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

Abstract

Providing users with information relevant to their destination. [Solution] The server device 10-2 is an information processing device that provides users with route guidance to move to a destination. The server device 10-2 uses a machine learning model that outputs text in response to prompt input to generate questions related to the destination, speaks the generated questions to the user at a different time than when the destination is set, and provides the user with destination-related information based on the user's answers to the spoken questions.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, when moving to a destination according to a guidance route, a navigation device that provides information related to a destination in the vicinity of the guidance route (appropriately, "destination-related information") to a driver or a passenger (appropriately, "user") driving the vehicle is known (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the above conventional technology, there is room for improvement when providing information related to a destination. For example, in the above conventional technology, it is not considered whether the provided information is suitable for the user.

[0005] The present invention has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of providing information related to a destination according to a user.

Means for Solving the Problems

[0006] To solve the above-mentioned problems and achieve the objective, the information processing device according to the present invention is an information processing device that provides a user with route guidance to move to a destination, and is characterized by comprising: a generation unit that generates questions related to the destination using a machine learning model that outputs text in response to prompt input; a speaking unit that speaks the generated questions to the user at a timing different from when the destination is set; and a providing unit that provides the user with destination-related information related to the destination based on the user's answer to the spoken questions.

[0007] Furthermore, the information processing method according to the present invention is an information processing method performed by an information processing device that provides a user with route guidance to a destination, and is characterized by including: a generation step of generating questions related to the destination using a machine learning model that outputs text in response to prompt input; an utterance step of speaking the generated questions to the user at a timing different from when the destination is set; and a provision step of providing destination-related information related to the destination to the user based on the user's answer to the spoken questions.

[0008] Furthermore, the information processing program according to the present invention is an information processing program to be executed by an information processing device that provides route guidance to a user to move to a destination, and is characterized by including: a generation procedure that generates questions related to the destination using a machine learning model that outputs text in response to prompt input; an utterance procedure that speaks the generated questions to the user at a timing different from when the destination is set; and a provision procedure that provides destination-related information related to the destination to the user based on the user's answer to the spoken questions. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a diagram showing an example of the configuration and processing of the information provision system according to Embodiment 1. [Figure 2] Figure 2 is a block diagram showing an example configuration of the information provision system according to Embodiment 1. [Figure 3] Figure 3 is a block diagram showing an example of the configuration of each device in the information provision system according to Embodiment 1. [Figure 4] Figure 4 shows an example of a user information storage unit of a server device according to Embodiment 1. [Figure 5] Figure 5 shows an example of a location information storage unit of a server device according to Embodiment 1. [Figure 6] Figure 6 shows an example of a destination-related information storage unit of a server device according to Embodiment 1. [Figure 7] Figure 7 shows an example of a machine learning model storage unit of a server device according to Embodiment 1. [Figure 8] Figure 8 shows a specific example of destination-related information in the information provision system according to Embodiment 1. [Figure 9] Figure 9 is a flowchart showing an example of the processing flow of the information provision system according to Embodiment 1. [Figure 10] Figure 10 shows an example of the configuration and processing of the information provision system according to Embodiment 2. [Figure 11] Figure 11 is a block diagram showing an example of the configuration of each device in the information provision system according to Embodiment 2. [Figure 12] Figure 12 shows an example of a question information storage unit of a server device according to Embodiment 2. [Figure 13] Figure 13 is a flowchart showing an example of the processing flow of the information provision system according to Embodiment 2. [Figure 14] Figure 14 is a hardware configuration diagram showing an example of a computer that implements the functions of the server devices of Embodiment 1 and Embodiment 2. [Modes for carrying out the invention]

[0010] Embodiments 1 and 2 of the information processing apparatus, information processing method, and information processing program according to the present invention will be described in detail below with reference to the drawings. However, the present invention is not limited to Embodiments 1 and 2 described below.

[0011] [Embodiment 1] The configuration and processing of the information providing system 100-1 according to Embodiment 1, the configuration and processing of each device of the information providing system 100-1, specific examples of each processing of the information providing system 100-1, the flow of processing of the information providing system 100-1, and the effects of Embodiment 1 will be described below.

[0012] [Configuration and Processing of Information Providing System 100-1] The configuration and processing of the information providing system 100-1 according to Embodiment 1 will be described using FIG. 1. FIG. 1 is a diagram showing a configuration example and a processing example of the information providing system 100-1 according to Embodiment 1. Below, a configuration example of the entire information providing system 100-1, a processing example of the information providing system 100-1, and the effects of the information providing system 100-1 will be described.

[0013] (1. Configuration Example of Information Providing System 100-1) The information providing system 100-1 shown in FIG. 1 includes a server device 10-1 and a vehicle VE. Note that the information providing system 100-1 may include a plurality of server devices 10-1. Also, the information providing system 100-1 may include a plurality of vehicles VE. Further, the vehicle VE has an in-vehicle device 20 (not shown) which will be described later.

[0014] Here, the server device 10-1 is an information processing device that executes information provision and the like for a driver DR of a vehicle VE, which is an example of a moving body, and a passenger (not shown). For example, it is realized by a cloud system, an on-premises system, an edge system, etc. Note that below, an example where the moving body is a vehicle will be described, but the moving body is not limited to a vehicle. Also, the technology related to the information providing system 100-1 can be applied to various products. For example, the technology related to the information providing system 100-1 may be realized as a device mounted on any type of moving body such as an automobile, an electric vehicle, a hybrid electric vehicle, a motorcycle, a bicycle, a personal mobility device, an airplane, a drone, a ship, a robot, etc.

[0015] (2. Processing Example of Information Provision System 100-1) First, the server device 10-1 speaks to the driver DR and passengers via the in-vehicle device 20 of the vehicle VE to ask questions related to the destination (step S11). For example, the server device 10-1 classifies topics related to the destination into categories such as "souvenir", "historic building", "gourmet food tour", "dining place", etc., and as knowledge levels indicating the degree of knowledge related to the destination, refers to each item classified into "level 1", "level 2", and "level 3", and asks the driver DR questions about whether each item is known in ascending order of the low knowledge level (e.g., in the order of "level 1", "level 2", "level 3"). Here, the knowledge level of "level 1" is an item that is considered to be known by anyone. Also, the knowledge level of "level 2" is an item that is considered to be known by those who are familiar with the destination. Also, the knowledge level of "level 3" is an item that is considered to be known only by local people. Note that the destination includes not only the final destination that the driver DR and passengers are ultimately scheduled to arrive at, but also the stopover locations that are scheduled to be visited on the way to the final destination.

[0016] At this time, the server device 10-1 refers to each item classified into the topics set by the driver DR and passengers as topics related to the destination, and asks the driver DR and passengers questions about whether each item is known in ascending order of the low knowledge level. Also, the server device 10-1 refers to each item classified into the topics identified using the historical information of the driver DR and passengers during past use as topics related to the destination, and asks the driver DR and passengers questions about whether each item is known in ascending order of the low knowledge level. Also, the server device 10-1 refers to each item classified into the topics randomly selected as topics related to the destination, and asks the driver DR and passengers questions about whether each item is known in ascending order of the low knowledge level.

[0017] Furthermore, the server device 10-1 speaks to the driver DR and passengers at times different from when the destination is set. For example, the server device 10-1 speaks to the driver DR and passengers after a predetermined time (e.g., 10 minutes) has elapsed since the driver DR started driving. The server device 10-1 also speaks to the driver DR and passengers during times when the driver DR and passengers will not arrive at the destination or stopover within the predetermined time (e.g., 10 minutes before the scheduled arrival time). The server device 10-1 also speaks to the driver DR and passengers when the driver DR is driving a route with a driving load below a predetermined value (e.g., while driving on a highway). The server device 10-1 also speaks to the driver DR and passengers at times when there is no conversation between the occupants of the vehicle VE, including the driver DR.

[0018] Secondly, the server device 10-1 receives answers to questions from the driver DR and passengers (step S12). For example, the server device 10-1 receives the driver DR's or passengers' answer "I don't know" to a destination-related question "Do you know ○○?" via the vehicle VE's onboard device 20. The server device 10-1 also receives the driver DR's or passengers' answer "I know" to a destination-related question "Do you know △△?" via the vehicle VE's onboard device 20.

[0019] Thirdly, the server device 10-1 identifies the knowledge level related to the destination of the driver DR and passengers from the received responses (step S13). For example, if the answers to the questions about knowledge level items of "Level 1" are "I know", the answers to the questions about knowledge level items of "Level 2" are "I know", and the answers to the questions about knowledge level items of "Level 3" are "I know", the server device 10-1 identifies the knowledge level related to the destination of the driver DR and passengers as "Level 3".

[0020] Fourth, the server device 10-1 provides destination-related information to the driver DR and passengers based on the identified knowledge level (step S14). For example, if the server device 10-1 identifies the driver DR and passengers' knowledge level related to the destination as "Level 3," it provides details via the vehicle VE's onboard device 20 about the items that the driver DR and passengers have indicated they "want to know" from among the items classified as "Level 3" knowledge level.

[0021] In this case, the server device 10-1 may use a large-scale language model M, which is a machine learning model, to generate questions to be spoken to the driver DR and passengers. The server device 10-1 may also use the large-scale language model M to select destination-related information to be provided to the driver DR.

[0022] (3. Effects of Information Provision System 100-1) Information provision system 100-1 can be applied, for example, to a scenario where the driver (DR) or a passenger sets a destination on the navigation system for a place they have never been to before, and is driving towards it, resulting in the following effects.

