Work content estimation system, and work content estimation method

Abstract

To provide a work content estimation system and a work content estimation method that can improve versatility of a machine learning model used to estimate a work content.SOLUTION: A work content estimation system includes: an acquisition portion that acquires log information of a work machine associated with a time; and an estimation portion that estimates time series of a work content of the work machine by inputting visual movement information based on the log information into a trained machine learning model that inputs the visual movement information that is time series information corresponding to visual movement of a movable portion of the work machine and outputs information representing an estimation result of the work content of the work machine.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present disclosure relates to a work content estimation system and a work content estimation method.

Background Art

[0002] Patent Document 1 describes an analysis support system including an estimation unit that estimates the work content of a work machine at each time from the log information of the work machine. The estimation unit obtains a time series of likelihoods related to unit work by inputting the log information into a unit work prediction model in chronological order. Note that the log information is time series information indicating the state of the work machine acquired by a plurality of sensors provided in the work machine. Further, Patent Document 1 lists, as examples of the log information, position information, roll angle, pitch angle, turning angle, boom angle, arm angle, bucket angle, information indicating the PPC (Proportional Pressure Control) pressure of the operating device, engine output, information indicating instantaneous fuel consumption, and the like.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above-described log information, information such as engine output and instantaneous fuel consumption is information that is easily affected by differences in the vehicle class of the work machine. Therefore, when using this information as input information for a machine learning model, it may be necessary to prepare a plurality of models according to differences in vehicle class.

[0005] An object of the present disclosure is to provide a work content estimation system and a work content estimation method that can enhance the versatility of a machine learning model used for estimating work content.

Means for Solving the Problems

[0006] The work content estimation system of the present disclosure includes an acquisition unit that acquires log information of a working machine associated with time, and a learned machine learning model that inputs appearance motion information, which is time-series information corresponding to the appearance motion of a movable part of the working machine, and outputs information representing an estimation result of the work content of the working machine. By inputting the appearance motion information based on the log information into the learned machine learning model, an estimation unit that estimates the time series of the work content of the working machine is provided.

[0007] The work content estimation method of the present disclosure includes a step of acquiring log information of a working machine associated with time, and a step of inputting appearance motion information, which is time-series information corresponding to the appearance motion of a movable part of the working machine, into a learned machine learning model that outputs information representing an estimation result of the work content of the working machine, and estimating the time series of the work content of the working machine by inputting the appearance motion information based on the log information.

Advantages of the Invention

[0008] According to the display control device and the display control method of the present disclosure, the versatility of the machine learning model used for estimating the work content can be enhanced.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0010] <First Embodiment> Hereinafter, a display control device and a display control method according to the first embodiment will be described in detail with reference to FIGS. 1 to 7.

[0011] (Overall Configuration of Analysis Support System) FIG. 1 is a diagram showing the overall configuration of an analysis support system according to the first embodiment. The analysis support system 1 includes a work content estimation system 10 and data loggers 20 mounted on each of a plurality of work machines 3.

[0012] The work machine 3 is an object of work analysis by the work content estimation system 10. Examples of the work machine 3 include a hydraulic excavator, a wheel loader, a bulldozer, and the like. In the following description, a hydraulic excavator will be described as an example of the work machine 3. A plurality of sensors are provided on each work machine 3. The data logger 20 records and accumulates in time series information indicating the state of the work machine 3 acquired by the sensor. Hereinafter, the information indicating the state of the work machine 3 at each time recorded by the data logger 20 will also be referred to as log information. In addition, when the operation mechanism for operating the work machine 3 is configured to operate the work machine 3 using an electrical operation signal, the information of the operation signal of the work machine 3 may be recorded and accumulated in time series and included in the log information. Further, the data logger 20 transmits the recorded log information to the work content estimation system 10 via a wide area communication network at regular time intervals. Note that the regular time interval is, for example, a 5-minute interval. The work content estimation system 10 records the log information received from the data logger 20 on a recording medium. The functions of the work content estimation system 10 will be described later.

