Estimation device, control program, estimation method, and estimation system

Abstract

To estimate a level of skill of a worker on the basis of difficulty of agricultural work.SOLUTION: An apparatus (20) for estimating a level of skill for remote operation of a worker in agricultural work includes: an efficiency calculation unit (21) which calculates work efficiency using land information of a first agricultural task executed recently and a work result of a first worker who executed the first agricultural task; a difficulty calculation unit (22) which calculates first difficulty of the first agricultural task, and acquires third difficulty by correcting second difficulty of the agricultural task before completion of the first agricultural task with the first difficulty; and a level of skill estimation unit (23) which estimates a first skill level of the first worker based on the work efficiency and the third difficulty, and acquires a third skill level by correcting a second skill level of the first worker on the completion of the first agricultural task with the first skill level.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an estimation device, a control program, an estimation method, an estimation system, and a data structure for estimating the skill level of a worker in remote operation for agricultural work performed by remote-controlling a working machine body.

Background Art

[0002] In recent years, working machine bodies capable of performing agricultural work by remote operation have been developed, and it has become possible for workers to perform agricultural work by remote-controlling the working machine bodies. In such agricultural work, the feasibility of implementation, work efficiency, and the like may vary depending on the skill level of the worker. Therefore, there is a demand for a method of estimating the worker's skill level for remote operation of a working machine body.

[0003] For example, Patent Document 1 discloses a skill level determination device that determines a worker's skill level by using field conditions during work to extract work records performed under unusual field conditions, and calculating the proportion of work records in which operation fluctuated abruptly.

Prior Art Literature

Patent Literature

[0004]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0005] The skill level determination device described in Patent Document 1 does not evaluate the worker's skill level based on the difficulty of agricultural work. An object of one aspect of the present invention is to implement an estimation device or the like that calculates the difficulty of agricultural work for each piece of land and estimates the worker's skill level based on the calculated difficulty.

Means for Solving the Problem

[0006] An estimation device according to one aspect of the present invention is an estimation device for estimating the skill level of an operator in remote operation of an agricultural machine, and includes: an efficiency calculation unit that calculates the work efficiency of a first agricultural machine using land information of the land that is the target of a first agricultural machine, which is the most recently performed agricultural machine, and the work results of the first agricultural machine performed by a first operator, who is the operator who performed the first agricultural machine; a difficulty calculation unit that calculates a first difficulty level, which is the difficulty level of the first agricultural machine, as a value that fluctuates according to the level of work efficiency, and obtains a third difficulty level by correcting a second difficulty level, which is the difficulty level of the agricultural machine calculated before the completion of the first agricultural machine, by the first difficulty level; and a skill level estimation unit that estimates a first skill level, which is the skill level of the first operator, based on the work efficiency and the third difficulty level, and obtains a third skill level by correcting a second skill level, which is the skill level of the first operator estimated before the completion of the first agricultural machine, by the first skill level.

[0007] An estimation method according to one aspect of the present invention is an estimation method for estimating the skill level of an operator in remote operation of an agricultural machine, the method comprising: an efficiency calculation step of calculating the work efficiency of a first agricultural machine using land information of the land that is the target of a first agricultural machine, which is the most recently performed agricultural machine, and the work results of the first agricultural machine performed by a first operator, who is the operator who performed the first agricultural machine; a difficulty calculation step of calculating a first difficulty level, which is the difficulty level of the first agricultural machine, as a value that fluctuates according to the level of work efficiency, and obtaining a third difficulty level by correcting a second difficulty level, which is the difficulty level of the agricultural machine calculated before the completion of the first agricultural machine, by the first difficulty level; and a skill level estimation step of estimating a first skill level, which is the skill level of the first operator, based on the work efficiency and the third difficulty level, and obtaining a third skill level by correcting a second skill level, which is the skill level of the first operator estimated before the completion of the first agricultural machine, by the first skill level.

[0008] An estimation system according to one aspect of the present invention is an estimation system for estimating the skill level of an operator in remote operation of an agricultural machine, the estimation system comprising a database and an estimation device for acquiring information from the database, the estimation device including: an efficiency calculation unit that calculates the work efficiency of the first agricultural work using land information of the land that is the target of the first agricultural work, which is the most recently performed agricultural work, and the work results of the first agricultural work performed by the first operator, who is the operator who performed the first agricultural work; a difficulty calculation unit that calculates a first difficulty level, which is the difficulty level of the first agricultural work, as a value that fluctuates according to the level of work efficiency, and acquires a third difficulty level by correcting a second difficulty level, which is the difficulty level of the agricultural work stored in the database before the completion of the first agricultural work, by the first difficulty level; and a skill level estimation unit that estimates the first skill level, which is the skill level of the first operator, based on the work efficiency and the third difficulty level, and acquires a third skill level by correcting a second skill level, which is the skill level of the first operator, which was stored in the database before the completion of the first agricultural work, by the first skill level.

[0009] A data structure according to one aspect of the present invention is a data structure that includes information used in an estimation device for estimating the proficiency of an operator in remote operation of an agricultural machine, the estimation device storing the following: land information of the land that is the target of the most recently performed agricultural machine, the first agricultural machine, and the work results of the first agricultural machine performed by the first operator, the operator who performed the first agricultural machine; a second difficulty level, which is the difficulty level of the agricultural machine before completion of the first agricultural machine; and a second proficiency level, which is the proficiency level of the first operator before completion of the first agricultural machine. The estimation device includes the information to perform the following processing: calculate the first difficulty level as a value that fluctuates according to the level of work efficiency; obtain a third difficulty level by correcting the second difficulty level by the first difficulty level; estimate the first proficiency level based on the work efficiency and the third difficulty level; and obtain a third proficiency level by correcting the second proficiency level by the first proficiency level.

[0010] Each aspect of the present invention may be implemented by a computer, in which case a control program for the estimation device that enables the computer to implement the estimation device by operating the computer as each part (software element) of the estimation device, and a computer-readable recording medium on which the program is recorded, also fall within the scope of the present invention. [Effects of the Invention]

[0011] According to one aspect of the present invention, it is possible to realize an estimation device that calculates the difficulty level of agricultural work for each plot of land and estimates the skill level of workers based on that difficulty level. [Brief explanation of the drawing]

[0012] [Figure 1] This is a block diagram showing the functional blocks of the estimation system according to Embodiment 1. [Figure 2] This is a schematic diagram showing the functional overview of the estimation system according to Embodiment 1. [Figure 3] This is a schematic diagram showing an example of a database included in the estimation system according to Embodiment 1. [Figure 4] This flowchart shows an example of the processing flow performed by the estimation device according to Embodiment 1. [Figure 5] This flowchart shows an example of the processing flow for the difficulty calculation step. [Figure 6] This flowchart shows an example of the processing flow for the proficiency estimation step. [Figure 7] This is a schematic diagram visually illustrating land information on a field levee and an example of the results of agricultural work. [Figure 8] This is a block diagram showing the functional blocks of the estimation system according to Embodiment 2. [Figure 9] This flowchart shows an example of the processing flow performed by the estimation device according to Embodiment 2. [Figure 10] This is a schematic diagram showing an example of a presentation mode for presenting candidates for agricultural work using the estimation device according to Embodiment 2. [Figure 11]It is a block diagram showing functional blocks of an estimation system according to Embodiment 3. [Figure 12] It is a flow chart showing an example of a processing flow executed by an estimation device according to Embodiment 3. [Figure 13] It is a schematic diagram visually showing an example of each work route history in a plurality of farm works by the estimation device according to Embodiment 3. [Figure 14] It is a schematic diagram visually showing an example of a result obtained by weighting the work route history with a second proficiency level. [Figure 15] It is a schematic diagram visually showing an example of an optimal route estimated by the estimation device according to Embodiment 3. MODE FOR CARRYING OUT THE INVENTION

[0013] (Embodiment 1) Hereinafter, one embodiment of the present invention will be described in detail. An estimation system 1 according to one embodiment of the present invention estimates a remote operation proficiency level of an operator for a farm work performed by remote operation of a work machine. The estimation system 1 is also a system that calculates the difficulty level of farm work for each piece of land and uses the difficulty level to estimate the proficiency level.

[0014] As shown in FIG. 1, in the present embodiment, the estimation system 1 may be described by taking as an example a case where the work machine is a mower 10, the farm work is mowing work, and the land that is the object of the farm work is a levee. In this specification, the difficulty level of farm work on a levee is described as indicating the difficulty level of mowing work, and for the sake of simplifying the description, it is not assumed that other types of farm work are performed on the levee. However, depending on the type of land, it may be assumed that a plurality of types of farm work are performed on one piece of land. In this case, the difficulty level of farm work on the land may be managed for each type of farm work.

[0015] The agricultural work to which Estimated System 1 can be applied is not limited to mowing. Agricultural work may include, but is not limited to, pesticide / herbicide application, fertilization, sowing, soil preparation, land leveling, puddling, compost spreading, plowing, furrowing, intertillage and weeding, harvesting, packaging, rice planting, transplanting, transportation, growth surveys, and wildlife damage control. Furthermore, the implements targeted by Estimated System 1 are not particularly limited as long as they are remotely operated implements and may be appropriately selected depending on the type of agricultural work. The implements may include, but are not limited to, mowers, drones, unmanned helicopters, tractors, cultivators, rice transplanters, boom sprayers, speed sprayers, combines, harvesters, roll balers, or transport vehicles. Agricultural work may be performed by remotely controlling one of these implements, or by using two or more implements in combination, with at least one of them being remotely controlled. Similarly, the land on which the agricultural work is performed may be appropriately selected depending on the type of agricultural work.

