Device and method

Abstract

A device (1) comprises an acquisition unit (11) that acquires feature information relating to a feature for determining a provision location of a sharing target in a sharing service, and a generation unit (12) that generates, on the basis of the feature information acquired by the acquisition unit (11), a prompt for instructing a generative AI to generate an explanation of a reason for determining the provision location. The acquisition unit (11) may further acquire at least one of subject information relating to a subject of the explanation and attribute information relating to an attribute of the subject, and the generation unit (12) may further generate the prompt on the basis of at least one of the subject information and the attribute information acquired by the acquisition unit (11). The generation unit (12) may further generate the prompt on the basis of an importance of the feature information acquired by the acquisition unit (11), the importance being determined on the basis of at least one of the subject information and the attribute information acquired by the acquisition unit (11).

Description

Device and Method

[0001] One aspect of the present disclosure relates to an apparatus and method for generating a prompt for instructing an AI that generates an explanation of the reason for determining a sharing target providing location in a sharing service.

[0002] In Patent Document 1 below, a car sharing system is disclosed in which an operator arranges shared cars secured in a plurality of parking lots, and users can freely select a desired parking lot at the time of use.

[0003] Japanese Patent Application Laid-Open No. 2016-206715

[0004] In the above car sharing system, the reason for determining the parking lot where the shared car is arranged is unclear. Therefore, it is desired to generate information that can generate an explanation of the reason for determining the sharing target providing location.

[0005] An apparatus according to one aspect of the present disclosure includes an acquisition unit that acquires feature information regarding features for determining a sharing target providing location in a sharing service, and a generation unit that generates a prompt for instructing an AI that generates an explanation of the reason for determining the providing location based on the feature information acquired by the acquisition unit.

[0006] In such an aspect, a prompt for instructing an AI that generates an explanation of the reason for determining a sharing target providing location in a sharing service is generated. That is, information that can generate an explanation of the reason for determining the sharing target providing location can be generated.

[0007] According to one aspect of the present disclosure, information that can generate an explanation of the reason for determining the sharing target providing location can be generated.

[0008] This figure shows an example of the system configuration of a system including the device according to the embodiment. This figure shows an example of the functional configuration of the device according to the embodiment. This figure shows an example of the system configuration including the device according to the embodiment. This figure shows a modified version of the system configuration in Figure 3. This figure shows an example of a table of first importance information. This figure shows an example of a table of second importance information. This figure shows an example of a table of condition information. This figure shows an example of a table of illustrative information. This figure shows an example of a prompt. This figure shows an example of an explanation of the reason. This flowchart shows an example of a process executed by the device according to the embodiment. This flowchart shows an example of a process executed by the system. This figure shows an example of the hardware configuration of a computer used in the device according to the embodiment.

[0009] The embodiments of this disclosure will be described in detail below with reference to the drawings. In the description of the drawings, the same elements will be denoted by the same reference numerals, and redundant descriptions will be omitted. Furthermore, the embodiments of this disclosure described below are specific examples of the present invention and are not limited to these embodiments unless otherwise stated to limit the present invention.

[0010] Figure 1 is a diagram showing an example of the system configuration of a system 5 including device 1 according to an embodiment. As shown in Figure 1, system 5 is composed of device 1, external device 2, recommendation device 3, and terminal 4. Device 1 and external device 2 are connected to each other via a network such as the Internet and can send and receive information from each other. Device 1 and recommendation device 3 are connected to each other via a network such as the Internet and can send and receive information from each other. Device 1 and terminal 4 are connected to each other via a network such as a mobile communication network and can send and receive information from each other.

[0011] Device 1 is a computer that generates information capable of generating an explanation for the reason for determining the location where the sharing item is provided in a sharing service.

[0012] Sharing services (sharing economy services) are services that provide or share, in other words, things owned or managed by individuals or businesses (including means of transportation), people, people's skills, money, or space, to people or businesses that need them. Specific examples of sharing services include bike sharing, electric scooter sharing, car sharing, flea markets, skill sharing, housekeeping services, crowdfunding, rental spaces, and short-term rentals. Sharing services are provided not only in physical spaces but also in virtual spaces.

[0013] The "sharing target" refers to the items or services shared within a sharing service. More specifically, sharing targets include the aforementioned items (including means of transportation), people, people's skills, money, or space. Sharing targets exist not only in the real world but also in virtual spaces.

[0014] A "place of provision" in a sharing service refers to the location where the items to be shared are provided for sharing. By placing the items to be shared at a place of provision, individuals or businesses that need those items can use them, thus enabling sharing. A place of provision is not limited to physical space; it also includes virtual space.

[0015] In this embodiment, we assume that the sharing service is bike sharing (shared bicycles, rental bicycles), the sharing target is bikes (bicycles, electric-assist bicycles, electric mobility devices), and the service location is a port (bike port, cycle port), but we are not limited to these.

