Work time prediction device, server device, terminal device, work time prediction method and program

A system using historical data and workability coefficients improves landscaping work time prediction, enhancing accuracy and cost estimation for landscaping tasks.

JP7587695B2Active Publication Date: 2024-11-20HONDA MOTOR CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
JP2023528799
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-06-15
Publication Date
2024-11-20
Estimated Expiration
2041-06-15

AI Technical Summary

Technical Problem

Existing methods for predicting work time in landscaping tasks, such as lawn mowing and grass cutting, lack accuracy, leading to imprecise estimates.

Method used

A system utilizing a server device and terminal device to acquire area information, leverage historical data through regression analysis, and apply coefficients based on workability factors to predict work time accurately.

Benefits of technology

Enhances the precision of work time estimation by considering area size, slope, obstacles, and plant types, allowing for more accurate cost estimation and resource allocation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007587695000001
    Figure 0007587695000001
  • Figure 0007587695000002
    Figure 0007587695000002
  • Figure 0007587695000003
    Figure 0007587695000003
Patent Text Reader

Abstract

According to the present invention, an acquisition means acquires area information related to the present work area. A prediction means predicts working hours for the present work area on the basis of the area information acquired by the acquisition means and history information in which area information related to a past work area and time information related to working hours for the past work area are associated with each other.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an activity time prediction device, a server device, a terminal device, an activity time prediction method, and a program. [Background technology]

[0002] In parks, gardens, etc., work such as mowing the lawn or weeding is sometimes performed by landscapers. Landscapers perform the work using devices such as lawnmowers (e.g., Patent Document 1), trimmers, or blowers, or by hand. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2009-118823 A Summary of the Invention [Problem to be solved by the invention]

[0004] When a landscaper receives a request for work from a client, the landscaper may observe the area to be worked on, predict the work time, and estimate the work cost based on the predicted work time. Therefore, it is desirable to improve the accuracy of the work time prediction in order to make an appropriate estimate.

[0005] The present invention provides a technique for appropriately predicting task time. [Means for solving the problem]

[0006] According to one aspect of the present invention, An acquisition means for acquiring area information relating to the current work area; a prediction means for predicting a work time in the current work area based on the area information acquired by the acquisition means, and history information in which area information on past work areas and time information on work times in the past work areas are associated with each other. picture, The prediction means predicts a work time required for the current work in the work area by using a calculation formula based on the history information, The arithmetic formula is a regression formula obtained by regression analysis using values ​​based on the history information as explanatory variables and response variables. The present invention provides an operation time prediction device. Effect of the Invention

[0007] According to the present invention, the operation time can be appropriately predicted. [Brief description of the drawings]

[0008] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. [Figure 1] FIG. 1 is a diagram showing an overview of an operation time prediction system according to an embodiment. [Diagram 2] FIG. 13 is a diagram showing an example of a work area for which a work time is predicted. [Diagram 3] FIG. 4 is a diagram showing an example of data stored in a storage unit. [Figure 4] FIG. 4 is a sequence diagram showing an example of control of a server device and a terminal device. [Diagram 5] FIG. 11 is a diagram showing an example of a screen of the display unit when input of area information is accepted. [Figure 6] FIG. 13 is a diagram showing an example of a screen of the display unit regarding predicted work time and estimates. [Figure 7] 5 is a flowchart showing a specific example of the process in FIG. 4. [Figure 8] A diagram showing historical information about a turf field. [Figure 9] FIG. 1 is a diagram showing an overview of an operation time prediction system according to an embodiment. [Figure 10] FIG. 4 is a sequence diagram showing an example of control of a server device and a terminal device. [Figure 11] 11A and 11B are diagrams showing examples of screens displayed on a display unit in a determination result confirmation process. [Figure 12] FIG. 11 is a diagram showing an example of a screen of the display unit when input of area information is accepted. [Figure 13] 5 is a flowchart showing a specific example of the process in FIG. 4. [Figure 14]5 is a flowchart showing a specific example of the process in FIG. 4. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims, and not all combinations of features described in the embodiments are essential to the invention. Two or more features among the multiple features described in the embodiments may be arbitrarily combined. In addition, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0010] First Embodiment <System Overview> Fig. 1 is a diagram showing an overview of a work time prediction system SY1 (hereinafter, system SY1) according to one embodiment. The system SY1 is a system for predicting the time required for a landscaper or the like to perform work such as mowing the lawn or weeding in a park, garden, or the like. The system SY1 includes a server device 1 and a terminal device 2. The server device 1 and the terminal device 2 are provided so as to be able to communicate with each other via a network NW such as the Internet.

[0011] The server device 1 functions as a task time prediction device for predicting the time required for a task. The server device 1 includes a processing unit 101, a storage unit 102, and a communication unit 103. The processing unit 101, the storage unit 102, and the communication unit 103 are connected by a bus (not shown). The processing unit 101 is a processor represented by a CPU, and realizes various functions related to the server device 1 as a task time prediction device by executing a program stored in the storage unit 102. The storage unit 102 is, for example, a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), or a solid state drive (SSD), and stores various data in addition to the program executed by the processing unit 101. The communication unit 103 is a communication interface with an external device.

