JP7426921B2 - Work judgment system, work judgment method and work judgment program - Google Patents

Description

The present invention relates to a work determination system, a work determination method, and a work determination program for estimating the type of work performed by a work vehicle.

In farming, it is desirable to record the work done as farm work in order to evaluate the current year's management and formulate improvement plans for the next year. However, when a tractor, which is a general-purpose work vehicle, is used, such recording work takes time and effort. This is because a variety of agricultural work can be performed by attaching various working machines to a single tractor, and there are many options for inputting work records.

Instead of manually recording work, we estimate the type of work using a method based on machine learning using operation information that indicates the operating status transmitted from a tractor with a predetermined communication function. There are systems that automatically record work based on results.

In relation to the above, Patent Document 1 (Japanese Unexamined Patent Application Publication No. 2018-190292) states that based on position information and operation information acquired when a working device such as a tractor operates while moving in a field and performs agricultural work, An agricultural work support system has been disclosed that determines the agricultural work performed by a working device and manages the agricultural work.

Furthermore, Patent Document 2 (Japanese Unexamined Patent Publication No. 2019-088227) discloses position information detected when a working machine such as a tractor with a working device installed on a vehicle body runs in a field and performs work, and A management device is disclosed that acquires work-related information based on information received from an RFID (Radio Frequency IDentification) tag provided with work equipment information indicating the model of the work equipment.

Japanese Patent Application Publication No. 2018-190292 JP2019-088227A

In the above technology, operating information such as the engine speed and PTO (Power Take Off) speed of the tractor is used as information used to estimate the type of work. However, in order to obtain such operating information, the tractor needs to be of a model that has a function of outputting operating information. In other words, since the types of tractors that output operating information are limited, it becomes difficult to estimate the type of work using a similar method if the user owns a different tractor.

When using a tractor model that does not support the above method, the user may record data indicating the type of work by manually inputting it into the tractor's terminal etc. before starting the work. . However, manually inputting work data every time the work equipment attached to the tractor is replaced and a different work is performed is cumbersome, and data may be frequently forgotten, making it difficult to know what kind of work has been performed. Situations are likely to occur in which it is difficult to record information about

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide a work determination system, a work determination method, and a work determination program that make it possible to estimate the type of work performed by a work vehicle even when operating information of the work vehicle cannot be obtained. Other objects and novel features will become apparent from the description of this specification and the accompanying drawings.

Below, means for solving the problem will be explained using the numbers used in (Detailed Description of the Invention). These numbers are added to clarify the correspondence between the claims and the detailed description. However, these numbers must not be used to interpret the technical scope of the invention stated in the (claims).

According to one embodiment for solving the above problem, the work determination system (1) includes an external information preparation means (531) and a work estimation means (533). The external information preparation means (531) prepares external information that can be prepared outside the work vehicle (2) that moves and performs work in the field and is independent of the operating status of the work vehicle (2). do. The work estimating means (533) estimates the type of work based on movement information that records movement of the work vehicle (2) and external information.

According to an embodiment for solving the above problems, the work determination method can be prepared outside the work vehicle (2) that moves in the field and performs the work, and is operable by the work vehicle (2). Preparing external information that is independent of the situation (S02), and estimating the type of work based on the movement information recording the movement of the work vehicle (2) and the external information (S04). include.

According to an embodiment for solving the above problem, the work determination program is executed by the arithmetic device (53) to realize a function for determining the type of work performed by the work vehicle (2). This is a work judgment program. This function can be prepared outside the work vehicle (2) that moves and performs work in the field, and provides external information that is independent of the operating status of the work vehicle (2) (S02). and estimating the type of work based on movement information recording movement of the work vehicle (2) and external information (S04).

According to the above embodiment, even if the operation information of the work vehicle cannot be obtained, the type of work performed by the work vehicle can be estimated.

FIG. 1 is a diagram illustrating a configuration example of a work determination system according to an embodiment. FIG. 2A is a diagram illustrating a configuration example of a work vehicle according to an embodiment. FIG. 2B is a block circuit diagram illustrating a configuration example of a data collection unit according to an embodiment. FIG. 3 is a block circuit diagram showing a configuration example of an in-vehicle terminal according to an embodiment. FIG. 4 is a block circuit diagram showing an example of a configuration of a server according to an embodiment. FIG. 5 is a block circuit diagram showing an example of a configuration of a terminal according to an embodiment. FIG. 6 is a flowchart illustrating a configuration example of a work determination method and a work determination program according to an embodiment. FIG. 7 is a diagram illustrating an example of a display by a terminal according to an embodiment. FIG. 8 is a block circuit diagram showing an example of a configuration of a server according to an embodiment. FIG. 9 is a flowchart illustrating a configuration example of a work determination method and a work determination program according to an embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of an information processing system and a server according to the present invention will be described below with reference to the accompanying drawings.