[0016] The explanation for determining the locations where the sharing service will be provided (hereinafter simply referred to as "explanation of reasons") may be in text, audio, or video format. In this embodiment, it is assumed that the explanation will be in text format, but it is not limited to this.

[0017] Device 1 may also have the functionality of a RAG (Retrieval-Augmented Generation). Details of Device 1 will be described later.

[0018] External device 2 is a computer that holds external data, which is arbitrary data. External device 2 can transmit the external data required by device 1 to device 1 at any time in response to a request from device 1. Details of external device 2 will be described later.

[0019] Recommendation device 3 is a server (computer) that makes recommendations for the relocation of bikes in a bike-sharing system (hereinafter simply referred to as "relocation recommendations" as appropriate). Relocation recommendations involve recommending to bike-sharing operators that bikes not currently being used by users be relocated from one port to another, based on the demand of bike-sharing users and the profits of the bike-sharing operators. Relocation recommendations are made using an existing AI (Artificial Intelligence) system. The AI ​​system may be included in recommendation device 3 or in an external device. If the AI ​​system is included in an external device, relocation recommendations may be made by communication between recommendation device 3 and the external device via a network. Details of recommendation device 3 will be described later.

[0020] In this embodiment, it is assumed that the relocation of the motorcycles is carried out by truck transport by truck drivers (hereinafter simply referred to as "truck drivers") who are contracted with the motorcycle sharing service provider, under the direction of the operator (hereinafter simply referred to as "operator" as appropriate).

[0021] Terminal 4 is a mobile communication terminal (computer) that performs mobile communication. For example, terminal 4 may be a tablet, smartphone, or laptop computer. Terminal 4 may be equipped with various functions and sensors that are typical of a mobile communication terminal. In this embodiment, a tablet is assumed to be terminal 4, but it is not limited to this. Also, in this embodiment, terminal 4 is assumed to be carried and used by an operator or truck driver, but it is not limited to this.

[0022] Figure 2 shows an example of the functional configuration of the device 1. As shown in Figure 2, the device 1 is composed of a storage unit 10, an acquisition unit 11 (acquisition unit), a generation unit 12 (generation unit), and an output unit 13.

[0023] Each functional block of Device 1 is intended to function within Device 1, but is not limited to this. For example, some of the functional blocks of Device 1 may function within a computer device separate from Device 1, connected to Device 1 via a network, while appropriately sending and receiving information with Device 1. Furthermore, some functional blocks of Device 1 may be omitted, multiple functional blocks may be integrated into a single functional block, or a single functional block may be broken down into multiple functional blocks.

[0024] The following describes the functions of the device 1 shown in Figure 2.

[0025] The storage unit 10 stores arbitrary information used in calculations and other operations in the device 1, as well as the results of calculations in the device 1. The information stored in the storage unit 10 may be referenced as appropriate by each function of the device 1.

[0026] The acquisition unit 11 may acquire any information used in calculations in the device 1 from the storage unit 10, or it may acquire (receive) information from other devices such as an external device 2 via a network. The acquisition unit 11 may acquire any information in advance prior to any calculations in the device 1, or it may acquire information when it is needed, according to the requirements of each function of the device 1. The acquisition unit 11 may store the received information in the storage unit 10, or it may output it to other functions of the device 1.

[0027] The acquisition unit 11 may acquire characteristic information relating to the characteristics for determining the location (port) where the shared item (bike) is provided in the sharing service (bike sharing). The characteristic information may be the information used by the aforementioned AI system that determines the port (relocation location, provision location) where the bike is relocated to determine the port.

[0028] For example, the characteristic information may be demand information regarding the demand for motorcycles. For example, the demand information may be population information using mobile spatial statistics (registered trademark), which is population statistics created using the mechanisms of a mobile communication network. Alternatively, for example, the demand information may be information on the number of motorcycle users in any area that is pre-owned by any device.

[0029] For example, the characteristic information may be weather information related to the weather. For example, the weather information may be weather forecast information obtained from a weather report, etc. Also, for example, the weather information may be information indicating the date and time and weather conditions (sunny, cloudy, rainy, etc.).

[0030] For example, the feature information may be distance information relating to the distance from other no-parking zones. For example, the distance information may be information indicating the distance (in km) from the starting point to the destination point when moving the motorcycle.

[0031] For example, the characteristic information may be transportation information relating to other carriers. For example, the transportation information may be information indicating how many motorcycles are being delivered from which area to which area at a given date and time.

[0032] For example, the feature information may be traffic information related to road traffic. For example, the traffic information may be information indicating the degree of road congestion along the route taken by a truck driver.

[0033] For example, the characteristic information may be profit information relating to the profits of a bike-sharing operator or a truck driver. For example, the profit information may be information indicating the profit that a bike-sharing operator or a truck driver gains from deploying bikes. More specifically, the profit information may be a value calculated by the AI ​​system described above, such as 500 yen because it is used only once, or 1500 yen because it is used frequently.

