WO2022001811A1 - 授信额度处理方法及装置、作物识别方法及装置 - Google Patents

授信额度处理方法及装置、作物识别方法及装置 Download PDF

Info

Publication number
WO2022001811A1
WO2022001811A1 PCT/CN2021/102030 CN2021102030W WO2022001811A1 WO 2022001811 A1 WO2022001811 A1 WO 2022001811A1 CN 2021102030 W CN2021102030 W CN 2021102030W WO 2022001811 A1 WO2022001811 A1 WO 2022001811A1
Authority
WO
WIPO (PCT)
Prior art keywords
crop
plot
information
target
credit
Prior art date
Application number
PCT/CN2021/102030
Other languages
English (en)
French (fr)
Inventor
顾欣欣
甘利民
汪佳
孙剑哲
余泉
孙晓冬
Original Assignee
浙江网商银行股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 浙江网商银行股份有限公司 filed Critical 浙江网商银行股份有限公司
Publication of WO2022001811A1 publication Critical patent/WO2022001811A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/188—Vegetation

Definitions

  • This document relates to the technical field of data processing, in particular to a method and device for processing a credit line, and a method and device for crop identification.
  • One or more embodiments of this specification provide a method for processing a credit line, including: acquiring plot information of a target user's crop plot; taking the plot coordinate information and time information contained in the plot information as input parameters , call the crop identification interface to identify the crop type; determine the confidence level of the plot information according to the crop type distribution returned by the crop identification interface and the target crop type included in the plot information; based on the confidence level, The land parcel information and the crop attribute corresponding to the target crop type determine the credit limit of the target user.
  • One or more embodiments of this specification provide a method for crop identification, including: receiving a call request sent by a caller to identify crop types; One or more crop plots mapped by the plot coordinate information; according to the crop species of the image units included in the one or more crop plots, determine the crop species distribution of the polygonal plot corresponding to the plot coordinate information; The caller returns the crop species distribution.
  • the crop type of the image unit included in the crop plot is output after the crop identification model is used to identify the input remote sensing image for the crop type.
  • One or more embodiments of this specification provide a credit line processing device, including: a plot information acquisition module, configured to acquire plot information of a target user's crop plots; a crop type identification module, configured to The plot coordinate information and time information contained in the plot information are input parameters, and the crop identification interface is called to identify the crop species; the confidence determination module is configured to be based on the crop species distribution returned by the crop identification interface, and the crop identification interface.
  • the target crop type included in the plot information determines the confidence level of the plot information; the credit limit determination module is configured to, based on the confidence level, the plot information and the crop attribute corresponding to the target crop type, Determine the credit limit of the target user.
  • One or more embodiments of the present specification provide a crop identification device, including: a call request receiving module configured to receive a call request sent by a caller to identify crop types; a crop plot determination module configured to The plot coordinate information and time information carried in the call request are used to determine one or more crop plots mapped by the plot coordinate information; the crop species distribution determination module is configured to determine one or more crop plots according to the one or more crop plots.
  • the crop type of the included image unit determines the crop type distribution of the polygonal plot corresponding to the plot coordinate information; the crop type distribution return module is configured to return the crop type distribution to the caller.
  • the crop type of the image unit included in the crop plot is output after the crop identification model is used to identify the input remote sensing image for the crop type.
  • One or more embodiments of the present specification provide a credit line processing device including a processor and a memory configured to store computer-executable instructions.
  • the computer-executable instructions when executed, cause the processor to: acquire the plot information of the target user's crop plot; take the plot coordinate information and time information contained in the plot information as input parameters, call the crop
  • the identification interface performs crop type identification; according to the crop type distribution returned by the crop identification interface and the target crop type included in the plot information, the confidence level of the plot information is determined; based on the confidence level, the The land parcel information and the crop attributes corresponding to the target crop type determine the credit limit of the target user.
  • One or more embodiments of the present specification provide a crop identification device including a processor and a memory configured to store computer-executable instructions.
  • the computer-executable instructions when executed, cause the processor to: receive a call request sent by a caller to identify crop types; and determine the land parcel according to the parcel coordinate information and time information carried in the invocation request One or more crop plots mapped by the coordinate information; according to the crop species of the image units included in the one or more crop plots, determine the crop species distribution of the polygonal plot corresponding to the plot coordinate information;
  • the caller returns the crop species distribution.
  • the crop type of the image unit included in the crop plot is output after the crop identification model is used to identify the input remote sensing image for the crop type.
  • One or more embodiments of the present specification provide a storage medium for storing computer-executable instructions, the computer-executable instructions, when executed, implement the following processes: acquiring plot information of a target user's crop plot; The plot coordinate information and time information contained in the plot information are input parameters, and the crop identification interface is called to identify the crop species; the crop species distribution returned by the crop identification interface, and the target contained in the plot information The crop type, the confidence level of the plot information is determined; the credit limit of the target user is determined based on the confidence level, the plot information and the crop attribute corresponding to the target crop type.
  • One or more embodiments of this specification provide a storage medium for storing computer-executable instructions, the computer-executable instructions, when executed, implement the following process: receiving a call request sent by a caller to identify crop species; One or more crop plots mapped by the plot coordinate information are determined according to the plot coordinate information and time information carried in the call request; according to the crop types of the image units contained in the one or more crop plots , determine the crop type distribution of the polygonal plot corresponding to the plot coordinate information; and return the crop type distribution to the caller.
  • the crop type of the image unit included in the crop plot is output after the crop identification model is used to identify the input remote sensing image for the crop type.
  • FIG. 1 is a processing flow chart of a method for processing a credit line provided by one or more embodiments of this specification;
  • Fig. 2 is a processing flow chart of a credit limit processing method applied to a scenario of agricultural assistance loan projects provided by one or more embodiments of this specification;
  • FIG. 3 is a processing flow chart of a method for processing a credit line applied to an agricultural security project scenario provided by one or more embodiments of this specification;
  • FIG. 4 is a processing flow chart of a method for processing a credit limit applied to a resource management project scenario provided by one or more embodiments of this specification;
  • FIG. 5 is a processing flow chart of a crop identification method provided by one or more embodiments of this specification.
  • FIG. 6 is a schematic diagram of a credit limit processing apparatus provided by one or more embodiments of the present specification.
  • FIG. 7 is a schematic diagram of a crop identification device provided by one or more embodiments of the present specification.
  • FIG. 8 is a schematic structural diagram of a credit line processing device provided by one or more embodiments of this specification.
  • FIG. 9 is a schematic structural diagram of a crop identification device according to one or more embodiments of the present specification.
  • FIG. 1 An embodiment of a credit limit processing method provided in this specification: Referring to Fig. 1 , the credit limit processing method provided by this embodiment includes steps S102 to S108.
  • Step S102 acquiring plot information of the target user's crop plot.
  • the credit limit processing method provided in this embodiment is aimed at target users in the list of large crop planters, combined with specific online applications or online services, to open a dedicated credit processing channel for these target users, specifically according to the input of the target users.
  • the plot coordinate information and time information contained in the plot information call the crop identification interface to identify the crop species, so as to verify the target crop species in the plot information entered by the target user according to the identified crop species, so as to determine the target.
  • the user's confidence level, and starting from the target user's confidence level, the credit line is allocated to the user in combination with the plot information and crop attributes, so that the target user can obtain a credit line that is more in line with the actual credit situation and asset status, and the provided credit line
  • the quota can facilitate the basic production and operation of the target user, thereby promoting the improvement of the production and operation efficiency of the target user.
  • the target users in this embodiment refer to the users recorded in the preset user list (for example, the list of large planting households). Specifically, they can own or contract a large amount of land (such as more than 10 mu) and use this as the main economic
  • the source growers are defined as large growers and included in the list of large growers.
  • the list of major planters can be provided by a third-party organization, or the list of major planters can be determined after an offline survey of the growers, and the list of major planters can also be generated through the grower's application based on the approved application. This is not limited.
  • the crop plot refers to the land, paddy field or seawater planting area used for planting crops, forest crops, aquatic crops and other surface-grown crops.
  • the plot information includes the types of crops planted in the crop plot, the plot area of the crop plot (for example, the value of the plot area in mu), and the coordinate information of the plot where the crop plot is located (such as , the latitude and longitude information of the crop plot) and time information.
  • this embodiment opens a credit processing channel for the target user in the preset user list, the credit processing channel is bound to the target application, and the identity information and land parcel information of the target user are triggered when the target user triggers the credit processing.
  • the target user in the preset user list can perform information entry and credit limit processing through the credit processing channel bound to the target application. For example, during the use of the target application, the credit limit can be increased by entering information.
  • the trigger control of the credit processing channel is displayed based on the application page of the target application, and the target The user triggers the credit processing channel by triggering the trigger control.
  • credit extension refers to funds directly provided by banks, payment platforms and other institutions to users, or guarantees for compensation and payment responsibilities that users may generate in relevant activities.
  • On-balance sheet services such as advances can also be provided for off-balance sheet services such as bill acceptance, letter of credit issuance, and letter of guarantee.
  • Credit line refers to the stock management index of short-term credit business approved by banks, payment platforms and other institutions for users.
  • the loan application in the payment platform is bound to the channel for increasing the credit line.
  • the loan amount needs to be determined with reference to the credit line of the grower.
  • the application page of the loan application is provided with an amount increase control for the grower to process the amount increase;
  • the amount control is used to trigger the credit limit increase channel, so that the credit limit increase process is performed through the credit limit increase channel.
  • the target user's credit is used as a guarantee or mortgage to provide the target user with corresponding resources to ensure The planting, production and business activities of the target user can be maintained.
  • the target user’s planting, production and business activities can be carried out normally by providing a credit guarantee or a mortgage loan to the target user.
  • the crop business contract refers to The target user signs the contract with the resource provider based on its own credit line, and the resources obtained after signing the crop management contract are agreed to be used for planting, production and operation activities.
  • the target user who signs the crop management contract can obtain corresponding funds from the loan provider.
  • the target user who signs the crop management contract can also obtain the planting required in the planting production and operation activities from the equipment provider.
  • the production equipment, or the target user who signs the crop management contract can also obtain the planting raw materials required in the planting production and business activities from the raw material provider, which is not limited.
  • the crop management contract described in this embodiment is signed in the following ways: obtaining the application request submitted by the target user through the application control configured on the contract application page that triggers the target application; judging whether the application amount contained in the application request is less than or equal to the Describe the credit line; if yes, sign the crop management contract with the target user as the contract participant based on the application amount and the plot information of the crop plot submitted by the target user; For the credit limit of the target user, it is sufficient to send a reminder to the target user that the applied limit exceeds the credit limit.
  • the loan application in the payment platform opens the function of applying for agricultural loans to grower A, and grower A can apply for a loan for planting, production and operation activities through the loan application.
  • grower A can apply for a loan for planting, production and operation activities through the loan application.
  • the loan application amount submitted by the grower A is determined based on the loan application limit of the grower A carried in the loan request. Whether it is greater than the credit limit of grower A (assuming it is 10,000 yuan); if the loan application amount submitted by grower A is less than 10,000 yuan, grower A is the borrower and the fund provider is the lender.
  • the farmer A's crop type as the plot, the plot coordinate information and time information of the plot where the crop plot is located are recorded in the agricultural assistance business loan contract.
  • the premise for the target user to obtain resource support in planting, production and business activities is to use the credit of the target user as a guarantee or mortgage, and deduct or freeze the corresponding part of the credit limit of the target user; this
  • the contract information includes the contract limit of the crop management contract, and after the target user signs the crop management contract based on the credit limit, the amount of the credit limit used for signing the crop management contract is determined.
  • the used sub-quota corresponding to the contract quota is frozen; correspondingly, the used sub-quota is restored after the target user performs the performance clause recorded in the crop management contract.
  • grower A's credit line is 10,000 yuan. If grower A applies for 6,000 yuan for planting, 6,000 yuan of the 10,000 yuan credit line will be frozen after signing the crop management contract; correspondingly, if grower A repays If some or all of the 6,000 yuan is received, the corresponding part of the frozen credit line will be unfrozen and repaid.
  • the credit application page of the credit processing channel under the target application is displayed to the target user; wherein, the credit application page is configured with an information input interface and a credit application control;
  • the block information is entered based on the information input interface, and the block information input by the target user is acquired after the credit application control is triggered, that is, the acquisition of the land block information of the target user's crop plot in this step is performed in the credit application control. Executed on a triggered basis.
  • Step S104 using the plot coordinate information and time information included in the plot information as input parameters, call the crop identification interface to identify crop types.
  • the crop type identification is performed by calling the crop identification interface.
  • based on The crop identification model configured by the crop identification interface is used to identify the crop type.
  • the crop identification model adopts the following method to identify the crop type.
  • the remote sensing image is used as the input, and the crop type identification is performed on the crop plots contained in the input remote sensing image at the image unit granularity, and the crop species corresponding to each image unit contained in the crop plot contained in the input remote sensing image is obtained.
  • the crop identification model is trained in the following ways: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring crops of crop plots in the specified area within the specified time range
