Handling task support apparatus, handling task support method, and handling task support program

The response work support device uses a generative AI model to process user requests and generate actionable information, addressing inefficiencies in service provider responses, thereby reducing waiting times and enhancing user satisfaction.

JP2026005253AActive Publication Date: 2026-01-16MITSUBISHI ELECTRIC CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024103457
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2026-01-16
Estimated Expiration
2044-06-27

AI Technical Summary

Technical Problem

Existing systems fail to efficiently support service providers in responding to diverse user requests, particularly in situations like train suspensions, leading to prolonged waiting times and reduced user satisfaction.

Method used

A response work support device utilizing a generative AI model to process user requests, generate corresponding actions for service providers, and provide actionable information through code generation, reducing the burden on staff by enhancing response efficiency.

Benefits of technology

The system significantly reduces the time required to respond to user requests, improving user satisfaction by enabling quicker and more accurate service provider actions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026005253000001_ABST
    Figure 2026005253000001_ABST
Patent Text Reader

Abstract

To reduce a burden on a service providing side for dealing with a user.SOLUTION: A response task support device 10 receives input of desired information D2 indicating action contents desired by users. The dealing work support device 10 inputs the received desired information D2 to a dealing generation model 31 which is a learning model, and acquires dealing information D6 which is the dealing information D2 output by the dealing generation model 31 and indicates dealing contents on the service providing side for achieving the action contents indicated by the desired information D6. The dealing service support device 10 generates code information D6 for displaying the acquired dealing information D7, and outputs it to the user terminals 36. The clerk terminals 37 read the code information D7 displayed on the user terminals 36 and display the corresponding information D6.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present disclosure relates to a technology for supporting service providers in their work to respond to users. [Background technology]

[0002] At various locations, such as train stations, airports, government offices, and hospitals, service providers' staff respond to requests from users. When an irregular situation occurs, staff must respond to many users. Requests from users can be diverse, and staff may take a long time to respond to each one. As a result, users may be kept waiting for a long time, which may reduce user convenience and satisfaction.

[0003] For example, at train stations, station staff respond to various requests from passengers. In order to respond appropriately to requests from passengers, station staff need to correctly understand the content of the request and the passenger's condition, organize the tasks that need to be done, and then take action. When trains are suspended due to an accident or other reason, many passengers request assistance from station staff. The request and situation vary from passenger to passenger. As a result, station staff take time to assist each passenger. As a result, passengers seeking assistance end up lining up in long queues.

[0004] Patent Document 1 describes a ticket vending machine that provides users with appropriate guidance information regarding transfers and the like. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-168003 Summary of the Invention [Problem to be solved by the invention]

[0006] The technology described in Patent Document 1 may be useful for helping passengers transfer. However, the technology described in Patent Document 1 is not a technology that can respond to various requests from passengers. In cases where train service is suspended due to an accident or other reason, the burden on station staff in responding to passengers cannot be fully reduced. The present disclosure aims to reduce the burden on service providers in dealing with users. [Means for solving the problem]

[0007] The response work support device according to the present disclosure comprises: an input unit that accepts input of desired information indicating the content of an action desired by a user; a model control unit that inputs the desired information received by the input unit into a correspondence generation model that is a learning model, and acquires correspondence information output by the correspondence generation model, the correspondence information indicating correspondence details on the service provider side that realizes the action details indicated by the desired information; a code generation unit that generates code information for displaying the correspondence information acquired by the model control unit; Equipped with. [Effects of the Invention]

[0008] In the present disclosure, desired information indicating the content of an action is input into a response generation model to obtain response information indicating the response content of the service provider that will realize the content of the action, and code information for displaying the response information is generated. The code information is presented to an attendant at the service provider and read by the attendant, allowing the attendant to understand the response information. This allows the attendant at the service provider to identify the response content required to respond to various requests from users, thereby reducing the burden on the service provider in responding to users. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a configuration diagram of a response work support system 100 according to a first embodiment. [Figure 2]1 is a configuration diagram of a response work support device 10 according to a first embodiment. [Figure 3] 10 is a flowchart of information setting processing according to the first embodiment. [Figure 4] FIG. 3 is an explanatory diagram of operation information D1 according to the first embodiment. [Figure 5] 10 is a flowchart of correspondence acquisition processing according to the first embodiment. [Figure 6] FIG. 4 is an explanatory diagram of desired information D2 according to the first embodiment. [Figure 7] FIG. 10 is an explanatory diagram of sorting information D3 according to the first embodiment. [Figure 8] FIG. 4 is an explanatory diagram of machine information D4 according to the first embodiment. [Figure 9] 10 is a flowchart of a cancellation refund process according to the first embodiment. [Figure 10] FIG. 10 is an explanatory diagram of correspondence information D6 in the case of cancellation refund processing according to the first embodiment. [Figure 11] FIG. 10 is an explanatory diagram of correspondence information D6 in the case of cancellation refund processing according to the first embodiment. [Figure 12] FIG. 10 is an explanatory diagram of information output in the case of cancellation refund processing according to the first embodiment. [Figure 13] 4 is a flowchart of a time change process for a designated train according to the first embodiment. [Figure 14] FIG. 10 is an explanatory diagram of correspondence information D6 for the time change process of the designated train according to the first embodiment. [Figure 15] FIG. 4 is an explanatory diagram of information output in the case of a time change process for a designated train according to the first embodiment. [Figure 16] 4 is a flowchart of an alternative route proposing process according to the first embodiment. [Figure 17] FIG. 10 is an explanatory diagram of correspondence information D6 for the alternative route proposal processing according to the first embodiment. [Figure 18] FIG. 4 is an explanatory diagram of information output in the case of the alternative route proposal process according to the first embodiment. [Figure 19] 4 is a flowchart of a response support process according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Embodiment 1 In the first embodiment, an example will be described in which the response work support system 100 is applied to responding to requests from users at a railway station.

