JP2010161991A - Work recording device, work recording system, and work recording program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a work recording device automatically recording a work record without performing a troublesome operation, and accurately recording what work is performed in which farm. <P>SOLUTION: This work recording device 20 includes acquiring the place of a worker and motion data related to motion of the worker, selecting farm candidates where the worker works according to the acquired place of the worker, and extracting the amount of characteristics from the acquired motion data of the worker. The work recording device 20 specifies the classification of work which the worker performs, using the extracted amount of characteristics, specifies the farm where the worker works from the selected farm candidates based on the specified classification of work, and records as a work record, the specified classification of work and the specified farm. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a work recording apparatus, a work recording system, and a work recording program that record a field in which work is performed and a work type performed by a worker.

  2. Description of the Related Art In recent years, in the field of agriculture, a work recording system that records which farm work has been performed on which farm and what farm work has been known for crop cost calculation and crop traceability (see, for example, Patent Document 1). ).

  As such a work recording system, a technique of manually inputting a work record and recording the work record is known. For example, after completing farm work, the user inputs data to a PC at home, or brings a mobile PC or mobile phone to the farm and inputs work records at the site.

  In addition, as a technology to record work records by automatically entering work records, GPS machines are attached to agricultural machines such as tractors and farm workers, the farm is identified from the position of the tractor and workers, and when and who farm There is a system that automatically records whether or not you are working.

  In such an automatic recording system, for example, as shown in FIG. 31, the movement trajectory of a farm worker or an agricultural machine is known, and the work required on the farm A is determined as a and the work required on the farm B is determined as b. Are recorded as operation a during the movement of farm A and operation b during the movement of farm B.

JP 2008-148565 A

  By the way, in the technique of manually recording the work record described above and recording the work record, the work record is input from the PC or the mobile phone, so that there is a problem that the operation of the work PC or the mobile phone is complicated.

  Further, in the technique of attaching a GPS receiver and automatically inputting work records and recording the work records, there are cases where errors occur in GPS. Therefore, as shown in FIG. An off-track occurs. In such a case, even if you work on Farm A, it may be recognized as Farm B because of the position error. You cannot determine which farm, and you cannot correctly determine the farm and record the work record. There was a problem.

  Accordingly, the present invention has been made to solve the above-described problems of the prior art, and automatically records a work record without performing complicated operations, and the accuracy of what work has been performed on which farm. The purpose is to record well.

  In order to solve the above-mentioned problems and achieve the purpose, this device identifies work from the movement feature amount of the worker, identifies the farm from the farm candidates based on the identified work, and selects which work on which farm. The work record is recorded automatically.

  The disclosed apparatus automatically records work records without complicated operations, and has an effect of accurately recording what work is performed on which farm.

FIG. 1 is a block diagram illustrating the configuration of the action recording apparatus according to the first embodiment. FIG. 2 is a diagram illustrating a mounting example of the behavior recording device. FIG. 3 is a block diagram illustrating the configuration of the work recording apparatus according to the first embodiment. FIG. 4 is a diagram illustrating an example of the farm position crop list. FIG. 5 is a diagram illustrating an example of the work movement feature amount list. FIG. 6 is a diagram illustrating an example of worker ID management information. FIG. 7 is a diagram for explaining processing for selecting farm candidates. FIG. 8 is a diagram for explaining a process of determining farm work. FIG. 9 is a diagram illustrating an example of a recorded work record. FIG. 10 is a flowchart illustrating the entire processing operation of the work recording apparatus according to the first embodiment. FIG. 11 is a flowchart illustrating the operation of the feature amount extraction process of the work recording apparatus according to the first embodiment. FIG. 12 is a flowchart illustrating the data transfer processing operation of the behavior recording apparatus according to the first embodiment. FIG. 13 is a diagram showing the trajectories of grouped farm work. FIG. 14 is a diagram for explaining processing for determining each group as a series of farm work. FIG. 15 is a flowchart illustrating the entire processing operation of the work recording apparatus according to the second embodiment. FIG. 16 is a diagram illustrating an example of a work motion feature amount list including basic operations. FIG. 17 is a flowchart illustrating the entire processing operation of the work recording apparatus according to the third embodiment. FIG. 18 is a diagram illustrating an example of the work motion feature amount list in consideration of the order. FIG. 19 is a flowchart illustrating the entire processing operation of the work recording apparatus according to the fourth embodiment. FIG. 20 is a diagram illustrating an example of a work motion feature amount list including a way of walking and a body orientation. FIG. 21 is a diagram for explaining processing for determining how to walk from the direction of the body and the direction of movement. FIG. 22 is a diagram for explaining the process of determining the posture from the ridge and the body direction. FIG. 23 is a diagram for explaining processing for determining the direction of ridges. FIG. 24 is a flowchart illustrating the processing operation for determining the ridge direction of the work recording apparatus according to the fifth embodiment. FIG. 25 is a diagram illustrating an example of trajectories of workers and work machines. FIG. 26 is a diagram illustrating an example of trajectories of grouped workers and work machines. FIG. 27 is a diagram for explaining processing for determining each group as a series of farm work. FIG. 28 is a flowchart illustrating the processing operation of the work recording apparatus according to the sixth embodiment. FIG. 29 is a flowchart illustrating an operation of data transfer processing of the action recording device attached to the work machine according to the sixth embodiment. FIG. 30 is a diagram illustrating a computer that executes a work recording program. FIG. 31 is a diagram for explaining the prior art. FIG. 32 is a diagram for explaining the prior art.

  Exemplary embodiments of a work recording apparatus, a work recording system, and a work recording program according to the present invention will be described below in detail with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments.

  In the following embodiments, the configuration of the action recording device and the work recording device according to the first embodiment and the flow of processing will be described in order, and finally the effects of the first embodiment will be described.

[Configuration of action recording device]
First, the configuration of the action recording device 10 will be described with reference to FIG. FIG. 1 is a block diagram illustrating the configuration of the action recording apparatus 10 according to the first embodiment. As shown in the figure, the action recording device 10 includes a position detection unit 11, a motion detection unit 12, a clock 13, a recording unit 14, and a communication unit 15, and is attached by a farmer and can communicate with the work recording device 20. The recording data is transferred when The processing of each of these units will be described below.

  Here, a wearing example of the action recording apparatus 10 will be described with reference to FIG. FIG. 2 is a diagram illustrating a mounting example of the behavior recording apparatus 10. As shown in FIG. 2, the waist behavior recording device 10 </ b> A is worn by a farm worker on the waist, and the arm behavior recording device 10 </ b> B is worn on a farm worker's arm.

  The position detection unit 11 detects the position of the farm worker with a GPS receiver or the like, notifies the storage unit 14 of the detected position of the farm worker, and records it. The motion detection unit 12 detects the movement of the farm worker using an acceleration sensor or the like, and notifies the storage unit 14 of data obtained by adding the ID of the owner of the behavior recording device 10 to the detected data and records the data. For example, a triaxial acceleration sensor is used for the arm and waist as the motion detection unit 12.