[0016] The land used for agricultural work is not particularly limited, but examples include land with sloping surfaces such as field levees, where remote operation of agricultural machinery is considered difficult. Estimation System 1 can be suitably used on such land. In land where remote operation of agricultural machinery is difficult, the operator's skill level in remote operation has a significant impact on work efficiency. Therefore, accurately estimating the operator's skill level in remote operation using Estimation System 1 is effective in improving work efficiency.

[0017] As shown in Figure 2, the estimation system 1 includes a worker database 31 and a land database 32, which will be described later. The estimation system 1 calculates the difficulty of agricultural work for each plot of land, using the skill level information of each worker stored in the worker database 31 and the difficulty level of agricultural work for each plot of land stored in the land database 32. The estimation system 1 also calculates the difficulty level of agricultural work for each plot of land based on the results of the work performed by the worker on that plot of land. The estimation system 1 may also reflect the skill level of the worker in calculating the difficulty level of agricultural work.

[0018] It is preferable that the estimation system 1 acquires such skill levels and difficulty levels each time agricultural work is performed by a worker. In this configuration, the estimation system 1 can always update the worker skill level information and land difficulty level information to the latest information. Figure 2 shows a schematic diagram illustrating the process by which the skill level of each worker and the difficulty level of agricultural work for each piece of land are corrected each time agricultural work is performed, but the numerical values ​​are merely examples.

[0019] According to the above configuration, users of Estimation System 1 can appropriately select workers suitable for agricultural work on the target land based on information about workers obtained through remote operation of agricultural work. This makes it possible to effectively utilize land by, for example, making it easier and more efficient to manage fallow land or abandoned farmland. Such effects also contribute to achieving goals such as "resilient agriculture" included in Goal 2 and "creating productive jobs" included in Goal 8 of the United Nations' Sustainable Development Goals (SDGs).

[0020] <Grass trimmer 10> The grass trimmer 10 is a work machine that can perform grass cutting work on levees and other areas by remote control. The grass trimmer 10 is equipped with a sensing device 11, a machine storage device 12, and a machine communication device 13.

[0021] The sensing device 11 may be a sensor capable of detecting the position of the grass mower 10 on the ridge. The sensing device 11 may be, for example, a sensor compatible with a GNSS (Global Navigation Satellite System) positioning system, and specifically a GPS (Global Positioning System) sensor. From the viewpoint of accurately understanding the work history of remote operation by the grass mower 10, it is preferable that the sensing device 11 is compatible with a high-precision positioning system such as an RTK (Real Time Kinematic)-GNSS positioning system.

[0022] The machine's internal memory device 12 is a memory device for storing information acquired or generated by the lawnmower 10. The machine's internal memory device 12 may be, for example, a ROM (Read Only Memory), an HDD (Hard Disk Drive), or an SSD (Solid State Drive).

[0023] The aircraft communication device 13 is a communication device for communicating between the lawnmower 10 and the estimation system 1. The aircraft communication device 13 may be configured to communicate with external devices other than the estimation system 1. The aircraft communication device 13 is preferably capable of wireless communication, but may also be capable of wired communication. The aircraft communication device 13 may be capable of communication via the Internet, or may be configured to only allow communication within a predetermined closed network.

[0024] The remote operation of the lawnmower 10 may be performed by receiving information from an operating terminal (not shown) operated by an operator via the machine communication device 13. This operating terminal may be a portable terminal such as a smartphone, a dedicated controller, or a computer terminal such as a desktop PC (Personal Computer) or notebook PC.

[0025] <Estimation System 1> The estimation system 1 comprises an estimation device 20, a server storage device 30 containing a database from which the estimation device 20 acquires information, and a server communication device 40. In this embodiment, the estimation system 1 is described as being configured as a server device that performs information processing. However, the form of the estimation system 1 is not limited to a server device. For example, the estimation device 20 and the server storage device 30 may be independent network devices or the like, configured to send and receive information from each other via a communication device (not shown).

[0026] Furthermore, the brush cutter 10 may be configured as one of the devices included in the estimation system 1. When the brush cutter 10 is configured as one of the devices included in the estimation system 1, it is easy to optimize the format of the information transmitted from the brush cutter 10 to the estimation system 1 for the information processing performed by the estimation system 1. The brush cutter 10 may be a work machine that is sold independently of the estimation system 1 and is configured to transmit information to the estimation system 1.

[0027] The server storage device 30 is a storage device for storing information acquired or generated by the estimated system 1. The server storage device 30 may be, for example, a ROM (Read Only Memory), an HDD (Hard Disk Drive), or an SSD (Solid State Drive).

[0028] The server storage device 30 includes a worker database 31 and a land database 32. The worker database 31 and the land database 32 are databases from which the estimation device 20 acquires information. As shown in Figure 3, the worker database 31 stores the skill level of each worker. Preferably, the worker's skill level is stored in a value estimated for each agricultural task (W) performed in the past, and associated with the work results of that agricultural task. The worker database 31 may also store information such as the worker's attributes or schedule, and information such as the worker's work history.

[0029] The land database 32 stores the difficulty level of agricultural work for each plot of land (L). Preferably, the difficulty level of agricultural work for a plot of land is stored in a value calculated for each agricultural work performed in the past, and associated with the results of that work. The land database 32 may also store land information, including topographic information of the land that is the target of agricultural work. The server storage device 30 may consist of multiple storage devices; for example, the worker database 31 and the land database 32 may be stored in different storage devices (not shown).

[0030] In Figure 3, agricultural tasks are simply represented as W1-W20, workers as O1-O3, and land as L1-L7, but this is merely an example. The number of agricultural tasks, workers, and land plots stored in the worker database 31 and land database 32 is not particularly limited.

[0031] The server communication device 40 is a communication device for communication between the lawnmower 10 and the estimation system 1. The server communication device 40 may be configured to communicate with external devices other than the lawnmower 10. The server communication device 40 is preferably capable of wireless communication, but may also be capable of wired communication. The server communication device 40 may be capable of communication via the Internet, or may be configured to only allow communication within a predetermined closed network.

[0032] In estimation system 1, estimation device 20 and server storage device 30 may each be equipped with communication devices (not shown), and may send and receive information from each other via these communication devices.

[0033] <Estimation device 20> The estimation device 20 functions as a control device that comprehensively controls the estimation system 1. The estimation device 20 may be implemented by a general-purpose integrated circuit such as a CPU (Central Processing Unit), or it may be implemented as a dedicated logic circuit. The estimation device 20 includes an efficiency calculation unit 21, a difficulty calculation unit 22, and a proficiency estimation unit 23 as functional blocks.

[0034] (Efficiency calculation unit 21) The efficiency calculation unit 21 calculates the work efficiency of the first agricultural work using the land information of the land that is the target of the first agricultural work, which is the most recently performed agricultural work, and the work results of the first agricultural work performed by the first worker, who is the worker who performed the first agricultural work.

[0035] Preferably, the efficiency calculation unit 21 calculates the work efficiency of a farming task each time it obtains the results of the farming task performed by the worker. In this case, the first farming task may be the most recently performed farming task that corresponds to the obtained work results.

[0036] On the other hand, the efficiency calculation unit 21 may calculate the work efficiency for each work result after acquiring multiple work results. In this case, the first agricultural work may be the agricultural work corresponding to each work result. For example, when multiple workers perform agricultural work on different ridges almost simultaneously, and the efficiency calculation unit 21 acquires the work results for each agricultural work almost simultaneously. In such a case, each agricultural work corresponding to each work result can be said to be the most recently performed agricultural work.

[0037] The efficiency calculation unit 21 may obtain the results of the first farming operation directly from the brush cutter 10, or from the server storage device 30. If the results of the first farming operation are obtained from the server storage device 30, the brush cutter 10 may transmit the results of the first farming operation to the server storage device 30 via the machine communication device 13 for storage.

[0038] The work results of the first agricultural operation acquired by the efficiency calculation unit 21 may be raw data of the detection results of the sensing device 11 acquired from the brush cutter 10, or the raw data may be processed information. This processing may be performed, for example, as one of the functions of the sensing device 11, or it may be performed by the estimation device 20 as preprocessing before processing by the efficiency calculation unit 21. The method of processing the detection results is not particularly limited and may be a general method.

[0039] The results of the first farming operation may include the working time from the start to the end of the first farming operation, a work route history showing the path the brush cutter 10 traveled during the first farming operation, and information such as the model information of the brush cutter 10 used in the first farming operation. The efficiency calculation unit 21 may use at least one of these pieces of information when calculating the work efficiency of the first farming operation. The efficiency calculation unit 21 may, for example, calculate the work efficiency based on the working time. When calculating the work efficiency of the first farming operation based on the working time, the efficiency calculation unit 21 may calculate the work efficiency of the first farming operation by comparing the actual working time with a standard working time set in advance for each ridge.

[0040] Furthermore, the efficiency calculation unit 21 may use the completed work area, unworked area, and overlapping work area in the first agricultural operation to calculate work efficiency. The completed work area, unworked area, and overlapping work area can be calculated, for example, by calculating the total work area on the ridge from the land information, and then calculating from the total work area, the work route history, and the machine information included in the work results. More specifically, the completed work area, unworked area, and overlapping work area can be calculated, for example, based on the size and work range of the brush cutter 10 included in the machine information, and the work route history.