[0011] ***Configuration Description*** The configuration of a response work support system 100 according to the first embodiment will be described with reference to FIG. The response work support system 100 comprises a response work support device 10, a response generation model 31, an operation information system 32, a fare calculation system 33, a seat management system 34, a work support system 35, a user terminal 36, and an attendant terminal 37.

[0012] The response work support device 10 is a computer that performs processing to support the work of the service provider. The response generation model 31 is a learning model that receives desired information indicating the content of an action as input and outputs response information D6 indicating the response content of the service provider that will realize the content of the action. The operation information system 32 is a system that manages the operation status of trains. The fare calculation system 33 is a system that calculates train fares. The seat management system 34 is a system that manages the reservation status of reserved seats, etc. on trains. The work support system 35 is a system for storing response information D6 indicating the work of the service provider. The user terminal 36 is a computer used by a user, such as a smartphone. The staff terminal 37 is a computer used by a station staff member, such as a tablet terminal.

[0013] The learning model is what is known as generative AI. AI stands for artificial intelligence. The learning model may be constructed using algorithms such as BERT and GPT, for example. BERT stands for Bidirectional Encoder Representations from Transformers. GPT stands for Generative Pretrained Transformer. The learning model may be constructed by combining multiple algorithms, including these algorithms.

[0014] The configuration of the response work support device 10 according to the first embodiment will be described with reference to FIG. The response work support device 10 includes hardware such as a processor 11, a memory 12, a storage 13, and a communication interface 14. The processor 11 is connected to other hardware via signal lines and controls the other hardware.

[0015] The processor 11 is an IC that performs processing. IC stands for Integrated Circuit. Specific examples of the processor 11 include a CPU, a DSP, and a GPU. CPU stands for Central Processing Unit. DSP stands for Digital Signal Processor. GPU stands for Graphics Processing Unit.

[0016] The memory 12 is a storage device that temporarily stores data. Specific examples of the memory 12 include SRAM and DRAM. SRAM stands for Static Random Access Memory. DRAM stands for Dynamic Random Access Memory.

[0017] The storage 13 is a storage device that stores data. A specific example of the storage 13 is an HDD. HDD is an abbreviation for Hard Disk Drive. The storage 13 may also be a portable recording medium such as an SD (registered trademark) memory card, CompactFlash (registered trademark), NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a DVD. SD is an abbreviation for Secure Digital. DVD is an abbreviation for Digital Versatile Disk.

[0018] The communication interface 14 is an interface for communicating with external devices. Specific examples of the communication interface 14 include Ethernet (registered trademark), USB, and HDMI (registered trademark) ports. USB stands for Universal Serial Bus. HDMI stands for High-Definition Multimedia Interface.

[0019] The response work support device 10 includes, as functional components, an input unit 21, a model control unit 22, a fare determination unit 23, a reservation confirmation unit 24, a code generation unit 25, and an output unit 26. The functions of each functional component of the response work support device 10 are realized by software. The storage 13 stores a program that realizes the function of each functional component of the response work support device 10. This program is read into the memory 12 by the processor 11 and executed by the processor 11. As a result, the function of each functional component of the response work support device 10 is realized.

[0020] 2 shows only one processor 11. However, there may be a plurality of processors 11, and the plurality of processors 11 may cooperate to execute programs that realize the respective functions.

[0021] ***Explanation of Operation*** The operation of the response work support device 10 according to the first embodiment will be described with reference to FIGS. The operation procedure of the response work support device 10 according to the embodiment 1 corresponds to the response work support method according to the embodiment 1. Moreover, the program that realizes the operation of the response work support device 10 according to the embodiment 1 corresponds to the response work support program according to the embodiment 1.

[0022] The operations of the response work support device 10 according to the first embodiment include information setting processing, response acquisition processing, and response support processing.

[0023] The information setting process according to the first embodiment will be described with reference to FIG. The information setting process is executed periodically or when there is a change in the train operation status, such as when there is a train service suspension or delay due to an accident, weather, or the like.

[0024] (Step S11: Inquiry processing) The input unit 21 inquires of the operation information system 32 about operation information D1 indicating the latest operation status. Then, the input unit 21 acquires the operation information D1 from the operation information system 32.