(First embodiment)
The work determination system, work determination method, and work determination program according to the present embodiment can estimate the type of work performed by a work vehicle based on information other than information indicating the internal state of the work vehicle during work. . As a result, even if the work vehicle is not compatible with a specific support system, it is possible to simplify and more reliably record the work performed in the past. Here, the types of work include, for example, land leveling, plowing, puddling, planting, fertilization, pest control, and harvesting.

As shown in FIG. 1, the work determination system 1 includes an in-vehicle terminal 3 and a server 5. The in-vehicle terminal 3 is mounted on the work vehicle 2. The in-vehicle terminal 3 and the server 5 are connected to each other via a network 4. Connection between the in-vehicle terminal 3 and the network 4 is realized by wireless communication. A mobile phone line may be used for this wireless communication, and in that case, the network 4 may include the mobile phone line. Further, a wireless LAN (Local Area Network) may be used for this wireless communication. The connection between the server 5 and the network 4 is realized by wired communication. A terminal 6 other than the in-vehicle terminal 3 may be further connected to the network 4.

As shown in FIG. 2A, the work vehicle 2 includes a vehicle body 21, a work implement 22, a pair of front wheels 23, a pair of rear wheels 24, a steering means 25, and a data collection section 26. An in-vehicle terminal 3 is mounted on the vehicle body 21.

The working machine 22 is, for example, a device for performing agricultural work, and is supported by the vehicle body 21 so as to be movable up and down. In the example of FIG. 2A, the work vehicle 2 is a tractor, and the work machine 22 is a tillage device for cultivating a field. The vehicle body 21 is supported by front wheels 23 and rear wheels 24, and is driven forward or backward by driving the rear wheels 24 by a power source (not shown). The steering means 25 is a steering wheel or a handle, and an operator can adjust the traveling direction of the vehicle body 21 by operating the steering means 25 to adjust the direction of the front wheels 23.

As a modification of the configuration shown in FIG. 2A, the work vehicle 2 may be of an integrated type, such as a combine harvester. In other words, the work vehicle 2 of this embodiment is not limited to the combination of a tractor and the work implement 22 that is detachably attached to the tractor.

As shown in FIG. 2B, the data collection unit 26 includes a bus 28, an interface device 27, and a plurality of sensors 29-1, 29-2, . . . , 29-N. When the plurality of sensors 29-1, 29-2, . . . , 29-N are not distinguished, they are simply referred to as sensors 29. Each sensor 29 is connected to an interface device 27 via a bus 28 . The interface device 27 is configured to be connectable to the in-vehicle terminal 3.

The plurality of sensors 29 generate sensor signals representing the states of the plurality of devices provided on the work vehicle 2. In other words, the sensor 29 generates a sensor signal as operating information representing the operating status of the work vehicle 2. The operating status of the work vehicle 2 includes at least the internal state related to the work of the work vehicle 2, such as the driving state of the drive source of the tractor and the operating state of the transmission mechanism that transmits the driving force of the drive source to the work implement 22. . The operating information representing the operating status of the work vehicle 2 includes, for example, drive source information representing the driving state of the drive source, transmission mechanism information representing the operating state of the transmission mechanism, engine rotation speed information representing the engine speed of the work vehicle 2, It includes PTO (Power Take Off) rotation speed information indicating the rotation speed of the PTO (Power Take Off), hitch height information and lift arm angle information indicating the elevation state of the work implement 22 with respect to the work vehicle 2, and the like.

However, in this embodiment, a case will be described in which the type of work is estimated without using operation information. In this case, the data collection unit 26 can be omitted. A case in which the type of work is estimated using the data collection unit 26 and operation information will be described later as another embodiment.

As shown in FIG. 3, the in-vehicle terminal 3 includes a bus 31, an operation information acquisition means 32, an arithmetic unit 33, a storage device 34, an external storage device 35, a position information acquisition means 36, and a communication device 37. It is equipped with The operation information acquisition means 32, the arithmetic device 33, the storage device 34, the external storage device 35, the position information acquisition means 36, and the communication device 37 are connected to each other via the bus 31 so that they can communicate with each other.

The in-vehicle terminal 3 may be a so-called computer. In other words, the functions of the in-vehicle terminal 3 may be realized by the arithmetic unit 33 such as a CPU (Central Processing Unit) executing a predetermined program stored in the storage device 34. This program may be read from the recording medium 351 by the external storage device 35 and stored in the storage device 34, or may be received from the outside via the communication device 37 and stored in the storage device 34. It may be something.