[0041] Thus, the efficiency calculation unit 21 may calculate work efficiency using the following (1) and (2); (1) Work time included in the work results, (2) The completed area, unworked area, and overlapping area for the first agricultural operation, calculated using the work route history and machine model information included in the work results, and the total work area on the land where the first agricultural operation is performed, calculated from the land information.

[0042] Furthermore, the efficiency calculation unit 21 may calculate work efficiency after adding or subtracting a correction value (a predetermined value) to the values ​​of work time, etc., used to calculate work efficiency. For example, if multiple entities are operating the estimation system 1, it is possible that the criteria for calculating work efficiency may differ for each operating entity. In that case, while the proficiency level estimated by the estimation system 1 can be compared for each worker within a single operating entity, it may not be suitable for comparisons between multiple operating entities.

[0043] In this case, the efficiency calculation unit 21 may add or subtract a correction value to at least one of the work time, unworked area, and overlapping work area used in calculating work efficiency, in order to equalize the differences in the work efficiency calculation criteria for each operating entity. The correction value may be set as appropriate by the operating entity of the estimation system 1, for example.

[0044] Thus, the efficiency calculation unit 21 may calculate work efficiency by adding or subtracting predetermined values ​​from the work time, unworked area, and overlapping work area, respectively. In this case, the efficiency calculation unit 21 may add or subtract at least one of the work time, unworked area, and overlapping work area. Furthermore, if the efficiency calculation unit 21 corrects two or more of the work time, unworked area, and overlapping work area, it may, for example, add one or two of them and subtract the others.

[0045] (Difficulty Calculation Section 22) The difficulty level calculation unit 22 calculates the first difficulty level, which is the difficulty level of the first farming operation, as a value that fluctuates according to the level of work efficiency in the first farming operation. The "first difficulty level" is the difficulty level calculated based on the results of the most recently performed first farming operation.

[0046] In this specification, "difficulty level" may be an index representing the difficulty of mowing grass on the ridges of fields. The difficulty level of agricultural work may be set as a value between 1 and 0, where a higher number indicates greater difficulty, for example, 1 being the most difficult and 0 being the easiest. Alternatively, the difficulty level of agricultural work may be set as a value where a higher number indicates greater ease.

[0047] The difficulty calculation unit 22 obtains a third difficulty level by correcting the second difficulty level, which is the difficulty level of agricultural work of the same type as the first agricultural work and was calculated before the completion of the first agricultural work, by the first difficulty level. An agricultural work of the same type as the first agricultural work is one in which the land and work content are substantially the same as those of the first agricultural work. For example, if the first agricultural work was mowing grass on a field ridge, the second difficulty level may be the difficulty level of grass mowing work previously calculated for that field ridge. In this case, the work area on the field ridge and the specific content of the grass mowing work do not need to be exactly the same.

[0048] The "second difficulty level" is the difficulty level of agricultural work of the same type as the first agricultural work that was performed before the completion of the first agricultural work, and may be, for example, the difficulty level stored in the land database 32 of the server storage device 30. The second difficulty level may be stored for each plot of land that is the subject of agricultural work, and it is preferable that the land database 32 stores together the second difficulty levels calculated for each plot of land based on the results of agricultural work performed by multiple workers.

[0049] The second difficulty level is preferably a value previously calculated by estimation system 1, but is not limited to this. For example, it may be a value initially set for each ridge, or it may be a value calculated by a method other than the estimation method performed by estimation system 1.

[0050] The "third difficulty level" is a value obtained by correcting the second difficulty level by the first difficulty level, and may be an indicator of the current (latest) difficulty level of the agricultural work in land that is subject to the same type of agricultural work as the first agricultural work. The method of correcting the second difficulty level by the first difficulty level is not particularly limited. As a correction method, for example, the average value of the second difficulty level and the first difficulty level may be obtained. Alternatively, if the first difficulty level is greater than the second difficulty level (or the average value if there are multiple second difficulty levels), a predetermined value may be added to the second difficulty level, and if it is smaller, a predetermined value may be subtracted from the second difficulty level.

[0051] Furthermore, it is preferable that the second difficulty level used in calculating the third difficulty level includes multiple difficulty levels calculated for each grass-cutting operation performed on the same ridge prior to the first agricultural operation. This is because the difficulty level of grass-cutting operations on the same ridge is not expected to change significantly over time, so it is preferable to obtain as many second difficulty levels as possible by going back in time. Figure 3 shows an example in which the third difficulty level is calculated as the average value of all previously calculated values ​​for the second difficulty level of agricultural operations on each plot of land stored in the land database 32. Alternatively, the second difficulty level used in calculating the third difficulty level may be a single difficulty level calculated for a specific agricultural operation, such as the earliest one.

[0052] The difficulty calculation unit 22 may store the acquired first and third difficulty levels in the land database 32. In the land database 32 shown in Figure 3, the difficulty value of each plot of land stored in correspondence with agricultural work is the first difficulty level estimated by the difficulty calculation unit 22. The first difficulty level stored in the land database 32 may be used as the second difficulty level in future processing by the estimation device 20.

[0053] (Proficiency level estimation section 23) The proficiency estimation unit 23 estimates the first proficiency level, which is the proficiency level of the first worker, based on work efficiency and the third difficulty level. The "first proficiency level" is the proficiency level of the first worker in remotely operating the brush cutter 10, estimated based on the results of the most recent first agricultural work performed.

[0054] In this specification, "skill level" may be an index indicating the operator's ability to remotely control a work machine such as a brush cutter 10. The operator's skill level may be set as a value between 1 and 0, where a higher number indicates higher remote control skill, for example, 1 indicating the highest skill level and 0 indicating the lowest skill level. Alternatively, the operator's skill level may be set as a value where a higher number indicates lower remote control skill.

[0055] The proficiency estimation unit 23 estimates the first proficiency level using the work efficiency of the first worker as well as the third difficulty level, which is the most recent difficulty level of the first agricultural work on the land targeted for the first agricultural work. Therefore, the proficiency estimation unit 23 can accurately estimate the proficiency level of the first worker in remotely operating the brush cutter 10 according to the type of first agricultural work and the characteristics of the land.

[0056] The method for estimating the first level of proficiency is not particularly limited. For example, the proficiency estimation unit 23 may add a value to the work efficiency that increases with the value of the third difficulty level to obtain an estimated value of the first level of proficiency. Alternatively, the proficiency estimation unit 23 may add a predetermined value to the work efficiency when the value of the third difficulty level exceeds a predetermined threshold to obtain an estimated value of the first level of proficiency.

[0057] The proficiency estimation unit 23 obtains a third proficiency level, which is the second proficiency level of the first worker estimated before the completion of the first agricultural work, by correcting it with the first proficiency level.

[0058] "Second skill level" is the skill level of the first worker with the same type of work machine used in the first farm work, performed before the completion of the first farm work, and may be, for example, the skill level stored in the worker database 31 of the server storage device 30. The same type of work machine may be the same work machine, or it may be a work machine with the same function. For example, a work machine with a different model number but substantially the same function as the brush cutter 10 can be said to be the same type of work machine as the brush cutter 10. The second skill level acquired by the skill level estimation unit 23 may be the skill level estimated when the combination of worker and work machine is the same as in the first farm work, and may include, for example, the skill level estimated based on the results of farm work on land different from the first farm work.

[0059] The second skill level is preferably the first skill level previously calculated by the estimation system 1 and stored in the worker database 31, but is not limited to this. The second skill level may be, for example, a value initially set for each worker or work machine, or a value calculated by a method other than the estimation method performed by the estimation system 1.

[0060] "Third skill level" is a value obtained by correcting the second skill level by the first skill level, and may be an indicator of the current (latest) skill level of the first operator in remotely operating the brush cutter 10. The method of correcting the second skill level by the first skill level is not particularly limited. As a correction method, for example, the average value of the second skill level and the first skill level may be obtained. Alternatively, if the first skill level is greater than the second skill level, a predetermined value may be added to the second skill level, and if it is less than the second skill level, a predetermined value may be subtracted from the second skill level.

[0061] The second level of proficiency used to acquire the third level of proficiency is preferably the proficiency estimated in the most recent agricultural work performed before the first agricultural work. It is assumed that the operator's proficiency will increase as they gain experience in remotely operating the brush cutter 10. Therefore, it is preferable to use a relatively recent estimate of the second level of proficiency, rather than going too far back, when acquiring the third level of proficiency, which is the most recent proficiency of the first operator.

[0062] Figure 3 shows an example in which, for each worker stored in the worker database 31, the skill level estimated from the most recent farm work is used as the first skill level, and the skill level estimated from the farm work immediately preceding that is used as the second skill level to obtain the third difficulty level. The second skill level used to obtain the third skill level may be multiple skill levels estimated from at least the most recent few farm work sessions.

[0063] The proficiency estimation unit 23 may further correct the second proficiency level of at least one of the second workers, who is a different worker from the first worker, based on the third difficulty level. "Second worker" refers to a worker different from the first worker whose proficiency level and other information is stored in the worker database 31 of the server storage device 30.

