Work support system, portable terminal, work support method and work support program

Abstract

In a work support system for supporting work of an operator carrying a portable terminal, the communication volume of the portable terminal is reduced. The work support system comprises: a portable terminal; and a support server that communicates with the portable terminal and supports the work of the operator carrying the portable terminal, wherein a control unit of the portable terminal determines the work action of the operator based on condition information specified for each work content of the operator, and changes the type of data sent from the portable terminal to the support server when it is determined that the work action of the operator is out of a range specified based on the condition information.

Description

Technical Field

[0001] The present disclosure relates to a work support system, a portable terminal, a work support method, and a work support program. Background Art

[0002] At various manufacturing sites such as chemical plants, on-site workers carry portable terminals such as wearable terminals to send voice data or dynamic image data obtained at the manufacturing site to remote supporters in real time. As a result, when on-site workers perform various operations, instructions can be sent remotely through voice, allowing on-site workers to perform various operations smoothly.

[0003] <Prior Art Literature>

[0004] <Patent Documents>

[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-177471 Summary of the invention

[0006] <Problems to be Solved by the Invention>

[0007] However, if the on-site operator and the remote supporter are configured to continuously send and receive dynamic image data or audio data, the communication volume will increase, resulting in communication costs, and the battery capacity of the portable terminal may be insufficient. On the other hand, the supporter does not need to continuously monitor the audio data or dynamic image data sent from the on-site operator's portable terminal, for example, when the on-site operator is moving. In addition, the on-site operator does not need to continuously receive audio instructions from the supporter during the operation, and there are also operations that do not require audio instructions from the supporter.

[0008] The present disclosure reduces the communication traffic of a portable terminal in a work support system that supports work of a worker who carries a portable terminal.

[0009] <Methods used to solve the problem>

[0010] The first aspect of the present disclosure provides a work support system comprising: a portable terminal; and a support server, which communicates with the portable terminal and supports the work of an operator carrying the portable terminal, wherein a control unit of the portable terminal determines the work action of the operator based on condition information specified for each work content of the operator, and changes the category of data sent from the portable terminal to the support server when it is determined that the work action of the operator deviates from the range specified based on the condition information.

[0011] According to the first aspect of the present disclosure, it is possible to reduce the amount of communication of a portable terminal in a work support system that supports work of a worker who carries a portable terminal.

[0012] In addition, the second aspect of the present disclosure is a work support system according to the first aspect, wherein the control unit changes the type of data sent from the portable terminal to the support server from data with a lower communication volume per unit time to data with a higher communication volume per unit time.

[0013] In addition, the third aspect of the present disclosure is a work support system according to the first or second aspect, wherein the control unit determines the work action of the operator based on condition information specified for each work content, including any one of the work time and the start time of the work.

[0014] In addition, the fourth aspect of the present disclosure is a work support system according to the third aspect, wherein the control unit obtains environmental information when the operator is working, and determines the operator's work action based on the condition information relative to the environmental information specified for each work content.

[0015] In addition, the fifth aspect of the present disclosure is a work support system according to the fourth aspect, wherein the environmental information is information obtained by the control unit when the operator is working, and the information obtained by the control unit includes any one of position information, image information, sound information, and acceleration information.

[0016] In addition, the sixth aspect of the present disclosure is a work support system according to the fourth aspect, wherein the condition information is generated based on any one or more of the work performance information for each of the work contents and the environmental information for each of the work contents obtained during the work.

[0017] In addition, the seventh aspect of the present disclosure is a work support system according to the sixth aspect, wherein the condition information is generated for each work content based on an index value of work performance information specified for each work content or an index value of environmental information specified for each work content.

[0018] In addition, an eighth aspect of the present disclosure is the work support system according to any one of the first to seventh aspects, wherein the condition information is generated by causing a learning model to perform learning.

[0019] In addition, the 9th aspect of the present disclosure is a work support system according to the 8th aspect, wherein the control unit obtains environmental information when the operator is working, and the condition information is generated by using the environmental information when the operator is working as input data and using information indicating whether the working action of the operator is normal when the operator is working as correct answer data for learning a learning data set to enable the learning model to learn.

[0020] In addition, the tenth aspect of the present disclosure is a work support system according to the ninth aspect, wherein the condition information is generated for each work content by using the learning data set for each work content to cause the learning model to learn.

[0021] In addition, the 11th aspect of the present disclosure is a work support system according to the 10th aspect, wherein the environmental information of the operator when working is collected when the determination result determined by the control unit is wrong, and the collected environmental information of the operator when working is used to re-learn the learning model of the corresponding work content.

[0022] In addition, aspect 12 of the present disclosure is a work support system according to aspect 8, wherein the control unit obtains environmental information when the operator is working, and the condition information is a rule-based model that uses the environmental information when the operator is working as input data and outputs information indicating whether the working action of the operator is normal when the operator is working.

[0023] A 13th aspect of the present disclosure provides a portable terminal that communicates with a support server that supports an operator's work. A control unit of the portable terminal determines the operator's work action based on condition information specified for each work content of the operator. When it is determined that the operator's work action deviates from the range specified based on the condition information, the control unit changes the category of data sent from the portable terminal to the support server.

[0024] Aspect 14 of the present disclosure provides a work support method in a work support system, the work support system comprising: a portable terminal; and a support server, which communicates with the portable terminal and supports the work of an operator carrying the portable terminal, the work support method comprising: a judgment step, which judges the work action of the operator based on condition information specified for each work content of the operator; and a change step, which changes the category of data sent from the portable terminal to the support server when it is determined that the work action of the operator deviates from the range specified based on the condition information.

[0025] Aspect 15 of the present disclosure provides a work support program for causing a control unit of a portable terminal carried by an operator and communicating with a support server that supports the operator's work to perform the following steps: a judgment step of judging the operator's work action based on condition information specified for each work content of the operator; and a change step of changing the category of data sent from the portable terminal to the support server when it is determined that the operator's work action deviates from the range specified based on the condition information. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] [ Figure 1 ] Figure 1 This is a diagram showing an example of the system configuration of the work support system.

[0027] [ Figure 2 ] Figure 2 1 is a diagram showing an example of the hardware configuration of a wearable terminal and the hardware configuration of a management server device or a support server device.

[0028] [ Figure 3 ] Figure 3 is a diagram showing an example of condition information.

[0029] [ Figure 4 ] Figure 4 is a diagram showing an example of a functional configuration of a wearable terminal.

[0030] [ Figure 5 ] Figure 5 This is a flowchart showing the flow of action determination processing.

[0031] [ Figure 6 ] Figure 6 This is a flowchart showing the flow of the work performance determination process.

[0032] [ Figure 7 ] Figure 7 This is a first flowchart showing the flow of the environmental information determination process.

[0033] [ Figure 8 ] Figure 8 This is a second flow chart showing the flow of the environmental information determination process.

[0034] [ Fig. 9 ] Fig. 9 1 is a diagram showing an example of the functional configuration of a wearable terminal and a management server device in a learning phase.