[0025] The operation information D1 is set for each route. As shown in Fig. 4, each operation information D1 includes the update date and time, the route name, the status, the affected area, the delay time, the expected recovery time, and the reason. The update date and time is the date and time when the operation information D1 was updated. The route name is the route that the operation information D1 covers. The status indicates the status of the target route, such as whether it is normal, delayed, or suspended. The affected area is the area of ​​the target route that is affected by the delay or suspension. The affected area is shown by the station section. The delay time indicates the length of the delay when the status is delayed. The expected restoration date indicates the estimated time when service will start when the status is suspended. If the estimated time when service will start is unknown, the expected restoration date may be set to no date or suspended for the entire day. The reason indicates the reason for the delay or suspension when the status is delayed or suspended.

[0026] (Step S12: Setting process) The input unit 21 provides the operation information D1 acquired in step S11 to the correspondence generative model 31. Providing the operation information D1 to the correspondence generative model 31 means that the correspondence generative model 31 can access the operation information D1.

[0027] The correspondence acquisition process according to the first embodiment will be described with reference to FIG. The correspondence acquisition process is executed every time a user instructs execution of the process.

[0028] Here, we assume a situation where a delay or cancellation has occurred due to an accident or other reason. However, the response acquisition process can also be executed when no delay or cancellation has occurred. We assume that the user's requests include ticket cancellation and refund, a change in the timetable of the designated train, and a suggestion of an alternative route. However, other requests may also be made.

[0029] (Step S21: Input reception process) The input unit 21 receives input of desired information D2 indicating the desired activity of a railway user. Specifically, the user operates the user terminal 36 to input desired information D2. The input unit 21 accepts the desired information D2 input from the user terminal 36. The desired information D2 may be voice data or text data. The desired information D2 may be input in any language. The desired information D2 may be in a natural language, and the order of the data included in the desired information D2 may be arbitrary.

[0030] As shown in FIG. 6, the desired information D2 includes the request content, the route to be taken, the departure station and the arrival station, ticket information, the ticket type, the ticket gate status, and location information. The request content is the request made by the user. Here, it is assumed that the request content is either ticket cancellation and refund, a change in the timetable of the designated train, or a proposal for an alternative route. The route to be taken is the route the user is boarding or currently boarding. The departure station and arrival station are the user's departure station and arrival station. The ticket information is the designated train number, reserved seat number, etc. The ticket type indicates whether the ticket is an IC card or a paper ticket. The ticket gate status indicates whether the ticket has been gated or is not yet gated. The location information indicates the location of the user terminal 36 determined by the user terminal 36 based on a positioning signal, etc. Note that the ticket gate status, such as whether the user is inside or outside the ticket gate, and the location information, such as where the user is within the station, may be determined from a dialogue with the user.

[0031] (Step S22: Desired information input process) The model control unit 22 inputs the desired information D2 input in step S21 to the correspondence generation model 31. Here, as described above, the train operation information D1 is provided to the correspondence generation model 31. The operation information D1 shown below is referenced when the dialogue generation model 31 generates the correspondence information D6. At this time, the model control unit 22 issues an instruction to organize the desired information D2 and generate organized information D3 for a person to understand the contents and machine information D4 for processing by a computer.

[0032] (Step S23: Output information acquisition process) The model control unit 22 acquires the sorting information D3 and the machine information D4 output by the correspondence generation model 31 in response to the desired information D2 input in step S22.

[0033] The organized information D3 is information that has been organized from the desired information D2. The organized information D3 is information that is intended for a person to understand the contents. For example, suppose that the desired information D2 is input in conversational language. In this case, as shown in FIG. 7, the organized information D3 is information that is itemized by extracting the request content, the route to be taken, the departure station, the arrival station, the ticket information, the ticket type, the ticket gate status, and the location information from the conversational language. The organized information D3 may be voice data or text data. The sentences may be generated in the input language. The location information is expressed in sentences as to which station and where.

[0034] Like the organized information D3, the machine information D4 is organized information of the desired information D2. The machine information D4 is information that is intended to be processed by a computer. Therefore, the machine information D4 is in a format that is easy to process by a computer, such as JSON format or XML format. JSON is an abbreviation for JavaScript Object Notation. XML is an abbreviation for Extensible Markup Language. For example, as shown in Fig. 8, the machine information D4 is configured by decomposing the organized information D3 shown in Fig. 7. In Fig. 8, the information is simply decomposed and itemized, but in reality, it is written in JSON format, XML format, or the like.

[0035] At this time, if there is missing information in the desired information D2, the correspondence generation model 31 also outputs a question D5 that fills in the missing information. When the question D5 is output, the model control unit 22 also acquires the question D5.

[0036] (Step S24: Final determination process) The model control unit 22 determines whether the request content of the user has been finalized. Specifically, if the question sentence D5 has not been output, the model control unit 22 determines that the request content has been finalized. On the other hand, if the question sentence D5 has been output, the model control unit 22 determines that the request content has not been finalized. If the request content has been finalized, the model control unit 22 proceeds to step S25. On the other hand, if the request content has not been finalized, the model control unit 22 outputs a question D5 to the user terminal 36 and displays it. The model control unit 22 may also accept an inquiry from the user. In response, the model control unit 22 prompts the user to input missing information. The model control unit 22 then returns the process to step S21 and accepts input of additional information for the request content. The additional information may include an inquiry from the user.

