Program, information processing method, and information processing apparatus.

Abstract

To provide a program which can acquire an objective index for accurately performing work in short time.SOLUTION: A program acquires a state amount indicating the state of a manual tool according to motion of a user detected by a detector provided on the manual tool, and causes a computer to execute processing of calculating a feature amount relating to the motion of the user on the basis of the acquired state amount.SELECTED DRAWING: Figure 12

Description

Technical Field

[0001] The present invention relates to a program, an information processing method, and an information processing apparatus.

Background Art

[0002] A polishing tool for mirror polishing has been proposed (see Patent Document 1). A skilled person can perform highly accurate polishing in a short time using the polishing tool.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Since there is no objective index for performing highly accurate polishing in a short time, it is difficult for a person other than a skilled person to perform highly accurate polishing in a short time. Such problems widely exist in various operations using manual tools.

[0005] An object of the present disclosure is to provide a program or the like that can obtain an objective index for performing work with high accuracy in a short time.

Means for Solving the Problems

[0006] A program according to an aspect of the present disclosure causes a computer to execute a process of obtaining a state quantity indicating a state of a manual tool according to an operation of a user detected by a detector provided in the manual tool, and calculating a feature quantity related to the operation of the user based on the obtained state quantity.

[0007] An information processing method according to one aspect of this disclosure involves a computer performing a process to acquire a state quantity indicating the state of a manual tool in accordance with the user's actions, detected by a detector provided in the manual tool, and to calculate a feature quantity related to the user's actions based on the acquired state quantity.

[0008] An information processing device according to one aspect of the present disclosure includes a control unit that acquires a state quantity indicating the state of a manual tool in accordance with the user's actions detected by a detector provided on the manual tool, and performs a process to calculate a feature quantity related to the user's actions based on the acquired state quantity. [Effects of the Invention]

[0009] According to this disclosure, objective indicators can be obtained to perform tasks accurately in a short amount of time. [Brief explanation of the drawing]

[0010] [Figure 1] This is an overview diagram of a manual tooling system. [Figure 2] This is a schematic perspective view of a hand tool. [Figure 3] Figure 2 is a schematic cross-sectional view of a manual tool with line III-III as the cutting line. [Figure 4] This is a simplified perspective view of the tool body. [Figure 5] This is a block diagram showing an example of the configuration of an information processing device. [Figure 6] This is a block diagram showing an example configuration of an information processing terminal. [Figure 7] This figure shows an example of the content of information stored in the detection information database. [Figure 8] This is an example of a graph showing the relationship between the detected value of the third strain gauge and time. [Figure 9A] This is an example of a graph showing the relationship between the detected values ​​of the second and fourth strain gauges and time. [Figure 9B] This is an example of a graph showing the relationship between the detected values ​​of the second and fourth strain gauges and time. [Figure 10A]An example of a graph showing the relationship between the detected value of the first strain gauge and time. [Figure 10B] An example of a graph showing the relationship between the detected value of the first strain gauge and time. [Figure 11A] An explanatory diagram for explaining a method of deriving a feature amount. [Figure 11B] An explanatory diagram for explaining a method of deriving a feature amount. [Figure 11C] An explanatory diagram for explaining a method of deriving a feature amount. [Figure 11D] An explanatory diagram for explaining a method of deriving a feature amount. [Figure 12] A flowchart showing an example of a processing procedure executed by a manual tool system. [Figure 13] A diagram showing an example of the content of information stored in an evaluation DB. [Figure 14] A schematic diagram showing an example of an evaluation screen. [Figure 15] A flowchart showing an example of a processing procedure for generating evaluation criteria. [Figure 16] A flowchart showing an example of a processing procedure for deriving evaluation information.

Embodiments for Carrying Out the Invention

[0011] Specific examples of a program, an information processing method, and an information processing apparatus according to an embodiment of the present invention will be described below with reference to the drawings. Note that the present invention is not limited to these examples, but is defined by the claims, and is intended to include all modifications within the meaning and scope equivalent to the claims. Also, at least a part of each of the embodiments described below may be arbitrarily combined.

[0012] Note that the sequences shown in each of the embodiments described below are not limited, and within a non - contradictory range, each processing procedure may be executed with its order changed, or a plurality of processes may be executed in parallel. The processing entity of each process is not limited, and within a non - contradictory range, the processing of each device may be executed by another device.

[0013] (First Embodiment) <Overall configuration of the information processing system> Figure 1 is a schematic diagram of the manual tool system 100. The manual tool system 100 comprises an information processing device 1, an information processing terminal 2, and a manual tool 3.

[0014] Information processing device 1 is a device capable of various information processing and information transmission / reception, such as a server computer, personal computer, or quantum computer. Information processing device 1 and information processing terminal 2 are connected via a network N such as the Internet, enabling communication and data transmission / reception. Information processing device 1 acquires state quantities indicating the state of the manual tool 3 through information processing terminal 2, and determines indicators related to the user's actions based on the acquired state quantities.

[0015] The information processing terminal 2 is a device capable of various information processing and information transmission / reception, such as a personal computer, smartphone, or tablet terminal. The information processing terminal 2 and the manual tool 3 are connected in a communication manner. The manual tool system 100 may include multiple information processing terminals 2.

[0016] Manual tool 3 is a tool used by the user for manual work. Manual tool 3 is used for polishing a workpiece surface (not shown), for example, a metal surface. Manual tool 3 is equipped with multiple detectors (see Figure 4). The detectors detect state quantities (detected values) that indicate the state of the manual tool according to the user's actions. The state quantities detected by the detectors are transmitted to the information processing device 1 via the information processing terminal 2.

[0017] The detector provided in the manual tool system 100 is not limited to one installed on the manual tool 3, but may also include, for example, a camera that captures images of the user's condition when using the manual tool 3.

[0018] Furthermore, the information processing device 1, the information processing terminal 2, and the manual tool 3 are not limited to being configured separately; all of them, or any two of them, may constitute a single device. For example, the information processing device 1 and the information processing terminal 2 may constitute a single device, or the information processing device 1 and / or the information processing terminal 2 and the manual tool 3 may constitute a single device.