  The clock 13 notifies the recording unit 14 of the time information and records it. The recording unit 14 receives the position, movement data, and time information of the farmer from the position detection unit 11, the movement detection unit 12, and the clock 13, and records them as recording data.

  The communication unit 15 is a wireless LAN or the like, and transfers the recording data recorded by the recording unit 14 to the work recording device 20 when the communication distance with the work recording device 20 is reached. For example, the communication unit 15 records the record data when the action recording device 10 attached to the worker returns to his / her home or office after working on the farm and the wireless communication with the work recording device 20 is possible. Transfer to device 20.

[Configuration of work recording device]
Next, the configuration of the work recording apparatus 20 will be described with reference to FIG. FIG. 3 is a block diagram illustrating the configuration of the work recording apparatus 20 according to the first embodiment. As shown in the figure, the work recording apparatus 20 includes a communication unit 21, a farm work database 22, a control unit 23, and a work recording unit 24. The processing of each of these units will be described below.

  The communication unit 21 is a wireless LAN or the like, and receives recording data from the behavior recording device 10 when the communication distance with the behavior recording device 10 is reached. Specifically, the communication unit 21 receives the farm worker's position, movement data, and time information as recording data from the behavior recording device 10, and notifies the control unit 23 of them.

  The farm work database 22 stores in advance data related to farm work necessary for various processes by the control unit 23. In particular, the farm position crop list storage unit 22a, the work movement feature amount list storage unit (farm field crop list storage unit) 22b, It has worker ID management information 22c.

  The farm position crop list storage unit 22a stores the position of each farm and the crops cultivated on the farm in association with each other. FIG. 4 is a diagram illustrating an example of the farm position crop list. Specifically, as illustrated in FIG. 4, the farm work database 22 includes a “farm name” that is the name of the farm, a “position” that indicates the area of each farm in the coordinates of the apex position, and cultivation on the farm. The associated “crop” is stored in association with each other.

  Here, it is assumed that the “position” indicating the area of each farm by the coordinates of the apex position is larger than the original area of the farm. That is, the farm position crop list storage unit 22a expands the farm range from A to A1 and from B to B1, as shown in FIG. 7, in accordance with the position measurement error of the action recording device 10.

  The work movement feature quantity list storage unit 22b stores the farm work necessary for the crop, the work time when the farm work is performed, and the motion feature quantity for each farm work in association with each other. FIG. 5 is a diagram illustrating an example of the work movement feature amount list. Specifically, as illustrated in FIG. 5, the work movement feature amount list storage unit 22b includes “a crop”, “a work name” indicating the name of the farm work necessary for the crop, and a work for the farm work. The “time” and the “motion feature value” that is the feature value of the motion for each farm work are stored in association with each other.

  The worker ID management information 22c stores the worker ID and the worker name in association with each other. FIG. 6 is a diagram illustrating an example of worker ID management information. Specifically, the worker ID management information 22c stores the “ID” of the worker or the work machine and the “owner” indicating the name of the worker or the work machine wearing the behavior recording apparatus 10 in association with each other. To do.

  The control unit 23 has an internal memory for storing a program that defines various processing procedures and necessary data, and executes various processes using these programs. In particular, the action record data acquisition unit 23a, the farm candidate selection A unit 23b, a crop candidate selection unit 23c, a farm work candidate selection unit 23d, a feature amount extraction unit 23e, a work specification unit 23f, and a farm specification unit 23g.

  The action record data acquisition unit 23a acquires movement data related to the position of the worker and the movement of the worker. Specifically, the action record data acquisition unit 23a acquires the position, movement data, and time information of the farm worker from the communication unit 21, and notifies the farm candidate selection unit 23b.

  The farm candidate selection unit 23b selects a farm candidate on which the farm worker is working according to the acquired position of the farm worker. Specifically, the farm candidate selection unit 23b uses the position data of the behavior recording device 10 worn by the farm worker to identify the farm candidate considered to be working by the farm worker as the farm position crop list storage unit. Select from 22a.

  Here, the process of selecting farm candidates will be described. FIG. 7 is a diagram for explaining processing for selecting farm candidates. As illustrated in FIG. 7, when the farm worker position data is within the area of the A farm, the farm candidate selection unit 23 b selects the A farm as the farm candidate, and the farm worker position data is the area of the B farm. If so, Farm B is selected as a farm candidate. Further, the farm candidate selection unit 23b selects the A farm and the B farm as farm candidates when the position data of the farm worker corresponds to both the A farm area and the B farm area.

  The crop candidate selection unit 23c selects a crop candidate using the farm candidate. Specifically, the crop candidate selection unit 23c selects a crop candidate corresponding to each farm candidate selected by the farm candidate selection unit 23b from the farm position crop list storage unit 22a.

  The farm work candidate selection unit 23d selects a farm work candidate from the work movement feature amount list storage unit 22b using the crop candidate and the time information. Specifically, the farm work candidate selection unit 23d selects the “work name” corresponding to the “time” corresponding to the crop candidate selected by the crop candidate selection unit 23c and the time information acquired by the action record data acquisition unit 23a. A selection is made from the work movement feature value list storage unit 22b.

  The feature amount extraction unit 23e extracts a feature amount from the acquired worker movement data. Here, the feature amount extraction processing of the feature amount extraction unit 23e will be described in detail. Below, the case where motion data is detected using a triaxial acceleration sensor on the farmer's arm and waist will be described. The feature amount extraction unit 23e performs coordinate conversion from the XYZ acceleration of the arm to the vertical, horizontal, and longitudinal acceleration, and performs a Fourier transform (FFT) process on the vertical, lateral, and longitudinal acceleration.

  Then, the feature amount extraction unit 23e performs a Fourier transform process on the XYZ acceleration of the waist. Subsequently, the feature amount extraction unit 23e searches for a peak frequency at which the acceleration peak of the arm and the waist is equal to or higher than a predetermined value Ap. As a result, the feature quantity extraction unit 23e determines, in descending order of the searched peak frequency, “frequency and magnitude of movement of the front and rear, left and right, and vertical direction of the arm” and “frequency and magnitude of movement of the waist up and down” Is stored in the internal memory. After that, the feature amount extraction unit 23e calculates the “waist angle” from the ratio of the X and Z acceleration components of the waist that are 0.1 Hz or less, and stores them in the internal memory.

  The work identifying unit 23f identifies the type of work performed by the farm worker using the feature amount extracted by the feature amount extracting unit 23e. Specifically, the work specifying unit 23f uses the feature amount extraction unit 23e as the movement feature amount stored in the internal memory, such as “frequency and magnitude of movement of the front / rear, left / right, and up / down directions”, “up / down of the waist” Using the “frequency and magnitude of direction movement” and “waist angle”, the farm work that best matches the feature quantity of each farm work candidate selected by the farm work candidate selection unit 23d is identified.