[0037] The model control unit 22 outputting question D5 to the user terminal 36 for display means that the model control unit 22 causes the output unit 26 to output and display question D5. Furthermore, the model control unit 22 prompting the user to input missing information, accepting an inquiry from the user, and accepting input of additional information for the request means that the model control unit 22 causes the input unit 21 to accept the user's response to the question, accept the inquiry from the user, and input it into the model control unit 22 as additional information. The model control unit 22 returns the processing to step S21, and when it receives input of additional information for the request content, it inputs the desired information with the additional information added to the correspondence generation model 31 and obtains the correspondence information output from the correspondence generation model.

[0038] (Step S25: Request determination process) The model control unit 22 determines whether the request is for ticket cancellation and refund, a change in the timetable of the designated train, or a proposal for an alternative route. If the request is for ticket cancellation and refund, the model control unit 22 proceeds to step S26. If the request is for a time change of the designated train, the model control unit 22 proceeds to step S27. If the request is for a proposal of an alternative route, the model control unit 22 proceeds to step S28.

[0039] The cancellation refund process (step S26 in FIG. 5) according to the first embodiment will be described with reference to FIG. (Step S31: Correspondence information generation process) The model control unit 22 inputs the organized information D3, which is generated when the request content is finalized, to the correspondence generation model 31, along with an instruction to generate correspondence information D6. Then, the model control unit 22 acquires the correspondence information D6 output by the correspondence generation model 31. The correspondence information D6 indicates the correspondence content of the service provider that realizes the action content indicated by the desired information D2. Here, the correspondence information D6 is a sentence indicating the specific processing content when a cancellation refund is made, as shown in FIG.

[0040] (Step S32: Amount calculation process) The fare determination unit 23 inputs the partial information of the departure station, intermediate stations, and arrival station from the machine information D4 when the request content is confirmed into the fare calculation system 33. Then, the fare determination unit 23 obtains the fare based on the departure station, intermediate stations, and arrival station from the fare calculation system 33 as the refund amount. The fare determination unit 23 sets the acquired refund amount in the corresponding information D6 acquired in step S31. For example, as shown in Fig. 11, the refund amount is set in the corresponding information D6 of Fig. 10.

[0041] (Step S33: Code generation process) The code generation unit 25 generates code information D7 for displaying response information D6 indicating the response content of the service provider side to realize the action content indicated by the desired information D2. The code information D7 is a code that records information such as a two-dimensional code or a barcode. In the first embodiment, the code information D7 is a two-dimensional code. Here, the code generation unit 25 generates code information D7 for indicating the correspondence information D6 in which the refund amount was set in step S32. Here, the code information D7 may be a code that records the correspondence information D6, or a code that records a URL or the like that indicates the location where the correspondence information D6 is saved. URL is an abbreviation for Uniform Resource Locator. Here, the code information D7 is assumed to be a URL. The correspondence information D6 is assumed to be stored in the task support system 35.

[0042] (Step S34: Output process) As shown in FIG. 12, the output unit 26 outputs the correspondence information D6 in which the amount is set in step S32 and the code information D7 generated in step S33 to the user terminal 36 for display.

[0043] The time change process for the designated train (step S27 in FIG. 5) according to the first embodiment will be described with reference to FIG. (Step S41: Time request process) The input unit 21 accepts input of a departure time or arrival time desired by the user. Specifically, the input unit 21 outputs an input request for a desired departure time or arrival time to the user terminal 36. The user inputs the desired departure time or arrival time by operating the user terminal 36. The input unit 21 accepts the input departure time or arrival time.

[0044] (Step S42: Corresponding information generation process) The model control unit 22 adds the departure time or arrival time input in step S41 to the organized information D3 when the request content is confirmed, along with an instruction to generate the correspondence information D6, and inputs this to the correspondence generation model 31. At this time, the model control unit 22 may refer to the operation information D1 and give an instruction to include train information indicating a train that meets the request in the correspondence information D6. Then, the model control unit 22 acquires the correspondence information D6 output by the correspondence generation model 31. Here, the correspondence information D6 is a sentence indicating the specific processing content when the time of the designated train is changed, as shown in FIG.

[0045] (Step S43: Check availability) The reservation confirmation unit 24 transmits the train information included in the correspondence information D6 acquired in step S42 to the seat management system 34 and inquires about available seats on the train indicated by the train information. The reservation confirmation unit 24 acquires the available seat information obtained as a result of the inquiry. At this time, the fare determination unit 23 inputs the train information included in the corresponding information D6 acquired in step S42 to the fare calculation system 33. Then, the fare determination unit 23 acquires the fare of the train indicated by the train information from the fare calculation system 33. The fare determination unit 23 sets the fare in the corresponding information D6.

