CN110826383A - Analysis system, analysis method, program, and storage medium - Google Patents
Analysis system, analysis method, program, and storage medium Download PDFInfo
- Publication number
- CN110826383A CN110826383A CN201910227735.0A CN201910227735A CN110826383A CN 110826383 A CN110826383 A CN 110826383A CN 201910227735 A CN201910227735 A CN 201910227735A CN 110826383 A CN110826383 A CN 110826383A
- Authority
- CN
- China
- Prior art keywords
- job
- time
- series data
- processing unit
- samples
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 97
- 238000003860 storage Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 124
- 230000008859 change Effects 0.000 claims abstract description 54
- 238000011156 evaluation Methods 0.000 claims description 41
- 238000000034 method Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 7
- 230000000306 recurrent effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 201000010099 disease Diseases 0.000 claims 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims 2
- 239000003054 catalyst Substances 0.000 claims 1
- 210000002569 neuron Anatomy 0.000 description 37
- 238000010586 diagram Methods 0.000 description 21
- 230000000694 effects Effects 0.000 description 13
- 230000004048 modification Effects 0.000 description 12
- 238000012986 modification Methods 0.000 description 12
- 238000001514 detection method Methods 0.000 description 10
- 238000012952 Resampling Methods 0.000 description 9
- 238000013500 data storage Methods 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 210000000988 bone and bone Anatomy 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 210000000707 wrist Anatomy 0.000 description 3
- 230000015654 memory Effects 0.000 description 2
- 210000000225 synapse Anatomy 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Provided are an analysis system, an analysis method, a program, and a storage medium, which can more automatically analyze a job and can shorten the time required for analysis. The analysis system of an embodiment includes an acquisition unit and a processing unit. The acquisition unit acquires time series data indicating an operation of the operator in the 1 st step including a plurality of operations. The processing unit detects a plurality of change points of the state in the time series data, and associates the time series data with each of the plurality of jobs using the plurality of change points.
Description
Technical Field
Embodiments of the present invention relate to an analysis system, an analysis method, a program, and a storage medium.
Background
Conventionally, in order to improve productivity in a manufacturing site, a method of recording information related to a job using a video shot or a stopwatch (stopwatch) and analyzing the information has been adopted. When a process including a plurality of operations is repeated, extraction of a cycle of the process, creation of a time chart as a detail thereof, distinction of operations among operators, and the like are performed in the analysis.
In order to shorten the time required for analysis, there are tools for supporting such analysis. However, even when this tool is used, marking and determination of information by a person are necessary. Further, the judgment varies depending on the skill and experience of the person who analyzes the analysis. Therefore, it is desired to develop a technique capable of more automatically analyzing and further shortening the time required for the analysis.
Documents of the prior art
Patent document
Patent document 1: japanese patent laid-open publication No. 2017-091249
Disclosure of Invention
Problems to be solved by the invention
An object of the present invention is to provide an analysis system, an analysis method, a program, and a storage medium that can analyze a job more automatically and shorten the time required for analysis.
Means for solving the problems
The analysis system of an embodiment includes an acquisition unit and a processing unit. The acquisition unit acquires time series data indicating an operation of the operator in the 1 st step including a plurality of operations. The processing unit detects a plurality of change points of the state in the time series data, and performs association between the time series data and each of the plurality of jobs using the plurality of change points.
Drawings
Fig. 1 is a block diagram showing the configuration of an analysis system according to embodiment 1.
Fig. 2 is a schematic diagram for explaining processing in the analysis system according to embodiment 1.
Fig. 3 is a schematic diagram for explaining processing in the analysis system according to embodiment 1.
Fig. 4 is a schematic diagram for explaining processing in the analysis system according to embodiment 1.
Fig. 5 is a schematic diagram for explaining processing in the analysis system according to embodiment 1.
Fig. 6 is a flowchart showing the processing in the analysis system according to embodiment 1.
Fig. 7 is a schematic diagram for explaining processing in the analysis system according to variation 1 of embodiment 1.
Fig. 8 is a flowchart showing a process in the analysis system according to variation 1 of embodiment 1.
Fig. 9 is a schematic diagram for explaining processing in the analysis system according to variation 2 of embodiment 1.
Fig. 10 is a flowchart showing a process in the analysis system according to variation 2 of embodiment 1.
Fig. 11 is a schematic diagram for explaining processing in the analysis system according to modification 3 of embodiment 1.
Fig. 12 is a flowchart showing a process in the analysis system according to variation 3 of embodiment 1.
Fig. 13 is a schematic diagram for explaining processing in the analysis system according to variation 4 of embodiment 1.
Fig. 14 is a flowchart showing a process in the analysis system according to variation 4 of embodiment 1.
Fig. 15 is a block diagram showing the configuration of the analysis system according to embodiment 2.
Fig. 16 is a schematic diagram showing a recurrent neural network.
Fig. 17 is a block diagram showing the LSTM structure.
Fig. 18 is a flowchart showing processing in the analysis system according to embodiment 2.
Fig. 19 is a graph showing data obtained in the example.
Fig. 20 is a graph showing data relating to the example.
Detailed Description
Embodiments of the present invention are described below with reference to the drawings.
In the present specification and the drawings, the same elements as those already described are denoted by the same reference numerals, and detailed description thereof is omitted as appropriate.
Fig. 1 is a block diagram showing the configuration of an analysis system according to embodiment 1.
Fig. 2 to 5 are schematic diagrams for explaining processing in the analysis system according to embodiment 1.
As shown in fig. 1, the analysis system 1 includes an acquisition unit 10, a processing unit 20, a storage unit 30, and a display unit 40.
The analysis system 1 is used to analyze the operation of an operator who is working in a certain process. Hereinafter, a case of analyzing the operation of the operator in the 1 st step including a plurality of operations will be described.
The acquisition unit 10 acquires time series data indicating the operation of the operator in the step 1.
The acquisition unit 10 includes, for example, an imaging device. The acquisition unit 10 photographs an operator who is working, and extracts skeleton information of the operator from the obtained image. The acquiring unit 10 acquires a change in position of a part of the skeleton (for example, the head) with the passage of time as time series data indicating the movement of the operator.
