Work content analysis device, work content analysis method, program, and sensor

Abstract

According to the embodiment, the work content analysis device is a work content analysis device that analyzes a work content of a worker according to a state of the worker, and includes: a first database that stores state information indicating the state of the worker in association with time information and identification information of the worker; a presumption unit that presumes the work content performed by the worker based on at least two pieces of state information associated with the same time among the state information stored in the first database; a determination unit that determines a work time taken for the presumed work content based on the state information stored in the first database and the time information associated with the state information; and an analysis unit that analyzes the work content based on the presumed work content and the determined work time.

Description

Technical Field

[0001] Embodiments of the present invention relate to a job content analysis device, a job content analysis method, a program, and a sensor for the job content analysis device for analyzing the job content of operators in a factory or the like based on the operator's status. Background Technology

[0002] Typically, to achieve higher efficiency in operations, it is common practice to measure the actual time required for each task, analyze the task sequence, and visualize the current state of the task based on the measurement and analysis results. This allows the sequence to be standardized, and each operator performs the task according to the standardized sequence.

[0003] However, the measurement of the work time required to analyze such past work sequences is done by a surveyor using a stopwatch. This incurs additional labor costs.

[0004] To measure work time without incurring additional labor costs, IoT can also be utilized. That is, envisioning IoT replacing human systems for work.

[0005] However, a stable IoT requires repairing the equipment in the factory itself, making it difficult to add to equipment already in operation in an additional way.

[0006] Thus, even if one wants to implement job content analysis, additional labor costs will be incurred for data collection. Conversely, if one wants to reduce labor costs, equipment needs to be modified, making it difficult to implement.

[0007] Therefore, the current situation makes it impossible to implement efficiency improvement measures in all related factories at an appropriate pace, and efficiency improvement measures for each factory are delegated to each factory individually. Attached Figure Description

[0008] Figure 1 This is a block diagram illustrating an example of the circuit structure of a job content analysis device that applies the job content analysis method of the first embodiment.

[0009] Figure 2A This is a conceptual diagram illustrating an example of the connection between a task content analysis device and other devices (including a camera).

[0010] Figure 2B This is a conceptual diagram illustrating an example of the connection between a job content analysis device and other devices (including equipment).

[0011] Figure 2C This is a block diagram illustrating an example of the circuit structure of a sensor.

[0012] Figure 3AThis is an example of displaying state information (sensor information representing the operating status of the device) that has been stored in the state information database in a time series.

[0013] Figure 3B This is another example of showing the status information (sensor information representing the operating status of the device) stored in the status information database in a time series.

[0014] Figure 4A This is a graph showing an example of the time-series changes in sensed information representing area numbers as location information.

[0015] Figure 4B It shows that by... Figure 4A The diagram shows an example of state information determined by performing computational processing on the sensed information.

[0016] Figure 5 This is a flowchart illustrating an example of the operation of a job content analysis device that applies the job content analysis method of the first embodiment.

[0017] Figure 6 This is a graphical display example showing the time required for each task.

[0018] Figure 7 It is a flowchart used to illustrate the process of business improvement.

[0019] Figure 8 This is a flowchart illustrating an example of the operation of a job content analysis device that applies the job content analysis method of the second embodiment.

[0020] Figure 9 This is a graphical example showing the frequency and duration of entry into each area of ​​the factory by all operators within the group.

[0021] Figure 10 This is a graphical display example that shows the actual results of the task in detail according to the task content and time. Detailed Implementation

[0022] Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings.

[0023] The work content analysis apparatus of the embodiment analyzes the work content of an operator based on the operator's status. It includes: a first database that stores status information indicating the status of one or more operators in association with time information and operator identification information; an estimation unit that estimates the work content performed by the operator based on at least two status information items associated with the same time in the status information stored in the first database; a determination unit that determines the work time spent on the estimated work content based on the status information stored in the first database and the time information associated with the status information; and an analysis unit that analyzes the work content based on the estimated work content and the determined work time. The status information includes at least one of the following: operator position information, activity information indicating whether the operator's hands are moving, and information indicating the operating status of equipment surrounding the operator.

[0024] (First Embodiment)

[0025] This describes a job content analysis apparatus that applies the job content analysis method of the first embodiment.

[0026] Figure 1 This is a block diagram illustrating an example of the circuit structure of a job content analysis device that applies the job content analysis method of the first embodiment.

[0027] Figure 2A This is a conceptual diagram illustrating an example of the connection between a task content analysis device and other devices (including a camera).

[0028] The work content analysis device 10 is a device for analyzing the work content performed by operators in factories, etc.

[0029] like Figure 1 As shown, the circuit of the job content analysis device 10 includes a CPU 12, a recording medium reading unit 14, a communication unit 15, a display unit 16 (e.g., a display), a memory 20, and a storage device 30, which are interconnected via a bus 11.

[0030] The memory 20 stores a processing module 21, a prediction module 22, a determination module 23, a job time comparison module 24, an analysis module 25, a display control module 26, and a judgment module 27 as the program for implementing the job content analysis device 10.

[0031] These program modules 21 to 27 can be pre-stored in the memory 20, or they can be read into the memory 20 from an external recording medium 13 such as a memory card via the recording medium reading unit 14. These program modules 21 to 27 cannot be rewritten.

[0032] In memory 20, in addition to such areas that cannot be modified by the user, there is also a writable data area 29 for storing data that can be modified.

[0033] CPU12 is an example of one or more processors capable of executing program modules 21 to 27, and controlling the operation of various parts of the circuit according to each program module 21 to 27.

[0034] The storage device 30 includes an operator database 31, a status information database 32, and a reference time database 33.

[0035] The operator database 31 stores, for example, the operator IDs (e.g., employee numbers, etc.) of each operator 100 in the factory.

[0036] The status information database 32 stores the sensing information from each sensor 110 installed on each operator 100 as status information representing the status of each operator 100, and associates it with time information, operator ID, and sensor ID.

[0037] Additionally, the status information database 32 can store sensing information from sensors 110, such as cameras, located near or around the operator 100, along with time information, operator ID, and sensor ID as status information for each operator 100. However, in this case, the sensor 110 is not installed on the operator 100, but the operator ID of the operator 100 located near the sensor 110 is associated with the sensor ID, for example, the operator 100 located within a predetermined distance.

[0038] The status information can include the location information of the operator 100, activity information indicating whether the operator 100's hands are moving, information indicating the operating status of the equipment around the operator 100, movement information indicating whether the operator 100 is moving, the operator 100's vital signs, the operator 100's voice information, the sound information around the operator 100, and the image information around the operator 100.