[0064] The proficiency estimation unit 23 may, in order to correct the second proficiency level, obtain the work efficiency value of the corresponding farm work for each second proficiency level from the server storage device 30, and recalculate the second proficiency level based on the obtained work efficiency and the latest third difficulty level. In this way, the proficiency estimation unit 23 may correct the second proficiency level by recalculating the proficiency level using the same method as for calculating the first proficiency level.

[0065] Furthermore, the proficiency estimation unit 23 may obtain the third proficiency level of at least one of the second workers from the corrected second proficiency level and update the third proficiency level stored in the worker database 31. When obtaining the third proficiency level of the first worker, the proficiency estimation unit 23 obtains the third proficiency level from the first proficiency level and the second proficiency level. Similarly, when obtaining the third proficiency level of the second worker, the proficiency estimation unit 23 may obtain the third proficiency level from two or more second proficiency levels. For example, when the proficiency estimation unit 23 obtains the third proficiency level from two second proficiency levels, it is preferable to obtain the third proficiency level from the second proficiency levels corresponding to the two most recent agricultural operations.

[0066] Thus, when the third difficulty level is updated, it is preferable for the proficiency estimation unit 23 to correct the second proficiency level stored in the worker database 31 for all second workers who have experience working in the area where the third difficulty level has been updated. Furthermore, it is preferable for the proficiency estimation unit 23 to update the third proficiency level of all second workers to the latest value using the corrected second proficiency level.

[0067] This allows the latest proficiency level information for the first worker and all second workers, which is the third proficiency level, to be corrected to a value based on the latest difficulty level information for the same type of farm work as the first farm work, which is the third difficulty level. Therefore, the proficiency estimation unit 23 can always maintain a highly accurate estimate of the third proficiency level of each worker stored in the worker database 31, based on the latest information on the third difficulty level.

[0068] The proficiency estimation unit 23 may store the acquired first and third proficiency levels in the worker database 31. In the worker database 31 shown in Figure 3, the proficiency level values ​​of each worker stored in correspondence with agricultural work are the first proficiency levels estimated by the proficiency estimation unit 23. The first proficiency levels stored in the worker database 31 may be used as second proficiency levels in future processing by the estimation device 20.

[0069] <Estimation method using estimation device 20> The estimation method according to this embodiment is an estimation method for estimating the skill level of an operator in remotely controlling agricultural machinery such as a brush cutter 10. An example of implementing the estimation method according to this embodiment using the estimation system 1 is described below.

[0070] As shown in Figure 4, first the efficiency calculation unit 21 obtains the work results of the first agricultural work performed by the first worker from the grass cutter 10 (S1). Having obtained the work results, the efficiency calculation unit 21 obtains land information of the ridge that is the target of the first agricultural work from the land database 32 (S2).

[0071] The work results acquired by the efficiency calculation unit 21 include, for example, the date and time of the first farm work, the work time from start to finish, a work route history showing the path the brush cutter 10 took during the first farm work, and information such as the model information of the brush cutter 10 used in the first farm work. The start time of the first farm work may be, for example, the time when the brush cutter 10 entered the area of ​​the ridge that is the target of the first farm work. The end time of the first farm work may be, for example, the time when the brush cutter 10 left the area of ​​the ridge.

[0072] Furthermore, as shown in Figure 7, the land information may include information on the area of ​​the area to be targeted for the first agricultural work (work area), standard work efficiency, and standard work time. Standard work efficiency may be, for example, a standard value for the work area per unit time. Standard work time may be a standard value for the work time from the start to the end of the work.

[0073] As shown in Figure 7, the efficiency calculation unit 21 can determine the areas on the ridge where mowing has been completed and areas where mowing has not been completed by combining the model information and work path history of the mower 10 with land information. The efficiency calculation unit 21 can also determine the areas where mowing has been repeated in the areas where mowing has been completed. From the results obtained in this way, the efficiency calculation unit 21 may calculate the area where work has been completed, the area where work has not been done, and the area where work has been repeated on the ridge.

[0074] Furthermore, the land information may also include information such as allowable work delay time, allowable unworked area, or allowable overlapping work area, as correction value information used to calculate work efficiency. The efficiency calculation unit 21 may determine whether or not such correction value information, such as allowable work delay time, is included in the land information (S3).

[0075] If the efficiency calculation unit 21 determines that the land information includes correction value information (Yes in S3), it adds or subtracts a predetermined correction value to at least one of the working time, unworked area, and overlapping work area (S4). Specifically, if the working time exceeds the standard working time, the efficiency calculation unit 21 may subtract the allowable work delay time from the working time. The efficiency calculation unit 21 may also subtract the allowable unworked area from the unworked area, or subtract the allowable overlapping work area from the overlapping work area. The allowable unworked area may be, for example, an area where mowing is permitted, or an area set on the assumption that there is a certain range within the ridge where work is unnecessary for some reason.

[0076] After processing in step S4, or if it is determined in step S3 that the land information does not contain correction value information (No in S3), the efficiency calculation unit 21 calculates the work efficiency of the first farm work using the land information and work results (S5, efficiency calculation step). The calculation criteria for work efficiency calculated by the efficiency calculation unit 21 are not particularly limited. For example, the efficiency calculation unit 21 may calculate at least one of the indicators showing the speed, completeness, overlap, and efficiency of the first farm work as work efficiency.

[0077] Speed ​​= Standard work time / Actual work time; Completeness = area completed / area covered; Redundancy = 1.00-(Duplicated work area / Work completed area); Efficiency = Effective Efficiency / Standard Work Efficiency (Effective efficiency = (Area of ​​work completed - Area of ​​overlapping work) / Working time).

[0078] In this case, the efficiency calculation unit 21 may calculate the speed and efficiency with a maximum value of 1.00, or it may calculate them with a value greater than 1.00.

[0079] For example, if the work area included in the land information is 565.5 m² 2 The standard work efficiency is 22.2m 2The work time was 25 mins, the work time included in the results was 32 mins, and the completed work area was 428.5 m². 2 The overlapping work area is 159.0 m². 2 Let's assume that this is the case. In this case, the speed is 0.78, the completeness is 0.76, the redundancy is 0.63, and the efficiency is 0.38. The efficiency calculation unit 21 may calculate work efficiency using one of these indicators, or it may calculate work efficiency using two or more of them. Also, when the efficiency calculation unit 21 calculates work efficiency using two or more of these indicators, it may calculate work efficiency as a value obtained by statistically processing these indicators. For example, the efficiency calculation unit 21 may obtain the average value of each indicator used, or it may multiply the values ​​of each indicator.

[0080] Next, the difficulty calculation unit 22 performs the difficulty calculation steps shown in Figure 5 (S6). The difficulty calculation unit 22 calculates the first difficulty level from the work efficiency calculated by the efficiency calculation unit 21 (S61). The first difficulty level may be a value calculated solely from work efficiency, or it may be a value calculated by adding the skill level of the first worker who performed the first agricultural work to the work efficiency.

[0081] The first difficulty level may be calculated, for example, by the following formula if the work efficiency is obtained as a value between 0 and 1; Difficulty Level 1 = 1 - Work Efficiency If the difficulty calculation unit 22 is configured to calculate the first difficulty level using such a formula, the more difficult it is to obtain a high work efficiency value in a given piece of land, the larger the first difficulty level can be calculated.

[0082] Next, the difficulty calculation unit 22 obtains the second difficulty level from the land database 32 (S62). The second difficulty level obtained by the difficulty calculation unit 22 may include the first difficulty level calculated for all agricultural work previously performed on the same ridge as the first agricultural work. The difficulty calculation unit 22 corrects the second difficulty level by the first difficulty level and obtains the third difficulty level (S63). For obtaining the third difficulty level, the difficulty calculation unit 22 may statistically process the first difficulty level calculated this time and all the obtained second difficulty levels to obtain the third difficulty level. For example, the difficulty calculation unit 22 may obtain the third difficulty level by obtaining the average value of the first difficulty level calculated this time and all the obtained second difficulty levels.

[0083] The third difficulty level may be calculated, for example, by the following formula: Third difficulty level = (1 - work efficiency + second difficulty level) / 2 In this case, "1-Work Efficiency" may be an example of the first difficulty level, as described above. Furthermore, the second difficulty level may be the second difficulty level corresponding to a single farming task on the land subject to the calculation of the third difficulty level, or it may be the average value of the second difficulty levels corresponding to multiple farming tasks.

[0084] Next, the proficiency estimation unit 23 performs the proficiency estimation step shown in Figure 6 (S7). The proficiency estimation unit 23 estimates the first proficiency level of the first worker from the first worker's work efficiency and the third difficulty level (S71). The first proficiency level can be calculated, for example, by the following formula: Skill Level 1 = Work Efficiency / (Difficulty Level 1 - Difficulty Level 3).

[0085] Here, for example, if work efficiency is calculated as four values: speed, completeness, redundancy, and efficiency, the proficiency estimation unit 23 may use a value obtained by statistically processing the values ​​of these four indicators as the work efficiency value for determining the first proficiency level. For example, the proficiency estimation unit 23 may use the average value of these four indicators as the work efficiency value for determining the first proficiency level.

[0086] Next, the proficiency estimation unit 23 obtains the second proficiency level of the first worker from the worker database 31 (S72). Here, it is preferable that the second proficiency level obtained by the proficiency estimation unit 23 is the proficiency level estimated from the results of the farm work performed by the first worker using the brush cutter 10 before the first farm work. The proficiency estimation unit 23 corrects the second proficiency level by the first proficiency level and obtains the third proficiency level (S73). For obtaining the third proficiency level, the proficiency estimation unit 23 may obtain the third proficiency level by statistically processing the first proficiency level calculated this time and the second proficiency level obtained. For example, the proficiency estimation unit 23 may obtain the third proficiency level by obtaining the average value of the first proficiency level calculated this time and the second proficiency level obtained.