Alternatively, the acquisition unit 10 may extract the angle of the joint from the bone information. The acquisition unit 10 acquires a change in the angle of the joint (for example, the angle of the elbow) with the passage of time as time series data indicating the movement of the operator. The angle of the joint is less dependent on the physical constitution. Therefore, by using the angle change of the joint as time series data, the influence of different physique on the analysis can be reduced, and the accuracy of the analysis can be improved.
The extraction of the bone information, the detection of the change in the position of the bone, the indirect detection of the change in the angle, and the like may be performed by the processing unit 20 described later.
Alternatively, the acquisition unit 10 may include an accelerometer. The accelerometer is attached to a part of the body such as the wrist or the foot of the operator. The acquisition unit 10 acquires information such as acceleration, angular velocity, and orientation obtained when the operator performs the step 1 as time series data indicating the operation of the operator.
The acquisition unit 10 stores the acquired data in the storage unit 30. The storage unit 30 is a hard disk drive, a flash memory, a network hard disk, or the like.
Fig. 2 (a) shows an example of time series data acquired by the acquisition unit 10 and stored in the storage unit 30. Fig. 2 (a) is acceleration information obtained by an accelerometer attached to the wrist of the operator in step 1. The time-series data in fig. 2 (b) and (b) show the processing performed by the processing unit 20. In the time-series data included in fig. 2 to 5, the horizontal axis represents time Ti, and the vertical axis represents acceleration Ac.
The processing unit 20 (processing circuit) analyzes the time series data stored in the storage unit 30.
First, the processing unit 20 divides time series data into a plurality of states and extracts a change point of the state. The extraction of the change points of the state uses, for example, a hidden markov model (HDP-HMM), a k-means method, an x-means method, or spectral clustering for a hierarchical dirichlet process. Fig. 2 (b) shows the result of division performed by the processing unit 20. As shown in fig. 2 (B), the time-series data is divided into a plurality of states a, and a change point B between the states a is extracted.
Next, the processing unit 20 refers to the standard time required for each operation included in step 1. The standard time of each job is stored in advance in the storage unit 30, for example. The standard time may be determined by a person, or may be a time described in an operation manual or the like for inputting an operation automatically. Fig. 2 (c) is an example thereof. In the example of fig. 2 (C), the 1 st step C includes a job C1 (1 st job), a job C2 (2 nd job), and a job C3 (3 rd job). The operations C1 to C3 required 18 seconds, 35 seconds, and 19 seconds, respectively.
Next, the processing unit 20 analyzes the correspondence between the time-series data and each job using the extraction result of the change point and the standard time of the job. First, the processing unit 20 sets the start point of the 1 st step C (operation C1) in the time series data. For example, any one of the plurality of change points B is set as a start point. Alternatively, the start point may be set randomly or based on some rule.
When setting the start point of job C1, processing unit 20 samples candidates for the start point of job C2. Here, a case will be described in which the start point of the job C2 is assumed to coincide with the end point of the job C1.
For example, as shown in fig. 3a, the start point D1 of the job C1 is determined, and samples D2a to D2C are set as the start point of the job C2 (the end point of the job C1). For example, the sample is set to be centered on the time from start point D1 after the time (18 seconds) required for job C1 has elapsed. The number of samples is determined in consideration of the time required for the processing and the necessary accuracy of the analysis.
The samples are set at regular intervals or randomly within a predetermined range from the center, for example. Alternatively, the number of samples may be set so that the number is larger near the center and smaller as the distance from the center increases. For example, the probability distribution is set in advance for each of the jobs C1 to C3 as shown in fig. 3 (b). In fig. 3 (b), the horizontal axis represents time Ti, and the vertical axis represents probability P that each time can be acquired. The peak of the probability P is at the standard time. The processing unit 20 may set samples according to the probability distribution.
The processing unit 20 calculates an evaluation value (2 nd evaluation value) using the distance between each sample and the change point B closest to each sample. As the distance, for example, an euclidean distance, a manhattan distance, a mahalanobis distance, or the like is used. For example, the higher the evaluation value calculated for a sample, the shorter the distance between the sample and the change point B closest to the sample. The processing unit 20 extracts 1 or more samples including the sample having the highest evaluation value. In the example shown in fig. 3 (a), the sample D2a is closest to the change point B1. The processing unit 20 sets the sample D2a to the start point D2 of the job C2.
After that, the sampling of the start point and the setting of the start point of each job by the processing unit 20 are repeated in the same manner.
That is, as shown in fig. 3 (C), the processing unit 20 sets samples D3a to D3C as candidates for the start point of the job C3. The processing unit 20 sets the sample D3C closest to the change point B2 as the start point D3 of the job C3.
As shown in fig. 4 (a), the processing unit 20 sets samples D4a to D4C as candidates for the end point of the job C3 (1 st step C). The processing section 20 sets the sample D4B closest to the change point B3 as the end point D4 of the job C3.
Through the series of processing, as shown in fig. 4 (b), a sample path E1 including a plurality of samples corresponding to the start points D1 to D3 and the end point D4 is generated. The processing unit 20 repeats the same processing while changing the position (time) of the start point D1. As a result, as shown in fig. 5 (a), a plurality of sample paths E1 to Ex (x is an integer of 2 or more) are generated.
The processing unit 20 calculates an evaluation value (1 st evaluation value) for each generated sample path. The evaluation value is calculated based on the degree of matching between the positions of the start point and the end point included in the sample path and the positions of the plurality of change points B. As the suitability, for example, the distance between the sample and the change point B closest to the sample is used. For example, the distance to the closest change point B is calculated for each sample included in a certain sample path, and the evaluation value is calculated based on the sum of these distances. For example, the shorter the distance, the higher the evaluation value is calculated. The processing unit 20 selects one sample path from the plurality of sample paths based on the evaluation value.
The selected sample path indicates which job the portion of the time-series data corresponds to. For example, in the time series data, data between a sample set as the start point of the job C1 and a sample set as the start point of the job C2 indicates the operation of the operator in the job C1.