[0039] Furthermore, the status information database 32, as status information, includes not only the sensing information obtained from the sensor 110 (including the camera 115) (hereinafter also referred to as "first status information"), but also the status information that has undergone mathematical operations based on the sensing information (first status information) (hereinafter also referred to as "second status information"), which is also stored in association with time information, operator ID, and sensor ID as status information representing the status of each operator 100. The status information is not limited to the sensing information from the sensor 110 (first status information), but may also include image information from the camera 115, such as signals from rotating warning lights.

[0040] The status information can be obtained not only as sensing information sent from the sensors 110 installed on each operator 100 and the camera 115 set at a fixed point and controlled by the microcontroller 120, but also as the second status information obtained from the aforementioned first status information, based on the sensing information.

[0041] For each operator 100, not limited to one type, multiple types of sensors 110 can be installed.

[0042] The sensor class, including these sensors 110 and cameras 115, is an IoT device used to visualize the operator's movements. Specific types include, but are not limited to, position sensors that determine the position of the operator 100 via GPS, WiFi, Bluetooth (registered trademark), or beacon 125; accelerometers that detect the movement of the operator 100's hands; vital sign sensors that measure vital signs such as the operator 100's pulse; microphones that detect the operator 100's voice; sound sensors that detect the sounds around the operator 100; and cameras that are installed on the operator and capture images in the operator 100's line of sight.

[0043] These sensors are mounted on the front of the operator 100's body, on the left and right sides of the waist, arms, wrists, head, shoulders, ears, and head in a manner that facilitates the reception of radio waves from the beacon 125. In addition, sensors 110, which acquire activity information, such as the aforementioned accelerometer, are mounted on the operator 100's dominant arm or dominant hand.

[0044] As a position sensor, wearable terminals, including smartphones, can also be used. In this case, the smartphone is placed in a waist support and secured with a belt, or it is attached to a loop by a hook. If the installation position is on the back, the communication unit 15 may have difficulty receiving signals from the smartphone, so it is best to install the smartphone in front of the operator 100, on either side of the waist. Alternatively, it can be carried through the operator 100's trouser pocket or breast pocket.

[0045] As a vital signs sensor, a wristband-side device can be used. In this case, when the device is installed on both arms or both hands of the operator 100, it may cause obstacles to the operation. Therefore, in order to capture the operator 100's activities and work content in detail with minimal structure, it is preferable to install the vital signs sensor on the operator 100's dominant arm or the arm or wrist of the dominant hand.

[0046] As a sound sensor, a headset-type device can be used. In this case, it can be worn on the operator's head or placed on the shoulder.

[0047] As a sound sensor, an earphone-type device can be used. In this case, it can be installed in the ear of operator 100 for use.

[0048] As a camera sensor, a smart glasses-type device can be used. In this case, it can be installed on the head of the operator 100 for use.

[0049] Additionally, although not installed on operator 100, fixed-point cameras 115 are also included in the sensor class, but are not limited to these.

[0050] Figure 2B This is a conceptual diagram illustrating an example of the connection between a job content analysis device and other devices (including equipment).

[0051] use Figure 2B This describes the method for obtaining the operating information of the equipment surrounding operator 100 in the status information.

[0052] Figure 2B The connection relationship shown is in place of Figure 2A The camera 115 shown differs from the device 116 in this respect, but the rest of the structure is the same. Therefore, the following description is the same as... Figure 2A The differences.

[0053] Device 116 is controlled by microcontroller 120, which then sends the operating information of device 116 to communication unit 15. Additionally, sensors (not shown) for acquiring operating information can be installed on device 116, and the operating information acquired from these sensors can be sent to communication unit 15.

[0054] In this way, the work content analysis device 10 can obtain the operating information of the equipment 116 surrounding the operator 100 as one of the status information.

[0055] Figure 2C This is a block diagram illustrating an example of the circuit structure of a sensor.

[0056] Figure 2C The illustrated block diagram is a general example of the structure of a sensor 110, which includes many types of sensors as described above.

[0057] The sensor 110 generally includes a CPU 1102, a sensing unit 1103, a transmitting unit 1104, a receiving unit 1105, a memory 1110, and a storage device 1120 that are interconnected via a bus 1101.

[0058] CPU12 is a processor that controls the operation of the various parts of the circuits that are interconnected via bus 1101.

[0059] The sensing unit 1103 is the part that acquires sensing information from the operator 100. For example, if the sensor 110 is an accelerometer, the sensing unit 1103 is equivalent to a detection unit that detects acceleration; if it is a vital sign sensor, it is equivalent to a detection unit that detects vital signs such as pulse; if it is a sound sensor, it is equivalent to a sound collection unit that detects sound; if it is a camera, it is equivalent to an image sensor; and if it is a position sensor, it is equivalent to GPS, WiFi, or Bluetooth functionality.

[0060] Sensor 110 can also be a position sensor that determines the position of operator 100 via beacon 125, but in this case, receiver 1105 receives the signal from beacon 125 as sensing information. Furthermore, beacon 125 can change the intensity of the transmitted radio waves.

[0061] When the sensing unit 1103 and the receiving unit 1105 acquire sensing information in this way, they output it to the storage device 1120. The storage device 1120 stores a sensing information database 1221 that stores sensing information, and stores the sensing information output from the sensing unit 1103 and the receiving unit 1105.

[0062] Storage devices 1120 include, for example, SSDs (Solid State Drives), HDDs (Hard Disk Drives), etc.

[0063] The memory 1110 stores the communication determination module 1111 as part of the program of the sensor 110.

[0064] The communication determination module 1111 determines whether the sensor 110 can communicate with the work content analysis device 10.

[0065] If the communication determination module 1111 does not determine that communication between the sensor 110 and the job content analysis device 10 is possible (i.e., if the communication determination module 1111 determines that communication between the sensor 110 and the job content analysis device 10 is not possible), the sensing information continues to be stored in the sensing information database 1221.

[0066] When the communication determination module 1111 determines that communication between the sensor 110 and the job content analysis device 10 is possible, the sending unit 1104 sends the sensing information stored in the sensing information database 1221 to the job content analysis device 10 via the communication network 70 every predetermined unit (e.g., every 5 seconds, every 10 seconds), regardless of whether new sensing information is acquired.

[0067] Furthermore, each sensor 110 is assigned a sensor ID as identification information and associated with the operator ID of the installed operator 100. When the transmitting unit 1104 transmits the sensing information as status information to the job content analysis device 10, it also transmits the sensor ID and the operator ID together.

[0068] Especially when the sensor 110 is a camera 115, the transmitting unit 1104 sends the image information as sensing information along with the sensor ID to the job content analysis device 10.