[0046] (Step S44: Train notification process) The output unit 26 outputs the correspondence information D6 acquired in step S42 and the vacant seat information acquired in step S43 to the user terminal 36 for display.

[0047] (Step S45: Desire determination process) The input unit 21 accepts a selection as to whether or not the desired result has been obtained. Specifically, the user operates the user terminal 36 to select whether or not the desired result has been obtained. The desired result is that a train that satisfies the user's desire and has available seats has been identified. The input unit 21 accepts the user's selection. If it is selected that the desired result has been obtained, the input unit 21 proceeds to step S46. On the other hand, if it is selected that the desired result has not been obtained, the input unit 21 returns the process to step S41, where improvement information D8 indicating desired improvements to the correspondence information D6 is input. Then, in step S42, the improvement information D8 is added to the input to the correspondence generation model 31, and the correspondence information D6 is generated. At this time, the input unit 21 may change the departure time or the arrival time.

[0048] (Step S46: Code generation process) The code generation unit 25 generates code information D7 for indicating the action content of the service provider side to realize the action content indicated by the desired information D2. Here, the code generation unit 25 generates code information D7 for indicating the action information D6 acquired in step S42.

[0049] (Step S47: Output process) As shown in FIG. 15, the output unit 26 outputs the correspondence information D6 acquired in step S42 and the code information D7 generated in step S46 to the user terminal 36 for display.

[0050] The alternative route proposing process (step S28 in FIG. 5) according to the first embodiment will be described with reference to FIG. (Step S51: Route generation process) The model control unit 22 inputs the organizing information D3 when the request content is confirmed, together with an instruction to specify an alternative route, to the correspondence generative model 31. Then, the model control unit 22 acquires route information D9 indicating the alternative route output by the correspondence generative model 31. Here, the route information D9 indicates one or more alternative routes.

[0051] (Step S52: Route presentation process) The output unit 26 outputs the route information D9 acquired in step S51 to the user terminal 36 for display.

[0052] (Step S53: Route selection process) The input unit 21 accepts the selection of a desired alternative route. Specifically, the user selects a desired alternative route from one or more alternative routes indicated by the route information D9. The input unit 21 accepts the selection by the user.

[0053] (Step S54: Corresponding information generation process) The model control unit 22 adds the alternative route selected in step S53 to the organized information D3 when the request content is confirmed, together with an instruction to generate the correspondence information D6, and inputs this to the correspondence generation model 31. Then, the model control unit 22 acquires the correspondence information D6 output by the correspondence generation model 31 with reference to the operation information D1. Here, the correspondence information D6 is a sentence indicating the specific processing content when an alternative route is used, as shown in FIG.

[0054] (Step S55: Amount calculation process) The fare determination unit 23 inputs partial information on the departure station, intermediate stations, and arrival stations from the machine information D4 when the request details are confirmed, and the departure station, intermediate stations, and arrival stations of the alternative route selected in step S53, into the fare calculation system 33. Then, the fare determination unit 23 obtains from the fare calculation system 33 the fare based on the current departure station, intermediate stations, and arrival stations as the refund amount, and obtains the fare based on the departure station, intermediate stations, and arrival stations of the alternative route as the substituted fare. The fare specification unit 23 sets the acquired refund amount and fare in the corresponding information D6 acquired in step S54.

[0055] (Step S56: Code generation process) The code generation unit 25 generates code information D7 for indicating the action content of the service provider that realizes the action content indicated by the desired information D2. Here, the code generation unit 25 generates code information D7 for indicating the action information D6 for which the fare was set in step S55.

[0056] (Step S57: Output process) As shown in FIG. 18, the output unit 26 outputs the correspondence information D6 in which the fare has been set in step S55 and the code information D7 generated in step S56 to the user terminal 36 for display.

[0057] The management support process according to the first embodiment will be described with reference to FIG. The response support process is executed when the code information D7 output to the user terminal 36 in the response acquisition process shown in FIG. 5 is presented to a staff member.

[0058] (Step S61: Code reading process) The attendant terminal 37 reads the presented code information D7. In the first embodiment, the staff terminal 37 starts an application program for reading a two-dimensional code, and reads the two-dimensional code, which is the code information D7, using the function of the application program. As described above, the code information D7 is set with a URL indicating the location where the corresponding information D6 is stored. Therefore, the staff terminal 37 obtains the URL by reading the code information D7. Then, the staff terminal 37 accesses the location where the corresponding information D6 is stored according to the URL and obtains the corresponding information D6. In this case, the corresponding information D6 is stored in the work support system 35. Therefore, the staff terminal 37 accesses the work support system 35 and obtains the corresponding information D6.

[0059] (Step S62: Correspondence display process) The staff terminal 37 displays the response information D6 acquired in step S61. The attendant then checks the corresponding information D6 as well as the information on the user's ticket and performs the process. Since the corresponding information D6 is read into the attendant terminal 37, it is also possible to proceed with the process by inputting the corresponding information D6 from the attendant terminal 37 into a system for handling the corresponding information D6.