[0087] Next, the proficiency estimation unit 23 corrects the second proficiency of the second worker, who is a worker other than the first worker and is stored in the worker database 31, based on the third difficulty level (S74). The method for correcting the second worker's second proficiency may be, for example, a method of recalculating the second proficiency using the work efficiency of the agricultural work corresponding to the second proficiency obtained from the worker database 31 and the latest third difficulty level. The specific method in this case is as described in the explanation of step S71.

[0088] Furthermore, the proficiency estimation unit 23 may update the third proficiency level for each second worker using the corrected second proficiency level (S75). The method for obtaining the third proficiency level using the second proficiency level may be the same as the method described in step S73, except that two or more corrected second proficiency levels are used instead of using the first and second proficiency levels.

[0089] The estimation device 20 may store the obtained first and third skill levels in the worker database 31 (S8). The estimation device 20 may store these skill levels all at once after completing the processes in steps S1 to S7. Alternatively, the estimation device 20 may store these skill levels at any time during the execution of the estimation method described above. Specifically, the skill level estimation unit 23 may store the first and third skill levels in the worker database 31 when they are estimated or acquired, respectively.

[0090] Furthermore, the estimation device 20 may store the obtained first difficulty level and third difficulty level in the land database 32 (S9). The estimation device 20 may store these difficulty levels all at once after completing the processes in steps S1 to S7. Alternatively, the estimation device 20 may store this information as appropriate during the execution of the estimation method described above. Specifically, the difficulty level calculation unit 22 may store the first difficulty level and third difficulty level in the land database 32 when they are calculated or acquired, respectively.

[0091] Furthermore, the estimation device 20 may also store information such as the obtained work results and work efficiency in the server storage device 30 as appropriate (S10).

[0092] <Data structure> The data structure of the server storage device 30 included in the estimation system 1 according to this embodiment is also included in one aspect of the present invention. This data structure is a data structure that includes information used in an estimation device 20 for estimating the skill level of an operator in remote operation of agricultural work performed by remote operation of a work machine such as a lawnmower 10.

[0093] This data structure stores the work efficiency of the first farming task, the second difficulty level acquired by the estimation device 20 in the past (before the completion of the first farming task), and the second proficiency level acquired by the estimation device 20 in the past. Details of work efficiency, second difficulty level, and second proficiency level have already been explained in the sections on <Estimation Device> and <Estimation Method>, so the explanation is omitted here.

[0094] The data structure is calculated by the estimation device 20 as a value that varies depending on the level of work efficiency, and the third difficulty level is obtained by correcting the second difficulty level by the first difficulty level. The data structure also includes information for processing the first proficiency level to be estimated based on work efficiency and the third difficulty level, and the third proficiency level to be obtained by correcting the second proficiency level by the first proficiency level. The first difficulty level, third difficulty level, first proficiency level, and third proficiency level, as well as the specific methods for obtaining them, have already been explained in the sections on <Estimation Device> and <Estimation Method>, so the explanation is omitted here.

[0095] [Embodiment 2] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0096] <Overview of Estimation System 1a> As shown in Figure 8, the estimation system 1a according to this embodiment differs from the estimation system 1 according to Embodiment 1 in that it includes an estimation device 20a which includes a work time estimation unit 24 and a candidate presentation unit 25. The estimation system 1a calculates a fourth skill level, which is the skill level that serves as the standard for performing agricultural work on the land, based on the history of past agricultural work.

[0097] As an example of how this fourth level of proficiency can be utilized, estimation system 1a calculates the likelihood of a worker completing a farming task based on the fourth level of proficiency in that task on the land. This likelihood of completion can be used, for example, to estimate the time required for each worker to perform the farming task. Specifically, estimation system 1a can estimate the estimated time a worker will spend on a farming task by using the likelihood of completion and the standard time required for the farming task.

[0098] According to such estimation system 1a, for example, a client requesting agricultural work can determine the appropriate worker based on the fourth skill level. Similarly, workers can decide whether or not to accept the requested agricultural work based on the fourth skill level. Furthermore, estimation system 1a can calculate costs such as the compensation required for the agricultural work by using the estimated work time.

[0099] <Estimation device 20a and estimation method> The estimation device 20a functions as a control device that comprehensively controls the estimation system 1a. The estimation device 20a may be implemented by a general-purpose integrated circuit such as a CPU (Central Processing Unit), or it may be implemented as a dedicated logic circuit. In addition to the efficiency calculation unit 21, the difficulty calculation unit 22, and the proficiency estimation unit 23, the estimation device 20a includes a work time estimation unit 24 and a candidate presentation unit 25 as functional blocks.

[0100] The processing performed by the estimation device 20a will be described below in conjunction with the processing flow of the estimation method according to this embodiment shown in Figure 9. Note that the processing flow of the estimation method described in this embodiment may be executed following the processing flow of the estimation method according to Embodiment 1 shown in Figure 4, or it may be executed independently of the estimation method according to Embodiment 1.

[0101] (Work time estimation unit 24) The work time estimation unit 24 calculates the estimated work time for agricultural work performed by the worker. The estimated work time can be calculated based on the fourth skill level, which serves as the standard for performing agricultural work. First, let's explain the fourth skill level.

[0102] The fourth skill level may be a value that indicates the standard of skill necessary or desirable for performing the agricultural work in question. For example, the fourth skill level may be an indicator that if a worker's third skill level is equal to or higher than the fourth skill level of the agricultural work, that worker can perform the agricultural work without problems. Alternatively, the fourth skill level may also be an indicator that even if a worker's third skill level is less than the fourth skill level, the closer that worker's third skill level is to the fourth skill level, the higher the likelihood that that worker can complete the agricultural work.

[0103] The fourth skill level may be calculated by the skill level estimation unit 23. In this case, the skill level estimation unit 23 calculates a fourth skill level, which represents the skill level that serves as the standard for performing agricultural work, from the second skill levels of multiple workers. For example, the skill level estimation unit 23 refers to the worker database 31 and obtains the second skill level for each agricultural work performed in the past (S21). The skill level estimation unit 23 also refers to the land database 32 and obtains information on which land corresponds to each second skill level obtained (S22).

[0104] The proficiency estimation unit 23 may statistically process multiple second proficiency values ​​for each plot of land and calculate a fourth proficiency value. For example, the proficiency estimation unit 23 may calculate the average value of multiple second proficiency values ​​as the fourth proficiency value (S23). In addition, for plots of land where only one second proficiency value is stored, the proficiency estimation unit 23 may use the value of that second proficiency value as the fourth proficiency value.

[0105] The fourth skill level acquired by the work time estimation unit 24 does not have to be the one calculated by the skill level estimation unit 23. The fourth skill level may be, for example, a value initially set for each plot of land, or a value calculated by a method other than the estimation method executed by the estimation system 1a. The work time estimation unit 24 may store the acquired fourth skill level for each plot of land in the land database 32.

[0106] Next, the work time estimation unit 24 calculates the feasibility rate for completing the agricultural work for each worker by comparing the fourth skill level with the third skill level (S24). The comparison between the fourth skill level and the third skill level may be, for example, the ratio of the third skill level to the fourth skill level (third skill level / fourth skill level). In this case, if the worker's third skill level is greater than their fourth skill level, the feasibility rate for completing the work will be greater than 1. The feasibility rate for completing the work may be an indicator that, for example, a value closer to 1 indicates that the agricultural work can be completed in a time close to the standard work time for the agricultural work, and a larger value estimates that the work time required for the agricultural work is shorter.

[0107] Furthermore, the work time estimation unit 24 may calculate the work completion rate as a value that indicates only whether or not the agricultural work can be performed, such that it is 1 when the third skill level is 4 or higher, and 0 when the third skill level is less than 4.

[0108] The work time estimation unit 24 calculates the estimated work time based on the work completion rate and the standard work time for the land (S25, work time estimation step). The standard work time for the land may be a fixed value stored in the land database 32, or it may be a value statistically calculated based on the history of work time for agricultural work performed in the past. The estimated work time may be a value calculated by, for example, multiplying the reciprocal of the work completion rate by the standard work time, as follows: Estimated work time = (1 / work completion rate) x standard work time.

[0109] The estimated work time obtained in this way is calculated based on the fourth skill level of each plot of land and the third skill level of each worker. Therefore, the estimation device 20a can estimate the work time required for agricultural work with high accuracy based on the latest skill level information for each worker.

[0110] The work time estimation unit 24 may further calculate a corrected estimated work time by dividing the estimated work time by the average work time for each plot of land from multiple agricultural tasks previously performed by each worker (S26). Thus, the work time estimation unit 24 may be configured to use not only the worker's third skill level but also actual past work time in estimating work time, in which case the work time estimation unit 24 can estimate work time that takes into account and reflects the characteristics of the worker. The estimated work time estimated by the work time estimation unit 24 is an accurate estimate of the work time required for agricultural work. Therefore, the work time estimation unit 24 may calculate only the estimated work time and not calculate the corrected estimated work time unless otherwise specified.