[0012] The terminal device 2 is, for example, a terminal operated by a user who performs work. The terminal device 2 may be, for example, a tablet, a smartphone, a PC, or the like. The terminal device 2 includes a processing unit 201, a storage unit 202, a communication unit 203, a display unit 204, and an input unit 205. The processing unit 201, the storage unit 202, the communication unit 203, the display unit 204, and the input unit 205 are connected by a bus (not shown). The processing unit 201 is a processor represented by a CPU, and realizes various functions related to the terminal device 2 by executing a program stored in the storage unit 202. The storage unit 202 is, for example, a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), or a solid state drive (SSD), and stores various data in addition to the program executed by the processing unit 201. The communication unit 203 is a communication interface with an external device.

[0013] The display unit 204 is a user interface that displays various information. For example, the display unit 204 may be a liquid crystal display or an organic EL panel. The input unit 205 is a user interface that accepts input from a user. For example, the input unit 205 may be a touch panel, a pointing device such as a mouse, or a hard key.

[0014] 1 shows one terminal device 2, two or more terminal devices 2 may be configured to be able to communicate with the server device 1. The server device 1 may be divided into two or more elements as necessary. That is, the server device 1 may be configured as an operation time prediction device by combining a plurality of devices. At least a part of the functions realized by the server device 1 may be realized by a known semiconductor device such as a programmable logic device (PLD) or an application specific integrated circuit (ASIC).

[0015] <Work area> 2 is a diagram showing an example of a work area 5 for which a work time is to be predicted. In this embodiment, the work area 5 is divided into a lawn area 51, a grass area 52, a handheld area 53, and a hedge area 54 according to the content of the work to be performed by the landscaper.

[0016] The lawn area 51 is an area where grass is planted. For example, the landscaper performs lawn mowing work using a riding lawnmower 61 or a walk-behind lawnmower (not shown). Alternatively, lawn mowing work may be performed by an autonomous robot lawnmower or the like. In this embodiment, trees 58 are planted in the lawn area 51, and the landscaper performs work while avoiding the trees 58 and their surroundings. In other words, the trees 58 and the area around them are areas where the work machine cannot enter.

[0017] The grass area 52 is an area where grass grows. For example, the landscaper performs grass cutting work using a riding grass cutter 62 or a walk-behind grass cutter. Alternatively, grass cutting work may be performed by an autonomous robotic grass cutter. In this embodiment, a pond 55 is disposed in the grass area 52, and the landscaper performs work while avoiding the pond 55 and its surroundings.

[0018] The handheld area 53 is an area where the landscaper performs manual work. In this embodiment, since it is difficult to work in the area adjacent to the building 56 or the path 57 using a riding lawn mower 61 or a riding grass mower 62, the landscaper performs the work manually using a handheld work machine 63 such as an edger.

[0019] Hedge area 54 is an area where a hedge is planted. For example, a landscaper uses a trimmer 64 to trim the outline of the hedge.

[0020] The division of the work area 5 is for convenience according to the work content, and can be set appropriately.

[0021] <Data Structure> FIG. 3 is a diagram showing an example of data stored in the storage unit 102. In this embodiment, a work history database 1021 is constructed in the storage unit 102, and history information regarding past work is stored therein. In this embodiment, the history information includes information that associates area information regarding past work areas with time information regarding past work times. Additionally, the history information includes information regarding estimates of work costs. In this embodiment, the storage unit 102 manages and stores the history information for each work area using an area ID.

[0022] The area information on the past work area includes the work category, the size of the work area, and a coefficient. The work category is a division of the area in the work area according to the work performed by the landscaper. In FIG. 3, the work categories are lawn, grass, handheld, and hedge, in accordance with the work area 5 in FIG. 2.

[0023] The size of the work area is shown for each work category. For lawns, grasslands, and handhelds, the respective areas are shown. For hedges, the surface area of ​​the part to be worked on is shown. Note that the size of a hedge may be shown, for example, as the area of ​​the area in which the hedge is planted. However, by expressing the size of the hedge as a surface area, the amount of work can be more appropriately understood.

[0024] The coefficient is a value multiplied by the size of the work area. In this embodiment, each coefficient is set to a value between 1 and 2. This coefficient is used to take into account not only the size of the work area but also the ease of work in the work area when predicting the work time described later. For example, when the work area has a slope or when work needs to be done while avoiding the waterside of the work area, it may take more time to work because it is necessary to reduce the moving speed of the work machine. Therefore, when an element that causes an increase in work time exists in the work area, the value obtained by multiplying the size of the work area by a predetermined coefficient is used to predict the work time, so that the work time can be predicted taking into account the ease of work in the work area. In other words, the value of the size x coefficient here can be said to be information used to predict the work time, taking into account the ease of work in the work area.

[0025] In this embodiment, the area information on the past work area includes coefficients related to slope, waterside, objects, and plants. That is, if the work area has a slope, a waterside, or there are objects that need to be avoided, it is considered that the work will take more time, and these factors are set as coefficients. Also, depending on the type of plant to be cut in the work area, it is considered that the work will take more time because it is hard and difficult to cut, and so on, so the type of plant is also set as a coefficient. Note that the targets for which coefficients are set are not limited to these, and can be set as appropriate.