[0060] ***Effects of the First Embodiment*** As described above, the customer service operation support device 10 according to the first embodiment inputs the desired information D2 indicating the action content into the action generation model 31, acquires the action information D6 indicating the action content of the station staff who will realize the action content, and generates code information D7 for displaying the action information D6. The code information D7 is presented to a staff member on the service providing side to have them read it, allowing the staff member to understand the action information D6. This allows the staff member on the service providing side to identify the action content required to respond to various requests from users, thereby reducing the burden on the service providing side in responding to users.

[0061] In addition, the time required to listen to the user's wishes and situation is reduced, which makes it possible to shorten the time required to respond to the user. As a result, the user's waiting time can be reduced, and user satisfaction can be improved.

[0062] ***Other Configurations*** <Variation 1> In the first embodiment, the fare determination unit 23 calculated the fare using the fare calculation system 33. However, the correspondence generation model 31 may also be made to calculate the fare. In this case, the correspondence generation model 31 is made to be able to access information about fares managed by the fare calculation system 33. Furthermore, when instructing the generation of correspondence information D6, the model control unit 22 instructs the correspondence generation model 31 to also include the necessary fares in the correspondence information D6.

[0063] <Variation 2> In the first embodiment, the reservation confirmation unit 24 confirmed vacant seats using the seat management system 34. However, the correspondence generation model 31 may also be made to confirm vacant seats. In this case, the correspondence generation model 31 is made to be able to access information about vacant seats managed by the seat management system 34. Furthermore, when instructing the generation of correspondence information D6, the model control unit 22 instructs the correspondence generation model 31 to also include necessary vacant seat information in the correspondence information D6.

[0064] <Variation 3> In the first embodiment, each functional component is realized by software. However, as a third modification, each functional component may be realized by hardware. The following describes the differences between the first embodiment and the third modification.

[0065] When each functional component is realized by hardware, the response work support device 10 includes an electronic circuit 15 instead of the processor 11, memory 12, and storage 13. The electronic circuit 15 is a dedicated circuit for realizing the functions of each functional component, the memory 12, and the storage 13.

[0066] The electronic circuit 15 may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA stands for Gate Array. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field-Programmable Gate Array. Each functional component may be realized by one electronic circuit 15, or each functional component may be realized by distributing it among a plurality of electronic circuits 15.

[0067] <Variation 4> As a fourth modification, some of the functional components may be realized by hardware, and other functional components may be realized by software.

[0068] The processor 11, memory 12, storage 13, and electronic circuit 15 are collectively referred to as a processing circuit. In other words, the functions of the respective functional components are realized by the processing circuit.

[0069] Furthermore, the term "unit" in the above description may be read as a "circuit," "step," "procedure," "process," or "processing circuit."

[0070] Embodiment 2 In the second embodiment, an example of an application of the response work support system 100 will be described. In the first embodiment, the customer service support system 100 is applied to a case where a request from a user at a train station is handled. However, the customer service support system 100 is not limited to this, and can also be applied to a case where a request from a user at another location is handled. This system is effective for applications that meet the following three conditions: Condition 1: There is a counter. Condition 2: There are processes that can only be done at the counter. Condition 3: There are cases where it takes time to explain things to the counter staff.

[0071] In the second embodiment, three examples of application, namely, an airport, a government office, and a hospital, in addition to a railway station, will be described.

[0072] (Example 1: When the application destination is an airport) A case where the emergency response work support device 10 supports emergency response work for airport users will be described.

[0073] 3, in steps S11 and S12, the input unit 21 acquires operation information indicating the operation status of aircraft, as in the case where the application is to a railway, and provides this to the correspondence generation model 31. In addition to this, the input unit 21 may also provide the correspondence generation model 31 with a response manual for an airport, etc.

[0074] 5, in step S21, the input unit 21 receives input of desired information D2 indicating the action content desired by an airport user. For example, the desired information D2 may include information such as what to do in the event of a flight suspension, a seat change, connecting flight instructions, and baggage search. In addition to the requested content, the desired information D2 includes information similar to that in the case of a train, such as the flight name, departure and arrival points, and ticket information. Then, in steps S22 to S24, the model control unit 22 inputs the desired information D2 into the correspondence generation model 31 to confirm the request content, as in the case where the application is a railway. Then, in step S26, the model control unit 22 determines what the request content is and proceeds to processing according to the request content. As a result, correspondence information D6 indicating the correspondence content of the service provider that will realize the action content indicated by the desired information D2 and code information D7 for displaying the correspondence information D6 are generated and output to the user terminal 36. The correspondence information D6 may indicate where the user needs to go, what they need to do, etc., in addition to the processing content to be performed by the service provider. This prevents the user from taking a different action than expected. As a result, unnecessary burdens on the user are prevented.

[0075] In the response support process shown in FIG. 19, in steps S61 and S62, the staff terminal 37 reads the code information D7 and displays the response information D6, just as in the case where the application destination is a railway.

[0076] (Example 2: When the application is to a government office) A case will be described in which the response operation support device 10 supports response operations for users at a government office. The government office may be a city hall, a ward office, a legal affairs bureau, a health center, or the like.

