Prompt generation support device and prompt generation support method

Abstract

This invention provides a prompt generation support device and a prompt generation support method that can support the generation of prompts for generating support information that takes into account communication restrictions on the communication path through which on-site information is transmitted. [Solution] The prompt generation support device includes a storage device and a processor. The storage device stores the communication status of a communication path that communicates with a user terminal and a communication path that communicates with a device that acquires on-site information about the site present at the site. The processor acquires support request information regarding a user's request for business support, generates restriction information that restricts the devices that acquire on-site information based on the communication status of the communication path through which the on-site information acquired from the site, which is the target of data acquisition based on the support request information, and generates a support request prompt based on the support request information and the restriction information.

Description

Technical Field

[0001] The present disclosure relates to a prompt generation support device and a prompt generation support method.

Background Art

[0002] In recent years, generative AI has been used in technologies for assisting on-site users (for example, surveillance systems using cameras, etc.). As a conventional technology related to generative AI, there is Patent Document 1. Patent Document 1 discloses a text generation device (hereinafter referred to as "conventional device 1") that generates a prompt for input to a large-scale model by adding reference information to an input question text.

[0003] Based on the input question text, the conventional device 1 obtains candidate texts related to the question text used to generate additional texts to be added as reference information to the question text, and generates a prompt by adding the additional texts generated based on the candidate texts as reference information.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In work support systems that assist on-site users, work support is provided using generative AI. In these work support systems, the support server receives voice and text-based support requests from on-site users, uses generative AI to generate work support information along with on-site information acquired by devices such as cameras and sensors, and provides this information to the user by transmitting it to the user's terminal. However, due to communication limitations in the communication paths between the on-site (devices) and the support server, and between the support server and the user terminal, it may not be possible to provide the user with all the on-site information that should be provided along with the support information generated by the generative AI.

[0006] This disclosure was made to solve the above-mentioned problems. Specifically, one of the purposes of this disclosure is to provide a prompt generation support device and a prompt generation support method that can support the generation of prompts for generating support information that takes into account communication restrictions on the communication path through which field information is transmitted. [Means for solving the problem]

[0007] To solve the above problems, the prompt generation support device of this disclosure is a prompt generation support device having a storage device and a processor, wherein the storage device stores the communication status of a communication path for communicating with a user terminal and a communication path for communicating with a device that acquires on-site information relating to the site present at the site, and the processor acquires support request information relating to a user's request for the provision of business support, generates restriction information that restricts the device that is the target of acquiring the on-site information based on the communication status in the communication path through which the on-site information acquired from the site, which is the target of data acquisition based on the support request information, generates a support request prompt based on the support request information and the restriction information.

[0008] The prompt generation support method of this disclosure is a prompt generation support method using a storage device and a processor, wherein the storage device stores the communication status of a communication path for communicating with a user terminal and a communication path for communicating with a device that acquires on-site information relating to the on-site located at the on-site, the processor acquires support request information relating to a user's request for the provision of business support, generates restriction information that restricts the device that is the target of acquiring the on-site information based on the communication status in the communication path through which the on-site information acquired from the on-site, which is the target of data acquisition based on the support request information, and generates a support request prompt based on the support request information and the restriction information. [Effects of the Invention]

[0009] According to this disclosure, it is possible to support the generation of prompts for generating support information that takes into account communication restrictions on the communication path through which on-site information is transmitted. The effects described herein are not necessarily limited and may include any of the effects described in this disclosure. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 shows an example of the configuration of a work support system. [Figure 2] Figure 2 is a functional block diagram showing an example of the support server configuration. [Figure 3] Figure 3 shows an example of a computer hardware configuration applied to a support server. [Figure 4] Figure 4 is a diagram illustrating communication status information. [Figure 5] Figure 5 is a diagram illustrating device management information. [Figure 6A] Figure 6A shows an example of a work support system applied to railway operations. [Figure 6B] Figure 6B is a diagram illustrating an overview of a work support system according to an embodiment of this disclosure. [Figure 7A] Figure 7A shows an example of support request information. [Figure 7B]FIG. 7B is a diagram showing an example of a restriction prompt. [Figure 7C] FIG. 7C is a diagram showing an example of an assistance request prompt. [Figure 8A] FIG. 8A is a diagram showing an example of first assistance information. [Figure 8B] FIG. 8B is a diagram showing an example of second assistance information. [Figure 9] FIG. 9 is a flowchart showing a processing flow executed by an assistance server. [Figure 10] FIG. 10 is a flowchart showing a processing flow executed by an assistance server. [Figure 11] FIG. 11 is a diagram for explaining Equation (1).