[0069] If you return to Figure 1 As described above, the communication unit 15 of the job content analysis device 10 is connected to the communication network 70. It receives sensor IDs, operator IDs, and sensing information transmitted from each sensor 110 via the communication network 70, and then sends the received sensor IDs, operator IDs, and sensing information to the processing module 21. Similarly, it receives sensor IDs and image information as sensing information transmitted from the camera 115, and sends the received sensor IDs and image information as sensing information to the processing module 21.

[0070] The communication unit 15 can also, as described later, display charts, etc., displayed by the display control module 26 from the display unit 16 from the external terminal 130, such as... Figure 2A , Figure 2B The data required for the chart display is output to the external terminal 130 via the communication network 70.

[0071] Thus, the sensing information transmitted from sensor 110 as status information includes the operator's position information, activity information related to the operator's hand movements, movement information related to the operator's movement, the operator's vital signs, the operator's voice information, the operator's surrounding sound information, the image information in the operator's line of sight, and the operator's image information. Furthermore, as described later, the processing module 21 can obtain the operator's activity information and position information from the image information from camera 115.

[0072] The status information database 32 is a database used to store status information. It can use time information timed by the internal clock (not shown) of the job content analysis device 10 as time information. In addition, it can also use time information synchronized with the clock (timing unit) of an external system connected to the destination of the job content analysis device 10.

[0073] In addition, if synchronization with the timing unit of the system connected to the destination is not possible, each sensor 110 can also use the time synchronized with the job content analysis device 10, with its own time as the reference time, in order to avoid time deviations between sensors.

[0074] The baseline time database 33 stores the baseline time predetermined for each task. The baseline time is not limited, but can include, for example, the target time that an application can predetermined for each task, or the time taken by a highly skilled person to complete the task.

[0075] The storage device 30 storing these databases 31 to 33 is also similar to the storage device 1120, including, for example, an SSD (Solid State Drive) or an HDD (Hard Disk Drive).

[0076] The processing module 21 receives the sensing information sent from the communication unit 15 along with the sensor ID, and if present, also receives the operator ID, and determines whether the sensing information needs to be processed. Then, it performs the necessary processing on the sensing information requiring processing, obtains status information, and sends the status information, along with the sensor ID and operator ID, to the status information database 32. Conversely, if the sensing information does not require processing, it does not process the sensing information and sends it as status information along with the sensor ID and operator ID to the status information database 32.

[0077] As an example of the sensing information that needs to be processed, there is image information from camera 115. As for processing this image information, for example, AI technology is used to determine the operator 100 captured by the camera, determine the operator ID of operator 100, detect the activity information and position information of the determined operator 100, and use the detected activity information and position information as status information. In this case of processing image information, processing module 21 specifically functions as an image processing module. Additionally, there may be cases where sensing information from an accelerometer is also processed using AI technology. Furthermore, it should be noted that the sensing information that needs to be processed is not limited to these examples.

[0078] When the status information is sent together with the sensor ID and the operator ID, the status information database 32 stores the status information, sensor ID, and operator ID in association with the time information.

[0079] In this way, the job content analysis device 10 can accumulate sensing information sent from the sensor 110 (including the camera 115) as status information. However, sometimes, even though the job content analysis device 10 is functioning normally, it may fail to send sensing information due to communication errors from the sensor 110 (including the camera 115), thus preventing the acquisition of status information. Conversely, sometimes there may be no problem with communication from the sensor 110 (including the camera 115), but due to certain faults within the job content analysis device 10, it may be unable to receive sensing information and acquire status information.

[0080] The determination module 27 determines whether the job content analysis device 10 is operating normally. For example, the determination module 27 can determine whether the job content analysis device 10 is operating normally by monitoring the operation of the CPU 12 and the communication unit 15.

[0081] If the status information cannot be obtained, and the determination module 27 determines that the job content analysis device 10 is normal, the processing module 21 stores the first fixed data (e.g., "0") in the status information database 32 as status information. If the determination module 27 determines that the job content analysis device 10 is abnormal, the processing module 21 stores the second fixed data (e.g., "-1") in the status information database 32 as status information. Furthermore, the data can be not only "0" but also strings such as "NULL".

[0082] By storing such fixed data in the state information database 32, the following actions can be achieved.

[0083] For example, let's take the case where the status information is sensor information indicating the operating status of device 116 as an example. Conventionally, when sensor information indicating the operating status as "1" is received from the sensors of monitoring device 116, "1" is stored as status information in the status information database 32. Therefore, the job content analysis device 10 determines that device 116 is operating.

[0084] However, in this case, if no sensing information is received, the status information is not stored. Therefore, even if the job content analysis device 10 is functioning normally, but sensing information cannot be received due to, for example, a communication error from the sensor of the monitoring device 116, or conversely, even if there is no problem in communication from the sensor, sensing information cannot be received due to a malfunction of the job content analysis device 10, the status information is not stored.

[0085] Figure 3A This is an example, arranged in time series, of the state information (sensor information representing the operating state of a device) previously stored in the state information database 32 in such a situation.

[0086] For example, in the first four time periods, no status information is stored, so the status information is represented as (none). Then, in the next three consecutive time periods, status information is received, so "1" is stored in the status information database 32, then becomes (none), then "1" is stored again, then becomes (none).

[0087] In the case where no status information is stored in the status database 32, it is completely unclear whether the problem lies with the job content analysis device 10 or outside the job content analysis device 10.

[0088] In contrast, in this embodiment, if the determination module 27 determines that the job content analysis device 10 is normal, but status information cannot be obtained, the processing module 21 stores "0 (zero)" in the status information database 32 as status information. On the other hand, if the determination module 21 determines that the job content analysis device 10 is malfunctioning, and status information cannot be obtained, the processing module 21 stores "-1" in the status information database 32 as status information. Furthermore, it can be not only "0 (zero)" but also strings such as "NULL".

[0089] Figure 3B This is an example of state information (sensor information representing the operating state of the device) stored in the state information database in this embodiment, shown in chronological order.

[0090] like Figure 3B As shown, in this embodiment, such a situation disappears. Furthermore, when... Figure 3B and Figure 3A When making comparisons, Figure 3A The first two (none) shown are in Figure 3B The value is represented as "-1". This indicates that the status information could not be obtained due to a malfunction in the work content analysis device 10. Additionally, Figure 3A The other four shown (none) are in Figure 3B The value in the middle is represented as "0". This indicates that although the work content analysis device 10 is functioning normally, it has failed to acquire status information.

[0091] In another example of processing, processing module 21 performs mathematical operations on one or more of the first state information from multiple state information sets to obtain second state information. Then, the first and second state information sets are stored in the state information database 32. This allows other state information to be derived from one state information set.