[0013] (Structure of Work Machine) FIG. 2 is a diagram showing the structure of a work machine according to the first embodiment. The work machine 3, which is a hydraulic excavator, excavates and levels earth and sand at a work site or the like. As shown in FIG. 2, the work machine 3, which is a hydraulic excavator, includes a lower traveling body 31 for traveling, and an upper revolving body 32 that is installed on the upper part of the lower traveling body 31 and can revolve. Further, the upper revolving body 32 is provided with a driver's cab 32A, a working machine 32B, and two GNSS (Global Navigation Satellite System) antennas G1 and G2. Hereinafter, the upper revolving body 32 is also referred to as a vehicle body.

[0014] The lower traveling body 31 has a left crawler CL and a right crawler CR. The work machine 3 moves forward, turns, and moves backward by the rotation of the left crawler CL and the right crawler CR. The work machine 3 moves forward, turns, and moves backward by the rotation of the left crawler CL and the right crawler CR.

[0015] The driver's cab 32A is a place where the operator of the work machine 3 boards and performs operations. The driver's cab 32A is installed, for example, on the left side of the front end of the upper revolving body 32. The internal configuration of the driver's cab 32A will be described later.

[0016] The working machine 32B includes a boom BM, an arm AR, and a bucket BK. The boom BM is attached to the front end of the upper revolving body 32. Further, the arm AR is attached to the boom BM. Further, the bucket BK is attached to the arm AR. Further, a boom cylinder SL1 is attached between the upper revolving body 32 and the boom BM. By driving the boom cylinder SL1, the boom BM can be operated with respect to the upper revolving body 32. An arm cylinder SL2 is attached between the boom BM and the arm AR. By driving the arm cylinder SL2, the arm AR can be operated with respect to the boom BM. A bucket cylinder SL3 is attached between the arm AR and the bucket BK. By driving the bucket cylinder SL3, the bucket BK can be operated with respect to the arm AR. The above-described upper revolving body 32, boom BM, arm AR, and bucket BK included in the work machine 3, which is a hydraulic excavator, are one aspect of the movable parts of the work machine 3. Further, the lower traveling body 31 is also one aspect of the movable parts of the work machine 3. In addition, the bucket BK is an example of a configuration of the "working tool" according to the present disclosure. The bucket BK is provided with a cutting edge BKT used for excavation or the like. In other types of working machines, for example, crawlers, blades, etc. are movable parts, and blades, rippers, etc. are working tools.

[0017] (Functional Configuration of Work Content Estimation System) FIG. 3 is a diagram showing the functional configuration of the work content estimation system according to the first embodiment. Hereinafter, with reference to FIG. 3, the functions of the work content estimation system 10 according to the first embodiment will be described. As shown in FIG. 3, the work content estimation system 10 includes a CPU 100, a memory 101, a display unit 102, an operation reception unit 103, a communication interface 104, and a storage 105. Note that the CPU (Central Processing Unit) 100 may be a processor such as an FPGA or a GPU instead of a CPU.

[0018] The CPU 100 is a processor that controls the overall operation of the work content estimation system 10. Various functions of the CPU 100 will be described later.

[0019] The memory 101 is a so-called main memory device. In the memory 101, instructions and data necessary for the CPU 100 to operate based on a program are expanded.

[0020] The display unit 102 is a display device capable of visibly displaying information, and is, for example, a liquid crystal display or an organic EL display.

[0021] The operation reception unit 103 is an input device, and is, for example, a general mouse, keyboard, touch sensor, etc.

[0022] The communication interface 104 is a communication interface for communicating with the data logger 20.

[0023] Storage 105 is a so-called auxiliary storage device, such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), etc. In storage 105, log information TL received from the data logger 20, the vehicle type of the working machine 3, the working machine model TM which is a 3D model prepared in advance for each model, etc. are recorded. Note that the working machine model TM will be described later. Also, in storage 105, the unit work estimation model PM1 which is a learned machine learning model used when estimating the work content of the working machine 3, the elemental work estimation model PM2, heatmaps (H1, H2) generated in the process of estimation, the estimated work content R of the working machine 3, etc. are also recorded. Note that the unit work estimation model PM1, the elemental work estimation model PM2, and the heatmaps (H1, H2) will be described later.