The processing unit 20 outputs the correspondence between the time-series data and each of the plurality of jobs to the outside. For example, the sample path E1 is selected from among a plurality of sample paths. As shown in fig. 5 (b), processing unit 20 causes display unit 40 to display start points D1 to D3 and end point D4 of sample path E1, a part of the time-series data corresponding to sample path E1, and the required time for each job calculated from start points D1 to D3 and end point D4.
The acquisition unit 10, the processing unit 20, the storage unit 30, and the display unit 40 are connected to each other by wire or wirelessly, for example. Alternatively, at least a part of these may be connected to each other via a network.
According to the analysis system 1 and the analysis method of embodiment 1, it is possible to automatically analyze which part corresponds to which job with respect to the time-series data indicating the operation of the operator. Therefore, it is not necessary to make a correspondence or a mark between time series data and each job by a person, and the time required for analysis can be shortened. Since the analysis time becomes short, analysis closer to real time, for example, can be realized. Further, establishing correspondence is performed based on the change point of the state in the time series data. Therefore, even a user who has no technique or experience regarding the analysis can analyze the work with high accuracy.
Fig. 6 is a flowchart showing the processing in the analysis system according to embodiment 1.
As an example, the processing unit 20 executes the processing shown in fig. 6. First, as shown in fig. 2 (b), a plurality of change points in time-series data are extracted (step S1). One of the plurality of change points is set as the start point of the nth job (step S2). In step S2, n is set to 1. That is, in step S2, the start point of the first job is set. As shown in fig. 3 (a), N candidates for the start point of the (N + 1) th job following the nth job are sampled (step S3). For each set sample, an evaluation value is calculated (step S4). As shown in fig. 3 (c) and the like, the start point of the (n + 1) th job is determined based on the evaluation value (step S5). As n, n +1 is set (step S6). It is determined whether or not the (n + 1) th job exists (step S7). If so, step S3 is executed again. If not, it means that a plurality of samples corresponding to the start points of all the jobs included in step 1 and the end point of step 1 have been set. As a result, as shown in fig. 4 (b), one sample path including the start point of each job and the end point of the 1 st step is generated.
Next, it is determined whether or not the end condition is sufficient (step S8). When the termination condition is insufficient, another one of the plurality of change points is set as the start point of the nth job (step S9). In step S9, n is set to 1. Thus, the starting point of the first job is set to a position (time) different from that before. After step S9, steps S3 to S8 are repeated.
The end condition is that, for example, each of the plurality of change points extracted in step S1 is set as the start point of the 1 st process and steps S3 to S7 are performed. Alternatively, the end conditions may be set by executing steps S3 to S7 for each change point within the predetermined range of the time series data.
When the termination condition is sufficient, a plurality of sample paths are generated as shown in fig. 5 (a). Evaluation values are calculated for these sample paths, respectively (step S10). Based on the evaluation value, 1 or more sample paths are determined (step S11). The result regarding the decided sample path is displayed (step S12). As a result, as described above, the start point and the end point included in the selected sample path, a part of the time-series data corresponding to the sample path, the required time of each job, and the like are displayed.
Although the processing is different from the processing shown in the flowchart of fig. 6, the evaluation value of the generated sample path may be calculated when the determination of step S8 is performed. For example, when the evaluation value satisfies a predetermined condition, it is determined that the termination condition is sufficient. In this case, steps S10 and S11 are omitted, and the result of the sample path for which the evaluation value satisfying the condition is obtained is displayed in step S12.
In the above example, the sample is reduced after the start point of the next job is sampled, and the next start point is sampled based on the reduced sample. In addition to this method, the next start point may be sampled on a sample-by-sample basis without reducing the samples. In this method, since the number of sample paths to be finally generated increases, the possibility of obtaining a sample path more suitable for the plurality of change points B increases. Thus, the correspondence relationship between the time-series data and the job can be analyzed with higher accuracy. On the other hand, when the sample is reduced and then the next sampling is performed, the amount of calculation is reduced, and therefore, the time required for the analysis can be shortened.
(modification 1: resampling)
Fig. 7 is a schematic diagram for explaining processing in the analysis system according to variation 1 of embodiment 1.
The start point of the next job may be sampled based on the start point of a certain job and then resampled.
Fig. 7 (a) is an enlarged view of a part of the time-series data shown in fig. 2 (a). As shown in fig. 7 (a), when samples D2a to D2C are set as candidates for the start point of the job C2, the processing unit 20 calculates the evaluation value of each sample. Then, the processing unit 20 defines a probability distribution based on the calculated evaluation value. The processing unit 20 resamples (resamples) the candidate for the start point of the job C2 according to the defined probability distribution.
In the example shown in fig. 7 (a), the sample D2a is closest to the change point B1, and the sample D2c is farthest from the change point B1. Therefore, the probability distribution defined based on the evaluation values of these samples has a high probability in the vicinity of the sample D2a and a low probability in the vicinity of the sample D2 c. According to the probability distribution, for example, as shown in fig. 7 (b), the processing unit 20 sets a plurality of samples D2a with the sample D2a as the center1~D2a3And a plurality of samples D2b are set with the sample D2b as the center1And D2b2. With respect to the sample D2c, no sample is set. The number of samples set for the samples D2a to D2c by resampling is obtained based on the evaluation value. That is, for a sample having a short distance from the change point, more samples are set by resampling.
After resampling, the processing unit 20 may, for example, convert the sample D2a into a sample1~D2a3、D2b1And D2b2Each is set as a candidate for the start point of the job C2. The processing unit 20 samples and resamples candidates of the start point of the next job based on each sample.
Fig. 8 is a flowchart showing a process in the analysis system according to variation 1 of embodiment 1.
The flowchart of modification 1 shown in fig. 8 differs from the flowchart shown in fig. 6 in that steps S20 and S21 are included instead of step S5.
