Method and system estimating work machine connected to work vehicle

Abstract

To more accurately estimate the type of a work machine connected to a work vehicle.SOLUTION: A method is disclosed which is implemented by one or more computers communicating with a work vehicle which drives a connected work machine to implement work. The method includes the steps of: repeatedly acquiring 10 or more signals each of which indicates a different internal state of the work vehicle, from the work vehicle; generating input data on the basis of the 10 or more signals; inputting the input data into one or more learned models for estimating the type of the work machine on the basis of the input data to estimate the type of the work machine; and generating and outputting output data including information indicating the estimated type of the work machine.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a method and system for estimating a work implement connected to a work vehicle. [Background technology]

[0002] There is an increasing need for predictive maintenance, which involves remotely monitoring the condition of a vehicle, grasping or predicting failures or malfunctions, and carrying out maintenance such as part replacement or repair. To carry out predictive maintenance, it is necessary to obtain various data showing the internal condition of the vehicle and estimate the vehicle's operating condition based on that data.

[0003] Patent Documents 1 and 2 disclose a technique for automatically estimating the type of work performed by a working machine attached to an agricultural tractor. In the technique disclosed in Patent Documents 1 and 2, a management server estimates the type of work performed by the working machine based on the position information and operation information transmitted from the tractor at each time and a pre-trained machine learning model. Examples of the operation information include vehicle speed, engine on / off information, engine speed, PTO clutch on / off information, PTO clutch speed, and engine load factor. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-089477 [Patent Document 2] Patent Publication No. 2021-087361 Summary of the Invention [Problem to be solved by the invention]

[0005] It is important for dealers and other businesses that provide services such as maintenance or repairs for agricultural tractors and other work vehicles, or for work vehicle manufacturers, to understand how work vehicles are usually used. In particular, since a wide variety of implements can be connected to work vehicles, it is important to understand what work is being performed using what implements in order to improve the quality of services or products.

[0006] The above-mentioned conventional techniques are capable of determining the type of work being performed, but are unable to accurately distinguish between the wide variety of work machines.

[0007] The present disclosure provides a technique for more accurately estimating the type of work machine connected to a work vehicle. [Means for solving the problem]

[0008] A method according to one aspect of the present disclosure is executed by one or more computers in communication with a work vehicle that drives a connected work machine to perform work. The method includes the steps of repeatedly acquiring 10 or more signals from the work vehicle, each of which indicates a different internal state of the work vehicle, generating input data based on the 10 or more signals, inputting the input data to one or more trained models for estimating the type of the work machine based on the input data to estimate the type of the work machine, and generating and outputting output data including information indicative of the estimated type of the work machine.

[0009] The general or specific aspects of the present disclosure may be realized by an apparatus, a system, a method, an integrated circuit, a computer program, or a computer-readable non-transitory storage medium, or any combination thereof. The computer-readable storage medium may include a volatile storage medium or a non-volatile storage medium. The apparatus may be composed of multiple devices. When the apparatus is composed of two or more devices, the two or more devices may be arranged in one device or may be arranged separately in two or more separate devices. Effect of the Invention

[0010] According to the embodiments of the present disclosure, it is possible to more accurately estimate the type of work machine connected to a work vehicle. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating a schematic configuration example of a system according to an exemplary embodiment of the present disclosure. [Diagram 2] FIG. 2 is a side view showing an example of a work vehicle and a work implement coupled to the work vehicle. [Diagram 3] FIG. 3 is a block diagram showing an example of the configuration of the work vehicle and the server. [Figure 4] FIG. 4 is a diagram showing an example of a group of operation switches provided inside the cabin. [Diagram 5] FIG. 5 is a block diagram showing an example of the hardware configuration of a dealer terminal and a manufacturer computer. [Figure 6] FIG. 6 is a flowchart showing an example of a data transmission operation by the communication device of the work vehicle. [Figure 7] FIG. 7 is a flowchart showing an example of the operation of the server. [Figure 8] FIG. 8 is a diagram illustrating an example of time-series data. [Figure 9] FIG. 9 is a flowchart showing a more specific example of the process of step S230 in FIG. [Figure 10] FIG. 10 is a diagram illustrating a decision tree, which is an example of a trained model used in the determination process in the first step (step S231). [Figure 11] FIG. 11 is a diagram showing a decision tree that is an example of a trained model used in the determination process in the second step (step S233). [Figure 12] FIG. 12 is a diagram showing an example of a signal waveform when the work machine is a plow. [Figure 13] FIG. 13 is a diagram showing an example of a signal waveform when the working machine is a slurry tanker. [Figure 14] FIG. 14 is a diagram showing an example of a signal waveform when the work machine is a seed drill. [Figure 15] FIG. 15 is a flow chart illustrating an example of operations performed by a processing circuit of a dealer terminal. [Figure 16] FIG. 16 is a diagram showing an example of an image displayed on the display. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present disclosure will be described. However, more detailed explanation than necessary may be omitted. For example, detailed explanation of already well-known matters and overlapping explanation of substantially the same configuration may be omitted. This is to avoid the following explanation becoming unnecessarily redundant and to facilitate understanding by those skilled in the art. Note that the inventor provides the accompanying drawings and the following explanation so that those skilled in the art can fully understand the present disclosure, and does not intend to limit the subject matter described in the claims by them. In the following description, components having the same or similar functions are given the same reference numerals.

[0013] The following embodiments are illustrative, and the technology of the present disclosure is not limited to the following embodiments. For example, the numerical values, shapes, steps, the order of the steps, the layout of the display screen, and the like shown in the following embodiments are merely examples, and various modifications are possible as long as no technical contradiction occurs. In addition, one aspect can be combined with another aspect as long as no technical contradiction occurs.

[0014] <System configuration example> 1 is a diagram illustrating a schematic configuration example of a system according to an exemplary embodiment of the present disclosure. The system is a system for remotely monitoring the operating status of one or more work vehicles 100.

[0015] The system shown in FIG. 1 includes a plurality of work vehicles 100, a server computer 600 (hereinafter referred to as "server 600"), a dealer terminal 400 provided at a dealership (dealer) of the work vehicles 100, and a manufacturer computer 500 managed by the manufacturer of the work vehicles 100. The server 600 may be, for example, a cloud server provided in a data center. Each of the work vehicles 100, the dealer terminal 400, and the manufacturer computer 500 is configured to be able to communicate with the server 600 via a network 80. In the example of FIG. 1, a plurality of work vehicles 100 are included in the system, but the number of work vehicles 100 may be one.

[0016] The work vehicle 100 and the dealer terminal 400 may be used in the same region or country, for example. Each of the manufacturer computer 500 and the server 600 may be provided in a region or country different from that of the work vehicle 100 and the dealer terminal 400. Each of the manufacturer computer 500 and the server 600 may be a collection of multiple computers. The server 600 may be a cloud server managed by a provider that provides machine learning services. In that case, the server 600 may be installed in a country different from that of the work vehicle 100, the dealer terminal 400, and the manufacturer computer 500. The server 600 may be a collection of multiple computers that are distributed and arranged in different regions or countries.

