Model generation device, evaluation device, support system, model generation method, and evaluation method

Abstract

To provide a technology that proposes a pest control method suitable for each farm producer.SOLUTION: A model generating device 10 includes a model generating unit 14 that generates a regression model which performs regression analysis on a data set including work information representing works relating to the cultivation carried out by a farm producer and to the pest control, and the evaluation value of a disease and insect damage preventing effect when the works are carried out, sets the work information as explanatory variables, and takes the evaluation value of the disease and insect damage preventing effect as an objective variable.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a model generation device, an evaluation device, a support system, a model generation method, and an evaluation method.

Background Art

[0002] In the "Green Food System Strategy", it is proposed to reduce the use of chemical pesticides by 50%, reduce the use of chemical fertilizers by 30%, and expand the proportion of the area under organic farming to 25% (1 million ha). To suppress the use of pesticides and effectively manage pests and diseases using other control techniques, advanced knowledge of pests and diseases is required. Therefore, there is a need for a control support technology that enables the management of pests and diseases using optimal control techniques even without advanced knowledge of pests and diseases.

[0003] Patent Document 1 describes an evaluation method for evaluating factors affecting the growth rate of pests by multiple regression analysis with the growth rate of pests as the target variable and the number of pests, natural enemies, competitors, and environmental factors such as temperature as explanatory variables. Patent Document 2 describes a system that analyzes accumulated data related to agriculture and measurement data for each farmland and transmits optimization advice for the target farmland to customers.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] The technology described in Patent Document 1 evaluates general factors that affect the growth rate of pests, and does not evaluate an optimal control method individually considering the circumstances of each crop producer. The technology described in Patent Document 2 is for providing optimization advice for farmland for each crop production, but does not consider the cultivation and control operations currently being carried out by crop producers.

[0006] Integrated Pest Management (IPM), which combines and implements various control techniques available for pest control, is known. For the effective implementation of IPM, it is important to evaluate the currently implemented control methods and optimize IPM by combining other more effective control techniques. And there is a demand for customized support so that an optimal IPM can be constructed even if crop producers do not have advanced knowledge about pests and diseases.

[0007] The present invention has been made to solve the above-described problems, and an object thereof is to provide a technology for proposing a control method suitable for each crop producer.

Means for Solving the Problems

[0008] A model generation device according to an aspect of the present invention is a model generation device that generates an evaluation model for evaluating the control effect of pests and diseases in crop production, and includes work information representing work related to cultivation and control performed by a crop producer, and a data set including an evaluation value of the pest and disease control effect when the work is performed is subjected to regression analysis, and a model generation unit that generates a regression model having the work information as an explanatory variable and the evaluation value of the pest and disease control effect as an objective variable.

[0009] An evaluation device according to one aspect of the present invention is an evaluation device for evaluating the control effect of pests and diseases in agricultural product production, and performs regression analysis on a data set including work information representing cultivation and control work performed by a crop producer and an evaluation value of the pest and disease control effect when the work is performed. An evaluation unit is provided that uses a regression model in which the work information is an explanatory variable and the evaluation value of the pest and disease control effect is an objective variable to obtain the evaluation value of the pest and disease control effect with the work information as an input.

[0010] A support system according to one aspect of the present invention is a support system for supporting the control of pests and diseases in crop production, and includes a model generation device according to one aspect of the present invention and an evaluation device according to one aspect of the present invention.

[0011] A model generation method according to one aspect of the present invention is a model generation method for generating an evaluation model for evaluating the control effect of pests and diseases in crop production, and includes a model generation step of performing regression analysis on a data set including work information representing cultivation and control work performed by a crop producer and an evaluation value of the pest and disease control effect when the work is performed, and generating a regression model in which the work information is an explanatory variable and the evaluation value of the pest and disease control effect is an objective variable.

[0012] An evaluation method according to one aspect of the present invention is an evaluation method for evaluating the control effect of pests and diseases in crop production, and includes an evaluation step of using a regression model generated by performing regression analysis on a data set including work information representing cultivation and control work performed by a crop producer and an evaluation value of the pest and disease control effect when the work is performed, with the work information as an explanatory variable and the evaluation value of the pest and disease control effect as an objective variable, and obtaining the evaluation value of the pest and disease control effect with the work information as an input.

