of the multiple similarities to reflect planting stability, etc.

[0158] In this embodiment, planting stability is determined by calculating the similarity between NDVI streams, which can calculate planting stability from a quantitative perspective and improve the efficiency of determining planting stability.

[0159] In some implementations, the first and second NDVI streams can be filtered before determining the similarity between them to improve the data quality of the NDVI streams and thus improve the accuracy of the determination of planting stability.

[0160] For example, each NDVI stream can be filtered using the Savitzky-Golay filtering method (SG filtering method, also known as the least squares convolution fitting algorithm). The filtering process of the SG filtering method can be simply described as follows:

[0161]

[0162] Among them, Y j * Y is the fitted value. j+1 For the original value, C i is the coefficient for filtering the i-th value, m is the length of half the filtering window, N is the filter length, and N = 2m + 1.

[0163] For simplicity, the first NDVI stream can be denoted as X. T ={x1,…,x t Let the second NDVI stream be denoted as Y. T ={y1,…,y t}

[0164] After the first NDVI stream is filtered and reconstructed, a new sequence X′ is obtained. T ={x′1,…,x′ t After the second NDVI stream is filtered and reconstructed, a new sequence Y′ is obtained. T ={y′1,…,y′ t}

[0165] Calculate sequence X′ T and Y′ T The Pearson correlation coefficient between two pairs is used to obtain the similarity COR(X′). T ,Y′ T The calculation formula is as follows:

[0166]

[0167] in:

[0168]

[0169] Taking P=5 as an example, the Pearson correlation coefficients of NDVI flows in two consecutive years over the past five years are compared one by one to obtain four correlation coefficient values. The average Pearson correlation coefficient value that can reflect the stability of planting is obtained by averaging them.

[0170] Optionally, after acquiring remote sensing data of the target plot over P crop cycles, the method further includes:

[0171] The target planting type and the area of ​​the target plot are determined based on remote sensing data.

[0172] Based on planting suitability and stability, the credit limit for the recipient is determined, including:

[0173] Determine the net income from planting based on the target planting type and plot area;

[0174] Based on planting suitability, planting stability, and a preset credit limit coefficient, the net planting income is adjusted to obtain the credit limit.

[0175] The target planting type, as explained above, can be the type of crop planted on the target plot in the current crop cycle, which can be obtained through analysis of remote sensing data.

[0176] The area of ​​the target plot can be determined in advance.

[0177] In practical applications, users can determine the boundaries of a target plot by selecting boundary points on a map and connecting them into a vector using a mobile application. Alternatively, users can carry a GPS-enabled phone and circle the farmland to obtain the boundaries of the target plot.

[0178] After obtaining the boundary points of the target plot, the plot area is calculated using the boundary information. If the target plot is a polygon, it can be divided into several triangles, and the total area can be obtained by calculating the area of ​​each individual triangle. For target plots with irregular boundaries, the total area can also be obtained using calculus.

[0179] Given a defined target planting type, financial institutions can determine the planting revenue and cost per unit area corresponding to the target planting type based on empirical data. Combined with the area of ​​the target plot, they can determine the total planting revenue (denoted as H) and total planting cost (denoted as C) of the target plot. The net planting revenue can then be denoted as (HC).

[0180] In some examples,

[0181]

[0182]

[0183] s i Let y be the area of ​​each sub-plot within the target plot. i p represents the yield per unit area of ​​crops in the subplot. i c is the price per unit yield of this crop. i This refers to the cost of crop cultivation per unit area.

[0184] In this embodiment, financial institutions can adjust the net income from planting based on planting suitability, planting stability, and a preset credit limit coefficient to obtain the credit limit.

[0185] For example, the credit limit is recorded as L. r It can be obtained using the following formula:

[0186] L r =α×k1×k2×(H–C)

[0187] Where α is the credit limit coefficient preset by the financial institution, k1 is the suitability for planting, and k2 is the stability of planting.

[0188] Of course, in practical applications, the way to adjust the net income from planting based on planting suitability, planting stability, and preset credit limits is not limited to multiplication. For example, in some feasible implementations, planting suitability or planting stability may correspond to an increased credit limit, and adjusting the net income from planting based on planting suitability or planting stability could involve adding the net income from planting to the increased credit limit, and so on.

[0189] In this embodiment, the credit limit is determined by combining planting suitability, planting stability, preset credit limit coefficient, and net planting income, which helps to improve the rationality of the determined credit limit.