[0092] As a mathematical operation, averaging and majority voting can be employed. The following description uses the application of sensed information representing location information as an example of employing averaging and majority voting as mathematical operations.

[0093] Figure 4A This is a graph showing an example of the time-series changes in sensed information representing area numbers as location information.

[0094] exist Figure 4A In the example shown, the ten sensing data points, arranged in time sequence, represent the position information detected per second by the sensor 110 installed on operator 100. The numbers indicate the area numbers. That is, Figure 4A The area number where operator 100 is located during a 10-second period is shown every second. According to this example, it is shown that operator 100 is in area 1 for the first second, but moves to area 2 after 1 second, and then returns to area 1 after 1 second, and then moves rapidly between area 1, 2 and 3 every second.

[0095] However, false detections are known to frequently occur in position detection. Furthermore, in reality, it is difficult to assume that the operator's position 100 moves frequently between three areas in a short period of time. Therefore, when using sensor information representing position information as status information, it is best not to use the raw data directly, but rather to perform calculations such as averaging the sensor information over arbitrary fixed periods like 10 seconds or using majority voting to determine the status information.

[0096] Figure 4B It shows that by... Figure 4A The diagram shows an example of state information determined by performing computational processing on the sensed information.

[0097] exist Figure 4A In the example shown, within a 10-second interval, the location information represents region 1 at most 6 times. Therefore, in cases like 1→2→1, the initial and final regions 1 are correctly identified and determined. On the other hand, region 2 in the middle is unrealistic and should be considered as region 1, so it is corrected as in 1→1→1. Furthermore, in cases like 1→2→3→1, the initial and final regions 1 are correctly identified and determined. Therefore, regions 2 and 3 in the middle are also unrealistic and should be considered as region 1, so they are corrected as in 1→1→1→1.

[0098] Through such computational processing, it is possible to extract from representations such as Figure 4A The time series sensing information shown is obtained as follows Figure 4B The time series shown contains state information.

[0099] Furthermore, although not illustrated, but related to Figure 4ASimilarly, when the location information represents the most cases of region 1, and the location information represents a time sequence like 1→2→2→1, the initial and final regions 1 are judged and determined to be correct. However, when region 1 is close to region 2, it is possible to move from region 1 to region 2, stay for 2 seconds, and then return to region 1. Therefore, it can be directly set as 1→2→2→1.

[0100] If you return again Figure 1 As described above, the estimation module 22 estimates the work content performed by the operator 100 based on at least two status information items associated with the same time in the status information of the operator 100 stored in the status information database 32. Furthermore, in this specification, the work content includes, for example, not only useful work and incidental work such as manual work and moving work such as moving a handcart, but also non-useful work such as simple walking, staying still, and resting.

[0101] For example, when inferring the work content of operator 100 (#1), the prediction module 22 takes the status information associated with operator ID of operator 100 (#1) stored in the status information database 32 as an object. Then, based on the time information associated with the status information and the sensor ID associated with the status information, focusing on at least two status information associated with the same time, it predicts the work content performed by operator 100 (#1). In addition, the at least two status information associated with the same time, such as operator 100 (#1) in this example, are not only the status information of one operator, but can also be set as the status information of multiple operators, such as operator 100 (#1) and other operators 100 (#2) in this example.

[0102] As an example of a case where at least two status information sources are from a single operator (e.g., operator 100(#1)), the case of position information from an operator's position sensor and acceleration information from an acceleration sensor is illustrated. In this case, if the position information indicates a work area and the acceleration information indicates a value greater than a predetermined value (indicating hand activity for manual work), then the estimation module 22 can infer that the work performed by operator 100(#1) is manual work.

[0103] On the other hand, if the position information remains unchanged and the acceleration information does not show an acceleration greater than a predetermined value (a state where the hand is almost motionless), then the inference module 22 can infer that the operator 100(#1) is stationary, i.e., not performing any work. In this case, time information is also considered, so if it is within the rest period of operator 100(#1), it can be inferred that operator 100(#1) is resting; if it is not within the rest period, it can also be inferred that operator 100(#1) is in a waiting state.

[0104] Furthermore, as another example where at least two status information points originate from a single operator (e.g., operator 100(#1)), if the position information changes over time while the acceleration information remains constant, the inference module 22 can infer that operator 100(#1) is in the process of moving. However, in this case, it is impossible to distinguish whether operator 100(#1) is moving for a task such as pushing a handcart, or simply walking. In such a case, the inference module 22 can further consider the sound from the microphone as well as the status information, and distinguish whether operator 100(#1) is performing a handcart movement task or simply walking based on whether sound accompanying the movement of the handcart is detected.

[0105] As an example of cases where at least two status information sources are from multiple operators (e.g., two operators, operator 100(#1) and operator 100(#2)), the case of location information from operator 100(#1)'s position sensor and audio information from a microphone, and the case of location information from operator 100(#2)'s position sensor and audio information from a microphone are described. In this case, if the location information of operator 100(#1) and operator 100(#2) indicates that they are in the same work area, and based on the audio information of operator 100(#1) and operator 100(#2), operator 100(#1) and operator 100(#2) are having a work-related conversation, then the inference module 22 can infer that operator 100(#1) and operator 100(#2) are working together, and can further infer the work content based on the content of the conversation.

[0106] As another example of a case where at least two status information are from multiple operators (e.g., operator 100(#1) and operator 100(#2)), at least one of the following information can be used: operator 100's position information, activity information indicating whether operator 100's hand is moving, and information indicating the operating status of equipment surrounding operator 100.

[0107] By using location information and activity information, it is possible to infer the content of work at each work site.

[0108] By using location information and equipment information, it is possible to predict the actions of operator 100 that match the operating status.

[0109] By using both activity information and equipment information, it is possible to predict the work of operator 100 that matches the operating status.

[0110] Furthermore, regarding the three scenarios mentioned above, data from groups comprising 100 operators can be used to infer the operations performed in these groups.

[0111] Furthermore, the above is merely an example. The prediction module 22 can predict various job contents based on combinations of other status information. Then, the predicted job contents are associated with the corresponding status information and stored in the status information database 32.

[0112] The determination module 23 determines the operation time for the operation content predicted by the prediction module 22 based on the status information of the operator 100 stored in the status information database 32 and the time information associated with the status information. For example, if the prediction module 22 predicts that a manual operation will be performed, the operation time for the manual operation will be determined from the time corresponding to the time information corresponding to the start time of the manual operation to the time corresponding to the time information corresponding to the end time of the manual operation. Then, the operation time determined in this way is associated with the corresponding status information and stored in the status information database 32.