Effect of the Invention

[0013] According to one aspect of the present invention, it is possible to provide a technique for proposing a control method suitable for each crop producer.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Mode for Carrying Out the Invention

[0015] One aspect of the present invention realizes a support system that evaluates the control effect of pests and diseases for IPM including operations related to cultivation and control in crop production, and proposes an IPM with a high control effect of pests and diseases to crop producers. The support system according to one aspect of the present invention can support the control of pests and diseases in crop production by proposing an IPM suitable for each crop producer on a made-to-order basis.

[0016] In this specification, IPM may be intended to be a comprehensive control method that includes operations related to cultivation and control performed by crop producers and combines multiple operations that affect pest control. The term "IPM element technology" is intended for each operation included in IPM. Also, each operation included in IPM can also be referred to as a factor that affects the success or failure of IPM. The term "IPM success or failure" represents the evaluation of the pest control effect of IPM. And when a predetermined pest control effect is obtained, it may be expressed as "IPM success", and when a predetermined pest control effect is not obtained, it may be expressed as "IPM failure".

[0017] 〔Support System 100〕 Based on FIG. 1, a support system 100 for supporting pest control in crop production will be described. FIG. 1 is a block diagram showing an example of the main configuration of the support system 100 according to one aspect of the present invention. The prediction system 100 includes a model generation device 10 and an evaluation device 20. The support system 100 further includes an input device 30, a storage device 40, and an output device 50. The support system 100 may include the model generation device 10 and the evaluation device 20 as independent devices, or may be integrally provided in one device.

[0018] Here, the support for pest control by the support system 100 will be described with reference to FIG. 2. FIG. 2 is a diagram for explaining the outline of the support system according to one aspect of the present invention. As shown in FIG. 2, as an example, the support system 100 executes processes including (1) information collection by questionnaire, (2) database creation of IPM element technology, (3) data analysis, (4) calculation of the effect amount on IPM success or failure, (5) scoring of IPM, and (6) proposal of IPM element technology. By executing the processes (1) to (6), the support system 100 proposes customized IPM for each crop producer and supports pest control in crop production. Details of each of the processes (1) to (6) will be described later.

[0019] The input device 30 receives input operations from the user for the support system 100. The user who uses the support system 100 can be a crop producer, an agricultural worker, or the like. The input device 30, as an example, receives the input of data used to generate an evaluation model in the model generation device 10. Further, the input device 30 receives the input of data used to evaluate IPM in the evaluation device 20.

[0020] The storage device 40 stores programs and data used in the support system 100. The storage device 40, as an example, stores various data input via the input device 30. Further, the storage device 40, as an example, stores a data set used to generate an evaluation model and the generated evaluation model in the model generation device 10. Furthermore, the storage device 40, as an example, stores an evaluation model, input information, and output information used to evaluate IPM in the evaluation device 20. The storage device 40 may have a database for storing various data on the cloud or a server.

[0021] The output device 50 outputs the result evaluated by the evaluation device 20. Further, the output device 50 may output IPM support information selected based on the result evaluated by the evaluation device 20. The IPM support information includes, as an example, an evaluation result for the current IPM, improvement points of the current IPM, a proposal of IPM element technology for improving the control effect, and the like.

[0022] The output mode by the output device 50 is not particularly limited. The output device 50 may be, for example, a display device that displays the information as an image, a printing device that prints the information, or an alarm device that outputs the information as sound. Further, the output device 50 may be a display of a mobile device such as a smartphone that displays the result evaluated by the evaluation device 20 or the IPM support information based on the result.

[0023] (Model Generation Device 10) The model generation device 10 generates an evaluation model for evaluating the control effect of pests and diseases in crop production. The model generation device 10 executes the processes (2) and (3) shown in FIG. 2 as an example.

[0024] The model generation device 10 includes a control unit 11. The control unit 11 comprehensively controls each part of the model generation device 10 and is realized by a processor and a memory as an example. In this example, the processor accesses a storage (not shown), loads a program (not shown) stored in the storage into the memory, and executes a series of instructions included in the program. Thereby, each part of the control unit 11 is configured. As each of these parts, the control unit 11 includes a data acquisition unit 12, a database generation unit 13, and a model generation unit 14.

[0025] <Data acquisition unit 12> The data acquisition unit 12 acquires data for generating an evaluation model. The data acquisition unit 22 reads data from the storage device 40 based on an input signal indicating the start instruction of generating a prediction model from the input device 30. Also, the data acquisition unit 12 may acquire data input via the input device 30. The data acquisition unit 12 outputs the acquired data to the database generation unit 13.