[0035] [ Fig.10 ] Fig.10 This is a diagram showing an example of the functional configuration of the learning unit.

[0036] [ Fig.11 ] Fig.11 2 is a diagram showing an example of the functional configuration of the wearable terminal in the determination phase.

[0037] [ Fig.12 ] Fig.12 This is a third flow chart showing the flow of the environmental information determination process. DETAILED DESCRIPTION

[0038] Hereinafter, various embodiments will be described with reference to the accompanying drawings. It should be noted that in this specification and the accompanying drawings, components having substantially the same functional configuration are denoted by the same reference numerals to omit repeated descriptions.

[0039] [First embodiment]

[0040] <System Configuration of Work Support System>

[0041] First, the system configuration of the work support system according to the first embodiment will be described. Figure 1 FIG. 1 is a diagram showing an example of a system configuration of a work support system. Figure 1 As shown, the work support system 100 includes a management server device 110 , a wearable terminal 120 , a support server device 130 , and a supporter terminal 140 .

[0042] In the work support system 100, the wearable terminal 120 and the supporter terminal 140 are respectively connected to the support server device 130 via the network 150 so as to be communicable. Thus, the wearable terminal 120 and the supporter terminal 140 can perform two-way communication under the management of the support server device 130.

[0043] In the work support system 100, the wearable terminal 120 is communicably connected to the management server device 110 via the network 150. Thus, the wearable terminal 120 can obtain various information (for example, condition information) managed by the management server device 110 from the management server device 110.

[0044] The management server device 110 has condition information for determining whether a work action performed by a field worker 160 at a manufacturing site is normal or abnormal, and provides the condition information to the wearable terminal 120 .

[0045] It should be noted that the normal operation of the on-site workers 160 at various manufacturing sites such as chemical plants (hereinafter referred to as manufacturing sites) refers to the following states, for example:

[0046] The work specified in the work schedule starts at the time specified in the work schedule and ends at the time specified in the work schedule.

[0047] ·Complete the work specified in the work schedule within the specified time,

[0048] ·The work is performed by the on-site operators specified in the work schedule.

[0049] On the other hand, abnormal working behavior of the on-site worker 160 at the manufacturing site refers to, for example, the following states that are out of the range specified based on the condition information:

[0050] ·The work specified in the work schedule does not start at the time specified in the work schedule,

[0051] ·The work specified in the work schedule has not been completed by the time specified in the work schedule,

[0052] ·The work specified in the work schedule is not completed within the specified time,

[0053] ・The status of work being performed by a field operator other than the field operator specified in the work schedule;

[0054] A state in which the information acquired by the wearable terminal during work (for example, sound information based on sound data, image information based on moving image data, etc.) includes information that is not visible under normal circumstances.

[0055] In addition, the work performed by the on-site workers 160 at the manufacturing site includes, for example, product analysis work, inspection work, material input work, etc. performed in a chemical plant or the like.

[0056] The wearable terminal 120 is one example of a portable terminal, and is a terminal worn by the field worker 160 at the manufacturing site.

[0057] like Figure 1 As shown, the wearable terminal 120 has, for example, a glasses-like shape, and has a function of shooting dynamic images, a function of detecting sounds (for example, speech of the on-site worker 160 ) or surrounding sounds, and the like.

[0058] In addition, if Figure 1 As shown, the wearable terminal 120 has a function of sending dynamic image data obtained by photographing the situation at the manufacturing site or sound data obtained by detecting the speech of the on-site worker 160 to the supporter 170 via the network 150. In this way, the supporter 170 can obtain the information required to give voice instructions to the on-site worker 160.

[0059] In addition, if Figure 1As shown, the wearable terminal 120 has a function of receiving a voice instruction from the supporter 170 as voice data via the network 150 and outputting it to the on-site worker 160. Thus, the on-site worker 160 can smoothly perform various tasks while receiving appropriate voice instructions from the supporter 170.

[0060] It should be noted that in this embodiment, for example, when it is determined that the work action performed by the on-site worker 160 at the manufacturing site is abnormal, two-way communication is performed between the wearable terminal 120 and the supporter terminal 140. By adopting such a configuration, the work support system according to this embodiment can reduce the amount of communication between the on-site worker 160 and the supporter 170 compared to the case where the two-way communication is performed regardless of normality.

[0061] The support server device 130 manages bidirectional communication between the wearable terminal 120 and the supporter terminal 140. Specifically, the support server device 130 transmits the moving image data and the sound data received from the wearable terminal 120 to the supporter terminal 140. In addition, the support server device 130 transmits the sound data received from the supporter terminal 140 to the wearable terminal 120.

[0062] The supporter terminal 140 is installed in a service station, for example, and obtains the moving image data captured by the wearable terminal 120 and the sound data detected by the wearable terminal 120 via the network 150, and outputs them to the supporter 170. In addition, the supporter terminal 140 receives the sound instruction from the supporter 170 and sends it to the on-site worker 160 via the network 150. In this way, the supporter 170 can remotely support the work of the on-site worker 160.

[0063] <Hardware Configuration of Wearable Terminal, Management Server Device, Support Server Device, and Supporter Terminal>

[0064] Next, the hardware configuration of the wearable terminal 120 , the management server device 110 , the support server device 130 , and the supporter terminal 140 will be described. Figure 2 1 is a diagram showing an example of the hardware configuration of a wearable terminal and the hardware configuration of a management server device or a support server device.

[0065] (1) Hardware Configuration of the Wearable Terminal 120

[0066] First, the hardware configuration of the wearable terminal 120 will be described. Figure 2 (a) is a diagram showing an example of the hardware configuration of the wearable terminal 120 .

[0067] like Figure 2As shown in (a), the wearable terminal 120 has a processor 201, a memory 202, an auxiliary storage device 203, a communication device 204, a GPS (Global Positioning System) device 205, and an acceleration measurement device 206. In addition, the wearable terminal 120 has a sound input device 207, a sound output device 208, a camera device 209, a connection device 210, an operating device 211, and a display device 212. It should be noted that the various hardware components constituting the wearable terminal 120 are connected to each other via a bus 220.

[0068] The processor 201 includes various computing devices such as a CPU (Central Processing Unit) etc. The processor 201 reads various programs (for example, a work support program described later) onto the memory 202 and executes them.

[0069] The memory 202 has a main storage device such as a ROM (Read Only Memory) and a RAM (Random Access Memory). The processor 201 and the memory 202 form a so-called computer (also called a "control unit"), and the processor 201 executes various programs read from the memory 202, thereby enabling the computer to realize various functions.

[0070] The auxiliary storage device 203 stores various programs and various information used when the processor 201 executes the various programs.

[0071] The communication device 204 is a communication device for receiving various information (eg, condition information) from the management server device 110 or performing two-way communication with the supporter terminal 140 via the support server device 130 to transmit and receive various data (eg, dynamic image data, sound data).

[0072] The GPS device 205 detects the position information of the wearable terminal 120. The acceleration measurement device 206 measures the acceleration information of the wearable terminal 120 in the three-axis directions.