[0026] In this embodiment, the workability information regarding the ease of work in the work area includes coefficients related to the slope, waterside, objects, and plants, but the workability information may be information other than the coefficients. For example, the workability information may be various information related to workability, such as the average slope of the work area, the area of ​​the waterside or object, and the perimeter of the waterside or object. For example, the workability information may be information related to weather, such as sunlight, sunshine hours, temperature, humidity, and precipitation in the work area. For example, the same plant may grow differently depending on sunlight and precipitation, and these may affect the work time. For example, if it rains on the day of work or the day before, the muddyness of the work area may affect the work time. Therefore, the coefficients described above may be set for these pieces of information.

[0027] The time information on past work times includes actual work time, the number of workers, and the number of work machines. Information on estimated work costs includes fuel consumption and actual costs (actual expenses) of the work machines. In this embodiment, the time information on past work times includes information on work time, the number of workers, and the number of work machines for each work category.

[0028] <Control example> 4 is a sequence diagram showing an example of control of the server device 1 and the terminal device 2. For example, this sequence is executed when a landscaper (user) predicts the work time and estimates the cost of a work area. In the following description, each step is simply represented as S1, etc.

[0029] At S1, the processing unit 201 executes an input reception process for area information related to the current work area. The processing unit 201 commands the input unit 205 to receive user input. Here, Fig. 5 is a diagram showing an example of a screen of the display unit 204 when receiving input of area information. In this embodiment, the input unit 205 receives input of area information related to the size of the work area and workability information related to the ease of work in the work area as area information. Here, "area" corresponds to the area information, and "coefficient" corresponds to the workability information related to the ease of work.

[0030] Furthermore, in this embodiment, the input unit 205 can accept input of division information related to work divisions as area information. Then, the input unit 205 accepts input of an area as size information and a coefficient as workability information for each work division. The work division may include at least one of lawn work, grass work, manual work, and hedge work. Furthermore, in this embodiment, for hedges, the input unit 205 accepts the surface area of ​​the part to be worked on as size information.

[0031] Furthermore, in this embodiment, the input unit 205 receives, as information for creating an estimate, the number of workers for each task category and the number of task patterns for which an estimate is to be created.

[0032] In this embodiment, the workability information that is received as input includes information on the slope of the work area, areas in the work area that cannot be accessed by the work machine, objects placed on the work area, and types of plants on the work area. Specifically, the input unit 205 is configured to be able to receive coefficients for each item. Note that the items of the coefficients that are received as input are not limited, and may include at least one of the exemplified items, or may include items other than the exemplified items.

[0033] In S2, the communication unit 203 transmits the area information acquired in S1 to the server device 1 based on a command from the processing unit 201.

[0034] In S3, the processing unit 101 of the server device 1 executes a receiving process of the area information transmitted from the terminal device 2. The processing unit 101 receives the area information transmitted from the terminal device 2 via the communication unit 103. That is, the processing unit 101 acquires area information related to the current working area by receiving the information from the terminal device 2. More specifically, the processing unit 101 acquires information input by the user to the terminal device 2 as the area information.

[0035] In S4, the processing unit 101 predicts the work time in the current work area based on the area information acquired in S3 and history information in which area information related to past work areas and time information related to work times in past work areas are associated with each other. Details of this step will be described later.

[0036] In S5, the processing unit 101 generates an estimate of the work cost based on the work time predicted in S4. For example, the processing unit 101 calculates an estimate taking into account the work time for each work section, the number of workers, the number of work machines, the fuel cost for the work machines, etc.

[0037] In S6, the communication unit 103 transmits information related to the predicted work time and the estimate based on the command from the processing unit 101. That is, the processing unit 101 outputs the work time predicted in S4 and the work cost estimate based on the work time to the terminal device 2 via the communication unit 103. Note that in this embodiment, the processing unit 101 outputs a plurality of patterns of work cost estimates according to the number of work machines used in the current work (see FIG. 6).

[0038] In S7, the processing unit 201 of the terminal device 2 executes a receiving process of the information transmitted from the server device 1. The processing unit 201 receives, via the communication unit 203, information on the predicted work time (prediction result) and the estimate transmitted from the server device 1.

[0039] In S8, the processing unit 201 executes a display process for the received information. The processing unit 201 commands the display unit 204 to display the information received in S7. Fig. 6 is a diagram showing an example of a screen of the display unit 204 relating to the predicted work time and estimates. The display unit 204 displays three patterns of predicted work time (prediction results) and estimates.

[0040] Specifically, in Fig. 6, predicted work times and estimates according to the number of workers and the number of work machines are shown for each pattern and for each task category. For example, pattern 1 is a pattern in which work is performed with the number of workers received by the input unit 205. Pattern 2 is a pattern in which the number of workers and the number of work machines are kept as low as possible, and pattern 3 is a pattern in which shortening work time is prioritized. In this way, by displaying multiple patterns of predicted work times and estimates, an appropriate pattern can be selected according to the personnel allocation, availability of work machines, etc.

[0041] FIG. 7 is a flow chart showing a specific example of step S4. In S401, the processing unit 101 selects a target category for predicting the work time. For example, the processing unit 101 selects a lawn as the target category.