  • the type and plot boundary information are used as sample labels; the mapping relationship between the training samples and the sample labels is established, and the training samples and the sample labels are used as training sets for model training to obtain the crop identification model.
  • the crop identification interface In order to improve the efficiency of crop type identification, enable the crop identification interface to respond quickly when it is called, and perform crop type identification on the crop plot to return the corresponding identification result.
  • the crop type is stored; correspondingly, in the process of calling the crop identification interface to perform the crop type identification step with the plot coordinate information and time information contained in the plot information as input parameters, the crop identification interface is based on the stored data.
  • the crop types of the crop plots in the target area within the target time range are determined, and the crop species distribution of the crop plots is determined, so as to improve the response efficiency of the crop identification interface to the identification of crop species.
  • the satellite remote sensing images of the designated area and time are downloaded from open source channels or purchased by satellite companies as training samples; the spatial resolution of the satellite remote sensing images is 10m, and the temporal resolution is 5 The number of spectral channels is red, green, blue and near-infrared; secondly, the historical crop distribution in the designated area is purchased from a third-party organization, or the historical crop information in the designated area is manually marked in a low-key manner, and the crop training model Sample label, the labeling data of the sample label includes the crop type and the latitude and longitude polygon information of the corresponding crop plot boundary; then, the crop distribution coordinates and satellite remote sensing images are converted and mapped, as the input of the training set of the crop identification model; the crop identification model Specifically, the deeplabv3+ semantic segmentation network in deep learning is used to abstract the identification of crop types of crop plots as a semantic segmentation problem; finally, on the basis of the crop identification model obtained after the training is completed, the satellite
  • the crop recognition model can also use other deep learning semantic segmentation algorithms such as HRNet OCR, FCN series, Unet and its various variants.
  • other traditional crop identification methods in the remote sensing field can also be used to identify crop species, such as the use of spectral matching methods to identify crop species on farmers' crop plots.
  • Step S106 Determine the confidence level of the plot information according to the crop type distribution returned by the crop identification interface and the target crop type included in the plot information.
  • the remote sensing image to which the image coordinate information of the plot coordinate information is mapped in the time information is used as input, and the image unit granularity
  • the crop plots included in the input remote sensing image are identified by crop species, so as to obtain the crop species corresponding to each image unit included in the crop plots included in the input remote sensing image.
  • the crop species distribution described in this embodiment is determined by the target user.
  • the crop plot consists of the corresponding crop types of each image unit contained in the crop plot.
  • the crop identification model configured by the crop identification interface divides the crop plot. It is 100 remote sensing image units, and then the corresponding crop types of these 100 remote sensing image units are respectively identified.
  • the set of crop types corresponding to the 100 remote sensing image units contained in the crop plot is the crop of the crop plot. species distribution.
  • the confidence level of the plot information is determined according to the crop type distribution returned by the crop identification interface and the target crop type included in the plot information, specifically according to the crop type and the crop type distribution in the crop type distribution The number of image units with the same target crop type, and the total number of image units in the species distribution, to calculate the confidence level of the plot information; wherein, the confidence level includes crops in the crop type distribution The ratio of the number of image units of the same type as the target crop type to the total number.
  • the crop identification interface returns the crop type distribution composed of the corresponding crop types of the 100 remote sensing image units (pixels in the remote sensing image) contained in the crop plot of grower A, specifically, 80 remote sensing image units correspond to
  • the crop type is identified as wheat, and the crop type corresponding to the 20 remote sensing image units is identified as rice; the crop type included in the plot information of the crop plot entered by grower A is wheat, that is: the crop input by grower A
  • the crop types corresponding to the 100 remote sensing image units included in the plot are all wheat, and in the crop type distribution returned by the crop identification interface, the number of remote sensing image units corresponding to the crop type is wheat is 80. Based on this, the growers are calculated.
  • Step S108 Determine the credit limit of the target user based on the confidence level, the plot information, and the crop attribute corresponding to the target crop type.
  • the confidence degree is regarded as the target user's confidence degree. Constraints for users to allocate credit lines, or use confidence as a parameter for evaluating the target user's credit line, so as to promote the improvement of the credit system through the constraints of confidence.
  • the confidence threshold is used to judge whether the plot information of the crop plot input by the target user is credible; if the confidence is greater than the preset confidence threshold, it indicates that the plot information input by the target user is credible, based on the plot information and the crop attribute corresponding to the target crop type, to determine the credit limit of the target user; wherein, according to the target crop type, the plot area included in the plot information, the regional information, and the crop attribute including If the confidence level is less than or equal to the preset credit threshold, it indicates that the plot information input by the target user is not credible, and the credit line is issued to the target user. Reminder of failed application.
  • the confidence level of the crop type of the crop plot input by grower A is 80%, which is greater than the preset confidence threshold of 60%, indicating that the plot information input by grower A is credible, then Based on the plot area of the crop plot contained in the plot information entered by grower A, the geographic information to which the crop plot belongs, the unit price per mu corresponding to the crop type of the crop plot, and the crops of the crop plot The value of the species corresponding to the information in this region fluctuates, and the exclusive credit line allocated to grower A is calculated.
  • different target users may apply for credit lines for different needs, or are in different credit states when applying for credit lines.
  • some growers have not yet opened credit services when applying for credit lines, or, some The grower has already opened the credit service and already has a certain credit line when applying for the credit line.
  • some growers have used their credit line through loans or mortgages when applying for the credit line.
  • This embodiment provides an optional In the implementation manner, after the credit limit of the target user is determined, in order to improve the user experience of the target user, starting from the credit status of the target user, targeted processing is performed on the target users in different credit status, and the specific implementation is as follows: read the target user.
  • the credit status of the user if the credit status of the target user is not granted, the credit processing is performed on the target user based on the credit limit; if the credit status of the target user is credit, the credit limit is based on the credit
  • the initial credit limit of the target user is adjusted; if the credit status of the target user is that the credit has been used, based on the contract information recorded in the crop management contract signed by the target user, a performance reminder is generated and sent to the target user. .
  • the crop plots of the target user can also be combined with the crop types of the crop plot to make risk predictions and remind the crop plot, so as to reduce the risk loss of the target user.
  • the specific implementation is as follows : obtain the positioning data of the terminal device of the target user; calculate the predicted plot area of the crop plot based on the positioning data; based on the target crop type, the predicted plot area, the The regional information, the crop value contained in the crop attributes, and the value fluctuation determine the risk level of the crop plot; based on the risk level, a risk warning prompt is generated and displayed to the target user.
  • the crop plot is calculated based on the target crop type, the plot area included in the plot information, and the crop attributes corresponding to the target crop type.
  • the crop value of the target user is determined according to the crop value, so as to provide security for the target user's crop plot.
  • the land parcel boundary information contained in the parcel information is read; the parcel boundary information is determined based on the labeling action input by the target user on the displayed map page;
  • the block boundary information calculates the predicted plot area of the crop plot; based on the target crop type, the predicted plot area and the crop attribute, calculates the crop value of the crop plot; according to the crop value and
  • the resource conversion rate corresponding to the target crop type is calculated, and the resource conversion value corresponding to the crop plot is calculated; based on the resource conversion value and the resource preference and/or resource status of the target user, the Resource management strategy.
  • Implementation mode 1 Calculate the crop value of the crop plot based on the target crop type, the plot area included in the plot information, and the crop attribute corresponding to the target crop type; determine the crop value according to the crop value. Describe the guaranteed amount of the target user.
  • Implementation mode 2 read the parcel boundary information contained in the parcel information; the parcel boundary information is determined based on the labeling action input by the target user on the displayed map page; The predicted plot area of the crop plot; based on the target crop type, the predicted plot area and the crop attribute, calculate the crop value of the crop plot; according to the crop value and the target crop type The corresponding resource conversion rate is calculated, and the resource conversion value corresponding to the crop plot is calculated; based on the resource conversion value and the resource preference and/or resource status of the target user, a resource management strategy for the crop plot is generated.
  • the following takes the application of a credit line processing method provided by this embodiment in the scenario of agricultural assistance loan projects as an example to further illustrate the credit quota processing method provided in this embodiment.
  • the credit limit processing method specifically includes steps S202 to S220.
  • Step S202 acquiring the plot information of the crop plot of the grower.
  • the project page based on the agricultural assistance loan project displays the trigger control of the credit processing channel; after detecting that the trigger control is triggered, it displays the assistance
  • the credit application page of the credit processing channel under the agricultural loan project is equipped with an information input interface and a credit application control; growers can enter the plot information of the crop plot through the information input interface, and can use the credit application control to enter the information. Apply for a line of credit.
  • the plot information includes the types of crops planted in the crop plot, the plot area of the crop plot (for example, the plot area value in mu), and the coordinate information of the plot where the crop plot is located (for example, Longitude and latitude information of crop plots) and time information.
  • Step S204 using the plot coordinate information and time information included in the plot information as input parameters, call the crop identification interface to identify the crop species.
  • Step S206 according to the crop type distribution returned by the crop identification interface and the target crop type included in the field information, determine the confidence level of the plot information.
  • Step S208 judging whether the confidence is greater than the preset reliability threshold; if so, indicating that the plot information input by the grower is credible, then step S212 is executed, based on the plot information and the crop attributes corresponding to the target crop species, determine the grower's credit If not, it indicates that the plot information input by the grower is not credible, and step S210 is executed to send a reminder to the grower that the application for the credit line fails.
  • Step S210 sending a reminder to the grower that the application for the credit line fails.
  • Step S212 based on the plot information and the crop attributes corresponding to the crop types contained in the plot information, determine the credit limit of the grower.
  • Step S214 read the credit status of the grower.
  • step S216 if the credit status of the grower is not granted, credit processing is performed on the grower based on the credit limit.
  • Step S220 if the credit status of the grower is that the credit has been used, based on the contract information recorded in the crop management contract signed by the grower, a contract performance reminder is generated and sent to the grower.
  • Step S302 acquiring the plot information of the crop plot of the grower.
  • the trigger control of the credit guarantee processing channel is displayed on the project page based on the agricultural security project; when it is detected that the trigger control is triggered After that, the credit guarantee application page of the credit guarantee processing channel under the agricultural guarantee project is displayed to the grower; the credit guarantee application page is equipped with an information input interface and a credit guarantee application control; the grower can enter the land of the crop plot through the information input interface.
  • the credit guarantee limit refers to the guarantee amount allocated to the grower's crop plot from the grower's credit.
  • the plot information includes the types of crops planted in the crop plot, the plot area of the crop plot (for example, the plot area value in mu), and the coordinate information of the plot where the crop plot is located (for example, Longitude and latitude information of crop plots) and time information.
  • Step S304 using the plot coordinate information and time information contained in the plot information as input parameters, call the crop identification interface to identify the crop species.
  • Step S306 Determine the confidence level of the plot information according to the distribution of crop species returned by the crop identification interface and the target crop species included in the plot information.
  • Step S308 judging whether the confidence is greater than the preset reliability threshold; if yes, it indicates that the plot information input by the grower is credible, then execute steps S312 to S314; if not, it indicates that the plot information input by the grower is not credible, execute Step S310, sending a reminder to the grower that the application for the credit guarantee limit fails.
  • Step S310 sending a reminder to the grower that the application for the credit guarantee limit fails.
  • Step S312 based on the target crop type, the plot area, and the crop attribute corresponding to the target crop type, calculate the crop value of the grower's crop plot.
  • Step S314 determining the credit guarantee limit of the grower's crop plot according to the crop value.
  • Step S402 acquiring the plot information of the crop plot of the grower.
  • the project page based on the agricultural assistance loan project displays the trigger control of the credit processing channel; after detecting that the trigger control is triggered, it displays the assistance
  • the credit application page of the credit processing channel under the agricultural loan project is equipped with an information input interface and a credit application control; growers can enter the plot information of the crop plot through the information input interface, and can use the credit application control to enter the information. Apply for a line of credit.
  • the plot information includes the types of crops planted in the crop plot, the coordinate information of the plot where the crop plot is located (for example, the longitude and latitude information of the crop plot), and time information.
  • Step S404 using the plot coordinate information and time information contained in the plot information as input parameters, call the crop identification interface to identify the crop species.
  • Step S406 according to the crop type distribution returned by the crop identification interface, and the target crop type included in the field information, determine the confidence level of the plot information.
  • Step S408 judging whether the confidence is greater than the preset reliability threshold; if yes, it indicates that the plot information input by the grower is credible, then execute steps S410 to S418; Just deal with it.
  • Step S410 Read the parcel boundary information contained in the parcel information.
  • the land boundary information is determined based on the labeling action input by the grower on the displayed map page.
  • Step S412 Calculate the predicted plot area of the crop plot based on the plot boundary information.
  • step S414 the crop value of the crop plot is calculated based on the target crop type, the predicted plot area and the crop attribute.
  • Step S416 Calculate the resource conversion value corresponding to the crop plot according to the crop value and the resource conversion rate corresponding to the target crop type.
  • the crop identification method provided in this embodiment includes steps S402 to S408.
  • Step S502 Receive a calling request for crop type identification sent by the calling party.
  • Step S504 Determine one or more crop plots mapped by the plot coordinate information according to the plot coordinate information and time information carried in the calling request.