[0019] <Configuration of manual tool 3> Figure 2 is a schematic perspective view of the manual tool 3, and Figure 3 is a schematic cross-sectional view of the manual tool 3 with line III-III in Figure 2 as the cutting line. The output unit 39 is omitted from the description in Figures 2 and 3. In the following description, the up, down, front, back, left, and right directions shown in Figures 2 to 4 will be used as appropriate. Note that the up, down, front, back, left, and right directions are used only to facilitate understanding of the embodiment and can be changed as appropriate, and do not limit the present invention. The manual tool 3 comprises a tool body 30, a cover 31 that covers the tool body 30, and an elastic sheet 33 that covers the cover 31.

[0020] The tool body 30 is rectangular in shape and extends in the front-to-back direction. The cover 31 is rectangular in shape and extends in the front-to-back direction. The end faces of the cover 31 form the front and rear faces, and the remaining four faces form the top, bottom, right, and left faces. A first opening 31a is formed in the upper front of the cover 31, penetrating from front to back. A second opening 31b is formed across the entire bottom surface of the cover 31. The upper right and upper left corners of the cover 31 are chamfered to form inclined surfaces 30a. The tool body 30 is housed inside the cover 31 so that the longitudinal direction of the cover 31 coincides with the longitudinal direction of the tool body 30. The tool body 30 is fixed inside the cover 31. As shown in Figure 3, the bottom surface of the tool body 30 is exposed through the second opening 31b. Hereinafter, the bottom surface of the tool body 30 will be referred to as the pressing surface 30b.

[0021] Figure 4 is a schematic perspective view of the tool body 30. Two first strain gauges 34 are mounted on the front of the tool body 30, and two first strain gauges 34 are mounted on the rear. In other words, a total of four first strain gauges 34 are mounted. The four first strain gauges 34 are mounted facing the pressing surface 30b, in other words, next to the edge of the pressing surface 30b, based on an orthogonal arrangement method.

[0022] The tool body 30 has a right side and a left side. Two second strain gauges 35, two third strain gauges 36, and two fourth strain gauges 37 are mounted on the right side. Two second strain gauges 35, two third strain gauges 36, and two fourth strain gauges 37 are also mounted on the left side.

[0023] The second strain gauges 35 are positioned at the rear ends of the left and right sides of the tool body 30, with two second strain gauges 35 mounted on the right side and two second strain gauges 35 mounted on the left side facing each other. The fourth strain gauges 37 are positioned at the front ends of the left and right sides of the tool body 30. Two fourth strain gauges 37 mounted on the right side and two fourth strain gauges 37 mounted on the left side face each other. The front-to-back positions of the second strain gauges 35 and the fourth strain gauges 37 may be reversed.

[0024] On the right side of the tool body 30, the two third strain gauges 36 are positioned in the center between the second strain gauge 35 and the fourth strain gauge 37. On the left side of the tool body 30, the two third strain gauges 36 are positioned in the center between the second strain gauge 35 and the fourth strain gauge 37. The two third strain gauges 36 mounted on the right side and the two third strain gauges 36 mounted on the left side face each other.

[0025] Similar to the first strain gauge 34, the four second strain gauges 35, the four third strain gauges 36, and the four fourth strain gauges 37 are each mounted facing the pressing surface 30b, in other words, next to the edge of the pressing surface 30b, based on an orthogonal arrangement method. The first strain gauges 34 to the fourth strain gauges 37 are examples of detectors. The elastic sheet 33 is made of, for example, rubber. The elastic sheet 33 covers the right, left, top, and rear surfaces of the cover 31.

[0026] When the workpiece surface is facing upwards, the user wraps an abrasive sheet 40 containing fine particles (abrasive) around the bottom, right, and left sides of the manual tool 3, grips the manual tool 3 and the abrasive sheet 40 from above, presses the abrasive sheet 40 against the workpiece surface, and moves the manual tool 3 in the back-and-forth direction to polish the workpiece surface. The abrasive sheet 40 is replaceable. The user moves the manual tool 3 back and forth. The user repeats the back-and-forth movement of the manual tool 3. The distance of the repeated back-and-forth movement is approximately constant, and the speed is also approximately constant. The first strain gauge 34 detects the amount of strain in the longitudinal direction of the tool body 30, i.e., in the front-and-back direction. The amount of strain in the front-and-back direction corresponds to the force acting on the manual tool 3 in the front-and-back direction. The second strain gauge 35, the third strain gauge 36, and the fourth strain gauge 37 detect the amount of strain in the direction perpendicular to the pressing surface 30b of the tool body 30, i.e., in the up-and-down direction.

[0027] Wiring 38 is connected to each of the first strain gauges 34 to the fourth strain gauge 37. The wiring 38 is pulled out from the first opening 31a and connected to the output unit 39 (see Figure 1). The output unit 39 is connected to the information processing terminal 2 by wire or wireless connection and outputs the detected values ​​(strain amounts) of the first strain gauges 34 to the fourth strain gauge 37 to the information processing terminal 2.

[0028] The first strain gauges 34 to the fourth strain gauges 37 are attached to the portion facing the pressing surface 30b. The pressing surface 30b is susceptible to force from the workpiece surface, and the portion facing the pressing surface 30b is prone to displacement. The amount of strain corresponds to the force acting on the tool body 30. In other words, by detecting the amount of strain in the portion facing the pressing surface 30b, the first strain gauges 34 to the fourth strain gauges 37 can accurately detect the force acting on the tool body 30.

[0029] The second strain gauge 35 to the fourth strain gauge 37 detect the amount of strain in the vertical direction, that is, in the direction perpendicular to the pressing surface 30b. The amount of strain in the direction perpendicular to the pressing surface 30b corresponds to the pressing force acting from the pressing surface 30b on the workpiece surface. Therefore, the distribution of the pressing force can be determined based on the second strain gauge 35 to the fourth strain gauge 37.

[0030] The first strain gauge 34 detects the amount of strain in the front-rear direction, i.e., in the direction of movement of the manual tool 3. The amount of strain in the direction of movement of the manual tool 3 corresponds to the force required to move the manual tool 3. Therefore, the force required to move the manual tool 3 can be determined based on the first strain gauge 34. The force required to move the manual tool 3 corresponds to the polishing force acting on the workpiece surface.