  For example, the work specifying unit 23f may perform “manual fertilizer application by hand”, “deep cultivation by cultivator”, “sowing by hand”, “thinning by hand”, “spreading herbicide by hand”, “weeding by hand”. Next, a case where there is “top fertilization by hand”, “tilling” and “harvest of fruit by hand” will be described. The work specifying unit 23f specifies that the hand is a slow motion of 0.5 to 1 Hz in the horizontal direction, and the vicinity of 2 Hz of walking is detected by the acceleration sensor attached to the waist, “spreading the original manure by hand”. To do.

  In addition, when the acceleration sensor attached to the hand detects the vibration frequency of 10 Hz or more of the cultivator and the vicinity of 2 Hz of the walking is detected by the acceleration sensor attached to the waist, the work specifying unit 23 f reads “Deep cultivation with the cultivator”. Identify. When the acceleration sensor attached to the hand detects the vertical direction near 1 Hz and the acceleration sensor attached to the waist detects that the waist is bent, the work specifying unit 23f reads “Seeding with hands”. Identify.

  Further, the work specifying unit 23f detects a slow vertical movement of 0.5 Hz or less by the acceleration sensor attached to the hand, and specifies “thinning by hand” when the hip is bent. In addition, the work specifying unit 23f detects a slow horizontal movement of 0.5Hz or less by the acceleration sensor attached to the hand, and if the acceleration sensor attached to the waist detects walking around 2Hz, the "dispersing machine" To identify herbicide application. In addition, the work specifying unit 23f detects that the acceleration sensor attached to the hand is in the vertical direction around 1 Hz, detects that the acceleration sensor attached to the waist is bent, and is in the middle of the harvesting period from sowing. Identifies “weeding by hand”.

  Further, the work specifying unit 23f detects a slow motion of 0.5 to 1 Hz in the horizontal direction by the acceleration sensor attached to the hand, and the acceleration sensor attached to the waist detects the vicinity of 2 Hz of walking, so When it is an intermediate period, it is specified as “manual fertilization work by hand”.

  In addition, the work specifying unit 23f detects the bending motion of the acceleration sensor attached to the waist, and specifies “standing” when the acceleration sensor attached to the hand detects a fast horizontal movement of 2 Hz or more. In addition, the work specifying unit 23f detects a slowly walking motion at 0.5 Hz or less while the acceleration sensor attached to the waist is standing, and the acceleration sensor attached to the hand detects a slow back-and-forth motion of 0.5 Hz or less. In this case, it is specified as “fruit harvest by hand”.

  Based on the farm work specified by the work specifying unit 23f, the farm specifying unit 23g specifies the farm on which the farm worker has worked from the farm candidates selected by the farm candidate selecting unit 23c. Specifically, as illustrated in FIG. 8, the farm specifying unit 23g determines that the work specifying unit 23f specifies the operation a performed on the farm A and the operation b performed on the farm B, respectively. It is determined that the work on farm B has been switched to work on farm B. As a result, it is specified that the farm where the farmer has performed the work a is the farm A, and the farm where the farmer has performed the work b is the farm B.

  The work recording unit 24 records the farm work specified by the work specifying unit 23f and the farm specified by the farm specifying unit 23g in association with each other as a work record. Specifically, as illustrated in FIG. 9, the work recording unit 24 includes a “farm name” indicating the name of the farm, a “crop” cultivated on the farm, and the work performed on the crop. The “work name” indicating the name, the “worker” who performed the work, the “start time” indicating the time when the work was started, and the “end time” indicating the time when the work was completed are stored in association with each other.

[Processing by work recording device]
Next, processing performed by the work recording apparatus 20 according to the first embodiment will be described with reference to FIG. FIG. 10 is a flowchart illustrating the entire processing operation of the work recording apparatus according to the first embodiment.

  As shown in the figure, the action record data acquisition unit 23a of the work recording device 20 acquires the position, motion data, and time information of the farm worker from the communication unit 21 (step S101). Then, the farm candidate selection unit 23b selects a farm candidate based on the position data of the action recording device 10 and the farm position crop list (step S102). Specifically, the farm candidate selection unit 23b uses the position data of the behavior recording device 10 worn by the farm worker to identify the farm candidate considered to be working by the farm worker as the farm position crop list storage unit. Select from 22a.

  Then, the crop candidate selection unit 23c selects a crop candidate corresponding to each farm candidate selected by the farm candidate selection unit 23b from the farm position crop list storage unit 22a (step S103). Subsequently, a farm work candidate is selected from the work motion feature quantity list storage unit 22b using the crop candidate, work motion feature quantity list, and time information (step S104). Specifically, the farm work candidate selection unit 23d selects the “work name” corresponding to the “time” corresponding to the crop candidate selected by the crop candidate selection unit 23c and the time information acquired by the action record data acquisition unit 23a. A selection is made from the work movement feature value list storage unit 22b.

  Thereafter, the feature amount extraction unit 23e performs a feature amount extraction process (to be described in detail later with reference to FIG. 11) from the acquired movement data of the worker (step S105). Then, the work specifying unit 23f determines whether the feature amount of the farm work candidate selected by the farm work candidate selection unit 23d most closely matches the feature amount extracted by the feature amount extraction unit 23e so far (Step S106). If they are the best match (Yes at Step S106), the farm work candidate is determined as farm work (Step S107).

  The work specifying unit 23f determines that the feature value of the farm work candidate selected by the farm work candidate selection unit 23d is not the best match with the feature value extracted by the feature value extracting unit 23e (No in step S106). ) Without determining that the farm work candidate as farm work, it is determined whether there is another farm work candidate (step S108).

  As a result, when it is determined that there are other farm work candidates (Yes at Step S108), the work specifying unit 23f returns to Step S106, and repeats the processes of Steps S106 to S108 for all the farm work candidates to obtain a plurality of farm work candidates. The farm work with the closest feature quantity is identified.

  If it is determined that there is no other farm work candidate (No at Step S108), the work identifying unit 23f identifies a farm based on the identified farm work (Step S109). Thereafter, the work specifying unit 23f associates and records the farm work specified by the work specifying unit 23f and the farm specified by the farm specifying unit 23g as a work record (step S110).

  Specifically, as illustrated in FIG. 9, the work recording unit 24 includes a “farm name” indicating the name of the farm, a “crop” cultivated on the farm, and the work performed on the crop. The “work name” indicating the name, the “worker” who performed the work, the “start time” indicating the time when the work was started, and the “end time” indicating the time when the work was completed are stored in association with each other.

  Next, the feature amount extraction processing by the work recording apparatus 20 according to the first embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating the operation of the feature amount extraction process of the work recording apparatus 20 according to the first embodiment. In the following, a case where motion data is detected using a triaxial acceleration sensor on the farmer's arm and waist will be described.

  As shown in the figure, the feature amount extraction unit 23e of the work recording device 20 performs coordinate conversion from the XYZ acceleration of the arm to the vertical, horizontal, and longitudinal acceleration (step S201), and the Fourier transform is performed for the vertical, lateral, and longitudinal acceleration. A transform (FFT: Fast Fourier transform) process is performed (step S202).

  Then, the feature amount extraction unit 23e performs a Fourier transform process on the XYZ acceleration of the waist (Step S203). Subsequently, the feature amount extraction unit 23e searches for a peak frequency at which the acceleration peak of the arm and the waist is equal to or higher than the predetermined value Ap (step S204).

  As a result, the feature quantity extraction unit 23e determines, in descending order of the searched peak frequency, “frequency and magnitude of movement of the front and rear, left and right, and vertical direction of the arm” and “frequency and magnitude of movement of the waist up and down” Is stored in the internal memory (step S205). After that, the feature amount extraction unit 23e calculates the “waist angle” from the ratio of the X and Z acceleration components of the waist that are 0.1 Hz or less, and stores them in the internal memory (step S206).

  Next, the data transfer process of the action recording device 10 according to the first embodiment will be described with reference to FIG. FIG. 12 is a flowchart illustrating an operation of data transfer processing of the action recording device 10 according to the first embodiment. As shown in the figure, when the behavior recording device 10 detects a motion (step S301), the behavior recording device 10 records the position, motion data, and time information of the farm worker as recording data (step S302).

  Then, the action recording device 10 determines whether or not communication with the work recording device 20 is possible (step S303). When communication is possible (Yes in step S303), the recorded farm worker's position, motion data, and time information are recorded. Is transferred to the work recording apparatus 20 (step S304), and the process returns to S301.

[Effect of Example 1]
As described above, the work recording apparatus 20 acquires movement data related to the position of the worker and the movement of the worker, and selects farm candidates on which the worker is working according to the acquired position of the worker. Select and extract feature values from the acquired worker movement data. Then, the work recording device 20 identifies the work type performed by the worker using the extracted feature amount, and the worker performs work from the selected farm candidates based on the identified work type. The visited farm is identified, and the identified work type is associated with the identified farm and recorded as a work record. For this reason, it is possible to automatically record work records without complicated operations, and to accurately record what work has been performed on which farm.

  Further, according to the first embodiment, the work recording device 20 stores the crops cultivated in each farm in the farm position crop list storage unit 22a, and the work types required for the crops and the characteristics of the movement for each work type. The amount is associated with each other and stored in the work movement feature amount list storage unit 22b. Then, the work recording device 20 selects a crop candidate cultivated on the farm stored in association with the selected farm candidate from the farm position crop list storage unit 22a, and associates it with the selected crop candidate. The work required for the crop stored in this way is selected as a work candidate from the work movement feature quantity list storage unit 22b. Subsequently, the work recording apparatus 20 detects the work type associated with the feature quantity closest to the extracted feature quantity from the work candidates, and identifies the work candidate as the work type performed by the worker. For this reason, it is possible to automatically record work records without complicated operations, and to accurately record what work has been performed on which farm.

  In addition, according to the first embodiment, the work recording apparatus 20 includes the farm position crop list storage unit (farm field position list storage unit) 22a that stores an enlarged area including the farm area, and the acquired work. If the person's position is within the enlarged area stored by the farm position crop list storage unit 22a, the farm included in the enlarged area is selected as a farm candidate. For this reason, even if there is a GPS error, it is possible to correctly determine the farm and perform work recording.

  By the way, in this embodiment, the time, position, and motion data from the action recording device may be grouped in an appropriate time unit (for example, in units of 10 minutes), and a feature amount may be extracted for each group.

  Accordingly, in the following second embodiment, the time, position, and motion data from the action recording device are grouped in an appropriate time unit (for example, in units of 10 minutes), and feature amounts are extracted for each group. The process of the work recording apparatus 20a in the second embodiment will be described with reference to FIG. FIG. 13 is a diagram showing the trajectories of grouped farm work. FIG. 14 is a diagram for explaining processing for determining each group as a series of farm work.

  In the work recording apparatus 20a according to the second embodiment, as illustrated in FIG. 13, the farm work trajectories are grouped into G1 to G12, respectively. The work recording device 20a extracts a feature value for each group, and selects a work candidate close to a predetermined amount from the selected feature values of the farm work.

  For example, in the group G1, the work of a1 is within a predetermined range, but in G2, the work of a2 and the work of a1 are within the predetermined range. In this case, the work recording device 20a may select the most continuous work instead of selecting the nearest work from the work candidates. For example, since the group G1 to G7 includes the task a1, the cropping operation recording apparatus 20a collectively determines that the group G1 to G7 is a series of farm work as the task a1 as illustrated in FIG. Similarly, the work recording device 20a determines that the work is b1 in G10 to G12. G8 and G9 are not recorded as farm work because there are no continuous work candidates.

  Next, the processing operation of the work recording apparatus 20a according to the second embodiment will be described with reference to FIG. The work recording apparatus 20a according to the second embodiment acquires work record data and selects a farm candidate, a crop candidate, and a farm work candidate in the same manner as the process of the work recording apparatus 20 according to the first embodiment illustrated in FIG. Step S401 to Step S404).

  Then, in the work recording apparatus 20a according to the second embodiment, the data of the action recording apparatus 10 is grouped every predetermined time (step S405), and the feature amount is extracted for each group (step S406). Subsequently, the work recording apparatus 20a according to the second embodiment determines whether or not the feature quantity of the selected farm work candidate matches the extracted feature quantity within a predetermined range (step S407), and matches within the predetermined range. If so (Yes in step S407), the farm work is added to the group farm work candidates (step S408).

  Then, the work recording apparatus 20a determines whether or not the operation has been performed for all the groups (step S409). If the operation has not been performed for all the groups (No in step S409), the process returns to step S407 and the feature amount of the selected farm work candidate is It is determined whether or not the extracted feature value matches within a predetermined range, and the process of adding farm work to the group farm work candidates is repeated for all groups (steps S407 to 409).

  Thereafter, when the work recording apparatus 20a has performed all groups (Yes at Step S409), the work continuous among the groups among the work candidates is determined as the farm work (Step S410), and the work continuous between the groups is determined. It is determined whether there is a candidate (step S411). As a result, when there is a continuous work candidate between groups (Yes at Step S411), the work recording device 20a repeats the process of determining as a continuous work (Steps S410 to S411).

  Then, the work recording apparatus 20a determines whether or not the number of continuous work candidate groups is equal to or greater than the specified number (for example, three) (step S412). As a result, when the number of continuous work candidate groups is the specified number of groups (Yes at Step S412), the work recording device 20a records as a series of farm work (Step S413). If the number of consecutive work candidate groups is less than the specified number (No in step S412), the work recording device 20a ends the process without recording the farm work.

  As described above, in the above-described second embodiment, the work recording apparatus 20a acquires movement data related to the worker position and the worker movement, and groups the worker position and the worker movement at predetermined time intervals. The feature amount is extracted for each group from the acquired worker movement data. Then, the work recording device 20a selects a work candidate for each group from the work motion feature quantity list storage unit using the extracted feature quantity for each group, and among the selected work candidates, a work candidate between groups. Are consecutive, the task candidate that is continuous between the groups is specified as the task type. For this reason, it is possible to accurately record what work has been performed on which farm for each group.

  By the way, in said Example 1, 2, although the case where a farm work was specified from the feature-value of a farm worker's movement was demonstrated, a present Example is not limited to this, From the feature-value of a farm worker's movement The farm work may be specified after selecting a basic motion candidate finer than the farm work. For example, the basic operations “Weeding”, “Weeding”, etc., which are subdivided operations of the farm work “Weeding” are stored in the work motion feature quantity list, and basic motion candidates that are close to the farmer's motion feature quantities are stored After selecting from the feature list, the farm work is identified.

  Therefore, in the following third embodiment, the process of the work recording apparatus 20b according to the third embodiment will be described with reference to FIGS. 16 and 17 as a case where the farm work is specified after the basic motion candidate is selected from the work motion feature amount list. explain. FIG. 16 is a diagram illustrating an example of a work motion feature amount list including basic operations.

  As illustrated in FIG. 16, the work recording device 20 b according to the third embodiment includes a “work name” indicating the name of the farm work, a “basic action” that is a finer action than the farm work, and a feature amount of the movement for each basic action The work motion feature amount list associated with the “motion feature amount” is stored. For example, the “weeding” operation includes a “weeding” operation in which the grass is taken by hand while crouching and a “weeding” operation in which the taken grass is carried out of the farm. Since the movements are completely different, the “Weeding” work decision and the “Weeding” work decision are made individually, and if the “Weeding” work and the “Weeding” work are close in time, the “Weeding” As good as

  Next, the processing operation of the work recording apparatus 20b according to the third embodiment will be described with reference to FIG. The work recording apparatus 20b according to the third embodiment acquires work record data and selects a farm candidate, a crop candidate, and a farm work candidate, similarly to the process of the work recording apparatus 20b according to the second embodiment illustrated in FIG. Step S501 to Step S504).

  Then, the work recording apparatus 20b according to the third embodiment selects a basic motion candidate from the selected farm work candidates (Step S505), and performs a feature amount extraction process from the acquired worker motion data (Step S506). Subsequently, the work recording device 20b selects a basic motion candidate that matches the feature amount within a predetermined range from the feature amount of the basic motion candidate from the work motion feature amount list (step S507).

  Then, the work recording device 20b determines whether any of the selected basic motion candidates are included in the same farm work (step S508), and as a result, if there are those included in the same farm work (step S508). (Yes), it is determined whether the time difference between the basic motion candidates included in the same farm work is within a predetermined time (step S509).

  As a result, when it is determined that the time difference is within the predetermined time (Yes at Step S509), the work recording device 20b determines each basic motion candidate included in the same farm work as one farm work (Step S510). , Return to S508. If it is determined that the time difference is not within the predetermined time (No at Step S509), the work recording apparatus 20b returns to S508 without determining each basic motion candidate as one agricultural work.

  In addition, when there are no selected basic motion candidates included in the same farm work (No in step S508), the work recording device 20b includes basic actions that are not determined as farm work among the basic motion candidates. (Step S511). As a result, when there is a basic motion that has not been determined as agricultural work among the basic motion candidates (Yes in step S511), the work recording device 20b determines the basic motion with the closest motion feature amount from the basic motion candidates. Then, the farm work is determined from the determined basic operation (step S513).

  As described above, according to the third embodiment, the work recording apparatus 20b uses the feature amount of the farmer's movement to select a basic motion candidate finer than the farm work and then identifies the farm work. Can be performed.

  By the way, in said Examples 1-3, although the case where a farm work was specified using the feature-value of a farm worker's movement was demonstrated, a present Example is not limited to this, A farm worker's movement is demonstrated. The farm work may be identified using the temporal order of the basic operations of the farm work and the duration of the basic actions together with the feature amount.

  Therefore, in the following Example 4, as a case where the farm work is specified using the temporal order of the basic action of the farm work and the duration of the basic action, FIG. 18 and FIG. 19 are used. The process of the work recording device 20c will be described. FIG. 18 is a diagram illustrating an example of the work motion feature amount list in consideration of the order.

  The work recording apparatus 20c according to the fourth embodiment stores a work movement feature amount list considering the order as illustrated in FIG. Specifically, as illustrated in FIG. 18, the work movement feature quantity list includes, for each work name, “order” indicating the order of basic actions, “action name” indicating the names of basic actions, and basic The “duration” of the motion and the “motion feature amount” of the basic motion are stored in association with each other.

  For example, the cabbage “harvest” operation involves moving the hand back and forth while crouching to “cut out” the cabbage, moving the hand slowly back and forth to “crate” the cabbage, and the next cabbage position. When these three operations are performed in sequence, it is determined that the cabbage is “harvesting”. In addition, the duration of the “cut” operation and the “put in the cage” operation is 1 s to 5 s, and the “walking” operation is 1 s to 60 s. Therefore, if the duration is within this range, it can be determined that the operation.

  Next, the processing operation of the work recording apparatus 20c according to the fourth embodiment will be described with reference to FIG. The work recording apparatus 20c according to the fourth embodiment obtains work record data in the same manner as the process of the work recording apparatus 20c according to the third embodiment illustrated in FIG. 17, and obtains farm candidates, crop candidates, farm work candidates, and first basics. A motion candidate is selected, and a feature amount is extracted from the motion data (steps S601 to S606).

  Thereafter, the work recording apparatus 20c according to the fourth embodiment determines whether the duration satisfies the condition from the characteristics of the basic motion candidates (step S607). As a result, the work recording device 20c determines that the feature amount of the basic motion candidate and the extracted feature amount are within a predetermined range when the duration satisfies the condition from the feature amounts of the basic motion candidate (Yes in step S607). (Step S608).

  As a result, when the feature amount of the basic motion candidate matches the extracted feature amount within the predetermined range (Yes in step S608), the work recording device 20c sets the matching basic motion candidate as the second basic motion candidate. Select (step S609). Thereafter, the work recording apparatus 20c determines whether the process of selecting the second basic motion candidate has been performed for all groups (step S610), and repeats the processes of steps S606 to S609 until the above process is performed for all groups.

  Then, the work recording device 20c determines whether there are those included in the same farm work among the second basic action candidates (step S611), and as a result, those included in the same farm work among the second basic action candidates. If there is (Yes in step S611), it is determined whether the order of the second basic motion candidates including the same farm work meets the conditions of the work motion feature amount list (step S612).

  As a result, when the order between the second basic motion candidates including the same farm work meets the conditions of the work motion feature list (Yes in step 612), the work recording device 20c selects the second basic motion candidates that meet the conditions. It decides as one farm work (Step S613), records it as work record, and returns to Step S611.

  Then, when there is no second basic motion candidate included in the same farm work (No in step S611), the work recording device 20c determines that the second basic motion candidate is not farm work and performs the process without recording it as a work record. finish.

  As described above, according to the fourth embodiment, the work recording device 20 specifies the farm work using the extracted feature quantity and the order of the work types and the duration of the work type, so the work recording is performed with higher accuracy. It becomes possible.

  By the way, in said Examples 1-4, although the case where a farm work was specified using the feature-value of a farm worker's movement was demonstrated, a present Example is not limited to this, A farm worker's movement is demonstrated. The farm work may be specified in consideration of the direction of the farmer's body along with the feature amount.

  Therefore, in the following fifth embodiment, the processing of the work recording device 20d in the fifth embodiment will be described with reference to FIGS. 20 to 24 as a case where the farm work is specified in consideration of the direction of the farmer's body. In the action recording apparatus according to the fifth embodiment, a geomagnetic sensor may be attached to the farmer's waist. The work recording apparatus 20d according to the fifth embodiment can acquire information related to the body orientation from an action recording apparatus having a geomagnetic sensor.

  Here, the work movement feature quantity list including the walking method and the body orientation stored in the work recording device 20d will be described. FIG. 20 is a diagram illustrating an example of a work motion feature amount list including a way of walking and a body orientation. The work recording apparatus 20d according to the fifth embodiment stores a work movement feature quantity list including a way of walking and a body orientation, as illustrated in FIG. In this work movement feature amount list, information on how the farm worker walks and the direction of the body is included as the “motion feature amount”.

  Here, a process in which the work recording apparatus 20d according to the fifth embodiment determines how to walk from the body direction and the movement direction will be described. FIG. 21 is a diagram for explaining processing for determining how to walk from the direction of the body and the direction of movement. As illustrated in FIG. 21, the work recording device 20 d acquires information on the body orientation and position information from the behavior recording device, and determines the movement direction and the body orientation of the farm worker.

  Then, the work recording device 20d determines whether the farm worker walks sideways or forward, based on the determined moving direction and body orientation. For example, in order to harvest a crop with a high cocoon such as a cucumber, it may be determined that it is a harvesting operation by walking sideways.

  Further, as shown in FIG. 22, the work recording device 20d may determine, as a feature amount, whether it is facing the crop or facing sideways from the body direction and the ridge direction. FIG. 22 is a diagram for explaining the process of determining the posture from the ridge and the body direction. The direction of the undulation may be registered in advance in the database, or may be determined from the locus of the position acquired from the action recording device as shown in FIG. FIG. 23 is a diagram for explaining processing for determining the direction of ridges.

  Here, processing for determining the direction of the ridge will be described. FIG. 24 is a flowchart illustrating the processing operation for determining the ridge direction of the work recording apparatus 20d according to the fifth embodiment. As shown in the figure, the work recording apparatus 20d calculates a moving average of the movement trajectory (step S701). Specifically, the work recording device 20d measures a worker trajectory indicating the trajectory moved by the farm worker, as shown in FIG.

  Then, the work recording apparatus 20d calculates the average moving direction within a predetermined time (step S702), counts all the average moving directions, and sets the direction in which the count value reaches a peak as the undulation direction (step S703). .

  As described above, according to the fifth embodiment, the work recording device 20 identifies the farm work using the information on the direction of the farmer's body together with the feature amount of the worker's movement. As a result of consideration, it is possible to perform work recording with higher accuracy.

  By the way, in this embodiment, when the action recording device is separately attached to the farm worker and the work machine, if the distance between the worker and the work machine at each time is within a predetermined range, the worker You may make it determine with using.

  Therefore, in Example 6 below, it is determined whether the distance between the worker and the work machine at each time is within a predetermined range. If the distance is within the predetermined range, the worker uses the work machine. The process of the work recording apparatus 20e in the sixth embodiment will be described with reference to FIGS. FIG. 25 is a diagram illustrating an example of trajectories of workers and work machines. FIG. 26 is a diagram illustrating an example of trajectories of grouped workers and work machines. FIG. 27 is a diagram for explaining processing for determining each group as a series of farm work.

  A process for determining whether the distance between the worker and the work machine at each time is within a predetermined range, and a process for determining that the worker is using the work machine, using the examples of FIGS. Will be described. As shown in FIG. 25, the work recording apparatus 20e according to the sixth embodiment has distances between worker positions p1, p2, and p3 and work machine positions q1, q2, and q3 within a predetermined range. Determines that the worker is using the work machine.

  On the other hand, the work recording device 20e determines that p11 and q11, and p12 and q12 are separated from each other by a predetermined distance or more, so that the worker and the work machine are acting differently. Then, the work recording device 20e obtains from the movements of the workers by grouping the groups determined to be using the work machine when the respective tracks are grouped in a predetermined time unit. The work is determined using either the work candidate or the work candidate obtained from the movement of the work machine.

  For example, as shown in FIG. 26, there is no work candidate having a feature amount close to a predetermined range within the group G1 of workers, but the work a1 is a candidate for the group G1 of work machines. In this case, the group G2 is a worker group G2 and the work a1 is a candidate, but the work machine group G2 has no work candidate. At this time, as shown in FIG. 27, the work recording device 20e collectively determines G1-G2 as work a1.

  Here, the processing operation of the work recording apparatus 20e according to the sixth embodiment will be described with reference to FIG. FIG. 28 is a flowchart illustrating the processing operation of the work recording apparatus according to the sixth embodiment. As shown in the figure, the work recording device 20e extracts the feature amount of the worker for each group, selects a work candidate for the worker (step S801), extracts the feature amount of the work machine for each group, A work candidate for the work machine is selected (step S802).

  Subsequently, the work recording device 20e determines whether the distance between the worker and the work machine is within a predetermined range for each group (step S803). As a result, when it is determined that the distance between the worker and the work machine is within a predetermined range for each group (Yes at Step S803), the work recording device 20e sets the worker and the work machine as the same group (Step S804). ).

  The work recording device 20e determines that the most continuous work between the groups among the work candidates of the workers and the work candidates of the work machine is the farm work (step S805), and determines whether there is a continuous work candidate between the groups ( In step S806), if there are continuous work candidates between groups (Yes in step S806), the process returns to step S805 to repeat the above processing.

  In addition, the work recording apparatus 20e determines whether the number of continuous work candidate groups is equal to or greater than the specified number (for example, three) (step S807). As a result, when the number of continuous work candidate groups is the specified number of groups (Yes at Step S807), the work recording device 20e records as a series of farm work (Step S808). If the number of consecutive work candidate groups is less than the specified number (No in step S807), the work recording apparatus 20e ends the process without recording as farm work.

  In the process described with reference to FIG. 28, only motion data is used for work determination. However, work determination may be performed using the fact that the worker uses a work machine. For example, if the work machine is an “agricultural chemical spreader”, if it is determined that the worker is using the agricultural chemical spreader, the work of the worker may be determined as “agricultural chemical spreader”.

  Further, the joint work between the workers may be determined in the same manner as the joint work determination between the worker and the work machine. If a plurality of workers are within a predetermined distance, they may be determined as the same group as a joint work. Furthermore, instead of using the distance between workers, it may be possible to collaborate by being on the same farm. That is, when there are a plurality of workers on the same farm at the same time, there is a high possibility that the same work is being performed.

  In addition, work machines such as tractors and agricultural chemical spreaders may be left on farms or work sheds after work is completed. For this reason, when the behavior recording device attached to the worker returns to his / her home or office after working on the farm, the behavior recording device returns to the area capable of wireless communication with the work recording device 20e. Often not come back to the possible area.

  Therefore, as described with reference to FIG. 12 in the first embodiment, the action recording device 10e attached to the worker records time, position, and motion data only when motion is detected, and can communicate with the work recording device. Then, the recorded data is transferred (steps S301 to S304), but the action recording device 10e attached to the work machine once instead of directly transmitting the data to the work recording device as shown in FIG. The data may be transferred to the worker action recording device 10e.

  Here, the data transfer process of the action recording device 10e attached to the work machine according to the sixth embodiment will be described with reference to FIG. FIG. 29 is a flowchart illustrating the data transfer processing operation of the action recording device 10e attached to the work machine according to the sixth embodiment. As shown in the figure, when the action recording device 10e attached to the work machine detects a movement (step S901), the position, movement data, and time information of the work machine are recorded as record data (step S902).

  Then, the behavior recording device 10e determines whether or not communication with the worker behavior recording device is possible (step S903). If communication is possible (Yes in step S903), the recorded position of the working machine, motion data, The time information is transferred to the worker action recording device (step S904), and the process returns to S901.

  As described above, according to the sixth embodiment, the work recording device 20e determines that the worker is using the work machine if the distance between the worker and the work machine at each time is within a predetermined range. Since workers and work machines are grouped together, work contents are judged more reliably because the work contents are judged from the movements of both workers and work machines, or the fact that the worker is using the work machine. It becomes possible to judge.

  Although the embodiments of the present invention have been described so far, the present embodiments may be implemented in various different forms other than the above-described embodiments. Accordingly, another embodiment included in the present invention will be described below as a seventh embodiment.

(1) System Configuration, etc. Each component of each illustrated device is functionally conceptual and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the farm candidate selection unit 23b, the crop candidate selection unit 23c, and the farm work candidate selection unit 23d may be integrated. Further, all or a part of each processing function performed in each device may be realized by a CPU and a program that is analyzed and executed by the CPU, or may be realized as hardware by wired logic.

  In addition, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedure, control procedure, specific name, and information including various data and parameters shown in the above-described document and drawings can be arbitrarily changed unless otherwise specified.

(2) Program By the way, the various processes described in the above embodiments can be realized by executing a program prepared in advance by a computer. Therefore, in the following, an example of a computer that executes a program having the same function as in the above embodiment will be described with reference to FIG. FIG. 30 is a diagram illustrating a computer that executes a work recording program.

  As shown in the figure, a computer 600 as a work recording device is configured by connecting an HDD 610, a RAM 620, a ROM 630, and a CPU 640 via a bus 650.

  In the ROM 630, a work recording program that exhibits the same function as in the above-described embodiment, that is, as shown in FIG. 30, an action record data acquisition program 631, a farm candidate selection program 632, a feature amount extraction program 633, a work A specific program 634 and a farm specific program 635 are stored in advance. Note that the programs 631 to 635 may be appropriately integrated or distributed in the same manner as each component of the work recording apparatus shown in FIG.

  Then, the CPU 640 reads these programs 631 to 635 from the ROM 630 and executes them, so that each program 631 to 635 has an action record data acquisition process 641, a farm candidate selection process 642, a feature amount, as shown in FIG. It functions as an extraction process 643, a work identification process 644 and a farm identification process 645. Each process 641 to 645 corresponds to the action record data acquisition unit 23a, the farm candidate selection unit 23b, the feature amount extraction unit 23e, the work identification unit 23f, and the farm identification unit 23g illustrated in FIG.

  Further, as shown in FIG. 30, farm work data 611 and work record data 612 are provided in the HDD 610. The farm work data 611 and the work record data 612 correspond to the farm work database 22 and the work record unit 24 shown in FIG. The CPU 640 registers data in the farm work database 22 and the work recording unit 24, reads data from the farm work database 22 and the work recording unit 24, stores the data in the RAM 620, and performs processing based on the data stored in the RAM 620. Execute.

  Regarding the embodiment including the above Examples 1 to 7, the following additional notes are further disclosed.

(Supplementary Note 1) An action record data acquisition unit that acquires movement data related to the position of the worker and the movement of the worker;
A field candidate selection unit for selecting a field candidate on which the worker is working according to the position of the worker acquired by the action record data acquisition unit;
A feature quantity extraction unit that extracts feature quantities from the movement data of the worker acquired by the behavior record data acquisition unit;
Using the feature amount extracted by the feature amount extraction unit, a work type identification unit that identifies the type of work performed by the worker;
Based on the work type specified by the work type specifying unit, a field specifying unit for specifying a field on which the worker has performed work from among the field candidates selected by the field candidate selecting unit;
A work recording unit that records the work type specified by the work type specifying unit as a work record in association with the field specified by the field specifying unit;
A work recording apparatus comprising:

(Appendix 2) A field crop list storage unit for storing crops cultivated in each field;
A work movement feature quantity list storage unit that stores a work type necessary for the crop and a feature quantity of movement for each work type in association with each other;
A crop candidate selection unit that selects, from the field crop list storage unit, crop candidates that are cultivated in the field stored in association with the field candidate selected by the field selection unit;
A work candidate selection unit that selects a work necessary for the crop stored in association with the crop candidate selected by the crop candidate selection unit as a work candidate from the work motion feature list storage unit; ,
The work type identification unit detects a work type associated with a feature quantity closest to the feature quantity extracted by the feature quantity extraction unit from the work candidates selected by the work candidate selection unit, and The work recording apparatus according to appendix 1, wherein a work candidate is specified as a work type performed by the worker.

(Additional remark 3) The field position list storage part which memorizes the expansion field expanded including the field field of the field is further provided,
When the position of the operator acquired by the action record data acquisition unit is within the expansion area stored by the field position list storage unit, the field selection unit selects a field included in the expansion area. The work recording apparatus according to Supplementary Note 1 or 2, wherein the work recording apparatus is selected as a field candidate.

(Appendix 4) The action record data acquisition unit acquires movement data related to the position of the worker and the movement of the worker, groups the position of the worker and the movement of the worker at predetermined time intervals,
The feature amount extraction unit extracts a feature amount for each group from the movement data of the worker acquired by the action record data acquisition unit,
The work candidate selection unit selects the work candidate for each group from the work motion feature amount list storage unit using the feature amount for each group extracted by the feature amount extraction unit,
The work type specifying unit, when work candidates are continuous among groups among the work candidates selected by the work candidate selection unit, the work candidates continuous between the groups are set as work types. 4. The work recording device according to appendix 2 or 3, characterized by specifying.

(Additional remark 5) The said work type specific | specification part specifies a work type using the order of work classification and the duration of work classification with the feature-value extracted by the said feature-value extraction part. The work recording device according to any one of?

(Additional remark 6) The said work classification specific | specification part specifies a work classification using the information regarding the direction of a farm worker's body with the feature-value of a worker's movement, Any one of Additional remark 1-4 characterized by the above-mentioned. Recording device described in one.