  • Step S506 according to the crop types of the image units included in the one or more crop plots, determine the crop type distribution of the polygonal plots corresponding to the plot coordinate information.
  • the crop type of the image unit included in the crop plot is output after the crop identification model is used to identify the input remote sensing image for the crop type.
  • Step S508 returning the crop type distribution to the caller.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range.
  • Crop type and plot boundary information are used as real labels; establish the mapping relationship between the training samples and the real labels, and use the training samples and the real labels as a training set for model training to obtain the crop identification model .
  • the receiving the calling request for crop type identification sent by the caller includes: inputting the remote sensing image data of the target area within the target time range into the crop identification model for crop type identification; storing the crop identification model. Output crop types of crop plots in the target area within the target time range.
  • the satellite remote sensing images of the designated area and time are downloaded from open source channels or purchased by satellite companies as training samples; the spatial resolution of the satellite remote sensing images is 10m, and the temporal resolution is 5 The number of spectral channels is red, green, blue and near-infrared; secondly, the historical crop distribution in the designated area is purchased from a third-party organization, or the historical crop information in the designated area is manually marked in a low-key manner, and the crop training model Sample label, the labeling data of the sample label includes the crop type and the latitude and longitude polygon information of the corresponding crop plot boundary; then, the crop distribution coordinates and satellite remote sensing images are converted and mapped, as the input of the training set of the crop identification model; the crop identification model Specifically, the deeplabv3+ semantic segmentation network in deep learning is used to abstract the identification of crop types of crop plots as a semantic segmentation problem; finally, on the basis of the crop identification model obtained after the training is completed, the satellite
  • the crop recognition model can also use other deep learning semantic segmentation algorithms such as HRNet OCR, FCN series, Unet and its various variants.
  • other traditional crop identification methods in the remote sensing field can also be used to identify crop species, such as the use of spectral matching methods to identify crop species on farmers' crop plots.
  • FIG. 6 it shows a schematic diagram of an apparatus for processing a credit limit provided by this embodiment.
  • the description is relatively simple, and for the relevant part, please refer to the corresponding description of the method embodiment provided above.
  • the apparatus embodiments described below are merely illustrative.
  • This embodiment provides a credit line processing device, including: a plot information acquisition module 602, configured to acquire plot information of a target user's crop plots; a crop type identification module 604, configured to use the plot information
  • the plot coordinate information and time information contained in are input parameters, and the crop identification interface is called to identify the crop species; the confidence determination module 606 is configured to be based on the crop species distribution returned by the crop identification interface, and the plot information.
  • the target crop type contained in the target crop type to determine the confidence level of the plot information;
  • the credit limit determination module 608 is configured to determine the target crop type based on the confidence level, the plot information and the crop attributes corresponding to the target crop type. Describe the credit limit of the target user.
  • the crop identification interface is configured with a crop identification model, and the crop identification model uses the following method to identify crop types: the remote sensing image to which the image coordinate information of the time information is mapped by mapping the coordinate information of the land plot to the image coordinate information of the time information.
  • the crop types are identified on the crop plots included in the input remote sensing image at the image unit granularity, and the crop species corresponding to each image unit included in the crop plots included in the input remote sensing image are obtained.
  • the confidence determination module 606 is specifically configured to be based on the number of image units in the crop type distribution with the same crop type as the target crop type, and the total number of image units in the crop type distribution. , calculate the confidence level of the plot information; wherein, the confidence level includes the ratio of the number of image units with the same crop type and the target crop type in the crop type distribution to the total number.
  • the credit limit determination module 608 includes: a confidence level judging submodule, configured to judge whether the confidence level is greater than a preset credit threshold; if so, run the credit limit determination submodule; the credit limit is determined A sub-module, configured to determine the credit limit of the target user based on the plot information and the crop attributes corresponding to the target crop type; if not, run the credit limit application failure reminder sub-module; the credit limit application fails The reminder sub-module is configured to send a reminder to the target user that the application for the credit line fails.
  • the credit limit determination sub-module is specifically configured to be based on the target crop type, the plot area included in the plot information, the regional information, the crop value included in the crop attribute, and the value fluctuation. , and their corresponding weights to calculate the credit limit.
  • the credit line processing apparatus further includes: a trigger control display module, configured to display all the information based on the application page of the target application in the case of detecting the application processing request of the target user for the target application.
  • the trigger control of the credit processing channel of the credit processing channel bound by the target application wherein, the credit processing channel is open to the target users recorded in the preset user list;
  • the credit application page display module is configured to detect the After the trigger control is triggered, the credit application page of the credit processing channel under the target application is displayed to the target user; wherein, the credit application page is configured with an information input interface and a credit application control; the land parcel information is based on The information input interface is used for inputting; correspondingly, the land parcel information acquisition module 602 runs after it is detected that the credit application control is triggered.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range. Crop types and plot boundary information are used as sample labels; establish the mapping relationship between the training samples and the sample labels, and use the training samples and the sample labels as a training set for model training to obtain the crop identification model .
  • the credit line processing device further includes: a crop type identification module, configured to input the remote sensing image data of the target area within the target time range into the crop identification model for crop type identification; a crop type storage module, is configured to store the crop types of the crop plots in the target area output by the crop identification model within the target time range; correspondingly, during the operation of the crop type identification module 604, the crop identification The interface determines the crop species distribution of the crop plot based on the stored crop species of the crop plot in the target area within the target time range.
  • the credit line processing device further includes: a credit status reading module configured to read the credit status of the target user; a credit processing module configured to read the credit status of the target user if the target user's credit status is not granted credit , perform credit processing on the target user based on the credit limit; the initial credit limit adjustment module is configured to, if the credit status of the target user is credit granted, the initial credit limit of the target user based on the credit limit Make adjustments; the performance reminder module is configured to generate a performance reminder and send it to the target user based on the contract information recorded in the crop management contract signed by the target user if the credit status of the target user is that the credit has been used. .
  • the credit line processing device further includes: a positioning data acquisition module configured to acquire positioning data of the terminal device of the target user; a predicted plot area calculation module configured to calculate based on the positioning data the predicted plot area of the crop plot; a risk level determination module configured to be based on the target crop species, the predicted plot area, the regional information of the crop plot, and the crops included in the crop attributes The value and value fluctuate to determine the risk level of the crop plot; the risk warning prompt display module is configured to generate a risk early warning prompt based on the risk level and display it to the target user.
  • the credit line processing device further includes: a crop value calculation module, configured to be based on the target crop type, the plot area included in the plot information, and the crop attribute corresponding to the target crop type , calculate the crop value of the crop plot; the guarantee amount determination module is configured to determine the guarantee amount of the target user according to the crop value.
  • a crop value calculation module configured to be based on the target crop type, the plot area included in the plot information, and the crop attribute corresponding to the target crop type , calculate the crop value of the crop plot
  • the guarantee amount determination module is configured to determine the guarantee amount of the target user according to the crop value.
  • the credit line processing device further includes: a land parcel boundary information reading module configured to read parcel boundary information contained in the parcel information; the parcel boundary information is based on the target The labeling action input by the user on the displayed map page is determined; the predicted plot area calculation module is configured to calculate the predicted plot area of the crop plot based on the plot boundary information; the crop value calculation module is configured to be based on The target crop type, the predicted plot area and the crop attribute are used to calculate the crop value of the crop plot; the resource conversion numerical calculation module is configured to Resource conversion rate, calculating the resource conversion value corresponding to the crop plot; a resource management strategy generation module, configured to generate the crop field based on the resource conversion value and the resource preference and/or resource status of the target user The resource management strategy for the block.
  • a land parcel boundary information reading module configured to read parcel boundary information contained in the parcel information
  • the parcel boundary information is based on the target The labeling action input by the user on the displayed map page is determined
  • the predicted plot area calculation module is configured to calculate the predicted plot area of the crop plot
  • FIG. 7 it shows a schematic diagram of a crop identification device provided in this embodiment.
  • the description is relatively simple, and for the relevant part, please refer to the corresponding description of the method embodiment provided above.
  • the apparatus embodiments described below are merely illustrative.
  • This embodiment provides a crop identification device, including: a call request receiving module 702, configured to receive a call request sent by a caller to identify crop types; a crop plot determination module 704, configured to The carried plot coordinate information and time information determine one or more crop plots mapped by the plot coordinate information; the crop species distribution determination module 706 is configured to, according to the images contained in the one or more crop plots The crop type of the unit, to determine the crop type distribution of the polygonal plot corresponding to the plot coordinate information; the crop type distribution return module 708 is configured to return the crop type distribution to the caller; wherein, the crop field The crop type of the image unit included in the block is output after the crop recognition model performs crop type recognition on the input remote sensing image.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range.
  • Crop type and plot boundary information are used as real labels; establish the mapping relationship between the training samples and the real labels, and use the training samples and the real labels as a training set for model training to obtain the crop identification model .
  • the crop identification device further includes: a crop type identification module, configured to input the remote sensing image data of the target area within the target time range into the crop identification model for crop type identification; a crop type storage module, which is It is configured to store crop types of crop plots in the target area within the target time range output by the crop identification model.
  • a crop type identification module configured to input the remote sensing image data of the target area within the target time range into the crop identification model for crop type identification
  • a crop type storage module which is It is configured to store crop types of crop plots in the target area within the target time range output by the crop identification model.
  • FIG. 8 is a schematic structural diagram of a credit limit processing device provided by one or more embodiments of this specification.
  • a credit limit processing device provided in this embodiment includes: as shown in FIG. 8 , the credit limit processing device may vary greatly due to different configurations or performance, and may include one or more processors 801 and memory 802 , one or more storage applications or data may be stored in the memory 802 .
  • the memory 802 may be short-term storage or persistent storage.
  • the application program stored in memory 802 may include one or more modules (not shown), each module may include a series of computer-executable instructions in the credit line processing device.
  • the processor 801 may be arranged to communicate with the memory 802 to execute a series of computer-executable instructions in the memory 802 on the credit line processing device.
  • the credit line processing device may also include one or more power supplies 803 , one or more wired or wireless network interfaces 804 , one or more input and output interfaces 805 , one or more keyboards 806 and so on.
  • the credit line processing device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and Each module may include a series of computer-executable instructions in the credit line processing apparatus, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for performing the following: obtaining a target user The plot information of the crop plot; using the plot coordinate information and time information contained in the plot information as input parameters, call the crop identification interface to identify the crop species; according to the crop species distribution returned by the crop identification interface, and the target crop species included in the plot information, to determine the confidence level of the plot information; based on the confidence level, the plot information and the crop attributes corresponding to the target crop species, determine the target user credit limit.
  • the crop identification interface is configured with a crop identification model, and the crop identification model uses the following method to identify crop types: the remote sensing image to which the image coordinate information of the time information is mapped by mapping the coordinate information of the land plot to the image coordinate information of the time information.
  • the crop types are identified on the crop plots included in the input remote sensing image at the image unit granularity, and the crop species corresponding to each image unit included in the crop plots included in the input remote sensing image are obtained.
  • determining the confidence level of the plot information according to the crop type distribution returned by the crop identification interface and the target crop type included in the plot information includes: according to the crop type distribution. The number of image units with the same crop type as the target crop type, and the total number of image units in the species distribution, to calculate the confidence level of the plot information; wherein, the confidence level includes the crop type The ratio of the number of image units with the same crop type as the target crop type in the distribution to the total number.
  • the determining the credit limit of the target user based on the confidence, the plot information and the crop attribute corresponding to the target crop type includes: judging whether the confidence is greater than a preset confidence threshold. If yes, determine the credit limit of the target user based on the plot information and the crop attributes corresponding to the target crop type; if not, send a reminder to the target user that the application for the credit limit fails.
  • determining the credit limit of the target user based on the plot information and the crop attribute corresponding to the target crop type includes: according to the target crop type and the land included in the plot information.
  • the credit limit is calculated based on the block area, regional information, the crop value and value fluctuation included in the crop attributes, and their corresponding weights.
  • the computer-executable instructions when executed, further include: in the case of detecting an application processing request by the target user for the target application, displaying the credit authorization bound to the target application based on the application page of the target application.
  • the trigger control of the credit processing channel of the processing channel the credit processing channel is open to the target user recorded in the preset user list; after detecting that the trigger control is triggered, the target user is displayed to the target user.