[0017] The work vehicle 100 in this embodiment is a tractor capable of performing agricultural work while traveling in a farm field. The work vehicle 100 is not limited to a tractor, and may be other types of agricultural work vehicles, such as a transplanter or harvester. Alternatively, the work vehicle 100 may be a vehicle used for purposes other than agriculture, such as a construction work vehicle.

[0018] A working machine can be connected to the front or rear of the work vehicle 100. The work vehicle 100 can drive the working machine to perform agricultural work corresponding to the working machine. There are many different types of working machines, and by replacing the working machine, different types of agricultural work can be performed.

[0019] The work vehicle 100 in this embodiment includes a communication device (also referred to as a "direct communication unit") for communicating with the server 600. The communication device is configured to repeatedly transmit a plurality of signals, each of which indicates a different internal state of the work vehicle 100, to the server 600. There are various types of signals, and for example, 10 or more, 20 or more, 50 or more, 100 or more, or 200 or more signals are transmitted from the communication device of the work vehicle 100 to the server 600. These signals may be generated based on signals transmitted between a plurality of sensors and a plurality of electronic control units (ECUs) in the work vehicle 100. For example, each signal may be a signal flowing through a bus such as a CAN (Control Area Network) in the work vehicle 100, or a signal processed based on a signal flowing through a bus. In this embodiment, the multiple signals transmitted from the work vehicle 100 to the server 600 may include not only signals indicating vehicle speed, engine on / off information, engine speed, PTO clutch on / off information, PTO clutch speed, and engine load factor, as disclosed in Patent Documents 1 and 2, for example, but also many more signals. The transmitted signals may include, for example, one or more of the following signals: - Signal indicating the measurement value of the draft sensor that measures the load caused by towing the work machine - Signal showing the driving speed (vehicle speed) of the work vehicle - Signal indicating the rotation speed of the power take-off (PTO) shaft that drives the implement - Signal indicating the height position of the coupling device (e.g. 3-point hitch) that connects the work machine -Signal indicating the rotation speed of the engine -Signal indicating the position of the hand accelerator - Signal indicating torque acting on the engine - Signals showing the direction of travel of work vehicles - Signals showing the location of work vehicles -Signal indicating gear shift status

[0020] A signal indicating a basic statistical quantity such as the average, standard deviation, or variance of such a signal over a predetermined time (e.g., 10 seconds, 30 seconds, 60 seconds, etc.) may be included in the transmitted signal. Each signal may be transmitted in association with a vehicle ID, which is an identifier of the work vehicle 100, and time information (timestamp) indicating the time when the signal was generated. The communication device of the work vehicle 100 may be configured to repeatedly transmit multiple signals to the server 600 at a predetermined time interval (e.g., 0.5 seconds, 1 second, or 2 seconds). This time interval may be set to a value of, for example, 5 seconds or less, more preferably 2 seconds or less. Note that the frequency of transmission may differ depending on the signal. For example, a signal whose value does not change frequently, such as a signal indicating the height position of a three-point hitch, may be transmitted only when the value changes.

[0021] The server 600 functions as a processing device that acquires a plurality of signals from the work vehicle 100 and estimates the type of work machine connected to the work vehicle 100 based on the signals. The server 600 performs pre-processing on the acquired plurality of signals to generate a plurality of time series data corresponding to the plurality of signals. The server 600 generates time series data having the values ​​of each signal for every fixed time (for example, 0.5 seconds, 1 second, 2 seconds, etc.), and generates input data based on the time series data. The pre-processing may include, for example, resampling the values ​​of the transmitted signal at fixed time intervals (for example, 1 second), complementing missing data, and correcting outliers. The server 600 generates input data indicating the time-dependent changes in a plurality of feature quantities based on the time series data including the values ​​of each signal for each time after the pre-processing. The feature quantities may be obtained by, for example, calculating the moving average, rate of change, or moving standard deviation of the signal values. For example, the moving average of the vehicle speed, the moving standard deviation of the acceleration, the moving average of the draft sensor values, the rate of change of the engine speed, the moving standard deviation of the hitch position, etc. may be generated as the feature quantities. In the following description, the feature amount contained in the input data may also be referred to as a "signal."

[0022] The storage device of the server 600 stores one or more machine learning models (trained models) that have been trained in advance. The models are models for estimating the type of work machine based on input data. The models are generated by commands from the manufacturer computer 500, and are trained using learning data transmitted from the manufacturer computer 500 as needed. The server 600 estimates the type of work machine 300 by inputting the input data into the trained models.

[0023] As the machine learning algorithm to be used, for example, an algorithm based on a decision tree may be used. By using a decision tree, it is possible to know what criteria were used to estimate the type of work machine, making it easier to improve the model compared to other black-box models in which the criteria are unknown. As the algorithm based on a decision tree, for example, ID3, C4.5, CART, CHAID, or random forest may be used. Not limited to the algorithm using a decision tree, other machine learning algorithms such as a neural network or a support vector machine may be used.

[0024] As will be described in detail later, the learned model may include a first model for determining whether the work vehicle 100 is working or in another state, and a second model for identifying the type of work implement connected to the work vehicle 100. In this case, the server 600 may be configured to estimate the work implement using the second model only when it is determined that the work vehicle 100 is working by estimation using the first model. By performing such a two-step estimation, the type of work implement 300 can be estimated more accurately than when the work implement is estimated in one step.

[0025] When the server 600 estimates the type of the work implement, it generates output data including information indicating the estimated type of the work implement. The output data may be generated constantly (e.g., every 0.5 seconds, 1 second, or 2 seconds) while the work vehicle 100 is in operation. The output data may include not only the estimated type of work implement but also information indicating the operation state of the work vehicle 100. The information indicating the operation state may include, for example, information on whether the work vehicle is working, traveling without work (referred to as "non-work traveling"), turning on the headland (referred to as "turning on the headland"), or idling. The information indicating the operation state may also include information such as vehicle speed, fuel consumption, or total operation time from a certain point in time. The server 600 transmits the output data to another computer such as the dealer terminal 400.

[0026] The dealer terminal 400 is a terminal device used by a supervisor (e.g., a dealer's staff member) who performs status monitoring, maintenance, or fault diagnosis of the work vehicle 100. The dealer terminal 400 shown in FIG. 1 is a laptop PC (Personal Computer) with a built-in display. The dealer terminal 400 may be a desktop PC with an external display. Alternatively, the dealer terminal 400 may be another type of computer such as a tablet computer or a smartphone. The dealer terminal 400 displays information indicating the time-series operating status of the work vehicle 100 on the display based on the output data transmitted from the server 600. The information indicating the time-series operating status may include, for example, information indicating the presence or absence of work for each day and time period, the type of work, or the type of work machine used. Based on the displayed information, the supervisor can grasp in real time how the work vehicle 100 is being used.