[0190] In some implementations, the aforementioned credit limit L r It can be an intermediate or recommended credit line during the credit line determination process. The final credit line that financial institutions determine for credit recipients can also take other factors into consideration.

[0191] For example, financial institutions can pre-determine a minimum guarantee amount L for credit recipients. f and cap amount L h The final credit line L determined by a financial institution for a credit recipient can be calculated using the following formula.

[0192] L=min{max{L r ,L f},L h}

[0193] like Figure 2 As shown, Figure 2 In a specific application example, the data processing method may include steps 201 to 212.

[0194] Step 201: Obtain farmer identity information.

[0195] In this specific application example, the recipient of the credit can be a farmer.

[0196] Step 202: Obtain the planting area and planting type of farmers.

[0197] In this step, the planting area of ​​farmers can correspond to the plot area of ​​the target land mentioned above, and the planting category can correspond to the target planting type mentioned above.

[0198] After step 202, steps 203 and 208 can be executed synchronously or asynchronously.

[0199] Step 203: Select criterion factors and stratify them.

[0200] In this step, we can obtain the criteria corresponding to the planting category, as well as the suitability indicators under each criterion. The criteria and suitability indicators can form a stratification.

[0201] Step 204: Construct a pairwise comparison matrix.

[0202] In this step, a pairwise comparison matrix can be constructed for multiple criteria, or for multiple suitability indicators within a single criterion. The pairwise comparison matrix can correspond to the weight judgment matrix mentioned above.

[0203] Step 205, Consistency check: If the consistency check of the pairwise comparison matrix passes, proceed to step 206; if the consistency check fails, return to step 204 and modify the values ​​of the elements in the pairwise comparison matrix.

[0204] Step 206: Obtain the planting suitability model for the target plot.

[0205] The planting suitability model can include the indicator weights of each suitability indicator, and the planting suitability model can be matched with the planting category.

[0206] Step 207: Calculate the planting suitability of the target plot.

[0207] Step 208: Analyze the spectral remote sensing data to obtain the NDVI curve.

[0208] The NDVI curve here corresponds to the NDVI flow described above.

[0209] Step 209: Use the SG filtering method to reconstruct the complete NDVI timing curve.

[0210] Step 210: Calculate the Pearson correlation coefficient for the NDVI time series curves of two adjacent years.

[0211] Step 211: Calculate the planting stability of farmers.

[0212] Step 212: Based on the calculation results of steps 207 and 211, analyze the farmer information to obtain the farmer's credit limit.

[0213] As can be seen from the above application examples, the data processing method provided in this application uses remote sensing data to determine the credit limit. On the one hand, it can reduce the workload caused by on-site inspections. On the other hand, it can comprehensively consider planting suitability and planting stability to determine the credit limit, thereby improving the accuracy and rationality of the credit limit.

[0214] To more directly understand the process of determining the credit limit in the embodiments of this application, the following will use some specific data to explain the calculation method of the credit limit.

[0215] Step 1: Obtain the farmer's identity information and the land information entered by the farmer himself.

[0216] Financial institutions need to extend credit to farmer B located in area A. In the process of determining the credit limit, financial institutions can enter farmer B's identity information and delineate the coordinates of farmer B's target land plot.

[0217] For example, if the target plot is rectangular, the coordinates of the latitude and longitude of the four corner points of the target plot can be entered.

[0218] Step 2: Obtain farmers' planting information based on remote sensing data.

[0219] Step 2.1: After obtaining the boundary points of the land parcel, calculate the land parcel area using the boundary information. Based on the boundary coordinates of the target land parcel, the land parcel area is calculated to be 12.47 mu (approximately 8.2 hectares).

[0220] Step 2.2: Analyze recent satellite remote sensing images of the target plot. Based on its spectral characteristics and crop phenological features, combined with prior information (the main crops grown in area A), obtain crop category information. The crop grown in the target plot is determined to be corn.

[0221] Step 3: Model and calculate the suitability for planting.

[0222] Step 3.1: Based on the crop's growth characteristics, construct a hierarchical structure and select criterion factors for the criterion layer and indicator layer, namely, the target layer (planting suitability), the criterion layer (climate, topography, soil, environment), and the indicator layer. For each factor in the indicator layer, determine the grading and scoring standards based on the crop's growth patterns and local conditions, as illustrated below:

[0223]

[0224]

[0225] Obtain the mean, standard deviation, and optimal value of a certain indicator, select a suitable fuzzy membership function to hash the input value, and obtain a single-factor model of suitability for that parameter.