  • the credit application page of the credit processing channel, the credit application page is configured with an information entry interface and a credit application control; the plot information is entered based on the information entry interface; correspondingly, the acquisition of the target user's crop plots
  • the land parcel information instruction is executed after it is detected that the credit application control is triggered.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range. Crop types and plot boundary information are used as sample labels; establish the mapping relationship between the training samples and the sample labels, and use the training samples and the sample labels as a training set for model training to obtain the crop identification model .
  • the computer-executable instruction when executed, it also includes: inputting the remote sensing image data of the target area within the target time range into the crop identification model for crop type identification; The crop types of the crop plots in the region within the target time range are stored; correspondingly, the crop identification interface is called to determine the crop types with the plot coordinate information and time information contained in the plot information as input parameters.
  • the crop identification interface determines the crop type distribution of the crop plot based on the stored crop species of the crop plot in the target area within the target time range.
  • the computer-executable instruction when executed, it further includes: reading the credit status of the target user; if the credit status of the target user is no credit, granting credit to the target user based on the credit limit. Processing; if the credit status of the target user is credited, adjust the initial credit limit of the target user based on the credit limit; if the credit status of the target user is credit used, based on the target user's participation Based on the contract information recorded in the signed crop management contract, a performance reminder is generated and sent to the target user.
  • the computer-executable instruction when executed, it further includes: acquiring positioning data of the terminal device of the target user; calculating the predicted plot area of the crop plot based on the positioning data; based on the target crop Type, the predicted plot area, the regional information of the crop plot, the crop value and value fluctuations contained in the crop attributes, determine the risk level of the crop plot; generate a risk warning prompt based on the risk level and show it to the target user.
  • the computer-executable instruction when executed, it further includes: calculating the crop plot based on the target crop type, the plot area included in the plot information, and the crop attribute corresponding to the target crop species.
  • the crop value of the block; the guarantee amount of the target user is determined according to the crop value.
  • the computer-executable instruction when executed, it further includes: reading the parcel boundary information contained in the parcel information; the parcel boundary information is based on the annotation input by the target user on the displayed map page. Action determination; calculating the predicted plot area of the crop plot based on the plot boundary information; calculating the crop value of the crop plot based on the target crop type, the predicted plot area and the crop attribute ; According to the resource conversion rate corresponding to the crop value and the target crop species, calculate the resource conversion value corresponding to the crop plot; Based on the resource conversion value and the resource preference and/or resource status of the target user, A resource management strategy for the crop plot is generated.
  • FIG. 9 is a schematic structural diagram of a crop identification device provided by one or more embodiments of the present specification.
  • a crop identification device provided in this embodiment includes: as shown in FIG. 9 , the crop identification device may have relatively large differences due to different configurations or performances, and may include one or more processors 901 and memory 902, and the memory One or more storage applications or data may be stored in 902 .
  • the memory 902 may be short-term storage or persistent storage.
  • the application program stored in memory 902 may include one or more modules (not shown), each module may include a series of computer-executable instructions in the crop identification device.
  • the processor 901 may be arranged to communicate with the memory 902 to execute a series of computer executable instructions in the memory 902 on the crop identification device.
  • the crop identification device may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input and output interfaces 905, one or more keyboards 906, and the like.
  • the crop identification device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each The modules may include a series of computer-executable instructions in the crop identification apparatus, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for performing the following: Carry out a call request for crop type identification; determine one or more crop plots mapped by the plot coordinate information according to the plot coordinate information and time information carried in the call request; according to the one or more crop plots crop types of the image units included in the block, determine the crop type distribution of the polygonal plot corresponding to the coordinate information of the plot; return the crop type distribution to the caller; wherein, the image units included in the crop plot Crop species, which is output after the crop identification model identifies the input remote sensing image.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range.
  • Crop type and plot boundary information are used as real labels; establish the mapping relationship between the training samples and the real labels, and use the training samples and the real labels as a training set for model training to obtain the crop identification model .
  • the computer-executable instruction when executed, it further includes: inputting the remote sensing image data of the target area within the target time range into the crop identification model for crop species identification; storing the target output from the crop identification model. The crop species of the crop plot in the region within the target time frame.
  • An example of a storage medium provided in this specification is as follows: corresponding to the method for processing a credit line described above, based on the same technical concept, one or more embodiments of this specification further provide a storage medium.
  • the storage medium provided in this embodiment is used to store computer-executable instructions, and when the computer-executable instructions are executed, the following processes are implemented: acquiring the plot information of the target user's crop plot; The plot coordinate information and time information are input parameters, and the crop identification interface is called to identify the crop species; according to the crop species distribution returned by the crop identification interface, and the target crop species contained in the plot information, determine the The confidence level of the block information; the credit limit of the target user is determined based on the confidence level, the plot information and the crop attribute corresponding to the target crop type.
  • the crop identification interface is configured with a crop identification model, and the crop identification model uses the following method to identify crop types: the remote sensing image to which the image coordinate information of the time information is mapped by mapping the coordinate information of the land plot to the image coordinate information of the time information.
  • the crop types are identified on the crop plots included in the input remote sensing image at the image unit granularity, and the crop species corresponding to each image unit included in the crop plots included in the input remote sensing image are obtained.
  • determining the confidence level of the plot information according to the crop type distribution returned by the crop identification interface and the target crop type included in the plot information includes: according to the crop type distribution. The number of image units with the same crop type as the target crop type, and the total number of image units in the species distribution, to calculate the confidence level of the plot information; wherein, the confidence level includes the crop type The ratio of the number of image units with the same crop type as the target crop type in the distribution to the total number.
  • the determining the credit limit of the target user based on the confidence, the plot information and the crop attribute corresponding to the target crop type includes: judging whether the confidence is greater than a preset confidence threshold. ;
  • determining the credit limit of the target user based on the plot information and the crop attribute corresponding to the target crop type includes: according to the target crop type and the land included in the plot information.
  • the credit limit is calculated based on the block area, regional information, the crop value and value fluctuation included in the crop attributes, and their corresponding weights.
  • the computer-executable instruction further implements the following process when it is executed: when it is detected that the application processing request of the target user for the target application is detected.
  • the trigger control of the credit processing channel of the credit processing channel bound to the target application is displayed based on the application page of the target application; wherein, the credit processing channel is open to the target user recorded in the preset user list;
  • the credit application page of the credit processing channel under the target application is displayed to the target user; wherein, the credit application page is configured with an information input interface and a credit application control;
  • the plot information is entered based on the information entry interface; correspondingly, the instruction to obtain the plot information of the target user's crop plot is executed after it is detected that the credit application control is triggered.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range. Crop types and plot boundary information are used as sample labels; establish the mapping relationship between the training samples and the sample labels, and use the training samples and the sample labels as a training set for model training to obtain the crop identification model .
  • the computer-executable instruction before the execution of the instruction to obtain the plot information of the crop plot of the target user, the computer-executable instruction also implements the following process when executed: inputting the remote sensing image data of the target area within the target time range into the computer;
  • the crop identification model is used to identify crop types; the crop types of the crop plots in the target area output by the crop identification model are stored within the target time range;
  • the included plot coordinate information and time information are input parameters, and the crop identification interface is called to carry out the execution of the crop type identification instruction.
  • the crop identification interface is based on the stored crop plots in the target area within the target time range. Crop species, determine the crop species distribution of the crop plot.
  • the computer-executable instruction is executed when the instruction is executed.
  • the following process is also implemented: reading the credit status of the target user; if the credit status of the target user is no credit, perform credit processing on the target user based on the credit limit; if the credit status of the target user is If the credit has been granted, the initial credit limit of the target user is adjusted based on the credit limit; if the credit status of the target user is that the credit has been used, based on the contract information recorded in the crop management contract signed by the target user, A fulfillment reminder is generated and sent to the target user.
  • the computer-executable instruction is executed when the instruction is executed.
  • the following processes are also implemented: obtaining the positioning data of the terminal device of the target user; calculating the predicted plot area of the crop plot based on the positioning data; based on the target crop type, the predicted plot area, the The regional information of the crop plot, the crop value and value fluctuations contained in the crop attributes determine the risk level of the crop plot; based on the risk level, a risk warning prompt is generated and displayed to the target user.
  • the following process is also implemented: based on the target crop type, the plot area included in the plot information, and the crop attribute corresponding to the target crop type, calculate the target crop type.
  • the crop value of the crop plot; the guarantee amount of the target user is determined according to the crop value.
  • the following procedures are further implemented: reading the parcel boundary information contained in the parcel information; the parcel boundary information is based on the map page displayed by the target user. Determine the input labeling action; calculate the predicted plot area of the crop plot based on the plot boundary information; calculate the crop plot based on the target crop type, the predicted plot area and the crop attribute According to the crop value and the resource conversion rate corresponding to the target crop species, calculate the resource conversion value corresponding to the crop plot; Based on the resource conversion value and the target user's resource preference and/or Resource status, generating a resource management strategy for the crop plot.
  • An example of a storage medium provided in this specification is as follows: corresponding to the crop identification method described above, based on the same technical concept, one or more embodiments of this specification further provide a storage medium.
  • the storage medium provided in this embodiment is used to store computer-executable instructions, and when the computer-executable instructions are executed, the following processes are implemented: receiving a calling request sent by a caller for identifying crop types; The plot coordinate information and time information are determined, and one or more crop plots mapped by the plot coordinate information are determined; the plot coordinates are determined according to the crop types of the image units contained in the one or more crop plots.
  • the crop type distribution of the polygonal plot corresponding to the information; the crop type distribution is returned to the caller; wherein, the crop type of the image unit included in the crop plot is determined by the crop identification model for the input remote sensing image. output after identification.
  • the crop identification model is trained in the following manner: acquiring remote sensing image data of a specified area within a specified time range as a training sample; acquiring the data of crop plots in the specified area within the specified time range.
  • Crop type and plot boundary information are used as real labels; establish the mapping relationship between the training samples and the real labels, and use the training samples and the real labels as a training set for model training to obtain the crop identification model .
  • the computer-executable instruction before the call request instruction for crop type identification sent by the receiving caller is executed, the computer-executable instruction also implements the following process when executed: inputting the remote sensing image data of the target area within the target time range.
  • the crop identification model performs crop type identification; and the crop types of the crop plots in the target area within the target time range output by the crop identification model are stored.
  • a Programmable Logic Device (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device.
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression Language
  • AHDL Altera Hardware Description Language
  • HDCal JHDL
  • Lava Lava
  • Lola MyHDL
  • PALASM RHDL
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • the controller may be implemented in any suitable manner, for example, the controller may take the form of eg a microprocessor or processor and a computer readable medium storing computer readable program code (eg software or firmware) executable by the (micro)processor , logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers, examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the control logic of the memory.
  • the controller may take the form of eg a microprocessor or processor and a computer readable medium storing computer readable program code (eg software or firmware) executable by the (micro)processor , logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers
  • ASICs application specific integrated circuits
  • controllers include but are not limited to
  • the controller in addition to implementing the controller in the form of pure computer-readable program code, the controller can be implemented as logic gates, switches, application-specific integrated circuits, programmable logic controllers and embedded devices by logically programming the method steps.
  • the same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for realizing various functions can also be regarded as a structure within the hardware component. Or even, the means for implementing various functions can be regarded as both a software module implementing a method and a structure within a hardware component.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.
  • one or more embodiments of this specification may be provided as a method, system or computer program product. Accordingly, one or more embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
  • the apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include forms of non-persistent memory, random access memory (RAM) and/or non-volatile memory in computer readable media, such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology.
  • Information may be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
  • computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.
  • One or more embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer.
  • program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types.
  • One or more embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network.
  • program modules may be located in both local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Artificial Intelligence (AREA)
  • Mining & Mineral Resources (AREA)
  • Technology Law (AREA)
  • Development Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Multimedia (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Seeds, Soups, And Other Foods (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