(Appendix 7) The action record data acquisition unit acquires movement data related to the position of the work machine and movement of the work machine together with movement data related to the position of the worker and movement of the worker,
It is determined whether the distance between the position of the worker acquired by the action record data acquisition unit and the position of the work machine is within a predetermined range, and if it is determined that the distance is within the predetermined range, A work recording apparatus, further comprising a work machine distance determination unit that determines that an operator is using the work machine.

(Supplementary note 8) A behavior recording device that detects movement data related to the position of the worker and the movement of the worker, and a work recording device that records the field on which the work was performed and the type of work performed by the worker as a work record. A work recording system comprising:
The work recording device is
An action record data acquisition unit for acquiring movement data relating to the position of the worker and the movement of the worker from the action recording device;
A field candidate selection unit for selecting a field candidate on which the worker is working according to the position of the worker acquired by the action record data acquisition unit;
A feature quantity extraction unit that extracts feature quantities from the movement data of the worker acquired by the behavior record data acquisition unit;
A work type identifying unit that identifies a work type performed by the worker using the feature amount extracted by the feature amount extraction unit;
Based on the work type specified by the work type specifying unit, a field specifying unit for specifying a field on which the worker has performed work from among the field candidates selected by the field candidate selecting unit;
A work recording unit that records the work type specified by the work type specifying unit as a work record in association with the field specified by the field specifying unit;
A work recording system comprising:

(Supplementary Note 9) Action record data acquisition procedure for acquiring movement data related to worker position and worker movement;
A field candidate selection procedure for selecting a field candidate on which the worker is working according to the position of the worker acquired by the action record data acquisition procedure;
A feature amount extraction procedure for extracting a feature amount from the movement data of the worker acquired by the action record data acquisition procedure;
Using the feature amount extracted by the feature amount extraction procedure, a work type specifying procedure for specifying the work type performed by the worker;
Based on the work type specified by the work type specifying procedure, a field specifying procedure for specifying a field on which the worker has performed work from among the field candidates selected by the field candidate selection procedure;
A work recording procedure for recording the work type identified by the work type identification procedure and the field identified by the field identification procedure as a work record in association with each other;
A work recording program for causing a computer to execute.

DESCRIPTION OF SYMBOLS 10 Action recording apparatus 11 Position detection part 12 Motion detection part 13 Clock 14 Recording part 15 Communication part 20 Work recording apparatus 21 Communication part 22 Farm work database 22a Farm position crop list memory | storage part 22b Work motion feature-value list memory | storage part 22c Worker ID management Information storage unit 23 Control unit 23a Action record data acquisition unit 23b Farm candidate selection unit 23c Agricultural crop candidate selection unit 23d Agricultural work candidate selection unit 23e Feature quantity extraction unit 23f Work identification unit 23g Farm identification unit 24 Work recording unit

Claims (7)

An action record data acquisition unit for acquiring movement data relating to the position of the worker and the movement of the worker;
A field candidate selection unit for selecting a field candidate on which the worker is working according to the position of the worker acquired by the action record data acquisition unit;
A feature quantity extraction unit that extracts feature quantities from the movement data of the worker acquired by the behavior record data acquisition unit;
A work type identifying unit that identifies a work type performed by the worker using the feature amount extracted by the feature amount extraction unit;
Based on the work type specified by the work type specifying unit, a field specifying unit for specifying a field on which the worker has performed work from among the field candidates selected by the field candidate selecting unit;
A work recording unit that records the work type specified by the work type specifying unit as a work record in association with the field specified by the field specifying unit;
A work recording apparatus comprising: A field crop list storage unit for storing crops cultivated in each field;
A work movement feature quantity list storage unit that stores a work type necessary for the crop and a feature quantity of movement for each work type in association with each other;
A crop candidate selection unit that selects, from the field crop list storage unit, crop candidates that are cultivated in the field stored in association with the field candidate selected by the field selection unit;
A work candidate selection unit that selects a work necessary for the crop stored in association with the crop candidate selected by the crop candidate selection unit as a work candidate from the work motion feature list storage unit; ,
The work type identification unit detects a work type associated with a feature quantity closest to the feature quantity extracted by the feature quantity extraction unit from the work candidates selected by the work candidate selection unit, and The work recording apparatus according to claim 1, wherein a work candidate is specified as a work type performed by the worker. A field position list storage unit that stores an enlarged area including the area of the field;
When the position of the operator acquired by the action record data acquisition unit is within the expansion area stored by the field position list storage unit, the field selection unit selects a field included in the expansion area. The work recording apparatus according to claim 1, wherein the work recording apparatus is selected as a field candidate. The behavior record data acquisition unit acquires movement data related to the position of the worker and the movement of the worker, groups the position of the worker and the movement of the worker for each predetermined time,
The feature amount extraction unit extracts a feature amount for each group from the movement data of the worker acquired by the action record data acquisition unit,
The work candidate selection unit selects the work candidate for each group from the work motion feature amount list storage unit using the feature amount for each group extracted by the feature amount extraction unit,
The work type specifying unit, when work candidates are continuous among groups among the work candidates selected by the work candidate selection unit, the work candidates continuous between the groups are set as work types. The work recording apparatus according to claim 2, wherein the work recording apparatus is specified.   The work type specifying unit specifies the work type using the order of the work types and the duration of the work type together with the feature amount extracted by the feature amount extraction unit. The work recording apparatus according to any one of the above. A work recording system comprising: an action recording device that detects movement data relating to a worker's position and the movement of the worker; and a work recording device that records the field in which the work is performed and the type of work performed by the worker as a work record. Because
The work recording device is
An action record data acquisition unit for acquiring movement data relating to the position of the worker and the movement of the worker from the action recording device;
A field candidate selection unit for selecting a field candidate on which the worker is working according to the position of the worker acquired by the action record data acquisition unit;
A feature quantity extraction unit that extracts feature quantities from the movement data of the worker acquired by the behavior record data acquisition unit;
Using the feature amount extracted by the feature amount extraction unit, a work type identification unit that identifies the type of work performed by the worker;
Based on the work type specified by the work type specifying unit, a field specifying unit for specifying a field on which the worker has performed work from among the field candidates selected by the field candidate selecting unit;
A work recording unit that records the work type specified by the work type specifying unit as a work record in association with the field specified by the field specifying unit;
A work recording system comprising: Action record data acquisition procedure for acquiring movement data relating to the position of the worker and the movement of the worker;
A field candidate selection procedure for selecting a field candidate on which the worker is working according to the position of the worker acquired by the action record data acquisition procedure;
A feature amount extraction procedure for extracting a feature amount from the movement data of the worker acquired by the action record data acquisition procedure;
Using the feature amount extracted by the feature amount extraction procedure, a work type specifying procedure for specifying the work type performed by the worker;
Based on the work type specified by the work type specifying procedure, a field specifying procedure for specifying a field on which the worker has performed work from among the field candidates selected by the field candidate selection procedure;
A work recording procedure for recording the work type identified by the work type identification procedure and the field identified by the field identification procedure as a work record in association with each other;
A work recording program for causing a computer to execute.

Images