If the evaluation value is calculated in step S4, a probability distribution is defined based on the evaluation value (step S20). The starting point of the (n + 1) th job is resampled by M according to the defined probability distribution (step S21). Thereafter, in the case where there is a next job, for each of the M samples, the start point of the next job is sampled in step S3.
By performing resampling based on the result of sampling, the start point and the end point more coincident with the plurality of change points B can be easily obtained. This can improve the accuracy of analysis.
(modification 2: Corrugation)
Fig. 9 is a schematic diagram for explaining processing in the analysis system according to variation 2 of embodiment 1.
The processing unit 20 may detect a characteristic pattern (moire) that repeatedly appears in the time series data. First, the processing unit 20 cuts out a part of the time series data. The range (length of time) of the extracted data is set based on, for example, the required time of any one of the plurality of jobs. As an example, as shown in fig. 9 (b), the processing unit 20 cuts out a part of the data from the entire time-series data shown in fig. 9 (a).
Next, the processing unit 20 compares the extracted data with other data of the same time length in the time series data. For example, the processing unit 20 calculates a DTW (Dynamic time warping) distance between the extracted data and other data. By using the DTW distance, the strength of the correlation between these data can be obtained regardless of the length of time. The processing unit 20 compares the extracted data with other data before finding out data similar to (having a strong correlation with) the extracted data. For example, the processing unit 20 compares the range of the other data with the extracted data while shifting the range of the other data by one frame.
The processing unit 20 extracts a portion similar to the cut-out data. For example, a portion where the DTW distance is smaller than a prescribed value is extracted. When there is no portion having a DTW distance smaller than the predetermined value, the processing unit 20 extracts data in another range or data of another time length from the time series data and compares the extracted data with other data.
By this processing, a plurality of mutually similar portions F (ripples) are extracted as shown in fig. 9 (c). The processing section 20 calculates the period G of the similar portion F. The period G is calculated by averaging the time between the centers of the adjacent similar sections F, for example. The processing unit 20 cuts out a part of the time-series data based on the period G. For example, the processing unit 20 cuts out data having a length 2 times the period G from the entire time series data. The position of the cut-out may be random or may be based on a predetermined rule. As in the method shown in fig. 2 (B), the processing unit 20 extracts a plurality of change points B with respect to the extracted data.
Fig. 10 is a flowchart showing a process in the analysis system according to variation 2 of embodiment 1.
The flowchart of modification 2 shown in fig. 10 differs from the flowchart shown in fig. 6 in that steps S30 to S32 are included instead of step S1.
When the time series data is acquired, a similar portion (ripple) in the time series data is extracted first (step S30). Based on the extracted similar portion, a part of the time-series data is cut out (step S31). A plurality of change points in the cut out time series data are extracted (step S32). Thereafter, step S2 is executed based on the extracted plurality of change points.
A plurality of similar portions similar to each other are extracted from time series data, and a part of the entire data is cut out based on the similar portions, whereby the time required for the subsequent processing can be significantly shortened.
As a method of cutting out a part of the entire data, there is also a method of using the standard time of the 1 st step C. For example, the processing unit 20 may cut out data 2 times or 3 times the standard time of the 1 st step C from the entire data. In this case as well, the time required for the subsequent processing can be significantly shortened.
However, in practice, the time required for the operator to perform the 1 st step C may be significantly different from the standard time of the 1 st step C. If the operator has high proficiency, the time actually required in the 1 st step C may be shorter than the standard time. That is, since data having a length longer than necessary is cut out, there is a possibility that the time required for the subsequent processing becomes longer than in the case of cutting out data based on the similar portion. On the other hand, if the operator's skill is low, the time actually required in the 1 st step C may be longer than the standard time. Therefore, the extracted data may not include the operation of all the jobs, and may not be analyzed properly.
By using the similar portion, the time required for the processing can be effectively shortened while suppressing a decrease in the accuracy of the analysis.
(modification 3: similarity)
Fig. 11 (a) and 11 (b) are schematic diagrams for explaining processing in the analysis system according to variation 3 of embodiment 1.
When calculating the evaluation value of the sample path, the processing unit 20 may refer to the similarity between the jobs included in the 1 st step. The similarity is stored in, for example, the storage unit 30.
As an example, the similarity (2 nd similarity) between jobs is set as in the table shown in fig. 11 (a). The similarity may be input by a person in advance, or may be automatically set by the processing unit 20. In the case of automatic setting, the similarity can be set based on articles described in the operation manual. For example, the similarity between the names of the respective jobs described in the operation manual is calculated and used. Alternatively, when the operation contents are described in the operation manual, the similarity between articles of the operation contents may be used.
The more similar the contents of 2 jobs, the higher the possibility that the waveforms of the time-series data obtained in these jobs are similar to each other. Fig. 11 (b) shows data corresponding to a sample path E1 among the plurality of sample paths E1 to Ex shown in fig. 5 (a). When calculating the evaluation value of the sample path, the processing unit 20 calculates the similarity (1 st similarity) between the data corresponding to each job, in addition to the distances between the start point and the end point and the change point. As the similarity, a DTW distance may be used.
For example, when calculating the DTW distance between the data corresponding to job C1 and the data corresponding to job C2, the processing unit 20 refers to the table shown in (a) of fig. 11. According to the table, the similarity between jobs C1 and C2 is low. Therefore, when the DTW distance is long, the DTW distance matches the preset similarity information. If the DTW distance between the data corresponding to the job C1 and the data corresponding to the job C3 is short, the similarity matches the similarity stored in the table. The processing unit 20 increases the evaluation value as the similarity between the data corresponding to each job and the similarity stored in the table are more consistent.
Fig. 12 is a flowchart showing a process in the analysis system according to variation 3 of embodiment 1.
The flowchart of modification 3 shown in fig. 12 differs from the flowchart shown in fig. 6 in that steps S40 and S41 are included instead of step S10.
If it is determined in step S8 that the termination condition is sufficient, the similarity between the preset jobs is referred to (step S40). Alternatively, the similarity may be calculated by reading an operation manual or the like in step S40. Next, the evaluation value of each sample path is calculated using the similarity (step S41).