本说明书实施例提供了授信额度处理方法及装置、作物识别方法及装置，其中，一种授信额度处理方法包括：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。

Description

授信额度处理方法及装置、作物识别方法及装置 技术领域
本文件涉及数据处理技术领域，尤其涉及一种授信额度处理方法及装置、作物识别方法及装置。
背景技术
随着通信技术和大数据在传统行业的推广和应用，在农业、林业、水产种植业等领域，已经出现了基于大数据进行数字化生产管理的服务，但对于传统种植大户而言，其收入来源则主要是依赖于生产种植活动，取决于其作物种植面积以及作物种类，这部分用户在进行资产评估、合同签署、征信分析等活动时受限于数据维度稀薄，往往处于较为不利的。
发明内容
本说明书一个或多个实施例提供了一种授信额度处理方法，包括：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
本说明书一个或多个实施例提供了一种作物识别方法，包括：接收调用方发送的进行作物种类识别的调用请求；根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；向所述调用方返回所述作物种类分布。其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
本说明书一个或多个实施例提供了一种授信额度处理装置，包括：地块信息获取模块，被配置为获取目标用户的作物地块的地块信息；作物种类识别模块，被配置为以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；置信度确定模块，被配置为根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；授信额度确定模块，被配置为基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
本说明书一个或多个实施例提供了一种作物识别装置，包括：调用请求接收模块，被配置为接收调用方发送的进行作物种类识别的调用请求；作物地块确定模块，被配置为根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；作物种类分布确定模块，被配置为根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；作物种类分布返回模块，被配置为向所述调用方返回所述作物种类分布。其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
本说明书一个或多个实施例提供了一种授信额度处理设备，包括处理器以及被配置为存储计算机可执行指令的存储器。所述计算机可执行指令在被执行时使所述处理器：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信 息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
本说明书一个或多个实施例提供了一种作物识别设备，包括处理器以及被配置为存储计算机可执行指令的存储器。所述计算机可执行指令在被执行时使所述处理器：接收调用方发送的进行作物种类识别的调用请求；根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；向所述调用方返回所述作物种类分布。其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
本说明书一个或多个实施例提供了一种存储介质，用于存储计算机可执行指令，所述计算机可执行指令在被执行时实现以下流程：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
本说明书一个或多个实施例提供了一种存储介质，用于存储计算机可执行指令，所述计算机可执行指令在被执行时实现以下流程：接收调用方发送的进行作物种类识别的调用请求；根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；向所述调用方返回所述作物种类分布。其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
附图说明
图1为本说明书一个或多个实施例提供的一种授信额度处理方法处理流程图；
图2为本说明书一个或多个实施例提供的一种应用于助农贷款项目场景的授信额度处理方法处理流程图；
图3为本说明书一个或多个实施例提供的一种应用于农业保障项目场景的授信额度处理方法处理流程图；
图4为本说明书一个或多个实施例提供的一种应用于资源管理项目场景的授信额度处理方法处理流程图；
图5为本说明书一个或多个实施例提供的一种作物识别方法处理流程图；
图6为本说明书一个或多个实施例提供的一种授信额度处理装置的示意图；
图7为本说明书一个或多个实施例提供的一种作物识别装置的示意图；
图8为本说明书一个或多个实施例提供的一种授信额度处理设备的结构示意图；
图9为本说明书一个或多个实施例提供的一种作物识别设备的结构示意图。
具体实施方式
本说明书提供的一种授信额度处理方法实施例：参见图1，本实施例提供的授信额 度处理方法，包括步骤S102至步骤S108。
步骤S102，获取目标用户的作物地块的地块信息。
实际应用中，对于农业领域、林业领域或者水产种植领域的传统种植大户，其收入主要依赖生产种植活动，取决于作物种植面积以及作物种类，同时，由于这部分用户(种植户)进行线上支付的活跃度本身也比较低，因此在进行经营贷款、资产评估、合同签署、征信分析等活动时，很难获得较大的额度。
本实施例提供的授信额度处理方法，针对作物种植大户清单中的目标用户，结合具体的线上应用或者线上服务，为这部分目标用户开通专属的授信处理通道，具体是根据目标用户输入的地块信息中包含的地块坐标信息和时间信息，调用作物识别接口进行作物种类识别，从而根据识别获得的作物种类对目标用户录入的地块信息中的目标作物种类进行核验，以此确定目标用户的置信度，并从目标用户的置信度出发，结合地块信息和作物属性为用户分配授信额度，以使目标用户能够获得更加符合实际信用情况和资产状况的授信额度，并且，提供的授信额度能够为目标用户的基础生产经营提供便利，进而促进目标用户的生产经营效率的提升。
本实施例所述目标用户，是指记录在预设用户清单(比如，种植大户清单)中的用户，具体的，可将拥有或承包大额土地(如大于10亩)并以此为主要经济来源的种植户定义为种植大户列入种植大户清单。该种植大户清单可由第三方机构提供，也可在对种植户进行线下地调后确定该种植大户清单，还可通过种植户申请，基于审核通过的申请对应的种植户生成该种植大户清单，对此不做限定。
所述作物地块，是指用于种植农作物、林业作物、水生作物等地表生长作物的土地、水田或者海水种植区域。所述地块信息，包括作物地块所种植的作物种类、作物地块的地块面积(比如，以亩为度量单位的地块面积数值)、作物地块所处的地块坐标信息(比如，作物地块的经纬度信息)以及时间信息。
需要说明的是，本实施例针对预设用户清单中的目标用户开放授信处理通道，所述授信处理通道与目标应用绑定，并且目标用户的身份信息和地块信息是在目标用户触发授信处理通道之后录入，换言之，预设用户清单中的目标用户，能够通过目标应用绑定的授信处理通道进行信息录入和授信额度处理，比如在目标应用的使用过程中通过录入信息来进行授信额度的提额处理；具体的，本实施例提供的一种可选实施方式中，在检测到目标用户针对目标应用的应用处理请求的情况下，基于目标应用的应用页面展示授信处理通道的触发控件，目标用户通过触发所述触发控件来触发所述授信处理通道。
其中，授信是指银行、支付平台等机构向用户直接提供的资金，或对用户在有关活动中可能产生的赔偿、支付责任做出的保证，授信既可以针对贷款、票据抵押、透支、各项垫款等表内服务，还可以针对票据承兑、开信用证、保函等表外服务。授信额度，是指银行、支付平台等机构为用户核定的短期授信业务的存量管理指标。
例如，支付平台中的贷款应用绑定了授信额度提升通道，种植大户清单中的种植户在该贷款应用申请贷款的过程中，贷款额度需要参考种植户的授信额度来确定，具体而言，种植大户清单中的种植户A在使用贷款应用进行贷款的过程中，贷款应用的应用页面设置有为种植户进行提额处理的提额控件；种植户A可通过点击贷款应用的应用页面设置的提额控件来触发授信额度提升通道，从而通过授信额度提升通道进行授信额度的提额处理。
在对目标用户进行授信并赋予目标用户相应授信额度的基础上，为了扶持或者帮助目标用户的种植生产经营活动，以目标用户的信用为担保或者抵押向目标用户提供相应的资源，以此来保障目标用户的种植生产经营活动能够维持，具体的，本实施例通过向目标用户提供信用担保或者抵押贷款的方式来使目标用户的种植生产经营活动能够正常进行，所述作物经营合约，即是指目标用户基于自身的授信额度与资源提供方签订的合约，并且签订该作物经营合约之后获得的资源被约定用于种植生产经营活动。
具体的，签订所述作物经营合约的目标用户可以从贷款提供机构获得相应资金，除此之外，签订所述作物经营合约的目标用户还可以从设备提供机构获得种植生产经营活动中所需种植生产设备，或者，签订所述作物经营合约的目标用户还可以从原料提供机构获得种植生产经营活动中所需种植原料，对此不做限定。
本实施例所述作物经营合约具体采用如下方式进行签订：获取目标用户通过触发目标应用的合约申请页面配置的申请控件提交的申请请求；判断所述申请请求中包含的申请数额是否小于或者等于所述授信额度；若是，基于所述申请数额和目标用户提交的所述作物地块的地块信息，以目标用户为合约参与方签订所述作物经营合约；若否，表明目标用户申请的额度超出该目标用户的授信额度，向目标用户发送申请的额度超出所述授信额度的提醒即可。
例如，支付平台中的贷款应用向种植户A开放申请助农贷款功能，种植户A可通过该贷款应用申请进行种植生产经营活动的贷款，具体申请过程中，输入相应的贷款申请额度，并通过触发贷款应用的申请页面配置的申请控件来提交贷款请求，在获取到种植户A提交的贷款请求之后，基于贷款请求中携带的种植户A的贷款申请额度，判断种植户A提交的贷款申请额度是否大于种植户A的授信额度(假设为10000元)；如果种植户A提交的贷款申请额度小于10000元，则以种植户A为借款方、资金提供方为借出方签订助农经营贷款合约，同时，在助农经营贷款合约中记录种植户A的作为地块的作物种类、作物地块所处的地块坐标信息以及时间信息等地块信息。
如上所述，目标用户在种植生产经营活动中获得资源扶持的前提，是以所述目标用户的信用为担保或者抵押，并在所述目标用户的授信额度中扣除或者冻结相应的额度部分；本实施例所述合约信息中包含所述作物经营合约的合约额度，所述目标用户在基于所述授信额度签订所述作物经营合约之后，签订所述作物经营合约所使用的所述授信额度中所述合约额度对应的已用子额度被冻结；相应的，所述已用子额度在所述目标用户履行所述作物经营合约中记录的履约条款之后被恢复。
例如，种植户A的授信额度为10000元，如果种植户A申请6000元以供种植使用，则在签订作物经营合约之后10000元授信额度中的6000元被冻结；相应的，如果种植户A偿还了6000元中的部分或者全部，则相应的会在被冻结的授信额度中解冻偿还的部分。
进一步，在检测到授信处理通道的触发控件被触发之后，向目标用户展示目标应用下授信处理通道的授信申请页面；其中，所述授信申请页面配置有信息录入接口和授信申请控件；所述地块信息基于所述信息录入接口进行录入，目标用户输入的地块信息在授信申请控件被触发后进行获取，也即是本步骤获取目标用户的作物地块的地块信息，是在授信申请控件被触发的基础上执行。
步骤S104，以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别。
具体实施时，在基于目标用户录入的作物地块的地块信息进行作物种类识别过程中，通过调用作物识别接口来进行作物种类的识别，本实施例提供的一种可选实施方式中，基于作物识别接口配置的作物识别模型来进行作物种类识别，具体的，所述作物识别模型采用如下方式进行作物种类识别：将所述地地块坐标信息在所述时间信息映射的影像坐标信息所属的遥感影像作为输入，在影像单元粒度对输入的遥感影像包含的作物地块进行作物种类识别，获得输入的遥感影像包含的作物地块包含的各影像单元对应的作物种类。
具体的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为样本标签；建立所述训练样本与所述样本标签的映射关系，并将所述训练样本和所述样本标签作为训练集进行模型训练，获得所述 作物识别模型。
为了提升作物种类识别的效率，使作物识别接口在被调用时能够快速响应，对作物地块进行作物种类识别返回相应的识别结果，可选的，在获取目标用户的作物地块的地块信息之前，将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别，并将所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类进行存储；相应的，在以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别步骤执行过程中，所述作物识别接口基于存储的所述目标地区在所述目标时间范围内的作物地块的作物种类，确定所述作物地块的作物种类分布并，以此来提升作物识别接口对作物种类识别的响应效率。
例如，在进行作物识别模型的训练过程中，首先，从开源渠道下载或卫星公司采购指定地区及时间的卫星遥感图像，作为训练样本；卫星遥感图像的空间分辨率为10m，时间分辨率为5天，光谱通道数为红绿蓝及近红外四通道；其次，从第三方机构处采购该指定地区的历史作物分布，或者采用人工低调的方式标注该指定地区的历史作物信息，作物训练模型的样本标签，该样本标签的标注数据包括作物种类及对应作物地块边界的经纬度多边形信息；然后，将作物分布坐标与卫星遥感图像进行转换及映射，作为作物识别模型的训练集输入；作物识别模型具体采用深度学习中的deeplabv3+语义分割网络，将作物地块的作物种类识别抽象为语义分割问题；最后，在训练完成后获得作物识别模型的基础上，输入新地区在时间的卫星遥感图像传入新时间或新地区的卫星底图后，获得全量预测结果供调用方调用。
所述作物识别模型除采用deeplabv3+语义分割网络之外，还可以采用HRNet OCR、FCN系列、Unet及其各种变体等其他深度学习语义分割算法。或者，还可以采用其他遥感领域的传统作物识别方法来进行作物种类识别，比如利用光谱匹配方法对种植户的作物地块进行作物种类识别。
步骤S106，根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度。
如上所述，在对目标用户的作物地块进行作物种类识别的过程中，将所述地地块坐标信息在所述时间信息映射的影像坐标信息所属的遥感影像作为输入，在影像单元粒度对输入的遥感影像包含的作物地块进行作物种类识别，从而获得输入的遥感影像包含的作物地块包含的各影像单元对应的作物种类；相应的，本实施例所述作物种类分布，由目标用户的作物地块包含的各影像单元对应的作物种类组成。
例如，种植户A的作物地块的地块信息中包含的经纬度坐标信息和时间信息被输入作物识别接口进行作物种类识别的过程中，由作物识别接口配置的作物识别模型将该作物地块分割为100个遥感影像单元，然后分别识别出这100个遥感影像单元各自对应的作物种类，该作物地块包含的100个遥感影像单元对应的作物种类组成的集合，即为该作物地块的作物种类分布。
具体实施时，根据所述作物识别接口返回的作物种类分布和所述地块信息中包含的目标作物种类，确定所述地块信息的置信度，具体是根据所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目，以及所述物种类分布中影像单元的总数目，计算所述地块信息的置信度；其中，所述置信度，包括所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目与所述总数目的比值。
沿用上例，作物识别接口返回种植户A的作物地块包含的100个遥感影像单元(遥感影像中的像素点)各自对应的作物种类组成的作物种类分布，具体为其中80个遥感影像单元对应的作物种类被识别为小麦，20个遥感影像单元对应的作物种类被识别为水稻；种植户A录入的作物地块的地块信息中包含的作物种类为小麦，即：种植户A输入的作物地块包含的100个遥感影像单元对应的作物种类均为小麦，而作物识别接口返回的作物种类分布当中，对应的作物种类为小麦的遥感影像单元的数目为80个，据此， 计算种植户A输入的该作物地块的作物种类的置信度为80/100＝80％。
步骤S108，基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
为了促进信用体系的提升，本实施例提供的一种可选实施方式中，在确定目标用户的授信额度的过程中，从目标用户录入的地块信息的置信度出发，将置信度作为向目标用户分配授信额度的约束条件，或者将置信度作为评估目标用户的授信额度的一个参数，以此通过置信度的约束来促进信用体系的完善，具体的，通过判断所述置信度是否大于预设置信度阈值，来判断目标用户输入的作物地块的地块信息是否可信；若所述置信度大于预设置信度阈值，表明目标用户输入的地块信息可信，基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度；其中，根据所述目标作物种类、所述地块信息中包含的地块面积、地域信息、所述作物属性中包含的作物价值和价值波动，以及各自对应的权重，计算所述授信额度；若所述置信度小于或者等于预设置信度阈值，表明目标用户输入的地块信息不可信，向目标用户发出授信额度申请失败的提醒。
仍以种植户A为例，种植户A输入的该作物地块的作物种类的置信度为80％，大于预先设置的置信度阈值60％，表明种植户A输入的地块信息可信，则基于种植户A录入的地块信息中包含的该作物地块的地块面积，该作物地块所属的地域信息，该作物地块的作物种类对应的亩产单价，以及该作物地块的作物种类在该地域信息对应的价值波动，计算向种植户A分配的专属授信额度。
实际应用中，不同的目标用户可能出于不同的需求来申请授信额度，或者在申请授信额度时处于不同的授信状态，比如有的种植户在申请授信额度时尚未开通授信服务，或者，有的种植户在申请授信额度时已经开通授信服务并且已经拥有一定的授信额度，再或者，有的种植户在申请授信额度时已经通过贷款或者抵押使用其授信额度，本实施例提供的一种可选实施方式中，在确定目标用户的授信额度之后，为了提升目标用户的用户体验，从目标用户的授信状态出发，对不同授信状态的目标用户进行针对性处理，具体实现如下：读取所述目标用户的授信状态；若所述目标用户的授信状态为未授信，基于所述授信额度对所述目标用户进行授信处理；若所述目标用户的授信状态为已授信，基于所述授信额度对所述目标用户的初始授信额度进行调整；若所述目标用户的授信状态为授信已用，基于所述目标用户参与签订的作物经营合约中记录的合约信息，生成履约提醒并向所述目标用户发送。