[0073] The voice input device 207 detects voice data such as the voice of the on-site worker 160 wearing the wearable terminal 120 or the surrounding sounds of the on-site.

[0074] The audio output device 208 outputs the audio data received from the support server device 130 to the on-site worker 160 wearing the wearable terminal 120 in the form of audio, for example.

[0075] The imaging device 209 captures the surroundings of the on-site worker 160 wearing the wearable terminal 120 and generates moving image data.

[0076] The connection device 210 is a connection device for connecting various auxiliary sensors to the wearable terminal 120 .

[0077] The operating device 211 receives simple operations performed by the on-site worker 160 on the wearable terminal 120 , such as a power ON / OFF switch of the wearable terminal 120 .

[0078] The display device 212 displays various information received from the management server device 110 in the form of images to the on-site worker 160 wearing the wearable terminal 120 , for example.

[0079] (2) Hardware Configuration of the Management Server 110 and Support Server 130

[0080] Next, the hardware configuration of the management server device 110 and the support server device 130 will be described. It should be noted that since the management server device 110 and the support server device 130 have the same hardware configuration, they will be described together here. Figure 2 (b) is a diagram showing an example of the hardware configuration of the management server device 110 and the support server device 130 .

[0081] like Figure 2 As shown in (b) of FIG. 1 , the management server device 110 and the support server device 130 include a processor 231, a memory 232, an auxiliary storage device 233, an operation device 234, a display device 235, a communication device 236, and a drive device 237. The hardware components constituting the management server device 110 and the support server device 130 are connected to each other via a bus 238.

[0082] The processor 231 includes various computing devices such as a CPU and a GPU (Graphic Processing Unit) etc. The processor 231 reads various programs (for example, a management program and a support program described later) to the memory 232 and executes them.

[0083] The memory 232 includes a main storage device such as a ROM and a RAM. The processor 231 and the memory 232 form a so-called computer, and the processor 231 executes various programs read out to the memory 232, thereby causing the computer to realize various functions.

[0084] The auxiliary storage device 233 stores various programs or various data used when the various programs are executed by the processor 231 (in the case of the management server device 110 , condition information used by the wearable terminal 120 ).

[0085] The operation device 234 is an operation device for allowing the administrator of the management server device 110 and the support server device 130 to perform various operations. The display device 235 is a display device for displaying the processing results of various processes executed by the management server device 110 and the support server device 130.

[0086] The communication device 236 is a communication device for communicating with an external device (for example, the wearable terminal 120 , the supporter terminal 140 ) via the network 150 .

[0087] The drive device 237 is a device for placing the recording medium 240. The recording medium 240 mentioned here includes a medium that records information optically, electrically or magnetically, such as a CD-ROM, a floppy disk, a magneto-optical disk, etc. In addition, the recording medium 240 may also include a semiconductor memory that records information electrically, such as a ROM, a flash memory, etc.

[0088] It should be noted that the various programs installed in the auxiliary storage device 233 are installed by, for example, placing the distributed recording medium 240 in the drive device 237 and having the drive device 237 read the various programs recorded in the recording medium 240. Alternatively, the various programs installed in the auxiliary storage device 233 may be installed by downloading from the network 150 via the communication device 236.

[0089] (3) Hardware Configuration of Supporter Terminal 140

[0090] Since the hardware configuration of the supporter terminal 140 is substantially the same as that of the management server device 110 or the support server device 130, the description thereof is omitted here. It should be noted that it is assumed that the supporter terminal 140 is provided with a sound input device and a sound output device in addition to the hardware configuration of the management server device 110 or the support server device 130. In addition, it is assumed that a two-way communication program for performing two-way communication with the wearable terminal 120 via the support server device 130 is installed in the auxiliary storage device of the supporter terminal 140.

[0091] <Specific example of condition information>

[0092] Next, the condition information held by the management server device 110 will be described. Figure 3 300 is a diagram showing an example of condition information. When the wearable terminal 120 determines whether the work action performed by the on-site worker 160 at the manufacturing site is normal or abnormal, the condition information 300 is used. Figure 3 As shown, the condition information 300 includes schedule information 310 and normal range information 320 .

[0093] The schedule information 310 is displayed on the wearable terminal 120.

[0094] ·Whether the work specified in the work schedule starts at the time specified in the work schedule and ends at the time specified in the work schedule,

[0095] ·Whether the work specified in the work schedule is completed within the specified time,

[0096] ·Whether the work is carried out by the on-site workers specified in the work schedule

[0097] Used when making judgments.

[0098] like Figure 3 As shown, the schedule information 310 specifies the schedule for the day when the field operator 160 (field operator name = "α") performs work. Specifically, the schedule information 310 specifies the work content (for example, "work A", "work B", "work C"), the work start time, work end time, work time and allowable range (index value) of each work content. It should be noted that the schedule information 310 also specifies actions other than work (for example, "movement").

[0099] The permissible range specified in the schedule information 310 is predetermined based on the deviation of the work start time, work end time, and work time when multiple on-site workers wear wearable terminals to perform various tasks and determine that the work actions are normal.

[0100] On the other hand, the normal range information 320 is displayed on the wearable terminal 120.

[0101] Whether the information obtained by the wearable terminal during the operation (e.g., sound information based on sound data, image information based on dynamic image data, etc.) contains information that is not visible under normal circumstances

[0102] Used when making judgments.

[0103] exist Figure 3 In the normal range information 320, each normal range is predetermined based on the information obtained by the wearable terminal when multiple on-site workers wear wearable terminals to perform various operations and when the operation is determined to be normal.

[0104] For example, "normal range A1" is defined for work content = "work A" based on the deviation of position information detected by GPS device 205 during work when multiple on-site workers wear wearable terminals to perform the work and the work is determined to be normal.

[0105] It should be noted that the deviation of the position information refers to, for example, the maximum and minimum values ​​of the x-axis, the maximum and minimum values ​​of the y-axis, and the maximum and minimum values ​​of the z-axis in the absolute coordinate system. However, the deviation of the position information is not limited to this, and may also be a value obtained by statistically processing the detected position information.

[0106] In addition, the "normal range A2" is defined based on the deviation of image information of the dynamic image data captured by the camera device 209 when the work content = "work A" is performed by multiple on-site workers wearing wearable terminals and the work action is determined to be normal.

[0107] It should be noted that the deviation of image information based on dynamic image data refers to, for example, the deviation of measurement values ​​indicated by a measuring instrument installed at the manufacturing site and reflected in the dynamic image data, or the deviation of operation positions indicated by an operation terminal installed at the manufacturing site.

[0108] In addition, the "normal range A3" is defined based on the deviation of the sound information of the sound data obtained by the sound input device 207 when the work content = "work A" is performed by multiple on-site workers wearing wearable terminals and the work action is determined to be normal.

[0109] It should be noted that the deviation of the sound information based on the sound data refers to, for example, the deviation of the intensity for each frequency calculated by performing spectral analysis on the sound data, and the "normal range A3" refers to the threshold value for detecting the intensity of abnormal sound calculated based on the deviation.