[0026] The data acquired by the data acquisition unit 12 may be, as an example, data obtained by a questionnaire regarding the current IPM element technology performed on crop producers and the evaluation of the control effect (IPM success or failure) by the IPM element technology. An example of the questions included in the questionnaire for crop producers is a question regarding IPM success or failure as the target variable and a question regarding IPM as the explanatory variable. The data obtained by such a questionnaire may be data in which the IPM element technology is specified based on the results of the crop producers' answers to the predetermined questions and the control effect is evaluated.

[0027] <Database generation unit 13> Based on the data acquired by the data acquisition unit 12, the database generation unit 13 generates a database that associates IPM element technologies with IPM success or failure. The database generation unit 13 generates a database that associates work information representing the cultivation and control operations performed by crop producers with the evaluation value of the pest control effect when the operations included in the work information are executed.

[0028] The IPM element technologies included in the above-described database can be work information including at least one piece of information on cultivation environment preparation work, cultivation environment management work, pest occurrence status confirmation work, response work at the time of pest occurrence, natural enemy utilization status of pests, and pesticide utilization status. The IPM success or failure included in the above-described database can be an evaluation value of the pest control effect obtained by evaluating the pest occurrence status, the work cost required for IPM, the labor of IPM, etc. The IPM success or failure included in the database may be an evaluation value obtained by evaluating the pest occurrence status and at least one of the work cost required for IPM and the labor of IPM.

[0029] <Model Generation Unit 14> The model generation unit 14 performs a regression analysis on a data set including work information representing the cultivation and control operations performed by crop producers and the evaluation value of the pest control effect when the operations are executed, and generates a regression model with the work information as an explanatory variable and the evaluation value of the pest control effect as an objective variable. That is, the model generation unit 14 performs a regression analysis on the acquired data set, and generates a regression model with IPM element technologies as explanatory variables and IPM success or failure as objective variables as an evaluation model for evaluating the pest control effect in crop production. The model generation unit 14 stores the generated evaluation model in the storage device 40.

[0030] As an example, the model generation unit 14 generates a linear regression model using, for example, Generalized Liner Regression (GLR), Partial Least Squares Regression (PLS), or the like. As another example, the model generation unit 14 may generate an evaluation model using known machine learning methods such as neural networks, decision trees, random forests, and support vector machines.

[0031] The model generation unit 14 may generate a multiple regression model obtained by performing multiple regression analysis on the plurality of explanatory variables, or a learned model obtained by performing machine learning using the plurality of explanatory variables, as an evaluation model. Further, the model generation unit 14 may generate a simple regression analysis model obtained by performing simple regression analysis on each of the plurality of explanatory variables, as an evaluation model. The multiple regression model and the learned model are generated in consideration of the correlation between the plurality of explanatory variables.

[0032] The model generation unit 14 may analyze the evaluation results by the evaluation device 20 and reconstruct the regression model. That is, the model generation unit 14 may regenerate the evaluation model based on the feedback from the evaluation device 20.

[0033] According to the model generation device 10, by performing regression analysis for each IPM operation executed by the crop producer, it is possible to generate an evaluation model capable of accurately evaluating the success or failure of IPM.

[0034] (Evaluation device 20) The evaluation device 20 evaluates the control effect of pests and diseases in crop production. The evaluation device 20 evaluates the success or failure of IPM using a regression model with the IPM element technology as an explanatory variable and the success or failure of IPM as an objective variable. As an example, the evaluation device 20 executes the processes (4) to (6) shown in FIG. 2.

[0035] The evaluation device 20 includes a control unit 21. The control unit 21 comprehensively controls each part of the evaluation device 20 and is realized by, for example, a processor and a memory. In this example, the processor accesses a storage (not shown), loads a program (not shown) stored in the storage into the memory, and executes a series of instructions included in the program. Thereby, each part of the control unit 21 is configured. As each of these parts, the control unit 21 includes a data acquisition unit 22, a model acquisition unit 23, an evaluation unit 24, and a proposal unit 25.

[0036] <Data acquisition unit 22> The data acquisition unit 22 acquires IPM data representing the IPM element technology to be evaluated. The IPM data to be evaluated may be data obtained based on the responses of crop producers to a questionnaire. The data acquisition unit 22 reads out the IPM data to be evaluated from the storage device 40 based on an input signal representing an evaluation start instruction from the input device 30. Further, the data acquisition unit 22 may acquire the IPM data to be evaluated input via the input device 30. The data acquisition unit 22 outputs the acquired IPM data to the evaluation unit 24.