[0023] Firstly, drivers and passengers may not be familiar with destination-related information (e.g., an overview of the destination, local specialties, souvenirs, shops around the destination) regarding the set destination. Because they are unfamiliar with this information, they cannot search for or research it, and as a result, they do not initiate conversations with the system to ask questions. Furthermore, when information is provided via a push notification system, the information may not be suitable for the driver or passenger, which can be perceived as bothersome. To address these problems, the information provision system 100-1 conducts a dialogue to assess the driver's and passenger's level of knowledge about the destination and can provide destination-related information appropriate to their knowledge level.

[0024] Secondly, if a dialogue is conducted to assess the driver's (DR) and passenger's (passenger's) level of knowledge about the destination when setting the destination, the dialogue may become lengthy, potentially hindering the decision-making process. To address these issues, the information provision system 100-1 can engage in dialogue with the driver's (DR) and passenger during driving after the destination has been set, providing destination-related information appropriate to their knowledge level.

[0025] [Configuration and processing of each device in Information Provision System 100-1] Using Figures 2 to 7, the configuration and processing of each device in the information provision system 100-1 according to Embodiment 1 will be described. Below, an example of the overall configuration of the information provision system 100-1 according to Embodiment 1 will be described, followed by an example of the configuration and processing of the server device 10-1 according to Embodiment 1, and an example of the configuration and processing of the in-vehicle device 20.

[0026] (1. Example of the overall configuration of Information Provision System 100-1) Using Figure 2, an example of the overall configuration of the information provision system 100-1 according to Embodiment 1 will be described. Figure 2 is a block diagram showing an example of the configuration of the information provision system 100-1 according to Embodiment 1. As shown in Figure 2, the information provision system 100-1 includes a server device 10-1 installed in the cloud system C and an in-vehicle device 20 mounted on the vehicle VE. The server device 10-1 is connected to the in-vehicle device 20 via a predetermined communication network N. Various communication networks such as the internet and dedicated lines can be used as the predetermined communication network N.

[0027] (2. Example configuration and processing of server device 10-1) Using Figure 3, an example of the configuration and processing of the server device 10-1, which is an information processing device, will be explained. Figure 3 is a block diagram showing an example of the configuration of each device in the information provision system 100-1 according to Embodiment 1. The server device 10-1 is an information processing device that provides route guidance to the driver DR and passengers, who are users, to travel to a destination. For example, the server device 10-1 is an information processing device that provides the driver DR and passengers with a drive plan showing the route from a departure point specified by the driver DR and passengers to a destination specified by the driver DR and passengers.

[0028] As shown in Figure 3, the server device 10-1 includes a communication unit 11, a storage unit 12-1, and a control unit 13. The server device 10-1 may also include an input unit (e.g., keyboard, mouse) for receiving various operations from the administrator of the server device 10-1, and a display unit (e.g., liquid crystal display) for displaying various information.

[0029] (2-1. Communications Section 11) The communication unit 11 is implemented, for example, by a NIC (Network Interface Card). The communication unit 11 is connected to a predetermined communication network by wire or wireless connection and performs information transmission and reception with various devices.

[0030] (2-2. Storage section 12-1) The storage unit 12-1 is implemented by, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disc. The storage unit 12-1 according to Embodiment 1, as shown in Figure 3, has a user information storage unit 12a, a location information storage unit 12b, a destination-related information storage unit 12c, and a machine learning model storage unit 12d. The storage unit 12-1 stores various information that the control unit 13 refers to when it operates, and various information acquired when the control unit 13 operates.

[0031] (2-2-1. User information storage unit 12a) The user information storage unit 12a stores user information received by the transmitting / receiving unit 13a, which will be described later. Here, an example of the information stored by the user information storage unit 12a will be explained using Figure 4. Figure 4 is a diagram showing an example of the user information storage unit 12a of the server device 10-1 according to Embodiment 1. In the example in Figure 4, the user information storage unit 12a has items such as "user ID", "user attributes", and "history information".

[0032] "User ID" indicates identification information used to identify the driver (DR). "User Attributes" is information that contributes to the classification of the driver (DR) who has been registered in advance, and includes information such as the driver (DR)'s name, gender, age, age group, occupation, annual income, place of residence, marital status, presence or absence of children, video images of the driver (DR), and categories of interest to the driver (DR). "History Information" is information such as search history, browsing history, purchase history, travel history, and communication history.

[0033] Figure 4 shows an example in which user information is stored in the user information storage unit 12a for a driver DR identified by user ID "UID#1", with user attributes being "User Attribute #1" and history information being "History Information #1".

[0034] (2-2-2. Location information storage unit 12b) The location information storage unit 12b stores location information received by the transmitting / receiving unit 13a, which will be described later. Here, an example of the information stored by the location information storage unit 12b will be explained using Figure 5. Figure 5 is a diagram showing an example of the location information storage unit 12b of the server device 10-1 according to Embodiment 1. In the example in Figure 5, the location information storage unit 12b has items such as "User ID" and "Location Information".

[0035] "User ID" refers to identification information used to identify the driver DR. "Location information" is information received from the onboard device 20 of the vehicle VE being driven by the driver DR, indicating the driver DR's current location, speed, means of transportation, etc.

[0036] Figure 5 shows an example where, for a driver DR identified by user ID "UID#1", user information with location information "Location Information #1" is stored in the location information storage unit 12b.

[0037] (2-2-3. Destination-related information storage unit 12c) The destination-related information storage unit 12c stores destination-related information that is referenced by the speech unit 13c, which will be described later. The destination-related information storage unit 12c also stores destination-related information that is referenced by the provision unit 13e, which will be described later. Here, an example of the information stored by the destination-related information storage unit 12c will be explained using Figure 6. Figure 6 is a diagram showing an example of the destination-related information storage unit 12c of the server device 10-1 according to the embodiment. In the example in Figure 6, the destination-related information storage unit 12c has items such as "destination ID," "level," and "topic." The destination-related information storage unit 12c also stores each item that is classified as a "topic" and associated with a "level" as destination-related information, as well as the details of each item.

[0038] "Destination ID" indicates identification information for identifying the destination. "Level" is a knowledge level indicating the degree of knowledge related to the destination, for example, "Level 1" is a level of knowledge that anyone would know, "Level 2" is a level of knowledge that someone familiar with the destination would know, and "Level 3" is a level of knowledge that only locals would know. "Topic" is a category of destination-related information, for example, "souvenirs," "historical buildings," "street food," "restaurants," etc.

[0039] Figure 6 shows an example in which destination-related information is stored in the destination-related information storage unit 12c for a destination identified by destination ID "DID#1", where "Topic 1" is {Level 1: "Destination-related information #1-1", Level 2: "Destination-related information #1-2", Level 3: "Destination-related information #1-3", ...}, "Topic 2" is {Level 1: "Destination-related information #2-1", Level 2: "Destination-related information #2-2", Level 3: "Destination-related information #2-3", ...}, and "Topic 3" is {Level 1: "Destination-related information #3-1", Level 2: "Destination-related information #3-2", Level 3: "Destination-related information #3-3", ...}, ....

[0040] (2-2-4. Machine Learning Model Memory Unit 12d) The machine learning model storage unit 12d stores a trained large-scale language model M used by the speech unit 13c, which will be described later. The machine learning model storage unit 12d also stores a trained large-scale language model M used by the provisioning unit 13e, which will be described later. Here, an example of the information stored by the machine learning model storage unit 12d will be explained using Figure 7. Figure 7 is a diagram showing an example of the machine learning model storage unit 12d of the server device 10-1 according to the embodiment. In the example in Figure 7, the machine learning model storage unit 12d has an item such as "machine learning model".

[0041] A "machine learning model" is model data of a trained large-scale language model M, which includes, for example, execution data for running the algorithm of the large-scale language model M, model parameters which are settings, hyperparameters, etc.

[0042] Figure 7 shows an example in which multiple trained large-scale language models M, designated as "M001," "M002," etc., are stored in the machine learning model storage unit 12d as "machine learning models." Note that the large-scale language models M may be managed by an external administrator and stored in a predetermined database.

[0043] (2-3. Control Unit 13) The control unit 13 is implemented, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in the memory device inside the server device 10-1 using RAM as the working area. Alternatively, the control unit 13 can be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0044] As shown in Figure 3, the control unit 13 includes a transmitting / receiving unit 13a, a generation unit 13b, a speech unit 13c, a specific unit 13d, and a providing unit 13e, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 13 is not limited to the configuration shown in Figure 3, and other configurations are also acceptable as long as they perform the information processing described later.

[0045] (2-3-1. Transceiver Unit 13a) The transmitting / receiving unit 13a transmits and receives various types of information. The transmitting / receiving unit 13a stores the received information in the storage unit 12-1. The transmitting / receiving unit 13a also refers to the information stored in the storage unit 12-1.

[0046] The transmitting / receiving unit 13a receives the driver DR's or passenger's response to a spoken question. For example, the transmitting / receiving unit 13a receives the driver DR's or passenger's response to a question inquiring whether they are known or not, via the vehicle VE's onboard device 20.

[0047] (2-3-2. Generation unit 13b) The generation unit 13b generates various types of information. The generation unit 13b stores the generated information in the storage unit 12-1. The generation unit 13b also refers to the information stored in the storage unit 12-1.

[0048] The generation unit 13b generates questions related to the destination. For example, the generation unit 13b refers to destination-related information stored in the destination-related information storage unit 12c and generates questions inquiring whether the driver DR or passengers are known or not.

[0049] (2-3-3. Speech section 13c) The speech unit 13c outputs various information through speech. The speech unit 13c also refers to the various information stored in the memory unit 12-1.