[0226] Taking the average temperature during the growing season as an example, statistics show that the average temperature in area A from early to mid-June to mid to late September is 23.4℃, and the variance of the historical average temperature is 1.5℃. Given that the optimal average temperature for summer maize during its growing season is 23℃, the average temperature range can be divided (optimal value ± one standard deviation is optimal, optimal value ± three standard deviations is suboptimal). A single-factor model of suitability regarding the average temperature during the growing season can be constructed using a parabolic function.

[0227]

[0228] Where tep is the average temperature during the reproductive period, and k(tep) is the suitability score corresponding to the average temperature during the reproductive period.

[0229] Similar analysis can yield the following climatic indicator evaluation criteria for summer maize in region A (growing period from early to mid-June to mid to late September, approximately 100 days):

[0230]

[0231] Step 3.2: Construct the weight judgment matrix. Taking climate conditions as an example, compare the importance of various climate factors to obtain the weight judgment matrix A:

[0232]

[0233] Step 3.3: Perform eigenvalue decomposition on the weight judgment matrix A, and find that the largest eigenvalue is λ. max =5.0495, and its corresponding eigenvector is V = [0.669, 0.619, 0.369, 0.100, 0.151]. T After normalization, the weight vector is obtained as W = [0.351, 0.324, 0.193, 0.052, 0.079]. T .

[0234] Perform a consistency check on A, where

[0235]

[0236]

[0237] The consistency check passes. RI can be obtained by querying the order of the weight judgment matrix A, and 0.1 can be a preset ratio.

[0238] Step 3.4: After completing the hierarchical analysis of the target layer-criteria layer and the criterion layer-indicator layer, the weight of each factor in the final indicator layer is the product of the weights of the two layers. This yields the local summer maize planting suitability model.

[0239]

[0240]

[0241] The suitability of summer maize for planting in the local area can be calculated using a planting suitability model. The formula is as follows:

[0242] Planting suitability = 0.232 × "Average temperature during the growing season" + 0.214 × "Rainfall during the growing season" + 0.128 × "Accumulated temperature ≥10℃" + 0.034 × "Number of days ≥10℃" + 0.052 × "Sunshine hours during the growing season" + 0.051 × "Soil pH value" + 0.153 × "Soil type" + 0.042 × "Altitude" + 0.042 × "Slope" + 0.004 × "Distance from road" + 0.001 × "Distance from river".

[0243] Substituting the plot data of farmer A's target plot into the above formula, the planting suitability value of the plot is calculated to be 0.87.

[0244] Step 4: Model planting stability using the similarity of historical normalized vegetation index curves.

[0245] Step 4.1: Obtain spectral remote sensing data of the region with a temporal resolution of no less than 16 days over the past five years of crop growth cycles.

[0246] Step 4.2: Analyze the spectral data to obtain the normalized vegetation index at each sampling time point, and then obtain the NDVI time series curve within a growth cycle.

[0247] like Figure 3 As shown, Figure 3 The NDVI curve X of the target plot in 2021 T And the NDVI curve Y in 2020 T Example diagram.

[0248] Step 4.3: Analyze the NDVI curves X for 2021 and 2020. T and Y T Savitzky-Golay filtering was performed to obtain the reconstructed NDVI time series X′. T and Y′ T :

[0249] Reconstructed NDVI time series X′ T and Y′ T See also Figure 4 .

[0250] Step 4.4: Calculate sequence X′ T and Y′ T The Pearson correlation coefficient between sequences is used to obtain sequence similarity.

[0251]

[0252] Analyzing the NDVI curves over the past five years, the Pearson correlation coefficient (COR) for adjacent two years was obtained. 21-20 COR 20-1 COR 19-1 COR 18-1 The average Pearson correlation coefficient COR was calculated. mean =0.95.

[0253] Step 5: Use farmer information to model and obtain farmer credit limits.