[0042] In S402, the processing unit 101 extracts data on past target sections similar to the current target section. Fig. 8 is a diagram showing past information on turf. In this embodiment, the work history database 1021 manages history information for each work area, but is configured to allow data on a specific work section (turf in the example of Fig. 8) to be extracted and used as needed.

[0043] For example, the processing unit 101 extracts data with a division ID of A0001 as data similar to the current target division. Here, the method of extracting similar data can be set appropriately. For example, data in which items with a coefficient exceeding 1 match may be extracted as similar data. Also, data in which the difference between each item is within a predetermined value or within a predetermined ratio may be extracted as similar data. Furthermore, data in which the difference between the value of area x coefficient is within a predetermined value or within a predetermined ratio may be extracted as similar data. Also, in this embodiment, the processing unit 101 extracts one similar data, but the number of data to be extracted may be two or more. In this case, the processing unit 101 may predetermine the number of data to be extracted, for example, 2 to 5, or may extract all data that satisfies a predetermined condition regarding the similarity.

[0044] In S403, the processing unit 101 determines the predicted work time. An example will be described. First, the processing unit 101 calculates the size of the lawn of the current work area multiplied by a coefficient based on the information received from the terminal device 2. In this example, 450 (area) x 1.3 (slope factor) x 1.4 (object factor) = 819 Next, the processing unit 101 predicts the work time for the lawn based on the calculated area x coefficient value and the similar past data extracted in S402. In this example, the past data shows that the area x coefficient value is 900, the number of workers is 1, the number of work machines is 1, and the actual work time is 40 minutes. On the other hand, for the current lawn, the area x coefficient value is 819, and the other conditions are the same, so the work time is calculated taking into account the difference in the area x coefficient value. 40(min)×(819 / 900)=36.4(min)≒36(min)

[0045] In this way, the processing unit 101 extracts history information of past work areas similar to the current work area, and predicts the work time in the current work area based on the extracted history information. Note that, when multiple similar data are extracted in S402, the average value of these data may be calculated, and the current work time may be calculated based on the average value.

[0046] In S404, the processing unit 101 checks whether or not there is a segment for which the predicted time has not been calculated. If there is a segment for which the predicted time has not been calculated, the process returns to S401, and if not, the process ends this flowchart.

[0047] As described above, according to this embodiment, the processing unit 101 predicts the work time in the current work area based on the history information of past work, and therefore can appropriately predict the work time.

[0048] <Second embodiment> 9 is a diagram showing an overview of a work time prediction system SY2 (hereinafter, system SY2) according to an embodiment. In the second embodiment, the system SY2 includes an image capturing device 3 that captures an image of a work area. Hereinafter, the same components as those in the first embodiment are denoted by the same reference numerals, and the description thereof will be omitted.

[0049] The photographing device 3 is a device for photographing an image used to predict the work time in the work area. The photographing device 3 may be, for example, an air vehicle such as a drone, and may be configured to be able to photograph the work area from the sky. For example, the photographing device 3 may be a mobile body capable of traveling on the work area. The mobile body may be, for example, a work machine such as an autonomous lawnmower, and a camera for peripheral detection provided on the work machine may function as the photographing unit 304 described later. For example, the photographing device 3 may be a surveillance camera or the like. The photographing device 3 may be owned by a landscaper or by a manager of the work area. Alternatively, the photographing device 3 may be a mobile terminal such as a digital camera or a smartphone owned by a general user such as a user of the work area. The photographing device 3 includes a processing unit 301, a storage unit 302, a communication unit 303, a photographing unit 304, and a moving unit 305. The processing unit 301, the storage unit 302, the communication unit 303, the imaging unit 304, and the movement unit 305 are connected by a bus (not shown).

[0050] The processing unit 301 is a processor represented by a CPU, and executes a program stored in the storage unit 302 to realize various functions related to the terminal device 2. The storage unit 302 is, for example, a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), or a solid state drive (SSD), and stores various data in addition to the program executed by the processing unit 301. The communication unit 303 is a communication interface with an external device. The photographing unit 304 is, for example, a camera, and is configured to be able to photograph still images or videos. The moving unit 305 moves the photographing device 3. For example, when the photographing device 3 is a drone, the moving unit 305 may be composed of a propeller and a motor for driving the propeller. Note that when the photographing device 3 is a security camera or a portable terminal such as a digital camera installed in a work area, the moving unit 305 is omitted.

[0051] In this embodiment, the photographing device 3 can be connected to the terminal device 2 by the communication unit 303 in a wired or wireless manner. For example, an image of the work area photographed by the photographing unit 304 is transmitted to the terminal device 2 by the communication unit 303. The communication method here can be appropriately adopted from known technologies, and the terminal device 2 and the photographing device 3 may be capable of communicating with each other by, for example, Wi-Fi (Wireless Fidelity) or Bluetooth (registered trademark). Alternatively, the photographing device 3 may be capable of communicating with the server device 1 or the terminal device 2 via a network NW such as the Internet. Although one photographing device 3 is shown in FIG. 9, two or more photographing devices 3 may be capable of communicating with the terminal device 2.