The operation information acquisition means 32 is configured to be able to acquire sensor signals from the data collection section 26. Communication between the on-vehicle terminal 3 and the data collection unit 26 of the work vehicle 2 is realized by wired communication or wireless communication between the operation information acquisition means 32 and the interface device 27.

The position information acquisition means 36 measures the position of the in-vehicle terminal 3 using GNSS (Global Navigation Satellite System) or the like. The position information acquisition means 36 measures the position of the in-vehicle terminal 3 by measuring the latitude and longitude of the in-vehicle terminal 3. Since the vehicle-mounted terminal 3 is mounted on the work vehicle 2, the position of the work vehicle 2 can be measured by measuring the position of the vehicle-mounted terminal 3. The arithmetic device 33 acquires position information representing the measured latitude and longitude and stores it in the storage device 34 .

The arithmetic device 33 stores the position information acquired at a plurality of times in the storage device 34 in association with the measurement time. These multiple times may have periodicity. As an example, the arithmetic device 33 acquires position information at a cycle of 1 second, and stores the position information in the storage device 34 in association with time information indicating the time when the position information was acquired.

The start and end of the measurement of position information may be automatically controlled in conjunction with the start and stop of the engine of the work vehicle 2, respectively.

The communication device 37 transmits the position information stored in the storage device 34 to the server 5 via the network 4.

As shown in FIG. 4, the server 5 includes a bus 51, a calculation device 53, a storage device 54, an external storage device 55, and a communication device 56. Arithmetic device 53, storage device 54, external storage device 55, and communication device 56 are connected via bus 51 so that they can communicate with each other.

The arithmetic device 53 implements the functions of the server 5 by executing programs stored in the storage device 54. In other words, the functions of the server 5 are realized by the cooperation of the arithmetic device 53 and the program stored in the storage device 54. This program may be read from the recording medium 551 by the external storage device 55 and stored in the storage device 54, or may be received from the outside via the communication device 56 and stored in the storage device 54. It may be something.

In FIG. 4, the functions of the server 5 realized in this way are shown as means included in the arithmetic device 53 for convenience. The calculation device 53 includes external information preparation means 531 and work estimation means 533.

External information preparation means 531 is used to estimate the type of work and prepares external information acquired from outside of work vehicle 2 so that it can be read by arithmetic device 53 . External information is information that is independent of the operating status of the work vehicle 2 and is information that is prepared outside the work vehicle 2.

The external information may include one or more pieces of information. One or more pieces of information included in the external information are referred to as one or more pieces of individual external information. The one or more individual external information includes one or more performance information indicating the performance according to the specifications of the work vehicle 2, one or more field geographical information indicating the geographical characteristics of the field where the work vehicle 2 works, and the land condition in the field. The information may include at least one of one or more field land attribute information indicating the characteristics of the field and one or more field weather information representing the weather in the field. The field land attribute information includes, for example, data based on information obtained by observing the ground surface from above using an artificial satellite, an aircraft, a drone, or the like.

The performance information of 1 or more includes maximum horsepower information representing the maximum horsepower according to the specifications of the work vehicle 2, driving method information representing the travel method in which the work vehicle 2 travels with tires and/or crawlers, and vehicle height of the work vehicle 2. The working vehicle 2 may include at least one of vehicle height information indicating the traveling width of the working vehicle 2 and traveling width information indicating the traveling width of the work vehicle 2 . The one or more pieces of field geographic information include at least one of field elevation information representing the altitude of the field, field soil information representing the type of soil in the field, and field area information representing the area where the field is located. It's okay to stay. The one or more pieces of field land attribute information include field surface information representing the nature of the field surface (e.g., information identifying whether it is concrete, soil, water, or plants), as well as information such as the coverage rate and growth state of plants in the field. field vegetation information (e.g., crop type, NDVI (Normalized Difference Vegetation Index), plant coverage, visible light, estimated nitrogen content, etc.), and field moisture information that represents field moisture content information. It may include at least one of these. The one or more pieces of field weather information include field precipitation information representing the amount of precipitation in a predetermined period of the field, field cumulative solar radiation information representing the cumulative amount of solar radiation in the field for a predetermined period, and average temperature of the field in a predetermined period. field average temperature information representing the maximum temperature of the field during a predetermined period, field maximum temperature information representing the maximum temperature of the field during a predetermined period of time, field minimum temperature information representing the minimum temperature of the field during a predetermined period of time, and representing the cumulative temperature of the field during a predetermined period of time. The information may include at least one of field integrated temperature information.