[0027] The dealer of the work vehicle 100 sells or rents the work vehicle 100 to users or agricultural managers, and also performs maintenance and repair of the work vehicle 100. In order to perform repairs and maintenance, it is important to know how the work vehicle 100 is usually used. In particular, it is important to know what kind of work equipment the user connects to the work vehicle 100 and uses to perform the work. However, with the conventional technology, it was not possible to accurately know what kind of work equipment the work vehicle 100 is equipped with and used, and maintenance and other tasks could not be performed efficiently. In particular, when the dealer's area of ​​responsibility is large, it was necessary to visit multiple users scattered over a wide area and conduct interviews to check the status of each work vehicle. According to this embodiment, the dealer can remotely use the dealer terminal 400 to know the type of work equipment connected to each work vehicle 100 and the operating status of the work vehicle 100. This reduces the frequency of visits and greatly improves the efficiency of maintenance and other tasks.

[0028] The manufacturer computer 500 is a computer for instructing the server 600 to generate and train a machine learning model. The manufacturer computer 500 may be any computer, such as a server computer, a personal computer (PC), a tablet computer, or a smartphone. The manufacturer computer 500 may be used, for example, by a person in charge of the manufacturer. The manufacturer computer 500 transmits learning data to the server 600 in response to an operation by the person in charge or according to a set schedule. The server 600 trains (learns) the machine learning model based on the transmitted learning data. The model training based on the learning data may be performed, for example, daily. This allows the trained model to be repeatedly improved, and the accuracy of estimation can be improved.

[0029] The server 600 may transmit output data including information such as the type of work equipment connected to each work vehicle 100 to the manufacturer computer 500. In this case, the manufacturer can grasp how each work vehicle 100 is being used. This makes it easier to identify the cause, for example, if a malfunction or breakdown occurs in the work vehicle 100. The manufacturer can use the information indicating the operating status of each work vehicle 100 obtained from the server 600 in future product development.

[0030] The configuration and operation of each component will be described in more detail below.

[0031] <Overview of work vehicle configuration> FIG. 2 is a side view showing an example of a work vehicle 100 and a work implement 300 coupled to the work vehicle 100. The work vehicle 100 includes a vehicle body 101, a prime mover 102, and a transmission 103. The vehicle body 101 is provided with wheels 104 with tires and a cabin 105. The wheels 104 include a pair of front wheels 104F and a pair of rear wheels 104R. A driver's seat 107, a steering device 106, and a group of switches for operation are provided inside the cabin 105. One or both of the front wheels 104F and the rear wheels 104R may be replaced with a plurality of wheels (crawlers) equipped with tracks instead of tires.

[0032] The work vehicle 100 further includes a GNSS unit 120. GNSS (Global Navigation Satellite System) is a general term for satellite positioning devices such as GPS (Global Positioning System), QZSS (Quasi-Zenith Satellite System, e.g., Michibiki), GLONASS, Galileo, and BeiDou. The GNSS unit 120 includes an antenna that receives signals from GNSS satellites, and a processor that determines the position of the work vehicle 100 based on the signals received by the antenna. The GNSS unit 120 receives GNSS signals transmitted from a plurality of GNSS satellites, and performs positioning based on the GNSS signals. In this embodiment, the GNSS unit 120 is provided on the top of the cabin 105, but may be provided in another position.

[0033] The prime mover 102 may be, for example, a diesel engine. An electric motor may be used instead of a diesel engine. The transmission 103 can change the propulsive force and travel speed of the work vehicle 100 by changing gears. The transmission 103 can also switch the work vehicle 100 between forward and reverse.

[0034] The steering device 106 includes a steering wheel, a steering shaft connected to the steering wheel, and a power steering device that assists steering by the steering wheel. The front wheels 104F are steered wheels, and the traveling direction of the work vehicle 100 can be changed by changing the turning angle (also referred to as the "steering angle"). The steering angle of the front wheels 104F can be changed by operating the steering wheel. The power steering device includes a hydraulic device or an electric motor that supplies an auxiliary force for changing the steering angle of the front wheels 104F. When automatic steering is performed, the steering angle is automatically adjusted by the force of the hydraulic device or the electric motor under the control of a control device arranged in the work vehicle 100.

[0035] A coupling device 108 is provided at the rear of the vehicle body 101. The coupling device 108 includes, for example, a three-point support device (also referred to as a "three-point hitch"), a PTO (Power Take Off) shaft, a universal joint, and a communication cable. The coupling device 108 can attach and detach the working equipment 300 to and from the work vehicle 100. The coupling device 108 can raise and lower the three-point hitch using, for example, a hydraulic device, and control the position or attitude of the working equipment 300. In addition, power can be sent from the work vehicle 100 to the working equipment 300 via the universal joint. The work vehicle 100 can make the working equipment 300 perform a predetermined task while towing the working equipment 300. The coupling device may be provided at the front of the vehicle body 101. In that case, the working equipment can be connected to the front of the work vehicle 100.

[0036] 2 is a rotary tiller, but the working machine 300 is not limited to a rotary tiller. For example, any working machine such as a mower, a seeder, a spreader, a rake, a baler, a harvester, a sprayer, or a harrow can be connected to the work vehicle 100 and used.

[0037] <Example of work vehicle and server configuration> Fig. 3 is a block diagram showing an example configuration of work vehicle 100 and server 600. Work vehicle 100 in the example of Fig. 3 includes a GNSS unit 120, an operation switch group 130, a drive unit 140, a sensor group 150, a storage device 170, a control device 180, a communication device 190, and the operation switch group 130. These components can be connected to each other via a bus so as to be able to communicate with each other.

[0038] The drive device 140 includes various devices necessary for the travel of the work vehicle 100 and the driving of the work equipment 300, such as the above-mentioned prime mover 102, transmission 103, steering device 106, and coupling device 108. The prime mover 102 may include an internal combustion engine such as a diesel engine. The drive device 140 may include an electric motor for traction instead of or in addition to the internal combustion engine.

[0039] The sensor group 150 includes various sensors such as an engine rotation sensor 151, an axle rotation sensor 152, a PTO rotation sensor 153, a hitch position sensor 154, and a draft sensor 155. The engine rotation sensor 151 measures the rotation speed of the engine, that is, the number of rotations per unit time (for example, one minute). The axle rotation sensor 152 measures the rotation speed of the axle connected to the wheels 104. The PTO rotation sensor 153 measures the rotation speed of the PTO shaft. The hitch position sensor 154 measures the height position of the three-point hitch. The draft sensor 155 measures the load associated with towing the work machine 300. The sensor group 150 may also include various sensors such as a temperature sensor, a fuel sensor, a water temperature sensor, an oil level gauge, a shuttle sensor, a hand accelerator sensor, an accelerator pedal sensor, a main shift lever sensor, an auxiliary shift lever sensor, an acceleration sensor, and an angular velocity sensor. The signals output from these sensors can be sent to the control device 180 via the bus and transmitted to the server 600 by the communication device 190.

[0040] The control device 180 is an assembly of multiple ECUs. The control device 180 includes, for example, an ECU 181 for communication control, an ECU 182 for engine control, and an ECU 183 for gear shift control. The control device 180 may also include various other ECUs, such as an ECU for steering control, an ECU for PTO control, and an ECU for hydraulic control. The ECU 181 for communication control controls the transmission of signals by the communication device 190. The operation of the multiple ECUs included in the control device 180 realizes the running of the work vehicle 100, the work by the work machine 300, and communication with the server 600. These ECUs can communicate with each other according to a vehicle bus standard such as CAN. Each ECU may include one or more processors and one or more memories.