[0024] The functions of the CPU 100 of the work content estimation system 10 according to the first embodiment will be described in detail. By operating based on a predetermined program, the CPU 100 exhibits functions as the acquisition unit 1000 and the estimation unit 1001. Note that the above-mentioned predetermined program may be for realizing a part of the functions to be exhibited by the work content estimation system 10. For example, the program may exhibit functions by combination with other programs already stored in the storage 105, or by combination with other programs implemented in other devices. In other embodiments, the work content estimation system 10 may include a custom LSI (Large Scale Integrated Circuit) such as a PLD (Programmable Logic Device) in addition to or instead of the above configuration. Examples of PLDs include PAL (Programmable Array Logic), GAL (Generic Array Logic), CPLD (Complex Programmable Logic Device), and FPGA (Field Programmable Gate Array). In this case, some or all of the functions realized by the processor may be realized by the integrated circuit.

[0025] The acquisition unit 1000 acquires log information TL to be analyzed from among a plurality of log information TL recorded and stored in the storage 105. Here, it is assumed that the plurality of log information TL are recorded separately for each file recorded with different file names in the storage 105. The acquisition unit 1000 acquires, for example, one piece of log information TL to be analyzed.

[0026] The estimation unit 1001 estimates the time series of the work content at each time of the machine tool 3 from the acquired log information TL.

[0027] (Processing flow of the work content estimation system) Hereinafter, with reference to FIGS. 4 to 7, the specific processing flow performed by the work content estimation system 10 will be described in detail.

[0028] The processing flow shown in FIG. 4 starts from the point in time when a dedicated application is started by the operator of the work content estimation system 10. When a dedicated application is started by the operator's operation, the acquisition unit 1000 of the CPU 100 expands and acquires the designated log information TL1 designated as the analysis target in the memory 101 (step S00).

[0029] Here, the log information TL will be described with reference to FIG. 5.

[0030] As shown in FIG. 5, the log information TL includes work machine identification information. Specifically, the work machine identification information is an individual identification number for individually identifying the work machine 3. In FIG. 5, it is assumed that the work machine identification information is allocated so as to correspond to the vehicle type, model, type, machine number, etc. of the work machine 3 indicating a hydraulic excavator, a wheel loader, a bulldozer, etc. Note that the work machine identification information may be a number, a combination of numbers, letters, symbols, or a combination thereof, etc.

[0031] As shown in FIG. 5, the log information TL includes information indicating the position and posture of the work machine 3 at each time, and angle information of the movable parts of the work machine 3. Specifically, the log information TL records the position of the work machine 3, the roll angle of the work machine 3 which is the inclination in the left-right direction of the machine body, the pitch angle which is the inclination in the front-rear direction of the machine body, the turning angle, the boom angle, the arm angle, and the bucket angle at each time. Here, the data logger 20 mounted on the work machine 3 is, for example, information obtained by receiving the GNSS antennas G1 and G2, and based on the positioning information indicating latitude, longitude, and altitude, identifies and records the position of the work machine 3. Further, the data logger 20 calculates and records the roll angle and pitch angle of the work machine 3 based on the measurement results of an IMU (Inertial Measurement Unit) mounted on the work machine 3. Further, the data logger 20 calculates and records the turning angle of the upper swing body 32 based on the positioning information obtained from each of the GNSS antennas G1 and G2 provided on the upper swing body 32. Note that the turning angle is the change in the azimuth of the upper swing body 32 per predetermined time. Furthermore, the data logger 20 calculates and records the boom angle, arm angle, and bucket angle based on the extension and contraction degrees of the boom cylinder SL1, arm cylinder SL2, and bucket cylinder SL3, respectively. Note that the boom angle, arm angle, bucket angle, and turning angle may be obtained, for example, by attaching an IMU to the boom, arm, bucket, and upper swing body and using those IMUs to obtain the boom angle, arm angle, bucket angle, and turning angle.

[0032] The position, roll angle, and pitch angle are information necessary to specify the position and attitude of the working machine 3 itself. Also, the roll angle, pitch angle, turning angle, boom angle, arm angle, and bucket angle are attitude information representing the attitude of the working machine 3.

[0033] The log information TL shown in FIG. 5 includes the position information, roll angle, pitch angle, turning angle, boom angle, arm angle, and bucket angle of the working machine 3. These pieces of information have the characteristic of being less affected by differences in the vehicle class of the working machine 3 when used as information for estimating the work content.

[0034] Returning to FIG. 4, the estimation unit 1001 of the CPU 100 estimates the work content of the working machine 3 at each time based on the designated log information TL1 acquired in step S00 (step S01).