[0031] <Configuration of Information Processing Device 1> Figure 5 is a block diagram showing an example configuration of the information processing device 1. The information processing device 1 comprises a control unit 11, a storage unit 12, and a communication unit 13. The information processing device 1 may be configured using multiple computers for distributed processing, or it may be implemented using multiple virtual machines located on a single server, or it may be implemented using a cloud server.

[0032] The control unit 11 includes a processor using one or more CPUs (Central Processing Units), GPUs (Graphics Processing Units), etc. The control unit 11 uses built-in memory such as ROM (Read Only Memory) or RAM (Random Access Memory), a clock, counters, etc., to control each component and execute processing.

[0033] The storage unit 12 includes, for example, a non-volatile memory such as a hard disk, flash memory, or SSD (Solid State Drive). The storage unit 12 may also be an external storage device connected to the information processing device 1. The storage unit 12 stores programs and data that the control unit 11 references. The programs stored in the storage unit 12 include a program 1P that causes the computer to execute processing related to the generation of indicators based on state variables.

[0034] The program (program product) stored in the storage unit 12 may be recorded on a recording medium in a computer-readable manner. The storage unit 12 stores the program read from the recording medium 1A by the reading device. The recording medium 1A is a magnetic disk, optical disk, semiconductor memory, etc. Alternatively, the program may be downloaded from an external server connected to a communication network and stored in the storage unit 12. The program 1P may be a single computer program or composed of multiple computer programs, and may be executed on a single computer or on multiple computers interconnected by a communication network.

[0035] The storage unit 12 also stores a detection information DB (Data Base) 121. The detection information DB 121 is a database that stores detection information, including state quantities that indicate the state of the manual tool 3. The storage unit 12 may also store an evaluation DB 122. The evaluation DB 122 will be described in detail in other embodiments.

[0036] The communication unit 13 includes a communication device for communicating with external devices via the network N. The control unit 11 sends and receives data to and from the information processing terminal 2 through the communication unit 13.

[0037] The configuration of the information processing device 1 is not limited to the example described above, and may include, for example, an operation unit for receiving user input, a display unit for displaying various types of information, and so on.

[0038] <Configuration of Information Processing Terminal 2> Figure 6 is a block diagram showing an example configuration of the information processing terminal 2. The information processing terminal 2 comprises a control unit 21, a storage unit 22, a communication unit 23, a display unit 24, an operation unit 25, and an input unit 26.

[0039] The control unit 21 includes one or more processors, such as CPUs and GPUs. The control unit 21 uses built-in memory such as ROM or RAM, a clock, counters, etc., to control each component and execute processing.

[0040] The storage unit 22 includes non-volatile memory such as a hard disk, flash memory, or SSD. The storage unit 22 stores programs and data referenced by the control unit 21. The programs stored in the storage unit 22 include a program 2P that causes a computer to execute processing related to the acquisition of indicators based on state variables. The programs (program products) stored in the storage unit 22 may also be recorded on a recording medium in a manner that is computer-readable. The storage unit 22 stores programs read from the recording medium 2A by a reading device. Alternatively, programs may be downloaded from an external server connected to a communication network and stored in the storage unit 22.

[0041] The communication unit 23 is equipped with a communication device for communicating with external devices via the network N. The control unit 21 sends and receives data to and from the information processing terminal through the communication unit 23.

[0042] The display unit 24 includes a display device such as a liquid crystal display or an organic electroluminescent (EL) display. The display unit 24 displays various types of information according to instructions from the control unit 21.

[0043] The operation unit 25 is equipped with an interface for receiving user input. The operation unit 25 includes, for example, a keyboard, a touch panel device with a built-in display, a speaker, and a microphone. The operation unit 25 receives user input and sends control signals to the control unit 21 according to the content of the operation.

[0044] The input unit 26 is equipped with an input interface for connecting the manual tool 3. The control unit 21 receives state values ​​output from the output unit 39 of the manual tool 3 through the input unit 26. The connection between the input unit 26 and the manual tool 3 may be wired or wireless. The input unit 26 may be equipped with a communication device that enables communication via short-range wireless communication such as Bluetooth®, WiFi®, or Low Energy, and may receive detected values ​​transmitted from the manual tool 3 via short-range wireless communication.

[0045] <Detection Information DB> Figure 7 shows an example of the contents of the information stored in the detection information DB121. The detection information DB121 includes a state quantity table 121a and a feature quantity table 121b.

[0046] The state quantity table 121a stores records that link information such as the detection date on which the detected value was detected in the manual tool 3, the user ID which is the identification information of the user of the manual tool 3, the detection time, and the detected value, using a detection information ID to identify the detection information as the key. Multiple types of detected values ​​are included.

[0047] In the example shown in Figure 7, the detected values ​​include the strain amounts for CH1 to CH4. The strain amount for CH1 is the strain amount detected by the first strain gauge 34 and corresponds to the polishing force. The strain amount for CH2 is the strain amount detected by the second strain gauge 35 and corresponds to the pressing force on the far side of the hand tool 3. The strain amount for CH3 is the strain amount detected by the third strain gauge 36 and corresponds to the pressing force in the middle of the hand tool 3. The strain amount for CH4 is the strain amount detected by the fourth strain gauge 37 and corresponds to the pressing force on the near side of the hand tool 3. The detection time for each detected value is synchronized.

[0048] Hereinafter, the strain amount of CH1 will also be referred to as the first state variable, the strain amount of CH2 as the second state variable, the strain amount of CH3 as the third state variable, and the strain amount of CH4 as the fourth state variable. In this embodiment, the first to fourth state variables are data representing waveforms. The detection information DB121 may store graphs showing the waveforms of the first to fourth state variables.

[0049] Note that the amount of strain is merely one example of a state variable indicating the state of the tool body 30. Other state variables that may be detected include vibration acting on the tool body 30, acceleration of the tool body 30, pressure acting on the abrasive sheet 40 (auxiliary tool) attached to the tool body 30, or the position of the tool body 30.

[0050] The feature table 121b stores records that link multiple features, user type, and evaluation information, for example, using a detection information ID as the key to identify detection information. The state table 121a and the feature table 121b are linked by the detection information ID.

[0051] Feature quantities are data that describe the characteristics of the user's actions when using the manual tool 3. As will be explained in more detail later, feature quantities are obtained by analyzing various state quantities. Depending on the work content, multiple feature quantities are defined to describe the characteristics of the user's actions. The feature quantity table 121b stores the values ​​of each feature quantity.

[0052] The characteristic features of this embodiment include, as an example, the smoothness of polishing, the speed of polishing, the uniformity of the pressing force, the pressing force at the back, middle, front, and overall of the hand tool, and the balance of the pressing force.

[0053] The user type includes classification information based on the user's proficiency level in using manual tools 3. For example, the user type is classified into "unskilled users," indicating that the user is inexperienced, and "skilled users," indicating that the user is skilled.

[0054] The evaluation information includes information regarding the evaluation of the user's actions. For example, the evaluation information includes an evaluation score. The user type and evaluation information will be described in detail in other embodiments.

[0055] <State variables> Figure 8 is an example of a graph showing the relationship between the detected value of the third strain gauge 36 and time. As shown in Figure 8, the amount of strain of the third strain gauge 36, i.e., the third state variable, forms a periodic waveform W3, with periodic peaks (maximum values) appearing. The time T between one peak and the next peak corresponds to the time it takes for the user to move the manual tool 3 back and forth once. Based on the periodic waveform W3 related to the amount of strain of the third strain gauge 36, the time T for one back and forth movement of the manual tool 3 can be determined. The waveform W3 related to the amount of strain of the third strain gauge 36 has a more stable shape, makes it easier to grasp the peaks, and allows for more accurate determination of the time T for one back and forth movement than the waveforms related to the amounts of strain of the first, second, and fourth strain gauges 37. Note that the waveform shown in Figure 8 is just one example, and it is natural that waveforms with different shapes from those shown in Figure 8 may appear.

[0056] Figures 9A and 9B are examples of graphs showing the relationship between the detected values ​​of the second strain gauge 35 and the fourth strain gauge 37 and time. Figures 9A and 9B show graphs for when different users use the manual tool 3, respectively. As shown in Figures 9A and 9B, the strain amounts of the second strain gauge 35 and the fourth strain gauge 37 form periodic waveforms W2 and W4. The period of waveforms W2 and W4 is the round-trip time T of the manual tool 3. As shown in Figures 9A and 9B, different waveforms often appear depending on the user. In other words, waveforms that reflect the user's characteristics tend to appear.

[0057] Figures 10A and 10B are examples of graphs showing the relationship between the detected value of the first strain gauge 34 and time. Figures 10A and 10B show graphs for when different users use the manual tool 3, respectively. The amount of strain in the first strain gauge 34 forms a periodic waveform W1, which forms, for example, a rectangular pulse wave as shown in Figure 10A or a triangular pulse wave as shown in Figure 10B. As shown in Figures 10A and 10B, different waveforms often appear depending on the user. In other words, waveforms that reflect the user's characteristics tend to appear.

[0058] <Method for deriving features> The information processing device 1 obtains multiple feature quantities related to the user's actions by analyzing the first to fourth state quantities.

[0059] In operations using the manual tool 3, predetermined unit movements are often repeated. For example, during polishing, the manual tool 3 is repeatedly moved back and forth in the forward and backward direction, i.e., the pushing and pulling motion of the manual tool 3 is repeated. In this embodiment, based on the state quantities for a series of movements performed in one operation, motion pattern data for one unit movement is generated, and feature quantities are obtained based on the generated motion pattern data.

[0060] Figures 11A to 11D are explanatory diagrams illustrating the method of deriving features. The method of deriving features will be explained in detail using Figures 11A to 11D.

[0061] The information processing device 1 performs waveform processing on each of the multiple state variables based on the information stored in the state variable table 121a. Specifically, the information processing device 1 generates a waveform data graph for the time-series data of the detected values ​​of each of the first strain gauges 34 to the fourth strain gauges 37, with the vertical axis representing strain and the horizontal axis representing time. The waveform data is data that shows the state variables of a series of polishing operations that include multiple unit operations. The graph shown in Figure 11A is an example of waveform data for the first to fourth state variables.

[0062] The information processing device 1 removes unwanted noise from the waveform data. An example of noise to be removed is detected values ​​related to temporary interruptions that occur during a series of operations. In manual work, for example, work may be temporarily interrupted to perform maintenance on the manual tool 3.

[0063] The graph in Figure 11B is a subset of the graph in Figure 11A, showing only one type of state variable waveform. As shown in Figure 11B, the graph over time during repeated unit operations shows a periodic waveform with repeated increases and decreases in strain. As indicated by the dashed line in the graph of Figure 11B, the series of data includes strain values ​​that behave differently from the periodic waveform described above. These strain values ​​with different behaviors correspond to detected values ​​related to interruption operations.

[0064] Thus, the waveform during interrupted operation differs from the waveform during unit operation. By removing the detected values ​​during interruption, i.e., the detected values ​​during times that do not correspond to unit operation, as noise from the waveform data, the characteristics of the actual operation can be suitably extracted.

[0065] While there are no limitations on the noise reduction method, one example is to divide the time-series data into predetermined operating cycles and then delete unnecessary operating cycles. The information processing device 1 extracts multiple local maxima from the waveform data related to one of the first to fourth state variables (hereinafter also referred to as the target state variable). In the graph shown in Figure 11B, the black circles correspond to the local maxima.

[0066] The information processing device 1 divides the time-series data into periods corresponding to one period, with each period defined as the time from one local maximum to the next consecutive local maximum. Each waveform data after division corresponds to the operation pattern data related to one unit operation.

[0067] The information processing device 1 identifies the maximum point among the extracted maximum points whose distortion amount is below a threshold, and removes the operating period containing the identified maximum point from the waveform data. The conditions for identifying the maximum points to be removed can be set appropriately depending on the type of state variable.

[0068] The information processing device 1 also applies the results of time-series data splitting and noise reduction performed using the target state quantity to state quantities other than the target state quantity, and similarly performs time-series data splitting and noise reduction. Preferably, the first to fourth state quantities are acquired in advance with synchronized detection times, but if the detection times are not synchronized, the above processing may be performed after the data is interpolated using an appropriate interpolation method.

[0069] The information processing device 1 preferably uses a third state variable as the target state variable. As described above, the third state variable has a more stable shape compared to other state variables, and can accurately identify the local maximum. The information processing device 1 may also extract the local maximum by considering multiple state variables.

[0070] The information processing device 1 may identify the start and end times of each unit operation included in a series of operations based on, for example, image data from a camera as a state variable. The information processing device 1 generates operation pattern data for each unit operation by dividing the time series data at detection points corresponding to the identified start and end times.

[0071] The graph shown in Figure 11C is an example of waveform data for the first to fourth states after noise reduction. By dividing the graph shown in Figure 11C by operating cycle, operating pattern data including waveform data for the first to fourth states for one unit operation can be obtained, as shown in Figure 11D.

[0072] The information processing device 1 calculates multiple types of feature quantities that quantify the characteristics of the user's actions based on each detected value included in the action pattern data.

[0073] Each feature can be obtained, for example, by the following calculation methods. Polishing smoothness is obtained by calculating the kurtosis of the waveform of the first state variable. Polishing speed is obtained by calculating the time required for one unit operation. Uniformity of pressing force is obtained by calculating the correlation coefficient of the detected values ​​for multiple points on the pressing surface. In this embodiment, the correlation coefficient of the second and fourth state variables is used as the uniformity of pressing force.

[0074] The pressing force towards the back is obtained by calculating the average value of the second state variable. The pressing force towards the middle is obtained by calculating the average value of the third state variable. The pressing force towards the front is obtained by calculating the average value of the fourth state variable. The pressing force for the whole is obtained by calculating the average of the sum of the second to fourth state variables. The balance of the pressing forces is obtained by subtracting the pressing force towards the front from the pressing force towards the back.

[0075] The feature quantities may include energy efficiency. Energy efficiency is the ratio of the pressing force applied to the manual tool to the energy used for the polishing action, and can be calculated, for example, using the sum of the second, third, and fourth state quantities, the polishing speed, and the number of cycles.

[0076] After calculating features for each motion pattern data, the average of the sum of features for all motion pattern data included in the sequence of motions is calculated to obtain the final features for the sequence of motions. The types and calculation methods of the above features are illustrative and not limited to those methods.

[0077] <Processing Procedure> Figure 12 is a flowchart showing an example of a processing procedure performed by the manual tool system 100. The processing in each of the following flowcharts may be executed by the control unit 11 according to a program 1P stored in the storage unit 12 of the information processing device 1, and by the control unit 21 according to a program 2P stored in the storage unit 22 of the information processing terminal 2, or it may be implemented by dedicated hardware circuits (e.g., FPGA or ASIC) provided in the control unit 11 and the control unit 21 respectively, or by a combination thereof.

[0078] The control unit 21 of the information processing terminal 2 obtains the user ID of the user using the manual tool 3 by accepting a login operation from the user, for example, through the operation unit 25 (step S11).

[0079] The control unit 21 acquires multiple state quantities during a single polishing operation through the first strain gauge 34 to the fourth strain gauge 37 (step S12). Specifically, the control unit 21 receives the detected values ​​output from the first strain gauge 34 to the fourth strain gauge 37 and the detection time of said detected values ​​in chronological order, thereby acquiring the chronological data of the received detected data as state quantities.

[0080] The control unit 21 associates the acquired user ID with the state quantity and transmits it to the information processing device 1 (step S13).

[0081] The control unit 11 of the information processing device 1 receives the user ID and status values ​​(step S14).

[0082] The control unit 11 performs waveform processing on each acquired state variable (step S15) and generates a graph of waveform data for each of the first to fourth state variables.

[0083] The control unit 11 divides the waveform data for a series of operations into periods of unit operation (step S16). The control unit 11 extracts all maximum points in the waveform data of the target state variable and divides the waveform data for each detection time point corresponding to each extracted maximum point. The control unit 11 similarly divides the waveform data of other state variables into periods of unit operation corresponding to the periods of unit operation identified for the target state variable.

[0084] The control unit 11 removes noise corresponding to the detected value at a time when the unit operation is not being performed from the waveform data divided into periods for each unit operation (step S17). The control unit 11 then performs noise removal on the waveform data of other state variables in the same manner, corresponding to the time of noise occurrence identified for the target state variable.

[0085] The control unit 11 calculates several types of feature quantities related to the user's actions based on the operation pattern data of each unit operation after division (step S18). The control unit 11 stores the obtained state quantities and feature quantities in the detection information DB 121 (step S19) and terminates the series of processes.

[0086] The processing entities in the flowchart described above are not limited. Some or all of the processing performed by the information processing device 1 may be performed by the information processing terminal 2.

[0087] The manual tool system 100 performs the above-described process each time a user performs an operation. As a result, state quantities and feature quantities related to various users are accumulated in the detection information DB 121.

[0088] In the process described above, the control unit 11 may acquire the detected value and the detection time via the information processing terminal 2 each time a detected value is detected by the first strain gauge 34 to the fourth strain gauge 37. The detection time may be acquired by the timing function of the information processing terminal 2 or the information processing device 1. Furthermore, the control unit 11 is not limited to acquiring the detected value via the information processing terminal 2, but may also be connected to the first strain gauge 34 to the fourth strain gauge 37 in a communicative manner and receive the detected value directly from the first strain gauge 34 to the fourth strain gauge 37.

[0089] According to this embodiment, a feature quantity that quantifies the user's actions can be obtained based on the amount of strain generated in the tool body 30. This feature quantity can be used as an objective indicator for the user to perform tasks accurately in a short amount of time. By detecting various amounts of strain generated in the tool body 30 using multiple strain gauges provided on the manual tool 3, multiple feature quantities that suitably represent the user's actions can be obtained. The feature quantities allow for a quantitative understanding of each user's work.

[0090] In the above description, state quantities are detected for a manual tool 3 used for polishing metal surfaces. However, state quantities may also be detected for manual tools 3 used for purposes other than polishing metal surfaces, such as forging, welding, cutting, sheet metal processing, or painting. For example, state quantities may be detected for hammers used for forging, welding rod holders, cutting tools for cutting, bending tools for sheet metal, or spray guns. In that case, the manual tool system 100 will determine feature quantities necessary for performing forging, welding, cutting, sheet metal processing, or painting accurately in a short amount of time. The shape of the manual tool 3 is not limited to a rectangular parallelepiped, but may also be a frustoconical shape, a sphere, or other shapes.

[0091] (Second Embodiment) In the second embodiment, the manual tool system 100 is applied as a user training system. The following mainly describes the differences from the first embodiment, and components common to both embodiments are denoted by the same reference numerals and their detailed descriptions are omitted.

[0092] In the second embodiment, the information processing device 1 uses the evaluation DB 122 stored in the storage unit 12 to derive evaluation information regarding the actions of inexperienced users. The evaluation information is used to improve the work skills of inexperienced users.

[0093] <Rating Database> Figure 13 shows an example of the contents of the information stored in the evaluation DB 122. The evaluation DB 122 is a database that stores information used to generate evaluation information for the user's actions. The evaluation DB 122 includes an evaluation criteria table 122a and an advice table 122b.

[0094] The evaluation criteria table 122a contains information used to calculate evaluation scores for user actions. The evaluation criteria table 122a stores records that link information such as user patterns and standard features. A user pattern is a pattern associated with a user and is classified into multiple types according to the characteristics of the user's actions. For example, a user pattern can be classified into either a first-class skilled user pattern or a second-class skilled user pattern.

[0095] The Criteria Feature column stores the values ​​of the criteria features for each type of feature. A criteria feature is a feature that serves as the baseline value for evaluation. The features included in the criteria feature column are the same as those in Feature Table 121b.

[0096] The advice table 122b contains information for generating advice based on the evaluation results. For example, the advice table 122b stores records that associate information such as the type of feature, evaluation score, feature, and advice information with an advice ID as the key to identify the advice.

[0097] The evaluation score is the evaluation score corresponding to the advice information and represents the evaluation score for the user. The features are the features corresponding to the advice information. The evaluation score and features may include thresholds such as upper or lower limits that define the range of the evaluation score and the range of the features. The advice information includes text data that provides advice to the user. The advice information varies depending on the type of feature and the evaluation score or feature.

[0098] The information processing device 1 collects detection information of skilled users skilled in polishing work by the process described in the first embodiment and stores it in the detection information DB 121. The information processing device 1 generates evaluation criteria using the stored detection information of skilled users and stores the generated evaluation criteria in the evaluation DB 122.

[0099] <Method for deriving evaluation information> First, the information processing device 1 generates a reference feature quantity that will serve as the evaluation criterion. The reference feature quantity can be, for example, a feature quantity based on a state quantity related to the actions of a skilled user. The reference feature quantity may also be a target value of the feature quantity estimated based on the reference feature quantity of the skilled user.

[0100] It is preferable that the characteristics of a skilled user are set by comprehensively integrating the state quantities related to multiple work sessions. The information processing device 1 calculates the average value of each characteristic obtained from the state quantities of each session, and uses the calculated average value as the reference characteristic. The reference characteristic is set for each type of characteristic. The obtained reference characteristics are stored in the evaluation criteria table 122a.

[0101] The information processing device 1 derives evaluation information for unskilled users using the above-mentioned standard features. The evaluation information includes, for example, an evaluation score for each feature and advice corresponding to the evaluation results.

[0102] The evaluation score is calculated by comparing a standard feature with a feature based on the state of the unskilled user. For example, the evaluation score is calculated by taking a perfect score when the difference between the unskilled user's feature and the standard feature is zero or less than the first threshold, and subtracting a score corresponding to the difference between the two from the perfect score. The information processing device 1 calculates the evaluation score for each type of feature.

[0103] The information processing device 1 may calculate a second reference value in addition to the mean value as a reference feature, and determine the points to be deducted from the maximum score using a function defined with the mean value and the second reference value. The second reference value can be, for example, the larger or smaller of the following two values: the value obtained by subtracting the mean value from the maximum value of the feature in the state quantity for multiple instances of a skilled user, and the value obtained by subtracting the minimum value from the mean value. Whether to use the larger or smaller numerical value as the second reference value can be appropriately selected depending on the type of feature.

[0104] The information processing device 1 further derives advice information using the advice table 122b. As described above, the advice table 122b stores advice information in association with evaluation scores or feature values ​​for each type of feature. The information processing device 1 identifies advice for each type of feature that corresponds to the evaluation score or feature value of an unskilled user. The advice may include, for example, advice corresponding to the evaluation score and advice corresponding to the feature value.

[0105] The aforementioned standard features are preferably set based on the features of multiple skilled users. When using the features of multiple skilled users, one type of standard feature may be obtained by comprehensively evaluating the features of all skilled users, or skilled users may be classified into multiple user patterns, and a standard feature may be obtained for each user pattern.

[0106] User patterns can be classified according to predetermined features. For example, if the surface uniformity value of the pressing force is above a predetermined value, the user is classified into the first skilled user pattern. If the surface uniformity value of the pressing force is below the predetermined value, the user is classified into the second skilled user pattern. The threshold for classification can be set based on the distribution of surface uniformity values ​​of skilled users belonging to each skilled user pattern.

[0107] User patterns may be classified by combining multiple features, such as the pressure applied to the back, middle, and front sides. User patterns may also be classified by taking into account data other than features, such as the user's physique and gender.

[0108] When deriving evaluation information for unskilled users, the information processing device 1 identifies the user pattern to which the unskilled user belongs based on the characteristic quantities of the unskilled user being evaluated. The information processing device 1 evaluates the actions of the unskilled user using evaluation criteria corresponding to the identified user pattern.

[0109] In tasks using manual tools 3, the characteristics of the movements differ depending on the skilled user, so the values ​​of certain feature quantities may change significantly depending on the skilled user. By classifying user patterns and using skilled users with similar movement characteristics to unskilled users as evaluation criteria, it becomes possible to perform evaluations that are more in line with the content of the movements.

[0110] <Evaluation screen> Figure 14 is a schematic diagram showing an example of the evaluation screen 240. Based on the screen information provided by the information processing device 1, the information processing terminal 2 displays the evaluation screen 240 showing evaluation information on the display unit 44, as shown in Figure 14.

[0111] The evaluation screen 240 includes an evaluation score display unit 241, a chart display unit 242, a feature graph display unit 243, and an advice display unit 244.

[0112] The evaluation score display unit 241 displays the evaluation score for each evaluation item and the total score for each evaluation item for multiple evaluation items. The content of each evaluation item corresponds to the content of each feature. The evaluation score display unit 241 also displays the user pattern used to evaluate the user. When the information processing device 1 derives evaluation scores for each feature of an unskilled user, it displays the derived evaluation scores and the total score on the evaluation score display unit 241.

[0113] The chart display unit 242 displays a radar chart 242a showing the evaluation score for each evaluation item. The information processing device 1 generates a radar chart 242a showing each evaluation item and its evaluation score based on the derived evaluation scores, and displays it on the chart display unit 242. By displaying the evaluation scores using the radar chart 242a, the evaluation scores for multiple evaluation items can be easily grasped visually. Note that the chart showing the evaluation scores is not limited to a radar chart; any chart or graph that clearly shows each evaluation item and its evaluation score is acceptable.

[0114] The feature graph display unit 243 shows a graph 243a with multiple features on each axis. In the example shown in Figure 14, graph 243a is a two-dimensional graph with the uniformity of pressing force on the vertical axis and the smoothness of polishing on the horizontal axis, and the features of an unskilled user are plotted on graph 243a. In Figure 14, the distribution area of ​​the features of an unskilled user is color-coded to make the distribution state of the features recognizable.

[0115] Furthermore, the baseline features of the user pattern to which unskilled users belong are superimposed on graph 243a. Similar to the features of unskilled users, the distribution state of the baseline features is shown by coloring the distribution region of the baseline features.

[0116] The uniformity of the pressing force is such that zero is the most non-uniform value, and as the value increases in the positive or negative direction, the uniformity improves. In the case of skilled users, there is often a strong positive or negative correlation between the second and fourth states, resulting in a uniform pressing force. On the other hand, in the case of unskilled users, the correlation between the second and fourth states is weak, resulting in a non-uniform pressing force.

[0117] The smoothness of polishing is indicated by the uniformity of the polishing force and the smoothness of the polishing process; a smaller value indicates a more uniform polishing force. In the case of skilled users, the kurtosis of the waveform of the first state variable is small, and the polishing force is often uniform. On the other hand, in the case of unskilled users, the kurtosis of the waveform of the first state variable is large, and the polishing force is often uneven.

[0118] The information processing device 1 extracts feature quantities for unskilled users corresponding to each axis of graph 243a, and applies display processing such as coloring and bordering to the distribution area of ​​the extracted feature quantities for unskilled users on graph 243a. The information processing device 1 also extracts reference feature quantities corresponding to the user pattern to which the unskilled users belong, and similarly applies display processing such as coloring and bordering to the distribution area of ​​the extracted reference feature quantities. In this case, it is preferable to display the feature quantities for unskilled users and the reference feature quantities in different display modes, for example, by changing the color or density depending on the feature quantities for unskilled users and reference feature quantities. In Figure 14, different hatching is applied to the distribution area of ​​the feature quantities for unskilled users and the distribution area of ​​the reference feature quantities.

[0119] Furthermore, the information processing device 1 may display not only the reference feature quantities corresponding to the user pattern to which the unskilled user belongs, but also reference feature quantities corresponding to other user patterns on graph 243a. Graph 243a may also be a graph for three or more types of feature quantities. The types of feature quantities displayed in graph 243a may be set according to the type of manual tool 3 and the type of detector.

[0120] By displaying the features using Graph 243a, the distribution of features for unskilled users can be easily understood visually. Furthermore, the display of baseline features on Graph 243a allows for a clear understanding of the relative positions of unskilled and skilled users.

[0121] On graph 243a, objects indicating a path to improve the evaluation score may also be displayed, as shown in Figure 14. The information processing device 1 generates an arrow, for example, starting from the average value of the features of an unskilled user and ending at the average value of the reference features, and superimposes it on graph 243a. The arrow makes it easy to understand the target value of the features.

[0122] The advice display unit 244 displays advice corresponding to the evaluation results. The information processing device 1 generates identified advice information using the advice table 122b and displays the generated advice information on the advice display unit 244.

[0123] <Processing Procedure> Figure 15 is a flowchart showing an example of the process for generating evaluation criteria.

[0124] The control unit 11 of the information processing device 1 obtains the characteristic quantities of skilled users for multiple tasks by referring to the detection information DB 121 and extracting characteristic quantities corresponding to skilled users (step S21). The control unit 11 identifies the user pattern of a skilled user based on the user pattern classification conditions of user patterns that are stored in advance, and classifies the obtained characteristic quantities of skilled users according to the user pattern (step S22).

[0125] The control unit 11 generates a reference feature that serves as the evaluation criterion by, for example, calculating the average value of the multiple feature quantities obtained (step S23). A reference feature is generated for each type of feature. In step S23, the control unit 11 generates a reference feature for each user pattern according to the classification result for each user pattern, using the feature quantities classified into the same user pattern.

[0126] The control unit 11 stores the generated evaluation criteria in the storage unit 12 (step S24), and terminates the series of processes.

[0127] Figure 16 is a flowchart showing an example of the procedure for deriving evaluation information. The control unit 21 of the information processing terminal 2 obtains the user ID of the unskilled user (step S31), obtains the state quantity (step S32), associates the user ID with the state quantity, and transmits it to the information processing device 1 (step S33). The processing in steps S31 to S33 is the same as steps S11 to S13 in Figure 12.

[0128] The control unit 11 of the information processing device 1 receives the user ID and status values ​​(step S34).

[0129] The control unit 11 performs waveform processing on the state variables (step S35), divides the waveform data into periods of unit operation (step S36), and removes noise from the waveform data corresponding to the detected values ​​at times when the unit operation is not being performed (step S37). Furthermore, the control unit 11 calculates several types of feature quantities related to the actions of an unskilled user (step S38). The processing in steps S35 to S38 is the same as steps S15 to S18 in Figure 12.