[0041] The communication device 190 is a device that performs wireless communication, such as a TCU (Telematics Control Unit). The communication device 190 communicates with the server 600 via a network 80. The network 80 may include, for example, a cellular mobile communication network such as 3G, 4G, or 5G, a wireless communication network such as Wi-Fi (Wireless Fidelity, registered trademark), or LPWA (Low Power Wide Area), and the Internet. The communication device 190 communicates with the server 600 via a plurality of network devices, such as routers and switches, included in the network 80.

[0042] The communication device 190 transmits data including a plurality of signals indicating different internal states of the work vehicle 100 to the server 600 in accordance with an instruction from the communication control ECU 181 in the control device 180. The communication device 190 includes a processing circuit 192 that generates data including a plurality of signals, and a communication circuit 194 that transmits the data wirelessly. The communication device 190 transmits various signals flowing through the CAN bus to the server 600 at a predetermined time interval determined for each signal. The communication device 190 may be directly connected to the communication control ECU 181 in the control device 180 instead of being connected to the bus. The type of signal transmitted by the communication device 190 may be set by the communication control ECU 181. The function of generating transmission data by the processing circuit 192 may be implemented in the communication control ECU 181 in the control device 180. In that case, the combination of the communication control ECU 181 and the communication device 190 may be called a "communication device."

[0043] The communication device 190 may be manufactured and sold independently of the work vehicle 100. For example, the communication device 190 may be later attached to a work vehicle 100 that does not have a communication device 190, thereby realizing the communication function in this embodiment.

[0044] The storage device 170 includes one or more storage media, such as a flash memory or a magnetic disk. The storage device 170 stores signals output from each sensor and various data generated by the control device 180. The storage device 170 may also be configured to store computer programs that cause each ECU in the control device 180 to execute various operations. Such computer programs may be provided to the work vehicle 100 via a storage medium (e.g., a semiconductor memory or an optical disk) or an electric communication line (e.g., the Internet). Such computer programs may be sold as commercial software.

[0045] FIG. 4 is a diagram showing an example of the operation switch group 130 provided inside the cabin 105. Inside the cabin 105, the operation switch group 130 including a plurality of switches (including buttons, levers, and pedals) that can be operated by the user is arranged. The operation switch group 130 may include, for example, a switch (e.g., a button) for switching the main gear shift stage, a switch (e.g., a shift lever) for switching the sub gear shift stage, a switch (e.g., a shuttle lever) for switching between forward and reverse, a switch for raising and lowering the work machine 300, and the like. Pedals such as a clutch pedal, an accelerator pedal, and a brake pedal are also included in the operation switch group 130. Each switch is provided with a sensor that detects the state of the switch. These sensors are also included in the sensor group 150.

[0046] Next, the hardware configuration of the server 600 will be described.

[0047] 3, the server 600 includes a storage device 650, a processing circuit 660, a read only memory (ROM) 670, a random access memory (RAM) 680, and a communication circuit 690. These components are connected to each other via a bus so as to be able to communicate with each other.

[0048] The communication circuit 690 is a communication module for communicating with an external device such as the work vehicle 100 via the network 80. The communication circuit 690 can perform wired communication conforming to a communication standard such as IEEE1394 (registered trademark) or Ethernet (registered trademark). The communication circuit 690 may perform wireless communication conforming to the Bluetooth (registered trademark) standard or the Wi-Fi standard, or cellular mobile communication such as 3G, 4G, or 5G.

[0049] The storage device 650 may be, for example, a magnetic storage device or a semiconductor storage device. An example of a magnetic storage device is a hard disk drive (HDD). An example of a semiconductor storage device is a solid state drive (SSD). The storage device 650 may be a device independent of the server 600. For example, the storage device 650 may be a storage device connected to the server 600 via the network 80, such as a cloud storage. The storage device 650 may store data transmitted from the work vehicle 100 and one or more trained models for estimating the type of the work machine 300 connected to the work vehicle 100.

[0050] The processing circuit 660 may be a semiconductor integrated circuit including a central processing unit (CPU), for example. The processing circuit 660 may be realized by a microprocessing circuit or a microcontroller. Alternatively, the processing circuit 660 may be realized by a field programmable gate array (FPGA) equipped with a CPU, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), an application specific standard product (ASSP), or a combination of two or more circuits selected from these circuits. The processing circuit 660 sequentially executes a computer program stored in the ROM 670, which describes a group of instructions for executing at least one process, to realize a desired process. For example, the processing circuit 660 estimates the work machine 300 connected to the work vehicle 100 based on data transmitted from the communication device 190 of the work vehicle 100 and a trained model stored in the storage device 650. The processing circuit 660 transmits output data including the estimation result to the dealer terminal 400 via the communication circuit 690. The processing circuitry 660 also generates and trains machine learning models based on instructions from the manufacturer computer 500.

[0051] The ROM 670 is, for example, a writable memory (e.g., PROM), a rewritable memory (e.g., flash memory), or a read-only memory. The ROM 670 stores a program that controls the operation of the processing circuit 660. The ROM 670 does not need to be a single storage medium, and may be a collection of multiple storage media. A part of the collection of multiple storage media may be a removable memory.

[0052] The RAM 680 provides a working area for temporarily loading, at boot time, the control program stored in the ROM 670. The RAM 680 does not have to be a single storage medium, and may be a collection of multiple storage media.

[0053] <Example of dealer terminal and manufacturer computer configuration> FIG. 5 is a block diagram showing an example of the hardware configuration of the dealer terminal 400 and the manufacturer computer 500. As shown in FIG.

[0054] The dealer terminal 400 includes an input device 420, a display 430, a storage device 450, a processing circuit 460, a ROM 470, a RAM 480, and a communication circuit 490. These components are connected to each other via a bus so as to be able to communicate with each other. The input device 420 is a device for converting instructions from a user into data and inputting the data to the processing circuit 460. The input device 420 may include, for example, a keyboard, a mouse, or a touch panel. The display 430 may be any display such as a liquid crystal display or an organic EL display. The hardware configurations of the processing circuit 460, the ROM 470, the RAM 480, the storage device 450, and the communication circuit 490 are similar to the hardware configurations of the corresponding devices in the server 600. The dealer terminal 400 is used to request output data indicating the operating state of the work vehicle 100 from the server 600 and to display an image based on the output data.

[0055] The manufacturer computer 500 includes a processing circuit 560, a ROM 570, a RAM 580, a storage device 550, and a communication circuit 590. The hardware configurations of the processing circuit 560, the ROM 570, the RAM 580, the storage device 550, and the communication circuit 590 are the same as the hardware configurations of the corresponding devices in the server 600. The manufacturer computer 500 may be used by being connected to an input device such as a keyboard and a mouse, and a display such as a liquid crystal display or an organic EL display. Alternatively, the manufacturer computer 500 may include an input device and a display. The manufacturer computer 500 is used to instruct the server 600 to generate and learn a machine learning model.