The work estimating means 533 uses the judgment model stored in the judgment model storage means 541 of the storage device 54 to estimate the type of work based on the position information and external information. The determination model is a mathematical model used to estimate the type of work using AI (Artificial Intelligence). The judgment model is constructed using machine learning and learns features contained in external information. For example, in the case of supervised learning, methods such as support vector machines, random forests, neural networks, logistic regression, and topological data analysis are used to estimate the type of work using external information as learning data. Note that the learning data here includes at least one of the one or more individual external information included in the external information as a correct answer label indicating the correct answer for estimating the type of work.

The user can use the terminal 6 to confirm the result of the estimation of the type of work performed by the work determination system 1 according to the present embodiment. The terminal 6 may be, for example, a tablet-type information terminal.

As shown in FIG. 5, the terminal 6 includes a bus 61, an input/output device 62, an arithmetic device 63, a storage device 64, an external storage device 65, and a communication device 67. The input/output device 62, the arithmetic device 63, the storage device 64, the external storage device 65, and the communication device 67 are connected to each other via the bus 61 so that they can communicate with each other.

Similarly to the in-vehicle terminal 3, the terminal 6 may be a so-called computer. In other words, the functions of the terminal 6 may be realized by the arithmetic unit 63 such as the CPU executing a predetermined program stored in the storage device 64. This program may be read from the recording medium 651 by the external storage device 65 and stored in the storage device 64, or may be acquired from the outside via the network 4 and the communication device 67 and stored in the storage device 64. It may be stored.

The input/output device 62 includes a touch panel device that is integrated with a display device and allows a user to perform input. The input/output device 62 may further include input devices such as keys, buttons, and switches for operating the terminal 6.

The communication device 67 is connected to the server 5 via the network 4 and can acquire data from the server 5, and conversely can also transmit data stored in the storage device 64 to the server 5.

An example of the operation of the work determination system 1 having the above configuration, that is, a configuration example of the work determination method according to the present embodiment will be described with reference to FIG. 6. Each step of the work determination method is realized by the arithmetic device 33 of the in-vehicle terminal 3, the arithmetic device 53 of the server 5, or the arithmetic device 63 of the terminal 6 executing the work determination program according to the present embodiment.

In the first step S01, when the work of the work vehicle 2 is completed and the position information of the work vehicle 2 during work is transmitted from the on-vehicle terminal 3 to the server 5, the work determination method is started in the server 5. When the work determination method is started, the determination model is prepared in the determination model storage means 541.

In the second step S02, various data used for estimating the type of work are prepared in the storage device 54. The data prepared here includes position information of the work vehicle 2 and external information prepared outside the work vehicle 2.

The position information of the work vehicle 2 is acquired by the position information acquisition means 36 at a plurality of times while the work vehicle 2 is moving in the field and performing work, and is stored in the storage device 34 of the vehicle-mounted terminal 3. This operation is completed before starting the work determination method in the first step S01.

As described above, the position information is transmitted from the computing device 33 of the in-vehicle terminal 3 to the computing device 53 of the server 5 via the network 4. The computing device 53 of the server 5 stores the received position information in the storage device 54, and makes it readable by the computing device 53.

As a modification of the position information, vehicle speed information may be used. In other words, the type of work may be estimated using vehicle speed information representing the vehicle speed of the work vehicle 2 at each of a plurality of times. Here, the vehicle speed information may be used instead of the position information or in addition to the position information.

The calculation of the vehicle speed information may be performed by the calculation device 53 of the server 5 or the calculation device 33 of the vehicle-mounted terminal 3 as a vehicle speed calculation means. Among the plurality of times at which position information was measured, vehicle speed information at a certain first time T1 is, for example, the first time T1, the second time T2 following that time (or the previous 0th time T0), etc. , can be easily calculated based on the first position information measured at time T1 and the second position information (or 0th position information) measured at second time T2 (or 0th time T0). Alternatively, the average value of the vehicle speed at each time may be used as the vehicle speed information.

The position information and vehicle speed information are collectively referred to as movement information that records movement of the work vehicle 2. In cases where vehicle speed information can be used together with position information and cases where vehicle speed information can be used instead of position information, position information or vehicle speed information may be read as movement information.

As described above, the external information preparation means 531 of the server 5 prepares the external information so that it can be read by the arithmetic device 53.

In the third step S03, the work estimating means 533 of the server 5 estimates the type of work of the work vehicle 2. At this time, the work estimating means 533 inputs the individual external information and position information into the determination model read from the determination model storage means 541 in order to estimate the type of work.