[0050] The speech unit 13c speaks questions related to the destination to the user, the driver (DR) or passenger, at a time different from when the destination is set. For example, the speech unit 13c speaks questions to the driver (DR) or passenger to inquire whether they are familiar with each item, which is classified into a predetermined topic and associated with a knowledge level, in order from lowest to highest knowledge level. The speech unit 13c also speaks questions to the driver (DR) or passenger regarding a predetermined topic set by the driver (DR) or passenger. Furthermore, the speech unit 13c speaks questions to the driver (DR) or passenger regarding a predetermined topic identified using the driver's (DR) or passenger's past usage history information. In addition, the speech unit 13c speaks questions to the driver (DR) or passenger after a predetermined amount of time has elapsed since the driver (DR) or passenger started moving. Furthermore, the speech unit 13c speaks questions to the driver (DR) or passenger during a period when the driver (DR) or passenger will not arrive at the destination within a predetermined time. Furthermore, the speech unit 13c speaks questions to the driver DR and passengers while they are traveling along a route with a travel load below a predetermined value. The speech unit 13c also speaks questions to the driver DR and passengers at times when there is no conversation between the occupants of the vehicle VE, including the driver DR. The speech unit 13c also speaks questions to the driver DR and passengers that are generated using a large-scale language model M as a machine learning model. The speech unit 13c also refers to destination-related information stored in the destination-related information storage unit 12c. The server device 10-1 can also refer to the details of each item stored in various databases. Details of the processing of the speech unit 13c will be explained in [Specific Examples of Each Process of the Information Provision System 100-1].

[0051] (2-3-4. Specific part 13d) The identification unit 13d identifies various types of information. The identification unit 13d then stores the identified information in the storage unit 12-1. The identification unit 13d also refers to the information stored in the storage unit 12-1.

[0052] The identification unit 13d identifies the knowledge level of the driver DR and passenger, indicating their degree of knowledge related to the destination, based on their responses to the spoken questions. For example, the identification unit 13d identifies the knowledge level corresponding to an item that the driver DR or passenger answered as unknown as the driver DR's or passenger's knowledge level. Details of the processing of the identification unit 13d will be explained in [Specific Examples of Each Process in Information Provision System 100-1].

[0053] (2-3-5.Providing part 13e) The information provision unit 13e generates various types of information. The information provision unit 13e also refers to the various types of information stored in the storage unit 12-1.

[0054] The information provision unit 13e provides destination-related information to the driver DR and passengers based on the identified knowledge levels of the driver DR and passengers. For example, the information provision unit 13e provides details of the items desired by the driver DR and passengers from among the items corresponding to the identified knowledge levels of the driver DR and passengers as destination-related information. The information provision unit 13e also provides destination-related information to the driver DR and passengers, selected using a large-scale language model M as a machine learning model. Details of the processing of the information provision unit 13e will be explained in [Specific Examples of Each Process of Information Provision System 100-1].

[0055] (3. Example configuration and processing of the in-vehicle device 20) Using Figure 3, an example of the configuration and processing of the in-vehicle device 20 will be explained. The in-vehicle device 20 may also have an input unit (e.g., a touch panel) for receiving various operations from the driver (DR), etc., and a display unit (e.g., a liquid crystal display) for displaying various information.

[0056] The in-vehicle device 20 is a dedicated navigation system built into or mounted on the vehicle's VE. For example, the in-vehicle device 20 consists of a navigation system and a recording device (drive recorder). As one example, the in-vehicle device 20 may be a complex device in which an independent navigation system and a recording device are communicated with each other. As another example, the in-vehicle device 20 may be a single device having both a navigation function and a recording function.

[0057] Furthermore, the in-vehicle device 20 may be equipped with various sensors. For example, the in-vehicle device 20 may have various sensors such as a camera, an accelerometer, a gyroscope, a GPS (Global Positioning System) sensor, and a barometric pressure sensor.

[0058] The in-vehicle device 20 receives data from the server device 10-1 indicating questions related to the destination and outputs it as audio and video. The in-vehicle device 20 also receives data from the server device 10-1 indicating destination-related information and outputs it as audio and video. Furthermore, the in-vehicle device 20 acquires data indicating the driver's (DR) and passenger's (passenger's) answers to the questions and transmits it to the server device 10-1.

[0059] [Specific examples of each process in Information Provision System 100-1] Specific examples of each process of the information provision system 100-1 according to Embodiment 1 will be described below. After describing specific examples of destination-related information, specific examples of destination-related information management processing of the information provision system 100-1 will be described.

[0060] (1. Specific examples of destination-related information) Using Figure 8, a specific example of destination-related information in the information provision system 100-1 will be explained. Figure 8 is a diagram showing a specific example of destination-related information in the information provision system 100-1 according to Embodiment 1. Below, the destination-related information stored in the destination-related information storage unit 12c will be described as destination, topic, and knowledge level.

[0061] (1-1.Destination) As shown in the "Destination" section of Figure 8, the destination-related information of the information provision system 100-1 is information set for each destination. In the example in Figure 8, the destination-related information is set at the "ST Prefecture KG City" level, but it may also be set at the level of country, region, prefecture, municipality, area, facility, etc., and is not particularly limited. Furthermore, the destination-related information may be a destination set by the driver DR or a passenger. In addition, the destination-related information may be set by specifying the destination by latitude and longitude, by specifying the destination by a square area such as a map mesh, or by specifying the destination by the navigation route ID.

[0062] (1-2. Topics) As shown in the "Topics" section of Figure 8, the destination-related information of the information provision system 100-1 includes items classified according to the categories of destination-related information. In the example of Figure 8, the destination-related information is classified as "Souvenirs," "Historical Buildings," "Street Food," and "Restaurants" as "Topics," but it may also include specific facilities and equipment such as "Art Museums," "Baseball Stadiums," "Parks," and "Hiking Trails," specific natural landmarks such as "Waterfalls," "Ponds," and "Coastlines," and specific food and beverages such as "Sweets," "Soba Noodles," and "Beef," and is not particularly limited. Furthermore, the destination-related information may also be topics set by the driver (DR) or passengers.

[0063] (1-3. Knowledge Level) As shown in the "Level" section of Figure 8, the destination-related information of the information provision system 100-1 includes items classified according to the knowledge level of destination-related information. In the example of Figure 8, destination-related information is classified into "Level 1," which is a knowledge level that everyone is expected to know; "Level 2," which is a knowledge level that someone familiar with the destination is expected to know; and "Level 3," which is a knowledge level that only locals are expected to know. However, it may also include "Level 4," a knowledge level that most people are expected to know, and is not particularly limited. Furthermore, destination-related information may also be based on the knowledge level set by the driver (DR) or passengers.

[0064] (2. Specific examples of destination-related information management processing) This section describes a specific example of destination-related information management processing in the information provision system 100-1. The following sections describe topic selection processing, knowledge level selection processing, dialogue timing determination processing, dialogue count determination processing, dialogue execution processing, and destination-related information provision processing.

[0065] (2-1. Topic Selection Process) The server device 10-1 selects a topic set by the driver (DR) or passenger as a topic related to the destination. For example, if the topic of interest set by the driver (DR) or passenger is "historical buildings," the server device 10-1 selects the topic "historical buildings" for the destination "KG City, ST County" and proceeds to the knowledge level selection process.

[0066] The server device 10-1 selects a topic related to the destination, using the driver's (DR) and passenger's past usage history information. For example, the server device 10-1 checks whether a route has been set in the past, and if the topic "Eating Out" is frequently used to classify facilities that the driver (DR) or passenger has previously set as destinations, it selects the topic "Eating Out" for the destination "ST Prefecture, KG City" and proceeds to the knowledge level selection process. Alternatively, the server device 10-1 checks the past conversation history, and if the topic "Restaurants" is frequently used, it selects the topic "Restaurants" for the destination "ST Prefecture, KG City" and proceeds to the knowledge level selection process.

[0067] Server device 10-1 randomly selects a topic related to the destination. For example, server device 10-1 randomly selects the topic "Souvenirs" for the destination "ST Prefecture, KG City," and proceeds to the knowledge level selection process. At this time, server device 10-1 may prioritize selecting topics that have been selected many times in the past, or it may prioritize selecting topics that have been selected infrequently.

[0068] If the server device 10-1 does not have a destination topic set by the driver DR or passenger, it may select a topic using the driver DR's or passenger's past usage history information, or it may select a topic randomly.

[0069] Server device 10-1 may select topics related to the destination, taking into account the time of day. For example, if it is lunchtime or dinnertime, server device 10-1 may prioritize selecting "restaurants". In this case, server device 10-1 may use a trained machine learning model to select topics.

[0070] The server device 10-1 may select topics related to the destination, taking into account the attributes of the driver (DR) and passengers (e.g., gender, age). For example, if the server device 10-1 determines, based on the audio of the conversation, that the driver (DR) or passenger is female, it may prioritize selecting "souvenirs." Alternatively, if the server device 10-1 determines, based on the audio of the conversation, that the driver (DR) or passenger is elderly, it may prioritize selecting "historical buildings." In this case, the server device 10-1 may use a trained machine learning model to select topics.

[0071] The server device 10-1 may select a topic for each driver DR as a topic related to the destination. For example, if the vehicle VE is a family car and the driver DR changes frequently, the server device 10-1 may determine the driver DR based on the voice of the conversation and prioritize selecting a topic set for each driver DR. In this case, the server device 10-1 may use a trained machine learning model to select the topic.