[0037] <Model acquisition unit 23> The model acquisition unit 23 acquires an evaluation model generated by the model generation device 10, with the IPM element technology as an explanatory variable and the IPM success or failure as an objective variable. The model acquisition unit 23 may acquire the evaluation model generated by the model generation device 10 and stored in the storage device 40. The model acquisition unit 23 outputs the acquired evaluation model to the evaluation unit 24.

[0038] <Evaluation unit 24> The evaluation unit 24 obtains an evaluation value of the pest control effect by using, as an input, the work information including work information representing the cultivation and control operations performed by the crop producer and an evaluation value of the pest control effect when the work is performed, and using a regression model generated by performing a regression analysis on a data set including the work information as an explanatory variable and the evaluation value of the pest control effect as an objective variable.

[0039] The evaluation unit 24 inputs the data of the IPM element technology to be evaluated into the acquired evaluation model, and obtains the evaluation value regarding the success or failure of the IPM output. The evaluation value regarding the success or failure of the IPM can be, for example, the success probability of the IPM, the effect size representing the degree of influence on the IPM, etc. The evaluation unit 24 outputs the acquired evaluation value to the proposal unit 25.

[0040] The evaluation unit 24 can output the effect size representing the degree of influence on the success or failure of the IPM for each IPM element technology. The effect size of each IPM element technology can be calculated as a statistic indicating the degree of influence of the IPM element technology on the success or failure of the IPM, obtained using, for example, the odds ratio, chi-square value, etc.

[0041] The evaluation unit 24 may aggregate the evaluation values of the pest control effects output for each piece of work information, and obtain the evaluation value for evaluating the overall pest control effect of the work information. The evaluation unit 24 can comprehensively evaluate the IPM element technologies implemented to obtain the desired pest control effect by aggregating the evaluation values obtained for each IPM element technology. The evaluation unit 24 may, for example, aggregate only the evaluation values that affect the success of the IPM and calculate the IPM success rate. Also, the evaluation unit 24 may aggregate only the evaluation values that affect the failure of the IPM and calculate the IPM failure rate. Then, the evaluation unit 24 may perform a comprehensive scoring of the IPM element technologies based on at least one of the IPM success rate and the IPM failure rate.

[0042] <Proposal unit 25> The proposal unit 25 selects the work information that increases the evaluation value and generates proposal information for the crop producer. The proposal unit 25 refers to the acquired evaluation value, selects the IPM element technology for improving the pest control effect, and proposes it to the crop producer. Thereby, it proposes the improvement of the IPM to the crop producer.

[0043] The proposal department 25 selects other IPM element technologies with an evaluation value higher than the standard based on the evaluation value that affects the IPM failure, for example. As for the information on other IPM element technologies, the information obtained in advance and stored in the storage device 40 can be used. The proposal department 25 creates proposal information including the selected IPM element technology. The proposal department 25 outputs the created proposal information to the output device 50. Also, the proposal department 25 may store the created proposal information in the storage device 40.

[0044] For the selected IPM element technology, the proposal department 25 can determine the priority in descending order of the evaluation value and generate the proposal information in descending order of the priority. Also, the proposal department 25 may propose the difference from the reference evaluation value as the scoring information for the IPM element technology to be proposed.

[0045] The evaluation device 20 can evaluate the pest control effect for the IPM element technology including the operations related to cultivation and control in crop production and propose the IPM element technology with a high pest control effect to the crop producer.

[0046] (Other configurations) The questionnaire items for the crop producer may be appropriately changed for the purpose of obtaining appropriate data regarding IPM. Creating the questionnaire items with reference to the evaluation results by the evaluation device 20 and executing the information collection by questionnaire to the crop producer as shown in (1) of FIG. 2 using the questionnaire items created in this way are also included in the scope of the present invention.

[0047] (Model generation process) The flow of the prediction model generation process (prediction model generation method) by the model generation device 10 will be described with reference to FIG. 3. FIG. 3 is a flowchart showing an example of the generation process executed by the model generation device 10 according to an aspect of the present invention. As shown in FIG. 3, first, the data acquisition unit 12 acquires a data set including IPM element technologies and IPM success / failure obtained by a questionnaire to agricultural producers (step S1). Next, the database generation unit 13 generates a database of IPM element technologies using the data acquired by the data acquisition unit 12 (step S2).