In the above example, the work estimating means 533 inputs into the third determination model C maximum horsepower information, which is individual external information, and time information and vehicle speed information derived from position information. Here, the maximum horsepower information indicates that the maximum horsepower according to the specification of the work vehicle 2 is "100 PS (horsepower)", the time information indicates that the season is "spring", and the vehicle speed information indicates that the maximum horsepower of the work vehicle 2 is "100 PS (horsepower)". A case where the average vehicle speed during work is "2 kilometers per hour" will be explained.

Note that the maximum horsepower information may be read out by the arithmetic unit 53 of the server 5 from a database stored in advance in the storage device 54 of the server 5 based on an identification signal transmitted from the in-vehicle terminal 3 to the server 5, for example. good. Here, for example, the identification signal includes model number information representing the model number of the work vehicle 2, the model number information is read by the on-vehicle terminal 3 from the data collection unit 26, and the database contains maximum horsepower information for each model number. It may also include information that represents. Furthermore, the time information is read out by the arithmetic unit 53 of the server 5 from the time information included in the position information transmitted from the in-vehicle terminal 3 to the server 5 and the database stored in advance in the storage device 54 of the server 5. good. Here, the time information includes the date on which the location information was acquired, and the database may include information representing the season for each date.

Under the prerequisites that the value of the field region information is "Kanto region" and the value of the field soil information is "paddy rice and cabbage," the third determination model C is such that the value of the time information is "spring," In addition, when the value of the vehicle speed information is "2 kilometers per hour", the maximum horsepower of the work vehicle 2 is often "100 PS or more" when performing plowing work, and this maximum horsepower is often used when performing land leveling work. Machine learning has learned that the power output is frequently between 50 and 70 horsepower. As a result, the third judgment model C outputs that the probability that the type of work is "land leveling" is 55%, and the probability that the type of work is "plowing" is 45%. . Each of the combinations in which the output type of work is associated with the accuracy is referred to as an estimation result.

In the fourth step S04, the work estimating means 533 of the server 5 records each estimation result in the storage device 54.

In the fifth step S05, the work estimating means 533 of the server 5 determines the type of work. In detail, the work estimating means 533 determines that among the estimation results obtained in the third step S03 and recorded in the fourth step S04, the type of work with the highest associated accuracy is the work actually performed. The determination result is recorded in the storage device 54.

In the sixth step S06, the terminal 6 displays the determination result to notify the user. Specifically, the work estimating means 533 of the server 5 transmits a signal to the terminal 6 to notify the terminal 6 that the determination result is ready. Upon receiving this signal, the terminal 6 receives the determination result and the estimation result from the storage device 54 of the server 5 and stores them in the storage device 64. The terminal 6 notifies the user through display, voice, etc. that it is ready to display the determination results and estimation results. The user operates the terminal 6 to display the determination result on the touch panel of the input/output device 62.

As shown in FIG. 7, the input/output device 62 of the terminal 6 may display map information 621 representing the field where the work was performed, as well as a window 622 representing the determination result of the type of work performed in this field. . This window 622 displays, for all estimation results including judgment results, the name of the estimated work type, the accuracy of this estimation, and the name of representative information input into the judgment model to perform this estimation. and the value may be displayed. This window 622 may further display the date and time zone in which the estimated work was performed.

In the example of FIG. 7, it is displayed that the estimated type of work is "ground leveling" and that the accuracy of this estimation is "55%." Further, as a result of another estimation, it is displayed that the estimated type of work is "plowing" and that the accuracy of this estimation is "45%". Here, in order to indicate that "land leveling" is the determination result among these estimation results, the terminal 6 surrounds and highlights the part "land leveling 55%" with a frame.

Furthermore, in the example of FIG. 7, typical information used for estimation is that the vehicle speed is "2", the maximum horsepower is "100", and the season is "spring". It is displayed in window 622.

Here, the user can check the display on the terminal 6 and correct the determination result of the type of work if it is wrong. In the example shown in Figure 7, the user performs operations such as tapping the "Plowing 45%" part on the touch panel in order to modify the work type determination result from "land leveling" to "plowing". . In response to the user's operation, the arithmetic unit 63 of the terminal 6 transmits a correction signal to the server 5 for correcting the work determination result to "plowing". Based on this modification signal, the server 5 modifies the work type determination result stored in the storage device 54 from "land leveling" to "plowing."

When the sixth step S06 is completed, the flowchart of FIG. 6 ends in a seventh step S07.

As described above, the work determination system 1 according to the present embodiment implements each step of the work determination method by executing the work determination program, so that even if the operation information of the work vehicle 2 cannot be obtained, The type of work performed by the work vehicle 2 can be estimated based on the position information of the work vehicle 2 and external information. Furthermore, it is possible to simplify the recording of work performed in the past and perform it more reliably.