与之相类似，在确定目标用户的授信额度之后，还可以结合目标用户的作物地块的作物种类，对作物地块进行风险预测并进行提醒，以此降低目标用户的风险损失，具体实现如下：获取所述目标用户的终端设备的定位数据；基于所述定位数据计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积、所述作物地块的地域信息、所述作物属性中包含的作物价值和价值波动，确定所述作物地块的风险等级；基于所述风险等级生成风险预警提示并向所述目标用户展示。
需要说明的是，在基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度的过程中，根据不同应用场景的实现特性，还可以针对不同场景进行相应处理，比如，在农业保障项目中，基于所述目标作物种类、所述地块信息中包含的地块面积和所述目标作物种类对应的作物属性，计算所述作物地块的作物价值，根据所述作物价值确定所述目标用户的保障额度，以此针对目标用户的作物地块提供保障。
再比如，在资源管理项目中，读取所述地块信息中包含的地块边界信息；所述地块边界信息基于所述目标用户在展示的地图页面输入的标注动作确定；基于所述地块边界信息计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积和所述作物属性，计算所述作物地块的作物价值；根据所述作物价值和所述目标作物种 类对应的资源转化率，计算所述作物地块对应的资源转化数值；基于所述资源转化数值和所述目标用户的资源偏好和/或资源状态，生成所述作物地块的资源管理策略。
此外，需要说明的是，上述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度这一实现过程，根据不同应用场景的应用特性，还可以被替换为不同场景中的相应处理动作，下述提供2种实现场景的具体实现方式：
实现方式一：基于所述目标作物种类、所述地块信息中包含的地块面积和所述目标作物种类对应的作物属性，计算所述作物地块的作物价值；根据所述作物价值确定所述目标用户的保障额度。
实现方式二：读取所述地块信息中包含的地块边界信息；所述地块边界信息基于所述目标用户在展示的地图页面输入的标注动作确定；基于所述地块边界信息计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积和所述作物属性，计算所述作物地块的作物价值；根据所述作物价值和所述目标作物种类对应的资源转化率，计算所述作物地块对应的资源转化数值；基于所述资源转化数值和所述目标用户的资源偏好和/或资源状态，生成所述作物地块的资源管理策略。
下述以本实施例提供的一种授信额度处理方法在助农贷款项目场景的应用为例，对本实施例提供的授信额度处理方法进行进一步说明，参见图2，应用于助农贷款项目场景的授信额度处理方法，具体包括步骤S202至步骤S220。
步骤S202，获取种植户的作物地块的地块信息。
具体的，在检测到种植户针对助农贷款项目的申请请求的情况下，基于助农贷款项目的项目页面展示授信处理通道的触发控件；在检测到触发控件被触发之后，向种植户展示助农贷款项目下授信处理通道的授信申请页面；其中，授信申请页面配置有信息录入接口和授信申请控件；种植户可通过信息录入接口录入作物地块的地块信息，并且可通过授信申请控件来申请授信额度。
其中，地块信息包括作物地块所种植的作物种类、作物地块的地块面积(比如，以亩为度量单位的地块面积数值)、作物地块所处的地块坐标信息(比如，作物地块的经纬度信息)以及时间信息。
步骤S204，以地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别。
步骤S206，根据作物识别接口返回的作物种类分布，以及地块信息中包含的目标作物种类，确定地块信息的置信度。
步骤S208，判断置信度是否大于预设置信度阈值；若是，表明种植户输入的地块信息可信，则执行步骤S212，基于地块信息以及目标作物种类对应的作物属性，确定种植户的授信额度；若否，表明种植户输入的地块信息不可信，执行步骤S210，向种植户发出授信额度申请失败的提醒。
步骤S210，向种植户发出授信额度申请失败的提醒。
步骤S212，基于地块信息以及地块信息包含的作物种类对应的作物属性，确定种植户的授信额度。
步骤S214，读取种植户的授信状态。
步骤S216，若种植户的授信状态为未授信，基于授信额度对种植户进行授信处理。
步骤S218，若种植户的授信状态为已授信，基于授信额度对种植户的初始授信额度进行调整。
步骤S220，若种植户的授信状态为授信已用，基于种植户参与签订的作物经营合约中记录的合约信息，生成履约提醒并向种植户发送。
下述以本说明书提供的一种授信额度处理方法在农业保障项目场景的应用为例，对本说明书提供的授信额度处理方法进行进一步说明，参见图3，应用于农业保障项目 场景的授信额度处理方法，具体包括步骤S302至步骤S314。
步骤S302，获取种植户的作物地块的地块信息。
具体的，在检测到种植户申请加入农业保障项目(比如，农业保险项目)的申请请求的情况下，基于农业保障项目的项目页面展示授信保障处理通道的触发控件；在检测到触发控件被触发之后，向种植户展示农业保障项目下授信保障处理通道的授信保障申请页面；其中，授信保障申请页面配置有信息录入接口和授信保障申请控件；种植户可通过信息录入接口录入作物地块的地块信息，并且可通过授信保障申请控件为作物地块申请授信保障额度，该授信保障额度是指从种植户的授信出发为种植户的作物地块分配的保障额度。
其中，地块信息包括作物地块所种植的作物种类、作物地块的地块面积(比如，以亩为度量单位的地块面积数值)、作物地块所处的地块坐标信息(比如，作物地块的经纬度信息)以及时间信息。
步骤S304，以地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别。
步骤S306，根据作物识别接口返回的作物种类分布，以及地块信息中包含的目标作物种类，确定地块信息的置信度。
步骤S308，判断置信度是否大于预设置信度阈值；若是，表明种植户输入的地块信息可信，则执行步骤S312至步骤S314；若否，表明种植户输入的地块信息不可信，执行步骤S310，向种植户发出授信保障额度申请失败的提醒。
步骤S310，向种植户发出授信保障额度申请失败的提醒。
步骤S312，基于目标作物种类、地块面积和目标作物种类对应的作物属性，计算种植户的作物地块的作物价值。
步骤S314，根据作物价值确定种植户的作物地块的授信保障额度。
下述以本说明书提供的一种授信额度处理方法在资源管理项目场景的应用为例，对本说明书提供的授信额度处理方法进行进一步说明，参见图4，应用于资源管理项目场景的授信额度处理方法，具体包括步骤S402至步骤S418。
步骤S402，获取种植户的作物地块的地块信息。
具体的，在检测到种植户针对助农贷款项目的申请请求的情况下，基于助农贷款项目的项目页面展示授信处理通道的触发控件；在检测到触发控件被触发之后，向种植户展示助农贷款项目下授信处理通道的授信申请页面；其中，授信申请页面配置有信息录入接口和授信申请控件；种植户可通过信息录入接口录入作物地块的地块信息，并且可通过授信申请控件来申请授信额度。
其中，地块信息包括作物地块所种植的作物种类、作物地块所处的地块坐标信息(比如，作物地块的经纬度信息)以及时间信息。
步骤S404，以地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别。
步骤S406，根据作物识别接口返回的作物种类分布，以及地块信息中包含的目标作物种类，确定地块信息的置信度。
步骤S408，判断置信度是否大于预设置信度阈值；若是，表明种植户输入的地块信息可信，则执行步骤S410至步骤S418；若否，表明种植户输入的地块信息不可信，不作处理即可。
步骤S410，读取地块信息中包含的地块边界信息。
其中，地块边界信息基于种植户在展示的地图页面输入的标注动作确定。
步骤S412，基于地块边界信息计算作物地块的预测地块面积。
步骤S414，基于目标作物种类、预测地块面积和作物属性，计算作物地块的作物价值。
步骤S416，根据作物价值和目标作物种类对应的资源转化率，计算作物地块对应的资源转化数值。
步骤S418，基于资源转化数值和种植户的资源偏好和/或资源状态，生成作物地块的资源管理策略。
本说明书提供的一种作物识别方法实施例如下：在上述的实施例中，提供了一种授信额度处理方法，与之相配合，还提供了一种作物识别方法，下面结合附图进行说明。
由于本方法实施例与上述提供的方法实施例在执行的过程中相配合，所以描述得比较简单，相关的部分请参见上述提供的方法实施例的对应说明即可。下述描述的方法实施例仅仅是示意性的。
参见图5，本实施例提供的作物识别方法，包括步骤S402至步骤S408。
步骤S502，接收调用方发送的进行作物种类识别的调用请求。
步骤S504，根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块。
步骤S506，根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布。
其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
步骤S508，向所述调用方返回所述作物种类分布。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为真实标签；建立所述训练样本与所述真实标签的映射关系，并将所述训练样本和所述真实标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，所述接收调用方发送的进行作物种类识别的调用请求之前包括；将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；存储所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类。
例如，在进行作物识别模型的训练过程中，首先，从开源渠道下载或卫星公司采购指定地区及时间的卫星遥感图像，作为训练样本；卫星遥感图像的空间分辨率为10m，时间分辨率为5天，光谱通道数为红绿蓝及近红外四通道；其次，从第三方机构处采购该指定地区的历史作物分布，或者采用人工低调的方式标注该指定地区的历史作物信息，作物训练模型的样本标签，该样本标签的标注数据包括作物种类及对应作物地块边界的经纬度多边形信息；然后，将作物分布坐标与卫星遥感图像进行转换及映射，作为作物识别模型的训练集输入；作物识别模型具体采用深度学习中的deeplabv3+语义分割网络，将作物地块的作物种类识别抽象为语义分割问题；最后，在训练完成后获得作物识别模型的基础上，输入新地区在时间的卫星遥感图像传入新时间或新地区的卫星底图后，获得全量预测结果供调用方调用。
所述作物识别模型除采用deeplabv3+语义分割网络之外，还可以采用HRNet OCR、FCN系列、Unet及其各种变体等其他深度学习语义分割算法。或者，还可以采用其他遥感领域的传统作物识别方法来进行作物种类识别，比如利用光谱匹配方法对种植户的作物地块进行作物种类识别。
本说明书提供的一种授信额度处理装置实施例如下：在上述的实施例中，提供了一种授信额度处理方法，与之相对应的，还提供了一种授信额度处理装置，下面结合附图进行说明。
参照图6，其示出了本实施例提供的一种授信额度处理装置的示意图。
由于装置实施例对应于方法实施例，所以描述得比较简单，相关的部分请参见上述提供的方法实施例的对应说明即可。下述描述的装置实施例仅仅是示意性的。
本实施例提供一种授信额度处理装置，包括：地块信息获取模块602，被配置为获取目标用户的作物地块的地块信息；作物种类识别模块604，被配置为以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；置信度确定模块606，被配置为根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；授信额度确定模块608，被配置为基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
可选的，所述作物识别接口配置有作物识别模型，所述作物识别模型采用如下方式进行作物种类识别：将所述地地块坐标信息在所述时间信息映射的影像坐标信息所属的遥感影像作为输入，在影像单元粒度对输入的遥感影像包含的作物地块进行作物种类识别，获得输入的遥感影像包含的作物地块包含的各影像单元对应的作物种类。
可选的，所述置信度确定模块606，具体被配置为根据所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目，以及所述物种类分布中影像单元的总数目，计算所述地块信息的置信度；其中，所述置信度，包括所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目与所述总数目的比值。
可选的，所述授信额度确定模块608，包括：置信度判断子模块，被配置为判断所述置信度是否大于预设置信度阈值；若是，运行授信额度确定子模块；所述授信额度确定子模块，被配置为基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度；若否，运行授信额度申请失败提醒子模块；所述授信额度申请失败提醒子模块，被配置为向所述目标用户发出授信额度申请失败的提醒。
可选的，所述授信额度确定子模块，具体被配置为根据所述目标作物种类、所述地块信息中包含的地块面积、地域信息、所述作物属性中包含的作物价值和价值波动，以及各自对应的权重，计算所述授信额度。
可选的，所述授信额度处理装置，还包括：触发控件展示模块，被配置为在检测到所述目标用户针对目标应用的应用处理请求的情况下，基于所述目标应用的应用页面展示所述目标应用绑定的授信处理通道的授信处理通道的触发控件；其中，所述授信处理通道向预设用户清单中记录的目标用户开放；授信申请页面展示模块，被配置为在检测到所述触发控件被触发之后，向所述目标用户展示所述目标应用下所述授信处理通道的授信申请页面；其中，所述授信申请页面配置有信息录入接口和授信申请控件；所述地块信息基于所述信息录入接口进行录入；相应的，所述地块信息获取模块602，在所述检测到所述授信申请控件被触发之后运行。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为样本标签；建立所述训练样本与所述样本标签的映射关系，并将所述训练样本和所述样本标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，所述授信额度处理装置，还包括：作物种类识别模块，被配置为将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；作物种类存储模块，被配置为将所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类进行存储；相应的，所述作物种类识别模块604运行过程中，所述作物识别接口基于存储的所述目标地区在所述目标时间范围内的作物地块的作物种类，确定所述作物地块的作物种类分布。
可选的，所述授信额度处理装置还包括：授信状态读取模块，被配置为读取所述目标用户的授信状态；授信处理模块，被配置为若所述目标用户的授信状态为未授信，基于所述授信额度对所述目标用户进行授信处理；初始授信额度调整模块，被配置为若所述目标用户的授信状态为已授信，基于所述授信额度对所述目标用户的初始授信额度 进行调整；履约提醒模块，被配置为若所述目标用户的授信状态为授信已用，基于所述目标用户参与签订的作物经营合约中记录的合约信息，生成履约提醒并向所述目标用户发送。
可选的，所述授信额度处理装置，还包括：定位数据获取模块，被配置为获取所述目标用户的终端设备的定位数据；预测地块面积计算模块，被配置为基于所述定位数据计算所述作物地块的预测地块面积；风险等级确定模块，被配置为基于所述目标作物种类、所述预测地块面积、所述作物地块的地域信息、所述作物属性中包含的作物价值和价值波动，确定所述作物地块的风险等级；风险预警提示展示模块，被配置为基于所述风险等级生成风险预警提示并向所述目标用户展示。
可选的，所述授信额度处理装置，还包括：作物价值计算模块，被配置为基于所述目标作物种类、所述地块信息中包含的地块面积和所述目标作物种类对应的作物属性，计算所述作物地块的作物价值；保障额度确定模块，被配置为根据所述作物价值确定所述目标用户的保障额度。
可选的，所述授信额度处理装置，还包括：地块边界信息读取模块，被配置为读取所述地块信息中包含的地块边界信息；所述地块边界信息基于所述目标用户在展示的地图页面输入的标注动作确定；预测地块面积计算模块，被配置为基于所述地块边界信息计算所述作物地块的预测地块面积；作物价值计算模块，被配置为基于所述目标作物种类、所述预测地块面积和所述作物属性，计算所述作物地块的作物价值；资源转化数值计算模块，被配置为根据所述作物价值和所述目标作物种类对应的资源转化率，计算所述作物地块对应的资源转化数值；资源管理策略生成模块，被配置为基于所述资源转化数值和所述目标用户的资源偏好和/或资源状态，生成所述作物地块的资源管理策略。
本说明书提供的一种作物识别装置实施例如下：在上述的实施例中，提供了一种作物识别方法，与之相对应的，还提供了一种作物识别装置，下面结合附图进行说明。
参照图7，其示出了本实施例提供的一种作物识别装置的示意图。
由于装置实施例对应于方法实施例，所以描述得比较简单，相关的部分请参见上述提供的方法实施例的对应说明即可。下述描述的装置实施例仅仅是示意性的。
