Agricultural work record creation device, agricultural work record creation program, and agricultural work record creation method

Abstract

This invention provides a farm work record creation device that allows for easy recording of farm work without the need for a special motion detection unit. [Solution] An agricultural work record creation device that creates agricultural work records based on information from an information terminal, comprising: a movement trajectory acquisition unit 11 that acquires a movement trajectory including date and time information from an information terminal; a feature extraction unit 12 that extracts work features based on the movement trajectory; a work type estimation unit 13 that estimates the work type from the work features; and an agricultural work record creation unit 14 that creates agricultural work records by associating the movement trajectory and the work type. The work features include the speed of movement of a portion that can be considered a straight line extracted from the movement trajectory, the width which is the distance between straight lines, crop information based on the position information of the movement trajectory, and time information based on the date and time the movement trajectory was recorded.

Description

Technical Field

[0001] The present invention relates to a farming work record creation device, a farming work record creation program, and a farming work record creation method.

Background Art

[0002] Various methods are being used to record farming work. For example, in Patent Document 1, there is an action record data acquisition unit that acquires movement data regarding the position and movement of a worker, a field candidate selection unit that selects a field candidate where the worker is working according to the position of the worker acquired by the action record data acquisition unit, a feature quantity extraction unit that extracts a feature quantity from the movement data of the worker acquired by the action record data acquisition unit, a work type identification unit that identifies the type of work performed by the worker using the feature quantity extracted by the feature quantity extraction unit, a field identification unit that identifies the field where the worker has performed work from the field candidates selected by the field candidate selection unit based on the work type identified by the work type identification unit, and a work record unit that records the work type identified by the work type identification unit and the field identified by the field identification unit in association with each other as a work record.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the case of Patent Document 1, in order to acquire motion data, the motion detection unit detects the movements of the farm worker using an acceleration sensor or the like, adds the ID of the owner of the action recording device to the detected data, and notifies the storage unit of the motion data as motion data for recording. For example, it is stated that a 3-axis acceleration sensor is used on the arm and waist as the motion detection unit. As examples of how the action recording device is attached (see Figure 2), a waist-mounted action recording device attached to the farm worker's waist and an arm-mounted action recording device attached to the farm worker's arm are shown. However, when performing farm work, using waist-mounted action recording devices, arm-mounted action recording devices, etc., may interfere with the work, and there has been a growing demand for a simpler way to record farm work.

[0005] The present invention was made to solve the aforementioned problems, and aims to provide a farm work record creation device, a farm work record creation program, and a farm work record creation method that can easily record farm work without using a special motion detection unit. [Means for solving the problem]

[0006] To achieve the above objective, the present invention provides an agricultural work record creation device that creates an agricultural work record based on information from an information terminal, and is characterized by comprising: a movement trajectory acquisition unit that acquires a movement trajectory including date and time information from the information terminal; a feature extraction unit that extracts work feature quantities based on the movement trajectory; a work type estimation unit that estimates the work type from the work feature quantities; and an agricultural work record creation unit that creates an agricultural work record by associating the movement trajectory and the work type. Other aspects of the present invention will be described in the embodiments described below. [Effects of the Invention]