[0056] <Example of communication operation> 6 is a flowchart showing an example of the data transmission operation by the communication device 190 of the work vehicle 100. The communication device 190 repeats the operations of steps S110 to S130 to sequentially transmit a plurality of signals indicating the internal state of the work vehicle 100 to the server 600. This operation can be performed at all times while the work vehicle 100 is in operation (e.g., while the engine is on).

[0057] In step S110, the processing circuit 192 of the communication device 190 generates transmission data including a plurality of signals each indicating an internal state of the work vehicle 100. The number of types of the plurality of signals is 10 or more, and can be typically 100 or more or 200 or more. These signals can be generated based on signals output from the sensor group 150. The transmission data can include not only the signals themselves output from the sensor group 150, but also signals indicating values ​​such as the average value or standard deviation of the signals over a predetermined period of time (e.g., 10 seconds). The processing circuit 192 generates data that associates each signal with a vehicle ID and a timestamp indicating the time when the signal was generated.

[0058] In step S120, the processing circuitry 192 transmits the generated data to the server 600 via the communication circuitry 194.

[0059] In step S130, the processing circuit 192 determines whether or not the operation of the work vehicle 100 has stopped. The processing circuit 192 determines that the operation of the work vehicle 100 has stopped when, for example, the engine is turned off. If the operation of the work vehicle 100 has stopped, the processing ends. If the operation of the work vehicle 100 has not stopped, the processing returns to step S110.

[0060] The operations of steps S110 to S130 are repeated during operation of the work vehicle 100. The generation and transmission of data to be transmitted may be repeatedly performed at predetermined time intervals (for example, 0.5 seconds, 1 second, 2 seconds, etc.).

[0061] The combination of signals included in the transmission data may be the same each time, or may be different for each transmission. For example, signals whose values ​​change frequently, such as vehicle speed and engine RPM, may be transmitted every time, and signals whose values ​​do not change frequently, such as the height position of the three-point hitch, may be transmitted only when the value changes. Which signals are transmitted and the frequency of transmission of each signal may be specified in a configuration file created by, for example, the communication control ECU 181. The communication device 190 may be configured to transmit a particular signal according to the configuration file.

[0062] 7 is a flowchart showing an example of the operation of the server 600. The server 600 repeats the processes of steps S210 to S260 to successively estimate the type of work machine 300 connected to the work vehicle 100. This operation can be performed at any time while the work vehicle 100 is in operation.

[0063] In step S210, the processing circuitry 660 of the server 600 determines whether or not data has been acquired from the work vehicle 100. As described above, data including a plurality of signals can be transmitted from the work vehicle 100 at predetermined time intervals. When the data is received by the communication circuitry 590, the process proceeds to step S220.

[0064] In step S220, the processing circuit 660 performs preprocessing based on the acquired data to generate input data to be input to the trained model. The transmission data includes values ​​of multiple signals and time information of each signal. The processing circuit 660 generates multiple time series data corresponding to multiple signals based on the values ​​and time information of each signal included in the continuously acquired transmission data. The processing circuit 660 generates input data to be input to the trained model based on the time series data.

[0065] FIG. 8 is a diagram showing an example of time-series data. The time-series data shown in FIG. 8 is data in which the date and time (for example, in units of seconds) are associated with the values ​​of each of a plurality of signals. In the example of FIG. 7, the values ​​of signals S1, S2, S3, S4, . . . are associated with each second. Each of the signals S1, S2, S3, S4, . . . represents a signal such as a vehicle speed, an engine rotation speed, a PTO shaft rotation speed, a height position of a three-point hitch, a measurement value of a draft sensor, and the like. Although four signals are shown as an example in FIG. 8, the number of types of signals may be 10 or more, 50 or more in one example, 100 or more in another example, and 200 or more in still another example. The time-series data may be data over a period of, for example, several seconds to several tens of seconds, or in some cases, several hundred seconds.

[0066] Signals transmitted from the work vehicle 100 may include signals transmitted at time intervals longer than one second. For example, signals may be transmitted every 10 seconds, or signals may be transmitted irregularly only when a value changes. For such signals, the processing circuit 660 may generate time series data by interpolating values ​​for times that do not have values.

[0067] Based on such time series data, the processing circuit 660 generates input data including a plurality of features to be input to the trained model. Each feature may be the signal value itself, or may be a value obtained by averaging the signal value over a certain time (e.g., 10 seconds, 30 seconds, 60 seconds, etc.) or calculating the standard deviation. Alternatively, each feature may be a value calculated by combining two or more signals in the time series data. The input data may be a combination of, for example, 10 or more, 20 or more, 50 or more, 100 or more, or 200 or more features.

[0068] 7, the processing circuitry 660 inputs the generated input data into one or more trained models to estimate the type of work implement 300 connected to the work vehicle 100. The trained models may be generated and trained by a machine learning algorithm, such as a decision tree, as described above.

[0069] FIG. 9 is a flowchart showing a more specific example of the process of step S230. In the example of FIG. 9, step S230 includes the processes of steps S231, S232, and S233. In this example, the input data includes first input data and second input data, and the trained model includes a first model and a second model. The first input data and the second input data may be the same or different. The first model is a model for determining whether the work vehicle 100 is working or in another state based on the first input data. The second model is a model for estimating the type of the work machine 300 based on the second input data. Each of the first model and the second model is a model based on a machine learning algorithm such as a decision tree.

[0070] In step S231, the processing circuit 660 inputs the first input data into the first model to determine whether the work vehicle 100 is working or in another state. The first model can be, for example, a model for determining whether the work vehicle 100 is working, traveling non-working, turning on the headland, or idling based on the first input data. In this case, the processing circuit 660 can determine whether the work vehicle 100 is working, traveling non-working, turning on the headland, or idling by inputting the first input data into the first model. Here, "working" refers to a state in which the work implement is driven. "Non-work traveling" refers to a state in which the work implement is not driven and the vehicle is traveling in a place other than the headland. "Turning on the headland" refers to a state in which the vehicle is turning on the headland outside the work area to travel back and forth within the field. "Idling" refers to a state in which the vehicle is stopped with the engine running.

[0071] In step S232, processing circuit 660 determines whether or not work vehicle 100 is working based on the determination result of step S231. If work vehicle 100 is working, the process proceeds to step S233. If work vehicle 100 is in a state other than working, step S230 ends and the process proceeds to step S240.

[0072] In step S233, the processing circuit 660 inputs the second input data into a second model to estimate the type of work implement 300 connected to the work vehicle 100. After step S233, the process proceeds to step S240.

[0073] 9, step S230 of estimating the type of work implement 300 includes a first step (step S231) of inputting first input data into a first model to determine whether the work vehicle 100 is working or in another state, and a second step (step S233) of inputting second input data into a second model to estimate the type of work implement 300 when it is determined that the work vehicle 100 is working. More specifically, the first step includes determining whether the work vehicle 100 is in a state of working, not working, turning around the headland, or idling. By performing such two-step processing, more accurate estimation is possible compared to estimating the type of work implement 300 in one step.

[0074] 10 is a diagram illustrating a decision tree that is an example of a trained model used in the determination process of the first step (step S231). In this decision tree, whether the work vehicle 100 is in a working state, a non-working state, a headland turning state, or another state (e.g., idling) is determined based on the signals or feature amounts shown in Table 1 below that are included in the input data.