[0072] The server device 10-1 may select a topic related to the destination, taking into account the conversation status of the driver (DR) and passengers. For example, even if the driver (DR) and passengers have set topics, if the server device 10-1 determines that there are few questions or answers from the driver (DR) and passengers and the conversation is not flowing well, it may select a topic different from the one set by the driver (DR) and passengers, or a topic that the driver (DR) and passengers have used less frequently. Also, even if the driver (DR) and passengers have set topics, if the server device 10-1 determines, based on the conversation with the driver (DR) and passengers, that their mood or physical condition is different from usual, it may select a topic different from the one set by the driver (DR) or a topic that the driver (DR) and passengers have used less frequently. In this case, the server device 10-1 may use a trained machine learning model to select the topic.

[0073] Server device 10-1 may select popular topics related to the destination through web searches. For example, if server device 10-1 searches for souvenirs recently featured on television, it may prioritize selecting "souvenirs." In this case, server device 10-1 may use a trained machine learning model to select topics.

[0074] (2-2. Knowledge Level Selection Process) Server device 10-1 prioritizes selecting the first knowledge level as the knowledge level associated with the destination. For example, server device 10-1 selects "Level 1," which is a knowledge level that is thought to be known by everyone, as the knowledge level associated with the destination, and proceeds to the dialogue timing determination process.

[0075] The server device 10-1 prioritizes selecting the second knowledge level as the knowledge level related to the destination if the driver DR or passenger is not at the first knowledge level. For example, the server device 10-1 selects "Level 2," a knowledge level that someone familiar with the destination "ST Prefecture KG City" would likely know, as the knowledge level related to the destination, and proceeds to the dialogue timing determination process.

[0076] The server device 10-1 selects the third knowledge level as the knowledge level related to the destination if the driver DR or passenger is neither at the first nor the second knowledge level. For example, the server device 10-1 selects "Level 3," a knowledge level that is thought to be known only by locals of the destination "KG City, ST Prefecture," and proceeds to the dialogue timing determination process.

[0077] The server device 10-1 may select a knowledge level as a knowledge level related to the destination, taking into account the knowledge level set by the driver DR or passenger. For example, if the first knowledge level set by the driver DR or passenger is "Level 2", the server device 10-1 may select the knowledge levels in the order of "Level 2" and then "Level 3" without selecting "Level 1".

[0078] If no topics or items corresponding to the first knowledge level exist for the destination, the server device 10-1 selects the second knowledge level. If no topics or items corresponding to either the first or second knowledge level exist for the destination, the server device 10-1 selects the third knowledge level.

[0079] The server device 10-1 may select a knowledge level for each driver DR as a knowledge level related to the destination. For example, if the vehicle VE is a family car and the driver DR changes frequently, the server device 10-1 may determine the driver DR based on the voice of the conversation and prioritize selecting the knowledge level set for each driver DR. In this case, the server device 10-1 may use a trained machine learning model to select the knowledge level.

[0080] The server device 10-1 may select a knowledge level related to the destination, identified using the driver's (DR) and passenger's past usage history information. For example, the server device 10-1 may refer to whether a route has been set in the past, and if the driver (DR) or passenger has set "ST Prefecture KG City" as a destination multiple times in the past, it may select knowledge levels in the order of "Level 2" and then "Level 3" without selecting "Level 1". Alternatively, the server device 10-1 may refer to past conversation history, and if the topic with the most frequent conversations is "Historical Buildings", it may select knowledge levels in the order of "Level 2" and then "Level 3" without selecting "Level 1". In this case, the server device 10-1 may use a trained machine learning model to select the knowledge level.

[0081] (2-3. Dialogue timing determination process) The server device 10-1 determines a timing for interacting with the driver DR or passenger that is different from the timing when the driver DR or passenger sets the destination, and is after a predetermined time has elapsed since the driver DR or passenger started driving. For example, the server device 10-1 determines a timing for interacting with the driver DR or passenger that is 10 minutes after the driver DR or passenger started driving from the departure point or stopover point, and proceeds to the dialogue count determination process. At this time, the server device 10-1 may use a trained machine learning model to determine the dialogue timing.

[0082] The server device 10-1 determines the timing for interacting with the driver DR or passenger to be different from the timing when the driver DR or passenger sets the destination, and to be a time when the driver DR or passenger will not arrive at the destination within a predetermined time. For example, the server device 10-1 determines the timing for interacting with the driver DR or passenger to be a time when the driver DR or passenger will not arrive at the final destination or stopover within 10 minutes, and proceeds to the dialogue count determination process. At this time, the server device 10-1 may use a trained machine learning model to determine the dialogue timing.

[0083] The server device 10-1 determines the timing for interacting with the driver DR and passengers to be different from the timing when the driver DR and passengers set a destination, and when the driver DR and passengers are traveling on a route with a driving load below a predetermined value. For example, the server device 10-1 determines the timing for interacting with the driver DR and passengers to be when the driver DR is driving on a highway or main road. At this time, for example, the server device 10-1 calculates a score indicating the driving load based on the vehicle VE's position information, and if the score is below a predetermined value, it determines that it is the right time to interact with the driver DR and passengers. The server device 10-1 also receives scores from various systems that estimate the driving load score, and if the score is below a predetermined value, it determines that it is the right time to interact with the driver DR and passengers and proceeds to the dialogue count determination process. At this time, the server device 10-1 may use a trained machine learning model to determine the dialogue timing.

[0084] The server device 10-1 determines that a time when the driver DR and passengers are not conversing with each other, and that is different from the time when the driver DR and passengers set the destination, is a time to converse with the driver DR and passengers. For example, the server device 10-1 determines that a time when the driver DR and passengers have not conversed for 5 minutes or more is a time to converse with the driver DR and passengers, and proceeds to the dialogue count determination process. At this time, the server device 10-1 may use a trained machine learning model to determine the dialogue timing.

[0085] (2-4. Determination of the number of dialogues) The server device 10-1 determines the number of interactions to have with each driver DR. For example, if the vehicle VE is a family car and the driver DR changes frequently, the server device 10-1 determines the driver DR from the voice of the interaction, and if the driver DR has had many interactions based on past history information, it decides to increase the number of interactions to have with the driver DR and proceeds to the interaction execution process. In this case, the server device 10-1 may use a trained machine learning model to determine the number of interactions.

[0086] The server device 10-1 determines the number of times to interact with the driver DR and passengers, taking into account the conversation status of the driver DR and passengers. For example, if the server device 10-1 determines that the number of interactions with the driver DR and passengers is low and the conversation is not flowing well, it decides to reduce the number of interactions with the driver DR and passengers and proceeds to the dialogue execution process. At this time, the server device 10-1 may also initiate another interaction with the driver DR and passengers when the current location is approaching the destination. Alternatively, the server device 10-1 may use a trained machine learning model to determine the number of interactions.

[0087] The server device 10-1 determines the number of conversations to have with the driver DR and passengers, taking into account the distance to the destination. For example, when the current location is far from the destination, the server device 10-1 decides to reduce the number of conversations with the driver DR and passengers, and when the current location is close to the destination, it decides to increase the number of conversations with the driver DR and passengers, and then proceeds to the conversation execution process. At this time, the server device 10-1 may use a trained machine learning model to determine the number of conversations.

[0088] The server device 10-1 determines the number of conversations to have with the driver (DR) and passengers, taking into account the time of day. For example, if the topic is "restaurants" and it is lunchtime or dinnertime, the server device 10-1 decides to increase the number of conversations to have with the driver (DR) and passengers and proceeds to the conversation execution process. In this case, the server device 10-1 may use a trained machine learning model to determine the number of conversations.

[0089] Here, the number of dialogues refers to the number of times the server device 10-1 speaks to the driver DR or passengers. For example, if the server device 10-1 asks, "Would you like to know more about the ○○ Bell, KG Castle, and Kwon, which are tourist attractions in KG City, ST County?" regarding the topic "Historical Buildings" and knowledge level "Level 1," and then provides destination-related information for "○○ Bell" and "KG Castle," the total number of dialogues will be counted as 3. Next, if the server device 10-1 asks, "Would you like to know more about the O Family Residence, the Former Y Family Villa, and the KG Chamber of Commerce, which are tourist attractions in KG City, ST County?" regarding the topic "Historical Buildings" and knowledge level "Level 2," and then provides destination-related information for "O Family Residence," "The Former Y Family Villa," and "KG Chamber of Commerce," the total number of dialogues will be counted as 7. Furthermore, if server device 10-1, regarding the topic "Street Food" and knowledge level "Level 1," asks "Would you like to know more about CO-an Chips, KG Pudding, and N Main Store's Grilled Rice Balls, which are street food items in KG City, ST Prefecture?", and then provides destination-related information only about "KG Pudding," the total number of dialogues will be 9. In the example above, if the determined number of dialogues is 9, server device 10-1 has reached its dialogue limit and will not ask any further questions or provide destination-related information. On the other hand, even if the dialogue limit has been reached, server device 10-1 will still engage in dialogue if the driver DR or passenger requests destination-related information such as "I want to know about tourist attractions in KG City, ST Prefecture."

[0090] (2-5. Dialogue Execution Process) Firstly, if the server device 10-1 selects the topic "Historical Buildings" for the destination "KG City, ST County" in the topic selection process described above, and selects knowledge level "Level 1" in the knowledge level selection process described above, then the destination-related information storage unit 12c stores {Destination: "KG City, ST County", Topic: "Historical Buildings", Knowledge Level: "Level 1"} and refers to {"○○ Bell", "KG Castle", "K-in"} as destination-related information.

[0091] Secondly, the server device 10-1 generates the following sentence as a question with the destination {destination: "KG City, ST County", topic: "historical buildings", knowledge level: "level 1"}: "Are you familiar with Kwon, a historical building in KG City, ST County, which is currently set as the destination?" and speaks it to the driver DR or passengers via the vehicle VE's onboard device 20.