Embodiments for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings of the embodiments, the same or corresponding parts may be denoted by the same reference numerals.

[0012] In the following description, various types of information may be described using expressions such as "table", "record", "row", "column", "line", etc., but the various types of information may be represented by other data structures. When describing identification information, expressions such as "ID", "name", etc. are used, but these are interchangeable with each other and can also be replaced with other expressions of identification information.

[0013] In the following description, when describing a process with a functional block as the subject, the subject of the process may be a CPU or a device instead of the functional block. The subject of the process performed by executing a program may be an arithmetic unit, and may include a dedicated circuit for performing a specific process. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a CPLD (Complex Programmable Logic Device), or the like.

[0014] The program may be installed from a program source into the information processing apparatus. The program source may be, for example, a program distribution server or a storage medium readable by the information processing apparatus. When the program source is a program distribution server, the program distribution server includes a storage resource for storing a processor and the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other information processing apparatuses. Also, in an embodiment, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0015] <<Embodiment>> A work support system including a support server 100 according to an embodiment of the present disclosure will be described. Hereinafter, a work support system applied to railway operations will be described. Note that the work support system is applicable not only to railway operations but also to various other operations.

[0016] FIG. 1 is a diagram showing a configuration example of a work support system. As shown in FIG. 1, the work support system includes a support server 100, a generation AI server 200, a plurality of information providing devices 300 (hereinafter sometimes referred to as "devices"), and a user terminal 400. These are communicably connected to each other via a network NW1. Note that the network NW1 includes a plurality of networks (network A, network B, network C, ··· and network X). Note that the user and the user terminal 400 used by the user may be present at the site.

[0017] FIG. 2 is a functional block diagram showing a configuration example of the support server 100. The support server 100 may be referred to as a "prompt generation support device" or a "work support device". As shown in FIG. 2, the support server 100 includes a communication status monitoring unit 110, a user prompt generation unit 120, a restriction item derivation unit 130, a restriction prompt generation unit 140, a prompt synthesis unit 150, and a support information generation unit 160.

[0018] The communication status monitoring unit 110 monitors the communication status of each network included in network NW1. The user prompt generation unit 120 generates prompts (hereinafter sometimes referred to as "user prompts") based on support requests from the user. The restriction item derivation unit 130 obtains information on the communication status of each network from the communication status monitoring unit 110 and derives restriction information based on the communication status information. The restriction information is information that restricts the devices that acquire on-site information. For example, the restriction information may be combinations of the limited number of devices that acquire on-site information or throughput limits for each device. The restriction item derivation unit 130 may also derive restriction information based on the communication status information and user prompts. The restriction prompt generation unit 140 generates a prompt (hereinafter sometimes referred to as "restriction prompt") that defines restrictions regarding devices that acquire on-site information from the restriction information. The restriction prompt is a prompt for restricting the on-site information to be included in the second support information (support information that the support server 100 provides to the user terminal 400 (details will be described later)). The restriction prompt only needs to contain information that the generation AI 210 can process. An example of a restriction prompt is one that limits the on-site information to be included in the second support information by restricting, for example, the location of the device, the type of device, or the number of devices. A specific example of a restriction prompt is: "Transmission is possible for a total of 5 cameras (in-car and side-car cameras) and 10 cameras (in-station cameras) at Station B, on a train stopped at Station B on Line A." Restriction prompts may also be information similar to the type and number of devices. Another specific example of a restriction prompt is: "The following combinations of the number of side-car cameras and in-car cameras must meet the following conditions: - total 10 Mbps or less, - side-car cameras 2 Mbps each, - in-car cameras 1.5 Mbps each."