[0075] [Table 1]

[0076] In the example shown in Fig. 10, c1, c2, c3, c4, and c5 represent certain constants and are determined based on a decision tree algorithm. It is also possible to display the discrimination results as shown in Fig. 10 on a display by using software that implements the decision tree algorithm. Such a display allows, for example, a user of the manufacturer computer 500 to know the basis of the estimation.

[0077] Note that the above signals or feature amounts are merely examples, and the state of the work vehicle 100 may be determined based on signals or feature amounts other than these. In the example of Fig. 10, the four types of feature amounts shown in Table 1 are used, but estimation may be performed based on a decision tree at a deeper level using more feature amounts. The order of judgments based on the respective feature amounts is not limited to the order shown in the figure, and may be changed depending on the algorithm or learning content used.

[0078] 11 is a diagram showing a decision tree that is an example of a trained model used in the determination process of the second step (step S233). In this decision tree, it is determined whether the type of work machine 300 connected to the work vehicle 100 is a baler, seed drill, harrow, shredder, stubble couch, plow, tedder, or front loader. The type of work machine 300 is determined based on the signals or feature amounts shown in Table 2 below that are included in the input data.

[0079] [Table 2]

[0080] In the example shown in Fig. 11, d1, d2, d3, d4, d5, d6, and d7 represent certain constants and are determined based on a decision tree algorithm. It is also possible to display the discrimination results as shown in Fig. 11 on a display by using software that implements the decision tree algorithm. Such a display allows, for example, a user of the manufacturer computer 500 to know the basis of the estimation.

[0081] The above signals or features are merely examples, and the type of the work machine 300 may be determined based on signals or features other than these. Also, models capable of determining other types of work machines may be used, not limited to balers, seed drills, harrows, shredders, stubble couches, plows, tedders, and front loaders. In the example of FIG. 11, six types of features shown in Table 2 are used, but estimation may be performed based on a decision tree with a deeper hierarchy using more features. The order of judgment based on each feature is not limited to the order shown in the figure, and may be changed depending on the algorithm or learning content used.

[0082] Here, examples of signal waveforms that differ depending on the type of work machine 300 will be described with reference to Figs.

[0083] FIG. 12 shows an example of a signal waveform in a certain working machine 300 (hereinafter referred to as "working machine 1"). FIG. 13 shows an example of a signal waveform in another working machine 300 (hereinafter referred to as "working machine 2"). FIG. 14 shows an example of a signal waveform in yet another working machine 300 (hereinafter referred to as "working machine 3"). The working machines 1, 2, and 3 are different types of working machines, and the uses of these working machines are different. FIGS. 12, 13, and 14 show waveforms showing time changes of four signals (signal 1, signal 2, signal 3, and signal 4). Signals 1 to 4 represent signals such as the height of a three-point hitch, the measurement value of a draft sensor, the vehicle speed, and the value of a PTO indicator lamp. Note that, although more signals may be used in practice, FIGS. 12 to 14 show waveforms of four signals as examples. As can be seen from these figures, when the type of working machine 300 is different, the waveforms of each signal are significantly different. In this embodiment, by using a machine learning model that estimates the type of work implement 300 based on the differences in these signal waveforms, the type of work implement 300 connected to the work vehicle 100 can be estimated with high accuracy.

[0084] Please refer to Figure 7 again. After the process of step S230 ends, the process proceeds to step S240.

[0085] In step S240, the processing circuit 660 generates output data including information on the state of the work vehicle 100 estimated in step S230 (working, not working, turning on the headland, idling, etc.) and the type of work implement 300 connected to the work vehicle 100. The output data may be, for example, data in which the date, time (e.g., in seconds), vehicle ID, the estimated state of the work vehicle 100, and the estimated type of work implement 300 are correlated with each other. The output data may also include the position of the work vehicle 100 measured by the GNSS unit 120 and measurement values ​​of one or more sensors included in the sensor group 150 (e.g., vehicle speed, remaining fuel, fuel consumption, total operating time, etc.).

[0086] In step S250, processing circuit 660 transmits the output data to dealer terminal 400 via communication circuit 690. Dealer terminal 400 records the transmitted output data in storage device 450. Dealer terminal 400 can generate and display an image showing the operating state of work vehicle 100 based on the output data in response to an operation by a user (e.g., a dealer's staff member).

[0087] In step S260, the processing circuit 660 determines whether or not to end the operation. For example, when an instruction to end the operation is given from an external computer such as the manufacturer computer 500, the processing circuit 660 determines that the operation is to be ended. The instruction to end the operation may be given, for example, when stopping the estimation operation to further train the learned model using new learning data. The processing from step S210 to S260 is repeated until the instruction to end the operation is given.

[0088] In the example of FIG. 7, after step S230, the generation of output data in step S240 and the transmission of the output data in step S250 are performed successively. In this case, the generation and transmission of the output data are performed at the same frequency as the frequency at which data is received from the work vehicle 100 (for example, every second). Instead of such an operation, for example, the generation and transmission of the output data in steps S240 and S250 may be performed after a plurality of estimation processes are completed. For example, the generation and transmission of the output data may be performed collectively at a predetermined time interval, such as once every 10 seconds or once every 100 seconds. Alternatively, the processing circuit 660 may generate and transmit the output data to the dealer terminal 400 only when requested by the dealer terminal 400.

[0089] Next, an operation of displaying the operating state of the work vehicle 100 by the dealer terminal 400 will be described.

[0090] FIG. 15 is a flow chart illustrating an example of operations performed by the processing circuitry 460 of the dealer terminal 400.

[0091] In step S310, processing circuit 460 determines whether or not an operation to display operation information of work vehicle 100 has been performed via input device 420. This operation may be performed, for example, by a maintenance technician for work vehicle 100 at a dealer. If this operation has been performed, the process proceeds to step S320.

[0092] In step S320, the processing circuitry 460 acquires the output data transmitted from the server 600 by reading it from the storage device 450. The server 600 may be configured to transmit the output data to the dealer terminal 400 in response to a request from the dealer terminal 400. In this case, the processing circuitry 460 acquires the output data by requesting the output data from the server 600 via the communication circuitry 490.

[0093] In step S340, the processing circuit 460 generates a display image including information showing the time-series operating state of the work vehicle 100 based on the output data, and causes the display 430 to display the image.

[0094] FIG. 16 is a diagram showing an example of an image displayed on the display 430. The display image in this example includes a plurality of display areas 431, 432, 433, and 434. The display area 431 shows the date and time on which the work vehicle 100 performed work. The display area 432 shows the usage rate of each work implement during a certain period. The display area 433 shows the fuel consumption per hour (average fuel consumption), the operation rate, the operation time, the idling time, and the fuel consumption during that period. The display area 434 shows detailed operation information of the work vehicle 100 during that period. The display area 434 displays information on the time, fuel consumption, average fuel consumption, average engine revolutions (RPM), and average PTO revolutions (RPM) for each of the states in which the work vehicle 100 is stopped (idling state), working, turning on the headland, and traveling without work. For the state in which work is being performed, the information is displayed for each type of work implement used.