[0007] According to the present invention, agricultural work can be easily recorded without using a special motion detection unit. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an agricultural work record creation device according to an embodiment of the present invention. [Figure 2]This figure shows an example of a user information data structure. [Figure 3] This figure shows an example of a data structure for movement trajectory information. [Figure 4] This figure shows an example of the data structure for field information. [Figure 5] This figure shows an example of a data structure for working feature information. [Figure 6] This figure shows an example of the data structure for work type information. [Figure 7] This figure shows an example of the data structure of work record information. [Figure 8] This is a flowchart showing the processing steps of the agricultural work record creation device. [Figure 9] This diagram shows the processing of the work type estimation unit. [Figure 10] This diagram shows an overview of the method for calculating work width and work speed. [Figure 11] This diagram shows a method for determining the intersection of line segments. [Figure 12] This diagram shows the method for calculating the working width. [Figure 13] This is a diagram showing the home screen of a mobile device. [Figure 14] This is a diagram showing the calendar screen of a mobile device. [Figure 15] This is a diagram showing the map screen of a mobile device. [Figure 16] This figure shows the work trajectory displayed on the mobile device in the first work example. [Figure 17] This diagram shows the processing of the work trajectory of the feature extraction unit in the first work example. [Figure 18] This diagram shows the type of work displayed on the mobile device in the first work example. [Figure 19] This figure shows the work trajectory displayed on the mobile device in the second work example. [Figure 20] This diagram shows the processing of the work trajectory of the feature extraction unit in the second work example. [Figure 21] This diagram shows the type of work displayed on the mobile device in the second work example. [Figure 22]It is a diagram showing the work trajectory displayed on the mobile terminal in the third work example. [Figure 23] It is a diagram showing the processing of the work trajectory of the feature extraction unit in the third work example. [Figure 24] It is a diagram showing the work type displayed on the mobile terminal in the third work example. [Figure 25] It is a diagram showing the work trajectory displayed on the mobile terminal in the fourth work example. [Figure 26] It is a diagram showing the processing of the work trajectory of the feature extraction unit in the fourth work example. [Figure 27] It is a diagram showing the work type displayed on the mobile terminal in the fourth work example. [Figure 28] It is a diagram showing an overview of the software framework.

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing an agricultural work record creation device 100 according to an embodiment of the present invention. The agricultural work record creation device 100 is a web server and is an agricultural work record creation device that creates an agricultural work record based on information from a mobile terminal 200 (information terminal). The agricultural work record creation device 100 includes a processing unit 10 that performs the processing of creating an agricultural work record, a database 20 that stores data when performing the processing of creating an agricultural work record, and a communication unit 50 that communicates with a mobile terminal 200 (information terminal) of a user who performs agricultural work and an administrator (contractor who uses the agricultural work record creation device) via the Internet 300.

[0010] The database 20 is composed of a hard disk drive (HDD) and other devices. The processing unit 10 is implemented by a CPU (Central Processing Unit) that loads programs stored in ROM (Read Only Memory), HDD, etc., into RAM (Random Access Memory) and executes them. The communication unit 50 exchanges various data and commands with mobile terminals 200 and other devices via the internet 300. The processing of the processing unit 10 may also be handled by a graphics processing unit (GPU).

[0011] The processing unit 10 has multiple programs, including a movement trajectory acquisition unit 11 that acquires a movement trajectory including date and time information from a mobile terminal 200 (information terminal), a feature extraction unit 12 that extracts work features based on the movement trajectory, a work type estimation unit 13 (see Figure 9) that estimates the work type from the work features, a farm work record creation unit 14 that creates a farm work record by associating the movement trajectory and the work type, a prediction model creation unit 15 used when the work type estimation unit 13 predicts the work type, and an input / output processing unit 16 that processes input and output with the information terminal.

[0012] The database 20 stores user information 21 (see Figure 2), which contains information about the contractor and their users; movement trajectory information 22 (see Figure 3), which records the movement trajectory from the mobile terminal 200; field information 23 (see Figure 4), which shows the relationship between the field and the crops; work feature information 24 (see Figure 5), which shows the work features extracted by the feature extraction unit 12; work type information 25 (see Figure 6), which shows the relationship between the crop and the type of work; work record information 26 (see Figure 7), which shows the work record from the start to the end of the work; and a trained model 27 created by the prediction model creation unit 15. Details of each piece of information will be described later with reference to Figures 2 to 7.

[0013] The work features include the speed of movement in the straight-line portions extracted from the movement trajectory, the width (distance between straight lines), crop information (crop name) based on the location information of the movement trajectory, and time information (work period) based on the recording date and time of the movement trajectory (see Figure 5). For details, please refer to Figures 8 and 10 to 12 below.