[0254] Based on historical data from area A, the average corn yield there is 635 kg / mu, the corn purchase price is 2720 yuan / ton, and the summer corn planting cost is approximately 800 yuan / mu. Therefore, the planting profit H and planting cost C are respectively:

[0255]

[0256]

[0257] Since the planting suitability k1 = 0.87 and the planting stability k2 = 0.95, the recommended credit limit L can be calculated based on the credit limit model. r for:

[0258] L r =α×k1×k2×(HC)

[0259] =1.5×0.87×0.95×(21538-9976)=14334

[0260] If the financial institution's pre-set safety net limit L f The amount is 3000 yuan, and the capped amount is L. h If the amount is 100,000 yuan, then the final credit limit L is:

[0261] L=min{max{L r ,L f},L h}=min{max{14334,3000},100000}=14334

[0262] That is, the credit line granted by the financial institution to farmer B can be 14,334 yuan.

[0263] like Figure 5 As shown in the figure, this application embodiment also provides a data processing apparatus, the apparatus including:

[0264] The acquisition module 501 is used to acquire remote sensing data of the target plot over P crop cycles. The target plot is the plot associated with the trusted object, and P is an integer greater than 1.

[0265] The first determining module 502 is used to determine planting suitability and planting stability based on remote sensing data;

[0266] The execution module 503 is used to determine the credit limit for the credit recipient based on planting suitability and planting stability, and to perform operations on the credit recipient according to the credit limit.

[0267] Optionally, the first determining module 502 includes:

[0268] The first determination submodule is used to determine the target planting type based on remote sensing data. The target planting type is the planting type in the target crop cycle within P crop cycles.

[0269] The first acquisition submodule is used to acquire R suitability indicators corresponding to the target planting type according to a preset first correspondence relationship. The first correspondence relationship includes the correspondence between the target planting type and the R suitability indicators, where R is an integer greater than 1.

[0270] The second acquisition submodule is used to acquire measurement data associated with the target plot and corresponding to R suitability indicators, and to determine the values ​​of R indicators corresponding to the R suitability indicators based on the measurement data.

[0271] The second determination submodule is used to determine planting suitability based on R index values.

[0272] Optionally, the second determining submodule includes:

[0273] The first acquisition unit is used to acquire the weight values ​​of R indicators corresponding to the R suitability indicators, wherein the weight values ​​of the indicators corresponding to the suitability indicators are positively correlated with the importance of the suitability indicators to the growth of the target planting type.

[0274] The first determining unit is used to calculate the weighted sum of the R indicator values ​​based on the weight values ​​of the R indicators to obtain the planting suitability.

[0275] Optionally, the R suitability indicators belong to at least one criterion;

[0276] The first acquisition unit includes:

[0277] The first acquisition subunit is used to acquire the criterion weight value of the target criterion and all S suitability indicators belonging to the target criterion, wherein the target criterion is any one of at least one criteria.

[0278] Establish a sub-unit to build a weight judgment matrix for S suitability indicators when S is an integer greater than 1. The value of the element in the i-th row and j-th column of the weight judgment matrix represents the relative growth importance between the i-th suitability indicator and the j-th suitability indicator. i and j are both positive integers less than or equal to S.

[0279] The second acquisition subunit is used to normalize the eigenvectors of the weight judgment matrix to obtain the weight vector;

[0280] The sub-unit is determined based on the criterion weight value and the weight vector to determine the indicator weight value corresponding to each of the S suitability indicators.

[0281] Optionally, the first acquisition unit may further include:

[0282] The verification subunit is used to verify the consistency of the weight judgment matrix when S is an integer greater than 2.

[0283] Accordingly, the second acquisition subunit can be specifically used for:

[0284] If the consistency check of the weight judgment matrix passes, the eigenvectors of the weight judgment matrix are normalized to obtain the weight vector.

[0285] Optionally, the inspection subunit is specifically used for:

[0286] Obtain the largest eigenvalue of the weight judgment matrix;

[0287] Based on the largest eigenvalue and the order of the weight judgment matrix, the consistency index of the weight judgment matrix is ​​determined. Based on the order of the weight judgment matrix and the correspondence between the preset order and the average consistency index, the average consistency index of the weight judgment matrix is ​​determined.

[0288] The consistency of the weight judgment matrix is ​​tested based on the ratio of the consistency index to the average consistency index.

[0289] Among them, the consistency test of the weight judgment matrix is ​​passed when the ratio of the consistency index to the average consistency index is less than the preset ratio.