[0113] The task time comparison module 24 compares the task time predicted by the prediction module 22 with the task time determined by the determination module 23 and the reference time stored in the reference time database 33. This comparison result can be set as the difference between the task time and the corresponding reference time. For example, if the prediction module 22 predicts a manual task as the task content, the determination module 23 determines the task time to be 30 minutes, and the reference time database 33 stores 33 minutes as the reference time for the manual task, the task time comparison module 24 obtains a comparison result of the manual task being the reference time + 3 minutes. Alternatively, the comparison result can also be set as a percentage relative to the reference time (in this case, reference time + 10%) instead of a difference.

[0114] The analysis module 25 uses the comparison results based on the work time comparison module 24, the information stored in the status information database 32 and the reference time database 33 to analyze the work content of the operator 100 from various perspectives.

[0115] The display control module 26 displays charts and other graphs representing the results of various analyses performed by the analysis module 25 from the display unit 16, or additionally from an external terminal 130 via the communication network 70. These charts may include, for example, comparison results of work times obtained by the work time comparison module 24, and actual work performance graphs generated based on time periods determined by the determination module 23.

[0116] Specific examples of the analysis performed by the analysis module 25 and the analysis results displayed by the display control module 26 will be described later.

[0117] Next, an example of the operation of a job content analysis device that applies the job content analysis method of the first embodiment configured as described above will be explained.

[0118] Figure 5 This is a flowchart illustrating an example of the operation of a job content analysis device that applies the job content analysis method of the first embodiment.

[0119] To analyze the work content of operator 100, sensors 110 need to be installed on each operator 100. For each operator 100, it is not limited to one type; multiple types of sensors 110 can be installed.

[0120] These sensors 110 are IoT devices used to visualize the actions of the operator 100. Examples include, but are not limited to, position sensors that determine the position of the operator 100 via GPS, WiFi, Bluetooth or beacon 125, accelerometers that detect the movement of the operator 100's hands, vital signs sensors that measure vital signs such as the operator 100's pulse, microphones that detect the operator 100's voice, sound sensors that detect the sounds around the operator 100, and cameras that capture images in the line of sight of the operator 100.

[0121] In addition, in order to analyze the work content of operator 100, image information from fixed-location camera 115 and sensing information from sensors installed on device 116 can also be used.

[0122] Each sensor 110 is assigned a unique sensor ID, and the operator ID of the installed operator 100 is also associated with it. Camera 115 is assigned a unique sensor ID.

[0123] The sensing information measured by the sensors installed on the operator 100 and the equipment 116, together with the sensor ID and the operator ID, is sent from the sensor 110 to the job content analysis device 10 via the communication network 70. The image information, which is the sensing information measured by the camera 115, is sent to the job content analysis device 10 along with the sensor ID via the communication network 70. (S1)

[0124] The sensing information sent to the job content analysis device 10, along with the sensor ID, is received by the communication unit 15. If present, the operator ID is also received by the communication unit 15, and then sent from the communication unit 15 to the processing module 21. In the processing module 21, it is determined whether the sensing information needs to be processed (S2).

[0125] Then, if the sensing information needs to be processed (S2: Yes), the processing module 21 performs the necessary processing on the sensing information and obtains state information from the sensing information (S3).

[0126] In step S2, as an example of sensing information to be processed, there is image information from camera 115. As for processing this image information, in processing module 21, for example, AI technology is used to determine the operator 100 captured by the camera from the image information, determine the operator ID of operator 100, detect the activity information and location information of the determined operator 100, and set the detected activity information and location information as status information.

[0127] In this way, the processing module 21 can function specifically as an image processing module.

[0128] Furthermore, the processing module 21 can also use AI technology to process and manipulate the sensing information from the accelerometer. Moreover, the sensing information that needs to be processed by the processing module 21 is not limited to these.

[0129] This status information, along with the sensor ID and operator ID, is sent from the processing module 21 to the status information database 32 (S4).

[0130] Examples of sensing information that needs to be processed include image information from camera 115 and sensing information from accelerometer.

[0131] When processing image information from camera 115, processing module 21 functions as an image processing module. Then, in processing module 21, for example, AI technology is used to determine the operator 100 captured by the camera from the image information, determine the operator ID of operator 100, detect the activity information and location information of the determined operator 100, and set the detected activity information and location information as status information.

[0132] In addition, when processing the sensing information from the accelerometer, the processing module 21 performs processing and manipulation using AI technology, for example, to obtain state information.

[0133] On the other hand, if the sensing information does not require processing (S2: No), the processing module 21 does not perform any processing on the sensing information, and the sensing information is sent to the status information database 32 as status information along with the sensor ID and the operator ID (S5).

[0134] In the status information database 32, the status information, sensor ID, operator ID and time information sent in steps S4 and S5 are associated and stored (S6).

[0135] Furthermore, the determination module 27 continuously monitors the operation of the CPU 12 and the communication unit 15, and continuously determines whether the job content analysis device 10 is operating normally. Correspondingly, if the determination module 27 determines that the job content analysis device 10 is operating normally, but status information cannot be obtained, the processing module 21 stores "0" in the status information database 32 as status information. On the other hand, if the determination module 27 determines that the job content analysis device 10 is not operating normally, and status information cannot be obtained, such as... Figure 3B As illustrated, the processing module 21 stores "-1" in the status information database 32 as status information.

[0136] Furthermore, such as using Figure 4A as well as Figure 4B As explained, the processing module 21 performs calculations as needed to determine the status information.

[0137] Subsequently, in the estimation module 22, the work content performed by the operator 100 is estimated based on at least two status information items associated with the same time in the status information of the operator 100 stored in the status information database 32 (S7). The estimation result is stored in the status information database 32 in association with the corresponding status information.

[0138] In the determination module 23, the operation time (S8) for the operation content predicted by the prediction module 22 is determined based on the status information of the operator 100 stored in the status information database 32 and the time information associated with the status information.

[0139] In the task time comparison module 24, the task content predicted by the prediction module 22 is compared with the task time determined by the determination module 23 and the reference time stored in the reference time database 33 (S9). The comparison result can be set as the difference between the task time and the corresponding reference time or the ratio (percentage) of the task time relative to the reference time. For example, if the prediction module 22 predicts a manual task as the task content, the determination module 23 determines that the task time for the manual task is 30 minutes, and 33 minutes is stored in the reference time database 33 as the reference time for the manual task, the task time comparison module 24 can obtain a comparison result such as the manual task being the reference time + 3 minutes or the reference time + 10%.

[0140] In the analysis module 25, the comparison results, information stored in the status information database 32 and the reference time database 33 are used to analyze the work content of the operator 100 from various perspectives (S10).