[0014] The mobile terminal 200 has functions such as starting and ending location information transmission notifications, transmitting the date, time, and location information of agricultural work to the agricultural work record creation device 100 based on signals from the positioning satellite 400, and viewing and modifying agricultural work records (work type, work trajectory, etc.). The mobile terminal 200 receives signals from the positioning satellite 400 that constitute the satellite positioning system. The satellite positioning system is, for example, GNSS (Global Navigation Satellite System).

[0015] The prediction model creation unit 15 uses past work records, i.e., past work features and work types, to train a trained model 27 (machine learning model) using machine learning or deep learning. The work type estimation unit 13 then uses the machine learning model trained from past work records to estimate the work type. Work features such as crop name, work period, work width, and work speed are explanatory variables, while work type and other factors are the dependent variables.

[0016] The work type estimation unit 13 performs work type AI prediction (see Figure 9, process S73). To do this, it is necessary to prepare a sufficient amount of training data in advance (a set of work features generated from movement trajectory information and data on the type of work at that time) and train the AI. AI training is performed using AI input data (work features, work type) generated from the movement trajectory information of the start and end time of the work recognized in work record generation and the type of work during that time period. AI training can be performed by batch processing in the AI ​​execution environment and can also be performed at any time. It is recommended to perform it approximately once a month using the task scheduler.

[0017] The prediction model creation unit 15 periodically checks whether work features corresponding to work records exist. If they do not exist, it generates work features from the movement trajectory information of the work record during the time period and registers them in the database. It periodically checks whether the AI ​​work type prediction result for work records corresponding to the work features has been set. For work records where the result has not been set, it uses the AI ​​input data (work features) to perform the AI ​​work type prediction and registers the result in the database. Since work type prediction only needs to be performed for work features that have been generated, it is preferable to perform the generation of work features and the work type prediction asynchronously.

[0018] The agricultural work record creation device 100 of this embodiment is characterized by its ability to determine the type of work and automatically create an agricultural work record using a movement trajectory including date and time information from a portable terminal 200 carried by the agricultural worker. It does not use special motion detection units such as a waist-mounted action recording device or arm-mounted action recording device as described in Patent Document 1. Furthermore, it can automatically create an agricultural work record without requiring any operation of the portable terminal 200 during agricultural work.

[0019] Next, each piece of information will be explained with reference to Figures 2 through 7. Figure 2 shows an example of the data structure of user information 21. User information 21 includes contract ID, contractor name, user IDs under the contractor's management, username, etc.

[0020] Figure 3 shows an example of the data structure of the movement trajectory information 22. The movement trajectory information 22 includes the work record FID (FileID), the date and time of positioning received from the mobile terminal 200, longitude, latitude, speed, direction, etc. The user's trajectory can be understood from the data in each row.

[0021] Figure 4 shows an example of the data structure of field information 23. Field information 23 includes field name, crop name, location information, and time information. Even in the same field, the crop grown in that field may differ depending on the time of year, so time information is associated with it. The field location and crop can be identified by the work start date and time and location information from the mobile terminal 200. According to Figure 4, it can be seen that soybeans are grown in field 5.

[0022] Figure 5 shows an example of the data structure of the work feature information 24. The work feature information 24 includes user ID, crop name, work period, work width, work speed, work record FID, etc. The work width and work speed are values ​​calculated by the feature extraction unit 12 based on the movement trajectory (work trajectory). If the work record FID is 4845, it can be seen that user U0001 is working on soybeans with a work width of 3.5896m and a work speed of 7.2401km / h.

[0023] Figure 6 shows an example of the data structure of work type information 25. Work type information 25 includes crop name, work type, etc. In the example in Figure 6, for soybeans, the work types include tillage, sowing, pest control, fertilization, intertillage / weeding, ..., harvesting, and other types.