[0019] The prompt synthesis unit 150 creates a prompt (which may be referred to as the "support request prompt") by synthesizing the user prompt and the restriction prompt, and inputs it to the generation AI 210.

[0020] The support information generation unit 160 obtains the first support information generated from the support request prompt by the generation AI 210 from the generation AI 210, obtains the on-site information corresponding to the first support information, and generates second support information including the first support information and the on-site information. Note that the first support information will take into account communication restrictions due to the restriction prompt included in the support request prompt, and therefore the on-site information corresponding to the first support information will also take communication restrictions into account. The support information generation unit 160 provides the second support information to the user by transmitting the second support information to the user terminal 400.

[0021] Figure 3 shows an example of the hardware configuration of the computer 3000 applied to the support server 100. The support server 100 may consist of multiple computers, or it may be a virtual computer on the cloud.

[0022] Computer 3000 is sometimes referred to as an "information processing device." Computer 3000 includes a processor (CPU 3001), ROM 3002, RAM 3003, a non-volatile storage device 3004 capable of reading and writing data, a network interface 3005, and an input / output interface 3006, among others. These are connected to each other via a bus 3007 so that they can communicate with one another.

[0023] The CPU 3001 loads various programs (not shown) stored in the ROM 3002 and / or storage device 3004 into the RAM 3003, and executes the programs loaded into the RAM 3003 to realize various functions of the support server 100.

[0024] As described above, RAM3003 is loaded with various programs executed by CPU3001, and temporarily stores data used by CPU3001 when executing these programs. ROM3002 and / or storage device3004 are non-volatile storage media, and various programs are stored in ROM3002 and / or storage device3004. ROM3002 and / or storage device3004 include, as programs, a communication status monitoring unit 110, a user prompt generation unit 120, a restriction item derivation unit 130, a restriction prompt generation unit 140, a prompt synthesis unit 150, and a support information generation unit 160. Furthermore, ROM3002 and / or storage device3004 also store the communication status information 4000 and device management information 5000, which will be described later.

[0025] The network interface 3005 is an interface for connecting the computer 3000 to a network. The input / output interface 3006 is an interface for connecting the computer 3000 to an operating device and a display device (display) capable of displaying images.

[0026] The computer 3000 may or may not include a display device. Alternatively, a hardware device in which part or all of the computer 3000 is configured using an FPGA (Field Programmable Gate Array) or the like may be used instead of the computer 3000.

[0027] The Generative AI Server 200 includes a Language Generating AI 210. The Language Generating AI 210 includes a Large Language Model (LLM). The Language Generating AI 210 is sometimes referred to simply as "Generating AI 210". A Large Language Model (LLM) is a language model constructed using a large amount of data and deep learning technology. The Generative AI 210 inputs the input prompt into the Large Language Model to generate an appropriate response (answer) and outputs the generated response (answer) (returns it as a response). The Generative AI Server 200 is composed of the computer 3000 shown in Figure 3. The Generative AI Server 200 may be composed of multiple computers, or it may be a virtual computer on the cloud.

[0028] The information providing device 300 is deployed at a work site, a site to be monitored, etc., acquires information about the site, and provides it to the support server 100 via the network. Multiple information providing devices 300 may be deployed at a single site. Sites include, for example, vehicles (mobile objects) and train stations. If the site is a vehicle, the information providing device 300 may be a surveillance camera installed inside the vehicle (in-vehicle camera) or a surveillance camera mounted on the outside of the vehicle (external camera). If the site is a train station, the information providing device 300 may be a surveillance camera installed on the station platform (station premises camera). The information providing device 300 may also be a sensor that acquires information about the site.

[0029] The user terminal 400 is, for example, a desktop PC (personal computer), a notebook PC, a smartphone, a tablet, or a command device. At least a portion of the user terminal 400 is composed of the computer 3000 shown in Figure 3.