[0141] The results of various analyses performed by the analysis module 25 are displayed, for example, in the form of charts by the display control module 26 from the display unit 16, and / or from the external terminal 130 (S11). These charts include, for example, not only comparison results of work times obtained by the work time comparison module 24 and actual work performance charts created based on the time periods determined by the determination module 23, but also graphical displays as described below.

[0142] Figure 6 This is a graphical display example showing the time required for each task.

[0143] Here, as an example, the base time database 33 stores the base time for the main job, the auxiliary job, and other jobs (150 minutes for the main job, 90 minutes for the auxiliary job, and 60 minutes for the others).

[0144] In addition, in the status information database 32, the job content (main job, auxiliary job, others) predicted by the prediction module 22 and the job time (120 minutes, 150 minutes, 120 minutes) of each job content determined by the determination module 23 are stored in association with the status information of the operator 100.

[0145] exist Figure 6 In (a), the cumulative time (in minutes) for each task is divided into baseline time and actual performance time and displayed.

[0146] As mentioned earlier, the reference time database 33 stores 150 minutes, 90 minutes and 60 minutes as the main job, auxiliary job and other reference times. Therefore, the analysis module 25 refers to the reference time database 33 and creates a chart of cumulative reference time according to the job content, as shown in the reference time chart a1.

[0147] Similarly, in the status information database 32, the job content (main job, auxiliary job, others) and the job time (120 minutes, 150 minutes, 120 minutes) of each job content are stored in association with the status information of a certain operator 100. Therefore, the analysis module 25 refers to the status information database 32 and creates a chart of the cumulative job time by job content for operator 100, as shown in the actual performance time chart a2. In addition, next to each job content in the actual performance time chart a2, the difference time (in minutes) between the same job content and the baseline time chart a1 is shown.

[0148] Based on this example, it is shown that for operator 100, the actual time for the main task is 30 minutes shorter than the benchmark time, the actual time for the ancillary task is 60 minutes longer than the benchmark time, and the actual time for other tasks is 90 minutes longer than the benchmark time.

[0149] On the other hand, Figure 6 (b) The time allocation for each task is displayed as a percentage.

[0150] In the baseline time chart b1, the entire time of the baseline time chart a1 is set to 100%. In the actual performance time chart b2, the entire time of the actual performance time chart a2 is set to 100%. The time proportion of each task is displayed as a percentage.

[0151] From this Figure 6 (a) and Figure 6 As shown in the graph in (b), the actual time spent on main tasks, which require only a short period, is lower relative to the overall task time compared to the baseline time. Conversely, the time spent on supplementary tasks and other tasks is not only longer than the baseline time, but also higher relative to the overall task time. Therefore, to improve task efficiency, it is necessary to further increase the time spent on main tasks and complete supplementary tasks and other tasks in a shorter time, which clarifies the specific coping strategies.

[0152] By visualizing the work process through such graphical representations, hidden waste can be identified. This clarifies specific areas for improvement, enabling the efficient development of improvement plans.

[0153] Furthermore, if productivity increases as a result of this improvement, production and allocation costs will also be reduced, thus the effect of cost reduction can be expected.

[0154] Figure 7 It is a flowchart used to illustrate the process of business improvement.

[0155] As described above, according to the job content analysis apparatus that applies the job content analysis method of the first embodiment, such as Figure 7 As shown in the flowchart, sensing information from sensors 110 installed on operator 100 and equipment 116, and fixed-point cameras 115 (S21) is acquired to collect various status information related to the operation (S22), which is then stored in the status information database 32 (S23) and various analyses are performed (S24). Through the results of this analysis, the operation content is visualized, hidden waste in the operation is identified, and specific and effective improvement plans for improving productivity can be designed (S25).

[0156] In this way, the job content analysis device 10 does not require personnel to acquire sensing information, nor does it require any modification to the equipment on the factory side, and can analyze job content.

[0157] Then, by implementing the improvement plan (S26), as an effect, if an increase in productivity is measured (S27), production costs and allocation costs will also be suppressed, so the effect of cost reduction can also be expected.

[0158] (Second Implementation)

[0159] This describes a job content analysis apparatus that applies the job content analysis method of the second embodiment.

[0160] Individual operators' work content analysis may also be subject to personal attacks. Moreover, in such cases, individuals may lose their motivation to produce results, making it difficult for them to accept the truthful analysis findings and ultimately hindering productivity improvements.

[0161] On the other hand, as long as the evaluation is not an individual's assessment but rather a group assessment, it will not be considered a personal attack, making the results of the job content analysis more acceptable. Consequently, the sense of coordination within the group is enhanced, and therefore, increased productivity can be expected.

[0162] When a group includes multiple operators forming a work team, there may be multiple operators performing the same task such as inspection or assembly, or multiple operators with different responsibilities such as a foreman or inspection supervisor.

[0163] Therefore, a job content analysis device that applies the job content analysis method of the second embodiment performs job content analysis, for example, on a group basis, such as a job team.

[0164] Therefore, in this embodiment, each operator belongs to any pre-classified group. Unlike the first embodiment, the work content analysis is not performed on an operator-by-operator basis, but on a group-by-group basis.

[0165] The structure of the job content analysis device that applies the job content analysis method of this second embodiment can be used... Figure 1 To illustrate, please refer to the following. Figure 1 Instead of repeating the description, I will explain the differences from the first embodiment.

[0166] In this embodiment, each operator 100 is classified into any group. For example, the group can be set as a work group that performs the work.

[0167] Correspondingly, the operator ID of each operator 100 not only includes identification information that identifies the operator 100, but also group information that specifies the group to which the operator 100 belongs. For example, if a pre-assigned group number is used as the group information, the operator ID can be set as a number formed by concatenating the employee number and the group number.

[0168] Therefore, the operator database 31 stores an operator ID for each operator 100, which includes identification information that identifies the operator and identification information that specifies the group to which the operator belongs. Similarly, the status information stored in the status information database 32 along with the time information is also stored in association with such operator IDs.

[0169] The estimation module 22 estimates the work content performed by the group based on at least two status information items associated with the same time from the status information of multiple operators 100 belonging to the same group stored in the status information database 32.

[0170] For example, as an example where at least two status information items are from two operators 100(#1) and 100(#2) belonging to the same group, the case of position information from operator 100(#1)'s position sensor and audio information from a microphone, and the case of position information from operator 100(#2)'s position sensor and audio information from a microphone are described. In this case, if it indicates that the position information of operator 100(#1) and operator 100(#2) are both within the work area, and based on the audio information of operator 100(#1) and operator 100(#2), operator 100(#1) and operator 100(#2) are having a work-related conversation, then the inference module 22 can infer that the group is in the process of work, and can further infer the work content based on the content of the conversation.