For example, the distances to the plurality of change points are calculated for the start point and the end point of each sample path. Further, based on each sample path, a part of the time series data corresponding to each job is extracted. Then, the similarity between the extracted data is calculated, and the similarity between the data and the similarity between the jobs are compared. An evaluation value is calculated based on the calculation result of the distance and the comparison result of the similarity. Then, a sample path is determined based on the calculated evaluation value.
According to the method, the corresponding relation between the time series data and the operation can be analyzed accurately and better.
(modification 4: Branch of work)
Fig. 13 is a schematic diagram for explaining processing in the analysis system according to variation 4 of embodiment 1.
Here, a case where there are a plurality of flow of the work performed in the 1 st step will be described. For example, as shown in fig. 13 (a), the 1 st step C further includes a work C4. There is a case where the job C4 is executed between the job C2 and the job C3. In the case where job C4 is not executed, job C3 is executed immediately after job C2. That is, a job that is possibly performed after the job C2 is branched into a job C3 and a job C4.
In this case, after determining the start point of the job C2, the processing unit 20 samples the start point candidates of the jobs C3 and C4, respectively. In the example shown in fig. 13 (a), the standard time required for the job C4 is 40 seconds. After determining the start point D3 as shown in fig. 13 (b), the processing unit 20 sets samples D4a to D4C in the vicinity of 19 seconds after the standard time of the job C3. Further, the processing unit 20 sets samples D4D to D4f in the vicinity of 40 seconds after the standard time of the operation C4.
The processing unit 20 calculates the distance between each sample and the closest change point B, and calculates the evaluation value. The processing unit 20 defines a probability distribution based on the evaluation value, for example. Next, the processing unit 20 performs resampling according to the probability distribution, as in the first modification 1. Then, the start point of the next job is sampled based on the sample set by the resampling. For a sample for which the next job does not exist, the processing is terminated and the sample path is stored in the storage unit 30.
Fig. 14 is a flowchart showing a process in the analysis system according to variation 4 of embodiment 1.
The flowchart of the 4 th modification shown in fig. 14 differs from the flowchart shown in fig. 6 in that it includes step S50 instead of step S3, steps S20 and S21 instead of step S5, and steps S51 to S53 instead of step S7.
If the start point of the nth job is set in step S2 or S9, the start point of the (N + 1) th job is sampled by N in step S50. At this time, as the N +1 th job, when there may be a plurality of jobs, the start point of each job is sampled by N. Next, the evaluation value of each sample is calculated (step S4), and resampling is performed in accordance with the probability distribution based on the evaluation values (steps S20 and S21). Thereafter, samples in which the (n + 1) th job exists are extracted from the samples set by the resampling in step S21, and a set S of samples is generated (step S51). Further, for the sample for which the n +1 th job does not exist, the sample path is saved (step S52).
After steps S51 and S52, it is determined whether or not a sample is present in the set S (step S53). When there are samples in the set S, the start point of the (N + 1) th job is sampled again N for each sample included in the set S (step S50). When no sample exists in the set S, step S8 is executed in the same manner as the flowchart shown in fig. 6.
When there is a branch in the flow of the work included in step 1, if the branch is not considered in the analysis, the correlation between the time series data and the work cannot be accurately performed. In the analysis system and the analysis method according to the present modification, even when there is a branch of such a job, each job after the branch is sampled. Thus, the accuracy of establishing correspondence between the time-series data and the job can be improved.
(embodiment 2)
Fig. 15 is a block diagram showing the configuration of the analysis system according to embodiment 2.
As shown in fig. 15, the analysis system 2 according to embodiment 2 further includes a learning data storage unit 50 and an RNN storage unit 60.
According to the analysis system 1 of embodiment 1, a part of the time-series data corresponding to the 1 st step can be extracted from the entire time-series data. The analysis system 2 of embodiment 2 learns a recurrent neural network (hereinafter referred to as RNN) using a part of the extracted time series data. The analysis system 2 also analyzes the operation of the operator using the RNN. Next, the RNN learning by the processing unit 20 and the analysis using the RNN will be described.
(learning)
When a part of the time series data corresponding to the 1 st step is extracted, the processing unit 20 stores the extracted data in the learning data storage unit 50. The learning data storage unit 50 stores, in addition to the time series data, information relating to the skill level of the operator who has acquired the time series data. The proficiency level is stored in the learning data storage unit 50 by the user in advance. Alternatively, the skill level may be calculated based on the length of time of the time series data and stored. In this case, the shorter the time required for the 1 st step, the higher the skill level is calculated.
The processing unit 20 learns the RNN stored in the RNN storage unit 60 using the time series data stored in the learning data storage unit 50. RNN is one type of neural network. Neural networks are obtained by using artificial neurons (nodes) to mimic biological recognition systems. A plurality of neurons are connected to each other by artificial synapses (connection lines) with weights set.
Fig. 16 is a schematic diagram showing a recurrent neural network.
As shown in fig. 16, the RNN200 includes an input layer 201, an intermediate layer 202, and an output layer 203. Further, with respect to RNN, the output of the neuron N of the intermediate layer 202 in a certain time division is connected to the output of the neuron N of the intermediate layer 202 in a subsequent time division.
The processing unit 20 inputs time-series data for learning to the neuron N included in the input layer 201. Then, the processing unit 20 inputs teacher data to the neuron N included in the output layer 203. As the teacher data, a value indicating the skill level is set. That is, when the inputted time series data is based on the action of the skilled person, a value indicating a high level of skill is set for the neuron N of the output layer 203. The weights of synapses included in the RNN are changed by learning so that the difference between the input time-series data and the teacher data becomes small. The learning is performed using time series data acquired from a plurality of operators having different proficiency levels. The processing unit 20 stores the learned RNN in the RNN storage unit 60.
The learning data storage unit 50 and the RNN storage unit 60 are hard disk drives, flash memories, network hard disks, or the like. One storage device may function as the storage unit 30, the learning data storage unit 50, and the RNN storage unit 60.