[0034] The acquisition unit 11 may further acquire at least one of the subject information concerning the person to whom the reason is to be explained (hereinafter simply referred to as "the person to be explained") and attribute information concerning the attributes of the person to be explained. That is, the acquisition unit 11 may further acquire subject information, or further acquire attribute information, or further acquire subject information and attribute information.

[0035] The subject information includes, for example, information indicating that the person being explained is an operator, information indicating that the person being explained is operator A, information indicating that the person being explained is a truck driver, and information indicating that the person being explained is truck driver B.

[0036] Attribute information includes, for example, information indicating that the person being explained to is a beginner, information indicating that the person being explained to is an advanced user, information indicating that the person being explained to is in their 20s, and information indicating that the person being explained to speaks Japanese.

[0037] The person to be explained may be determined based on the designation of the user of device 1 (for example, an employee of a bike-sharing service provider). In other words, the person to be explained may be determined based on the designation of the user.

[0038] Attribute information may be information obtained based on subject information. The acquisition of subject information may be performed by the acquisition unit 11 or by any other arbitrary means. For example, the acquisition unit 11 may first acquire subject information and then acquire attribute information based on the acquired subject information. More specifically, if the acquisition unit 11 first acquires subject information and the acquired subject information indicates that the subject is a truck driver named B, then the acquisition unit 11 may then acquire attribute information based on that subject information indicating that B is a novice truck driver.

[0039] The acquisition unit 11 may further acquire location information relating to the provision location (port, relocation location). For example, the provision location may be information that uniquely designates the location of the bicycle parking area, and port identification information.

[0040] The acquisition unit 11 may further acquire constraint information regarding restrictions on the sharing service. For example, the constraint information may be information about ports where the number of bicycles has been specified by the government. To give a specific example, the constraint information may be information that indicates "Specifying source: P Ward Office, Specified destination: Port in Q area, Specified time: R month S day T hour, Specified number of bicycles: U bicycles (lower limit) to T bicycles (upper limit)". Alternatively, the constraint information may be complaint information regarding a specific port (for example, complainant, complaint content: There are too many bicycles and it is causing a nuisance).

[0041] The generation unit 12 generates a prompt to instruct the generation AI to generate arbitrary information.

[0042] Generative AI is a technology that, in response to input from a prompt containing input information, generates content according to one or a combination of the instructions, context, questions, and output formats indicated by the prompt, and returns that content as response information. The prompt can also include input information, in which case the generative AI generates response information based on that input information. The generative AI may be a conversational AI that includes, for example, a Large Language Model (LLM) and a User Interface (UI) for interacting with the user, enabling text-based or voice-based chat with the user. Examples of such generative AI include tsuzumi®, ChatGPT, GPT®-3.5, GPT-4V, and PaLM2.

[0043] The generated AI may be stored in other devices connected to device 1 via a network, and configured to allow information exchange. Figure 3 shows an example of a system configuration including device 1. In the system configuration shown in Figure 3, the generated AI, LLM20, is stored in LLM server 6 connected to device 1 via a network. When needed, device 1 has LLM20 perform processing via the network, receives the execution results, and uses them. Note that LLM server 6 may be included in system 5.

[0044] The generation AI may be stored in the device 1. FIG. 4 is a diagram showing a modified example of the system configuration of FIG. 3. In the modified example shown in FIG. 4, the LLM 20, which is the generation AI, is stored in the device 1. The device 1 causes the LLM 20 stored in the device 1 to execute processing when necessary and uses the execution result.

[0045] A prompt is information indicating an instruction or question input by a user in an interactive system such as an interaction with a generation AI or a command-line interface (CLI). For example, in a prompt, by text, an instruction for the generation AI to execute, a task for the generation AI to execute, a background / context (e.g., role, condition) to be considered by the generation AI, a question for which an answer is desired from the generation AI, an output format / output format of response information from the generation AI, etc. are expressed. Further, input information that is the target of the instruction / task executed by the generation AI can be added to the prompt. Examples of such input information include data files having a file name including a predetermined extension such as text data, image data, application-related data, audio data, moving image data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a predetermined application program.

[0046] The generation unit 12 may generate a prompt for instructing the generation AI to generate an explanation of the reason for determining the provision location. The generation unit 12 may generate a prompt (hereinafter, this prompt will be simply referred to as "prompt" as appropriate) for instructing the generation AI to generate an explanation of the reason for determining the provision location based on the feature information acquired by the acquisition unit 11. For example, the generation unit 12 may generate a prompt including text related to features for determining the port (relocation location) of a bicycle in a bike-sharing, indicated by the feature information acquired by the acquisition unit 11.

[0047] The generation unit 12 may further generate (a prompt) based on at least one of the target person information and the attribute information acquired by the acquisition unit 11. That is, the generation unit 12 may generate based on the target person information acquired by the acquisition unit 11 and further (for example, based on the feature information and the target person information), or may generate based on the attribute information acquired by the acquisition unit 11 and further (for example, based on the feature information and the attribute information), or may generate based on the target person information and the attribute information acquired by the acquisition unit 11 and further (for example, based on the feature information, the target person information, and the attribute information).