(Second embodiment)
This embodiment is a modification of the first embodiment with the following changes added. That is, in the first embodiment, a configuration in which there is one judgment model for use in work estimation has been described, but in this embodiment, a plurality of judgment models are prepared in the judgment model storage means 541, and these plural judgment models are One judgment model is selected from among the judgment models and used for work estimation.

As shown in FIG. 8, the server 5 according to this embodiment is obtained by adding the following changes to the server 5 according to the first embodiment shown in FIG. That is, the arithmetic device 53 further includes a judgment model selection means 532. The judgment model selection means 532 selects a judgment model to be used for estimating the type of work from among the plurality of judgment models stored in the judgment model storage means 541.

The plurality of determination models have different external information used as learning data. For example, the first determination model A of the determination models is trained using learning data whose field soil information is paddy rice. Further, the second determination model B, which is different from the first determination model A, is trained using learning data whose field soil information is paddy rice and cabbage.

In this embodiment, when the judgment model selection means 532 selects a judgment model from among a plurality of judgment models, learning is performed using learning data that matches the individual external information prepared by the external information preparation means 531. Select the selected judgment model. By using the judgment model selected in this way for estimating work, it can be expected that excellent accuracy will be obtained in estimating work.

Referring to FIG. 9, an example of the operation of the work determination system 1 having the above configuration, that is, a configuration example of the work determination method according to the present embodiment will be described. Each step of the work determination method is realized by the arithmetic device 33 of the in-vehicle terminal 3, the arithmetic device 53 of the server 5, or the arithmetic device 63 of the terminal 6 executing the work determination program according to the present embodiment.

The first step S11 and the second step S12 are the same as the first step S01 and the second step S02 of the first embodiment shown in FIG. 6, respectively.

In the third step S13, the judgment model selection means 532 of the server 5 selects a judgment model to be used for estimating the type of work. The judgment model selection means 532 selects a judgment model that matches the individual external information included in the external information stored in the storage device 54 from among the plurality of judgment models stored in the judgment model storage means 541.

When using a judgment model that is trained using individual external information and correct labels as training data, even when inputting individual external information that is not used for learning into the judgment model, it is possible to determine the type of work with high accuracy. can be estimated. The process of estimating the type of work from such external information is expressed as the individual external information matching the correct label.

As an example, a case will be described in which the judgment model storage unit 541 stores three judgment models each having a different combination of individual external information matching the correct label. The first determination model A is suitable for the correct label of the combination in which the field soil information is paddy rice and the field area information is the Kyushu region. The second determination model B is suitable for the correct label of the combination in which the field soil information is paddy rice and cabbage, and the field region information is the Kyushu region. The third determination model C is suitable for the correct label of a combination in which the field soil information is paddy rice and cabbage, and the field region information is the Kanto region. Here, the field soil information represents crops that have been cultivated in that field in the past, and represents that the field has soil characteristics suitable for growing that crop. . Further, the field area information represents the region where the field is located.

In the above example, if the field area information is "Kanto region" and the field soil information is "paddy rice and cabbage" among the individual external information prepared for the work for which you want to estimate the type, then the correct answer label is matched. The determination model selection means 532 selects the third determination model C that matches the individual external information.

In the fourth step S14, the work estimating means 533 of the server 5 estimates the type of work of the work vehicle 2. The fourth step S14 of the present embodiment is the third step S03 of the first embodiment with the following changes. That is, the work estimating means 533 inputs the individual external information and the position information into the determination model selected in the third step S13 in order to estimate the type of work.

The fifth step S15, the sixth step S16, the seventh step S17, and the eighth step S18 are respectively the fourth step S04, the fifth step S05, the sixth step S06, and the fourth step S04 of the first embodiment shown in FIG. This is the same as step S07.

As described above, the work determination system 1 according to the present embodiment is capable of selecting a determination model that matches the correct label from among a plurality of determination models as a determination model used to estimate the type of work. can. Therefore, it can be expected that superior accuracy in estimating work will be obtained compared to the first embodiment.

(Third embodiment)
In this embodiment, as information used to estimate the type of work of the work vehicle 2, in addition to the position information of the work vehicle 2 and external information prepared outside the work vehicle 2, information on the operation of the work vehicle 2 is used. Further use operational information to describe the situation.

Furthermore, the configuration of the work determination method and work determination program according to the present embodiment includes the following changes made to the flowchart of the first embodiment shown in FIG. 6 or the flowchart of the second embodiment shown in FIG. It can be obtained with First, while the work vehicle 2 is working, the in-vehicle terminal 3 acquires operation information in addition to position information. This operation is performed in the first step S01 in FIG. 6 or the first step S11 in FIG.

The operation information includes, for example, drive source information indicating the driving state of the drive source, transmission mechanism information indicating the operating state of the transmission mechanism, engine rotation speed information indicating the engine rotation speed of the work vehicle 2, and engine load of the work vehicle 2. Engine load factor information indicating the rate, PTO rotation speed information indicating the rotation speed of the PTO that transmits power from the work vehicle 2 to the work implement 22, hitch height and lift arm angle indicating the elevation status of the work implement 22 with respect to the work vehicle 2. Contains information, etc.

Next, in the second step S02 of FIG. 6 or the second step S12 of FIG. 9, the operating information is transmitted to the arithmetic device 53 of the server 5 and stored in the storage device 54 in the same way as the position information. In the third step S13 of FIG. 9, the determination model selection means 532 uses the operation information stored in the storage device 54 in addition to the position information and external information when selecting a determination model. In the third step S03 in FIG. 6 or the fourth step S14 in FIG. 9, the work estimating means 533 inputs operation information into the determination model in addition to the position information and external information to estimate the type of work. In the sixth step S06 in FIG. 6 or the seventh step S17 in FIG. good.

The work determination system 1 according to the present embodiment executes the work determination program and implements each step of the work determination method, thereby estimating the type of work of the work vehicle 2 with higher accuracy than when operating information cannot be acquired. I can do it. Furthermore, it is possible to simplify the recording of work performed in the past and perform it more reliably.

Although the present invention has been specifically described above based on each embodiment, the present invention is not limited to the above-described embodiments, and can be modified in various ways without departing from the gist thereof. Furthermore, the features described in the above embodiments can be freely combined without technically contradicting each other.

As a modification of the work determination system 1 according to each embodiment, the in-vehicle terminal 3 and the terminal 6 may be the same terminal. In other words, the terminal 6 detachably connected to the work vehicle 2 may be used as the in-vehicle terminal 3. When the terminal 6 is used as the in-vehicle terminal 3, the terminal 6 further includes various components provided to realize the functions of the in-vehicle terminal 3. The input/output device 62 further includes an interface device for connecting to the data collection unit 26 .

As a modification of the first embodiment that does not use operating information, if the data collection unit 26 is omitted, the operating information acquisition means 32 of the in-vehicle terminal 3 can also be omitted.

Each of the recording medium 351, the recording medium 551, and the recording medium 651 may be a non-transitory tangible media.

A plurality of methods for the external information preparation means 531 to prepare external information in the storage device 54 will be described. The external information preparation means 531 may acquire external information from another server connected to the network 4 via the network 4 and the communication device 56 and store it in the storage device 54, or may acquire external information from the storage medium 551 into the external storage. External information may be acquired via the device 55 and stored in the storage device 54, or may be read from a database stored in the storage device 54 in advance. The external information may be registered in the storage device 54 in advance. In either case, the external information preparation means 531 can prepare external information by reading the external information from the storage device 54.

As a modification of the sixth step S06 of the first embodiment and the seventh step S07 of the second embodiment, when the user modifies the determination result of the work type by the work estimation means 533 of the server 5, The determination model used to estimate the type of work may be updated. Updating the determination model may include performing additional learning on the determination model using different learning data. Furthermore, in the second embodiment, updating the determination model may include changing the criteria and/or method for selecting the determination model to be used from among the plurality of determination models in the third step S13.

1 Work Judgment System 2 Work Vehicle 21 Vehicle Body 22 Work Machine 23 Front Wheel 24 Rear Wheel 25 Steering Means 26 Data Collection Unit 27 Interface Device 28 Bus 29, 29-1, 29-2, 29-N Sensor 3 On-board Terminal 31 Bus 32 Operation Information acquisition means 33 Arithmetic device 34 Storage device 35 External storage device 351 Recording medium 36 Position information acquisition means 37 Communication device 4 Network 5 Server 51 Bus 53 Arithmetic device 531 External information preparation means 532 Judgment model selection means 533 Work estimation means 54 Storage device 541 Judgment model storage means 55 External storage device 551 Recording medium 56 Communication device 6 Terminal 61 Bus 62 Input/output device 621 Map information 622 Window 63 Arithmetic device 64 Storage device 65 External storage device 651 Recording medium 67 Communication device

Claims (11)

External information preparation means for preparing external information that can be prepared outside a work vehicle that moves and performs work in a field and that is independent of the operating status of the work vehicle;
comprising a work estimation means for estimating the type of work based on movement information recording movement of the work vehicle and the external information ;
The external information includes one or more individual external information,
The one or more individual external information is obtained by observing the ground surface from above, including one or more performance information indicating the performance according to the specifications of the work vehicle, one or more field geographical information indicating the geographical characteristics of the field. Contains at least one of one or more field land attribute information indicating the characteristics of the land condition in the field based on the information, and one or more field weather information representing the weather in the field.
Work judgment system. The work determination system according to claim 1,
The movement information is
including position information representing the position of the work vehicle at each of a plurality of times;
A work determination system further comprising a position information acquisition means for acquiring the position information. The work determination system according to claim 1 or 2,
The movement information is
A work determination system including vehicle speed information representing the vehicle speed of the work vehicle at each of a plurality of times. In the work determination system according to any one of claims 1 to 3 ,
The one or more pieces of performance information include maximum horsepower information representing a maximum horsepower according to specifications of the work vehicle, driving method information representing a travel method of the work vehicle, and vehicle height information representing a vehicle height of the work vehicle; including at least one of traveling width information representing a traveling width of the work vehicle;
The one or more pieces of field geographic information include at least the following: field elevation information representing the altitude of the field, field soil information representing the type of soil in the field, and field area information representing the region where the field is located. including one;
The one or more pieces of field weather information include field precipitation information representing the amount of precipitation in the field during a predetermined period, field cumulative solar radiation information representing the cumulative amount of solar radiation in the field during a predetermined period, and field weather information representing the cumulative amount of solar radiation in the field during a predetermined period. Field average temperature information representing the average temperature for a period, field maximum temperature information representing the maximum temperature for a predetermined period of the field, field minimum temperature information representing the minimum temperature for a predetermined period of the field, and a predetermined temperature for the field. A work determination system including at least one of field cumulative temperature information representing cumulative temperature for a period of . In the work determination system according to any one of claims 1 to 4 ,
Judgment model storage means for storing a judgment model trained to estimate the type of work using learning data that includes at least one of the one or more pieces of individual external information as a correct answer label for supervised learning. Furthermore,
A work determination system, wherein the work estimation means estimates the type of work using the determination model. In the work determination system according to any one of claims 1 to 4 ,
A judgment model that stores a plurality of judgment models trained to estimate the type of work using learning data that includes at least one of the one or more pieces of individual external information as a correct answer label for supervised learning. storage means,
further comprising a judgment model selection means for selecting one judgment model from the plurality of judgment models based on the individual external information included in the external information,
The work estimation system estimates the type of work using the judgment model selected by the judgment model selection means. The work determination system according to any one of claims 1 to 6 ,
The work estimation system further estimates the type of work based on operation information representing the operation status of the work vehicle. The work determination system according to claim 7 ,
The operation information includes engine rotation speed information representing the engine rotation speed of the work vehicle, engine load factor information representing the engine load factor of the work vehicle, and PTO (PTO) that transmits power from the work vehicle to an external work machine. The work includes at least one of PTO rotation speed information representing the rotation speed of the Power Take Off (Power Take Off), and hitch height information and lift arm angle information representing the lifting/lowering state of the work equipment with respect to the work vehicle. Judgment system. The work determination system according to any one of claims 1 to 8 ,
a display device that displays the result of estimating the type of work together with the name and value of the information used for the estimation;
A work determination system further comprising: an input device that accepts an input for modifying a result of estimating the type of work. Preparing external information that can be prepared outside a work vehicle that moves and performs work in the field and is independent of the operating status of the work vehicle;
estimating the type of work based on movement information recording movement of the work vehicle and the external information ,
The external information includes one or more individual external information,
The one or more individual external information is obtained by observing the ground surface from above, including one or more performance information indicating the performance according to the specifications of the work vehicle, one or more field geographical information indicating the geographical characteristics of the field. Contains at least one of one or more field land attribute information indicating the characteristics of the land condition in the field based on the information, and one or more field weather information representing the weather in the field.
Work judgment method. A work determination program for realizing a function for determining the type of work performed by a work vehicle by being executed by a calculation device, the program comprising:
The said function is
preparing external information that can be prepared outside the work vehicle that moves in the field and performs the work, and that is independent of the operating status of the work vehicle;
estimating the type of work based on movement information recording movement of the work vehicle and the external information ,
The external information includes one or more individual external information,
The one or more pieces of individual external information are obtained by observing the ground surface from above, including one or more performance information indicating the performance according to the specifications of the work vehicle, one or more field geographical information indicating the geographical characteristics of the field. Contains at least one of one or more field land attribute information indicating the characteristics of the land condition in the field based on the information, and one or more field weather information representing the weather in the field.
Work judgment program.

Images