[0130] The control unit 11 identifies the user pattern of an unskilled user based on the user pattern classification conditions stored in advance (step S39).

[0131] The control unit 11 refers to the evaluation DB 122 and derives evaluation information based on the standard feature quantities that serve as evaluation criteria corresponding to the identified user pattern and the feature quantities of the unskilled user (step S40). Based on the evaluation criterion table 122a, the control unit 11 calculates an evaluation score corresponding to the feature quantities of the unskilled user and identifies advice information corresponding to the evaluation score or feature value of the unskilled user based on the advice table 122b.

[0132] The control unit 11 stores the user ID of the unskilled user, the detected value, evaluation information, etc., in the detection information DB 121 (step S41).

[0133] The control unit 11 generates an evaluation screen containing the derived evaluation information (step S42). The control unit 11 transmits the generated evaluation screen to the information processing terminal 2 used by the logged-in user (step S43).

[0134] The control unit 21 of the information processing terminal 2 receives the evaluation screen (step S44). The control unit 21 displays the received evaluation screen on the display unit 24 (step S45) and terminates the series of processes.

[0135] According to this embodiment, the manual tool system 100 can be applied as an educational system for improving the skills of unskilled users. The evaluation results regarding work using the manual tool 3 can be shown quantitatively, and the target movements for unskilled users are quantified and shown, allowing them to efficiently acquire the skills of skilled users. The evaluation results are presented in charts and graphs, making them easy to understand visually.

[0136] By classifying user patterns, it becomes possible to set skilled users, whose movements are similar to those of unskilled users, as the target, thereby efficiently defining improvement paths for skill development.

[0137] The matters described in each embodiment can be combined with each other. Furthermore, the independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. In addition, the claims use a form in which claims referencing two or more other claims (multi-claim form), but are not limited to this. A form in which multi-claims referencing at least one multi-claim (multi-multi-claim) may also be used. [Explanation of Symbols]

[0138] 1. Information Processing Device 11 Control Unit 12 Storage section 13 Communications Department 121 Detection Information DB 122 Evaluation DB 1P Program 1A Recording medium 2. Information Processing Terminal 21 Control Unit 22 Memory section 23 Communications Department 24 Display section 25 Control section 26 Input section 2P Program 2A recording medium 3 hand tools 30 Tool body 30b Pressing surface 34. First strain gauge (detector) 35. Second strain gauge (detector) 36. Third strain gauge (detector) 37. Fourth strain gauge (detector) 39 Output section

Claims

1. A detector provided in a manual tool used for polishing metal surfaces, comprising a first detector that detects the amount of strain in the direction of movement of the manual tool, and a second detector that detects the amount of strain in a direction different from the direction of movement of the manual tool, wherein a plurality of state quantities, which are time-series data of detection data indicating the state of the manual tool in accordance with the user's actions detected by the detector, are acquired. The acquired state quantities are divided into time widths corresponding to the unit operation cycle, and noise corresponding to the time when the unit operation is not being performed is removed to generate operation pattern data for each unit operation. Based on the motion pattern data of each generated unit motion, feature quantities related to the user's motion are calculated, including two or more of the following: smoothness of polishing, speed of polishing, energy efficiency, uniformity of pressing force, and balance of pressing force. The calculated feature quantities are output in a multi-dimensional graph format with two or more of the feature quantities as axes. A program that causes a computer to perform a process.

2. Based on the feature quantities relating to the user's actions and the reference feature quantities indicating the basis for the feature quantities, evaluation information for the user's actions is output. The program according to claim 1.

3. The aforementioned standard feature quantity is calculated based on a state quantity that indicates the state of the manual tool in accordance with the actions of a user other than the aforementioned user. The program according to claim 2.

4. Based on the state quantities detected by the multiple detectors, multiple feature quantities relating to the user's actions are calculated. Based on the calculated multiple features, a chart is output showing the evaluation scores for multiple evaluation items. The program according to any one of claims 1 to 3.

5. The uniformity of force in the manual tool is calculated based on the correlation coefficients of multiple state variables. The program according to any one of claims 1 to 4.

6. The feature quantities of another user, different from the aforementioned user, are superimposed onto the graph showing the feature quantities of the aforementioned user. The program according to claim 1.

7. The state quantity includes a state quantity indicating the polishing force of the manual tool and a state quantity indicating the pressing force of the manual tool. The program according to any one of claims 1 to 6.

8. A detector provided in a manual tool used for polishing a metal surface, comprising a first detector that detects the amount of strain in the direction of movement of the manual tool, and a second detector that detects the amount of strain in a direction different from the direction of movement of the manual tool, wherein a plurality of state quantities are acquired, which are time-series data of detection data indicating the state of the manual tool in accordance with the user's actions detected by the detector, The acquired state quantities are divided into time widths corresponding to the unit operation cycle, and noise corresponding to the time when the unit operation is not being performed is removed to generate operation pattern data for each unit operation. Based on the motion pattern data of each generated unit motion, feature quantities related to the user's motion are calculated, including two or more of the following: smoothness of polishing, speed of polishing, energy efficiency, uniformity of pressing force, and balance of pressing force. The calculated feature quantities are output in a multi-dimensional graph format with two or more of the feature quantities as axes. An information processing method in which a computer performs the processing.

9. A detector provided in a manual tool used for polishing a metal surface, comprising a first detector that detects the amount of strain in the direction of movement of the manual tool, and a second detector that detects the amount of strain in a direction different from the direction of movement of the manual tool, wherein a plurality of state quantities are acquired, which are time-series data of detection data indicating the state of the manual tool in accordance with the user's actions detected by the detector, The acquired state quantities are divided into time widths corresponding to the unit operation cycle, and noise corresponding to the time when the unit operation is not being performed is removed to generate operation pattern data for each unit operation. Based on the motion pattern data of each generated unit motion, feature quantities related to the user's motion are calculated, including two or more of the following: smoothness of polishing, speed of polishing, energy efficiency, uniformity of pressing force, and balance of pressing force. The calculated feature quantities are output in a multi-dimensional graph format with two or more of the feature quantities as axes. It includes a control unit that performs processing. Information processing device.

Images