[0110] It should be noted that the "normal range A4" is defined by the deviation of the acceleration information measured by the acceleration measuring device 206 when the work content = "work A" is performed by multiple on-site workers wearing wearable terminals and the work action is determined to be normal.

[0111] It should be noted that the deviation of the acceleration information refers to, for example, the maximum and minimum values ​​of the acceleration data in the x-axis direction, the maximum and minimum values ​​of the acceleration data in the y-axis direction, and the maximum and minimum values ​​of the acceleration data in the z-axis direction. The deviation of the acceleration information is not limited to this, and may also be a value obtained by statistically processing the measured acceleration information.

[0112] In addition, the "normal range A5" is defined by the deviation of the accessory sensor information detected by the accessory sensor when the work content = "work A" is performed by multiple on-site workers wearing wearable terminals and the work action is determined to be normal.

[0113] It should be noted that the deviation of the auxiliary sensor information is, for example, the deviation of the concentration of a specific gas when the auxiliary sensor is a sensor for detecting the specific gas, and the "normal range A5" refers to the concentration threshold for detecting the generation of the specific gas calculated based on the deviation.

[0114] <Functional composition of wearable terminals>

[0115] Next, the functional configuration of the wearable terminal 120 will be described. Figure 4 As described above, the wearable terminal 120 is installed with a work support program, and by executing the program, the wearable terminal 120 functions as the following parts:

[0116] Condition information acquisition unit 410,

[0117] Position information acquisition unit 421,

[0118] Acceleration information acquisition unit 422,

[0119] · Accessory sensor information acquisition unit 423,

[0120] Voice data acquisition unit 424,

[0121] ·Moving image data acquisition unit 425,

[0122] Voice data output unit 426,

[0123] Voice recognition unit 431,

[0124] Sound analysis unit 432,

[0125] Image recognition unit 433,

[0126] Determination unit 430,

[0127] Bidirectional communication unit 440.

[0128] Among them, the condition information acquisition unit 410 acquires the condition information from the management server device 110 and notifies the determination unit 430 of the condition information.

[0129] The position information acquisition unit 421 acquires the position information detected by the GPS device 205 when the on-site worker 160 is working, and notifies the determination unit 430 of the position information.

[0130] The acceleration information acquisition unit 422 acquires acceleration information measured by the acceleration measurement device 206 when the on-site worker 160 performs work, and notifies the determination unit 430 of the acceleration information.

[0131] The accessory sensor information acquisition unit 423 acquires accessory sensor information detected by the accessory sensor when the on-site worker 160 is working, and notifies the determination unit 430 of the information.

[0132] The voice data acquisition unit 424 acquires voice data detected by the voice input device 207 when the on-site worker 160 performs work, and notifies the same to the determination unit 430 via the voice recognition unit 431 or the voice analysis unit 432. In addition, when the determination unit 430 determines that two-way communication is to be performed, the voice data acquisition unit 424 notifies the two-way communication unit 440 of the acquired voice data.

[0133] The dynamic image data acquisition unit 425 acquires dynamic image data captured by the camera device 209 when the on-site worker 160 performs work, and notifies the determination unit 430 via the image recognition unit 433. In addition, when the determination unit 430 determines that two-way communication is performed, the dynamic image data acquisition unit 425 notifies the two-way communication unit 440 of the acquired dynamic image data.

[0134] When the determination unit 430 determines that two-way communication is being performed, the audio data output unit 426 outputs audio data transmitted from the supporter terminal 140 via the support server device 130 .

[0135] When the voice data is notified from the voice data acquisition unit 424 , the voice recognition unit 431 performs voice recognition processing to extract information indicating the start of work and information indicating the end of work from the words of the on-site worker 160 , and notifies the determination unit 430 of the information.

[0136] When the sound data is notified from the sound data acquisition unit 424 , the sound analysis unit 432 notifies the determination unit 430 of the intensity for each frequency calculated by executing the spectrum analysis as the sound information.

[0137] When the dynamic image data is notified from the dynamic image data acquisition unit 425, the image recognition unit 433 performs image recognition processing to recognize the measurement value of the measuring device and the operation position of the operating terminal reflected in each frame of the dynamic image data, and notifies the determination unit 430 of the recognition result as image information.

[0138] The determination unit 430 determines whether the job specified in the job schedule starts at the time specified in the job schedule and ends at the time specified in the job schedule (whether it is within an allowable range), based on the schedule information 310 included in the condition information 300 notified from the condition information acquisition unit 410 and the information indicating the start of the job and the information indicating the end of the job notified from the voice recognition unit 431.

[0139] ·Whether the work specified in the work schedule is completed within the specified time (whether it is within the allowable range),

[0140] · Determine whether the work action is performed by the on-site workers specified in the work schedule. It should be noted that the information indicating the start of work and the information indicating the end of work used in the comparison with the schedule information 310 are collectively referred to as "work performance information" hereinafter.

[0141] In addition, the determination unit 430 compares the normal range information 320 included in the condition information notified from the condition information acquisition unit 410 with

[0142] The location information notified from the location information acquisition unit 421,

[0143] acceleration information notified from the acceleration information acquisition unit 422,

[0144] · The attached sensor information notified from the attached sensor information acquisition unit 423,

[0145] · Sound information notified from the sound analysis unit 432,

[0146] Image information notified from the image recognition unit 433,

[0147] The comparison is made respectively, and the operation action is judged by whether the information obtained by the wearable terminal during the operation includes information that is not normally visible. It should be noted that the position information, acceleration information, auxiliary sensor information, sound information, and image information obtained when the on-site operator 160 performs the operation and used for comparison with the normal range information 320 are collectively referred to as "environmental information" hereinafter.

[0148] Furthermore, the determination unit 430 notifies the two-way communication unit 440 of the determination result (whether the work action performed by the on-site worker 160 is normal or abnormal).

[0149] The two-way communication unit 440 starts two-way communication when the determination result is notified from the determination unit 430 and when it is determined that the work action performed by the on-site worker 160 is abnormal. Specifically, the two-way communication unit 440 transmits the voice data notified from the voice data acquisition unit 424 and the moving image data notified from the moving image data acquisition unit 425 to the supporter terminal 140 via the support server device 130. In addition, the two-way communication unit 440 notifies the voice data output unit 426 of the voice data received from the supporter terminal 140 via the support server device 130.

[0150] <Action determination processing by wearable terminal>

[0151] Next, the action determination process performed by the wearable terminal 120 will be described. Figure 5 This is a flowchart showing the flow of action determination processing.

[0152] In step S501 , the condition information acquisition unit 410 acquires condition information from the management server device 110 .

[0153] In step S502 , the determination unit 430 starts acquiring work performance information and environmental information.

[0154] In step S503, the determination unit 430 compares the schedule information 310 included in the condition information 300 with the work performance information, and performs a "work performance determination process" for determining whether the work action performed by the on-site worker 160 is normal. It should be noted that the details of the work performance determination process will be described later.

[0155] In step S504, the determination unit 430 compares the normal range information 320 included in the condition information 300 with the environmental information, and performs an "environmental information determination process" for determining whether the work action performed by the on-site worker 160 is normal. It should be noted that the details of the environmental information determination process will be described later.

[0156] In step S505 , the determination unit 430 determines whether the work action performed by the on-site worker 160 has shifted from a normal state to an abnormal state.

[0157] In step S506, if it is determined that the state has not changed from the normal state to the abnormal state (if it is "No" in step S505), the process proceeds to step S507.

[0158] Maintain a normal state,

[0159] Maintain an abnormal state,

[0160] ·Transition from an abnormal state to a normal state,

[0161] In any of the situations.

[0162] In step S507 , the determination unit 430 determines whether the work action performed by the on-site worker 160 has shifted from an abnormal state to a normal state.

[0163] In step S507, if it is determined that the state has not been changed from the abnormal state to the normal state (if it is "No" in step S507), the process proceeds to step S509.

[0164] Maintain a normal state,

[0165] Maintain an abnormal state,

[0166] In any of the situations.

[0167] On the other hand, when it is determined in step S507 that the state has shifted from the abnormal state to the normal state (if "YES" in step S507), the process proceeds to step S508.

[0168] In step S508, the determination unit 430 determines that the two-way communication is to be terminated, and notifies the two-way communication unit 440. As a result, the two-way communication unit 440 terminates the two-way communication.

[0169] In addition, in step S505, when it is determined that the state has shifted from the normal state to the abnormal state (if "YES" in step S505), the process proceeds to step S506.

[0170] In step S506, the determination unit 430 determines that the two-way communication is started, and notifies the two-way communication unit 440. As a result, the two-way communication unit 440 starts the two-way communication.

[0171] In step S509, the determination unit 430 determines whether to terminate the action determination process. If it is determined in step S509 that the action determination process is not to be terminated (in the case of "No" in step S509), the process returns to step S503.

[0172] On the other hand, when it is determined in step S509 that the action determination process is to be terminated (in the case of YES in step S509 ), the process proceeds to step S510 .

[0173] In step S510 , the determination unit 430 ends the acquisition of the work performance information and the environmental information, and ends the action determination process.

[0174] <Work Performance Judgment Processing Flow>

[0175] Next, the details of the work performance determination process (step S503) will be described. Figure 6 This is a flowchart showing the flow of the work performance determination process.

[0176] In step S601, the determination unit 430 determines whether the voice recognition unit 431 has recognized the voice indicating the start of work. If it is determined in step S601 that the voice indicating the start of work has not been recognized (No in step S601), the process proceeds to step S602.

[0177] In step S602 , the determination unit 430 identifies a job scheduled at the current time based on the schedule information 310 .

[0178] On the other hand, when it is determined in step S601 that the sound indicating the start of the work has been recognized (in the case of YES in step S601 ), the process proceeds to step S603 .

[0179] In step S603 , the determination unit 430 recognizes the content of the work performed by the voice recognition unit 431 .

[0180] In step S604, the determination unit 430 determines whether there is a delay from the job start time specified in the schedule information 310. If it is determined in step S604 that there is a delay from the job start time (if "yes" in step S604), the process proceeds to step S610.

[0181] It should be noted that the situations where a delay occurs relative to the start time of a job include:

[0182] Although the current time is outside the permissible range of the start time of the job specified in the schedule information 310, the sound indicating the start of the job has not yet been recognized, or

[0183] Although a sound indicating the start of a work is recognized for the work content specified in the schedule information 310 , the time of the recognized sound is outside the permissible range of the start time specified in the schedule information 310 .

[0184] On the other hand, when it is determined in step S604 that there is no delay with respect to the start time of the job (in the case of NO in step 604 ), the process proceeds to step S605 .

[0185] In step S605, the determination unit 430 determines whether the voice recognition unit 431 has recognized the voice indicating the completion of the work. In step S605, if it is determined that the voice indicating the completion of the work has not been recognized (No in step S605), the process proceeds to step S606.

[0186] In step S606 , the determination unit 430 identifies the work scheduled at the current time based on the schedule information 310 .

[0187] On the other hand, when it is determined in step S605 that the sound indicating the completion of the work has been recognized (in the case of YES in step S605 ), the process proceeds to step S607 .

[0188] In step S607 , the determination unit 430 recognizes the content of the work performed by the voice recognition unit 431 .

[0189] In step S608, the determination unit 430 determines whether there is a delay with respect to the job end time specified in the schedule information 310. If it is determined in step S608 that there is a delay with respect to the job end time (if "yes" in step S608), the process proceeds to step S610.

[0190] It should be noted that the situations where a delay occurs relative to the end time of the job include:

[0191] Although the current time is outside the permissible range of the end time of the job specified in the schedule information 310, the voice recognition has not yet been performed for the information indicating the end of the job, or

[0192] Although a sound indicating the end of work is recognized for the work content specified in the schedule information 310 , the time of the recognized sound is outside the permissible range of the end time specified in the schedule information 310 .

[0193] In step S609, the determination unit 430 determines whether the actual working time exceeds the working time specified in the schedule information 310. If it is determined in step S609 that the actual working time exceeds (if "yes" in step S609), the process proceeds to step S610.

[0194] In step S610, the determination unit 430 determines that the operation performed by the on-site operator 160 is abnormal, and returns to Figure 5 Step S504.

[0195] On the other hand, when it is determined in step S609 that the actual operation time has not exceeded (in the case of "No" in step S609), the process directly returns to step S609. Figure 5 Step S504.

[0196] <Flow of Environmental Information Determination Process>

[0197] Next, the details of the environmental information determination process (step S504) will be described. Figure 7 This is a first flowchart showing the flow of the environmental information determination process.

[0198] In step S701 , the determination unit 430 identifies the current work content based on the schedule information.

[0199] In step S702, the determination unit 430 determines whether the work content has been changed. If it is determined in step S702 that the work content has not been changed (in the case of "No" in step S702), the process proceeds to step S704.

[0200] On the other hand, when it is determined in step S702 that the work content has been changed (in the case of YES in step S702 ), the process proceeds to step S703 .

[0201] In step S703 , the determination unit 430 acquires normal range information corresponding to the work content recognized in step S701 .

[0202] In step S704 , the determination unit 430 acquires environmental information.

[0203] In step S705 , the determination unit 430 determines whether any of the environmental information acquired in step S704 exceeds the corresponding normal range in the normal range information 320 acquired in step S703 .

[0204] If it is determined in step S705 that the number has not exceeded (in the case of "No" in step S705), the process returns to Figure 5 Step S505.

[0205] On the other hand, when it is determined in step S705 that the normal range is exceeded (in the case of YES in step S705 ), the process proceeds to step S706 .

[0206] In step S706, the determination unit 430 determines that the operation performed by the on-site operator 160 is abnormal, and returns to the Figure 5 Step S505.

[0207] <Conclusion>

[0208] As is clear from the above description, in the work support system 100 according to the first embodiment,

[0209] A wearable terminal and a supporter terminal that communicates with the wearable terminal and supports the work of a field worker wearing the wearable terminal.

[0210] The wearable terminal determines the work action of the on-site worker based on the condition information specified for each work content of the on-site worker.

[0211] When it is determined that the work action of the on-site worker deviates from the range (permissible range or normal range) specified in the condition information, bidirectional communication with the supporter terminal is started.

[0212] Thus, in the first embodiment, when it is determined that the work action of the on-site worker is out of the range specified in the condition information, two-way communication is started. Thus, according to the first embodiment, compared with the case where two-way communication is performed regardless of the out-of-range, the communication volume can be reduced.

[0213] In other words, according to the first embodiment, it is possible to reduce the communication volume of the wearable terminal in the work support system that supports the work of the on-site worker wearing the wearable terminal.

[0214] [Second embodiment]

[0215] In the first embodiment, the case where the work action performed by the on-site operator is determined to be abnormal when any one of the environmental information is determined to be outside the corresponding normal range in the normal range information 320 is described as an example. However, the method of determining whether the work action performed by the on-site operator is normal or abnormal is not limited to this.

[0216] It can also be configured so that when it is determined that any multiple combinations in the environmental information are respectively out of the corresponding normal range combinations in the normal range information 320, the work action performed by the on-site operator is determined to be abnormal. It should be noted that it can also be configured so that the combination pattern at this time is pre-defined as a predetermined judgment rule (a model based on rules), and in the judgment unit 430, each time the environmental information is obtained, all the combination patterns are judged to be in compliance. It should be noted that the judgment rule can also be specified for each work content. The second embodiment is described below with the differences from the first embodiment as the center.

[0217] <Flow of Environmental Information Determination Process>

[0218] Figure 8 is a second flow chart showing the flow of environmental information determination processing. Figure 7 The difference in the environmental information determination process shown is steps S801 and S802.

[0219] In step S801 , the determination unit 430 acquires environmental information and compares it with the combination pattern included in the determination rule.

[0220] In step S802 , the determination unit 430 determines whether the acquired environmental information matches any combination pattern among the combination patterns included in the determination rule.

[0221] When it is determined in step S802 that the arbitrary combination pattern is met (in the case of "Yes" in step S802), the process proceeds to step S706. On the other hand, when it is determined in step S802 that the arbitrary combination pattern is not met (in the case of "No" in step S802), the process returns to step S706. Figure 5 Step S505.

[0222] <Conclusion>

[0223] As is clear from the above description, in the work support system 100 according to the second embodiment,

[0224] Wearable terminals can obtain environmental information of on-site workers during their work.

[0225] The wearable terminal uses a rule-based model that uses environmental information of the on-site workers as input data to determine whether the work actions performed by the on-site workers are normal.

[0226] Therefore, according to the second embodiment, the same effects as those of the first embodiment can be achieved.

[0227] [Third Embodiment]

[0228] In the second embodiment, a rule-based model is used to determine whether the work action performed by the on-site operator is normal based on the environmental information. In contrast, in the third embodiment, a learning model that performs machine learning on the relationship between the environmental information and whether the work action performed by the on-site operator is normal is used to determine whether the work performed by the on-site operator is normal based on the environmental information. The third embodiment will be described below, centering on the differences from the first and second embodiments.

[0229] <Functional composition of wearable terminal and management server in the learning phase>

[0230] First, the functional configuration of the wearable terminal and the management server in the learning phase will be described. Fig. 9 1 is a diagram showing an example of the functional configuration of a wearable terminal and a management server device in a learning phase.

[0231] like Fig. 9 As shown, in the learning phase, multiple wearable terminals are used to collect environmental information. For convenience, Fig. 9 The example shows three wearable terminals 120_1 to 120_3, but the number of wearable terminals for collecting environmental information may be more than three.

[0232] In addition, if Fig. 9As shown, the multiple wearable terminals 120_1 to 120_3 respectively have the following parts:

[0233] Position information acquisition unit 421,

[0234] Acceleration information acquisition unit 422,

[0235] · Accessory sensor information acquisition unit 423,

[0236] Voice data acquisition unit 424,

[0237] Sound analysis unit 432,

[0238] ·Moving image data acquisition unit 425,

[0239] Image recognition unit 433,

[0240] Environmental information collection unit 910,

[0241] Transmitting unit 911.

[0242] It should be noted that, due to the use of Figure 4 The functions of the position information acquisition unit 421 to the image recognition unit 433 have been described, and thus their description is omitted here.

[0243] The environmental information collection unit 910 obtains the position information, acceleration information, auxiliary sensor information, sound information, and image information as environmental information from the position information acquisition unit 421 to the image recognition unit 433. In addition, when obtaining the environmental information, the environmental information collection unit 910 determines the content of the work performed by the on-site worker, and separates the environmental information for each work content and stores it in the environmental information storage unit 912.

[0244] The transmission unit 911 transmits the environment information for each job content stored in the environment information storage unit 912 to the management server device 110 .

[0245] In addition, if Fig. 9 As shown, in the learning phase, the management server device 110 functions as a learning data set generating unit 920 and a learning unit 921 .

[0246] The learning data set generation unit 920 associates the environmental information for each work content sent from the plurality of wearable terminals 120_1 to 120_3 and the like with the state information, and stores the same as a learning data set in the learning data set storage unit 922. It should be noted that the state information is information indicating whether the work action performed by each on-site worker when the environmental information is obtained is normal or abnormal.

[0247] The learning unit 921 reads out the learning data set stored in the learning data set storage unit 922, and uses the read learning data set to perform learning processing for each operation content. It should be noted that the learning model generated by the learning unit 921 performing learning processing for each operation content is performed in the wearable terminal.

[0248] <Functional Structure of the Learning Department>

[0249] Next, the functional configuration of the learning unit 921 will be described. Fig.10 FIG. 1 is a diagram showing an example of the functional configuration of the learning unit. Fig.10 As shown, the learning unit 921 has a model and a comparison / change unit for each operation content. Fig.10 The example shows a case where "job A", "job B", and "job C" are included as job contents, and learning processing is performed on models corresponding to the three jobs. However, the job contents are not limited to three, and for example, learning processing can be performed on models corresponding to more than three jobs.

[0250] The environment information corresponding to the task content "task A" in the learning data sets 1010_1 to 1010_3 is input as input data to the task A model 1001. The task A model 1001 operates by receiving the input data and outputs output data.

[0251] The comparison / change unit 1002 receives the correct answer data corresponding to the task content = "task A" in the learning data sets 1010_1 to 1010_3, etc., and compares the correct answer data with the output data output from the task A model 1001. In addition, the comparison / change unit 1002 updates the model parameters of the task A model 1001 based on the comparison result, thereby performing a learning process on the task A model 1001. Thus, a learning completion model for task A is generated. The learning completion model for task A is equivalent to the normal range (indicator value) associated with the task content = "task A" in the normal range information 320 of the condition information 300 in the first embodiment.

[0252] Similarly, the environment information corresponding to the task content "task B" in the learning data sets 1010_1 to 1010_3 is input as input data to the task B model 1011. The task B model 1011 operates by receiving the input data and outputs output data.

[0253] The comparison / change unit 1012 receives the correct answer data corresponding to the task content = "task B" in the learning data sets 1010_1 to 1010_3, etc., and compares the correct answer data with the output data output from the task B model 1011. In addition, the comparison / change unit 1012 updates the model parameters of the task B model 1011 based on the comparison result, thereby performing a learning process on the task B model 1011. Thus, a learning completion model for task B is generated. The learning completion model for task B is equivalent to the normal range (indicator value) associated with the task content = "task B" in the normal range information 320 of the condition information 300 in the first embodiment.

[0254] Similarly, the environment information corresponding to the task content "task C" in the learning data sets 1010_1 to 1010_3 is input as input data to the task C model 1021. The task C model 1021 operates by receiving the input data and outputs output data.

[0255] The comparison / change unit 1022 receives the correct answer data corresponding to the task content = "task C" in the learning data sets 1010_1 to 1010_3, etc., and compares the correct answer data with the output data output from the task C model 1021. In addition, the comparison / change unit 1022 updates the model parameters of the task C model 1021 based on the comparison result, thereby performing a learning process on the task C model 1021. Thus, a learning completion model for task C is generated. The learning completion model for task C is equivalent to the normal range (indicator value) associated with the task content = "task C" in the normal range information 320 of the condition information 300 in the first embodiment.

[0256] <Functional Configuration of Wearable Terminal in the Determination Phase>

[0257] Next, the functional configuration of the wearable terminal in the determination phase will be described. Fig.11 2 is a diagram showing an example of the functional configuration of the wearable terminal in the determination phase.

[0258] like Fig.11 As shown, the wearable terminal 1100 in the determination stage has

[0259] Condition information acquisition unit 410,

[0260] Position information acquisition unit 421,

[0261] Acceleration information acquisition unit 422,

[0262] · Accessory sensor information acquisition unit 423,

[0263] Voice data acquisition unit 424,

[0264] ·Moving image data acquisition unit 425,

[0265] Voice data output unit 426,

[0266] Voice recognition unit 431,

[0267] Sound analysis unit 432,

[0268] Image recognition unit 433,

[0269] Operation performance determination unit 1110,

[0270] Environmental information determination unit 1120,

[0271] Bidirectional communication unit 1130.

[0272] It should be noted that, due to the use of Figure 4 The functions of the condition information acquisition unit 410 to the image recognition unit 433 have been described, and thus their description is omitted here.

[0273] The work performance determination unit 1110 determines the work performance based on the schedule information 310 included in the condition information 300 notified from the condition information acquisition unit 410 and the work performance information notified from the voice recognition unit 431.

[0274] ·Whether the work specified in the work schedule starts at the time specified in the work schedule and ends at the time specified in the work schedule,

[0275] ·Whether the work specified in the work schedule is completed within the specified time,

[0276] · It is determined whether the work is being performed by the on-site worker specified in the work schedule, etc. In addition, the work performance determination unit 1110 notifies the two-way communication unit 1130 of the determination result.

[0277] The environmental information determination unit 1120 includes a learning completion model 1121 for task A, a learning completion model 1122 for task B, and a learning completion model 1123 for task C.

[0278] When the current work content is determined to be "work A" based on the schedule information 310 notified from the condition information acquisition unit 410, the work A learning completion model 1121 operates. When the environmental information is input, the work A learning completion model 1121 infers whether the work action of the on-site worker 160 is normal or abnormal, and notifies the two-way communication unit 1130 of the inference result.

[0279] Similarly, when the current work content is determined to be "work B" based on the schedule information 310 notified from the condition information acquisition unit 410, the work B learning completion model 1122 operates. When the environmental information is input, the work B learning completion model 1122 infers whether the work action of the on-site worker 160 is normal or abnormal, and notifies the two-way communication unit 1130 of the inference result.

[0280] Similarly, when the current work content is determined to be "work C" based on the schedule information 310 notified from the condition information acquisition unit 410, the work C learning completion model 1123 operates. When the environmental information is input, the work C learning completion model 1123 infers whether the work action of the on-site worker 160 is normal or abnormal, and notifies the two-way communication unit 1130 of the inference result.

[0281] As described above, in the present embodiment, the learned models 1121 for work A to 1123 for work C correspond to the normal range information 320 of the condition information 300 in the first and second embodiments described above.

[0282] When the determination result is notified from the work performance determination unit 1110, and when it is determined that the work action performed by the on-site worker 160 is abnormal, the two-way communication unit 1130 starts two-way communication. Alternatively, when the inference result is notified from the environmental information determination unit 1120, and when it is inferred that the work action performed by the on-site worker 160 is abnormal, the two-way communication unit 1130 starts two-way communication.

[0283] Specifically, the two-way communication unit 1130 transmits the audio data notified from the audio data acquisition unit 424 and the moving image data notified from the moving image data acquisition unit 425 to the supporter terminal 140 via the support server device 130. In addition, the two-way communication unit 440 notifies the audio data output unit 426 of the audio data received from the supporter terminal 140 via the support server device 130.

[0284] <Flow of Environmental Information Determination Process>

[0285] Next, the details of the environmental information determination process performed by the wearable terminal 1100 are described. Fig.12 3 is a flowchart showing the flow of environmental information determination processing. Figure 7 The difference in the environmental information determination process shown is steps S1201 to S1203.

[0286] In step S1201 , the environmental information determination unit 1120 switches to a learning completion model corresponding to the task content.

[0287] In step S1202, the environmental information determination unit 1120 acquires environmental information and inputs the acquired environmental information into the switched learned model, so that the learned model outputs an inference result.

[0288] In step S1203, the environmental information determination unit 1120 determines whether the work action performed by the on-site worker 160 is a normal inference result or an abnormal inference result. If it is determined to be a normal inference result in step S1203 (in the case of "No" in step S1203), the process returns to step S1204. Figure 5 Step S505.

[0289] On the other hand, when it is determined in step S1203 that the estimation result is abnormal (in the case of "YES" in step S1203), the process proceeds to step S706.

[0290] <Conclusion>

[0291] As is clear from the above description, in the work support system 100 according to the third embodiment,

[0292] The environmental information determination unit is generated by performing a learning process on the learning model.

[0293] The learning process for the learning model is performed using a learning data set that uses environmental information when the on-site worker is working as input data and information indicating whether the on-site worker's work is normal as correct answer data.

[0294] Therefore, according to the third embodiment, the same effects as those of the first embodiment can be achieved.

[0295] [Other embodiments]

[0296] In the above-mentioned embodiments, the two-way communication with the supporter terminal 140 is not performed during the period when the work action performed by the field worker 160 is determined to be normal, and the two-way communication with the supporter terminal 140 is started when the work action performed by the field worker 160 is determined to be abnormal. However, the method for reducing the communication volume is not limited to this, and the communication volume during the period when the work action performed by the field worker 160 is determined to be normal and the communication volume after the work action performed by the field worker 160 is determined to be abnormal may be different.