[0048] The model generation unit 14 generates a regression model by performing regression analysis using the information on the IPM element technologies included in the database as explanatory variables and the information on IPM success / failure as objective variables (step S3). The model generation unit 14 stores the generated regression model in the storage device 40 (step S4) and ends the model generation process.

[0049] (Evaluation process) The flow of the evaluation process (evaluation method) by the evaluation device 20 will be described with reference to FIG. 4. FIG. 4 is a flowchart showing an example of the evaluation process executed by the evaluation device 20 according to an aspect of the present invention. As shown in FIG. 4, first, the data acquisition unit 22 acquires IPM element technology information representing the IPM element technologies executed by agricultural producers (step S11). The model acquisition unit 23 acquires the evaluation model generated by the model generation device 10 (step S12). Then, the evaluation unit 24 inputs the IPM element technology information into the evaluation model and acquires the evaluation value for the IPM success / failure output (step S13). The proposal unit 25 selects the IPM element technologies that improve the evaluation value for the IPM success / failure (step S14). Then, the proposal unit 25 generates proposal information including the selected IPM element technologies and outputs it to the output device 50 (step S15), and ends the evaluation process.

[0050] (Support process) An example of the support process by the support system 100 including the processes (1) to (6) in FIG. 2 will be described with reference to FIGS. 5 to 12.

[0051] (1) Information collection by questionnaire As the (1) information collection by questionnaire shown in FIG. 2, a questionnaire including questions for collecting information on the objective variable (IPM success or failure) and the explanatory variable (IPM elemental technology) is implemented for crop producers.

[0052] Examples of questions for collecting information on the objective variable include, for example, the degree of occurrence of pests and diseases, the degree of damage to agricultural harvests caused by pests and diseases, the perception of the control effect by natural enemies, the yield and quality of agricultural harvests, the cost spent on pest and disease control, the labor (time and effort) spent on pest and disease control, the degree of reduction in the number of applications of synthetic chemical insecticides due to the use of natural enemies, etc. Table 1 shows examples of questions for collecting information on the objective variable.

Table 1

[0053] Examples of questions for collecting information on the explanatory variable include, for example, cultivation management and pest and disease observation before and after crop planting, cultivation management and pest and disease observation during the cultivation period, the method of selecting and using insecticides, the method of installing natural enemy materials, the observation of natural enemies, the method of using pesticides before and after the installation of natural enemy materials, etc. Table 2 shows examples of questions for collecting information on the explanatory variable.

Table 2

[0054] Among the questions as described above, for items related to the degree of occurrence of pests and diseases, the degree of damage to agricultural harvests caused by pests and diseases, and the perception of the control effect by natural enemies, questions may be set for each period if necessary. Also, the questions for implementing the questionnaire can be selected and set for each crop variety. It is preferable that the questions for implementing the questionnaire are about 2 to 5 each for the objective variable and the explanatory variable. Also, it is preferable to set the order of the questions so that they are asked in order from the questions having a high influence on IPM success or failure.

[0055] (2) Aggregate knowledge database of IPM Next, the data obtained from the questionnaire conducted on crop producers is stored in a database to create a collective knowledge database for IPM. As an example, a collective knowledge database for IPM is created based on the results of the questionnaire conducted on crop producers. An example of the collective knowledge database for IPM is shown in FIG. 5. As shown in FIG. 5, a database is created by associating the respondent ID with the responses regarding the attributes of the crop producers, the responses regarding the target variables, and the responses regarding the explanatory variables.

[0056] Next, as shown in FIG. 6, the questionnaire responses are binarized (converted to 0 / 1). As the binarization process, for example, positive responses to IPM success are converted to "1" and negative responses are converted to "0", and the process is performed so that the total number of responses is evenly distributed. As a result, as shown in FIG. 7, a collective knowledge database for IPM with binarized responses is obtained.

[0057] (3) Analysis of data Using the created database, data analysis of each explanatory variable for each target variable is performed. The data analysis generates an evaluation model that calculates the degree of influence (effect size) of each explanatory variable on the target variable by using multiple explanatory variables for each target variable in multiple regression analysis or machine learning, or by performing simple regression analysis for each explanatory variable for each target variable. When the number of explanatory variables becomes large, for example, 15 or more, and the solution becomes unstable in multiple regression analysis, the analysis method can be appropriately selected, such as performing simple regression analysis. Note that this effect size is the evaluation value of the pest control effect.