[0035] Here, the procedure for the estimation unit 1001 to estimate the work content of the working machine 3 from the log information TL will be described with reference to FIG. 7. The estimation unit 1001 estimates the work content of the working machine 3 with respect to both unit work and elemental work. Unit work is work that accomplishes one work objective. Elemental work is work that represents a series of operations or work that are elements constituting the unit work and are classified by purpose.

[0036] Examples of the classification of unit work include, for example, "excavation and loading", "weeding", "slope (from below)", "loading collection", "traveling", "stopping and resting" shown in FIG. 7, as well as "trench excavation", "backfilling", "slope (from above)", and the like. Excavation and loading is work that digs, cuts, and loads the excavated earth and sand or rock onto the loading platform of a transport vehicle. Excavation and loading is a unit work composed of excavation, loading turning, soil discharge, empty load turning, waiting for soil discharge, and load platform pressing. Weeding is work that flattens and cuts off excess undulations on the ground to a predetermined height. Weeding is a unit work composed of excavation and soil discharge, or excavation, loading turning, soil discharge, and empty load turning, and may include leveling and sweeping. The slope work (from below) is an operation of creating a slope by a working machine 3 located below the target location. The slope work (from below) is a unit operation composed of rolling compaction, excavation, loading swing, soil dumping, and empty swing, and may include leveling. Loading collection is an operation of collecting the earth and sand excavated by excavation or the like before loading it onto a transport vehicle. Loading collection is a unit operation composed of excavation, loading swing, soil dumping, and empty swing, and may include leveling. Traveling is an operation of moving the working machine 3. Traveling as a unit operation is a unit operation composed of traveling as an elemental operation. Stopping and idling is a state where there is no earth and sand or rock in the bucket BK and the machine has stopped for a predetermined time or more. Stopping and idling as a unit operation is a unit operation composed of stopping as an elemental operation. Trench excavation is an operation of digging and scraping the ground into a long and narrow groove shape. Trench excavation is a unit operation composed of excavation, loading swing, soil dumping, and empty swing, and may include leveling. Backfilling is an operation of putting earth and sand into an existing groove or hole in the ground and filling it flat. Backfilling is a unit operation composed of excavation, loading swing, soil dumping, rolling compaction, and empty swing, and may include leveling and brooming. The slope work (from above) is an operation of creating a slope by a working machine 3 located above the target location. The slope work (from above) is a unit operation composed of rolling compaction, excavation, loading swing, soil dumping, and empty swing, and may include leveling.

[0037] Examples of the classification of elemental operations include "excavation", "loading swing", "waiting for soil dumping", "soil dumping", "empty swing", "holding down the loading platform" shown in FIG. 7, and also "rolling compaction", "leveling", "brooming", etc. Excavation is an operation of digging and scraping earth and sand or rock with the bucket BK. Loading swing is an operation of swinging the upper slewing body 32 while holding the excavated earth and sand or rock in the bucket BK. Waiting for soil dumping is an operation of waiting for a transport vehicle for loading while holding the excavated earth and sand or rock in the bucket BK. Dumping is an operation of unloading the excavated earth and sand or rock from the bucket BK onto a transport vehicle or a predetermined location. Empty-load slewing is an operation of slewing the upper slewing body 32 with no earth and sand or rock in the bucket BK. Bed pressing is an operation of pressing down the earth and sand loaded on the bed of the transport vehicle with the bucket BK from above to make it flat. Rolling compaction is an operation of pushing the earth and sand into the disturbed ground with the bucket BK to shape and strengthen the ground. Leveling is an operation of leveling the earth and sand with the bottom surface of the bucket BK. Sweeping is an operation of leveling the earth and sand with the side surface of the bucket BK.

[0038] The estimation unit 1001 obtains a time series of likelihoods related to unit operations using the unit operation estimation model PM1. The unit operation estimation model PM1 is a learned machine learning model that takes, as explanatory variables, appearance motion information, which is time series information corresponding to the appearance motions of the movable parts of the working machine 3, and outputs information representing the estimation result of the working content of the working machine 3. Here, the appearance motion of the movable part of the working machine 3 is a motion visible from the outside of the movable part of the working machine 3. The appearance motions of the movable parts of the working machine 3 are, for example, the motions of the upper slewing body 32, the boom BM, the arm AR, the bucket BK, and the lower traveling body 3.