[0171] Furthermore, the above is merely an example. The estimation module 22 can infer various tasks performed by the group based on a combination of other status information from multiple operators belonging to the same group. Then, the estimation results are associated with the status information of the corresponding operator 100 and stored in the status information database 32.

[0172] The determination module 23 determines the work time corresponding to the work content predicted by the prediction module 22 based on the status information of multiple operators 100 belonging to the same group stored in the status information database 32. For example, if the prediction module 22 predicts that manual work is to be performed in this group, the time period from the time information corresponding to the start time of the manual work to the time information corresponding to the end time of the manual work is determined as the work time spent on the manual work. Then, the work time determined in this way is associated with the status information of the corresponding operator 100 and stored in the status information database 32.

[0173] Similar to the first embodiment, the task time comparison module 24 compares the task time determined by the determination module 23 with the reference time stored in the reference time database 33 regarding the task content inferred by the estimation module 22.

[0174] The analysis module 25 analyzes the work content of the group based on the work content predicted by the prediction module 22 and the work time determined by the determination module 23. Alternatively, it analyzes the work content of each operator 100 belonging to the group based on the work content predicted by the prediction module 22 and the work time determined by the determination module 23, and then analyzes the work content of the group as a whole based on the results.

[0175] Next, an example of the operation of a job content analysis device that applies the job content analysis method of the second embodiment configured as described above will be explained.

[0176] Figure 8 This is a flowchart illustrating an example of the operation of a job content analysis device that applies the job content analysis method of the second embodiment.

[0177] exist Figure 8 In China, regarding and Figure 5 Use the same processing steps with the same step numbers to avoid repetitive explanations and to describe different content.

[0178] Each operator 100 is equipped with one or more types of sensors 110, similar to the first embodiment. Additionally, similar to the first embodiment, a camera 115 is fixedly installed.

[0179] Each sensor 110 is assigned a sensor ID, which is associated with the operator ID. However, the operator ID contains not only the identification information of the operator 100, but also the identification number of the group to which the operator 100 belongs.

[0180] Therefore, the following, in Figure 5 The description states that the operator ID includes not only the identification information of operator 100, but also the identification number of the group to which operator 100 belongs.

[0181] In the estimation module 22, the work content performed by the group is estimated based on at least two status information that are associated with the same time in the status information of multiple operators 100 belonging to the same group stored in the status information database 32 (S7a).

[0182] In the determination module 23, the operation time (S8a) of the operation content inferred by the inference module 22 is determined based on the status information of multiple operators 100 belonging to the same group stored in the status information database 32.

[0183] In the job time comparison module 24, similarly to the first embodiment, the job time determined by the determination module 23 and the reference time stored in the reference time database 33 are compared with the job content estimated by the estimation module 22 (S9a).

[0184] In the analysis module 25, the work content of the group is analyzed based on the work content predicted by the prediction module 22 and the work time determined by the determination module 23. Alternatively, the work content of each operator 100 belonging to the group is analyzed based on the work content predicted by the prediction module 22 and the work time determined by the determination module 23, and then the work content of the group as a whole is analyzed based on the results (S10a).

[0185] Similar to the first embodiment, the analysis can also be performed from various perspectives using information stored in the status information database 32 and the reference time database 33.

[0186] Regarding this group, charts representing the various analysis results performed by the analysis module 25 are displayed by the display control module 26 from the display unit 16 and the external terminal 130 (S11a).

[0187] The following describes an example of a graphic display from the display unit 16 and / or the external terminal 130, based on the analysis results from the analysis module 25.

[0188] Figure 9 This is a graphical example showing the frequency and duration of entry into each area of ​​the factory by all operators within the group.

[0189] Figure 9 (a) shows the cumulative time that operator 100 spends in each area A-J within one day (or one week) for manual work. Figure 9 In (a), the vertical axis represents cumulative time, and the horizontal axis represents the region.

[0190] according to Figure 9 (a) indicates that in area D, the workers belonging to this group spent a total of 6 hours and 15 minutes on manual tasks. Furthermore, according to... Figure 9 (b) It can be seen that as a breakdown of 6 hours and 15 minutes, operator X has 3 hours and 33 minutes, operator Y has 1 hour and 24 minutes, and operator Z has 1 hour and 18 minutes.

[0191] Figure 9 (c) shows the following according to Figure 9 (a) shows the results categorized into three types based on the proportion of stay time in each region relative to the total cumulative time of the entire region (regional concentration). Figure 9 (c) shows the areas schematically according to their actual layout within the factory. Figure 9 As shown in example (c), for manual operations, only region D has a regional concentration of over 21%, only region I has a regional concentration of less than 4%, and the regional concentration of other regions ranges from 5% to 20%.

[0192] In addition, such as Figure 9 As shown in (a), not only manual operations, but also operations can be performed according to the various tasks of operator 100, such as trolley operations, walking, and stationary operations. Figure 9 That kind of display.

[0193] This display allows for visualization of the actual on-site actions within a group, such as which area the operators are concentrated in / not concentrated in during which operation, and which person in charge has a heavy / light workload.

[0194] Figure 10 This is another example showing a comparison of actual performance on tasks between people with high and low proficiency.

[0195] Figure 10 This is a graphical display example that shows the actual results of the task in detail according to the task content and time.

[0196] As assignment content, in this example, it is categorized into main assignment, supplementary assignment, and other.

[0197] Figure 10 (a) The vertical axis represents cumulative time. Figure 10 (b) The vertical axis represents the time percentage.

[0198] For example, comparing the actual performance of a person with high proficiency, such as an experienced worker, with that of a person with low proficiency, such as a beginner. Figure 10 (a) and Figure 10 (b) shows that compared to experienced operator X, novice operator Y has a longer total working time, a lower proportion of main tasks, and a higher proportion of incidental and other tasks. Therefore, the improvement project to enhance the work efficiency of novice operators can be specifically defined as reducing the proportion of incidental and other tasks and increasing the proportion of main tasks, thereby shortening the total working time.

[0199] As described above, the work content analysis apparatus that applies the work content analysis method of the second embodiment can perform the work content analysis performed on each individual operator in the first embodiment on a group basis.

[0200] Therefore, individual operators will not be criticized, making them more receptive to the analysis results and the areas for improvement identified. Consequently, each operator will actively strive to improve their work, fostering a sense of coordination within the group. This leads to increased communication within the group, or the expectation of proactive efforts to improve work processes, such as changing work sequences or layouts, thus enhancing group activity.