[0024] In agriculture, tillage is the process of digging up and turning over the soil. Sowing is the process of planting seeds. Pest control is the prevention and eradication of diseases and pests in agriculture. Fertilization is the application of fertilizer to improve crop growth and increase yield. Intertillage is the process of shallowly tilling the surface of the ridges or tilling the spaces between the ridges (pathways). Figure 6 shows an example of soybeans, but the database 20 contains information on various types of work 25, including rice.

[0025] Figure 7 shows an example of the data structure of work record information 26. Work record information 26 includes user ID, field name, crop name, work start date and time, work end date and time, work type, work record FID, etc. Work record information 26 can be divided into work record information 26A when the work type is not estimated and work record information 26B when the work type is estimated or specified. According to work record information 26B in Figure 7, if the work record FID is 4845, it can be seen that user U0001 performed tillage work on soybeans in field 5, with a work start date and time of 2024 / 05 / 03 11:16:00, a work end date and time of 2024 / 05 / 03 13:01:00, and a work type of tillage.

[0026] Figure 28 shows an overview of the software framework. The online processing of agricultural work record creation by the agricultural work record creation device 100 employs a three-tier system. In the three-tier system, the entire system is divided into three layers: the P layer (presentation layer), the F layer (function layer), and the D layer (data layer), and implemented on the web server side. By separating and arranging the processing in multiple layers, it is possible to respond flexibly when it becomes necessary to make changes to any of the layers.

[0027] The P layer processes requests from the browser of mobile device 200 and handles the resulting response processing. It processes requests from the browser and calls the F layer logic corresponding to the request (event). It also sends the results from the F layer back to the browser as a response.

[0028] The F layer uses web-independent classes and is designed to be executable from layers other than the P layer as a library. It is designed to handle browser requests with a single logic. The D layer sets the parameters received from the F layer into SQL, executes it, and then returns the result to the F layer.

[0029] Next, the detailed procedure for creating farm work records will be explained with reference to Figure 8. Figure 8 is a flowchart of the farm work record creation process S60. Figure 1 will be used as a reference for further explanation. The farm work record creation unit 14 acquires movement trajectory information (step S61) upon receiving a notification from the mobile terminal 200 that the transmission of location information has ended (the timing when the user stops recording positioning points). It then recognizes a single work section from the field information and work trajectory (i.e., determines the work start date and end date and time) and registers it in the work record information 26A (step S62). At this point, the type of work has not yet been registered.

[0030] The start and end dates and times of work registered in the work log serve as prerequisite information for extracting work features. The start and end dates and times of work can be determined by the program (for example, the date and time of entering or leaving the field) or by notification from the user (for example, the date and time of performing the work start and end actions). The system periodically checks for new work logs and work feature registrations, and when each registration is detected, it executes the process of registering the next work feature and estimating the work type.

[0031] When the feature extraction unit 12 detects that a new work record has been registered, it extracts the work trajectory between the work start date and time and the end date and time, extracts and calculates work features (crop name, work period, work width, work speed), and registers them in the work feature information 24 (see Figure 5) (Step S63: Work feature extraction).

[0032] The extraction of working features in step S63 (see working feature information 24 in Figure 5) is as follows. (a) The crop name is determined by comparing the location information (longitude, latitude) and work start date and time (positioning date and time) of the movement trajectory information 22 with the location information and time information of the field information 23 and selecting the one that matches. If time information is not registered in the field information 23, the crop name is determined by comparing the location information (longitude, latitude) of the movement trajectory information 22 with the location information of the field information 23 and selecting the one that matches.