[0039] The appearance motion information is information including the detection result of the appearance motion of the movable part by the sensor, the calculated value based on the detection result, and the like. For example, as shown in FIG. 6, the appearance motion information D1 includes the posture information D2, the processing information D3, and the other motion information D4. The posture information D2 is information representing the posture of the working machine 3 as described above, and includes, for example, the boom angle D21, the arm angle D22, the bucket angle D23, the slewing angle D24, the pitch angle D25, and the roll angle D26. Further, the processing information D3 includes the differential value D31 of the posture information D2, the cutting edge information D32 of the bucket, and the differential value D33 of the cutting edge information D32 of the bucket. The differential value D31 of the posture information D2 includes the boom angular velocity D311, the arm angular velocity D312, the bucket angular velocity D313, and the slewing angular velocity D314. The cutting edge information D32 of the bucket includes the cutting edge position of the bucket (height in the direction perpendicular to the vehicle body) D321, the cutting edge position of the bucket (distance in the horizontal direction with respect to the vehicle body) D322, and the cutting edge angle of the bucket (angle with respect to the vehicle body) D323.

[0040] The cutting edge position of the bucket (height in the direction perpendicular to the vehicle body) D321 can be calculated using the following equations (1) to (3).

[0041]

Equation

[0042]

Equation

[0043]

Equation

[0044] Here, boom_h, arm_h, and bucket_h are the heights of the boom, arm, and bucket, respectively. boom_deg, arm_deg, and bucket_deg are the angles of the boom, arm, and bucket, respectively. BOOM, ARM, and BUCKET are the lengths of the boom, arm, and bucket, which are model-specific values.

[0045] The cutting edge position (horizontal distance from the vehicle body) D322 of the bucket can be calculated using the following equations (4) to (6).

[0046]

Equation

[0047]

Equation

[0048]

Equation

[0049] Here, boom_d, arm_d, and bucket_d are the distances from the vehicle body of the boom, arm, and bucket, respectively.

[0050] The cutting edge angle (angle with respect to the vehicle body) D323 (edge_deg) can be calculated using the following equation (7).

[0051]

Equation

[0052] The differential value D33 of the cutting edge information D32 of the bucket includes the cutting edge speed (vertical speed with respect to the vehicle body) D331, the cutting edge speed (horizontal speed with respect to the vehicle body) D332, and the cutting edge angular velocity (angular velocity with respect to the vehicle body) D333 of the bucket. The other operation information D4 includes, for example, the moving distance D41 of the vehicle body. Note that the appearance operation information D1 may include all the information illustrated in FIG. 6 or may include only a part of it.

[0053] The appearance motion information D1 includes, for example, part or all of the posture information D2 representing the posture of the working machine shown in FIG. 6, and part or all of the processing information D3 calculated based on the posture information D2. That is, the posture information D2 includes information representing at least one of, for example, the roll angle, pitch angle, turning angle, boom angle, arm angle, or bucket angle of the working machine 3. Further, the processing information D3 calculated based on the posture information D2 includes information representing at least one of, for example, the position, distance, speed, angle, or angular velocity of the movable part or the working tool of the working machine 3. Further, the information representing at least one of the position, speed, angle, or angular velocity calculated based on the posture information D2 included in the processing information D3 includes the angular velocity of the movable part calculated based on the roll angle, pitch angle, turning angle, boom angle, arm angle, or bucket angle of the working machine 3, and at least one of the position, speed, angle, or angular velocity of the working tool of the working machine 3. Note that the moving distance D41 of the vehicle body is information calculated based on the position information shown in FIG. 5. Further, as other operation information D4, for example, the moving speed of the vehicle body, the relative position (distance) between the working tool such as the bucket and the blade and the lower traveling body 31, the change amount (speed) of the relative position, the ground contact angle of the working tool, the change amount (angular velocity) of the ground contact angle, etc. can be exemplified.

[0054] The unit operation estimation model PM1 is a machine learning model that has been machine-learned in advance by supervised learning or unsupervised learning. When the appearance motion information based on the log information TL is input, the unit operation estimation model PM1 is a model that outputs the likelihood related to the unit operation as information representing the estimation result of the operation content of the working machine 3, and the output information may be stored in, for example, the storage 105.