本实施例提供一种作物识别装置，包括：调用请求接收模块702，被配置为接收调用方发送的进行作物种类识别的调用请求；作物地块确定模块704，被配置为根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；作物种类分布确定模块706，被配置为根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；作物种类分布返回模块708，被配置为向所述调用方返回所述作物种类分布；其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为真实标签；建立所述训练样本与所述真实标签的映射关系，并将所述训练样本和所述真实标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，所述作物识别装置，还包括；作物种类识别模块，被配置为将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；作物种类存储模块，被配置为存储所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类。
本说明书提供的一种授信额度处理设备实施例如下：对应上述描述的一种授信额度处理方法，基于相同的技术构思，本说明书一个或多个实施例还提供一种授信额度处理设备，该授信额度处理设备用于执行上述提供的授信额度处理方法，图8为本说明书 一个或多个实施例提供的一种授信额度处理设备的结构示意图。
本实施例提供的一种授信额度处理设备，包括：如图8所示，授信额度处理设备可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上的处理器801和存储器802，存储器802中可以存储有一个或一个以上存储应用程序或数据。其中，存储器802可以是短暂存储或持久存储。存储在存储器802的应用程序可以包括一个或一个以上模块(图示未示出)，每个模块可以包括授信额度处理设备中的一系列计算机可执行指令。更进一步地，处理器801可以设置为与存储器802通信，在授信额度处理设备上执行存储器802中的一系列计算机可执行指令。授信额度处理设备还可以包括一个或一个以上电源803，一个或一个以上有线或无线网络接口804，一个或一个以上输入输出接口805，一个或一个以上键盘806等。
在一个具体的实施例中，授信额度处理设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对授信额度处理设备中的一系列计算机可执行指令，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
可选的，所述作物识别接口配置有作物识别模型，所述作物识别模型采用如下方式进行作物种类识别：将所述地地块坐标信息在所述时间信息映射的影像坐标信息所属的遥感影像作为输入，在影像单元粒度对输入的遥感影像包含的作物地块进行作物种类识别，获得输入的遥感影像包含的作物地块包含的各影像单元对应的作物种类。
可选的，所述根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度，包括：根据所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目，以及所述物种类分布中影像单元的总数目，计算所述地块信息的置信度；其中，所述置信度，包括所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目与所述总数目的比值。
可选的，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性确定所述目标用户的授信额度，包括：判断所述置信度是否大于预设置信度阈值；若是，基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度；若否，向所述目标用户发出授信额度申请失败的提醒。
可选的，所述基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度，包括：根据所述目标作物种类、所述地块信息中包含的地块面积、地域信息、所述作物属性中包含的作物价值和价值波动，以及各自对应的权重，计算所述授信额度。
可选的，计算机可执行指令在被执行时还包括：在检测到所述目标用户针对目标应用的应用处理请求的情况下，基于所述目标应用的应用页面展示所述目标应用绑定的授信处理通道的授信处理通道的触发控件，所述授信处理通道向预设用户清单中记录的目标用户开放；在检测到所述触发控件被触发之后，向所述目标用户展示所述目标应用下所述授信处理通道的授信申请页面，所述授信申请页面配置有信息录入接口和授信申请控件；所述地块信息基于所述信息录入接口进行录入；相应的，所述获取目标用户的作物地块的地块信息指令，在所述检测到所述授信申请控件被触发之后执行。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为样本标签；建立所述训练样本与所述样本标 签的映射关系，并将所述训练样本和所述样本标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，计算机可执行指令在被执行时，还包括：将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；将所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类进行存储；相应的，所述以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别指令执行过程中，所述作物识别接口基于存储的所述目标地区在所述目标时间范围内的作物地块的作物种类，确定所述作物地块的作物种类分布。
可选的，计算机可执行指令在被执行时，还包括：读取所述目标用户的授信状态；若所述目标用户的授信状态为未授信，基于所述授信额度对所述目标用户进行授信处理；若所述目标用户的授信状态为已授信，基于所述授信额度对所述目标用户的初始授信额度进行调整；若所述目标用户的授信状态为授信已用，基于所述目标用户参与签订的作物经营合约中记录的合约信息，生成履约提醒并向所述目标用户发送。
可选的，计算机可执行指令在被执行时，还包括：获取所述目标用户的终端设备的定位数据；基于所述定位数据计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积、所述作物地块的地域信息、所述作物属性中包含的作物价值和价值波动，确定所述作物地块的风险等级；基于所述风险等级生成风险预警提示并向所述目标用户展示。
可选的，计算机可执行指令在被执行时，还包括：基于所述目标作物种类、所述地块信息中包含的地块面积和所述目标作物种类对应的作物属性，计算所述作物地块的作物价值；根据所述作物价值确定所述目标用户的保障额度。
可选的，计算机可执行指令在被执行时，还包括：读取所述地块信息中包含的地块边界信息；所述地块边界信息基于所述目标用户在展示的地图页面输入的标注动作确定；基于所述地块边界信息计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积和所述作物属性，计算所述作物地块的作物价值；根据所述作物价值和所述目标作物种类对应的资源转化率，计算所述作物地块对应的资源转化数值；基于所述资源转化数值和所述目标用户的资源偏好和/或资源状态，生成所述作物地块的资源管理策略。
本说明书提供的一种作物识别设备实施例如下：对应上述描述的一种作物识别方法，基于相同的技术构思，本说明书一个或多个实施例还提供一种作物识别设备，该作物识别设备用于执行上述提供的作物识别方法，图9为本说明书一个或多个实施例提供的一种作物识别设备的结构示意图。
本实施例提供的一种作物识别设备，包括：如图9所示，作物识别设备可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上的处理器901和存储器902，存储器902中可以存储有一个或一个以上存储应用程序或数据。其中，存储器902可以是短暂存储或持久存储。存储在存储器902的应用程序可以包括一个或一个以上模块(图示未示出)，每个模块可以包括作物识别设备中的一系列计算机可执行指令。更进一步地，处理器901可以设置为与存储器902通信，在作物识别设备上执行存储器902中的一系列计算机可执行指令。作物识别设备还可以包括一个或一个以上电源903，一个或一个以上有线或无线网络接口904，一个或一个以上输入输出接口905，一个或一个以上键盘906等。
在一个具体的实施例中，作物识别设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对作物识别设备中的一系列计算机可执行指令，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令：接收调用方发送的进行作物种类识别的调用请求；根据所述调用 请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；向所述调用方返回所述作物种类分布；其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为真实标签；建立所述训练样本与所述真实标签的映射关系，并将所述训练样本和所述真实标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，计算机可执行指令在被执行时，还包括：将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；存储所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类。
本说明书提供的一种存储介质实施例如下：对应上述描述的一种授信额度处理方法，基于相同的技术构思，本说明书一个或多个实施例还提供一种存储介质。
本实施例提供的存储介质，用于存储计算机可执行指令，所述计算机可执行指令在被执行时实现以下流程：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
可选的，所述作物识别接口配置有作物识别模型，所述作物识别模型采用如下方式进行作物种类识别：将所述地地块坐标信息在所述时间信息映射的影像坐标信息所属的遥感影像作为输入，在影像单元粒度对输入的遥感影像包含的作物地块进行作物种类识别，获得输入的遥感影像包含的作物地块包含的各影像单元对应的作物种类。
可选的，所述根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度，包括：根据所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目，以及所述物种类分布中影像单元的总数目，计算所述地块信息的置信度；其中，所述置信度，包括所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目与所述总数目的比值。
可选的，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性确定所述目标用户的授信额度，包括：判断所述置信度是否大于预设置信度阈值；
若是，基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度；若否，向所述目标用户发出授信额度申请失败的提醒。
可选的，所述基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度，包括：根据所述目标作物种类、所述地块信息中包含的地块面积、地域信息、所述作物属性中包含的作物价值和价值波动，以及各自对应的权重，计算所述授信额度。
可选的，所述获取目标用户的作物地块的地块信息指令执行之前，所述计算机可执行指令在被执行时还实现以下流程：在检测到所述目标用户针对目标应用的应用处理请求的情况下，基于所述目标应用的应用页面展示所述目标应用绑定的授信处理通道的授信处理通道的触发控件；其中，所述授信处理通道向预设用户清单中记录的目标用户开放；在检测到所述触发控件被触发之后，向所述目标用户展示所述目标应用下所述授信处理通道的授信申请页面；其中，所述授信申请页面配置有信息录入接口和授信申请控件；所述地块信息基于所述信息录入接口进行录入；相应的，所述获取目标用户的作物地块的地块信息指令，在所述检测到所述授信申请控件被触发之后执行。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为样本标签；建立所述训练样本与所述样本标签的映射关系，并将所述训练样本和所述样本标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，所述获取目标用户的作物地块的地块信息指令执行之前，所述计算机可执行指令在被执行时还实现以下流程：将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；将所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类进行存储；相应的，所述以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别指令执行过程中，所述作物识别接口基于存储的所述目标地区在所述目标时间范围内的作物地块的作物种类，确定所述作物地块的作物种类分布。
可选的，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度指令执行之后，所述计算机可执行指令在被执行时还实现以下流程：读取所述目标用户的授信状态；若所述目标用户的授信状态为未授信，基于所述授信额度对所述目标用户进行授信处理；若所述目标用户的授信状态为已授信，基于所述授信额度对所述目标用户的初始授信额度进行调整；若所述目标用户的授信状态为授信已用，基于所述目标用户参与签订的作物经营合约中记录的合约信息，生成履约提醒并向所述目标用户发送。
可选的，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度指令执行之后，所述计算机可执行指令在被执行时还实现以下流程：获取所述目标用户的终端设备的定位数据；基于所述定位数据计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积、所述作物地块的地域信息、所述作物属性中包含的作物价值和价值波动，确定所述作物地块的风险等级；基于所述风险等级生成风险预警提示并向所述目标用户展示。
可选的，所述计算机可执行指令在被执行时还实现以下流程：基于所述目标作物种类、所述地块信息中包含的地块面积和所述目标作物种类对应的作物属性，计算所述作物地块的作物价值；根据所述作物价值确定所述目标用户的保障额度。
可选的，所述计算机可执行指令在被执行时还实现以下流程：读取所述地块信息中包含的地块边界信息；所述地块边界信息基于所述目标用户在展示的地图页面输入的标注动作确定；基于所述地块边界信息计算所述作物地块的预测地块面积；基于所述目标作物种类、所述预测地块面积和所述作物属性，计算所述作物地块的作物价值；根据所述作物价值和所述目标作物种类对应的资源转化率，计算所述作物地块对应的资源转化数值；基于所述资源转化数值和所述目标用户的资源偏好和/或资源状态，生成所述作物地块的资源管理策略。
需要说明的是，本说明书中关于存储介质的实施例与本说明书中关于授信额度处理方法的实施例基于同一发明构思，因此该实施例的具体实施可以参见前述对应方法的实施，重复之处不再赘述。
本说明书提供的一种存储介质实施例如下：对应上述描述的一种作物识别方法，基于相同的技术构思，本说明书一个或多个实施例还提供一种存储介质。
本实施例提供的存储介质，用于存储计算机可执行指令，所述计算机可执行指令在被执行时实现以下流程：接收调用方发送的进行作物种类识别的调用请求；根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；向所述调用方返回所述作物种类分布；其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进 行作物种类识别后输出。
可选的，所述作物识别模型，采用如下方式进行训练：获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为真实标签；建立所述训练样本与所述真实标签的映射关系，并将所述训练样本和所述真实标签作为训练集进行模型训练，获得所述作物识别模型。
可选的，所述接收调用方发送的进行作物种类识别的调用请求指令执行之前，所述计算机可执行指令在被执行时还实现以下流程：将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；存储所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类。
需要说明的是，本说明书中关于存储介质的实施例与本说明书中关于作物识别方法的实施例基于同一发明构思，因此该实施例的具体实施可以参见前述对应方法的实施，重复之处不再赘述。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
在20世纪30年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device，PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的 用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本说明书实施例时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本说明书一个或多个实施例可提供为方法、系统或计算机程序产品。因此，本说明书一个或多个实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本说明书可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书是参照根据本说明书实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有 的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本说明书一个或多个实施例可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本说明书的一个或多个实施例，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本文件的实施例而已，并不用于限制本文件。对于本领域技术人员来说，本文件可以有各种更改和变化。凡在本文件的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本文件的权利要求范围之内。