[0030] Figure 4 is a diagram illustrating the communication status information 4000. As shown in Figure 4, the communication status information 4000 includes a network ID 4001 and a communication status 4002 as columns for storing information (values). In the communication status information 4000, information corresponding to each column regarding the communication status of each network is associated with each other and stored as row-level information (records). Specifically, the network ID 4001 stores an ID for identifying the network. The communication status 4002 stores information indicating the communication status of the network (communication bandwidth (Mbps (megabits per second))). Here, if the communication status changes over time, the value of the communication status 4002 may change over time.

[0031] Figure 5 is a diagram illustrating device management information 5000. As shown in Figure 5, device management information 5000 includes the following columns for storing information (values): device ID 5001, device type 5002, communication performance 5003, communication path 5004, and device location information 5005. In device management information 5000, the information corresponding to each column for each device in the field is associated with each other and stored as row-level information (records). Specifically, device ID 5001 stores an ID for identifying the device (information providing device 300). Device type 5002 stores the type of device. Communication performance 5003 stores the communication performance of the device. Communication path 5004 stores the name of the network which is the communication path of the device. Device location information 5005 stores information indicating the location of the device (for example, the installation location (field), longitude and latitude coordinate information, etc.).

[0032] <Summary of this disclosure> This document outlines the contents of this disclosure. Figure 6A shows an example of a work support system applied to railway operations. For example, in a work support system applied to railway operations, the support server 100 collects information from the field, such as moving vehicles and stations. Based on voice and other instructions input to the support server 100 by users (user terminals 400) such as dispatchers, station staff, and maintenance personnel at the control center, the support server 100 generates a user prompt, inputs the user prompt to the generation AI 210, and causes the generation AI 210 to create first support information. The support server 100 transmits the first support information and second support information, including field information, to the user terminal 400 of the user who requested the support.

[0033] In such a work support system, on-site information is transmitted to the support server 100 via various networks such as public networks and cloud networks, and then transmitted from the support server 100 to the user terminal 400 via various networks such as public networks and cloud networks. Therefore, due to the communication conditions (communication restrictions) of each network through which the on-site information is transmitted, it may become difficult to transmit information (on-site information) from the on-site information providing device 300 to the support server 100 and from the support server 100 to the user terminal 400.

[0034] The generating AI 210 needs to generate first support information (answers) in response to the input user prompt. However, it is difficult for the generating AI 210 to consider the communication status (communication restrictions) of the network (communication path) through which the field information is transmitted. For this reason, it is difficult for the generating AI 210 to create first support information that takes into account the communication status (communication restrictions) of the network (communication path) through which the field information is transmitted. For example, if the first support information generated is "Please check with the station staff on site to see if there are any passengers trapped or any contact with people by looking at all the cameras inside the train," then the support server 100 needs to send the second support information to the user terminal 400, which includes the first support information and the corresponding field information (video from all the cameras inside the train).

[0035] However, depending on the communication conditions (communication restrictions) of the network (communication path) through which on-site information is transmitted, it may be difficult to transmit on-site information (video from all in-vehicle cameras installed in the vehicle), or even if transmission is possible, it may take a long time.

[0036] In contrast, as shown in Figure 6B, the present disclosure enables the generating AI 210 to understand the communication status of the network (communication path) through which the field information is transmitted. It adds a restriction prompt to the user prompt according to the network (communication path) communication status to create a support request prompt, and inputs this support request prompt to the generating AI 210. As previously described, the restriction prompt specifies limitations regarding the device acquiring the field information. Therefore, the first support information (response) (and second support information) generated by the generating AI 210 from the support request prompt takes into account the communication status (communication restrictions) of the network (communication path) through which the field information is transmitted. Consequently, the support server 100 of this disclosure can assist in generating prompts for generating the first support information (and second support information) that takes communication restrictions into account. Furthermore, the support server 100 of this disclosure can provide the user with appropriate support information (second support information) that takes the communication status into account.

[0037] In the work support system shown in Figure 6B, the support server 100 monitors the communication status of various networks, including the network between the on-site information provision device 300 and the user terminal 400, and the network between the user terminal 400 and the support server 100. The support server 100 obtains support request information from the user, including the content of the support request via voice or text, and creates a user prompt. The support request information may also include information related to the location where the information is obtained (station name, location information obtained from GPS).