(analysis)
In the analysis using RNN, for example, it is possible to investigate the degree of skill to which the operation of a certain operator corresponds. Further, the operator can find a point to be improved during the operation. In the analysis, time series data indicating the operation in the 1 st step of the operator to be analyzed is stored in the storage unit 30 in advance. The time series data is extracted by, for example, the processing explained in the analysis system 1.
The processing unit 20 inputs the time series data of the analysis target to the RNN storing unit 60, which has completed the learning. If the input layer 201 of the RNN is inputted with timing data, the neuron N of the output layer 203 may react. The processing unit 20 detects the response of the neuron N of the output layer 203. For example, the processing unit 20 compares the activity level of the neuron N with a predetermined threshold value. When the activity level of the neuron N is higher than a predetermined threshold value, the processing unit 20 detects that the neuron N is responding. The processing unit 20 may extract data of a period in which the neuron N reacts in the time series data. Alternatively, the processing unit 20 may extract data indicating the activity level of the neuron N and a part of the time series data in the period.
The display unit 40 displays the detection result of the processing unit 20. For example, the display unit 40 displays a part of the time-series data extracted by the processing unit 20 so as to be distinguishable from other parts. When the response of the neuron N is not detected, the display unit 40 may display a result indicating that the response is not detected.
The neurons N of the middle layer 202 of the RNN have, for example, a LSTM (Long Short term memory) configuration. The neural network having the LSTM configuration can improve the recognition rate of time series data having a longer operation cycle than the neural networks having other configurations.
Fig. 17 is a block diagram showing the LSTM structure.
As shown in fig. 17, LSTM configuration 300 includes a forgetting gate (gate)310, an input gate 320, and an output gate 330.
In FIG. 17, xtRepresenting the input value to neuron N in time t. CtRepresenting the state of the neuron N in time t. f. oftRepresenting the output value of the forgetting gate 310 in time t. i.e. itRepresenting the output value of the input gate in time t. otRepresenting the output value of the output gate in time t. h istRepresents the output value of neuron N in time t. f. oft、it、Ct、otAnd ht are expressed by the following expressions "expression 1" to "expression 5", respectively.
[ mathematical formula 1 ]
ft=σ(Wf·[ht-1,xt]+bf)
[ mathematical formula 2 ]
it=σ(Wi·[ht--1,xt]+bi)
[ mathematical formula 3 ]
Ct=ft*Ct-1+it*tanh(WC·[ht-1,xt]+bC)
[ mathematical formula 4 ]
ot=σ(Wo·[ht-1,xt]+bo)
[ math figure 5 ]
ht=ot*tanh(Ct)
In addition, the neuron elements N in the intermediate layer 202 of the RNN may have a Gated cycle Unit (Gated recovery Unit) structure, a bi-directional (bi-directional) LSTM structure, or the like, without being limited to the example shown in fig. 17.
Fig. 18 is a flowchart showing processing in the analysis system according to embodiment 2.
First, the analysis processing shown in the flowcharts of fig. 6, 8, 10, 12, 14, and the like is executed to acquire time series data indicating the operation in the step 1 (step S60). Next, RNN learning is performed using the time series data acquired in step S60 (step S61). Next, time series data to be analyzed is acquired (step S62). The acquired time series data is input to the learned RNN, and the response of the neuron is detected (step S63). The detection result is displayed on the display unit 40 (step S64).
Effects of embodiment 2 will be described.
According to the analysis system 2 and the analysis method of embodiment 2, it is possible to detect whether or not the operation in step 1 of a certain operator includes a point to be improved. Conventionally, whether or not the operation should be improved has been confirmed by observation of a human, for example. However, in this case, the observer has to observe all the operations of the respective operators, and a long time is required. Further, since the extraction of the points to be improved depends on the subjectivity, experience, and skill of the observer, variations may occur.
On the other hand, in the analysis system 2 and the detection method according to the present embodiment, the point to be improved is detected based on the RNN. The RNN is learned using data based on the actions of other operators. Thus, the point to be improved is objectively detected without depending on the experience of the observer or the like. Further, the point to be improved is automatically detected by the analysis system 2 and the detection method, and therefore an observer is not required. Thus, according to the present embodiment, an analysis system and a detection method capable of automatically and objectively detecting an action to be improved by an operator are provided.
Here, the description is made for the purpose of detecting an operation to be improved by an operator. However, the application of the analysis system 2 and the detection method according to the embodiment is not limited to this example. For example, the analysis system 2 and the detection method of the present embodiment may be used to detect excellent motions of an operator.
The analysis system 2 analyzes the job using the RNN. The following effects are obtained by using RNN.
The work cycle varies from operator to operator. Therefore, even if each operator starts the work at the same time, the work performed by each operator at a certain point in time varies with the passage of time. In this regard, by using the RNN, it is possible to eliminate the influence of such a variation in the operation cycle and to detect an operation to be improved in the operation. By using the RNN, it is possible to consider the correlation between a certain time-division operation and a subsequent time-division operation. As a result, not only the operation that causes the increase in the operation time but also the operation that causes the increase in the operation time can be detected.
Furthermore, in the analysis system 2 and the detection method according to the present embodiment, it is desirable that the neurons N in the intermediate layer 202 of the RNN200 have the LSTM structure shown in fig. 17. By adopting the LSTM configuration, the state of the neuron N included in the intermediate layer 202 can be maintained over a longer period. The mutual dependence of the operations at the respective time points can be analyzed over a longer period. Therefore, not only the operation at a certain point in time but also a certain neuron N included in the output layer 203 can react to the operations before and after the operation. As a result, the operation to be improved of the operator can be detected more comprehensively.
By using the processing method described in embodiment 1, time series data necessary for RNN learning can be automatically extracted. Thus, the time required for preparation of analysis by RNN can be significantly shortened.
(examples)
Fig. 19 (a) and 19 (b) are graphs showing data obtained in the examples.
Fig. 20 (a) is a graph showing data obtained in the example. Fig. 20 (b) and 20 (c) are graphs showing the activity of neurons in the examples.