[0290] Optionally, the first determining module 502 includes:

[0291] The second acquisition submodule is used to acquire P normalized vegetation index (NDVI) streams of the target plot in P crop cycles based on remote sensing data. Each NDVI stream includes NDVI at multiple preset sampling time points in the corresponding crop cycle.

[0292] The third determination submodule is used to determine the planting stability based on P NDVI streams.

[0293] Optionally, the third determining submodule may include:

[0294] The second acquisition unit is used to acquire the first NDVI stream and the second NDVI stream, which are any two NDVI streams that are adjacent in the crop cycle.

[0295] The second determining unit is used to determine the similarity between the first NDVI stream and the second NDVI stream;

[0296] The third determining unit is used to determine planting stability based on similarity.

[0297] Optionally, the data processing apparatus may further include:

[0298] The second determination module is used to determine the target planting type and the area of ​​the target plot based on remote sensing data;

[0299] The third determination module is used to determine the credit limit for the credit recipient based on planting suitability and stability, including:

[0300] The fourth module is used to determine the net income from planting based on the target planting type and the area of ​​the plot.

[0301] The correction module is used to adjust the net income from planting based on planting suitability, planting stability, and a preset credit limit coefficient to obtain the credit limit.

[0302] It should be noted that this data processing device is a device corresponding to the above-described data processing method. All implementation methods in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0303] Figure 6 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0304] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

[0305] Specifically, the processor 601 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0306] Memory 602 may include mass storage for data or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 602 is non-volatile solid-state memory.

[0307] In a particular embodiment, memory 602 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0308] The processor 601 implements any of the data processing methods described in the above embodiments by reading and executing computer program instructions stored in the memory 602.

[0309] In one example, the electronic device may also include a communication interface 603 and a bus 610. For example, Figure 6 As shown, the processor 601, memory 602, and communication interface 603 are connected through bus 610 and complete communication with each other.

[0310] The communication interface 603 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0311] Bus 610 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 610 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0312] Furthermore, in conjunction with the data processing methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the data processing methods in the above embodiments.

[0313] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0314] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0315] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0316] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0317] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A data processing method, characterized by, The method comprises the following steps: acquiring remote sensing data of a target land plot in P crop cycles, the target land plot being a land plot associated with a credit object, P being an integer greater than 1, the P crop cycles corresponding to crop cycles of multiple years; determining, according to the remote sensing data, a planting suitability and a planting stability, the planting suitability representing an adaptability of a crop type planted in the target land plot to relevant factors of the target land plot, the planting stability representing a variation of the crop type planted in the P crop cycles, the planting suitability and the planting stability having a correlation with a repayment ability of the credit object; determining a credit limit for the credit object according to the planting suitability and the planting stability, and performing an operation on the credit object according to the credit limit; determining the planting suitability according to the remote sensing data comprises the following steps: determining a target planting type according to the remote sensing data, the target planting type being a planting type in a target crop cycle in the P crop cycles; acquiring R suitability indexes corresponding to the target planting type according to a preset first correspondence relationship, the first correspondence relationship comprising a correspondence relationship between the target planting type and the R suitability indexes, R being an integer greater than 1, the R suitability indexes belonging to at least one criterion; acquiring measurement data associated with the target land plot and corresponding to the R suitability indexes, and determining R index values corresponding to the R suitability indexes according to the measurement data; acquiring a criterion weight value of a target criterion and all S suitability indexes belonging to the target criterion, the target criterion being any one of the at least one criterion; in a case where S is an integer greater than 1, establishing a weight judgment matrix for the S suitability indexes, a value of an ith row, jth column element in the weight judgment matrix representing a relative growth importance between the ith suitability index and the jth suitability index, i and j both being positive integers less than or equal to S; normalizing a characteristic vector of the weight judgment matrix to obtain a weight vector; determining an index weight value corresponding to each of the S suitability indexes according to the criterion weight value and the weight vector, wherein the index weight value corresponding to the suitability index is positively correlated with a growth importance of the suitability index to the target planting type; weighting and summing the R index values according to the R index weight values to obtain the planting suitability.

2. The method of claim 1, wherein, Before the characteristic vector of the weight judgment matrix is normalized to obtain the weight vector, the method further comprises the following steps: in a case where S is an integer greater than 2, checking consistency of the weight judgment matrix; the normalization of the characteristic vector of the weight judgment matrix to obtain the weight vector comprises the following steps: in a case where the consistency check of the weight judgment matrix is passed, the characteristic vector of the weight judgment matrix is normalized to obtain the weight vector.