[0038] The support server 100 creates restriction information from the communication status and generates a restriction prompt that specifies the restrictions on the information that can be transmitted according to the communication status based on the restriction information. The restriction prompt may be generated by the generation AI 210 by inputting the restriction information and an instruction prompt instructing the generation AI 210 to create a restriction prompt from the restriction information, and then retrieved from the generation AI 210. The restriction prompt may be generated using a format corresponding to the restriction information.

[0039] To facilitate understanding of the work support system disclosed herein, a specific use case will be explained. For example, suppose that immediately after a train (vehicle) departs from a station, the emergency stop button on the station platform is pressed. In this situation, the dispatcher at the control center inputs the voice information shown in Figure 7A ("Tell me if something is happening at the station") as support request information to the support server 100 via the user terminal 400. In this example, the support request information includes location information indicating the station's location. The support server 100 creates a user prompt from the support request information, including the voice information. In this example, the user prompt is the same as "Tell me if something is happening at the station" shown in Figure 7A.

[0040] The support server 100 extracts the train (vehicle) present at the location (station) where the emergency stop button was pressed, and the devices such as cameras installed at the station where the emergency stop button was pressed. It then derives restriction information from the status of the network (communication path through which on-site information acquired from the site passes) corresponding to the train and the station. From the restriction information, the support server 100 creates the restriction prompt shown in Figure 7B ("However, a maximum of 5 cameras can be used inside the train, and a maximum of 20 cameras can be used within the station premises").

[0041] The support server 100 creates the support request prompt shown in Figure 7C by combining the user prompt and the restriction prompt.

[0042] The generating AI 210 creates the first support information shown in Figure 8A from the support request prompt ("Please check with the on-site station staff to see if there are any passengers trapped or any contact with people, by looking at the even-numbered car cameras in the train cars and the cameras near the train cars in the station premises"). This first support information is created by the generating AI 210 taking into account the restriction prompts included in the support request prompt. In this example, considering communication restrictions, the first support information includes instructions to check limited camera information, specifically by looking at the even-numbered car cameras in the train cars and the cameras near the train cars in the station premises.

[0043] The support server 100 obtains first support information from the generating AI 210. The support server 100 provides the dispatcher by transmitting the first support information and the second support information shown in Figure 8B, which includes camera footage from the camera corresponding to the first support information, to the dispatcher's user terminal 400 at the control center. The dispatcher confirms the second support information and takes appropriate action, such as sending appropriate instructions to station staff.

[0044] <Specific operation> Figure 9 is a flowchart showing the processing flow executed by the support server 100. The support server 100 starts processing from step 900, and after sequentially executing the processes from steps 905 to 930 described below, proceeds to step 995 and terminates this processing flow.

[0045] Step 905: The user prompt generation unit 120 receives support request information from the user via the user terminal 400 and generates a user prompt.

[0046] Step 910: The limitation deriving unit 130 identifies the on-site information providing device 300 based on the location information and device management information 5000 of the information acquisition target included in the support request information, and obtains information from the communication status monitoring unit 110 regarding the communication status of the first communication path between the on-site information providing device 300 and the support server 100, and the second communication path between the support server 100 and the user terminal 400 (each network (i.e., each network (communication path) through which on-site information passes)).

[0047] Step 915: The restriction information deriving unit 130 derives restriction information from the information regarding the communication status. Details of the process in step 915 will be described later.

[0048] Step 920: The restriction prompt generation unit 140 generates a restriction prompt that the generation AI 210 can understand from the restriction information.

[0049] Step 925: The prompt synthesis unit 150 synthesizes the user prompt and the restriction prompt to create a support request prompt and sends (transmits) it to the generation AI 210.

[0050] Step 930: The support information generation unit 160 receives the first support information generated by the generation AI 210, generates second support information from the first support information and the field information acquired in accordance with the first support information, and provides the second support information to the user by transmitting it to the user terminal 400.