[0077] In the information setting process shown in FIG. 3, in steps S11 and S12, the input unit 21 acquires business information about the business handled by each department of the government office and provides it to the correspondence generation model 31. The business information includes information indicating the content of the business handled by each department, the procedure content of each department, and the location of each department. The information indicating the procedure content also includes information about what is needed for the procedure. In addition to this, the input unit 21 may provide the correspondence generation model 31 with a response manual or the like for each department.

[0078] In the correspondence acquisition process shown in FIG. 5, in step S21, the input unit 21 accepts input of desired information D2 indicating the action desired by a user of the government office. For example, the requested content in the desired information D2 may be the procedure to be carried out. For example, if the user has moved, the requested content may be that the user wants to carry out procedures to move in. In addition to the requested content, the desired information D2 may also include information corresponding to the requested content. For example, if the requested content is that the user wants to carry out procedures to move in, information such as the current address and previous address may be included. Then, in steps S22 to S24, the model control unit 22 inputs the desired information D2 into the correspondence generation model 31 to confirm the request content, as in the case where the application destination is a railway. Then, in step S26, the model control unit 22 determines what the request content is and proceeds to processing according to the request content. As a result, correspondence information D6 indicating the correspondence content of the service provider side to realize the action content indicated by the desired information D2 and code information D7 for displaying the correspondence information D6 are generated and output to the user terminal 36. In addition to the processing content to be performed by the service provider side, the correspondence information D6 may also indicate which department the user should go to and what items the user should bring. This prevents the user from going to the wrong department or being short on items. As a result, unnecessary burdens on the user and the service provider side are prevented.

[0079] In the response support process shown in FIG. 19, in steps S61 and S62, the staff terminal 37 reads the code information D7 and displays the response information D6, just as in the case where the application destination is a railway.

[0080] (Example 3: When the application is to a hospital) A case where the medical service support device 10 supports medical service for hospital users will be described.

[0081] 3, in steps S11 and S12, the input unit 21 acquires information about medical departments and medical interview information about each patient, and provides this to the correspondence generation model 31. The information about medical departments includes information about cases that each department can handle, how busy the department is, the location of the department, etc. In addition to this, the input unit 21 may also provide the correspondence generation model 31 with a hospital's response manual, etc.

[0082] In the response acquisition process shown in Fig. 5, in step S21, the input unit 21 accepts input of desired information D2 indicating the action content desired by a hospital user. For example, the request content in the desired information D2 may include information such as which medical department to visit or whether to visit an inpatient. In addition to the request content, the desired information D2 may also include information corresponding to the request content. For example, in the case of the content regarding which medical department to visit, information such as the user's symptoms and condition may be included. Thereafter, in steps S22 to S24, the model control unit 22 inputs the desired information D2 into the correspondence generation model 31 to confirm the request details, just as in the case where the application destination is a railway. Then, in step S26, the model control unit 22 determines what the request details are and proceeds to processing according to the request details. As a result, correspondence information D6 indicating the correspondence details of the service provider that will realize the activity details indicated by the desired information D2 and code information D7 for displaying the correspondence information D6 are generated and output to the user terminal 36. The correspondence information D6 may indicate what to bring, etc., in addition to the processing details to be performed by the service provider. This prevents the user from running out of belongings.

[0083] In the response support process shown in FIG. 19, in steps S61 and S62, the staff terminal 37 reads the code information D7 and displays the response information D6, just as in the case where the application destination is a railway.

[0084] Various aspects of the present disclosure are summarized below as appendices. (Appendix 1) an input unit that accepts input of desired information indicating the content of an action desired by a user; a model control unit that inputs the desired information received by the input unit into a correspondence generation model that is a learning model, and acquires correspondence information output by the correspondence generation model, the correspondence information indicating correspondence details on the service provider side that realizes the action details indicated by the desired information; a code generation unit that generates code information for displaying the correspondence information acquired by the model control unit; A response work support device equipped with the above. (Appendix 2) the input unit accepts input of the desired information from a user terminal used by the user, The response work support device further comprises: an output unit that outputs the code information generated by the code generation unit to the user terminal; 2. A response work support device according to claim 1, comprising: (Appendix 3) The output unit further outputs the correspondence information to the user terminal. Response work support device according to appendix 2. (Appendix 4) the input unit receives, from the user terminal, input of improvement information indicating content that the user desires to improve with respect to the correspondence information; The model control unit inputs the improvement information into the correspondence generation model and acquires new correspondence information output by the correspondence generation model. Response operation support device according to appendix 3. (Appendix 5) the model control unit, when there is missing information in the desired information, acquires a question sentence that supplements the missing information output from the correspondence generation model; the input unit receives, as additional information, an input of at least one of a response from the user to the question sentence and an inquiry from the user; The model control unit inputs the desired information to which the additional information has been added to the correspondence generation model, and acquires the correspondence information output from the correspondence generation model. 5. A response operation support device according to any one of appendixes 1 to 4. (Appendix 6) the response work support device supports response work for railway users, The correspondence generation model is generated by 6. A response work support device according to any one of appendix 1 to 5. (Appendix 7) The response operation support device supports response operations for airport users, The correspondence generation model is given aircraft operation information. 6. A response work support device according to any one of appendix 1 to 5. (Appendix 8) The response operation support device supports response operations for users of a government office, The correspondence generation model is given business information about the business handled by each department of the government office. 6. A response work support device according to any one of appendix 1 to 5. (Appendix 9) the response operation support device supports response operations for hospital users, The correspondence generation model is generated by giving information on each medical department of the hospital and medical interview information of each patient. 6. A response work support device according to any one of appendix 1 to 5. (Appendix 10) The computer accepts input of desired information indicating the action the user wishes to take, a computer inputs the received desired information into a correspondence generation model, which is a learning model, and acquires correspondence information output by the correspondence generation model, the correspondence information indicating the correspondence content of the service provider that will realize the action content indicated by the desired information; A response work support method in which a computer generates code information for displaying the acquired response information. (Appendix 11) an input process for receiving input of desired information indicating the content of an action desired by the user; a model control process in which the desired information received by the input process is input into a correspondence generation model, which is a learning model, and correspondence information output by the correspondence generation model is acquired, the correspondence information indicating the correspondence content of the service provider side that realizes the action content indicated by the desired information; a code generation process for generating code information for displaying the correspondence information acquired by the model control process; A response work support program that causes a computer to function as a response work support device that performs the above.