[0058] (4) Calculation of effect size Using the generated evaluation model, calculate the effect size. Figure 8 shows the calculation of the effect size using the multiple regression model generated by multiple regression analysis or machine learning, and Figure 9 shows the calculation of the effect size using the simple regression model generated by simple regression analysis. When using the multiple regression model, as shown in Figure 8, for each target variable, after adjusting the correlation between the explanatory variables, the effect size of each explanatory variable is calculated. On the other hand, when using the simple regression model, as shown in Figure 9, for each target variable, the effect size of each explanatory variable is calculated without adjusting the correlation between the explanatory variables. The calculated effect size may be converted to a percentage (%).

[0059] In addition, when the attributes of the questionnaire respondents (such as the answering year and production area) strongly affect the calculation of the effect size, the information on the attributes may be treated as a variable effect. The databases used for calculating the effect sizes shown in Figures 8 and 9 were automatically generated by pseudo-random numbers from the answers to the questionnaires of 300 crop producers. In the examples shown in Figures 8 and 9, a logistic regression model (binomial distribution model) was used, and the effect size was calculated as the odds ratio (OD).

[0060] (5) Scoring of IPM Element Technologies Based on the calculated effect size, score the answers to the questionnaires of each crop producer, and evaluate the IPM element technologies implemented by each crop producer. As an example, add the effect size (%) to a positive answer (1) for the success or failure of IPM, and calculate the total score. This calculation is performed for each target variable. An example of the scoring process for IPM element technologies is shown in Figure 10.

[0061] As shown in Figure 10, for example, the score for the IPM element technology of respondent ID0001 for "Qm01. Yield damage and fruit damage caused by virus disease (mosaic symptoms) from planting to December" is 89 points / 100 points. Also, the score for the IPM element technology of respondent ID0001 for "Qm05. Reduce the number of insecticide sprays when using natural enemies" is 85 points / 100 points.

[0062] Next, the score of the IPM element technology for "Qm01. Yield damage and fruit damage caused by virus disease (mosaic symptoms) from planting to December" of respondent ID0002 is 66 points / 100 points. Also, the score of the IPM element technology for "Qm05. Reduce the number of pesticide sprays when using natural enemies" of respondent ID0002 is 63 points / 100 points.

[0063] Furthermore, the score of the IPM element technology for "Qm01. Yield damage and fruit damage caused by virus disease (mosaic symptoms) from planting to December" of respondent ID0300 is 43 points / 100 points. Also, the score of the IPM element technology for "Qm05. Reduce the number of pesticide sprays when using natural enemies" of respondent ID0300 is 51 points / 100 points.

[0064] (6) Proposal of recommended operations and creation of IPM diagnosis report Based on the scoring results, for the responses of each crop producer to the questionnaire, propose IPM element technologies that can improve the scores to propose IPM improvement. An example of the proposal process for IPM element technologies is shown in Figure 11. As shown in Figure 11, based on the effect size (%) calculated for the explanatory variables (operations related to IPM success or failure) that gave a negative response (0) to IPM success or failure, determine the priority of the proposals in descending order of the effect size. As a result, recommend operations in descending order of priority and calculate the additional score when this operation is performed. Also, if necessary, set hyperlinks or the like so that crop producers can access detailed information about this operation. Create an IPM diagnosis report as shown in Figure 12, including recommended operations, additional scores, hyperlinks, etc., and propose it to the crop producers who responded to the questionnaire. That is, IPM can be supported by an "diagnosis report" optimized for each agricultural producer (questionnaire response).

[0065] Thus, according to the support system 100, it is possible to evaluate the control effect of pests and diseases for IPM including operations related to cultivation and control in crop production, and propose IPM element technologies with a high control effect of pests and diseases to crop producers. According to the support system 100, by customizing and proposing an appropriate IPM for each crop producer, it is possible to support the control of pests and diseases in crop production.

[0066] According to such a configuration, it leads to the maintenance and development of agriculture through the popularization of IPM, and can contribute to the achievement of the sustainable development goal (SDGs) of protecting the richness of the land.

[0067] 〔Example of implementation by software〕 The functions of the model generation device 10 and the evaluation device 20 (hereinafter referred to as "devices") are programs for causing a computer to function as the devices, and can be realized by programs for causing a computer to function as each control block of the devices (especially each part included in the control unit 11 and the control unit 21).