[0095] By displaying such information, the dealer's staff can understand how the work vehicle 100 is being used. This allows, for example, early detection of breakdowns or malfunctions of the work vehicle 100, or signs of such breakdowns or malfunctions, and allows efficient maintenance, such as part replacement and repairs.

[0096] 16 is merely an example, and the layout of the display screen is not limited to that shown in the figure. What is displayed based on the data transmitted from the server 600 is appropriately determined according to the purpose.

[0097] In this embodiment, the dealer terminal 400 generates and displays a display image based on the output data transmitted from the server 600, but a similar operation may be performed by the manufacturer computer 500. For example, the server 600 may transmit output data including the estimated results of the work machine to the manufacturer computer 500 in response to a request from the manufacturer computer 500. The manufacturer computer 500 may display a display image such as that shown in Fig. 16 on the display based on the output data. Such a display allows the manufacturer's personnel to obtain knowledge about how the work vehicle 100 is actually used, and the knowledge can be used for future product development or services.

[0098] The same operation as that of the dealer terminal 400 may be performed by a terminal device used by a user or owner (e.g., an agricultural manager) of the work vehicle 100. For example, the server 600 may transmit output data including the estimated results of the work machine to the terminal device in response to a request from the terminal device. The terminal device may display a display image as shown in FIG. 16 on the display based on the output data. By such a display, for example, the agricultural manager can check how the work vehicle 100 is being used, which can lead to future improvements in agricultural management. For example, if it is found that the work vehicle 100 used by the employer is idling too much, the employer can be instructed to reduce idling, thereby reducing fuel consumption. Also, if it is found that there are too many headland turns, a decision can be made to introduce a wider work machine to reduce the number of turns or to introduce a larger work vehicle.

[0099] A similar judgment can also be made by the dealer's staff. When the dealer's staff sees, for example, that there are too many headland turns by looking at a display screen like that shown in Fig. 16, they can suggest the introduction of a wider implement or a larger work vehicle. This can lead not only to more efficient maintenance work but also to improved sales activities.

[0100] In the above embodiment, the system includes one or more work vehicles 100, a server 600, a dealer terminal 400, and a manufacturer computer 500, but this is merely an example. For example, the system may include only some of these devices. Also, each of the server 600, the dealer terminal 400, and the manufacturer computer 500 may be another type of computer. For example, both the server 600 and the manufacturer computer 500 may be computers managed by the manufacturer of the work vehicle 100. Also, a company other than the manufacturer of the work vehicle 100 may sell or operate a communication device mounted on the work vehicle 100 or a computer that collects signals from the communication device and executes the estimation process according to this embodiment. Such a company may further use a terminal device similar to the dealer terminal 400 to monitor the operating status of the work vehicle 100 and provide services such as maintenance.

[0101] The computer programs that define the methods executed by each device in the above-mentioned embodiments may be manufactured and sold separately from the devices. The computer programs may be provided, for example, by being stored in a computer-readable non-transitory storage medium. The computer programs may also be provided by downloading via a telecommunications line (for example, the Internet).

[0102] As described above, the present disclosure includes methods, processing devices, programs, communication devices, work vehicles, terminal devices, and systems described in the following items.

[0103] [Item 1] 1. A method implemented by one or more computers in communication with a work vehicle that drives a connected work implement to perform work, comprising: repeatedly acquiring 10 or more signals from the work vehicle, each signal indicative of a different internal state of the work vehicle; generating input data based on the ten or more signals; inputting the input data into one or more trained models for estimating the type of the work machine based on the input data to estimate the type of the work machine; generating and outputting output data including information indicating the estimated type of the work machine; The method includes:

[0104] [Item 2] 2. The method according to claim 1, wherein the step of generating input data includes generating ten or more time series data corresponding to the ten or more signals, respectively, and generating the input data based on the time series data.

[0105] [Item 3] the input data includes first input data and second input data; the one or more trained models include a first model for determining whether the work vehicle is working or in another state based on the first input data, and a second model for estimating the type of the work machine based on the second input data; The estimating step includes: a first step of inputting the first input data into the first model to determine whether the work vehicle is working or in another state; a second step of estimating the type of the work machine by inputting the second input data into the second model when it is determined that the work vehicle is working; The method according to item 1 or 2, comprising:

[0106] [Item 4] the first model is a model for determining whether the work vehicle is in a working state, a non-work traveling state, a headland turning state, or an idling state, based on the first input data; The first step includes inputting the first input data into the first model to determine whether the work vehicle is in a working state, a non-work traveling state, a headland turning state, or an idling state. The method according to item 3.

[0107] [Item 5] 5. The method according to claim 3 or 4, wherein each of the first model and the second model is a decision tree-based model.

[0108] [Item 6] 6. The method of any one of items 1 to 5, wherein the 10 or more signals are 20 or more signals.

[0109] [Item 7] 7. The method of any one of items 1 to 6, wherein the 10 or more signals are 50 or more signals.

[0110] [Item 8] 8. The method according to any one of items 1 to 7, wherein the ten or more signals include a signal indicating a measurement value of a draft sensor that measures a load associated with towing the work machine.

[0111] [Item 9] The method according to any one of items 1 to 8, wherein the ten or more signals include a signal indicating the travel speed of the work vehicle, a signal indicating the rotational speed of a power take-off (PTO) shaft that drives the work machine, a signal indicating the height position of a coupling device that couples the work machine, and a signal indicating the rotational speed of a prime mover.

[0112] [Item 10] 10. The method according to any one of claims 1 to 9, wherein each of the ten or more signals is generated based on a signal flowing through a Control Area Network (CAN) bus in the work vehicle.

[0113] [Item 11] 11. The method according to any one of claims 1 to 10, wherein the outputting step includes transmitting the output data to another computer.

[0114] [Item 12] the other computer is a terminal device used by a supervisor who performs status monitoring, maintenance, or fault diagnosis of the work vehicle; The output data is used to display a time-series operating status of the work vehicle on a display of the terminal device. Item 12. The method according to item 11.

[0115] [Item 13] 13. The method according to any one of items 1 to 12, wherein the work vehicle is an agricultural tractor and drives the implement to perform agricultural work.

[0116] [Item 14] A processing device that communicates with a work vehicle that drives a connected work machine to perform work, a communications circuit that repeatedly receives ten or more signals from the work vehicle, each signal indicating a different internal state of the work vehicle; a processing circuit that generates input data based on the 10 or more signals, inputs the input data to one or more trained models for estimating the type of the work machine based on the input data to estimate the type of the work machine, and generates and outputs output data including information indicating the estimated type of the work machine; A processing device comprising:

[0117] [Item 15] A computer program executed by a computer that communicates with a work vehicle that drives a connected work machine to perform work, repeatedly receiving ten or more signals from the work vehicle, each signal indicative of a different internal state of the work vehicle; generating input data based on the ten or more signals; inputting the input data into one or more trained models for estimating the type of the work machine based on the input data to estimate the type of the work machine; generating and outputting output data including information indicating the estimated type of the work machine; A computer program that causes the computer to execute the above.