[0033] (b) The timing of the work is determined from the start date and time of the work (positioning date and time) of the movement trajectory information 22. In this embodiment, the work period is divided into the beginning, middle, and end of each month, resulting in 36 divisions from the beginning of January to the end of December. The work period is converted into a work period code (numerical value) and becomes the AI's training data. Actual farm work cannot always be performed at the same time and date as in the past, and if the granularity of the work period is set to the day and time, the training data will be too fine-grained, and slight differences in the day and time will easily affect the estimation results. For this reason, the granularity is set to the beginning, middle, and end of the month. (c) The working width and working speed are determined by the calculation method described later in Figure 10.

[0034] Returning to Figure 8, when the work type estimation unit 13 detects that a new work feature has been registered, it uses the trained model 27 to predict the work type using AI based on the work feature information 24 and the work type information 25, which is a list of crop work types (candidates) (Step S64: Work Type Estimation). The work type estimation unit 13 estimates the work type using AI (DNN: Deep Neural Network) based on the work feature.

[0035] The work type estimation unit 13 determines the work type based on the estimated probability and registers the result in the work record information 26 (Step S65: Work type determination). The registered result becomes the work record information 26B (see Figure 7).

[0036] The user can view the work record created by the system from the mobile terminal 200. If a prediction result has been registered, the predicted work type will be displayed on the mobile terminal 200. Otherwise, it will display "Predicting." The user can check and correct the displayed work record, and once the confirmed operation is performed, the work type will be finalized and the work record will be completed (Step S66: Setting the work record result). The finalized work type can be used as training data in the future.

[0037] Figure 9 shows the processing (processing S70) of the work type estimation unit 13. Based on the work feature information 24, the work type estimation unit 13 generates AI input data (processing S71) and stores the AI ​​input data in the memory unit (processing S72). Generating AI input data means converting it into a code (numerical representation) that can be processed by the AI. Then, based on the already trained model 27, the work type information 25, and the AI ​​input data, the work type estimation unit 13 performs AI prediction of the work type (processing S73) and outputs the prediction result (processing S74).

[0038] (Method for calculating working width and working speed) Figure 10 shows an overview of the method for calculating working width and working speed. Figure 10 shows the positioning points (○) in the field and the detected regression line. The working width is considered to be the distance between adjacent parallel straight sections of the working trajectory during back-and-forth movement. The straight sections of the work trajectory are detected as follows. (1) Trace the positioning points in chronological order, and take the point just before the point where the azimuth difference from the starting point (which is considered a straight line) exceeds a certain magnitude as the final point, and extract the consecutive positioning points between those points. (2)Approximulate the positioning points from (1) with a regression line to obtain the slope and intercept, and the latitude (y coordinate) of the starting and ending points of the line segment shall be the value obtained from slope × longitude (x coordinate) + intercept.

[0039] The definitions of work width and work speed are as follows: (3) The detected line segments are taken out in chronological order, and for any two line segments that are within a certain range of error in the slope between the extracted line segment 1 and subsequent line segments 2 (the range in which they can be considered parallel), a perpendicular line can be drawn from the midpoint of line segment 2 to line segment 1. (4) If the perpendicular line does not intersect with any other detected line segments, the length of the perpendicular line shall be used as the working width. However, if the working width exceeds a certain size, it shall not be used as the working width. In addition, the working speed of the line segment shall be the average of the speeds of the positioning points included in (1).

[0040] Regarding (3), whether a perpendicular can be drawn from a point on one line segment to another is determined by whether the dot product of the two line segments is negative. Regarding (4), whether two line segments intersect can be determined by checking whether the cross product of the two line segments is negative. In other words, it is best to use the line segment intersection test.

[0041] Figure 11 shows an example of determining whether a work width is feasible. If the user moves in the order of line segment 1 → line segment 2 → line segment 3 → line segment 4, the dashed arrow is not considered part of the work width because it intersects with other line segments.