[0092] Thirdly, if the driver DR or passenger answers "I don't know" to a question of knowledge level "Level 1", the server device 10-1 determines the driver DR or passenger's knowledge level to be "Level 1". The server device 10-1 also generates a sentence such as "Would you like to know more about the tourist attractions of KG City, ST Prefecture: the ○○ Bell, KG Castle, and K-Inn?" and speaks it to the driver DR or passenger via the vehicle VE's onboard device 20. If the driver DR or passenger answers "Yes", the server device 10-1 proceeds to the destination-related information provision process. On the other hand, if the driver DR or passenger answers "No", the server device 10-1 terminates the conversation. Similarly, the server device 10-1 terminates the conversation if there is a complaint such as "It's too noisy" or if no one answers.

[0093] Fourth, if the driver DR or passenger answers "I know" to a question of knowledge level "Level 1", the server device 10-1 refers to the destination-related information stored in the destination-related information storage unit 12c for {Destination: "ST Prefecture KG City", Topic: "Historical Buildings", Knowledge Level: "Level 2"}, specifically {"O Family Residence", "Former Y Family Villa", "KG Chamber of Commerce and Industry"}.

[0094] Fifth, the server device 10-1 generates the following sentence as a question with {Destination: "KG City, ST County", Topic: "Historical Buildings", Knowledge Level: "Level 2"}: "Are you familiar with the former Y family villa, a historical building, in KG City, ST County, which is currently set as the destination?" and speaks it to the driver DR or passengers via the vehicle VE's onboard device 20.

[0095] Sixth, if the driver DR or passenger answers "I don't know" to a question of knowledge level "Level 2", the server device 10-1 determines the driver DR or passenger's knowledge level to be "Level 2". The server device 10-1 also generates the sentence, "Would you like to know more about the tourist attractions in KG City, ST Prefecture: the O Family Residence, the former Y Family Villa, and the KG Chamber of Commerce?" and speaks it to the driver DR or passenger via the vehicle VE's onboard device 20. If the driver DR or passenger answers "Yes", the server device 10-1 proceeds to provide destination-related information. On the other hand, if the driver DR or passenger answers "No", the server device 10-1 terminates the conversation. Similarly, the server device 10-1 terminates the conversation if there is a complaint such as "It's too noisy" or if no one answers.

[0096] Seventh, if the driver DR or passenger answers "I know" to a question of knowledge level "Level 2", the server device 10-1 determines the driver DR or passenger's knowledge level to be "Level 3". In addition, the server device 10-1 refers to the destination-related information stored in the destination-related information storage unit 12c for {Destination: "ST Prefecture KG City", Topic: "Historical Buildings", Knowledge Level: "Level 3"}, specifically {"Former T Family Residence", "KG Church", "H Folk Museum"}.

[0097] Eighth, the server device 10-1 generates the sentence, "Would you like to know more about the tourist attractions in KG City, ST County: the former T family residence, KG Church, and H Folk Museum?" and speaks it to the driver DR and passengers via the vehicle VE's onboard device 20. If the driver DR or passengers respond with "Yes," the server device 10-1 proceeds to provide destination-related information. On the other hand, if the driver DR or passengers respond with "No," the server device 10-1 terminates the conversation. Similarly, the server device 10-1 terminates the conversation if there is a complaint such as "It's too noisy," or if no one responds.

[0098] In the above dialogue execution process, the server device 10-1 can also generate questions using a large-scale language model M. For example, the server device 10-1 can generate a question corresponding to {destination: "KG city, ST prefecture", topic: "historical buildings", knowledge level: "level 1"} by inputting "Create a sentence asking whether you know about a well-known historical building in KG city, ST prefecture" as a prompt to the large-scale language model M stored in the machine learning model memory unit 12d.

[0099] (2-6. Processing of destination-related information) The server device 10-1 retrieves details of {"○○ Bell", "KG Castle", "K-Inn"} as destination-related information stored in the destination-related information storage unit 12c for {Destination: "ST County KG City", Topic: "Historical Buildings", Knowledge Level: "Level 1"}, and provides this destination-related information to the driver DR and passengers via the vehicle VE's onboard device 20. The server device 10-1 can also retrieve details of each item stored in various databases and provide this destination-related information to the driver DR via the vehicle VE's onboard device 20.

[0100] The server device 10-1 refers to the details of {"O Family Residence", "Former Y Family Villa", "KG Chamber of Commerce"} as destination-related information for {Destination: "ST Prefecture KG City", Topic: "Historical Buildings", Knowledge Level: "Level 2"} stored in the destination-related information storage unit 12c, and provides this destination-related information to the driver DR and passengers via the vehicle VE's onboard device 20. The server device 10-1 can also refer to the details of each item stored in various databases and provide this destination-related information to the driver DR and passengers via the vehicle VE's onboard device 20.

[0101] The server device 10-1 retrieves details of {"Former T Family Residence", "KG Church", and "H Folk Museum"} as destination-related information stored in the destination-related information storage unit 12c for {Destination: "ST County KG City", Topic: "Historical Buildings", Knowledge Level: "Level 3"}, and provides this destination-related information to the driver DR and passengers via the vehicle VE's onboard device 20. The server device 10-1 can also retrieve details of each item stored in various databases and provide this destination-related information to the driver DR and passengers via the vehicle VE's onboard device 20.

[0102] In the destination-related information provision process described above, the server device 10-1 can also select destination-related information using a large-scale language model M. For example, if the driver DR or a passenger responds that they would like to know more about KG Church, the server device 10-1 can generate destination-related information corresponding to "KG Church" by inputting "Please tell me more about KG Church" as a prompt into the large-scale language model M stored in the machine learning model memory unit 12d.

[0103] [Processing flow of Information Provision System 100-1] The processing flow of the information provision system 100-1 according to Embodiment 1 will be explained using Figure 9. Figure 9 is a flowchart showing an example of the processing flow of the information provision system 100-1 according to Embodiment 1. Note that the processes in steps S101 to S104 below can be executed in a different order. Also, some of the processes in steps S101 to S104 below may be omitted.

[0104] (1. Question utterance processing) Firstly, the server device 10-1 performs question utterance processing (step S101). For example, the server device 10-1 utters destination-related questions to the driver DR and passengers via the vehicle VE's onboard device 20 in the order of "Level 1", "Level 2", and "Level 3".

[0105] (2. Processing of received responses) Secondly, the server device 10-1 performs response reception processing (step S102). For example, the server device 10-1 receives the response "I don't know" from the driver DR or passenger to the destination-related question "Do you know ○○?" via the vehicle VE's onboard device 20.

[0106] (3. Knowledge level identification process) Thirdly, the server device 10-1 performs knowledge level identification processing (step S103). For example, if the answer to a question about an item with a "Level 2" knowledge level is "I don't know", the server device 10-1 identifies the knowledge level related to the driver DR's or passenger's destination as "Level 2".

[0107] (4. Processing of destination-related information) Fourth, the server device 10-1 performs destination-related information provision processing (step S104) and then terminates the processing. For example, if the server device 10-1 identifies the driver DR's or passenger's knowledge level related to the destination as "Level 2", it provides details via the vehicle VE's onboard device 20 about the items that the driver DR or passenger answered they "want to know" from among the items classified as "Level 2" knowledge level.

[0108] [Effects of Embodiment 1] The effects of Embodiment 1 will now be described. Below, effects 1 to 10 corresponding to each process in Embodiment 1 will be explained.

[0109] (1. Effect 1) Firstly, in the process according to Embodiment 1 described above, the server device 10-1 is an information processing device that provides route guidance to the driver DR and passengers to move to a destination. At a timing different from when the destination is set, it speaks questions related to the destination to the driver DR and passengers, identifies the knowledge level indicating the degree of knowledge of the driver DR and passengers related to the destination based on the answers of the driver DR and passengers to the spoken questions, and provides destination-related information to the driver DR and passengers based on the identified knowledge level of the driver DR and passengers. Therefore, in this process, the knowledge level of the driver DR and passengers related to the destination can be identified, and destination-related information can be provided according to the driver DR and passengers.

[0110] (2. Effect 2) Secondly, in the process according to Embodiment 1 described above, the server device 10-1 asks questions to inquire whether the driver DR or passenger is familiar with each item, which has been classified into a predetermined topic and associated with a knowledge level, in order from lowest to highest knowledge level. The server device identifies the knowledge level corresponding to the item that the driver DR or passenger answers as unfamiliar, and provides details of the items that the driver DR or passenger desires from among the items corresponding to the identified knowledge level of the driver DR or passenger as destination-related information. Therefore, in this process, the knowledge level of the driver DR or passenger related to the destination can be identified through dialogue, and destination-related information can be provided according to the driver DR or passenger.

[0111] (3. Effect 3) Thirdly, in the process according to Embodiment 1 described above, the server device 10-1 speaks questions to the driver DR or passenger regarding predetermined topics set by the driver DR or passenger. Therefore, in this process, the knowledge level of the topics set by the driver DR or passenger can be determined through dialogue, and destination-related information can be provided according to the driver DR or passenger.

[0112] (4. Effect 4) Fourth, in the process according to Embodiment 1 described above, the server device 10-1 speaks to the driver DR and passengers with questions about predetermined topics identified using the driver DR's and passengers' past usage history information. Therefore, in this process, the knowledge level of the topics set based on the driver DR's and passengers' history information can be identified through dialogue, and destination-related information can be provided according to the driver DR and passengers.