[0118] [Item 16] A communication device that is mounted on a work vehicle that drives a connected work machine to perform work and communicates with the processing device described in item 14, a processing circuit for generating data including ten or more signals, each signal indicative of a different internal condition of the work vehicle; a communication circuit for transmitting the data to the processing device; A communication device comprising:

[0119] [Item 17] A work vehicle equipped with the communication device according to item 16.

[0120] [Item 18] A terminal device that communicates with the processing device according to item 14, a communication circuit for receiving the output data from the processing device; a processing circuit that displays an image showing a time-series operating state of the work vehicle on a display based on the output data; A terminal device comprising:

[0121] [Item 19] Item 15. A processing device according to item 14, A communication device according to item 16, A system comprising:

[0122] [Item 20] Item 15. A processing device according to item 14, Item 15: A work vehicle according to the present invention; A system comprising:

[0123] [Item 21] 20. The system according to claim 19, further comprising the terminal device according to claim 18.

[0124] [Item 22] providing ten or more signals to one or more computers, each signal indicative of a different internal state of the work vehicle; The one or more computers, generating input data based on the ten or more signals; inputting the input data into one or more trained models for estimating a type of a work implement connected to the work vehicle based on the input data to estimate the type of the work implement; outputting the estimation result of the type of the work machine; and The method includes:

[0125] [Item 23] A method performed by a communication device mounted on the work vehicle in communication with the computer executing the method according to item 1, generating the ten or more signals based on signals output from a plurality of devices mounted on the work vehicle; transmitting the ten or more signals to the computer; The method includes:

[0126] [Item 24] A method executed by another computer connected via a network to a computer executing the method according to item 1, Sending learning data to the computer for generating the trained model; causing the computer to generate the trained model based on the trained model; The method includes:

[0127] [Item 25] A method executed by a terminal device connected via a network to a computer that executes the method according to item 1, requesting the computer to transmit the output data; receiving the output data transmitted from the computer; displaying an image indicating the estimated type of the work machine on a display based on the output data; The method includes: [Industrial Applicability]

[0128] The technology disclosed herein can be applied to work vehicles such as tractors, transplanters, harvesters, construction vehicles, or snowplows, communication devices mounted on the work vehicles, and processing devices that communicate with the work vehicles. [Explanation of symbols]

[0129] 80 network, 100 work vehicle, 101 vehicle body, 102 prime mover, 103 transmission, 104 wheels, 105 cabin, 106 steering device, 107 driver's seat, 108 coupling device, 120 GNSS unit, 140 drive device, 150 sensor group, 170 storage device, 180 control device, 190 communication device, 300 work equipment, 400 dealer terminal, 420 input output device, 430...display, 450...storage device, 460...processing circuit, 470...ROM, 480...RAM, 490...communication circuit, 500...manufacturer computer, 550...storage device, 560...processing circuit, 570...ROM, 580...RAM, 590...communication circuit, 600...server computer, 650...storage device, 660...processing circuit, 670...ROM, 680...RAM, 690...communication circuit

Claims

1. 1. A method implemented by one or more computers in communication with a work vehicle that drives a connected work implement to perform work, comprising: repeatedly acquiring ten or more signals from the work vehicle, each signal indicative of a different internal state of the work vehicle; generating input data based on the ten or more signals; A step of estimating the type of the work machine by inputting the input data into one or more trained models for estimating the type of the work machine based on the input data; generating and outputting output data including information indicating the estimated type of the work machine; The method includes:

2. The method of claim 1 , wherein the step of generating input data comprises generating ten or more time series data respectively corresponding to the ten or more signals, and generating the input data based on the time series data.

3. the input data includes first input data and second input data; the one or more trained models include a first model for determining whether the work vehicle is working or in another state based on the first input data, and a second model for estimating the type of the work machine based on the second input data; The estimating step includes: a first step of inputting the first input data into the first model to determine whether the work vehicle is working or in another state; a second step of estimating the type of the work machine by inputting the second input data into the second model when it is determined that the work vehicle is working; The method of claim 1 , comprising:

4. the first model is a model for determining whether the work vehicle is in a working state, a non-work traveling state, a headland turning state, or an idling state, based on the first input data; The first step includes inputting the first input data into the first model to determine whether the work vehicle is in a working state, a non-work traveling state, a headland turning state, or an idling state. The method according to claim 3.

5. The method of claim 3 or 4, wherein each of the first model and the second model is a decision tree based model.

6. The method of claim 1 , wherein the 10 or more signals are 20 or more signals.

7. The method of claim 1 , wherein the 10 or more signals is 50 or more signals.

8. The method according to claim 1 , wherein the ten or more signals include a signal indicating a measurement value of a draft sensor that measures a load associated with towing the work machine.

9. The method according to any one of claims 1 to 4, wherein the ten or more signals include a signal indicating the travel speed of the work vehicle, a signal indicating the rotational speed of a power take-off (PTO) shaft that drives the work machine, a signal indicating the height position of a coupling device that couples the work machine, and a signal indicating the rotational speed of a prime mover.

10. The method according to claim 1 , wherein each of the ten or more signals is generated based on a signal flowing through a Control Area Network (CAN) bus in the work vehicle.

11. The method of claim 1 , wherein the outputting step includes transmitting the output data to another computer.

12. the other computer is a terminal device used by a supervisor who performs status monitoring, maintenance, or fault diagnosis of the work vehicle; The output data is used to display a time-series operating status of the work vehicle on a display of the terminal device. The method of claim 11.

13. The method according to claim 1 , wherein the work vehicle is an agricultural tractor and drives the implement to perform agricultural work.

14. A processing device that communicates with a work vehicle that drives a connected work machine to perform work, a communications circuit that repeatedly receives ten or more signals from the work vehicle, each signal indicating a different internal state of the work vehicle; a processing circuit that generates input data based on the 10 or more signals, inputs the input data to one or more trained models for estimating the type of the work machine based on the input data to estimate the type of the work machine, and generates and outputs output data including information indicating the estimated type of the work machine; A processing device comprising:

15. A computer program executed by a computer that communicates with a work vehicle that drives a connected work machine to perform work, repeatedly receiving ten or more signals from the work vehicle, each signal indicating a different internal state of the work vehicle; generating input data based on the ten or more signals; A step of estimating the type of the work machine by inputting the input data into one or more trained models for estimating the type of the work machine based on the input data; generating and outputting output data including information indicating the estimated type of the work machine; A computer program that causes the computer to execute the above.

16. A communication device that is mounted on a work vehicle that drives a connected work machine to perform work, and communicates with the processing device according to claim 14, a processing circuit for generating data including ten or more signals, each signal indicative of a different internal condition of the work vehicle; a communication circuit for transmitting the data to the processing device; A communication device comprising:

17. A work vehicle comprising the communication device according to claim 16.

18. A terminal device in communication with the processing device according to claim 14, a communication circuit for receiving the output data from the processing device; a processing circuit that displays an image showing a time-series operating state of the work vehicle on a display based on the output data; A terminal device comprising:

19. A processing device according to claim 14; A communication device according to claim 16; A system comprising:

20. A processing device according to claim 14; A work vehicle according to claim 15; A system comprising:

21. 20. The system of claim 19, further comprising a terminal device of claim 18.

Images