[0055] Further, the estimation unit 1001 obtains a time series of likelihoods related to the elemental operations by inputting the log information TL into the elemental operation estimation model PM2 in chronological order. The elemental operation estimation model PM2 is, for example, a trained machine learning model machine-learned by learning using training data or learning without using training data, and is a model that outputs a likelihood related to the elemental operation when inputting appearance operation information based on the log information TL. The output information may be stored in, for example, the storage 105.

[0056] The estimation unit 1001 smooths the time series of likelihoods by applying the time series of likelihoods related to the unit operations and the time series of likelihoods related to the elemental operations to a time average filter respectively, and generates a unit operation heatmap H1 representing the smoothed time series of likelihoods related to the unit operations and an elemental operation heatmap H2 representing the smoothed time series of likelihoods related to the elemental operations as shown in FIG. 7. The heatmaps H1 and H2 are maps in which, based on the smoothed time series of likelihoods, a color representing the likelihood of the operation category is assigned to a plane with the operation category on the vertical axis and the time on the horizontal axis. The color related to the heatmap may, for example, approach blue as the likelihood of the operation category is lower and approach red as the likelihood of the operation category is higher. The estimation unit 1001 stores the heatmaps H1 and H2 in the storage 105.

[0057] The estimation unit 1001 specifies a time period in which the likelihood of the unit operation is dominant based on the smoothed time series of likelihoods, and estimates the operation content of the work machine 3 in that time period. For example, in a time period in which the likelihood of the unit operation "excavation and loading" is dominant, the operation content of the work machine 3 is estimated to be "excavation and loading". Similarly, the estimation unit 1001 specifies a time period in which the likelihood of the elemental operation is dominant based on the smoothed time series of likelihoods, and estimates the operation content of the work machine 3 in that time period. For example, in a time period in which the likelihood of the elemental operation "excavation" is dominant, the operation content of the work machine 3 is estimated to be "excavation". The estimation unit 1001 stores the information on the operation content R estimated for the work machine 3 in the storage 105 or displays it on the display unit 102 (step S02).

[0058] (Function, effect) As described above, the work content estimation system 10 according to the first embodiment includes an acquisition unit 1000 that acquires log information TL of the working machine 3 associated with time, and a learned machine learning model (unit work estimation model PM1 and element work estimation model PM2) that inputs appearance motion information D10, which is time-series information corresponding to the appearance motion of the movable part of the working machine 3, and outputs information representing the estimation result of the work content of the working machine 3. By inputting the appearance motion information D10 based on the log information TL to the learned machine learning model, an estimation unit 1001 estimates the time series of the work content of the working machine 3. According to this configuration, since it is not necessary to input information that is easily affected by differences in vehicle types, the versatility of the machine learning model used for estimating the work content can be enhanced.

[0059] (Modification example) The content of the log information TL according to the first embodiment is not limited to this in other embodiments. For example, when the working machine 3 is not a hydraulic excavator but another vehicle type, log information TL corresponding to the vehicle type is recorded. Other vehicle types include, for example, wheel loaders, bulldozers, etc.

[0060] Also, the work content estimation system 10 according to the first embodiment has been described as being installed at a location away from the working machine 3 and connected to the data logger 20 mounted on the working machine 3 via a wide area communication network. However, in other embodiments, it is not limited to this mode.

[0061] For example, in the work content estimation system 10 according to other embodiments, part or all of the configuration of the work content estimation system 10 may be installed inside the working machine 3. In this case, the data logger 20 may transmit the log information TL to the work content estimation system 10 via a network inside the working machine 3 without using a wide area communication network. By doing so, the operator boarding the working machine 3 can confirm the estimation result of the work content on the spot.

[0062] Incidentally, the work content estimation system 10 installed inside the working machine 3 may acquire the log information TL of other working machines 3 via a wide area communication network or the like. By doing so, it is possible to estimate the work content of the working machines 3 other than the working machine 3 equipped with the work content estimation system 10.

[0063] Incidentally, the processes of various processes of the work content estimation system 10 described above are stored in a computer-readable recording medium in the form of a program, and the above various processes are performed by the computer reading and executing this program. Further, the computer-readable recording medium refers to a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, or the like. Further, this computer program may be distributed to the computer via a communication line, and the computer that has received this distribution may execute the program.