[0113] (5. Effect 5) Fifth, in the process according to Embodiment 1 described above, the server device 10-1 speaks a question to the driver DR or passenger after a predetermined time has elapsed since the driver or passenger started driving. Therefore, in this process, the knowledge level can be determined by engaging in dialogue after a predetermined time has elapsed since the driver DR or passenger started driving, and destination-related information can be provided according to the driver DR or passenger.

[0114] (6. Effect 6) Sixth, in the process according to Embodiment 1 described above, the server device 10-1 speaks questions to the driver DR and passengers during the time when the driver DR and passengers do not arrive at the destination within a predetermined time. Therefore, in this process, the knowledge level can be determined by engaging in dialogue with the driver DR and passengers during the time when they do not arrive at the destination within a predetermined time, and destination-related information can be provided according to the driver DR and passengers.

[0115] (7. Effect 7) Seventh, in the process according to Embodiment 1 described above, the server device 10-1 speaks questions to the driver DR or passenger while they are driving a route with a driving load below a predetermined value. Therefore, in this process, the knowledge level can be determined by the interaction between the driver DR and passenger while they are driving a route with a driving load below a predetermined value, and destination-related information can be provided according to the driver DR and passenger.

[0116] (8. Effect 8) Eighth, in the process according to Embodiment 1 described above, the server device 10-1 speaks questions to the driver DR and passengers at times when the occupants of the vehicle VE are not conversing with each other. Therefore, in this process, the knowledge level can be determined by engaging in dialogue at times when the occupants of the vehicle VE are not conversing with each other, and destination-related information can be provided according to the driver DR and passengers.

[0117] (9. Effect 9) Ninth, in the process according to Embodiment 1 described above, the server device 10-1 speaks questions generated using the large-scale language model M as a machine learning model to the driver DR and passengers. Therefore, in this process, the knowledge level can be identified by engaging in dialogue with questions generated by the large-scale language model M, and destination-related information can be provided according to the driver DR and passengers.

[0118] (10. Effect 10) Tenth, in the process according to Embodiment 1 described above, the server device 10-1 provides destination-related information selected using a large-scale language model M as a machine learning model to the driver DR and passengers. Therefore, in this process, destination-related information can be provided according to the driver DR and passengers, as the knowledge level can be identified and then selected by the large-scale language model M.

[0119] [Embodiment 2] The following describes the configuration and processing of the information provision system 100-2 according to Embodiment 2, the configuration and processing of each device in the information provision system 100-2, specific examples of each process in the information provision system 100-2, the processing flow of the information provision system 100-2, and the effects of Embodiment 2. Note that configurations and processes common to Embodiment 1 will not be described.

[0120] [Configuration and Processing of Information Provision System 100-2] The configuration and processing of the information provision system 100-2 according to Embodiment 2 will be explained using Figure 10. Figure 10 is a diagram showing an example of the configuration and processing of the information provision system 100-2 according to Embodiment 2. Below, an example of the overall configuration of the information provision system 100-2, an example of the processing of the information provision system 100-2, and the effects of the information provision system 100-2 will be explained.

[0121] (1. Example configuration of information provision system 100-2) The information provision system 100-2 shown in Figure 10 includes a server device 10-2 and a vehicle VE. The information provision system 100-2 may include multiple server devices 10-2. Furthermore, the information provision system 100-2 may include multiple vehicle VEs. The vehicle VE also includes an on-board device 20 (not shown), which will be described later.

[0122] Here, the server device 10-2 is an information processing device that provides information to the driver DR and passengers of a vehicle VE, which is an example of a mobile object, and is implemented by, for example, a cloud system, an on-premise system, or an edge system.

[0123] (2. Example of processing in Information Provision System 100-2) Firstly, the server device 10-2 uses a large-scale language model M, which is a machine learning model, to generate a question related to the destination (step S21). For example, the server device 10-2 inputs the following prompts into the large-scale language model M, which include the destination "KG City, ST County", the destination-related topic "Historical Buildings", and "Top 5 Popularity Ranking" for each item classified under the topic, ranging from middle to lower ranks: "Create a sentence asking if you know about the top 5 popular historical building in KG City, ST County", and "Please omit the phrase 'Top 5 Popularity Ranking'", to generate the question "Are you familiar with the KG Church, a historical building in KG City, ST County, which is currently set as the destination?". Note that the destination includes not only the final destination where the driver DR and passengers are scheduled to arrive, but also any stops they plan to make along the way to the final destination.

[0124] At this time, the server device 10-2 selects a topic set by the driver DR or passenger as a topic related to the destination, generates a prompt, and generates a question. Alternatively, the server device 10-2 selects a topic identified using the driver DR or passenger's past usage history information as a topic related to the destination, generates a prompt, and generates a question. Alternatively, the server device 10-2 selects a randomly selected topic as a topic related to the destination, generates a prompt, and generates a question.

[0125] Secondly, the server device 10-2 speaks a question related to the destination to the driver DR or passenger (step S22). For example, the server device 10-2 speaks to the driver DR or passenger via the vehicle VE's onboard device 20 as a question related to the generated destination, such as, "Are you familiar with KG Church, a historical building in KG City, ST County, which is currently set as the destination?"

[0126] Furthermore, the server device 10-2 speaks to the driver DR and passengers at times different from when the destination is set. For example, the server device 10-2 speaks to the driver DR and passengers after a predetermined time (e.g., 10 minutes) has elapsed since the driver DR started driving. The server device 10-2 also speaks to the driver DR and passengers during times when the driver DR and passengers will not arrive at the destination or stopover within the predetermined time (e.g., 10 minutes before the scheduled arrival time). The server device 10-2 also speaks to the driver DR and passengers when the driver DR is driving a route with a driving load below a predetermined value (e.g., driving on a highway). The server device 10-2 also speaks to the driver DR and passengers at times when there is no conversation between the occupants of the vehicle VE, including the driver DR.

[0127] Thirdly, the server device 10-2 receives answers to questions from the driver DR and passengers (step S23). For example, the server device 10-2 receives the driver DR's or passenger's answer "I don't know" or "I know" to the destination-related question "Do you know about KG City in ST County, which is currently set as the destination?" via the vehicle VE's onboard device 20.

[0128] Fourth, the server device 10-2 provides destination-related information to the driver DR and passengers based on their responses (step S24). For example, if the driver DR or passengers respond that they "don't know" about "KG Church" via the vehicle VE's onboard device 20, and the driver DR or passengers respond that they "want to know" about "KG Church", the server device 10-2 collects details about "KG Church" from various databases and explains them to the driver DR and passengers.

[0129] In this case, the server device 10-2 may use a large-scale language model M to select destination-related information to provide to the driver DR.

[0130] (3. Effects of Information Provision System 100-2) In addition to the effects of information provision system 100-1, information provision system 100-2 can more easily provide destination-related information suitable for drivers DR and passengers by having the large-scale language model M generate questions about items that tend to generate engaging conversations in the middle to lower ranks of the popularity ranking.

[0131] [Configuration and processing of each device in the information provision system 100-2] The configuration and processing of each device in the information provision system 100-2 according to Embodiment 2 will be described using Figures 11 and 12. Below, an example of the configuration and processing of the server device 10-2 according to Embodiment 2 will be described. Note that the overall configuration example of the information provision system 100-2 according to Embodiment 2, as well as the configuration example and processing example of the in-vehicle device 20, are the same as those in Embodiment 1, so their explanation will be omitted.

[0132] (1. Example configuration and processing of server device 10-2) Using Figure 11, an example of the configuration and processing of the server device 10-2, which is an information processing device, will be explained. Figure 11 is a block diagram showing an example of the configuration of each device in the information provision system 100-2 according to Embodiment 2. The server device 10-2 is an information processing device that provides route guidance to the driver DR and passengers, who are users, to travel to a destination. For example, the server device 10-2 is an information processing device that provides the driver DR and passengers with a drive plan showing the route from a departure point specified by the driver DR and passengers to a destination specified by the driver DR and passengers.

[0133] As shown in Figure 11, the server device 10-2 includes a communication unit 11, a storage unit 12-2, and a control unit 13. The server device 10-2 may also have an input unit (e.g., keyboard, mouse) for receiving various operations from the administrator of the server device 10-2, and a display unit (e.g., liquid crystal display) for displaying various information.

[0134] (1-1. Communications Section 11) The communication unit 11 is implemented, for example, by a NIC (Network Interface Card). The communication unit 11 is connected to a predetermined communication network by wire or wireless connection and performs the transmission and reception of information with various devices.

[0135] (1-2.Storage unit 12-2) The storage unit 12-2 is implemented by, for example, a semiconductor memory element such as RAM or flash memory, or a storage device such as a hard disk or optical disc. The storage unit 12-2 according to Embodiment 2 has a user information storage unit 12a, a location information storage unit 12b, a question information storage unit 12e, and a machine learning model storage unit 12d, as shown in Figure 11. The storage unit 12-2 stores various information that the control unit 13 refers to when it operates, and various information acquired when the control unit 13 operates. The configuration examples and processing examples of the user information storage unit 12a, the location information storage unit 12b, and the machine learning model storage unit 12d are the same as in Embodiment 1, so their explanation is omitted.

[0136] (1-2-1. Question Information Storage Unit 12e) The question information storage unit 12e stores the question information generated by the generation unit 13b, which will be described later. Here, an example of the information stored by the question information storage unit 12e will be explained using Figure 12. Figure 12 is a diagram showing an example of the question information storage unit 12e of the server device 10 according to the embodiment. In the example in Figure 12, the question information storage unit 12e has items such as "User ID", "Prompt", and "Question".

[0137] "User ID" indicates identification information for identifying the driver DR. "Prompt" is an instruction generated by the generation unit 13b and input to the large-scale language model M, which is a machine learning model, and is an instruction to create a question that includes, for example, a destination, a topic, and a ranking in the popularity ranking, and asks whether the driver DR or passenger is familiar with it or not. "Question" is the sentence of the question output by the large-scale language model M, and is, for example, a sentence of a question that asks whether the driver DR or passenger is familiar with a predetermined item in the popularity ranking that is classified into a predetermined topic related to the destination.

[0138] Figure 12 shows an example in which question information is stored in the question information storage unit 12e for a driver DR identified by user ID "UID#1", with the following format: {Prompt: "Prompt #1-1", Question: "Question #1-1", ...}, {Prompt: "Prompt #1-2", Question: "Question #1-2", ...}, {Prompt: "Prompt #1-3", Question: "Question #1-3", ...}, ...

[0139] (1-3. Control Unit 13) The control unit 13 is implemented, for example, by a CPU or MPU executing various programs stored in the internal memory of the server device 10 using RAM as the working area. Alternatively, the control unit 13 can be implemented by an integrated circuit such as an ASIC or FPGA.

[0140] As shown in Figure 11, the control unit 13 includes a transmitting / receiving unit 13a, a generation unit 13b, a speech unit 13c, a specific unit 13d, and a providing unit 13e, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 13 is not limited to the configuration shown in Figure 11, and other configurations are also acceptable as long as they perform the information processing described later.

[0141] (1-3-1. Transceiver Unit 13a) The transmitting / receiving unit 13a transmits and receives various types of information. The transmitting / receiving unit 13a stores the received information in the storage unit 12-2. The transmitting / receiving unit 13a also refers to the information stored in the storage unit 12-2.

[0142] The transmitting / receiving unit 13a receives the driver DR's or passenger's response to a spoken question. For example, the transmitting / receiving unit 13a receives the driver DR's or passenger's response to a question inquiring whether they are known or not, via the vehicle VE's onboard device 20.

[0143] (1-3-2. Generation unit 13b) The generation unit 13b generates various types of information. The generation unit 13b stores the generated information in the storage unit 12-2. The generation unit 13b also refers to the information stored in the storage unit 12-2.

[0144] The generation unit 13b generates questions related to the destination. For example, the generation unit 13b generates questions related to the destination using a large-scale language model M, which is a machine learning model that outputs text in response to prompt input. The generation unit 13b also generates prompts that include the destination, a predetermined topic, and a popularity ranking lower than a predetermined value for each item classified under the predetermined topic, and inputs these into the large-scale language model M, which is a machine learning model, to generate questions that inquire whether the driver DR or passengers are familiar with a predetermined item in the popularity ranking classified under a predetermined topic related to the destination.

[0145] (1-3-3. Speech section 13c) The speech unit 13c outputs various information through speech. The speech unit 13c also refers to the various information stored in the memory unit 12-2.

[0146] The speech unit 13c speaks questions related to the generated destination to the user, the driver DR, or passengers, at a time different from when the destination is set. For example, the speech unit 13c speaks a question to inquire whether the driver DR or passengers are familiar with a predetermined item in a popularity ranking that is classified into a predetermined topic related to the destination. The speech unit 13c also speaks questions to the driver DR or passengers regarding a predetermined topic set by the driver DR or passengers. Furthermore, the speech unit 13c speaks questions to the driver DR or passengers regarding a predetermined topic identified using the driver DR or passengers' past usage history information. In addition, the speech unit 13c speaks questions to the driver DR or passengers after a predetermined amount of time has elapsed since the driver DR or passengers started moving. Furthermore, the speech unit 13c speaks questions to the driver DR or passengers during a period when the driver DR or passengers will not arrive at the destination within a predetermined time. Furthermore, the speech unit 13c speaks questions to the driver DR and passengers while they are traveling along a route with a travel load below a predetermined value. The speech unit 13c also speaks questions to the driver DR and passengers at times when there is no conversation between the occupants of the vehicle VE, which is a moving object including the driver DR. The speech unit 13c also speaks questions to the driver DR and passengers that have been generated using a large-scale language model M as a machine learning model. The server device 10-2 can also refer to the details of each item stored in various databases. Details of the processing of the speech unit 13c will be explained in [Specific Examples of Each Process of the Information Provision System 100-2].

[0147] (1-3-4. Specific part 13d) The identification unit 13d identifies various types of information. The identification unit 13d stores the identified information in the storage unit 12-2. The identification unit 13d also refers to the information stored in the storage unit 12-2. The details of the processing of the identification unit 13d are the same as in Embodiment 1, so the explanation is omitted.

[0148] (1-3-5.Providing part 13e) The information provision unit 13e generates various types of information. The information provision unit 13e also refers to the various types of information stored in the storage unit 12-2.

[0149] The information provision unit 13e provides destination-related information to the driver DR and passengers based on their responses to spoken questions. For example, the information provision unit 13e provides details of items that the driver DR or passengers answered as unknown as destination-related information. The information provision unit 13e also provides destination-related information to the driver DR and passengers selected using a large-scale language model M as a machine learning model. Details of the processing of the information provision unit 13e will be explained in [Specific Examples of Each Process of Information Provision System 100-2].

[0150] [Specific examples of each process in the information provision system 100-2] Specific examples of each process of the information provision system 100-2 according to Embodiment 2 will be described below. Specifically, a specific example of the destination-related information management process of the information provision system 100-2 will be described.

[0151] (1. Specific examples of destination-related information management processing) This section describes a specific example of destination-related information management processing in the information provision system 100-2. The following sections describe topic selection processing, question generation processing, dialogue timing determination processing, dialogue count determination processing, dialogue execution processing, and destination-related information provision processing.

[0152] (1-1. Topic Selection Process) The server device 10-2 executes the topic selection process and then proceeds to the question generation process. The topic selection process is the same as in Embodiment 1, so its explanation is omitted.

[0153] (1-2. Question generation process) Firstly, the server device 10-2 generates a prompt, which is an instruction to generate a question related to the destination. For example, the server device 10-2 generates a prompt that includes the destination "KG City, ST County", the topic related to the destination "Historical Buildings", and the popularity ranking of each item classified under the topic "Top 5 in Popularity Ranking", such as "Please create a sentence asking if you know about the top 5 historical building in KG City, ST County", and "Please omit the phrase 'Top 5 in Popularity Ranking'", and stores it in the question information storage unit 12e.

[0154] Secondly, the server device 10-2 generates a question related to the destination by inputting the generated prompt into the large-scale language model M. For example, the server device 10-2 refers to the prompt stored in the question information storage unit 12e and inputs the prompt into the large-scale language model M stored in the machine learning model storage unit 12d, thereby generating the question, "Are you familiar with the KG Church, a historical building in KG City, ST Prefecture, which is currently set as the destination?", storing it in the question information storage unit 12e, and proceeding to the dialogue timing determination process.

[0155] The server device 10-2 may select a popularity ranking based on the driver's (DR) and passenger's past usage history information. For example, the server device 10-2 may refer to whether or not a route has been set in the past, and if the driver (DR) or passenger has set "ST Prefecture KG City" as a destination multiple times in the past, it may select the lower-ranked "8th place in popularity ranking."

[0156] (1-3. Dialogue timing determination process) The server device 10-2 executes the dialogue timing determination process and then proceeds to the dialogue count determination process. The dialogue timing determination process is the same as in Embodiment 1, so its explanation is omitted.

[0157] (1-4. Determination of the number of dialogues) The server device 10-2 executes the dialogue count determination process and then proceeds to the destination-related information provision process. The dialogue count determination process is the same as in Embodiment 1, so its explanation is omitted.

[0158] (1-5. Dialogue Execution Process) The server device 10-2 speaks questions related to the generated destination to the driver DR and passengers. For example, the server device 10-2 refers to the question stored in the question information storage unit 12e, "Are you familiar with the historical building KG Church in KG City, ST County, which is currently set as the destination?", and speaks it to the driver DR and passengers via the vehicle VE's onboard device 20. If the driver DR or passengers answer "I don't know," the server device 10-2 proceeds to destination-related information provision processing if they answer "I want to know." On the other hand, if the driver DR or passengers answer "I don't want to know," the server device 10-2 terminates the conversation.

[0159] (1-6. Processing of destination-related information) The server device 10-2 provides destination-related information to the driver (DR) and passengers. For example, the server device 10-2 refers to the details of each item stored in various databases and provides this information to the driver (DR) and passengers via the vehicle's onboard device 20. Alternatively, the server device 10-2 can also refer to the details of each item stored in the storage unit 12-2 and provide this information to the driver (DR) and passengers via the vehicle's onboard device 20.

[0160] In the destination-related information provision process described above, the server device 10-2 can also select destination-related information using a large-scale language model M. For example, if the driver DR or a passenger responds, "I want to know more about K Hospital," the server device 10-2 can generate destination-related information corresponding to "K Hospital" by inputting "Please tell me more about K Hospital" as a prompt into the large-scale language model M stored in the machine learning model memory unit 12d.

[0161] [Processing flow of Information Provision System 100-2] The processing flow of the information provision system 100-2 according to Embodiment 2 will be explained using Figure 13. Figure 13 is a flowchart showing an example of the processing flow of the information provision system 100-2 according to Embodiment 2. Note that the processes in steps S201 to S204 below can be executed in a different order. Also, some of the processes in steps S201 to S204 below may be omitted.

[0162] (1. Question generation process) Firstly, the server device 10-2 performs a question generation process (step S201). For example, the server device 10-2 generates a question related to a destination by inputting prompts including the destination, topic, and popularity ranking into the large language model M.