[0052] FIG. 10 is a sequence diagram showing an example of control of the server device 1, the terminal device 2, and the image capturing device 3. In FIG. In S21, the processing unit 301 controls the photographing unit 304 and the moving unit 305 to photograph the work area. The photographed image obtained in this step may be a still image or a video. For example, when the photographing device 3 is a drone or an autonomous lawnmower, the photographing device 3 starts photographing the work area based on receiving an instruction to photograph the area from the terminal device 2.

[0053] In S22, the communication unit 303 transmits the captured image acquired in S21 to the terminal device 2 based on the command from the processing unit 301.

[0054] In this embodiment, the photographed image is transmitted from the photographing device 3 to the terminal device 2, but the photographed image may be transmitted from the photographing device 3 to the server device 1. In this case, the server device 1 may transmit the photographed image to the terminal device 2 when it receives a transmission request for the photographed image from the terminal device 2. That is, a configuration in which the photographed images of the photographing device 3 are stored in the server device 1 and the terminal device 2 acquires the stored photographed images from the server device 1 as necessary may also be adopted. In addition, the server device 1 may transmit the photographed images received from the photographing device 3 directly to the terminal device 2, or may extract the photographed images required by the terminal device 2 for subsequent processing or perform predetermined image processing before transmitting them to the terminal device 2.

[0055] In S23, the processing unit 201 of the terminal device 2 executes a process for receiving the captured image transmitted from the photographing device 3. The processing unit 201 receives the captured image transmitted from the photographing device 3 via the communication unit 203.

[0056] In S24, the processing unit 201 executes an area determination process using the received captured image. This process is a process for dividing the captured work area into work sections. A publicly known image processing technique can be appropriately adopted for dividing the work area.

[0057] In S25, the processing unit 201 executes a process of confirming the determination result in S24. FIG. 11 is a diagram showing an example of a screen displayed on the display unit 204 in the determination result confirmation process. In FIG. 11, the work area is divided into a lawn determination area 71 determined to be a lawn, a grass determination area 72 determined to be a grass, a handheld determination area 73 determined to be a handheld, and a hedge determination area 74 determined to be a hedge, based on the captured image. In addition, a tree 58 in the lawn determination area 71 and its surroundings are determined to be a non-entry area 76 for a work machine of a work machine. Furthermore, a pond 55 in the grass determination area 72 is determined to be a waterside 75. If the determination of the work area has been performed appropriately based on the confirmation screen displayed on the display unit 204, the user presses a confirmation button using the input unit 205. On the other hand, if the determination of the work area has not been performed appropriately, the user presses a correction button using the input unit 205. When the correction button is pressed, the processing unit 201 may perform the area determination process of S24 again. Alternatively, each determination area may be configured to be correctable by the user on the screen of the display unit 204.

[0058] In S26, the processing unit 201 executes the input reception process of the area information. FIG. 12 is a diagram showing an example of a screen of the display unit 204 when the input of the area information is received. In this embodiment, the numerical values ​​in the thick frame 2041 of the screen are generated by the processing unit 201. That is, the processing unit 201 specifies the size of each of the lawn determination area 71, the grass determination area 72, the handheld determination area 73, and the hedge determination area 74 based on the image captured by the image capture device 3 and the result of the area determination process in S24. In addition, the image processing of the captured image specifies the slope, waterside, objects or plant species to be avoided, etc. in the work area. In this embodiment, the area information is generated based on the image captured by the image capture device 3, so that the effort of the user to input the information can be reduced. In this embodiment, the user only needs to input the number of workers for each work section and the number of work patterns for which an estimate is to be created.

[0059] 4, so explanations of the subsequent steps from S2 onward are omitted, but in this embodiment, the server device 1 as a work time prediction device acquires, as area information related to the work area, information based on images captured by a camera device 3 capable of capturing images of the work area. Therefore, it is possible to reduce the effort required of the user when predicting the work time.

[0060] In this embodiment, the area determination process of S24 is executed by the terminal device 2, but may be executed by the server device 1. By having the server device 1 execute the area determination process, the processing load on the terminal device 2 side can be reduced. In this case, in S22, an image captured by the photographing device 3 may be transmitted to the server device 1. After executing the area determination process, the server device 1 may then transmit to the terminal device 2 information required for the terminal device 2 to execute a process of checking the determination result in S25.

[0061] <Modification 1 of work time prediction> FIG. 13 is a flowchart showing S4 in FIG. 4. In this embodiment, the processing unit 101 obtains a predicted result of the work time by inputting data according to the area information acquired this time to a trained model that has been machine-learned using history information as teacher data. That is, before executing this flowchart, a trained model is generated using history information accumulated in the work history database 1021. The trained model here is a model obtained by a machine learning technique such as CNN (Convolutional Neural Network). Details of the learning method are omitted here, and it is assumed that a known method can be applied. In this embodiment, a trained model is generated using teacher data in which area information (size, coefficient) regarding past work areas included in the history information is input as input data, and time information regarding past work times is output as output data. As a result, when area information of the current work area is input, a predicted work time in the current work area is output. In this embodiment, a trained model is generated for each work category. Since the generation of a trained model imposes a large load, it is assumed that the trained model is generated in advance and stored in the storage unit 102 of the server device 1.