[0048] As described above, in the embodiment, "further based on X" means based on any one or more pieces of information and X that are used when generating the prompt, which appears throughout the description of the generation unit 12 in the embodiment.

[0049] For example, the generation unit 12 may generate a prompt including text related to the feature indicated by the feature information and text related to the target person to be described indicated by the target person information. Also, for example, the generation unit 12 may generate a prompt including text related to the feature indicated by the feature information and text related to the attribute indicated by the attribute information. Also, for example, the generation unit 12 may generate a prompt including text related to the feature indicated by the feature information, text related to the target person to be described indicated by the target person information, and text related to the attribute indicated by the attribute information.

[0050] The generation unit 12 may further generate (a prompt) based on the importance level of the feature information acquired by the acquisition unit 11, which is determined based on at least one of the target person information and the attribute information acquired by the acquisition unit 11. That is, the generation unit 12 may generate based on the importance level determined based on the target person information acquired by the acquisition unit 11 and further based on the importance level of the feature information acquired by the acquisition unit 11, or may generate based on the importance level determined based on the attribute information acquired by the acquisition unit 11 and further based on the importance level of the feature information acquired by the acquisition unit 11, or may generate based on the importance level determined based on the target person information and the attribute information acquired by the acquisition unit 11 and further based on the importance level of the feature information acquired by the acquisition unit 11.

[0051] The determination of importance may be performed by the generation unit 12, or by any other arbitrary means.

[0052] An example of how the generation unit 12 generates a prompt based on the importance level determined based on the target information, and further based on the importance level of the feature information, will be described. For example, if the target information indicates that the person being described is a truck driver, the generation unit 12 may determine the importance level of the demand information and the profit information among the feature information to be "somewhat important," and further generate a prompt based on the fact that the demand information and the profit information are "somewhat important." Here, the importance levels are, in descending order of importance, "important," "somewhat important," "average," "somewhat unimportant," and "unimportant," but are not limited to these.

[0053] When determining importance, the generation unit 12 (or any other arbitrary means) may determine it based on first importance information, which associates target information, characteristic information, and importance, and is stored by the storage unit 10 (or stored in an external device 2, etc.). Figure 5 is a diagram showing an example of a table of first importance information. As shown in the example table in Figure 5, the first importance information associates target information, characteristic information, and importance. For example, if the subject indicated by the target information is a truck driver, in the example table in Figure 5, the record (two records) containing "Target Information: Truck Driver" associates "Character Information: Demand Information, Importance: Somewhat Important" and "Character Information: Profit Information, Importance: Somewhat Important," respectively. Therefore, according to the example table of first importance information shown in Figure 5, the generation unit 12 determines the importance of the demand information and profit information among the characteristic information to be "Somewhat Important."

[0054] Let me explain an example of how the generation unit 12 generates prompts based on the importance level determined from the target information and attribute information, and further based on the importance level of the feature information. For example, if the target information indicates that the person being described is a truck driver, and the attribute information indicates that the truck driver is a beginner, the generation unit 12 may raise the importance level of the demand information among the feature information by one level (from the initial "somewhat important") to "important," and further generate prompts based on the fact that the demand information is "important" (meaning it is primarily demand-driven). Alternatively, for example, if the target information indicates that the person being described is a truck driver, and the attribute information indicates that the truck driver is an advanced driver, the generation unit 12 may raise the importance level of the benefit information among the feature information by one level (from the initial "somewhat important") to "important," and further generate prompts based on the fact that the benefit information is "important" (meaning it is primarily profit-driven).

[0055] The generation unit 12 (or any other arbitrary means) may determine importance based on second importance information, which is associated with target information, attribute information, characteristic information, and importance, and which is stored by the storage unit 10 (or stored in an external device 2, etc.). Figure 6 is a diagram showing an example of a table of second importance information. As shown in the example table in Figure 6, the second importance information is associated with target information, attribute information, characteristic information, and importance. For example, if the target information indicates that the person being described is a truck driver, and the attribute information indicates that the person is a beginner, then in the example table in Figure 6, a record containing "Target information: Truck driver, Attribute information: Beginner" is associated with "Character information: Demand information, Importance: Important". Therefore, the generation unit 12 determines the importance of the demand information among the characteristic information to be "Important" according to the example table of second importance information shown in Figure 6.

[0056] The generation unit 12 may further generate (prompts) based on conditions for explaining the reason, which are determined based on at least one of the subject information and attribute information acquired by the acquisition unit 11. That is, the generation unit 12 may further generate based on conditions for explaining the reason, which are determined based on the subject information acquired by the acquisition unit 11, or the generation unit 12 may further generate based on conditions for explaining the reason, which are determined based on the attribute information acquired by the acquisition unit 11, or the generation unit 12 may further generate based on conditions for explaining the reason, which are determined based on the subject information and attribute information acquired by the acquisition unit 11.

[0057] The determination of the conditions may be performed by the generation unit 12, or by any other arbitrary means.

[0058] An example of how the generation unit 12 generates a prompt based on conditions determined based on the target person information, and further based on the conditions for explaining the reason, will be described. For example, if the target person information indicates that the person to be explained is a truck driver, the generation unit 12 may determine the condition for explaining the reason (which is instruction information (text) for the prompt) to be "Please tell me the reason for placing it in the port," and further generate a prompt based on the fact that the condition for explaining the reason is "Please tell me the reason for placing it in the port."

[0059] The generation unit 12 (or any other arbitrary means) may determine the conditions for the explanation of the reason based on condition information that associates the target person information with the conditions, which is stored by the storage unit 10 (or stored in an external device 2, etc.). Figure 7 is a diagram showing an example of a condition information table. As shown in the example table in Figure 7, the condition information associates the target person information with the conditions. For example, if the target person information indicates a truck driver, in the example table in Figure 7, the record containing "Target person information: Truck driver" is associated with "Condition: Please tell us the reason for placing it in the port." Therefore, the generation unit 12 determines the condition for the explanation of the reason to be "Please tell us the reason for placing it in the port." according to the example table of condition information in Figure 7. Note that, as shown in the example table in Figure 7, if the target person information indicates an operator, the generation unit 12 determines the condition for the explanation of the reason to be "Please tell us the reason for choosing this port instead of other ports." (which is also the reason why other ports were not used.)

[0060] The generation unit 12 may further generate (prompts) based on examples of explanations of reasons determined based on at least one of the subject information and attribute information acquired by the acquisition unit 11. That is, the generation unit 12 may further generate based on examples of explanations of reasons determined based on the subject information acquired by the acquisition unit 11, the generation unit 12 may further generate based on examples of explanations of reasons determined based on the attribute information acquired by the acquisition unit 11, and the generation unit 12 may further generate based on examples of explanations of reasons determined based on the subject information and attribute information acquired by the acquisition unit 11.

[0061] The determination of the examples may be performed by the generation unit 12, or by any other arbitrary means.

[0062] This section describes an example of how the generation unit 12 generates an example based on the target person information and attribute information, and further based on an example of an explanation of the reason. For example, if the target person information indicates that the person being explained is a truck driver, and the attribute information indicates that the person is a beginner, the generation unit 12 will generate an example of an explanation of the reason (which is instruction information (text) to the prompt) that reads: "The substitute port is H1-156-XXXXXX. Please place approximately 10 units in this area. There is a possibility that demand will be high around 15:00, and rain is forecast, so it is unlikely that there will be inflow from other ports, and it may not be possible to cover the demand. There are 5 units to replace batteries. Please replace them in order starting with the YY devices. If there is a problem..." The prompt may be generated based on the following example of explanation for the reason: "The substitute port is H1-156-XXXXXX. Please place approximately 10 units in the area. There is a possibility of high demand around 15:00, and rain is forecast, so inflow from other ports is unlikely, and it may not be possible to cover the demand. There are 5 units to replace batteries. Please replace them in order starting with YY devices. Please replace any that appear to be malfunctioning as needed."

[0063] The generation unit 12 (or any other arbitrary means) may determine an example of an explanation of the reason based on example information that associates the target person information, attribute information, and example, which is stored by the storage unit 10 (or stored in an external device 2, etc.). Figure 8 is a diagram showing an example table of example information. As shown in the example table in Figure 8, the example information associates the target person information, attribute information, and example. For example, if the target person information indicates a truck driver and the attribute information indicates a beginner, then in the example table in Figure 8, a record containing "Target person information: Truck driver, Attribute information: Beginner" would contain the following example: "Example: The substitute port is H1-156-XXXXXX. Please place approximately 10 units in this area. There is a possibility of high demand around 15:00, and rain is forecast, so inflow from other ports is unlikely, and it may not be possible to cover the demand. There are 5 batteries to replace. Please replace them in order from the YY devices. If there is a problem..." 。 English: Since the message "Please replace any items that seem to be malfunctioning as appropriate" is attached, the generation unit 12 determines the example explanation of the reason according to the example information table shown in Figure 8, and decides the example explanation of the reason to be "The substitute port is H1-156-XXXXXX. Please place approximately 10 units in the area. There is a possibility that demand will be high around 15:00, and rain is forecast, so it is unlikely that there will be inflow from other ports, and it may not be possible to cover the demand. The number of batteries to be replaced is 5. Please replace them in order from YY devices. Please replace any items that seem to be malfunctioning as appropriate." In addition, as shown in the example table shown in Figure 8, if the person information indicates that the person to be explained is a truck driver, and the attribute information indicates that the person is an advanced user, the generation unit 12 determines the example explanation of the reason to be "H1-156-XXXXXX. Please place approximately 10 units in the area. The number of batteries to be replaced is 5."

[0064] The generation unit 12 may generate (prompts) based on the location information acquired by the acquisition unit 11. For example, the generation unit 12 may generate a prompt that includes text about the port (relocation location) indicated by the location information acquired by the acquisition unit 11.

[0065] The generation unit 12 may generate (prompts) based on the constraint information acquired by the acquisition unit 11. For example, the generation unit 12 may generate a prompt that includes text relating to the constraints indicated by the constraint information acquired by the acquisition unit 11.

[0066] Figure 9 shows an example of a prompt generated by the generation unit 12. The example prompt shown in Figure 9 is a prompt to instruct the generation AI to generate an explanation of the reason for determining the delivery location, and includes text related to the feature information, target information, attribute information, importance (of the feature information), conditions (of the explanation of the reason), examples (of the explanation of the reason), location information, and constraint information, as described above.

[0067] The generation unit 12 may instruct the generation AI, LLM 20, to process the generated prompt to generate an explanation of the reason, and as a result obtain the explanation of the reason generated by LLM 20. The generation unit 12 may store the obtained explanation of the reason in the storage unit 10, or output it to other functions of the device 1.

[0068] Figure 10 shows an example of a reason explanation. The example of a reason explanation shown in Figure 10 is the text: "The reason for selecting Port A is that there is a possibility of high demand around 15:00, and since rain is forecast, it is unlikely that there will be inflow from other ports, and it may not be possible to cover the demand." In other words, it is text that explains the reason for deciding on a bike port in bike sharing. As mentioned above, the reason explanation is not limited to text, but may also be any content such as audio or video.

[0069] The output unit 13 may output (transmit) arbitrary information to other devices such as external device 2 via a network or the like. For example, the output unit 13 may output a prompt generated by the generation unit 12, or an explanation of the reason obtained by the generation unit 12, to other devices.

[0070] Next, an example of the process performed by device 1 will be explained with reference to Figure 11. Figure 11 is a flowchart showing an example of the process (generation process) performed by device 1.

[0071] First, the acquisition unit 11 acquires characteristic information related to the characteristics for determining the port, which is the location where bikes are provided in bike sharing (step S1, acquisition step). Next, the generation unit 12 generates a prompt to instruct the LLM 20 to generate an explanation of why the port was determined, based on the characteristic information acquired in step S1 (step S2, generation step).

[0072] Next, we will explain an example of the process that System 5 executes, referring to Figure 12. Figure 12 is a flowchart showing an example of the process that System 5 executes.

[0073] First, device 1 (its acquisition unit 11) requests external data from external device 2 (step S10). The timing of this request may be arbitrary. Next, in response to the request in step S10, external device 2 transmits external data in accordance with the request to device 1 (step S11). Examples of external data transmitted in step S11 include bike-sharing data, weather data, real-time population data, and information about relocating users.

[0074] Information regarding the redeployed user may include, for example, any or a combination of the following: (1) Identification information (account information) that identifies the redeployed user; (2) Type of redeployed user (information indicating whether they are a truck driver or an operator); (3) Information indicating the experience level of the truck driver or operator (beginner, advanced, etc.); (4) Information indicating the area under the redeployed user's jurisdiction (e.g., Shibuya Ward); (5) (If the redeployed user is a truck driver,) Information indicating the truck driver's location (e.g., GPS (Global Positioning System) information); (6) Other information (e.g., name, age, gender, length of service, etc.). This information is output to the prompt by device 1, and is also used when obtaining examples from external devices such as device 2 when outputting to the prompt.

[0075] Following step S11, device 1 (including its acquisition unit 11) requests recommendation device 3 for a relocation recommendation (step S12). When making this request, device 1 transmits to recommendation device 3 not only the external data received in step S11 (by the acquisition unit 11 of device 1), but also relocation truck data relating to the trucks to be relocated, demand forecast data relating to the motorcycle demand forecast, inter-port distance data relating to the distance between ports, and relocation user data relating to the users to be relocated.

[0076] The reassigned user data is a portion of the data described in (1) to (6) above. It is the information passed to the prompt, and the information used to search for the information passed to the prompt. For example, the information about the reassigned user is described in (1) to (6) above, and the reassigned user data is the person who will be recommended in the explanation, described in (1) to (3) above (or (1) to (4) above).

[0077] Following step S12, the recommendation device 3 calculates the relocation and the relocation route, which is the truck transportation route associated with the relocation, based on the request in step S12 and the data received in step S12 (step S13). Next, the recommendation device 3 extracts feature information (step S14). Feature information is information about important features in the calculation in step S13 using the AI ​​system. The feature information extracted in step S14 is information that makes the calculation results understandable to humans. For example, since vector information is incomprehensible to humans, it is text that explains it in a way that humans can understand. Next, the recommendation device 3 transmits (replies to, outputs) relocation recommendation information to device 1, which includes the relocation and relocation route calculated in step S13, and the feature information extracted in step S14 (step S15). The relocation recommendation information may also include destination ports, the number of battery replacements, and the number of motorcycles to be recovered and deployed.

[0078] Next, the device 1 (generation unit 12) generates a prompt based on the relocation recommendation information received (acquired) in step S15 (by the acquisition unit 11 of the device 1) (step S16). Next, the device 1 (generation unit 12) has the LLM 20 process the prompt generated in step S16 to obtain an explanation of the reason (including information on why this relocation route was calculated) (step S17). As described above, the device 1 uses the LLM 20 to calculate the recommendation reason using important features in the relocation route calculation and user information.

[0079] Next, the device 1 (output unit 13) transmits output information, including an explanation of the reason for acquiring the data in step S17, to the terminal 4 (step S18). Next, the terminal 4 displays the output information received in step S18 on its own device (step S19).

[0080] Next, the effects and advantages of the apparatus 1 according to this embodiment will be described.

[0081] The device 1 includes an acquisition unit 11 that acquires feature information related to the characteristics for determining the location of a sharing target in a sharing service, and a generation unit 12 that generates a prompt to instruct a generation AI to generate an explanation of the reason for determining the location based on the feature information acquired by the acquisition unit 11. With this configuration, a prompt is generated to instruct the generation AI to generate an explanation of the reason for determining the location of a sharing target in a sharing service. In other words, it is possible to generate information that can generate an explanation of the reason for determining the location of a sharing target.

[0082] In the device 1, the acquisition unit 11 may further acquire at least one of the subject information concerning the person being explained (the person being explained) and attribute information concerning the attributes of the person being explained, and the generation unit 12 may further generate based on at least one of the subject information and attribute information acquired by the acquisition unit 11. With this configuration, it is possible to generate a more accurate and detailed explanation of reasons based on at least one of the subject information and attribute information.

[0083] In the device 1, the generation unit 12 may generate (prompts) based on the importance of the feature information acquired by the acquisition unit 11, which is determined based on at least one of the subject information and attribute information acquired by the acquisition unit 11. This configuration makes it possible to generate a more accurate and detailed explanation of the reason based on the importance of the feature information determined based on at least one of the subject information and attribute information.

[0084] In the apparatus 1, the generation unit 12 may generate (prompts) based on further explanation conditions determined based on at least one of the subject information and attribute information acquired by the acquisition unit 11. This configuration makes it possible to generate more accurate and detailed explanations of reasons based on further explanation conditions determined based on at least one of the subject information and attribute information.

[0085] In the apparatus 1, the generation unit 12 may generate (prompts) based on examples of explanations determined based on at least one of the subject information and attribute information acquired by the acquisition unit 11. This configuration makes it possible to generate more accurate and detailed explanations of reasons based on examples of explanations determined based on at least one of the subject information and attribute information.

[0086] In device 1, the person to be explained may be determined based on the user's designation. This configuration makes it possible to generate a reasoning explanation that better reflects the user's intent, based on at least one of the person information regarding the person to be explained and attribute information regarding the attributes of the person to be explained.

[0087] In device 1, attribute information may be information obtained based on subject information. This configuration makes it possible to generate a more accurate and detailed explanation of the reason based on at least one of the subject information and attribute information obtained based on said subject information.

[0088] In the device 1, the acquisition unit 11 may further acquire location information regarding the place of provision, and the generation unit 12 may generate (prompts) based on the location information acquired by the acquisition unit 11. This configuration makes it possible to generate more accurate and detailed explanations of reasons based on the location information.

[0089] In device 1, the acquisition unit 11 may further acquire constraint information regarding the constraints of the sharing service, and the generation unit 12 may generate (prompts) based on the constraint information acquired by the acquisition unit 11. This configuration makes it possible to generate more accurate and detailed explanations of reasons based on the constraint information.

[0090] With the above-described device 1, for example, the person being explained to can understand the explanation for the reasoning behind the decision on the location where the sharing item will be provided in the sharing service, thereby encouraging a more convincing decision-making and action.

[0091] The apparatus 1 of this disclosure may have the following configuration.

[0092] [1] A device comprising: an acquisition unit that acquires characteristic information relating to the characteristics for determining the location of a sharing service; and a generation unit that generates a prompt to instruct a generating AI to generate an explanation of the reason for determining the location of the sharing service based on the characteristic information acquired by the acquisition unit.

[0093] [2] The apparatus according to [1], wherein the acquisition unit further acquires at least one of subject information relating to the subject described above and attribute information relating to the attributes of the subject, and the generation unit further generates based on at least one of the subject information and attribute information acquired by the acquisition unit.

[0094] [3] The apparatus according to [2], wherein the generation unit generates based on the importance of the feature information acquired by the acquisition unit, which is determined based on at least one of the subject information and attribute information acquired by the acquisition unit.

[0095] [4] The apparatus according to [2] or [3], wherein the generating unit generates based on the conditions described above, which are determined based on at least one of the subject information and attribute information acquired by the acquisition unit.

[0096] [5] The apparatus according to any one of [2] to [4], wherein the generating unit generates based on the examples of the description above, which are determined based on at least one of the subject information and attribute information acquired by the acquisition unit.

[0097] [6] The device described in any one of items [2] to [5], wherein the subject is a person determined based on the user's designation.