[0042] Figure 12 shows the method for calculating the working width. Since the working width is estimated to be several tens of meters, we consider the working width as the distance between a point on a plane and a straight line. In this case, the working width is calculated as follows. The working width is defined as the distance between the straight line and point Q, which is the intersection point of the straight line and the regression line n. If the slope of the regression line n is a and the intercept is b, Point P(x) on the regression line n+1 n+1 , y n+1 The point Q, which passes through the line and intersects it with a line perpendicular to the regression line, is given by equation (1).

number

[0043] Since the coordinates of points P and Q are their latitude and longitude on Earth, the working width is calculated using a highly accurate method that takes this into account. For example, as a method for calculating the distance between two points on Earth, If the radius of the Earth is r = 6378137.0 [m], the distance [m] between two points PQ is given by equation (2).

number

[0044] (Example of display on a mobile device) Figure 13 shows the home screen of the mobile terminal 200. The display screen of the mobile terminal 200 consists of an upper menu section 201, a lower menu section 202, and a main display section 203. The upper menu section 201 has selection buttons for all crops, all tasks, all fields, etc. The lower menu section 202 has a home button 202a, a calendar button 202b, a map button 202c, and a settings button 202d. The main display section 203 of the home screen of the mobile terminal 200 consists of a location information communication status 210, a task start button 211, a task end button 212 (task stop button), and a location information transmission restriction setting area 213.

[0045] When the user enters the field and begins work, they press the work start button 211, and when they finish work, they press the work end button 212. This allows the mobile terminal 200 to transmit information about the movement trajectory, including date and time information, to the agricultural work record creation device 100.

[0046] Figure 14 shows the calendar screen of the mobile terminal 200. When the calendar button 202b in the lower menu section 202 is pressed, a calendar with the types of work listed is displayed. For example, it can be seen that the "plowing" work was performed on April 6th and the "sowing" work was performed on April 18th.

[0047] Figure 15 shows the map screen of the mobile terminal 200. When the map button 202c on the lower menu section 202 is pressed, the field and movement trajectory (work trajectory) are displayed. The main display section 203 has a trajectory display button 230 and zoom in / out buttons 235, and the field is displayed as shown by reference numeral 231. When the trajectory display button 230 is pressed, the movement trajectory is displayed on the field as shown by reference numeral 232. This allows the user to check the movement trajectory on the field.

[0048] Next, I will explain an example of the process. (Example of first task) Figure 16 shows the work trajectory displayed on the mobile terminal 200 in the first work example. Figure 17 shows the processing of the work trajectory by the feature extraction unit 12 in the first work example. Figure 17 shows an example in which the feature extraction unit 12 calculates the work width and work speed based on the data received from the mobile terminal 200. Figure 17 shows the positioning points (○) in the field and the detected regression line. As a result, the work width is calculated to be 3.59 m and the work speed to be 7.24 km / h.

[0049] The work type estimation unit 13 performed AI prediction of the work type based on work characteristics and calculated the following percentages: tillage 73.6%, sowing 15.9%, pest control 0.9%, fertilization 4.8%, intertillage / weeding 3.4%, etc. As a result, the work type was estimated to be "tilling". Figure 18 shows the work type displayed on the mobile terminal 200 in the first work example. The mobile terminal 200 displays the field name, crop name, work type, etc. The user checks the estimated work type. If corrections are needed, they can be made by pressing the pen mark.

[0050] (Example of second task) Figure 19 shows the work trajectory displayed on the mobile terminal 200 in the second work example. Figure 20 shows the processing of the work trajectory by the feature extraction unit 12 in the second work example. Figure 20 shows an example in which the feature extraction unit 12 calculates the work width and work speed based on the data received from the mobile terminal 200. Figure 20 shows the positioning points (○) in the field and the detected regression line. As a result, the work width is calculated to be 3.17 m and the work speed to be 4.15 km / h.

[0051] The work type estimation unit 13 performed AI prediction of the work type based on work characteristics and calculated the following probabilities: tillage 10.4%, sowing 66.7%, pest control 11.3%, fertilization 6.0%, intertillage / weeding 3.5%, etc. As a result, the work type was estimated to be "sowing". Figure 21 shows the work type displayed on the mobile terminal 200 in the second work example. The mobile terminal 200 displays the field name, crop name, work type, etc. The user checks the estimated work type. If corrections are needed, they can be made by pressing the pen mark.