[0064] Also, in the first embodiment, it is assumed that the unit work estimation model PM1 outputs the likelihood related to the unit work and the element work estimation model PM2 outputs the likelihood related to the element work. However, for example, the unit work estimation model PM1 may input the appearance operation information based on the log information TL and output both the likelihood related to the unit work and the likelihood related to the element work.

[0065] The above program may be for realizing a part of the above-described functions. Further, it may be a so-called difference file or difference program that can be realized in combination with a program already recorded in the computer system for the above-described functions.

[0066] A part or all of the functions of the work content estimation system 10 described above may be assigned to the working machine 3. For example, some or all of the functions of the acquisition unit 1000, the estimation unit 1001, the memory 101, the display unit 102, the operation reception unit 103, the communication interface 104, and the storage 105 may be assigned to the working machine 3.

[0067] As described above, some embodiments of the present disclosure have been explained. However, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, as well as in the invention described in the claims and the equivalent scope thereof.

[0068] (Appendix) The work content estimation system 10 according to the present disclosure is grasped as follows, for example.

[0069] (1) The work content estimation system 10 according to the first aspect includes an acquisition unit 1000 that acquires log information TL of the work machine 3 associated with time, and a learned machine learning model (unit work estimation model PM1 and element work estimation model PM2) that inputs appearance motion information D1, which is time-series information corresponding to the appearance motion of the movable part of the work machine, and outputs information representing the estimation result of the work content of the work machine. By inputting the appearance motion information based on the log information to the learned machine learning model, an estimation unit 1001 estimates the time series of the work content of the work machine. According to this aspect and the following aspects, the versatility of the machine learning model used for estimating the work content can be enhanced.

[0070] (2) The work content estimation system 10 according to the second aspect is the work content estimation system 10 of (1), wherein the appearance motion information includes posture information representing the posture of the work machine and information representing at least one of position, speed, angle, or angular velocity calculated based on the posture information.

[0071] (3) The work content estimation system 10 according to the third aspect is the work content estimation system 10 of (1) or (2), wherein the posture information includes information representing at least one of the roll angle, pitch angle, turning angle, boom angle, arm angle, and bucket angle of the work machine.

[0072] (4) The work content estimation system 10 according to the fourth aspect is the work content estimation system 10 of (2) or (3), and the information representing at least one of position, speed, angle, or angular velocity calculated based on the posture information is the angular velocity of the movable part calculated based on the roll angle, pitch angle, turning angle, boom angle, arm angle, or bucket angle of the work machine, and includes information representing at least one of the position, speed, angle, or angular velocity of the working tool of the work machine.

Description of Signs

[0073] 1 Analysis support system, 10 Work content estimation system, 100 CPU, 1000 Acquisition unit, 1001 Estimation unit, 101 Memory, 102 Display unit, 103 Operation reception unit, 104 Communication interface, 105 Storage, 20 Data logger, 3 Work machine, H1~H2 Heat map, TL Log information, PM1 Unit work estimation model, PM2 Element work estimation model, R Estimated work content

Claims

1. An acquisition unit that acquires log information of a working machine associated with a time; An estimation unit that estimates a time series of the working content of the working machine by inputting the appearance motion information, which is time series information corresponding to the appearance motion of the movable part of the working machine, into a learned machine learning model that outputs information representing an estimation result of the working content of the working machine; A working content estimation system comprising the above.

2. The appearance motion information includes posture information representing the posture of the working machine and information representing at least one of position, speed, angle, or angular velocity calculated based on the posture information. The working content estimation system according to Claim 1.

3. The posture information includes information representing at least one of the roll angle, pitch angle, turning angle, boom angle, arm angle, and bucket angle of the working machine. The working content estimation system according to Claim 2.

4. The information representing at least one of position, speed, angle, or angular velocity calculated based on the posture information includes information representing at least one of the angular velocity of the movable part, the position, speed, angle, or angular velocity of the working tool of the working machine, calculated based on the roll angle, pitch angle, turning angle, boom angle, arm angle, or bucket angle of the working machine. The working content estimation system according to Claim 3.

5. A step of acquiring log information of a working machine associated with a time; A step of estimating a time series of the working content of the working machine by inputting the appearance motion information, which is time series information corresponding to the appearance motion of the movable part of the working machine, into a learned machine learning model that outputs information representing an estimation result of the working content of the working machine; A working content estimation method including the above.

Images