[0098] [7] Attribute information is information obtained based on subject information, the device described in any one of items [2] to [6].

[0099] [8] The apparatus according to any one of [1] to [7], wherein the acquisition unit further acquires location information relating to the provision location, and the generation unit generates based on the location information acquired by the acquisition unit.

[0100] [9] The apparatus according to any one of [1] to [8], wherein the acquisition unit further acquires constraint information relating to the constraints of the sharing service, and the generation unit generates based on the constraint information acquired by the acquisition unit.

[0101]

[10] A method performed by a computer, comprising: an acquisition step of acquiring characteristic information relating to characteristics for determining the location of a sharing service; and a generation step of generating a prompt to instruct a generating AI to generate an explanation of the reason for determining the location of the service, based on the characteristic information acquired in the acquisition step.

[0102] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0103] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0104] For example, Apparatus 1 in one embodiment of the present disclosure may function as a computer that processes the method of the present disclosure. Figure 13 is a diagram showing an example of the hardware configuration of Apparatus 1 according to one embodiment of the present disclosure. Physically, Apparatus 1 described above may be configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0105] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of device 1 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0106] Each function in device 1 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0107] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the acquisition unit 11, generation unit 12, and output unit 13 described above may be implemented by the processor 1001.

[0108] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the acquisition unit 11, the generation unit 12, and the output unit 13 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0109] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out a wireless communication method according to one embodiment of the present disclosure.

[0110] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., Compact Disc, Digital Multipurpose Disc, Blu-ray® Disc), a smart card, flash memory (e.g., a card, stick, key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0111] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the acquisition unit 11, generation unit 12 and output unit 13 described above may be implemented by the communication device 1004.

[0112] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0113] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0114] Furthermore, the device 1 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0115] The notification of information is not limited to the manner / embodiments described herein and may be carried out by other means.

[0116] Each aspect / embodiment described in this disclosure may be applied to at least one of the following systems: LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0117] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0118] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0119] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0120] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0121] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0122] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0123] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0124] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0125] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

[0126] The terms “system” and “network” as used in this disclosure are interchangeable.

[0127] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0128] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure.

[0129] As used in this disclosure, the terms “determining” and “decision” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, search, inquiry (e.g., searching in tables, databases or other data structures), and ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and accessing (e.g., accessing data in memory). Furthermore, “determining” may include resolving, selecting, choosing, establishing, and comparing. In other words, "judgment" and "decision" can include considering that some action has been "judged" or "decided." Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0130] The terms “connected,” “coupled,” and any variations thereof mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0131] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0132] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0133] In the configuration of each of the above devices, "means" may be replaced with "part," "circuit," "device," etc.

[0134] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0135] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0136] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0137] 1...Device, 2...External device, 3...Recommendation device, 4...Terminal, 5...System, 6...LLM server, 10...Storage unit, 11...Acquisition unit, 12...Generation unit, 13...Output unit, 20...LLM, 1001...Processor, 1002...Memory, 1003...Storage, 1004...Communication device, 1005...Input device, 1006...Output device, 1007...Bus.

Claims

1. A device comprising: an acquisition unit that acquires characteristic information relating to the characteristics for determining the location of a sharing target in a sharing service; and a generation unit that generates a prompt to instruct a generating AI to generate an explanation of the reason for determining the location of the sharing target based on the characteristic information acquired by the acquisition unit.

2. The apparatus according to claim 1, wherein the acquisition unit further acquires at least one of subject information relating to the subject described above and attribute information relating to the attributes of the subject, and the generation unit further generates based on at least one of the subject information and attribute information acquired by the acquisition unit.

3. The apparatus according to claim 2, wherein the generation unit generates further information based on the importance of the feature information acquired by the acquisition unit, which is determined based on at least one of the subject information and attribute information acquired by the acquisition unit.

4. The apparatus according to claim 2, wherein the generation unit generates based on the conditions described above, which are determined based on at least one of the subject information and attribute information acquired by the acquisition unit.

5. The apparatus according to claim 2, wherein the generation unit generates based on the examples described above, which are determined based on at least one of the subject information and attribute information acquired by the acquisition unit.

6. The apparatus according to claim 2, wherein the subject is a person determined based on the user's designation.

7. The apparatus according to claim 2, wherein the attribute information is information obtained based on the subject information.

8. The apparatus according to claim 1, wherein the acquisition unit further acquires location information relating to the provision location, and the generation unit further generates based on the location information acquired by the acquisition unit.

9. The apparatus according to claim 1, wherein the acquisition unit further acquires constraint information relating to the constraints of the sharing service, and the generation unit further generates based on the constraint information acquired by the acquisition unit.

10. A computer-based method comprising: an acquisition step of acquiring characteristic information relating to characteristics for determining the location of a sharing service; and a generation step of generating a prompt to instruct a generating AI to generate an explanation of the reasons for determining the location of the service, based on the characteristic information acquired in the acquisition step.

Images