[0085] The embodiments and modifications of the present disclosure have been described above. Some of these embodiments and modifications may be combined and implemented. Also, one or more of them may be implemented partially. Note that the present disclosure is not limited to the above embodiments and modifications, and various modifications are possible as needed. [Explanation of symbols]

[0086] 100 Response work support system, 10 Response work support device, 11 Processor, 12 Memory, 13 Storage, 14 Communication interface, 21 Input unit, 22 Model control unit, 23 Fare determination unit, 24 Reservation confirmation unit, 25 Code generation unit, 26 Output unit, 31 Response generation model, 32 Operation information system, 33 Fare calculation system, 34 Seat management system, 35 Work support system, 36 User terminal, 37 Staff terminal.

Claims

1. an input unit that accepts input of desired information indicating the content of an action desired by a user; a model control unit that inputs the desired information received by the input unit into a correspondence generation model that is a learning model, and acquires correspondence information output by the correspondence generation model, the correspondence information indicating correspondence details on the service provider side that realizes the action details indicated by the desired information; a code generation unit that generates code information for displaying the correspondence information acquired by the model control unit; A response work support device equipped with the above.

2. the input unit accepts input of the desired information from a user terminal used by the user, The response work support device further comprises: an output unit that outputs the code information generated by the code generation unit to the user terminal; The response work support device according to claim 1 , comprising:

3. The output unit further outputs the correspondence information to the user terminal. The response work support device according to claim 2.

4. the input unit receives, from the user terminal, input of improvement information indicating content that the user desires to improve with respect to the correspondence information; The model control unit inputs the improvement information into the correspondence generation model and acquires new correspondence information output by the correspondence generation model. The response work support device according to claim 3.

5. the model control unit, when there is missing information in the desired information, acquires a question sentence that supplements the missing information output from the correspondence generation model; the input unit receives, as additional information, an input of at least one of a response from the user to the question sentence and an inquiry from the user; The model control unit inputs the desired information to which the additional information has been added to the correspondence generation model, and acquires the correspondence information output from the correspondence generation model. The response work support device according to claim 1.

6. the response work support device supports response work for railway users, The correspondence generation model is generated by The response work support device according to any one of claims 1 to 5.

7. The response operation support device supports response operations for airport users, The correspondence generation model is given aircraft operation information. The response work support device according to any one of claims 1 to 5.

8. The response operation support device supports response operations for users of a government office, The correspondence generation model is given business information about the business handled by each department of the government office. The response work support device according to any one of claims 1 to 5.

9. the response operation support device supports response operations for hospital users, The correspondence generation model is generated by giving information on each medical department of the hospital and medical interview information of each patient. The response work support device according to any one of claims 1 to 5.

10. The computer accepts input of desired information indicating the action the user wishes to take, a computer inputs the received desired information into a correspondence generation model, which is a learning model, and acquires correspondence information output by the correspondence generation model, the correspondence information indicating the correspondence content of the service provider that will realize the action content indicated by the desired information; A response work support method in which a computer generates code information for displaying the acquired response information.

11. an input process for receiving input of desired information indicating the content of an action desired by the user; a model control process in which the desired information received by the input process is input into a correspondence generation model, which is a learning model, and correspondence information output by the correspondence generation model is acquired, the correspondence information indicating the correspondence content of the service provider side that realizes the action content indicated by the desired information; a code generation process for generating code information for displaying the correspondence information acquired by the model control process; A response work support program that causes a computer to function as a response work support device that performs the above.

Citation Information

Patent Citations

  • Management server

    JP2008065781A

  • Application support system and application support program

    JP2022132686A

  • Work assistance system and work assistance method

    WO2020095941A1

  • Ticket vending machine, server device, terminal device, and ticket vending system

    JP2021168003A