The data shown in fig. 19 (a), 19 (b), and 20 (a) are obtained based on the operation performed by the 1 st, 2 nd, and 3 rd workers when performing the 1 st work, respectively. The data of fig. 19 (a), 19 (b), and 20 (a) are obtained by attaching an accelerometer to the right wrist of each of the 1 st, 2 nd, and 3 rd workers.
In fig. 19 (a), 19 (b), and 20 (a), the abscissa represents time Ti, and the ordinate represents acceleration Ac. The solid line and the broken line respectively indicate the acceleration in the X-axis direction and the acceleration in the Y-axis direction.
The acquisition unit 10 acquires data shown in fig. 19 (a) and 19 (b) and stores the data in the storage unit 30. The processing unit 20 refers to the data shown in fig. 19 (a) and 19 (b) and learns the RNN stored in the RNN storage unit 60. As can be seen from a comparison between fig. 19 (a) and 19 (b), the time required for the 1 st operator to perform the 1 st operation is shorter than the time required for the 2 nd operator to perform the 1 st operation. That is, the proficiency of the 1 st worker is superior to that of the 2 nd worker.
The processing unit 20 inputs the data shown in fig. 20 (a) to the RNN having completed learning stored in the RNN storage unit 60. Fig. 20 (b) and 20 (c) are graphs showing the activity levels of the 1 st neuron and the 2 nd neuron when the data shown in fig. 20 (a) is input, respectively. When the activity of the 1 st neuron is high, it indicates that the action corresponding to the input data corresponds to the 1 st skill of the 1 st operator. When the activity of the 2 nd neuron is high, it indicates that the action corresponding to the input data corresponds to the 2 nd skill of the 2 nd operator. In fig. 20 (b) and 20 (c), the horizontal axis represents time Ti, and the vertical axis represents the activity degree Act of the neuron. The greater the absolute value of the activity of a neuron, the stronger the response of the neuron.
As is clear from fig. 20 (b) and 20 (c), the activity level of the 2 nd neuron increases from time T1 to time T2. That is, the operation of the 3 rd operator during the time period from T1 to T2 corresponds to the 2 nd skill of the 2 nd operator. For example, the activity of neuron 2 exceeds the threshold value from time T1 to time T2. The processing unit 20 detects that the 2 nd neuron is reacting. As shown in fig. 20 (a), for example, the display unit 40 can display the data of the 3 rd operator at time T1 to time T2 separately from the other parts. From the results of this example, it is found that it is preferable to improve the action of detecting the response of the 2 nd neuron.
By using the analysis system and the analysis method according to the above-described embodiments, the work in the 1 st step can be more automatically analyzed, and the time required for the analysis can be shortened. Similarly, by using a program for causing the processing unit to execute the above-described processing or a storage medium storing the program, the work in step 1 can be more automatically analyzed, and the time required for the analysis can be shortened.
While several embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These new embodiments may be implemented in other various forms, and various omissions, substitutions, and changes may be made without departing from the spirit of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalent scope thereof. The above embodiments can be combined with each other.
Description of the reference numerals
1, 2 analysis system, 10 acquisition unit, 20 processing unit, 30 storage unit, 40 display unit, 50 learning data storage unit, 60RNN storage unit, 201 input layer, 202 intermediate layer, 203 output layer, 300LSTM structure, 310 forgetting gate, 320 input gate, 330 output gate, a state, B1-B3 change point, C process, C1-C4 operation, D1-D3 start point, D4 end point, D2 a-D2C, D2a1~D2a3,D2b1,D2b2D3 a-D3 c, D4 a-D4F samples, E1-Ex sample path, FPartial (wave), G period, N neuron, S1-12, S20, S21, S30-S32, S40, S41, S50-S53, S60-S64 steps, Ti time, T1, T2 time
Claims (14)
1. An analysis system, comprising:
an acquisition unit that acquires time series data indicating an operation of a worker in a step 1 including a plurality of operations; and
and a processing unit configured to detect a plurality of change points of a state in the time series data, and associate the time series data with each of the plurality of jobs using the plurality of change points.
2. The analytical system of claim 1,
the above-mentioned treatment portion can be used for treating various diseases,
a plurality of similar portions similar to each other are extracted in the above time-series data,
cutting out a part of the time series data based on the length of time between the similar parts,
in the associating, the extracted time-series data is associated with each of the plurality of jobs.
3. The analysis system according to claim 1 or 2,
the plurality of jobs include a 1 st job and a 2 nd job executed after the 1 st job,
the processing unit, in the establishing correspondence,
generating a sample path including a plurality of samples corresponding to the start point and the end point of the 1 st operation and the 2 nd operation, respectively,
calculating a 1 st evaluation value based on the degrees of suitability between the plurality of samples and the plurality of change points,
in the associating, the time-series data is associated with each of the 1 st job and the 2 nd job using the 1 st evaluation value.
4. The analytical system of claim 3,
the processing unit, in the establishing correspondence,
extracting 1 st data corresponding to the 1 st job and 2 nd data corresponding to the 2 nd job from the time-series data based on the plurality of samples,
calculating the 1 st similarity between the 1 st data and the 2 nd data,
in the calculation of the 1 st evaluation value, the 1 st evaluation value is calculated based on the suitability, the 1 st similarity, and the 2 nd similarity between the 1 st job and the 2 nd job.
5. The analysis system according to claim 3 or 4,
the processing unit, in the generation of the sample path,
setting one of the plurality of change points as a start point of the 1 st job,
setting a plurality of samples as candidates for a start point of the 2 nd job based on the time required for the 1 st job,
calculating a distance to the closest change point for each of the plurality of samples,
using the plurality of distances, one of the plurality of samples is set as a starting point of the 2 nd job.
6. The analysis system according to claim 3 or 4,
the processing unit, in the generation of the sample path,
setting one of the plurality of change points as a start point of the 1 st job,
setting a plurality of samples as candidates for a start point of the 2 nd job based on the time required for the 1 st job,
calculating a 2 nd evaluation value for each of the plurality of samples using a distance to the closest change point,
a plurality of other samples are set as candidates for the starting point of the 2 nd job in accordance with a probability distribution defined using the plurality of 2 nd evaluation values.