[0052] (Example 3 of the work) Figure 22 shows the work trajectory displayed on the mobile terminal 200 in the third work example. Figure 23 shows the processing of the work trajectory by the feature extraction unit 12 in the third work example. Figure 23 shows an example in which the feature extraction unit 12 calculates the work width and work speed based on the data received from the mobile terminal 200. Figure 23 shows the positioning points (○) in the field and the detected regression line. As a result, the work width is calculated to be 24.11 m and the work speed to be 4.54 km / h.

[0053] The work type estimation unit 13 performs AI prediction of work type based on work characteristics, with tillage accounting for 1.3%, sowing for 1.0%, pest control for 94.0%, fertilization for 1.2%, and intertillage / weeding for 1.0%. These calculations were performed. As a result, the type of work is estimated to be "pest control." Figure 24 shows the work type displayed on the mobile terminal 200 in the third work example. The mobile terminal 200 displays the field name, crop name, work type, etc. The user checks the estimated work type. If corrections are needed, they can be made by pressing the pen mark.

[0054] (Example 4 of the work) Figure 25 shows the work trajectory displayed on the mobile terminal 200 in the fourth work example. Figure 26 shows the processing of the work trajectory by the feature extraction unit 12 in the fourth work example. Figure 26 shows an example in which the feature extraction unit 12 calculates the work width and work speed based on the data received from the mobile terminal 200. Figure 26 shows the positioning points (○) in the field and the detected regression line. As a result, the work width is calculated to be 18.05 m and the work speed to be 4.39 km / h.

[0055] The work type estimation unit 13 performed AI prediction of the work type based on work characteristics and calculated the following probabilities: tillage 0.9%, sowing 0.7%, pest control 95.9%, fertilization 1.2%, intertillage / weeding 0.5%, etc. As a result, the work type was estimated to be "pest control". Figure 27 shows the work type displayed on the mobile terminal 200 in the fourth work example. The mobile terminal 200 displays the field name, crop name, work type, etc. The user checks the estimated work type. If corrections are needed, they can be made by pressing the pen mark.

[0056] The agricultural work record creation device 100, agricultural work record creation program, and agricultural work record creation method of this embodiment described above have the following features. (1) A farm work record creation device that creates farm work records based on information from an information terminal (mobile terminal 200), comprising: a movement trajectory acquisition unit 11 that acquires a movement trajectory including date and time information from the information terminal; a feature extraction unit 12 that extracts work features based on the movement trajectory; a work type estimation unit 13 that estimates the work type from the work features; and a farm work record creation unit 14 that creates a farm work record by associating the movement trajectory and the work type. This makes it possible to easily record farm work without using a special motion detection unit. In this embodiment, since it creates farm work records based on information from an information terminal, it may be held by the user or installed on a tractor or the like.

[0057] (2) In the above (1), the work features include the speed of movement of the portion that can be considered a straight line extracted from the movement trajectory, the width which is the distance between the straight lines, crop information based on the position information of the movement trajectory, and time information based on the date and time the movement trajectory was recorded.

[0058] (3) In (1) above, the work type estimation unit 13 is an agricultural work record creation device that uses a machine learning model learned from past work records to estimate the work type.

[0059] (4) A farm work record creation program that creates a farm work record based on information from an information terminal, which causes a computer to perform a movement trajectory acquisition process (mainly step S61) to acquire a movement trajectory including date and time information from an information terminal, a feature extraction process (step S63) to extract work features based on the movement trajectory, a work type estimation process (steps S64, S65) to estimate the type of work from the work features, and a farm work record creation process (mainly step S66) to create a farm work record by associating the movement trajectory and the type of work.

[0060] (5) In (4) above, the work features include the speed of movement of the portion that can be considered a straight line extracted from the movement trajectory, the width which is the distance between the straight lines, crop information based on the position information of the movement trajectory, and time information based on the date and time the movement trajectory was recorded, which is the agricultural work record creation program.

[0061] (6) In (4) above, the work type estimation process is a farm work record creation program that uses a machine learning model learned from past work records to estimate the type of work.

[0062] (7) A method for creating agricultural work records for an agricultural work record creation device that creates agricultural work records based on information from an information terminal, wherein the processing unit 10 of the agricultural work record creation device performs a movement trajectory acquisition process to acquire a movement trajectory including date and time information from an information terminal, a feature extraction process to extract work features based on the movement trajectory, a work type estimation process to estimate the type of work from the work features, and an agricultural work record creation process to create an agricultural work record by associating the movement trajectory and the type of work. [Explanation of Symbols]

[0063] 10 Processing Unit 11 Movement trajectory acquisition section 12 Feature Extraction Unit 13. Work Type Estimation Unit 14. Agricultural Work Record Creation Department 15. Predictive Model Creation Department 16 Input / Output Processing Unit 20 Databases 21 User Information 22 Movement trajectory information 23 Field Information 24. Work Feature Information 25. Work Type Information 26 Work Record Information 27 Trained Models 50 Communications Department 100 Agricultural work record creation device 200 Mobile devices (information terminals) 300 Internet 400 positioning satellites

Claims

1. A farm work record creation device that creates farm work records based on information from an information terminal, A movement trajectory acquisition unit acquires a movement trajectory including date and time information from the aforementioned information terminal, A feature extraction unit extracts work features based on the aforementioned movement trajectory, A work type estimation unit that estimates the type of work from the aforementioned work characteristics, A farm work record creation device characterized by having a farm work record creation unit that creates a farm work record by associating the aforementioned movement trajectory with the aforementioned work type.

2. The aforementioned work features include: The speed of movement of the portion that can be considered a straight line, extracted from the aforementioned movement trajectory, and the width, which is the distance between the straight lines, Crop information based on the location information of the aforementioned movement trajectory, Includes time information based on the date and time the aforementioned movement trajectory was recorded. The agricultural work record creation device according to feature 1.

3. The aforementioned work type estimation unit uses a machine learning model learned from past work records to estimate the work type. The agricultural work record creation device according to feature 1.

4. A farm work record creation program that creates farm work records based on information from an information terminal, On the computer, A movement trajectory acquisition process that acquires a movement trajectory including date and time information from the aforementioned information terminal, A feature extraction process that extracts work features based on the aforementioned movement trajectory, A work type estimation process that estimates the type of work from the aforementioned work features, A farm work record creation program for executing a farm work record creation process that creates a farm work record by associating the aforementioned movement trajectory with the aforementioned work type.

5. The aforementioned work features include: The speed of movement of the portion that can be considered a straight line, extracted from the aforementioned movement trajectory, and the width, which is the distance between the straight lines, Crop information based on the location information of the aforementioned movement trajectory, Includes time information based on the date and time the aforementioned movement trajectory was recorded. The agricultural work record creation program according to feature 4.

6. The aforementioned work type estimation process uses a machine learning model learned from past work records to estimate the work type. The agricultural work record creation program according to feature 4.

7. A method for creating agricultural work records for an agricultural work record creation device that creates agricultural work records based on information from an information terminal, The processing unit of the aforementioned agricultural work record creation device is: A movement trajectory acquisition process that acquires a movement trajectory including date and time information from the aforementioned information terminal, A feature extraction process that extracts work features based on the aforementioned movement trajectory, A work type estimation process that estimates the type of work from the aforementioned work features, A method for creating agricultural work records, characterized by performing an agricultural work record creation process that creates an agricultural work record by associating the aforementioned movement trajectory with the aforementioned work type.

Images