[0111] Next, as an example of how the estimated work time or corrected estimated work time estimated by the work time estimation unit 24 is utilized, the processing of the candidate presentation unit 25 will be described below.

[0112] (Candidate presentation section 25) The candidate presentation unit 25 presents candidates suitable for agricultural work using the estimated work time estimated by the work time estimation unit 24. First, the candidate presentation unit 25 selects workers whose available work time is within the range of the estimated work time (S27). In other words, the candidate presentation unit 25 determines for each worker whether their available work time is within the range of the estimated work time. The worker's available work time may be, for example, information obtained from the worker's schedule stored in the worker database 31. Note that from step S27 onward, the candidate presentation unit 25 may use corrected estimated work time instead of estimated work time.

[0113] The candidate presentation unit 25, for example, compares the work period for agricultural work with the worker's schedule information and selects workers who can work within the set work period for agricultural work. The candidate presentation unit 25 may then obtain the time that the worker can work within the set work period from the worker's schedule as available work time and determine whether or not that available work time is within the range of estimated work time. The candidate presentation unit 25 may exclude workers other than those selected in step S27 from the candidates presented, and may assign label information indicating that they are unable to perform agricultural work.

[0114] Next, the candidate presentation unit 25 calculates an estimated remuneration for each worker by multiplying the set unit price for the farm work by the estimated working time (S28). The candidate presentation unit 25 also calculates the requested remuneration by multiplying the worker's requested unit price by the estimated working time (S29). The candidate presentation unit 25 determines whether the estimated remuneration is equal to or greater than the requested remuneration, and presents workers whose estimated remuneration is equal to or greater than the requested remuneration as candidates for farm work (S30, candidate presentation step). The candidate presentation unit 25 may exclude workers whose estimated remuneration is determined to be lower than the requested remuneration from the presentation, or it may present them with label information indicating that they are unsuitable for contracting farm work.

[0115] The set unit price for farm work may be, for example, a unit price per hour within the range that the client requesting the farm work can afford, or it may be a unit price per hour that is the market average for similar farm work. The candidate suggestion unit 25 can estimate the estimated compensation for farm work by multiplying such a set unit price for farm work by the estimated work time.

[0116] Furthermore, the worker's requested unit price may be stored in the worker database 31 as part of the worker's information, for example. If the worker's requested unit price is not set in advance, the candidate suggestion unit 25 may, for example, refer to the amount of compensation the worker received for the previous farm work to set the worker's unit price and use that unit price as the worker's requested unit price. By multiplying such a worker's requested unit price by the estimated work time, the candidate suggestion unit 25 can estimate the requested compensation that the worker will request for performing the farm work.

[0117] By making such a determination, the candidate presentation unit 25 can preemptively exclude workers whose estimated compensation is lower than the requested compensation from the list of candidates for agricultural work. As a result, the estimation device 20a can present only workers who are estimated to receive financial benefits from performing agricultural work as candidates. Therefore, the estimation device 20a can reduce the risk that, for example, after requesting agricultural work from a worker, the worker may refuse the request because the compensation amount is not agreeable, requiring the device to re-request the work from another worker.

[0118] The estimation device 20a may, for example, perform the work time estimation unit 24 and the candidate presentation unit 25 processing for each of the multiple clients requesting agricultural work, each with a different set unit price for the work, and present a summary of whether multiple potential workers can undertake the agricultural work from each client. The candidate presentation unit 25 may, for example, display combinations of workers and clients (corporations, etc.) in a matrix, as shown in Figure 10, and present whether each combination can perform the agricultural work and whether it can be undertaken.

[0119] Here, the candidate presentation unit 25 may indicate whether or not a worker can perform the agricultural work as "possible" if their available working time falls within the estimated working time range, and as "impossible" if their available time falls outside that range. Furthermore, regarding whether or not a worker can undertake the work if they are able to perform the agricultural work, the candidate presentation unit 25 may indicate as "possible" if their estimated compensation is equal to or greater than the requested compensation, and as "possible but not undertaking the work" if their estimated compensation is less than the requested compensation. Note that the candidate presentation method shown in Figure 10 is merely an example, and the candidate presentation unit 25 may present candidates in other ways.

[0120] Furthermore, the candidate presentation unit 25 may also display estimated remuneration amounts at the locations of combinations determined to be "possible" in the matrix-like display configuration described above. In addition, the candidate presentation unit 25 may also display the combination of client and worker that results in the smallest estimated remuneration amount, and the combination that results in the largest estimated remuneration amount. With this configuration, users of the estimation system 1a can grasp the optimal combination of farm work and worker at a glance.

[0121] According to the estimation method of this embodiment, it becomes possible to match requests for agricultural work with workers in a way that satisfies both the requests of the requesters and the workers. For example, a requester for agricultural work wants to request work from a worker who can complete the work without any problems. Also, a worker wants to accept requests for agricultural work from a requester who offers the highest possible compensation. The candidate presentation unit 25 can present candidates for each agricultural work in a way that is highly likely to satisfy the desires of both parties.

[0122] The estimation device 20a may not include the efficiency calculation unit 21, the difficulty calculation unit 22, and the proficiency estimation unit 23. For example, the estimation device 20a may include only the work time estimation unit 24, or only the work time estimation unit 24 and the candidate presentation unit 25, from the functional blocks shown in Figure 8. In this case, the work time estimation unit 24 may calculate the estimated work time using information such as the third proficiency level and the fourth proficiency level stored in the server storage device 30. In other words, the function of the estimation device 20 to acquire the latest land difficulty level and worker proficiency level, and the functions of the work time estimation unit 24 and the candidate presentation unit 25 may be implemented by different devices.

[0123] [Embodiment 3] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0124] <Overview of Estimation System 1b> As shown in Figure 11, the estimation system 1b according to this embodiment differs from the estimation system 1 according to Embodiment 1 in that it includes an estimation device 20b that includes a path estimation unit 26. The estimation system 1b estimates the optimal path for a work machine such as a brush cutter 10 based on the history of past agricultural work. At this time, the estimation system 1b can estimate the optimal path by taking into account the skill level of the workers who have performed agricultural work in the past.

[0125] Past records of agricultural work may include a mix of records from highly skilled and experienced workers, as well as records from less skilled and inexperienced workers. In this case, if the optimal route is estimated uniformly from the work history regardless of the worker's skill level, the estimation accuracy is likely to be poor because the history of inexperienced workers will be heavily reflected. This is because the work path taken by a remotely operated machine run by a skilled worker is likely to be close to the optimal route, while the work path taken by a remotely operated machine run by an inexperienced worker is likely to deviate significantly from the actual optimal route.

[0126] The estimation system 1b can estimate the optimal route with high accuracy because it takes into account the skill level of workers who have performed agricultural work in the past. The optimal route estimated by estimation system 1b can be applied, for example, as a work route when performing agricultural work using an autonomous work machine. In addition, the optimal route estimated by estimation system 1b may be used as a reference route when workers perform agricultural work by remotely controlling a work machine.

[0127] <Estimation device 20b and estimation method> The estimation device 20b functions as a control device that comprehensively controls the estimation system 1b. The estimation device 20b may be implemented by a general-purpose integrated circuit such as a CPU (Central Processing Unit), or it may be implemented as a dedicated logic circuit. In addition to the efficiency calculation unit 21, the difficulty calculation unit 22, and the proficiency estimation unit 23, the estimation device 20b includes a path estimation unit 26 as a functional block.

[0128] The processing performed by the estimation device 20b will be described below in conjunction with the processing flow of the estimation method according to this embodiment shown in Figure 12. The processing flow of the estimation method described in this embodiment may be performed following the processing flow of the estimation method according to Embodiment 1 shown in Figure 4, or following the processing flow of the estimation method according to Embodiment 2 shown in Figure 9. Furthermore, the estimation method according to this embodiment may be performed independently of the estimation methods according to Embodiments 1 and 2.

[0129] (Route estimation unit 26) The path estimation unit 26 estimates the optimal path for the lawnmower 10 in agricultural work. First, the path estimation unit 26 acquires the work path history included in the work results of multiple agricultural tasks (S41). The path estimation unit 26 may acquire the work results of multiple agricultural tasks from, for example, the server storage device 30.

[0130] The multiple agricultural tasks are not particularly limited, as long as they have been performed in the past and have work results, including a work route history. Figure 13 shows an example in which the movement trajectories of the grass cutter 10, drawn based on the work route history of each of the seven agricultural tasks performed, are superimposed on 3D map data of the ridge, which is the land where grass cutting is performed as an agricultural task.

[0131] Thus, when agricultural work is performed multiple times, the work routes chosen by the workers are usually different each time. In this case, within the area of ​​the land, there may be locations where the brush cutter 10 travels frequently and locations where it travels infrequently. Locations where the brush cutter 10 travels frequently are considered to be locations that many workers have used the brush cutter 10 to travel to, and are therefore of high importance from the perspective of carrying out agricultural work. On the other hand, locations where the brush cutter 10 travels infrequently are considered to be locations where it is difficult to travel with the brush cutter 10, or locations that are of low importance in carrying out agricultural work and are not cost-effective. Therefore, locations where the brush cutter 10 travels frequently are considered to be locations that are more likely to be included in the optimal route for the brush cutter 10 in agricultural work.