[0051] Figure 10 is a flowchart showing the processing flow of the process in step 915 described above, which is executed by the limitation deriving unit 130. When the support server 100 proceeds to step 915, it starts processing from step 1000 in Figure 10, and after sequentially executing the processes in steps 1005 to 1025 described below, it proceeds to step 1095 and terminates this processing flow. After that, the support server 100 proceeds to step 920.

[0052] Step 1005: The limitation derivation unit 130 extracts the communication path that is the bottleneck from the first and second communication paths identified in step 910 of Figure 9, based on the communication bandwidth. Note that the extracted path may be at least one of the first and second communication paths.

[0053] Step 1010: The limitation deriving unit 130 extracts the communication bandwidth of the extracted communication path (network) from the monitoring information (communication status information 4000).

[0054] Step 1015: The limitation derivation unit 130 refers to the device management information 5000 and groups the extracted communication paths (networks) for each device (information providing device 300) that have the same throughput characteristics (communication performance 5003). It assigns an ID (=i) to identify each device group and extracts the throughput (ri) of the device in the device group indicated by ID=i. Note that a fixed value corresponding to the communication performance 5003 may be used for this throughput (ri).

[0055] Step 1020: The limitation derivation unit 130 derives the limit number of devices for each device group using equation (1). That is, using equation (1), the combination of the number of devices ni (limit number) for each device group is derived such that the sum of the device throughput and margin (M) for each combination of the number of devices in each device group is less than or equal to the communication bandwidth of the bottleneck communication path, and the total number of combinations of the number of devices ni is maximized. Note that instead of the communication bandwidth of the bottleneck communication path, the communication bandwidth calculated based on the communication bandwidth of at least one of the first and second communication paths extracted in step 1005 may be used.

[0056] Step 1025: The restriction item derivation unit 130 creates restriction information from the derived combinations of the number of restricted units. An example of restriction information is information such as the number of restricted units for in-vehicle cameras: 2 units, and the number of restricted units for side-vehicle cameras: 3 units.

[0057] <Effects> As described above, the support server 100 according to the embodiment of this disclosure can assist in generating prompts for generating support information that takes communication restrictions into consideration. Furthermore, the support server 100 according to the embodiment of this disclosure can create support information that takes communication restrictions into consideration and provide it to the user who requested support.

[0058] <Example 1> In the above embodiment, the support request information may include information regarding the accuracy of the data. This information may include, for example, parameters indicating the accuracy of the data. In this case, the limitation derivation unit 130 of the support server 100 may set the size of the margin (M) in equation (1) according to the information regarding the accuracy of the data. The limitation derivation unit 130 of the support server 100 may set the margin (M) to decrease as the accuracy of the data increases. This allows the number of devices to be limited according to the accuracy of the data, and if the accuracy of the data is high, the amount of data transferred per device can be increased, so that more accurate on-site information (for example, video with higher image quality) can be included in the second support information and provided to the user.

[0059] <Modification 2> In the above embodiment, if the site is a moving object such as a vehicle, the storage device 3004 of the support server 100 may store moving object information including the location of the moving object and information indicating the movement status of the moving object (such as speed, direction, route information, and time information). In this case, the support request information may include information regarding the desired time (time) for providing the business support information to the user. In this case, the support server 100 may predict the location of the moving object at the desired time (time) based on the moving object information and the information regarding the desired time (time), generate a restriction prompt based on the communication status at the location of the moving object at that time, and provide the user with the site information of the predicted moving object (site) included in the second support information.

[0060] <Variation 3> The support request information may include information about the period of data to be acquired from the field. In this case, the support server 100 may determine the size of the margin (M) in equation (1) based on the information about the period of data to be acquired from the field. The limitation derivation unit 130 of the support server 100 may be set so that the margin (M) increases as the period of data to be acquired from the field increases. This is because the longer the data period, the higher the possibility of larger fluctuations in throughput, and therefore the margin (M) needs to be increased.

[0061] <<Other variations>> This disclosure is not limited to the embodiments and their respective modifications, and various modifications can be adopted within the scope of this disclosure. Furthermore, the embodiments and their respective modifications can be combined with each other, as long as they do not deviate from the scope of this disclosure.

[0062] In the above embodiments and their respective modifications, the support server 100 may have a generation AI 210 internally. In this case, the work support system does not need to have a generation AI server 200.

[0063] In the above embodiments and each of its modifications, the support server 100 may generate a support request prompt based on the support request information and restriction information. [Explanation of Symbols]

[0064] 100...Support server, 110...Communication status monitoring unit, 120...User prompt generation unit, 130...Restriction item derivation unit, 140...Restriction prompt generation unit, 150...Prompt synthesis unit, 160...Support information generation unit, 200...Generating AI server, 210...Generating AI, 300...Information provision device, 400...User terminal, 4000...Communication status information, 5000...Device management information

Claims

1. A prompt generation support device having a storage device and a processor, The storage device stores the communication status of the communication path that communicates with the user terminal and the communication path that communicates with a device that acquires on-site information about the site located at the site. The processor acquires support request information relating to a user's request for business support, generates restriction information that restricts the devices that are to acquire the on-site information based on the communication status in the communication path through which the on-site information acquired from the on-site is traversed, and generates a support request prompt based on the support request information and the restriction information. It is configured in such a way. A prompt generation support device.

2. In the prompt generation support device according to claim 1, The storage device further stores device management information, which is information about a plurality of devices classified into one or more groups based on throughput. The aforementioned processor, As the communication status, the communication bandwidth of the communication path through which the field information passes is obtained, and based on the communication bandwidth and the device management information, the limit information is generated, including the combination of groups and the maximum number of devices in each group of the combination of groups, such that the total throughput is less than or equal to the communication bandwidth and the difference between the communication bandwidth and the total throughput is greater than or equal to a predetermined width. It is configured in such a way. A prompt generation support device.

3. In the prompt generation support device according to claim 2, The processor uses, as the communication status of the communication path through which the field information passes, the communication status in at least one of the communication paths between the device at the site, which is the data acquisition target based on the support request information, and the prompt generation support device, and between the environment to which the user terminal belongs and the prompt generation support device. A prompt generation support device.

4. In the prompt generation support device according to claim 2, The processor generates a user prompt based on the support request information, generates a restriction prompt specifying the limitations relating to the device based on the restriction information, and generates the support request prompt based on the user prompt and the restriction prompt. It is configured in such a way. A prompt generation support device.

5. In the prompt generation support device according to claim 2, The aforementioned support request information includes data accuracy information regarding the accuracy of the data to be obtained from the site, The processor determines the size of the predetermined width based on the data accuracy information. It is configured in such a way. A prompt generation support device.

6. In the prompt generation support device according to claim 2, The plurality of devices includes one or more devices mounted on a mobile body. The aforementioned site includes the aforementioned mobile body, A prompt generation support device.

7. In the prompt generation support device according to claim 6, The storage device further stores information about the mobile body, including the operating status of the mobile body. The aforementioned support request information includes information regarding the desired time for providing the support information to the user, The processor predicts the position of the mobile object at the desired service time based on the mobile object information and the information regarding the desired service time. It is configured in such a way. A prompt generation support device.

8. In the prompt generation support device according to claim 2, The aforementioned support request information includes information regarding the period for which the data to be obtained from the site is to be collected. The processor determines the size of the predetermined width based on information regarding the period of the data. It is configured in such a way. A prompt generation support device.

9. In the prompt generation support device according to claim 2, The aforementioned processor, By inputting the aforementioned support request prompt to the generating AI, the generating AI generates first support information including support content corresponding to the support request prompt, and the first support information is obtained from the generating AI. The system acquires the field information corresponding to the first support information from the device and generates second support information including the first support information and the field information. It is configured in such a way. A prompt generation support device.

10. A method for supporting prompt generation using a storage device and a processor, The storage device stores the communication status of the communication path used to communicate with the user terminal and the communication path used to communicate with a device that acquires on-site information about the site located at the site. The processor acquires support request information relating to a user's request for business support, generates restriction information that restricts the devices that acquire the on-site information based on the communication status in the communication path through which the on-site information acquired from the on-site is traversed, and generates a support request prompt based on the support request information and the restriction information. A method for assisting in prompt generation.

Images