7. The analytical system of any one of claims 3 to 6,
the above-mentioned treatment portion can be used for treating various diseases,
generating a plurality of sample paths while changing the change point set as the start point of the 1 st operation,
calculating the 1 st evaluation value for each of the plurality of sample paths,
selecting one of the plurality of sample paths based on the plurality of 1 st evaluation values,
the plurality of samples included in the one of the plurality of sample paths are set as a start point and an end point of the plurality of jobs.
8. The analytical system of any one of claims 1 to 7,
the processing unit calculates a time length of a portion of the time-series data corresponding to each of the plurality of jobs and outputs the time length to the outside.
9. The analytical system of any one of claims 1 to 8,
the processing unit learns a recurrent neural network using the time-series data associated with each of the plurality of tasks and information on the proficiency of the operator.
10. The analytical system of claim 9,
the processing unit inputs other time series data indicating the operation of the other operator in the step 1 to the learned recurrent neural network, and detects the response of the output layer of the recurrent neural network.
11. An analysis system, comprising:
an acquisition unit that acquires time series data indicating an operation of an operator who repeats step 1; and
and a processing unit that detects a plurality of change points of the state in the time series data and extracts a portion of the time series data corresponding to one operation of the 1 st step using the plurality of change points.
12. A method of analysis, wherein,
acquiring time series data indicating an operation of a worker in a step 1 including a plurality of works;
detecting a plurality of change points of the state in the time series data;
and associating the time-series data with each of the plurality of jobs using the plurality of change points.
13. A process in which, in the presence of a catalyst,
causing a processing unit to detect a plurality of change points of a state from time series data indicating an operation of a worker in a step 1 including a plurality of jobs,
and associating the time-series data with each of the plurality of jobs using the plurality of change points.
14. A storage medium, wherein,
a program according to claim 13 is stored.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2018150213A JP7049212B2 (en) | 2018-08-09 | 2018-08-09 | Analytical systems, analytical methods, programs, and storage media |
JP2018-150213 | 2018-08-09 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110826383A true CN110826383A (en) | 2020-02-21 |
CN110826383B CN110826383B (en) | 2023-12-01 |
Family
ID=69547574
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910227735.0A Active CN110826383B (en) | 2018-08-09 | 2019-03-25 | Analysis system, analysis method, program, and storage medium |
Country Status (2)
Country | Link |
---|---|
JP (1) | JP7049212B2 (en) |
CN (1) | CN110826383B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113486072B (en) * | 2020-03-17 | 2024-06-18 | ***通信集团福建有限公司 | Data analysis method, device, electronic equipment and computer readable storage medium |
WO2023276083A1 (en) * | 2021-06-30 | 2023-01-05 | 慎平 大杉 | Information processing system, trained model, information processing method, and program |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106997505A (en) * | 2015-11-11 | 2017-08-01 | 株式会社东芝 | Analytical equipment and analysis method |
JP2018045512A (en) * | 2016-09-15 | 2018-03-22 | オムロン株式会社 | Workability evaluation device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5884220B2 (en) | 2011-03-07 | 2016-03-15 | 国立大学法人 筑波大学 | Work management system |
-
2018
- 2018-08-09 JP JP2018150213A patent/JP7049212B2/en active Active
-
2019
- 2019-03-25 CN CN201910227735.0A patent/CN110826383B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106997505A (en) * | 2015-11-11 | 2017-08-01 | 株式会社东芝 | Analytical equipment and analysis method |
JP2018045512A (en) * | 2016-09-15 | 2018-03-22 | オムロン株式会社 | Workability evaluation device |
Also Published As
Publication number | Publication date |
---|---|
JP7049212B2 (en) | 2022-04-06 |
JP2020027324A (en) | 2020-02-20 |
CN110826383B (en) | 2023-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6897037B2 (en) | Workability evaluation device | |
CN108602191B (en) | Operation information generating device, operation information generating method, and recording medium | |
JP6765449B2 (en) | Work analyzer and work analysis method | |
JP5455787B2 (en) | Motion analysis apparatus and motion analysis method | |
KR101872907B1 (en) | Motion analysis appratus and method using dual smart band | |
KR20120052610A (en) | Apparatus and method for recognizing motion using neural network learning algorithm | |
JP2006209468A (en) | Work operation analysis device, work operation analysis method and work operation analysis program | |
KR20190099537A (en) | Motion learning device, function determining device and function determining system | |
CN110826383B (en) | Analysis system, analysis method, program, and storage medium | |
US20200074361A1 (en) | Performance measurement device, performance measurement method and performance measurement program | |
Lin et al. | Segmenting human motion for automated rehabilitation exercise analysis | |
KR102363879B1 (en) | Method for predicting clinical functional assessment scale using feature values derived by upper limb movement of patients | |
Han et al. | A machine-learning classification approach to automatic detection of workers' actions for behavior-based safety analysis | |
Malawski et al. | Real-time action detection and analysis in fencing footwork | |
JP7165108B2 (en) | Work training system and work training support method | |
JP2019103609A (en) | Operation state estimation apparatus, operation state estimation method, and program | |
JP5300795B2 (en) | Facial expression amplification device, facial expression recognition device, facial expression amplification method, facial expression recognition method, and program | |
JPH08115408A (en) | Finger language recognition device | |
KR20200120365A (en) | Machine learning method and system for automatically grading severity from separated actions of a parkinsonian patient video | |
JP2022186422A (en) | Classification apparatus, classification method, and classification program | |
EP3758023B1 (en) | Method and device for assessing physical movement of an operator during a work cycle execution on an industrial manufacturing work station | |
JP2022003491A (en) | Analyzer, analysis system, method for analysis, program, and recording medium | |
JP7347539B2 (en) | Foreground extraction device, foreground extraction method, and program | |
WO2021039641A1 (en) | Motion verbalization device, motion verbalization method, program, and motion recording device | |
US20240127459A1 (en) | Method and apparatus for classifying and evaluating motion based on motion feature |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |