Information processing method, information processing device, information processing system, and computer program

The method automatically tailors work procedures to worker attributes using language models, addressing the need for manual preparation and enhancing operational efficiency.

JP7769995B1Active Publication Date: 2025-11-14DAIKIN INDUSTRIES LTD +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2024171418
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2025-11-14
Estimated Expiration
2044-09-30

AI Technical Summary

Technical Problem

Existing systems require manual preparation of work materials based on worker skill levels, leading to significant operational man-hours.

Method used

An information processing method that automatically generates work procedure information using language models to consider worker attributes, such as proficiency and qualifications, and adjusts the level of detail in the procedure based on these attributes.

Benefits of technology

Automatically generates work procedure information tailored to individual worker skills, reducing operational man-hours and improving work quality and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007769995000001_ABST
    Figure 0007769995000001_ABST
Patent Text Reader

Abstract

To provide an information processing method, an information processing device, an information processing system, and a computer program. [Solution] A computer executes a process to acquire attribute information indicating the attributes of the worker performing the work, generate work procedure information according to the worker's attributes using one or more language models that reference the acquired attribute information and standard procedure information indicating the standard procedure for the work, and output the generated work procedure information.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to an information processing method, an information processing device, an information processing system, and a computer program. [Background technology]

[0002] Patent Document 1 discloses a technology that stores a work manual containing predetermined work content and work procedures, as well as worker information about the worker, and switches the method of presenting the work content and work procedures depending on the worker's level of proficiency. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2019-57099 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, it is necessary to predict in advance what information should be presented depending on the skill level of the worker and store it in the system. Therefore, it is necessary to prepare materials in advance depending on the skill level of the worker, which poses the problem of a large amount of operational man-hours.

[0005] An object of the present disclosure is to provide an information processing method, an information processing device, an information processing system, and a computer program that can automatically generate work procedure information according to the attributes of workers. [Means for solving the problem]

[0006] An information processing method according to a first aspect of the present disclosure includes a process performed by a computer to acquire attribute information indicating the attributes of a worker performing work, generate work procedure information according to the attributes of the worker using one or more language models that reference the acquired attribute information and standard procedure information indicating a standard procedure for the work, and output the generated work procedure information.

[0007] An information processing method according to a second aspect of the present disclosure is the information processing method according to the first aspect, wherein the attribute information includes at least one of the worker's proficiency, qualifications, work speed, and an evaluation of the worker.

[0008] An information processing method according to a third aspect of the present disclosure is the information processing method according to the second aspect, wherein the evaluation includes at least one of the multiple service rate, the rate of free multiple part replacement, the rate of paid service, the average number of visits, and the rate of inquiries to the call center.

[0009] An information processing method according to a fourth aspect of the present disclosure is the information processing method according to any one of the first to third aspects, further acquiring at least one of information about the work, information about the equipment to be worked on, information about past cases of the work, and supplementary information about the standard procedure, and causing the computer to execute a process of generating work procedure information according to the attributes of the worker using a language model that references the attribute information, the standard procedure information, and the acquired at least one piece of information.

[0010] An information processing method according to a fifth aspect of the present disclosure is the information processing method according to the fourth aspect, wherein the information about the work includes at least one of information about a work site and information about time constraints on the work.

[0011] An information processing method according to a sixth aspect of the present disclosure is the information processing method according to the fourth aspect, wherein the information about the device includes at least one of configuration information of the device, measurement values ​​measured for the device, control values ​​input to the device, and usage purposes of the device.

[0012] An information processing method according to a seventh aspect of the present disclosure is an information processing method according to any one of the first to sixth aspects, wherein at least one of image data captured at a work site of the work and audio data recorded at the work site is acquired, and a process of generating work procedure information according to the attributes of the worker using a language model that references the attribute information, the standard procedure information, and at least one of the acquired data is executed by the computer.

[0013] An information processing method according to an eighth aspect of the present disclosure is the information processing method according to any one of the first to seventh aspects, in which a process is executed by the computer to receive a worker's request for work procedure information and generate work procedure information according to the received worker's request using the language model.

[0014] An information processing device according to a ninth aspect of the present disclosure includes at least one control unit, which acquires attribute information indicating the attributes of a worker performing work, generates work procedure information according to the attributes of the worker using one or more language models that reference the acquired attribute information and standard procedure information indicating a standard procedure for the work, and outputs the generated work procedure information.

[0015] An information processing system according to a tenth aspect of the present disclosure includes a terminal device of a worker, and a server device communicatively connected to the terminal device and having a memory unit that stores standard procedure information indicating standard procedures for work, wherein the server device acquires attribute information indicating attributes of the worker performing the work, generates work procedure information according to the attributes of the worker performing the work using one or more language models that reference the acquired attribute information and the standard procedure information stored in the memory unit, and outputs the generated work procedure information.

[0016] A computer program according to an eleventh aspect of the present disclosure is a computer program for causing a computer to execute a process of acquiring attribute information indicating the attributes of a worker performing work, generating work procedure information according to the attributes of the worker using one or more language models that reference the acquired attribute information and standard procedure information indicating a standard procedure for the work, and outputting the generated work procedure information. [Effects of the Invention]

[0017] According to the present disclosure, work procedure information can be automatically generated according to the attributes of the workers. [Brief explanation of the drawings]

[0018] [Figure 1] FIG. 2 is an explanatory diagram illustrating an overview of a process executed by an information processing system according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing the internal configuration of the wearable device. [Figure 3] FIG. 2 is a block diagram showing the internal configuration of the server device. [Figure 4] FIG. 10 is a conceptual diagram illustrating an example of a work management table. [Figure 5] FIG. 10 is a conceptual diagram illustrating an example of an attribute database. [Figure 6] FIG. 10 is a conceptual diagram illustrating an example of a standard procedure database. [Figure 7] FIG. 10 is an explanatory diagram illustrating an example of generating a revised procedure manual. [Figure 8] FIG. 10 is a schematic diagram showing an example of a prompt to be input to a language model. [Figure 9] 10 is a flowchart illustrating a procedure of a process executed by a server device. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, an information processing system according to an embodiment will be specifically described with reference to the drawings. 1 is an explanatory diagram outlining the processing executed by an information processing system 1 according to an embodiment. The information processing system 1 according to the embodiment includes a wearable device 10 worn by a worker and a server device 20 that manages work processes. The wearable device 10 and the server device 20 are connected to each other so as to be able to communicate with each other via a communication network NW such as the Internet. An LLM server 30 is also connected to the communication network NW, and the server device 20 can use a language model MD installed in the LLM server 30 via the communication network NW.

[0020] In this embodiment, the worker is, for example, a worker who performs installation work, repair work, inspection work, etc. related to refrigeration and air conditioning related equipment. Refrigeration and air conditioning related equipment refers to equipment that is connected to refrigerant piping and constitutes a refrigeration cycle. Refrigeration and air conditioning related equipment includes equipment such as outdoor units, indoor units, ventilators, heat source equipment, and central control devices that constitute an air conditioning system, and equipment such as chillers, heat exchangers, and control devices that constitute a chiller system.

[0021] The server device 20 generates a work procedure manual (work procedure information) according to the worker's attributes by using the language model MD. Here, the worker's attributes include at least one of the worker's proficiency, qualifications, work speed, and worker evaluation. The work procedure manual is data that defines the work procedures for tasks such as installation, repair, and inspection, and is composed of multiple work procedures. It is assumed that standard work procedures for each task are created in advance by a work manager or the like and registered in a standard procedure database DB2 (see FIG. 6). The server device 20 generates a work procedure manual according to the worker's attributes by sending the worker's attribute information and standard procedure information indicating the standard procedure for the task to be performed by the worker to the LLM server 30 and inputting them into the language model MD.

[0022] When the language model MD receives the attribute information of a worker and the standard procedure information of the work performed by the worker, it outputs a work procedure manual (hereinafter also referred to as a revised procedure manual) that is a revision of the standard procedure according to the worker's attributes. For example, if the worker has a high level of proficiency, the language model MD may output a revised procedure manual in which the explanation of the work procedure is omitted or simplified, or in which part of the work procedure is skipped. On the other hand, if the worker has a low level of proficiency, the language model MD may output a revised procedure manual in which the explanation of the work procedure is added or detailed, or in which some preliminary work procedures are added.

[0023] The server device 20 transmits the revised procedure manual for each worker, which is generated by using the language model MD, to the wearable device 10 via the communication network NW.

[0024] The wearable device 10 is a device that has an imaging function, a recording function, a voice output function, a communication function, and the like. The wearable device 10 is worn, for example, around the neck of a worker. Alternatively, the wearable device 10 may be worn on the worker's head, or on another body part such as the shoulder or arm. The wearable device 10 may also be a goggle-type camera device, and any device having the above functions, such as a smartphone or an action camera, may be used instead of the wearable device 10.

[0025] The wearable device 10 acquires a revised procedure manual for the work to be performed by the worker from the server device 20. The wearable device 10 provides audio guidance in accordance with the revised procedure manual acquired from the server device 20. For example, the wearable device 10 can refer to the revised procedure manual and provide audio instructions on the work to be performed by the worker. The wearable device 10 can also refer to the revised procedure manual and ask the worker audio questions about the work that has been performed. The worker performs the work according to the audio guidance output from the wearable device 10, checks the work that has been performed, and answers the questions from the wearable device 10 audio.

[0026] The wearable device 10 starts capturing and recording images when audio guidance corresponding to each work procedure is output. Because the wearable device 10 is worn by the worker, the images captured by the wearable device 10 are images from the worker's perspective (i.e., a first-person perspective). In this embodiment, the images captured by the wearable device 10 are videos captured at an appropriate frame rate, but may also be still images captured at appropriate time intervals. The images captured by the wearable device 10 include the work scene, the equipment being used, various measuring instruments, and the like. The sounds recorded by the wearable device 10 include any sounds generated at the work site, such as the voice of the worker, sounds emitted from the equipment being used, and environmental sounds. The sounds recorded by the wearable device 10 preferably include the audio from the audio guidance described above.

[0027] When one work procedure is completed, the wearable device 10 stops capturing images and recording audio. In this embodiment, image data and audio data are obtained for each work procedure. The image data and audio data for each work procedure are an example of work data in the present disclosure.

[0028] The work data may include image data and audio data for each work procedure, as well as data on work results input by the worker. The work results are input to the wearable device 10 as a voice response to an inquiry from the wearable device 10. The work result data may be voice data or may be text data converted by voice recognition.

[0029] The work data may include imaging data and acoustic data for each work procedure, as well as equipment data obtained for the equipment being worked on. The equipment data includes data on measurement values ​​measured for the equipment being worked on, such as current, voltage, electrical resistance, power, temperature, air volume, and air speed. The measurement values ​​may be values ​​measured by a measuring instrument or sensor equipped in the equipment being worked on, or may be values ​​measured by a worker using a measuring instrument or sensor. The equipment data may also be status data, error codes, etc. output from the equipment being worked on.

[0030] The wearable device 10 uploads the acquired work data to the server device 20 via the communication network NW.

[0031] The server device 20 may determine whether the work performed by the worker is appropriate based on the work result data uploaded by the wearable device 10. If the server device 20 determines that the work performed by the worker is appropriate, it can provide instructions to the wearable device 10 to encourage the worker to move on to the next work procedure. On the other hand, if the server device 20 determines that the work is inappropriate, it can provide instructions to the wearable device 10 to output audio guidance that encourages the worker to correct the work content, thereby guiding the worker to perform the work appropriately.

[0032] The worker may carry a mobile terminal such as a smartphone in addition to the wearable device 10. The mobile terminal has an input unit such as a touch panel and a display unit such as a liquid crystal display, and complements some of the functions that the wearable device 10 does not have. The mobile terminal is configured to be able to communicate with the wearable device 10 using short-range wireless communication such as Bluetooth (registered trademark) or ZigBee (registered trademark). The mobile terminal is also configured to be able to communicate with the server device 20 via the communication network NW.

[0033] 2 is a block diagram showing the internal configuration of wearable device 10. Wearable device 10 includes a control unit 11, a storage unit 12, a communication unit 13, an imaging unit 14, a sound input unit 15, a sound output unit 16, a sensor unit 17, and the like.

[0034] The control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The ROM included in the control unit 11 stores control programs and the like that control the operation of each hardware unit included in the wearable device 10. The CPU in the control unit 11 reads and executes the control programs and the like stored in the ROM, and controls the operation of each hardware unit, thereby causing the entire device to function as the terminal device of the present disclosure. The RAM included in the control unit 11 temporarily stores data used during the execution of various processes.

[0035] The control unit 11 may have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when an instruction to start measurement is given until when an instruction to end measurement is given, and a counter that counts numbers.

[0036] The storage unit 12 is equipped with an auxiliary storage device and stores various types of data as well as computer programs executed by the control unit 11. The data stored in the storage unit 12 includes work data (image data, acoustic data, processing result data, and equipment data) acquired for each work procedure. The computer programs stored in the storage unit 12 include a transmission control program that transmits the work data acquired for each work procedure to the server device 20.

[0037] The communication unit 13 includes a communication module for wireless communication with an external device such as the server device 20. The communication module may be a communication module for wireless communication using a known mobile communication standard such as 3G, 4G, or 5G, or a wireless LAN system such as WiFi (registered trademark). The communication unit 13 communicates with the external device such as the server device 20 via the communication network NW, and transmits necessary data such as work data, and receives appropriate data transmitted from the external device.

[0038] The communication unit 13 may include a communication module for short-range wireless communication such as Bluetooth (registered trademark) or ZigBee (registered trademark) in order to communicate with a mobile terminal such as a smartphone carried by the worker.

[0039] The imaging unit 14 includes an optical lens, an imaging element, a driver circuit, etc. A wide-angle lens is preferably used as the optical lens. The imaging element is a CMOS (Complementary Metal Oxide Semiconductor), a CCD (Charge-Coupled Device), etc., and generates an electrical signal according to the intensity of light imaged through the optical lens. The driver circuit includes a timing generator (TG), etc., and sequentially reads out the electrical signals from the imaging element in synchronization with a clock signal output from the TG to generate video data. The video data generated by the imaging unit 14 is sent to the control unit 11 and stored in the memory unit 12. The video data generated by the imaging unit 14 is also transmitted to the server device 20 via the communication unit 13.

[0040] The sound input unit 15 includes a microphone for collecting sound, a processing circuit for converting the collected sound into a digital signal (sound data), etc. The sound data generated by the sound input unit 15 is sent to the control unit 11, where it is subjected to appropriate processing such as noise removal, and then stored in the storage unit 12. The sound data that has been subjected to appropriate processing by the control unit 11 is also transmitted to the server device 20 via the communication unit 13.

[0041] The sound output unit 16 includes a speaker that outputs sound. The sound output unit 16 outputs sound based on acoustic data provided by the control unit 11.

[0042] The sensor unit 17 includes a non-contact sensor for detecting the worker's fingers and the like. The sensors included in the sensor unit 17 include a proximity sensor, a gesture sensor, and the like. The proximity sensor detects, for example, when the worker's fingers approach within a predetermined range. The gesture sensor detects, for example, the movement of the worker's fingers. The detection result by the sensor unit 17 is notified to the control unit 11. The control unit 11 may control the operation of the wearable device 10 based on the detection result by the sensor unit 17.

[0043] 3 is a block diagram showing the internal configuration of the server device 20. The server device 20 is a dedicated or general-purpose server device, and includes, for example, a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25.

[0044] The control unit 21 includes a CPU, a ROM, a RAM, etc. The ROM included in the control unit 21 stores a control program and the like that controls the operation of each hardware unit included in the server device 20. The CPU in the control unit 21 reads and executes the control program stored in the ROM and a computer program (described below) stored in the storage unit 22, and executes processing to control the operation of each hardware unit, thereby causing the entire device to function as the server device 20 of the present disclosure. The RAM included in the control unit 21 temporarily stores data used during the execution of various processes.

[0045] In the embodiment, the control unit 21 is configured to include a CPU, a ROM, and a RAM, but the configuration of the control unit 21 is not limited to the above. The control unit 21 may be one or more processing circuits including, for example, a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), a quantum processor, volatile or non-volatile memory, etc. The control unit 21 may also have functions such as a clock that outputs date and time information, a timer that measures the elapsed time from when a measurement start instruction is given until when a measurement end instruction is given, and a counter that counts numbers.

[0046] The storage unit 22 includes a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 22 stores various computer programs executed by the control unit 21 and various data used when the computer programs are executed. The computer programs stored in the storage unit 22 include a procedure generation program PG that causes a computer to execute a process of acquiring attribute information indicating the attributes of a worker who will perform a task, generating work procedure information according to the worker's attributes using a language model MD that references the acquired attribute information and standard procedure information indicating a standard procedure for the task, and outputting the generated work procedure information.

[0047] A computer program including the procedure generation program PG may be provided by a non-transitory recording medium RM on which the computer program is readably recorded. The recording medium RM is a portable memory such as a CD-ROM, a USB memory, an SD card, a micro SD card, or a CompactFlash (registered trademark). The control unit 21 reads various computer programs from the recording medium RM using a reading device (not shown) and stores the read various computer programs in the storage unit 22. The computer programs stored in the storage unit 22 may also be provided by communication. In this case, the control unit 21 acquires the computer programs by communication via the communication unit 23 and stores the acquired computer programs in the storage unit 22.

[0048] The procedure generation program PG may be a single computer program or may be composed of multiple computer programs. The procedure generation program PG may be executed by a single computer or may be executed cooperatively by multiple computers (e.g., the server device 20 and the LLM server 30). Furthermore, the procedure generation program PG may partially use an existing library.

[0049] The storage unit 22 also includes a work management table TB, an attribute database DB1, and a standard procedure database DB2. The contents stored in the work management table TB, the attribute database DB1, and the standard procedure database DB2 will be specifically described with reference to FIGS.

[0050] The communication unit 23 includes a communication module for wireless communication with an external device such as the wearable device 10. The communication module may be a communication module for wireless communication using a known mobile communication standard such as 3G, 4G, or 5G, or a wireless LAN system such as WiFi (registered trademark). The communication unit 23 communicates with an external device such as the wearable device 10 via the communication network NW, receives data such as a visual field image (video data), and transmits appropriate data to be transmitted to the external device. The communication unit 23 may further include a communication module for short-range wireless communication such as Bluetooth (registered trademark) or ZigBee (registered trademark).

[0051] The operation unit 24 is equipped with operation devices such as a touch panel, a keyboard, and switches, and receives various inputs and operations from a work manager, etc. The control unit 21 acquires information input through the operation unit 24 and performs appropriate control based on various operation information provided by the operation unit 24.

[0052] The display unit 25 includes a display device such as a liquid crystal monitor or an organic EL (Electro-Luminescence) monitor, and displays information to be notified to the work manager or the like in response to an instruction from the control unit 21.

[0053] The server device 20 may be a single computer, or may be a computer system configured with multiple computers and peripheral devices, etc. The server device 20 may also be a virtual machine whose entity is virtualized, or may be a cloud.

[0054] FIG. 4 is a conceptual diagram showing an example of a work management table TB. The work management table TB is a table for managing work performed by workers. The work management table TB stores, for example, the work name, model name, work date and time, worker ID, standard procedure manual ID, supplementary information, equipment data, and procedure manual transmission destination in association with one another. The work name is the name of the work to be performed by the worker. The model name is the name of the model to be worked on. The work date and time includes the start date and time of the work. The worker ID is an identifier for identifying the worker. Multiple worker IDs may be assigned to one work. The standard procedure manual ID is an identifier for identifying the standard procedure manual for that work. The standard procedure manual is created separately by a work manager or the like and registered in the standard procedure database DB2 in association with the standard procedure manual ID.

[0055] Supplementary information is supplementary information related to the work. Examples of supplementary information include service guides, instruction manuals, installation manuals, past failures, and recent trend information for the equipment being worked on. Supplementary information may also include information about the equipment being worked on, its intended use, its age, and past repair history. Supplementary information may also include information about peripheral devices connected to the equipment being worked on (e.g., fan coil units, thermostats, filters, and third-party components and devices). Supplementary information may also include information about the property where the equipment being worked on is installed (information about the property's intended use, ambient temperature, wind speed, and solar radiation conditions), information about the work site (information about the installation location, such as installation height and distance from the wall), and information about time constraints for the work. Supplementary information may be registered as a link to an electronic document or as text data.

[0056] The equipment data is data obtained about the equipment to be worked on, and includes data such as control values ​​input to the equipment to be worked on and measurement values ​​measured about the equipment to be worked on. The equipment data may also include image data captured in advance at the work site and audio data recorded in advance at the work site. The equipment data is registered as a link to electronic data.

[0057] The procedure manual destination indicates the destination of the revised procedure manual. The server device 20 uses the language model MD to generate a revised procedure manual according to the attributes of the worker, and transmits the generated revised procedure manual to the wearable device 10 worn by the worker. The communication address of the wearable device 10 is specified as the destination of the revised procedure manual.

[0058] Of the information registered in the work management table TB, the work name, model name, work date and time, worker ID, standard procedure manual ID, and procedure manual transmission destination are registered in advance by the work manager, etc. Supplementary information is not required, but if there is information that needs to be registered, it is registered in advance by the work manager, etc. Equipment data is also not required, but if it is obtained at the work site before the start of work, it is registered in advance by the worker, etc.

[0059] FIG. 5 is a conceptual diagram showing an example of the attribute database DB1. The attribute database DB1 is a database that stores attribute information of workers in association with worker IDs. In the example of FIG. 5, the attribute information stored includes the worker's proficiency, qualifications, work speed, and evaluation of the worker (rate of multiple service visits, rate of free multiple part replacements, rate of paid services, average number of visits, and rate of call center (CC) inquiries). The attribute database DB1 may store any one of these pieces of attribute information.

[0060] Proficiency is an index showing the worker's overall level of proficiency in the work. In the example of FIG. 5, two levels, high and low, are used as indicators. However, three or more levels may be used as indicators, and years of experience may also be used as indicators. Furthermore, proficiency does not necessarily have to be assigned to a single worker. For example, proficiency may be assigned for each type of air conditioner, such as a residential air conditioner, commercial air conditioner, or air purifier, or for each type of refrigeration system, such as a direct expansion type or an indirect expansion type. Qualifications indicate whether or not the worker has a public qualification or a qualification obtained through an in-house certification test. Information on the type of qualification held by the worker may also be included. Work speed indicates the number of days required to complete a task. Alternatively, a relative indicator, such as fast or slow, may be used to indicate work speed.

[0061] The multiple service rate indicates the rate at which a customer requests the same work after the work is completed. The rate of free multiple part replacement indicates the rate at which parts are replaced without charging the customer. This indicator is based on the fact that if part A is broken but part B is replaced without improving the situation, the cost of part B cannot be charged. The paid rate indicates the rate at which work is performed for which a fee can be charged, rather than work that is free of charge. The average number of visits indicates the average number of visits to the work site per work. The call center inquiry rate indicates the rate at which customers make repeat inquiries to the call center after the work has been completed.

[0062] In addition to the information shown in Figure 5, the worker attribute information may include information such as the customer's subjective evaluation (friendliness, etc.), self-reported evaluation, the number of tasks performed in the past, efforts to visit in the shortest time possible, efforts to adjust remaining tasks in the shortest time possible, efforts to gradually reduce estimate completion, efforts to complete estimated and ordered tasks in the shortest time possible, proposals to customers (refurbished base proposals, use of refrigerant leak prevention agents, etc.), promotion of the use of specific parts (right-side discharge heat exchangers), and part return rate.

[0063] FIG. 6 is a conceptual diagram showing an example of the standard procedure database DB2. The standard procedure database DB2 is a database that stores standard procedures in association with standard procedure IDs. A standard procedure exists for each model and classification of equipment to be worked on and each type of work (inspection work, repair work, installation work, trial operation work, disposal work, etc.), and is composed of standard work procedures for that work. The standard procedure database stores, for example, a procedure number, type, classification, and text in association with each other. The procedure number indicates the order of the procedure. The type indicates whether it is guidance or question. If the type is a question, it indicates a procedure that requires a response from the worker. The questions exemplified by procedure numbers "02" to "06" in FIG. 6 all indicate questions that can be answered with YES or NO. The classification indicates the work target (outdoor unit, indoor unit, controller, tank, etc.). The text is a text version of the audio guidance output from the wearable device 10, and indicates the work that the worker should perform in that procedure.

[0064] Although FIG. 6 shows examples of questions that can be answered with YES or NO, questions that expect answers by inputting numerical values ​​such as temperature or pressure, or questions that expect answers by inputting text such as error codes or free description may also be registered.

[0065] The attribute database DB1 and the standard procedure database DB2 may be provided outside the server device 20 as long as they are accessible from the server device 20. Furthermore, the attribute database DB1 and the standard procedure database DB2 may be accessible from the LLM server 30.

[0066] The server device 20 generates a revised procedure manual using a language model MD that references the attribute information of the worker and the standard procedure manual for the work performed by the worker. FIG. 7 is an explanatory diagram illustrating an example of generating a revised procedure manual. The attribute information of the worker referenced by the language model MD and the standard procedure manual for the work performed by the worker are specified by the server device 20. For example, when generating a revised procedure manual for the work (inspection work) registered as the first record in the work management table TB of FIG. 4, the server device 20 searches the attribute database DB1 using the worker ID (USER001 in this example) as a search key and acquires the attribute information of the corresponding worker. The server device 20 specifies the attribute information acquired from the attribute database DB1 as the attribute information of the worker to be used when generating the revised procedure manual. Furthermore, by referring to the work management table TB, it is found that the standard procedure manual ID for the inspection work is "SM001." Therefore, the server device 20 specifies the standard procedure manual for "SM001" as the standard procedure manual to be used when generating the revised procedure manual.

[0067] The language model MD generates a revised procedure manual by referencing the attribute information of the worker specified by the server device 20 and the standard procedure manual. The language model MD is a deep learning learning model configured to output an answer sentence (text data) in response to an input question sentence (text data). The language model MD uses existing language models (large-scale language models) such as GPT-4 (Generative Pretrained Transformer 4), LLaMA (Large Language Model Meta AI), and BERT (Bidirectional Encoder Representations from Transformers). The language model MD is not limited to the above language models, and may also be a unique language model tuned from an existing language model. Furthermore, the language model MD may be a multimodal language model that can input measurement data, imaging data, acoustic data, etc. obtained regarding the equipment to be worked on in addition to text data.

[0068] The revised procedure manual generated by the language model MD is a revision of the standard procedure manual according to the worker's attribute information. A worker with the worker ID "USER001" has attributes such as high proficiency, qualifications, fast work speed, and high evaluation of the work. Therefore, as shown in Figure 7, the explanation of some work steps (e.g., step 01) may be omitted, and some work steps (e.g., step 03) may be skipped. Even in the revised procedure manual for a highly skilled worker, an additional step (step 04+α) may be added from the standard procedure manual. Although not shown in Figure 7, for a worker with attributes such as low proficiency, no qualifications, slow work speed, or low evaluation of the work, the explanation of some work steps may be detailed, and preliminary work steps may be added to some work steps.

[0069] Figure 7 describes an example of revising a standard procedure manual by referring to worker attribute information, but it is also possible to specify that supplementary information or equipment data registered in the work management table TB be referenced in addition to the worker attribute information, and generate a revised procedure manual that takes into account the supplementary information or equipment data.

[0070] For example, if past examples of breakdowns or recent trend information are specified as supplementary information, additional procedures may be added to prevent problems that are likely to occur in the equipment being worked on. Also, if information on peripheral equipment, properties, work sites, etc. is specified as supplementary information, additional procedures may be added based on information that can only be determined at the work site. Furthermore, if equipment data is specified, additional procedures may be added to resolve problems that have already occurred in the work equipment.

[0071] In order to generate the above-described revised procedure manual, the server device 20 generates input data (prompts) for the language model MD. FIG. 8 is a schematic diagram showing an example of a prompt to be input to the language model MD. As a prompt to be input to the language model MD, the server device 20 generates a prompt that instructs, for example, that the role is the manager of the work process, that the worker's attribute information listed in the reference information column should be referenced, that a base standard procedure manual (in the example of FIG. 8, the standard procedure manual for SM0001) is registered in the standard procedure database DB2, and that a revised procedure manual should be created by revising the standard procedure manual in accordance with the worker's attributes. The server device 20 generates such a prompt and transmits it to the LLM server 30 via the communication network NW.

[0072] The LLM server 30 inputs the prompt received from the server device 20 into the language model MD and obtains a revision procedure manual that is output as a response sentence from the language model MD. The LLM server 30 returns the revision procedure manual to the server device 20. The server device 20 receives the revision procedure manual sent from the LLM server 30. The server device 20 can generate the revision procedure manual by using the language model MD provided in the LLM server 30.

[0073] While Fig. 8 shows an example of a prompt for creating a revised procedure manual by referring to the worker's attribute information, the same applies to prompts for creating a revised procedure manual by referring to supplementary information or equipment data in addition to the attribute information. That is, the supplementary information or equipment data to be referenced can be listed in the reference information field. If the supplementary information or equipment data to be referenced exists as a data file, a link to that data file can be specified as the reference information.

[0074] The process executed by the server device 20 will be described below. 9 is a flowchart illustrating the procedure of the process executed by the server device 20. The control unit 21 of the server device 20 refers to the work management table TB and selects a work for which a revised procedure manual is to be created (step S101). For example, the control unit 21 checks the work date and time column in the work management table TB and selects a work that will start in the near future.

[0075] The control unit 21 reads out the worker ID and standard procedure manual ID registered in association with the selected work from the work management table TB (step S102). The control unit 21 searches the attribute database DB1 using the read worker ID as a search key, and reads out the attribute information of the corresponding worker from the attribute database DB1 (step S103).

[0076] The control unit 21 generates a prompt to be input to the language model MD based on the information read in steps S102 and S103 (step S104). The control unit 21 generates, as the prompt to be input to the language model MD, a prompt that instructs, for example, that the role is the manager of the work process, that the attribute information of the worker listed in the prompt should be referenced, that a base standard procedure manual is registered in the standard procedure database DB2, and that a revised procedure manual that revises the standard procedure manual should be created in accordance with the worker's attributes. If supplemental information or equipment data is registered in the work management table TB, the control unit 21 may generate a prompt that specifies a reference to the supplemental information or equipment data in addition to the attribute information.

[0077] The control unit 21 transmits the generated prompt to the LLM server 30 via the communication network NW (step S105). When the LLM server 30 receives the prompt, it inputs the received prompt into the language model MD and generates a response sentence (a revised procedure manual in this embodiment) using the language model MD. The LLM server 30 returns the revised procedure manual obtained from the language model MD to the server device 20 via the communication network NW.

[0078] The control unit 21 receives the revised procedure manual returned from the LLM server 30 after sending the prompt (step S106). The control unit 21 identifies a destination of the received revised procedure manual by referring to the work management table TB (step S107). The control unit 21 transmits the revised procedure manual received in step S106 to the destination (wearable device 10) identified in step S107 (step S108).

[0079] The wearable device 10 receives the revised procedure manual transmitted from the server device 20, and provides audio guidance in accordance with the received revised procedure manual.

[0080] As described above, in the embodiment, revised procedures for each worker can be automatically created based on the standard procedure manual, thereby reducing the man-hours required for creating the procedure manual. For highly skilled workers, unnecessary voice guidance and work procedures can be omitted. For less experienced workers, detailed explanations of work procedures can be provided, which is expected to improve the quality and speed of work.

[0081] In this embodiment, a single language model MD is used to generate a revised procedure manual. However, for example, a first language model configured to output procedure information based on worker attribute information, a second language model configured to output procedure information based on supplementary information, a third language model configured to output procedure information based on equipment data, and a main language model that generates the final revised procedure manual to be presented to the worker based on the procedure information output from the first to third language models may be prepared, and a multi-agent mechanism in which these language models cooperate to generate the revised procedure manual may be used. The first language model generates a procedure with steps or explanations added (or omitted) based on the worker's attributes. The second language model may generate additional procedures to prevent malfunctions that are likely to occur in the equipment to be worked on based on past cases such as breakdowns and recent trend information. The third language model may generate additional procedures to resolve malfunctions that have already occurred in the work equipment. The main language model may generate a single revised procedure manual that integrates these procedures.

[0082] In this embodiment, a revised procedure manual is generated according to the attribute information of the worker, but the server device 20 may also receive a request from the worker himself / herself, generate a prompt instructing the server device 20 to create a revised procedure manual that takes into account the worker's request, and transmit the generated prompt to the LLM server 30. The worker may use his / her own terminal to issue a request to the server device 20, such as requesting more explanation or less explanation. The server device 20 can generate a revised procedure manual with more explanation (or less explanation) by transmitting a prompt generated in accordance with such a request to the LLM server 30.

[0083] The embodiments disclosed herein should be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0084] 10. Wearable Devices 20 Server device 21 Control Unit 22 Memory section 23 Communications Department 24 Control section 25 Display section 30 LLM Servers PG Procedure Generator TB Work Management Table DB1 Attribute Database DB2 Standard Procedure Database MD language model

Claims

1. Acquire attribute information indicating the attributes of the worker who will perform the work; acquiring at least one of image data captured at a work site and sound data recorded at the work site; generating work procedure information according to the attributes of the worker using one or more language models that refer to the acquired attribute information, standard procedure information indicating a standard procedure for the work, and at least one of the acquired data; Output the generated work procedure information An information processing method in which processing is carried out by a computer.

2. The attribute information includes at least one of the worker's skill level, qualifications, work speed, and evaluation of the worker. The information processing method according to claim 1 .

3. The evaluation includes at least one of a multiple service rate, a rate of free replacement of multiple parts, a rate of charging for the service, an average number of visits, and a rate of inquiries to a call center. The information processing method according to claim 2 .

4. Further obtaining at least one of information about the work, information about the equipment to be worked on, information about past cases of the work, and supplementary information about the standard procedure; generating work procedure information according to the attributes of the worker using a language model that references the attribute information, the standard procedure information, and at least one of the acquired information; 2. The information processing method according to claim 1, wherein the processing is executed by the computer.

5. The information about the work includes at least one of information about a work site and information about time constraints in the work. The information processing method according to claim 4.

6. The information about the device includes at least one of configuration information about the device, a measurement value measured about the device, a control value input to the device, and a usage purpose of the device. The information processing method according to claim 4.

7. Accepting a worker's request for work procedure information; Using the language model, work procedure information is generated in accordance with the received worker request.

2. The information processing method according to claim 1, wherein the processing is executed by the computer.

8. At least one control unit is provided, The control unit Acquire attribute information indicating the attributes of the worker who will perform the work; acquiring at least one of image data captured at a work site and sound data recorded at the work site; generating work procedure information according to the attributes of the worker using one or more language models that refer to the acquired attribute information, standard procedure information indicating a standard procedure for the work, and at least one of the acquired data; Output the generated work procedure information Information processing device.

9. A terminal device of a worker; a server device communicably connected to the terminal device and including a storage unit for storing standard procedure information indicating a standard procedure for work; Equipped with The server device acquiring attribute information indicating attributes of a worker who will perform the work; acquiring at least one of image data captured at a work site and sound data recorded at the work site; generating work procedure information according to the attributes of the worker who will perform the work, using one or more language models that refer to the acquired attribute information, the standard procedure information stored in the storage unit, and at least one of the acquired data; Output the generated work procedure information Information processing system.

10. Acquire attribute information indicating the attributes of the worker who will perform the work; acquiring at least one of image data captured at a work site and sound data recorded at the work site; generating work procedure information according to the attributes of the worker using one or more language models that refer to the acquired attribute information, standard procedure information indicating a standard procedure for the work, and at least one of the acquired data; Output the generated work procedure information A computer program that causes a computer to execute a process.

Citation Information

Patent Citations

  • Information processing apparatus, information processing system, information processing method, and information processing program

    JP2017126292A

  • Inspection work support system, method, and program

    JP2019057099A

  • Manual management device, manual management system, and control program

    JP2020004274A

  • Maintenance work support device, maintenance work support method, maintenance work support program, and recording medium

    JP2020035497A

  • Information processing method, computer program, and information processing device

    WO2023182424A1