[0201] Moreover, there is high expectation that this will lead to cost reductions, such as increased productivity and reduced production and allocation costs.

[0202] Furthermore, the above explains how to improve work efficiency by focusing on the work time and work time details of experienced workers. However, in addition to this, we can also focus on the movement locations of experienced workers (e.g., experienced workers perform tasks in this location, but beginners do not) and movement paths (experienced workers move along this path, but beginners move along other paths) to improve work efficiency.

[0203] While some embodiments have been described, these embodiments are presented by way of illustration only and are not intended to limit the scope of the invention. In fact, the new embodiments described herein can be embodied in various other ways, and thus, various omissions, substitutions, and changes can be made to the embodiments described herein without departing from the spirit of the invention. The claims and their equivalents are intended to cover any form or modification falling within the scope and spirit of the invention.

Claims

1. A work content analysis device, which analyzes the work content of an operator based on the operator's status, comprising: The first database stores status information representing the status of one or more operators in association with time information and the operator's identification information. The status information includes at least one of the following: the operator's location information, activity information indicating whether the operator's hand is moving, and information indicating the operating status of the equipment around the operator. The estimation unit estimates the content of the work performed by the operator based on at least two status information stored in the first database that are associated with the same time. The determination unit determines the estimated operation time for the operation content based on the status information stored in the first database and the time information associated with the status information. The analysis department analyzes the work content based on the predicted work content and the determined work time; The determination unit determines whether the work content analysis device is operating normally; as well as If the processing unit cannot obtain the status information, and the determination unit determines that the job content analysis device is normal, then the first fixed data is stored in the first database as the status information; if the determination unit determines that the job content analysis device is malfunctioning, then the second fixed data is stored in the first database as the status information. The processing unit further obtains second state information by averaging or majority voting on one or more of the multiple state information, and stores the first state information and the second state information in the first database.

2. The work content analysis device according to claim 1, wherein, The status information is acquired by sensors installed on the operator or placed around the operator and stored in the first database.

3. The work content analysis device according to claim 2, wherein, The first database stores the sensor in association with the identification information of the operator on which the sensor is installed, or stores the sensor in association with the identification information of the operator within a predetermined distance from the location where the sensor is installed.

4. The work content analysis device according to claim 1, wherein, It also has: The second database stores a pre-determined baseline time for each of the aforementioned tasks; and The task time comparison unit compares the estimated task content with the determined task time and the corresponding reference time.

5. The work content analysis device according to claim 4, wherein, The comparison result includes the difference or ratio between the operation time and the corresponding baseline time.

6. The job content analysis device according to claim 5, wherein, The job content analysis device also includes a display control unit, which displays the difference or the ratio for each job content.

7. The work content analysis device according to claim 5, wherein, The analysis unit then analyzes the operator's work content based on the difference or the ratio.

8. The work content analysis device according to claim 1, wherein, The job content analysis device also includes a display control unit, which displays the analysis results based on the analysis unit.

9. The work content analysis device according to claim 8, wherein, The determining unit then determines the time period corresponding to the inferred task content based on the status information stored in the first database. The display control unit displays the actual performance chart of the task content on the time axis as the analysis result, based on the determined time period.

10. The work content analysis device according to claim 1, wherein, The status information also includes at least one of the following: movement information indicating whether the operator has moved, the operator's vital signs, the operator's voice, the operator's surrounding sound information, and the operator's surrounding image information.

11. The work content analysis device according to claim 1, wherein, The time information stored in the first database is synchronized with the timing unit of the system connected to the destination of the job content analysis device.

12. The work content analysis device according to claim 1, wherein, The work content inferred by the aforementioned inference department includes the operator's rest period.

13. A work content analysis device, which analyzes the work content of an operator based on the operator's status, comprising: The first database stores status information representing the status of one or more operators in association with time information and the operator's identification information. The status information includes at least one of the following: the operator's location information, activity information indicating whether the operator's hand is moving, and information indicating the operating status of the equipment around the operator. The estimation unit estimates the content of the work performed by the operator based on at least two status information stored in the first database that are associated with the same time. The determination unit determines the estimated operation time for the operation content based on the status information stored in the first database and the time information associated with the status information. The analysis department analyzes the work content based on the predicted work content and the determined work time. The operators belong to any pre-classified group. The identification information includes group information specifying the group to which the operator belongs. The estimation unit estimates the work content performed by the group based on at least two status information entries stored in the first database that are associated with the same time from the status information of operators belonging to the same group. The determining unit determines the estimated time required for the task based on the status information of operators belonging to the same group stored in the first database. The analysis unit analyzes the task content of the group based on the inferred task content and the determined task time. A second state information is obtained by averaging or majority voting on one or more of the stated state information, and the first and second state information are stored in the first database.

14. A method for analyzing work content, implemented by a work content analysis device to analyze the work content of an operator based on the operator's status. The job content analysis device performs: Status information representing the status of one or more operators is associated with time information and the operator's identification information and stored in a database. The status information includes at least one of the following: the operator's location information, activity information indicating whether the operator's hand is moving, and information indicating the operating status of the equipment around the operator. Based on at least two status information items stored in the database that are associated with the same time, the content of the work performed by the operator can be inferred. Based on the status information stored in the database and the time information associated with the status information, the estimated time spent on the task is determined. Based on the inferred task content and the determined task time, analyze the task content; Determine whether the work content analysis device is operating normally; as well as If the status information cannot be obtained, and the job content analysis device is determined to be normal, then the first fixed data is stored in the database as the status information; if the job content analysis device is determined to be malfunctioning, then the second fixed data is stored in the database as the status information. A second state information is obtained by averaging or majority voting on one or more of the stated state information, and the first and second state information are stored in the database.

15. A recording medium containing a program applied to a job content analysis device for analyzing an operator's job content based on the operator's state, wherein... The program is used to enable the computer to perform the following functions: Status information representing the status of one or more operators is associated with time information and the operator's identification information and stored in a database. The status information includes at least one of the following: the operator's location information, activity information indicating whether the operator's hand is moving, and information indicating the operating status of the equipment around the operator. Based on at least two status information items stored in the database that are associated with the same time, the content of the work performed by the operator can be inferred. Based on the status information stored in the database and the time information associated with the status information, the estimated time spent on the task is determined. Based on the inferred task content and the determined task time, analyze the task content; Determine whether the work content analysis device is operating normally; as well as If the status information cannot be obtained, and the job content analysis device is determined to be normal, then the first fixed data is stored in the database as the status information; if the job content analysis device is determined to be malfunctioning, then the second fixed data is stored in the database as the status information. A second state information is obtained by averaging or majority voting on one or more of the stated state information, and the first and second state information are stored in the database.

Images