[0297] As a method for configuring so that the communication volume is different, for example, there is a method of changing the type of data for bidirectional communication with the supporter terminal 140. In addition, the method of changing the type of data includes changing from data with a low communication volume per unit time to data with a high communication volume per unit time, for example, including the following methods, etc.:

[0298] A method of transmitting audio data when the period is determined to be normal, and transmitting audio data and moving image data when the period is determined to be abnormal,

[0299] A method of changing the data quality (compression rate, transmission interval, etc.) between the audio data and moving image data transmitted during a period determined to be normal and the audio data and moving image data transmitted when determined to be abnormal.

[0300] In addition, in each of the above embodiments, position information, acceleration information, attached sensor information, sound information, and image information are exemplarily shown as environmental information. However, the environmental information is not limited thereto, and other information may also be used as long as it is information that can be obtained by the wearable terminal 120 when the on-site worker 160 is working.

[0301] In addition, in the above-mentioned embodiments, the case of obtaining the position information detected by the GPS device 205 is described as an example, but the method of obtaining the position information is not limited to this, and the position information can also be obtained by other methods. As other methods of obtaining, for example, there is a method of obtaining the position information based on the dynamic image data captured by the camera device using Visual SLAM (Simultaneous Localization and Mapping) technology.

[0302] Although the functional configuration of the wearable terminal when generating the normal range information 320 is not mentioned in the first embodiment, when generating the normal range information 320, for example, the wearable terminal may be used in the third embodiment. Fig. 9 The functional composition of the description.

[0303] In the third embodiment described above, the learning unit 921 has described a case where the learning unit 921 generates a learning model by performing learning processing using a learning data set. However, in the case where the inference result obtained by the generated learning model is wrong, the learning model of the corresponding work content may be re-learned. In the re-learning process, the learning unit 921 uses, for example, the environmental information of the on-site operator when the inference result is wrong.

[0304] In addition, in the above-mentioned embodiments, the case where a wearable terminal worn by a field worker is used is described, but a portable terminal carried by a field worker may be used instead of the wearable terminal.

[0305] Although the embodiments have been described above, it will be understood that various changes in form and detail may be made without departing from the spirit and scope of the claims.

[0306] This application claims the priority of Japanese Patent Application No. 2022-061127 filed on March 31, 2022, and the entire contents of the Japanese Patent Application are cited by reference in this application.

[0307] Explanation of symbols

[0308] 100: Operation support system

[0309] 110: Management server device

[0310] 120: Wearable terminal

[0311] 130: Support server devices

[0312] 140: Supporter Terminal

[0313] 300: Condition information

[0314] 310: Schedule Information

[0315] 320: Normal range information

[0316] 410: Condition information acquisition unit

[0317] 421: Position information acquisition unit

[0318] 422: Acceleration information acquisition unit

[0319] 423: Accessory sensor information acquisition unit

[0320] 424: Audio data acquisition unit

[0321] 425: Dynamic image data acquisition unit

[0322] 426: Audio data output unit

[0323] 430: Judgment Department

[0324] 431: Voice Recognition Department

[0325] 432: Sound Analysis Department

[0326] 433: Image Recognition Department

[0327] 440: Two-way communication department

[0328] 910: Environmental Information Collection Department

[0329] 911: Sending Department

[0330] 920: Dataset generation for learning

[0331] 921: Learning Department

[0332] 1110: Work performance assessment department

[0333] 1120: Environmental Information Determination Department

[0334] 1121: Assignment A using learning to complete the model

[0335] 1122: Assignment B using learning to complete the model

[0336] 1123: Assignment C using learning to complete the model

[0337] 1130: Two-way communication unit.

Claims

1. A work support system comprising: A portable terminal; and a support server that communicates with the portable terminal and supports the work of the operator carrying the portable terminal, The portable terminal has a control unit The work action of the operator is determined based on condition information specified for each work content of the operator. When it is determined that the operator's work action is out of a range defined by the condition information, the type of data transmitted from the mobile terminal to the support server is changed from data with a lower communication volume per unit time to data with a higher communication volume per unit time.

2. The work support system according to claim 1, in, The control unit determines the work action of the worker based on condition information including any one of a work time and a start time of the work specified for each work content.

3. The work support system according to claim 2, in, The control unit Obtaining the environmental information of the operator during operation, The work action of the worker is determined based on the condition information relative to the environmental information that is defined for each work content.

4. The work support system according to claim 3, in, The environmental information is information acquired by the control unit when the operator is working, and the information acquired by the control unit includes any one of position information, image information, sound information, and acceleration information.

5. The work support system according to claim 3, in, The condition information is generated based on one or more of work performance information for each of the work contents and the environmental information for each of the work contents acquired during work.

6. The work support system according to claim 5, in, The condition information is generated for each work content based on an index value of work performance information specified for each work content or an index value of environment information specified for each work content.

7. The work support system according to claim 1, in, The condition information is generated by causing the learning model to perform learning.

8. The work support system according to claim 7, in, The control unit obtains the environmental information of the operator during operation. The condition information is generated by causing the learning model to learn using a learning data set that uses environmental information when the operator is working as input data and information indicating whether the operator's working behavior is normal when the operator is working as correct answer data.

9. The work support system according to claim 8, in, The condition information is generated by causing the learning model to perform learning for each work content using the learning data set for each work content.

10. The work support system according to claim 9, in, When the determination result determined by the control unit is erroneous, the environment information of the operator during operation is collected, and the learning model of the corresponding operation content is relearned using the collected environment information of the operator during operation.

11. The operation support system according to claim 7, wherein, the control unit acquires environmental information during the operation of the operator, the condition information is a rule-based model that takes the environmental information during the operation of the operator as input data and outputs information indicating whether the operation action is normal during the operation of the operator.

12. A portable terminal communicates with a support server that supports the operation of an operator, the control unit included in the portable terminal determines the operation action of the operator based on condition information specified for each operation content of the operator, and when it is determined that the operation action of the operator deviates from the range specified based on the condition information, changes the type of data transmitted from the portable terminal to the support server from data with a lower communication volume per unit time to data with a higher communication volume per unit time.

13. An operation support method in an operation support system, the operation support system including: a portable terminal ； and a support server that communicates with the portable terminal and supports the operation of an operator carrying the portable terminal, the operation support method including: a determination step of determining the operation action of the operator based on condition information specified for each operation content of the operator; and a change step of, when it is determined that the operation action of the operator deviates from the range specified based on the condition information, changing the type of data transmitted from the portable terminal to the support server from data with a lower communication volume per unit time to data with a higher communication volume per unit time.

14. An operation support program product for causing a control unit included in a portable terminal carried by an operator and communicating with a support server that supports the operation of the operator to execute the following steps: a determination step of determining the operation action of the operator based on condition information specified for each operation content of the operator; and a change step of, when it is determined that the operation action of the operator deviates from the range specified based on the condition information, changing the type of data transmitted from the portable terminal to the support server from data with a lower communication volume per unit time to data with a higher communication volume per unit time.

Images