[0068] In this case, the above device includes a computer having at least one control device (for example, a processor) and at least one storage device (for example, a memory) as hardware for executing the above program. By executing the above program with this control device and storage device, each function described in the above embodiments is realized.

[0069] The above program may be recorded on one or more computer-readable recording media, not temporarily. This recording medium may or may not be provided in the above device. In the latter case, the above program may be supplied to the above device via any wired or wireless transmission medium.

[0070] In addition, part or all of the functions of each of the above control blocks can also be realized by a logic circuit. For example, an integrated circuit in which a logic circuit functioning as each of the above control blocks is formed is also included in the scope of the present invention. In addition to this, for example, it is also possible to realize the functions of each of the above control blocks by a quantum computer.

[0071] Also, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI may operate in the above control device, or may operate in another device (for example, an edge computer or a cloud server, etc.).

[0072] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

Explanation of Reference Numerals

[0073] 10 Model generation device 14 Model generation unit 20 Evaluation device 24 Evaluation unit 25 Proposal unit 100 Support system

Claims

1. A model generation device for generating an evaluation model for evaluating the control effect of pests and diseases in crop production, performing a regression analysis on a dataset including work information representing cultivation and control operations performed by crop producers and an evaluation value of the pest and disease control effect when the operations are performed, and generating a regression model having the work information as an explanatory variable and the evaluation value of the pest and disease control effect as an objective variable, the model generation device comprising a model generation unit, wherein the evaluation value is data obtained from a questionnaire regarding the evaluation of the pest and disease control effect conducted on crop producers.

2. The model generation device according to claim 1, wherein the model generation unit generates a multiple regression model obtained by performing multiple regression analysis on a plurality of the explanatory variables, or a learned model obtained by performing machine learning using a plurality of the explanatory variables.

3. The model generation device according to claim 1, wherein the model generation unit generates a simple regression analysis model obtained by performing simple regression analysis on each of a plurality of the explanatory variables.

4. An evaluation device for evaluating the control effect of pests and diseases in agricultural product production, using a regression model having the work information as an explanatory variable and the evaluation value of the pest and disease control effect as an objective variable, which is generated by performing a regression analysis on a dataset including work information representing cultivation and control operations performed by crop producers and an evaluation value of the pest and disease control effect when the operations are performed, and obtaining the evaluation value of the pest and disease control effect with the work information as an input, the evaluation device comprising an evaluation unit, wherein the evaluation value is data obtained from a questionnaire regarding the evaluation of the pest and disease control effect conducted on crop producers.

5. The evaluation device according to claim 4, wherein the evaluation unit aggregates the evaluation values of the pest and disease control effect output for each piece of the work information and obtains an evaluation value for evaluating the overall pest and disease control effect of the work information.

6. further comprising a proposal unit that selects the work information for increasing the evaluation value and generates proposal information for crop producers, wherein the proposal unit determines priorities in descending order of the evaluation values of the pest and disease control effect for the work for which crop producers have given negative answers to the evaluation of the pest and disease control effect, and proposes the proposal information in descending order of the priorities.

7. A model generation device according to any one of claims 1 to 3, and an evaluation device according to any one of claims 4 to 6, comprising A support system for assisting in the control of pests and diseases in crop production.

8. A model generation method for generating an evaluation model for evaluating the control effect of pests and diseases in crop production, including a model generation step of performing a regression analysis on a dataset including work information representing the cultivation and control operations performed by crop producers and an evaluation value of the pest and disease control effect when the operations are performed, and generating a regression model with the work information as an explanatory variable and the evaluation value of the pest and disease control effect as an objective variable. The model generation method, wherein the evaluation value is data obtained from a questionnaire regarding the evaluation of the pest and disease control effect conducted on crop producers.

9. An evaluation method for evaluating the control effect of pests and diseases in crop production, including an evaluation step of using a regression model generated by performing a regression analysis on a dataset including work information representing the cultivation and control operations performed by crop producers and an evaluation value of the pest and disease control effect when the operations are performed, with the work information as an explanatory variable and the evaluation value of the pest and disease control effect as an objective variable, and obtaining the evaluation value of the pest and disease control effect by inputting the work information. The evaluation method, wherein the evaluation value is data obtained from a questionnaire regarding the evaluation of the pest and disease control effect conducted on crop producers.

Images