Claims (21)

  1. 一种授信额度处理方法，包括：
    获取目标用户的作物地块的地块信息；
    以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；
    根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；
    基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
  2. 根据权利要求1所述的授信额度处理方法，所述作物识别接口配置有作物识别模型，所述作物识别模型采用如下方式进行作物种类识别：
    将所述地块坐标信息在所述时间信息映射的影像坐标信息所属的遥感影像作为输入，在影像单元粒度对输入的遥感影像包含的作物地块进行作物种类识别，获得输入的遥感影像包含的作物地块包含的各影像单元对应的作物种类。
  3. 根据权利要求1所述的授信额度处理方法，所述根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度，包括：
    根据所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目，以及所述物种类分布中影像单元的总数目，计算所述地块信息的置信度；
    其中，所述置信度，包括所述作物种类分布中作物种类与所述目标作物种类相同的影像单元的数目与所述总数目的比值。
  4. 根据权利要求1所述的授信额度处理方法，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性确定所述目标用户的授信额度，包括：
    判断所述置信度是否大于预设置信度阈值；
    若是，基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度；
    若否，向所述目标用户发出授信额度申请失败的提醒。
  5. 根据权利要求4所述的授信额度处理方法，所述基于所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度，包括：
    根据所述目标作物种类、所述地块信息中包含的地块面积、地域信息、所述作物属性中包含的作物价值和价值波动，以及各自对应的权重，计算所述授信额度。
  6. 根据权利要求1所述的授信额度处理方法，所述获取目标用户的作物地块的地块信息步骤执行之前，还包括：
    在检测到所述目标用户针对目标应用的应用处理请求的情况下，基于所述目标应用的应用页面展示所述目标应用绑定的授信处理通道的授信处理通道的触发控件；其中，所述授信处理通道向预设用户清单中记录的目标用户开放；
    在检测到所述触发控件被触发之后，向所述目标用户展示所述目标应用下所述授信处理通道的授信申请页面；其中，所述授信申请页面配置有信息录入接口和授信申请控件；所述地块信息基于所述信息录入接口进行录入；
    相应的，所述获取目标用户的作物地块的地块信息步骤，在所述检测到所述授信申请控件被触发之后执行。
  7. 根据权利要求2所述的授信额度处理方法，所述作物识别模型，采用如下方式进行训练：
    获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；
    获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为样本标签；
    建立所述训练样本与所述样本标签的映射关系，并将所述训练样本和所述样本标签作为训练集进行模型训练，获得所述作物识别模型。
  8. 根据权利要求7所述的授信额度处理方法，所述获取目标用户的作物地块的地块信息步骤执行之前，包括：
    将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；
    将所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类进行存储；
    相应的，所述以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别步骤执行过程中，所述作物识别接口基于存储的所述目标地区在所述目标时间范围内的作物地块的作物种类，确定所述作物地块的作物种类分布。
  9. 根据权利要求1所述的授信额度处理方法，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度步骤执行之后，还包括：
    读取所述目标用户的授信状态；
    若所述目标用户的授信状态为未授信，基于所述授信额度对所述目标用户进行授信处理；
    若所述目标用户的授信状态为已授信，基于所述授信额度对所述目标用户的初始授信额度进行调整；
    若所述目标用户的授信状态为授信已用，基于所述目标用户参与签订的作物经营合约中记录的合约信息，生成履约提醒并向所述目标用户发送。
  10. 根据权利要求1所述的授信额度处理方法，所述基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度步骤执行之后，还包括：
    获取所述目标用户的终端设备的定位数据；
    基于所述定位数据计算所述作物地块的预测地块面积；
    基于所述目标作物种类、所述预测地块面积、所述作物地块的地域信息、所述作物属性中包含的作物价值和价值波动，确定所述作物地块的风险等级；
    基于所述风险等级生成风险预警提示并向所述目标用户展示。
  11. 根据权利要求1所述的授信额度处理方法，还包括：
    基于所述目标作物种类、所述地块信息中包含的地块面积和所述目标作物种类对应的作物属性，计算所述作物地块的作物价值；
    根据所述作物价值确定所述目标用户的保障额度。
  12. 根据权利要求1所述的授信额度处理方法，还包括：
    读取所述地块信息中包含的地块边界信息；所述地块边界信息基于所述目标用户在展示的地图页面输入的标注动作确定；
    基于所述地块边界信息计算所述作物地块的预测地块面积；
    基于所述目标作物种类、所述预测地块面积和所述作物属性，计算所述作物地块的作物价值；
    根据所述作物价值和所述目标作物种类对应的资源转化率，计算所述作物地块对应的资源转化数值；
    基于所述资源转化数值和所述目标用户的资源偏好和/或资源状态，生成所述作物地块的资源管理策略。
  13. 一种作物识别方法，包括：
    接收调用方发送的进行作物种类识别的调用请求；
    根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射 的一个或者多个作物地块；
    根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；
    向所述调用方返回所述作物种类分布；
    其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
  14. 根据权利要求13所述的作物识别方法，所述作物识别模型，采用如下方式进行训练：
    获取指定地区在指定时间范围内的遥感影像数据，作为训练样本；
    获取所述指定地区在所述指定时间范围内的作物地块的作物种类以及地块边界信息，作为真实标签；
    建立所述训练样本与所述真实标签的映射关系，并将所述训练样本和所述真实标签作为训练集进行模型训练，获得所述作物识别模型。
  15. 根据权利要求13所述的作物识别方法，所述接收调用方发送的进行作物种类识别的调用请求步骤执行之前，包括；
    将目标地区在目标时间范围内的遥感影像数据输入所述作物识别模型进行作物种类识别；
    存储所述作物识别模型输出的所述目标地区在所述目标时间范围内的作物地块的作物种类。
  16. 一种授信额度处理装置，包括：
    地块信息获取模块，被配置为获取目标用户的作物地块的地块信息；
    作物种类识别模块，被配置为以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；
    置信度确定模块，被配置为根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；
    授信额度确定模块，被配置为基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
  17. 一种作物识别装置，包括：
    调用请求接收模块，被配置为接收调用方发送的进行作物种类识别的调用请求；
    作物地块确定模块，被配置为根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；
    作物种类分布确定模块，被配置为根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；
    作物种类分布返回模块，被配置为向所述调用方返回所述作物种类分布；
    其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
  18. 一种授信额度处理设备，包括：
    处理器；以及，
    被配置为存储计算机可执行指令的存储器，所述计算机可执行指令在被执行时使所述处理器：
    获取目标用户的作物地块的地块信息；
    以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；
    根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；
    基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述 目标用户的授信额度。
  19. 一种作物识别设备，包括：
    处理器；以及，
    被配置为存储计算机可执行指令的存储器，所述计算机可执行指令在被执行时使所述处理器：
    接收调用方发送的进行作物种类识别的调用请求；
    根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；
    根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；
    向所述调用方返回所述作物种类分布；
    其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
  20. 一种存储介质，用于存储计算机可执行指令，所述计算机可执行指令在被执行时实现以下流程：
    获取目标用户的作物地块的地块信息；
    以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；
    根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；
    基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。
  21. 一种存储介质，用于存储计算机可执行指令，所述计算机可执行指令在被执行时实现以下流程：
    接收调用方发送的进行作物种类识别的调用请求；
    根据所述调用请求中携带的地块坐标信息和时间信息，确定所述地块坐标信息映射的一个或者多个作物地块；
    根据所述一个或者多个作物地块包含的影像单元的作物种类，确定所述地块坐标信息对应的多边形地块的作物种类分布；
    向所述调用方返回所述作物种类分布；
    其中，所述作物地块包含的影像单元的作物种类，由作物识别模型对输入的遥感影像进行作物种类识别后输出。
PCT/CN2021/102030 2020-06-30 2021-06-24 授信额度处理方法及装置、作物识别方法及装置 WO2022001811A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010613765.8 2020-06-30
CN202010613765.8A CN111507833A (zh) 2020-06-30 2020-06-30 授信额度处理方法及装置、作物识别方法及装置

Publications (1)

Publication Number Publication Date
WO2022001811A1 true WO2022001811A1 (zh) 2022-01-06

Family

ID=71877168

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/102030 WO2022001811A1 (zh) 2020-06-30 2021-06-24 授信额度处理方法及装置、作物识别方法及装置

Country Status (3)

Country Link
CN (1) CN111507833A (zh)
TW (1) TWI780641B (zh)
WO (1) WO2022001811A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115034888A (zh) * 2022-06-16 2022-09-09 支付宝(杭州)信息技术有限公司 信用服务提供方法及装置
CN115187413A (zh) * 2022-07-13 2022-10-14 阳光农业相互保险公司 一种基于土地确权信息构建的农险承保方法
CN116308762A (zh) * 2023-05-19 2023-06-23 杭州钱袋数字科技有限公司 一种基于人工智能的可信度评估及授信处理方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111507833A (zh) * 2020-06-30 2020-08-07 浙江网商银行股份有限公司 授信额度处理方法及装置、作物识别方法及装置
CN112328913A (zh) * 2020-11-05 2021-02-05 浙江网商银行股份有限公司 任务处理方法以及装置
CN112396438B (zh) * 2021-01-18 2021-04-20 浙江网商银行股份有限公司 资产处理方法、装置及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105787796A (zh) * 2016-05-23 2016-07-20 中国农业银行股份有限公司 一种授信额度处理方法及装置
CN107451926A (zh) * 2017-07-18 2017-12-08 福农宝（厦门）大数据科技有限公司 一种基于大数据的助农贷款平台
CN108510385A (zh) * 2018-03-21 2018-09-07 安徽天勤盛创信息科技股份有限公司 一种农业贷款综合业务管理系统
CN108537657A (zh) * 2018-04-03 2018-09-14 毛磊 一种基于大数据的助农贷款平台
CN109815916A (zh) * 2019-01-28 2019-05-28 成都蝉远科技有限公司 一种基于卷积神经网络算法的植被种植区域识别方法及系统
CN110930260A (zh) * 2019-10-30 2020-03-27 中国银行保险信息技术管理有限公司 种植业保险标的地块级全核全验方法及装置
CN111507833A (zh) * 2020-06-30 2020-08-07 浙江网商银行股份有限公司 授信额度处理方法及装置、作物识别方法及装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101609148B (zh) * 2009-07-08 2011-04-06 北京农业信息技术研究中心 遥感影像数据处理和发布的方法
CN101699315B (zh) * 2009-10-23 2012-04-25 北京农业信息技术研究中心 一种作物长势均匀度的监测装置和方法
TWM530994U (zh) * 2016-05-16 2016-10-21 國泰人壽保險股份有限公司 不動產估價系統
BR112019021011A2 (pt) * 2017-04-10 2020-05-05 Decisive Farming Corp método e sistema de gerenciamento de colheita
CN108876229A (zh) * 2017-05-08 2018-11-23 华农（北京）电子商务有限公司 一种农资供应链管理与服务互联网平台
US20180330435A1 (en) * 2017-05-11 2018-11-15 Harvesting Inc. Method for monitoring and supporting agricultural entities
CN110969520A (zh) * 2018-09-30 2020-04-07 重庆小雨点小额贷款有限公司 一种贷款申请方法、装置、服务器及计算机存储介质
CN109785168A (zh) * 2019-01-08 2019-05-21 北京佰信蓝图科技股份公司 一种农业保险地块的信息采集方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105787796A (zh) * 2016-05-23 2016-07-20 中国农业银行股份有限公司 一种授信额度处理方法及装置
CN107451926A (zh) * 2017-07-18 2017-12-08 福农宝（厦门）大数据科技有限公司 一种基于大数据的助农贷款平台
CN108510385A (zh) * 2018-03-21 2018-09-07 安徽天勤盛创信息科技股份有限公司 一种农业贷款综合业务管理系统
CN108537657A (zh) * 2018-04-03 2018-09-14 毛磊 一种基于大数据的助农贷款平台
CN109815916A (zh) * 2019-01-28 2019-05-28 成都蝉远科技有限公司 一种基于卷积神经网络算法的植被种植区域识别方法及系统
CN110930260A (zh) * 2019-10-30 2020-03-27 中国银行保险信息技术管理有限公司 种植业保险标的地块级全核全验方法及装置
CN111507833A (zh) * 2020-06-30 2020-08-07 浙江网商银行股份有限公司 授信额度处理方法及装置、作物识别方法及装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115034888A (zh) * 2022-06-16 2022-09-09 支付宝(杭州)信息技术有限公司 信用服务提供方法及装置
CN115187413A (zh) * 2022-07-13 2022-10-14 阳光农业相互保险公司 一种基于土地确权信息构建的农险承保方法
CN115187413B (zh) * 2022-07-13 2023-09-05 阳光农业相互保险公司 一种基于土地确权信息构建的农险承保方法
CN116308762A (zh) * 2023-05-19 2023-06-23 杭州钱袋数字科技有限公司 一种基于人工智能的可信度评估及授信处理方法
CN116308762B (zh) * 2023-05-19 2023-08-11 杭州钱袋数字科技有限公司 一种基于人工智能的可信度评估及授信处理方法

Also Published As

Publication number Publication date
TWI780641B (zh) 2022-10-11
TW202203127A (zh) 2022-01-16
CN111507833A (zh) 2020-08-07

Similar Documents

Publication Publication Date Title
WO2022001811A1 (zh) 授信额度处理方法及装置、作物识别方法及装置
WO2022001812A1 (zh) 授信额度处理方法及装置、用户资源处理方法及装置
TWI769763B (zh) 資料處理方法及裝置
TWI686760B (zh) 保險欺詐識別的資料處理方法、裝置、設備及伺服器
WO2021103909A1 (zh) 风险预测和风险预测模型的训练方法、装置及电子设备
CN110751286B (zh) 神经网络模型的训练方法和训练系统
Feng et al. Environmental conservation in agriculture: land retirement vs. changing practices on working land
US11544627B1 (en) Machine learning-based methods and systems for modeling user-specific, activity specific engagement predicting scores
WO2021204041A1 (zh) 数据处理
WO2021189926A1 (zh) 业务模型训练方法、装置、系统及电子设备
WO2021098652A1 (zh) 一种数据处理方法及装置
DK202370110A1 (en) Environmental, social, and governance (esg) performance trends
US8577701B1 (en) System and method for processing data related to investment management
WO2024041275A1 (zh) 物种分布数据聚合方法、系统及存储介质
WO2020155831A1 (zh) 数据标签生成、模型训练、事件识别方法和装置
Zeng et al. A hybrid modeling approach considering spatial heterogeneity and nonlinearity to discover the transition rules of urban cellular automata models
Gao et al. Social capital, phone call activities and borrower default in mobile micro-lending
CN113610572A (zh) 一种营销策略优化方法、装置以及电子设备
Sourabh et al. Liquidity risk in derivatives valuation: an improved credit proxy method
Meera et al. Digital disruption at field level: tipping point experiments from rice sector
CN113822730A (zh) 信息的推荐方法、装置、计算设备及介质
JP2020021231A (ja) 情報処理方法、情報処理装置、およびプログラム
Sahil FACTORS INFLUENCING THE ADOPTION OF DIGITAL TECHNOLOGIES BY SMALL-SCALE PRODUCERS IN INDIA'S AGRICULTURE VALUE CHAINS (AVCS)
CN117314756B (zh) 基于遥感图像的验保方法、装置、计算机设备及存储介质
Okoroji Farmers’ use of mobile phone applications in Abia state, Nigeria: a thesis submitted in partial fulfilment of the requirements for the Degree of Master of Commerce (Agricultural) at Lincoln University

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21833669

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21833669

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19/06/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21833669

Country of ref document: EP

Kind code of ref document: A1