[0062] Since steps S401 and S404 are the same as those in the flowchart of FIG. 7, the description thereof will be omitted. In S412, the processing unit 101 inputs the area information acquired from the terminal device 2 to the trained model. For example, the processing unit 101 inputs the size of the target section and each coefficient to the trained model.

[0063] In S413, the processing unit 101 acquires the output of the trained model as a predicted result of the work time.

[0064] According to this modification, by using a trained model, it is possible to more appropriately predict the work time based on the history information. In this modification, the input data of the trained model is the size of the work area and the coefficient, but for example, the image captured by the image capture device 3 may be used as the input data of the trained model. In other words, the contents of the trained model can be set appropriately.

[0065] <Modification 2 of work time prediction> FIG. 14 is a flowchart showing S4 in FIG. 4. In this embodiment, the processing unit 101 predicts the work time required for the work in the current work area by using an arithmetic expression based on the history information stored in the work history database 1021. That is, when executing this flowchart, a predetermined arithmetic expression is set in advance based on the history information stored in the work history database 1021. The arithmetic expression may be, for example, a regression expression obtained by a simple regression analysis in which the area x coefficient value included in the history information is an explanatory variable and the work time is an objective variable. Alternatively, the arithmetic expression may be a regression expression obtained by a multiple regression analysis in which the area and each coefficient included in the history information are an explanatory variable and the work time is an objective variable. A specific analysis method may be a well-known method.

[0066] Since steps S401 and S404 are the same as those in the flowchart of FIG. 7, the description thereof will be omitted. In S422, the processing unit 101 performs a calculation based on the area information acquired from the terminal device 2. For example, the processing unit 101 acquires a predicted work time as a calculation result by substituting the value of area x coefficient into a calculation formula.

[0067] According to this modification, the operation time can be predicted using an arithmetic expression. In addition, since there is no need to refer to past data stored in the operation history database 1021 when predicting the operation time, the processing load can be reduced.

[0068] <Other embodiments> In the above embodiment, the server device 1 functions as the work time prediction device, but the terminal device 2 may function as the work time prediction device. In this case, the terminal device 2 may obtain information about the current work area by receiving a user's input via the input unit 205. Alternatively, the terminal device 2 may obtain information about the current work area by receiving a captured image from the photographing device 3 and performing area determination processing or the like on the image.

[0069] Regarding the prediction of the work time, for example, when the terminal device 2 predicts the work time according to the flowchart shown in FIG. 7, the processing unit 201 of the terminal device 2 may store history information of past work. Also, for example, when the terminal device 2 predicts the work time according to the flowchart shown in FIG. 13, the server device 1 may generate a trained model using the information of the work history database 1021 stored in the storage unit 102, and the generated trained model may be provided to the terminal device 2. In such a case, when the information of the work history database 1021 is accumulated, the server device 1 may update the trained model and periodically provide the updated trained model to the terminal device 2. Also, for example, when the terminal device 2 predicts the work time according to the flowchart shown in FIG. 14, the server device 1 may acquire an arithmetic expression using the information of the work history database 1021 stored in the storage unit 102, and the acquired arithmetic expression may be provided to the terminal device 2. In such a case, when the information of the work history database 1021 is accumulated, the server device 1 may update the arithmetic expression and periodically provide the updated arithmetic expression to the terminal device 2.

[0070] In the above embodiment, the work time when a landscaper performs work such as mowing the lawn or weeding in a park or garden is predicted, but the configuration of the above embodiment can be applied to prediction of other types of work. For example, the configuration of the above embodiment can be applied to snow removal work using a snowplow, cultivation work using agricultural machinery, ground leveling work using construction machinery, etc.

[0071] <Summary of the embodiment> The above-described embodiment discloses at least the following task time prediction device, server device, terminal device, task time prediction method, and program.

[0072] 1. The operation time prediction device (for example, 1) of the above embodiment is An acquisition means (e.g., 101, S3) for acquiring area information related to the current work area; and a prediction means (e.g., 101, S4) for predicting the work time in the current work area based on the area information acquired by the acquisition means and history information in which area information on past work areas and time information on work times in the past work areas are associated.

[0073] According to this embodiment, the prediction means predicts the work time in the current work area based on the history information of past work, so that the work time can be predicted appropriately.

[0074] 2. According to the above embodiment, The area information includes size information relating to the size of the work area, and workability information relating to the ease of work in the work area.

[0075] According to this embodiment, the prediction means predicts the task time based on the ease of work in the task area, so that the accuracy of the task time prediction can be improved.

[0076] 3. According to the above embodiment, The area information includes division information regarding a division of work, The area information includes information on the area of ​​each of the work sections, The workability information includes information regarding the workability for each category of the work.

[0077] According to this embodiment, the prediction means predicts the task time for each task category based on the ease of the task, so that the accuracy of task time prediction can be improved.

[0078] 4. According to the above embodiment, The acquiring means acquires information input by a user as the area information.

[0079] According to this embodiment, since the task time is predicted based on the information input by the user, the task time can be predicted with a simple configuration.

[0080] 5. According to the above embodiment, The acquisition means acquires, as the area information, information based on an image captured by a device capable of capturing an image of the work area.

[0081] According to this embodiment, since the acquisition means acquires information based on a photographed image as area information, it is possible to reduce the effort required for the user to input area information.