3. The method of claim 2, wherein, the consistency check of the weight judgment matrix comprises the following steps: acquiring a maximum eigenvalue of the weight judgment matrix; determine a consistency index of the weight judgment matrix according to the maximum eigenvalue and an order of the weight judgment matrix, and determine an average consistency index of the weight judgment matrix according to the order of the weight judgment matrix and a preset correspondence between orders and average consistency indexes; verify the consistency of the weight judgment matrix according to a ratio of the consistency index to the average consistency index; wherein, in a case that the ratio of the consistency index to the average consistency index is less than a preset ratio, the consistency verification of the weight judgment matrix is passed.

4. The method of claim 1, wherein, determine a planting stability according to the remote sensing data, including: obtain P normalized vegetation index (NDVI) flows of the target land plot in P crop cycles according to the remote sensing data, each of the NDVI flows including NDVI at a plurality of preset sampling time points in a corresponding crop cycle; determine the planting stability according to the P NDVI flows.

5. The method of claim 4, wherein, The determining of the planting stability according to the P NDVI flows includes: obtain a first NDVI flow and a second NDVI flow, the first NDVI flow and the second NDVI flow being any two NDVI flows adjacent to each other in the crop cycles; determine a similarity between the first NDVI flow and the second NDVI flow; determine the planting stability according to the similarity.

6. The method of claim 1, wherein, After the remote sensing data of the target land plot in the P crop cycles is obtained, the method further includes: determine a target planting type according to the remote sensing data, and determine a land plot area of the target land plot; determine a credit limit for the credit object according to the planting suitability and the planting stability, including: determine a planting net income according to the target planting type and the land plot area; correct the planting net income based on the planting suitability, the planting stability, and a preset limit coefficient to obtain the credit limit.

7. A data processing apparatus, characterized by The device includes: an obtaining module, configured to obtain remote sensing data of a target land plot in P crop cycles, the target land plot being a land plot associated with a credit object, P being an integer greater than 1, and the P crop cycles corresponding to crop cycles of multiple years; a first determining module, configured to determine a planting suitability and a planting stability according to the remote sensing data, the planting suitability representing an adaptation capability of a crop type planted in the target land plot to relevant factors of the target land plot, and the planting stability representing a variation of the crop type in the P crop cycles, the planting suitability and the planting stability having a correlation with a repayment capability of the credit object; a determining and performing module, configured to determine a credit limit for the credit object according to the planting suitability and the planting stability, and perform an operation on the credit object according to the credit limit; the first determining module is specifically configured to: determine a target planting type according to the remote sensing data, the target planting type being a planting type in a target crop cycle in the P crop cycles. According to a preset first correspondence relationship, R suitability indexes corresponding to the target planting type are obtained, the first correspondence relationship including a correspondence relationship between the target planting type and the R suitability indexes, R being an integer greater than 1, the R suitability indexes belonging to at least one criterion; Measurement data associated with the target plot and corresponding to the R suitability indexes are obtained, and R index values corresponding to the R suitability indexes are determined according to the measurement data; A criterion weight value of a target criterion and all S suitability indexes belonging to the target criterion are obtained, the target criterion being any one of the at least one criterion; In the case where S is an integer greater than 1, a weight judgment matrix is established for the S suitability indexes, a value of an element in the ith row and the jth column of the weight judgment matrix representing a relative growth importance between the ith suitability index and the jth suitability index, i and j being positive integers less than or equal to S; A weight vector is obtained by normalizing a characteristic vector of the weight judgment matrix; According to the criterion weight value and the weight vector, an index weight value corresponding to each of the S suitability indexes is determined, wherein the index weight value corresponding to the suitability index is positively correlated with the growth importance of the suitability index to the target planting type; According to the R index weight values, the R index values are weighted and summed to obtain the planting suitability.

8. An electronic device, comprising: The device comprises a processor and a memory storing computer program instructions; The processor executes the computer program instructions to implement the data processing method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer program instructions are stored on the computer readable storage medium, and when executed by the processor, implement the data processing method of any one of claims 1-6.

10. A computer program product, characterised in that, The instructions in the computer program product are executed by the processor of the electronic device, so that the electronic device executes the data processing method of any one of claims 1-6.

Images