[0132] Next, the route estimation unit 26 obtains the estimated second skill level for each farming task (S42). The second skill level may be obtained, for example, from the worker database 31. In this case, the worker database 31 may store the second skill level value and the work results of the farming task used to estimate the second skill level in a mutually corresponding format. Furthermore, the second skill level obtained by the route estimation unit 26 only needs to be a value that relatively indicates the skill level of the worker at the time of performing the farming task, and does not need to be the skill level estimated by the estimation system 1 or the like.

[0133] Next, the route estimation unit 26 weights the degree to which the work route history is taken into account in calculating the travel frequency according to the acquired second skill level (S43), and calculates the travel frequency of the brush cutter 10 at each location on the land (S44). The second skill level for each agricultural task acquired by the route estimation unit 26 indicates the skill level of the worker at the time the agricultural task was performed. Workers who were calculated to have a high second skill level are likely to have empirically understood the optimal route at the time the agricultural task was performed. Therefore, the route taken by workers who were calculated to have a high second skill level when operating the brush cutter 10 during agricultural work is considered to be a route close to the optimal route. On the other hand, the route taken by workers who were calculated to have a low second skill level when operating the brush cutter 10 is likely to be a route different from the optimal route.

[0134] Therefore, the route estimation unit 26 may process the data such that, for example, the work route history of an operator with a higher second skill level is more significantly reflected in the calculation of the travel frequency. The left diagram of Figure 14 shows an example in which the movement trajectories of each agricultural task shown in Figure 13 are drawn with varying line thicknesses (dot sizes) according to the level of the second skill level. In the left diagram of Figure 14, the movement trajectory is drawn thicker the higher the second skill level. The route estimation unit 26 may, for example, calculate the travel frequency according to the thickness of the drawn line.

[0135] Furthermore, it is preferable that the route estimation unit 26 calculates the travel frequency using a statistical method. Examples of statistical methods include methods that can identify spatial clusters with statistically significant large or small values, such as hotspot analysis (Getis-Ord Gi*).

[0136] As an example of the travel frequency calculated by the route estimation unit 26, the right-hand figure of Figure 14 shows an example in which the work route history of each worker is classified by statistical values ​​using the hotspot analysis according to the level of the second skill level, and the obtained results are plotted on 3D map data. In the example shown in the right-hand figure of Figure 14, "Hot Spot" indicates a location where the movement trajectories of workers with high second skill levels are statistically significantly concentrated, and "Cold Spot" indicates a location where the movement trajectories of workers with low second skill levels are statistically significantly concentrated. The route estimation unit 26 may determine whether the second skill level is high or low by, for example, whether it is above a predetermined threshold, or whether it is above the average value of the second skill levels of all workers.

[0137] Furthermore, "Not Significant" indicates locations where no statistically significant difference was observed in the distribution of worker movement trajectories based on the level of skill level. In the example shown in the right-hand figure of Figure 14, statistical significance is classified into three categories based on confidence levels: 90% to less than 95% (90% Confidence), 95% to less than 99% (95% Confidence), and 99% or higher (99% Confidence).

[0138] The route estimation unit 26 estimates the optimal route for the lawnmower 10 in agricultural work from the travel frequency obtained in this way (S45, route estimation step). The route estimation unit 26 may estimate the optimal route by assuming that the more frequently a location is traveled, the more likely it is to be the optimal route. Since the travel frequency is calculated by weighting it according to the level of the second skill level, routes selected by workers with a high second skill level are more likely to be calculated as locations with a high travel frequency. Therefore, the route estimation unit 26 can improve the estimation accuracy by giving more weight to routes selected by workers with a high second skill level when estimating the optimal route.

[0139] In the example shown in the right-hand diagram of Figure 14, the route estimation unit 26 rejects locations classified as Cold Spots, for example, as routes mainly traveled by workers with low second-level proficiency. The route estimation unit 26 also rejects locations classified as Not Significant or 90% Confidence, as they lack sufficient statistical significance. The route estimation unit 26 may then select Hot Spots with 95% Confidence and 99% Confidence as routes mainly traveled by workers with high second-level proficiency, and estimate the shortest route connecting these Hot Spots as the optimal route. In this case, the route estimation unit 26 may calculate the travel cost for each location on the land based on the slope angle, etc., and then estimate the optimal route after correcting the shortest route to minimize the travel cost.

[0140] Furthermore, the route estimation unit 26 may estimate the optimal route by multiplying the actual travel frequency at each of the Cold Spot, Not Significant, and Hot Spot locations by a predetermined coefficient set for each classification, so that locations with high travel frequency are preferentially selected. The predetermined coefficient may be, for example, less than 1 for Cold Spot and Not Significant, and 1 or greater for Hot Spot. Also, the predetermined coefficient may be larger for Hot Spot as the confidence coefficient increases, and smaller for Cold Spot as the confidence coefficient increases.

[0141] The route estimation unit 26 may store the estimated optimal route in the land database 32 (S46).

[0142] The upper part of Figure 15 shows an example of the optimal route estimated by the route estimation unit 26. The estimation system 1b may also update the second skill level of each worker stored in the worker database 31 whenever the third difficulty level of the land changes, using the skill level estimation unit 23. In this case, the route estimation unit 26 may update the optimal route whenever the second skill level of any worker is updated. The lower part of Figure 15 shows the latest optimal route after the route estimation unit 26 has estimated the optimal route (upper part of Figure 15), based on the results of a total of seven agricultural work operations. These seven agricultural work operations may correspond to the work route history shown in Figure 13. If the agricultural work performed by the workers results in the accumulation of work route history or updates to the information on the third difficulty level of the land, the route estimation unit 26 can sequentially estimate the most efficient optimal route based on the latest information.

[0143] Furthermore, the estimation device 20b may not include the efficiency calculation unit 21, the difficulty calculation unit 22, and the proficiency estimation unit 23. For example, the estimation device 20b may include only the route estimation unit 26 among the functional blocks shown in Figure 11. In this case, the route estimation unit 26 may use information such as the work route history stored in the server storage device 30 to estimate the optimal route. In other words, the function of the estimation device 20, which acquires the latest land difficulty and worker proficiency, and the function of the route estimation unit 26 may be implemented by different devices.

[0144] [Examples of implementation using software] The functions of the estimation devices 20, 20a, and 20b (hereinafter referred to as "devices") are programs that cause a computer to function as a device, and these can be realized by programs that cause a computer to function as each control block of the device.

[0145] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the program. By executing the program using this control device and storage device, each of the functions described in each of the embodiments is realized.

[0146] The program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0147] Furthermore, some or all of the functions of each control block can also be implemented by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the control blocks are formed is also included in the scope of the present invention. In addition, it is also possible to implement the functions of each control block using, for example, a quantum computer.

[0148] Furthermore, each of the processes described in the above embodiments may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the control device described above, or it may operate on other devices (for example, an edge computer or a cloud server).

[0149] 〔summary〕 An estimation device according to embodiment 1 of the present invention is an estimation device for estimating the skill level of an operator in remote operation of an agricultural machine, and includes: an efficiency calculation unit that calculates the work efficiency of a first agricultural machine using land information of the land that is the target of a first agricultural machine, which is the most recently performed agricultural machine, and the work results of the first agricultural machine performed by a first operator, who is the operator who performed the first agricultural machine; a difficulty calculation unit that calculates a first difficulty level, which is the difficulty level of the first agricultural machine, as a value that fluctuates according to the level of work efficiency, and obtains a third difficulty level by correcting a second difficulty level, which is the difficulty level of the agricultural machine calculated before the completion of the first agricultural machine, by the first difficulty level; and a skill level estimation unit that estimates a first skill level, which is the skill level of the first operator, based on the work efficiency and the third difficulty level, and obtains a third skill level by correcting a second skill level, which is the skill level of the first operator estimated before the completion of the first agricultural machine, by the first skill level.

[0150] In the estimation device according to embodiment 2 of the present invention, in embodiment 1, the proficiency estimation unit may further correct the second proficiency of at least one of the second workers, who is a different worker from the first worker, based on the third difficulty level, and update the third proficiency of at least one of the second workers based on the corrected second proficiency.

[0151] In the estimation device according to embodiment 3 of the present invention, in embodiment 1 or 2, the efficiency calculation unit may calculate the work efficiency using the work area, unworked area, and overlapping work area in the first agricultural work, which are calculated using the work time included in the work result, the work route history and the model information of the work machine included in the work result, and the total work area on the land calculated from the land information.

[0152] In the estimation device according to embodiment 4 of the present invention, in embodiment 3, the efficiency calculation unit may calculate the work efficiency by adding or subtracting a predetermined value to at least one of the work time, the unworked area, and the overlapping work area.

[0153] An estimation device according to embodiment 5 of the present invention further includes a work time estimation unit that calculates the estimated work time of the agricultural work performed by the worker in any of embodiments 1 to 4, wherein the proficiency estimation unit further calculates a fourth proficiency level indicating the proficiency level that serves as the standard for performing the agricultural work from the second proficiency levels of a plurality of workers, and the work time estimation unit may calculate the estimated work time for each worker based on the feasibility rate of completing the agricultural work calculated by comparing the fourth proficiency level with the third proficiency level and the standard work time of the land.

[0154] The estimation device according to embodiment 6 of the present invention may further include, in embodiment 5, a candidate presentation unit that determines, for each worker, whether the worker's available working time is within the range of the estimated working time, and whether the estimated remuneration obtained by multiplying the set unit price of the agricultural work by the estimated working time is equal to or greater than the requested remuneration obtained by multiplying the worker's requested unit price by the estimated working time, and presents workers for whom the estimated remuneration is determined to be equal to or greater than the requested remuneration as candidates for the agricultural work.