[0082] 6. According to the above embodiment, The prediction means extracts the history information of the past work area similar to the current work area, and predicts the work time in the current work area based on the extracted history information.

[0083] According to this embodiment, since history information of past work areas similar to the current work area is extracted and used to predict the work time, the accuracy of the work time prediction can be improved.

[0084] 7. According to the above embodiment, The prediction means obtains a prediction result of the work time by inputting information according to the area information acquired by the acquisition means into a trained model that has been subjected to machine learning using the historical information as training data.

[0085] According to this embodiment, by using a trained model, it is possible to more appropriately predict work time based on historical information.

[0086] 8. According to the above embodiment, The prediction means predicts the work time required for the current work in the work area by using a calculation formula based on the history information.

[0087] According to this embodiment, since the task time is predicted by an arithmetic expression, the process related to the prediction of the task time can be simplified.

[0088] 9. According to the above embodiment, The system further includes an output means (eg, 101, S5) for outputting an estimate of a task cost based on the task time predicted by the prediction means.

[0089] According to this embodiment, an estimate is output in accordance with the estimated time of the work predicted by the prediction means, so that a highly accurate estimate can be provided to the requester of the work.

[0090] 10. According to the above embodiment, The output means outputs a plurality of patterns of work cost estimates according to the number of work machines used in the current work.

[0091] According to this embodiment, a plurality of estimates can be provided to the requester of the work.

[0092] 11. According to the above embodiment, The apparatus further comprises a storage means (eg, 102) for storing the history information.

[0093] According to this embodiment, the prediction means can predict the operation time based on the history information stored in the storage means.

[0094] 12. According to the above embodiment, The workability information includes information about at least one selected from the group consisting of the slope of the work area, areas in the work area where a work machine cannot enter, objects placed on the work area, and types of plants on the work area.

[0095] According to this embodiment, the prediction means can more appropriately grasp the ease of the task, and therefore the accuracy of prediction of the task time can be improved.

[0096] 13. According to the above embodiment, The area information includes information about the surface area of ​​the hedge to be worked on.

[0097] According to this embodiment, the amount of work can be more appropriately grasped, and therefore the accuracy of prediction of the work time can be improved.

[0098] 14. According to the above embodiment, The work category includes at least one selected from the group consisting of lawn work, grass work, hand work, and hedge work.

[0099] According to this embodiment, it is possible to more appropriately predict the task time according to the task classification.

[0100] 15. The server device (eg, 1) in the above embodiment functions as each of the means (eg, 101) of the task time prediction device described above in 1. to 14.

[0101] According to this embodiment, a server device capable of appropriately predicting a task time is provided.

[0102] 16. The terminal device (eg, 2) in the above embodiment functions as each of the means (eg, 201) of the task time prediction device described above in 1. to 14.

[0103] According to this embodiment, a terminal device capable of appropriately predicting a task time is provided.

[0104] 17. The terminal device of the above embodiment A transmitting means (e.g., 203) for transmitting area information regarding the current work area to the server device of 16 above; A receiving means (e.g., 203, S7) for receiving a prediction result of the prediction means from the server device; and a display means (eg, 204) for displaying the prediction result received by the receiving means.

[0105] According to this embodiment, the result of the operation time prediction by the server device can be confirmed on the terminal device.

[0106] 18. The operation time prediction method of the above embodiment is An acquisition step (e.g., S3) for acquiring area information related to the current work area; The method includes a prediction process (e.g., S4) of predicting the work time in the current work area based on the area information acquired in the acquisition process and historical information in which area information regarding past work areas and time information regarding work times in the past work areas are associated.

[0107] According to this embodiment, the prediction means predicts the task time based on the ease of work in the task area, so that the accuracy of the task time prediction can be improved.

[0108] 19. The program of the above embodiment is Computer, An acquisition means (e.g., S3) for acquiring area information related to the current work area; A prediction means (e.g., S4) for predicting the work time in the current work area based on the area information acquired by the acquisition means, area information related to past work areas, and time information related to work times in the past work areas, and history information in which the area information is associated with the area information acquired by the acquisition means; It will function as a means to:

[0109] According to this embodiment, the prediction means predicts the task time based on the ease of work in the task area, so that the accuracy of the task time prediction can be improved.

[0110] 20. The program of the above embodiment is A program for causing a computer of a terminal device (e.g., 2) capable of communicating with a server device (e.g., 1) to execute a method for displaying a predicted task time, The server device includes: An acquisition means (e.g., 101, S3) for acquiring area information related to the current work area; a prediction means (e.g., 101, S4) for predicting a work time in the current work area based on the area information acquired by the acquisition means, area information on past work areas, and time information on past work times in the work areas, The display method includes: A transmission step (e.g., S2) of transmitting area information regarding the current work area to the server device; A receiving step (e.g., S7) of receiving a prediction result of the prediction means from the server device; and a display step (eg, S8) of displaying the prediction result received in the receiving step.

[0111] According to this embodiment, the prediction means predicts the task time based on the ease of work in the task area, so that the accuracy of the task time prediction can be improved.

[0112] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0113] 1: server device, 2: terminal device, 101: processing unit

Claims

1. An acquisition means for acquiring area information relating to the current work area; a prediction means for predicting a work time in the current work area based on the area information acquired by the acquisition means, and history information in which area information on past work areas and time information on work times in the past work areas are associated with each other, The prediction means predicts a work time required for the current work in the work area by using a calculation formula based on the history information, The operation time prediction device, wherein the arithmetic formula is a regression formula obtained by regression analysis using values ​​based on the history information as explanatory variables and objective variables.

2. The operation time prediction device according to claim 1, The area information includes area information regarding the area of ​​the work area and workability information regarding the ease of work in the work area. A task time prediction device comprising:

3. The operation time prediction device according to claim 2, The area information includes division information regarding a division of work, The area information includes information on the area of ​​each of the work sections, The workability information includes information regarding the workability for each of the work categories. A task time prediction device comprising:

4. The operation time prediction device according to any one of claims 1 to 3, The acquiring means acquires information input by a user as the area information. A task time prediction device comprising:

5. The operation time prediction device according to any one of claims 1 to 3, the acquiring means acquires, as the area information, information based on an image captured by a device capable of capturing an image of the work area; A task time prediction device comprising:

6. An operation time prediction device according to any one of claims 1 to 5, The area information includes division information regarding a division of work, A work time prediction device characterized in that the calculation formula is a regression formula obtained by simple regression analysis or multiple regression analysis with the width of each section included in the historical information and the coefficient value multiplied by the width as explanatory variables, and work time as a response variable.

7. The operation time prediction device according to claim 6, The coefficients include coefficients relating to at least one of slope, water, objects, and vegetation. A task time prediction device comprising:

8. The operation time prediction device according to any one of claims 1 to 7, The system further includes an output unit for outputting an estimate of a task cost based on the task time predicted by the prediction unit. A task time prediction device comprising:

9. The operation time prediction device according to claim 8, The output means outputs a plurality of patterns of work cost estimates according to the number of work machines used in the current work. A task time prediction device comprising:

10. The operation time prediction device according to any one of claims 1 to 9, Further comprising a storage means for storing the history information. A task time prediction device comprising:

11. The operation time prediction device according to claim 2, The workability information includes information on at least one selected from the group consisting of an inclination of the work area, a non-entry area of ​​a work machine in the work area, an object placed on the work area, and a type of plant on the work area. A task time prediction device comprising:

12. The operation time prediction device according to claim 2, The area information includes information about the surface area of ​​the hedge to be worked on; A task time prediction device comprising:

13. The operation time prediction device according to claim 3, The work category includes at least one selected from the group consisting of lawn work, grass work, manual work, and hedge work; A task time prediction device comprising:

14. The operation time prediction device according to claim 6, The operation time prediction device further comprises an input unit that accepts a user input of a value of the coefficient.

15. A server device that functions as each of the means of the operation time prediction device according to any one of claims 1 to 14.

16. A terminal device that functions as each of the means of the operation time prediction device according to any one of claims 1 to 14.

17. a transmitting means for transmitting area information relating to a current work area to the server device according to claim 15; a receiving means for receiving a prediction result of the prediction means from the server device; A display means for displaying the prediction result received by the receiving means. A terminal device comprising:

18. A task time prediction method executed by a task time prediction device, comprising: An acquisition step in which an acquisition means of the operation time prediction device acquires area information related to a current operation area; a prediction step in which a prediction means of the work time prediction device predicts a work time in the current work area based on the area information acquired in the acquisition step and history information in which area information on past work areas and time information on work times in the past work areas are associated with each other, In the prediction step, a work time required for the current work in the work area is predicted using a calculation formula based on the history information, The operation time prediction method, wherein the arithmetic formula is a regression formula obtained by regression analysis using values ​​based on the history information as explanatory variables and objective variables.

19. Computer, A means for acquiring area information relating to the current work area; a prediction means for predicting a work time in the current work area based on the area information acquired by the acquisition means, and history information in which area information on past work areas and time information on work times in the past work areas are associated with each other; A program for causing each of the above-mentioned means to function as the above-mentioned means, The prediction means predicts a work time required for the current work in the work area by using a calculation formula based on the history information, The program, wherein the arithmetic formula is a regression formula obtained by regression analysis using values ​​based on the history information as explanatory variables and objective variables.

20. A program for causing a computer of a terminal device capable of communicating with a server device to execute a method for displaying a predicted task time, The server device includes: An acquisition means for acquiring area information relating to the current work area; a prediction means for predicting a work time in the current work area based on the area information acquired by the acquisition means, and history information in which area information on past work areas and time information on work times in the past work areas are associated with each other, The prediction means predicts a work time required for the current work in the work area by using a calculation formula based on the history information, the arithmetic formula is a regression formula obtained by regression analysis using values ​​based on the history information as explanatory variables and response variables, The display method includes: a transmission step of transmitting area information regarding the current work area to the server device; a receiving step of receiving a prediction result of the prediction means from the server device; A display step of displaying the prediction result received in the receiving step. program.

Citation Information

Patent Citations

  • Autonomous moving device

    JP2009031992A

  • Lawn mower

    JP2009118823A

  • Arrangement optimization system and arrangement optimization method

    JP2020119166A

  • Data analysis device and data analysis method

    JP2021056918A

  • Artificial intelligence robot cleaner

    US20200046193A1