[0163] (2. Question Utterance Processing) Secondly, the server device 10-2 performs question utterance processing (step S202). For example, the server device 10-2 utters a question related to the generated destination to the driver DR or passengers via the vehicle VE's onboard device 20.

[0164] (3. Processing of received responses) Thirdly, the server device 10-2 performs response reception processing (step S203). For example, the server device 10-2 receives the response "I don't know" from the driver DR or passenger to the destination-related question "Do you know ○○?" via the vehicle VE's onboard device 20.

[0165] (4. Processing of destination-related information) Fourth, the server device 10-2 performs destination-related information provision processing (step S204) and then terminates the processing. For example, the server device 10-2 explains the details of the items that the driver DR and passengers have indicated they "want to know" via the vehicle VE's onboard device 20.

[0166] [Effects of Embodiment 2] The effects of Embodiment 2 will now be described. Below, effects 1 to 10 corresponding to each process in Embodiment 2 will be explained.

[0167] (1. Effect 1) Firstly, in the process according to Embodiment 2 described above, the server device 10-2 is an information processing device that provides route guidance to the driver DR and passengers to move to a destination. It uses a machine learning model that outputs text in response to prompt input to generate questions related to the destination, and speaks questions related to the destination to the driver DR and passengers at a different time than when the destination is set. Based on the answers of the driver DR and passengers to the spoken questions, it provides destination-related information to the driver DR and passengers. Therefore, in this process, it is possible to generate questions related to the destination for the driver DR and passengers, and thus provide destination-related information according to the driver DR and passengers.

[0168] (2. Effect 2) Secondly, in the process according to Embodiment 2 described above, the server device 10-2 generates a prompt including a destination, a predetermined topic, and a popularity ranking lower than a predetermined value for each item classified under the predetermined topic, and inputs this into a machine learning model. This generates a question inquiring whether the driver (DR) or passenger is familiar with the predetermined items in the popularity ranking classified under the predetermined topic related to the destination. The generated question is then spoken to the driver (DR) or passenger, and details of the items that the driver (DR) or passenger answered as unfamiliar are provided as destination-related information. Therefore, this process can efficiently generate destination-related questions for the driver (DR) or passenger, and can provide destination-related information according to the driver (DR) or passenger.

[0169] (3. Effect 3) Thirdly, in the process according to Embodiment 2 described above, the server device 10-2 speaks questions to the driver DR or passenger regarding predetermined topics set by the driver DR or passenger. Therefore, this process can generate questions related to topics set by the driver DR or passenger, and can provide destination-related information according to the driver DR or passenger.

[0170] (4. Effect 4) Fourth, in the process according to Embodiment 2 described above, the server device 10-2 speaks questions to the driver DR and passengers regarding predetermined topics identified using the driver DR's and passengers' past usage history information. Therefore, in this process, questions related to topics set based on the driver DR's and passengers' history information can be generated, and destination-related information can be provided according to the driver DR and passengers.

[0171] (5. Effect 5) Fifth, in the process according to Embodiment 2 described above, the server device 10-2 speaks a question to the driver DR or passenger after a predetermined time has elapsed since the driver or passenger started driving. Therefore, this process can generate questions to be asked after a predetermined time has elapsed since the driver DR or passenger started driving, and can provide destination-related information according to the driver DR or passenger.

[0172] (6. Effect 6) Sixth, in the process according to Embodiment 2 described above, the server device 10-2 speaks questions to the driver DR and passengers during the time when the driver DR and passengers do not arrive at the destination within a predetermined time. Therefore, this process can generate questions to be asked during the time when the driver DR and passengers do not arrive at the destination within a predetermined time, and can provide destination-related information according to the driver DR and passengers.

[0173] (7. Effect 7) Seventh, in the process according to Embodiment 2 described above, the server device 10-2 speaks questions to the driver DR or passenger while they are driving a route with a driving load below a predetermined value. Therefore, this process can generate questions that the driver DR or passenger may ask while they are driving a route with a driving load below a predetermined value, and can provide destination-related information according to the driver DR or passenger.

[0174] (8. Effect 8) Eighth, in the process according to Embodiment 2 described above, the server device 10-2 speaks questions to the driver DR and passengers at times when the occupants of the vehicle VE are not conversing with each other. Therefore, in this process, questions can be generated at times when the occupants of the vehicle VE are not conversing with each other, and destination-related information can be provided according to the driver DR and passengers.

[0175] (9. Effect 9) Ninth, in the process according to Embodiment 2 described above, the server device 10-2 speaks questions generated using the large-scale language model M as a machine learning model to the driver DR and passengers. Therefore, in this process, since questions can be generated by the large-scale language model M, destination-related information can be provided according to the driver DR and passengers.

[0176] (10. Effect 10) Tenth, in the process according to Embodiment 2 described above, the server device 10-2 provides destination-related information selected using a large-scale language model as a machine learning model to the driver DR and passengers. Therefore, in this process, after generating a question, it is possible to select the provision of destination-related information selected by the large-scale language model M, so that destination-related information can be provided according to the driver DR and passengers.

[0177] [Hardware configuration] Furthermore, the server device 10-1 according to Embodiment 1 and the server device 10-2 according to Embodiment 2 described above are implemented by a computer 1000 having a configuration such as that shown in Figure 14. Hereinafter, the server device 10-1 or the server device 10-2 will be used as an example for explanation. Figure 14 is a hardware configuration diagram showing an example of a computer that implements the functions of the server devices of Embodiment 1 and Embodiment 2. The computer 1000 has a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0178] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0179] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 receives data from other devices via a predetermined communication network and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined communication network.

[0180] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600.

[0181] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0182] For example, when the computer 1000 functions as a server device 10-1 according to Embodiment 1 or a server device 10-2 according to Embodiment 2, the CPU 1100 of the computer 1000 realizes the functions of the control unit 13 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0183] 〔others〕 Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0184] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0185] Furthermore, the above embodiments can be combined as appropriate, provided that the processing content is not contradictory.

[0186] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0187] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the transmitting / receiving unit can be replaced with transmitting / receiving means or transmitting / receiving circuit. [Explanation of Symbols]

[0188] 10-1, 10-2 Server Equipment 11 Communications Department 12-1, 12-2 Storage section 12a User information storage unit 12b Location information storage section 12c Destination-related information storage unit 12d Machine Learning Model Memory Unit 12e Question Information Storage Unit 13 Control Unit 13a Transceiver Unit 13b Generator 13c Speech Unit 13d Specific part 13e supply department 20 Onboard equipment 100-1, 100-2 Information Provision System 1000 computers 1100 CPU 1200 RAM 1300 ROM 1400 HDD 1500 Communication Interface (I / F) 1600 Input / Output Interfaces (I / F) 1700 Media Interface (I / F) 1800 recording media C Cloud System M Large-scale language models N Communication Network

Claims

1. An information processing device that provides users with route guidance to travel to their destination, A generation unit that generates questions related to the destination using a machine learning model that outputs text in response to prompt input, A speech unit that speaks the generated question to the user at a different time than when the destination is set, A provisioning unit that provides destination-related information to the user based on the user's response to the spoken question, An information processing device characterized by comprising:

2. The generating unit is By generating a prompt that includes the destination, a predetermined topic, and a popularity ranking lower than a predetermined value for each item classified under the predetermined topic, and inputting this prompt into the machine learning model, a question is generated that inquires whether the user is familiar with a predetermined item in the popularity ranking classified under the predetermined topic related to the destination. The aforementioned speech unit, The generated question is spoken to the user. The aforementioned supply unit is, The user will provide details of the items for which they responded that they were unknown, as destination-related information. The information processing apparatus according to feature 1.

3. The aforementioned speech unit, The system speaks to the user the question related to the predetermined topic set by the user. The information processing apparatus according to feature 2.

4. The aforementioned speech unit, The system speaks to the user the question concerning the predetermined topic identified using the user's past usage history information. The information processing apparatus according to feature 2.

5. The aforementioned speech unit, After a predetermined amount of time has elapsed since the user began to move, the question is spoken to the user. The information processing apparatus according to feature 1.

6. The aforementioned speech unit, During the time period when the user does not arrive at the destination within the predetermined time, the question is spoken to the user. The information processing apparatus according to feature 1.

7. The aforementioned speech unit, The question is spoken to the user while the user is traveling along a route with a travel load below a predetermined value. The information processing apparatus according to feature 1.

8. The aforementioned speech unit, The question is spoken to the user at a time when there is no conversation between the passengers of the mobile vehicle, including the user. The information processing apparatus according to feature 1.

9. The generating unit is The machine learning model used to generate the question is a large-scale language model. The information processing apparatus according to any one of claims 1 to 8.

10. The aforementioned supply unit is, The destination-related information selected using a large-scale language model as the machine learning model is provided to the user. The information processing apparatus according to any one of claims 1 to 8.

11. An information processing method performed by an information processing device that provides users with route guidance to move to a destination, A generation process that generates questions related to the destination using a machine learning model that outputs text in response to prompt input, A speech step in which the generated question is spoken to the user at a different time than when the destination is set, A provision step of providing destination-related information to the destination based on the user's response to the spoken question, An information processing method characterized by including

12. An information processing program to be executed by an information processing device that provides users with route guidance to move to a destination, A generation procedure for generating questions related to the destination using a machine learning model that outputs text in response to prompt input, A speech procedure in which the generated question is spoken to the user at a different time than when the destination is set, A provision procedure for providing destination-related information to the user based on the user's response to the spoken question, An information processing program characterized by including the following.

Images