[0155] The estimation device according to embodiment 7 of the present invention further includes a path estimation unit that, in any of embodiments 1 to 6, calculates the frequency of travel of the work machine at each location on the land from the work path history included in the work results of a plurality of agricultural operations, and estimates the optimal path of the work machine in the agricultural operation from the travel frequency, wherein the path estimation unit may acquire the second skill level estimated for each agricultural operation, and in calculating the travel frequency, weighting may be applied to the degree to which the work path history is taken into account according to the level of the second skill level.

[0156] An estimation program according to aspect 8 of the present invention is a control program for causing a computer to function as an estimation device according to any one of aspects 1 to 7, wherein the computer functions as at least the efficiency calculation unit, the difficulty calculation unit, and the proficiency estimation unit.

[0157] An estimation method according to aspect 9 of the present invention is an estimation method for estimating the skill level of an operator in remote operation of an agricultural machine, and includes: an efficiency calculation step of calculating the work efficiency of a first agricultural machine using land information of the land that is the target of a first agricultural machine, which is the most recently performed agricultural machine, and the work results of the first agricultural machine performed by a first operator, who is the operator who performed the first agricultural machine; a difficulty calculation step of calculating a first difficulty level, which is the difficulty level of the first agricultural machine, as a value that fluctuates according to the level of work efficiency, and obtaining a third difficulty level by correcting a second difficulty level, which is the difficulty level of the agricultural machine calculated before the completion of the first agricultural machine, by the first difficulty level; and a skill level estimation step of estimating a first skill level, which is the skill level of the first operator, based on the work efficiency and the third difficulty level, and obtaining a third skill level by correcting a second skill level, which is the skill level of the first operator estimated before the completion of the first agricultural machine, by the first skill level.

[0158] An estimation system according to aspect 10 of the present invention is an estimation system for estimating the skill level of an operator in remote operation of an agricultural machine, and comprises a database and an estimation device for acquiring information from the database, wherein the estimation device includes: an efficiency calculation unit that calculates the work efficiency of the first agricultural work using land information of the land that is the target of the first agricultural work, which is the most recently performed agricultural work, and the work results of the first agricultural work performed by the first operator, who is the operator who performed the first agricultural work; a difficulty calculation unit that calculates a first difficulty level, which is the difficulty level of the first agricultural work, as a value that fluctuates according to the level of work efficiency, and acquires a third difficulty level by correcting a second difficulty level, which is the difficulty level of the agricultural work stored in the database before the completion of the first agricultural work, by the first difficulty level; and a skill level estimation unit that estimates the first skill level, which is the skill level of the first operator, based on the work efficiency and the third difficulty level, and acquires a third skill level by correcting a second skill level, which is the skill level of the first operator, which was stored in the database before the completion of the first agricultural work, by the first skill level.

[0159] A data structure according to embodiment 11 of the present invention is a data structure that includes information used in an estimation device for estimating the skill level of an operator in remote operation of an agricultural machine, the estimation device storing the following: land information of the land that is the target of the most recently performed agricultural machine, the first agricultural machine, and the work results of the first agricultural machine performed by the first operator, the operator who performed the first agricultural machine; a second difficulty level, which is the difficulty level of the agricultural machine before the completion of the first agricultural machine; and a second skill level, which is the skill level of the first operator before the completion of the first agricultural machine. The estimation device includes the information to perform the following processing: calculate the first difficulty level as a value that fluctuates according to the level of work efficiency; obtain a third difficulty level by correcting the second difficulty level by the first difficulty level; estimate the first skill level based on the work efficiency and the third difficulty level; and obtain a third skill level by correcting the second skill level by the first skill level.

[0160] [Additional Notes] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of 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 symbols]

[0161] 1, 1a, 1b Estimation System 10 Lawn Mower 20, 20a, 20b Estimation device 21 Efficiency Calculation Unit 22 Difficulty Calculation Section 23 Proficiency Estimation Section 24. Work Time Estimation Unit 25 Candidate presentation section 31. Worker Database (Database) 32. Land Database (Database)

Claims

1. An estimation device for estimating the skill level of an operator in remote operation of agricultural machinery, An efficiency calculation unit calculates the work efficiency of the first agricultural work using land information of the land that is the target of the first agricultural work, which is the agricultural work that was most recently carried out, and the work results of the first agricultural work performed by the first worker, who is the worker who carried out the first agricultural work. A difficulty calculation unit calculates a first difficulty level, which is the difficulty level of the first farming task, as a value that fluctuates according to the level of work efficiency, and obtains a third difficulty level by correcting the second difficulty level, which is the difficulty level of the farming task calculated before the completion of the first farming task, by the first difficulty level. An estimation device comprising: a skill level estimation unit that estimates a first skill level, which is the skill level of the first worker, based on the work efficiency and the third difficulty level; and a skill level estimation unit that obtains a third skill level obtained by correcting the second skill level, which is the skill level of the first worker estimated before the completion of the first agricultural work, by the first skill level.

2. The estimation device according to claim 1, further comprising: the proficiency estimation unit correcting the second proficiency of at least one of the second workers, who is a different worker from the first worker, based on the third difficulty level, and updating the third proficiency of at least one of the second workers based on the corrected second proficiency.

3. The efficiency calculation unit, The work time included in the aforementioned work results, The estimation device according to claim 1 or 2, which calculates the work efficiency using the work area, unworked area, and overlapping work area in the first agricultural work, which are calculated using the work route history and machine model information of the work equipment included in the work results and the total work area on the land calculated from the land information.

4. The estimation device according to claim 3, wherein the efficiency calculation unit calculates the work efficiency by adding or subtracting a predetermined value to at least one of the work time, the unworked area, and the overlapping work area.

5. The system further includes a work time estimation unit that calculates the estimated work time of the aforementioned agricultural work performed by the aforementioned worker, The proficiency estimation unit further calculates a fourth proficiency level, which indicates the proficiency level that serves as the standard for performing the agricultural work, from the second proficiency levels of the multiple workers. The estimation device according to claim 1 or 2, wherein the work time estimation unit calculates the estimated work time for each worker based on the feasibility rate of completing the agricultural work calculated by comparing the fourth skill level with the third skill level, and the standard work time for the land.

6. For each worker, it is determined whether the worker's available working time falls within the range of the estimated working time, and whether the estimated compensation obtained by multiplying the set unit price for the agricultural work by the estimated working time is equal to or greater than the requested compensation obtained by multiplying the worker's requested unit price by the estimated working time. The estimation device according to claim 5, further comprising a candidate presentation unit that presents workers whose estimated compensation is determined to be equal to or greater than the requested compensation as candidates for the agricultural work.

7. The system further includes a path estimation unit that calculates the frequency of travel of the work machine at each location on the land from the work path history included in the work results of multiple agricultural operations, and estimates the optimal path of the work machine in the agricultural operation from the travel frequency, The estimation device according to claim 1 or 2, wherein the route estimation unit obtains the second skill level estimated for each of the farm work tasks, and in calculating the travel frequency, weights the degree to which the work route history is taken into account according to the level of the second skill level.

8. A control program for causing a computer to function as an estimation device according to claim 1, wherein the computer functions as the efficiency calculation unit, the difficulty calculation unit, and the proficiency estimation unit.

9. A computer-based estimation method for estimating the skill level of an operator in remotely controlling agricultural machinery, in relation to agricultural work performed by remote control of the machinery, An efficiency calculation step that calculates the work efficiency of the first agricultural work using land information of the land that is the target of the first agricultural work, which is the agricultural work that was most recently carried out, and the work results of the first agricultural work performed by the first worker, who is the worker who carried out the first agricultural work, A difficulty calculation step involves calculating a first difficulty level, which is the difficulty level of the first agricultural work, as a value that fluctuates according to the level of work efficiency, and obtaining a third difficulty level by correcting the second difficulty level, which is the difficulty level of the agricultural work calculated before the completion of the first agricultural work, by the first difficulty level. An estimation method comprising: an estimation step of estimating a first skill level, which is the skill level of the first worker, based on the work efficiency and the third difficulty level; and obtaining a third skill level by correcting the second skill level, which is the skill level of the first worker estimated before the completion of the first agricultural work, by the first skill level.

10. An estimation system for estimating the skill level of an operator in remotely controlling agricultural machinery, in relation to agricultural work performed by remote control of the machinery, It comprises a database and an estimation device that acquires information from the database. The estimation device is, An efficiency calculation unit calculates the work efficiency of the first agricultural work using land information of the land that is the target of the first agricultural work, which is the agricultural work that was most recently carried out, and the work results of the first agricultural work performed by the first worker, who is the worker who carried out the first agricultural work. A difficulty calculation unit calculates a first difficulty level, which is the difficulty level of the first farming task, as a value that fluctuates according to the level of work efficiency, and obtains a third difficulty level by correcting the second difficulty level, which is the difficulty level of the farming task stored in the database before the completion of the first farming task, by the first difficulty level. An estimation system including a skill level estimation unit that estimates a first skill level, which is the skill level of the first worker, based on the work efficiency and the third difficulty level, and obtains a third skill level obtained by correcting the second skill level, which is the skill level of the first worker, stored in the database before the completion of the first agricultural work, by the first skill level.

Images