Method, information processing apparatus, and system

Abstract

To improve a technique for providing a driving environment corresponding to a user.SOLUTION: The information processing apparatus 10 detects the occurrence of any of one or more events based on the vehicle information acquired from the vehicle. Next, the information processing apparatus 10 acquires user information and prompt generation information corresponding to the detected event. Next, the information processing apparatus 10 uses the acquired user information and prompt generation information to generate a prompt for causing the language model server 20 to output an action for the detected event. Next, the information processing apparatus 10 inputs the prompt to the language model server 20. Then, the information processing device 10 executes an action based on the output of the language model server 20 in response to the prompt.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for providing a driving environment tailored to a user. For example, Patent Document 1 discloses an invention in which a vehicle-related action is executed for each user within the vehicle. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-055148 Summary of the Invention [Problem to be solved by the invention]

[0004] There was room for improvement in the technology that provides a driving environment tailored to the user.

[0005] In view of the above circumstances, an object of the present disclosure is to improve the technology for providing a driving environment that suits the user. [Means for solving the problem]

[0006] According to one embodiment of the present disclosure, a method comprises: A method executed by an information processing device, Detecting an occurrence of any of one or more events based on vehicle information obtained from the vehicle; obtaining user information and prompt generation information responsive to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; performing an action based on an output of the first language model in response to the prompt; Includes.

[0007] An information processing device according to an embodiment of the present disclosure includes: Detecting an occurrence of one or more events based on vehicle information obtained from the vehicle; Obtaining user information and prompt generation information according to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; a control unit that performs an action based on an output of the first language model in response to the prompt; Equipped with.

[0008] In accordance with one embodiment of the present disclosure, a system includes: A system including an information processing device and a language model server storing a first language model, The information processing device includes: Detecting an occurrence of one or more events based on vehicle information obtained from the vehicle; Obtaining user information and prompt generation information according to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; The language model server outputting the first language model in response to the prompt; The information processing device includes: Perform an action based on the output. [Effects of the Invention]

[0009] According to one embodiment of the present disclosure, a technique for providing a user-specific driving environment is improved. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram illustrating a schematic configuration of a system according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a block diagram showing a schematic configuration of an information processing device. [Figure 3] FIG. 10 is a flowchart illustrating the operation of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present disclosure will be described.

[0012] (Outline of the embodiment) An overview of a system 1 according to an embodiment of the present disclosure will be described with reference to Fig. 1. The system 1 includes an information processing device 10, a language model server 20, and a content server 30. The information processing device 10, the language model server 20, and the content server 30 are communicably connected to a network 40 including, for example, the Internet and a mobile communication network.

[0013] The information processing device 10 is, for example, an in-vehicle device installed in a vehicle, or a server that issues instructions to the vehicle via a network 40. The information processing device 10 is capable of communicating with a language model server 20 and a content server 30 via the network 40.

[0014] The language model server 20 is a server that exists, for example, on a cloud and provides a first language model. The first language model is, for example, a large-scale language model (LLM) such as ChatGPT or Megatron-Turing Natural Language Generation (MT-NLG), but is not limited to these, and any language model may be used. The language model server 20 receives a prompt input from the information processing device 10 via the network 40 and transmits an output in response to the prompt to the information processing device 10. Alternatively, the language model server 20 may be the information processing device 10.

[0015] The content server 30 is a server that provides content such as music and videos to users. The content server 30 is, for example, a streaming service such as YouTube (registered trademark), TikTok, Netflix, or Spotify, but is not limited to these, and any streaming service may be used. Furthermore, the information processing device 10 may also function as the content server 30.

[0016] First, an overview of this embodiment will be described, and details will be provided later. The information processing device 10 detects the occurrence of one or more events based on vehicle information acquired from a vehicle. Next, the information processing device 10 acquires user information and prompt generation information corresponding to the detected event. Next, the information processing device 10 uses the acquired user information and prompt generation information to generate a prompt for causing the language model server 20 to output an action for the detected event. Next, the information processing device 10 inputs the prompt to the language model server 20. Then, the information processing device 10 executes an action based on the output of the language model server 20 for the prompt.

[0017] Conventional technologies for providing a driving environment tailored to a user execute a uniform action, making it difficult to provide an environment that takes into account various factors such as the user's state and driving situation. In contrast, according to the present embodiment, a prompt created using user information and prompt generation information tailored to a detected event is input into a first language model, and an action is executed based on the output of the first language model in response to the prompt. Therefore, for example, if a child is a passenger in a vehicle and the child starts crying, the probability of executing an action that takes into account the user's state, characteristics, preferences, etc. in response to an event that has occurred is increased, such as playing a popular video of content that the child likes. Therefore, according to the present embodiment, the probability of executing an action that takes into account the user's state, characteristics, preferences, etc. in response to an event that has occurred is increased, thereby improving the technology for providing a driving environment tailored to a user.

[0018] Next, each component of the system 1 will be described in detail.

[0019] (Configuration of information processing device) 2, the information processing device 10 includes a communication unit 11, an output unit 12, an input unit 13, a storage unit 14, a control unit 15, a sensor unit 16, and an image capturing unit 17. In this embodiment, the information processing device 10 may be configured with an in-vehicle device and a server that issues instructions to the vehicle. For example, the output unit 12, the input unit 13, the sensor unit 16, and the image capturing unit 17 of the information processing device 10 may be provided in the in-vehicle device, and the storage unit 14 and the control unit 15 may be provided in the server.

[0020] The communication unit 11 includes one or more communication interfaces connected to the network 40. The communication interfaces may be compatible with, for example, a mobile communication standard, a wired LAN (Local Area Network) standard, or a wireless LAN standard, but are not limited to these and may be compatible with any communication standard. In this embodiment, the information processing device 10 communicates with the language model server 20 and the content server 30 via the communication unit 11 and the network 40.

[0021] The output unit 12 includes one or more output devices that are installed in the vehicle and that output information. The output devices may be, for example, but are not limited to, a display that outputs information as a video or a speaker that outputs information as a sound. Alternatively, the output unit 12 may include an interface for connecting an external output device.

[0022] The input unit 13 includes one or more input devices mounted on the vehicle that detect input operations by a user. Examples of the input devices include, but are not limited to, physical keys, capacitive keys, a mouse, a touch panel, a touch screen integrated with the display of the output unit 12, or a microphone. Alternatively, the input unit 13 may include an interface for connecting an external input device. In this embodiment, the input unit 13 may also be used to acquire user voice, which is necessary for acquiring vehicle information or user information.

[0023] In this embodiment, the term "user" refers not only to the driver of the vehicle but also to passengers, such as family members such as the driver's children, etc. Passengers may also include pets.

[0024] The storage unit 14 includes one or more memories. Each memory included in the storage unit 14 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 14 stores any information used in the operation of the information processing device 10. For example, the storage unit 14 may store a system program, an application program, embedded software, etc. In the present embodiment, the storage unit 14 stores user information. The storage unit 14 may be provided in an in-vehicle device or a server, or the entire storage unit 14 may be configured by the in-vehicle device and the server. In addition, when the information processing device 10 serves as a content server 30, the storage unit 14 may store programs and data required for the content server 30. The storage unit 14 may also store a second language model, which is a language model different from the first language model.

[0025] The control unit 15 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor may be, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process, but is not limited to these. The programmable circuit may be, for example, but is not limited to, an FPGA (Field-Programmable Gate Array). The dedicated circuit may be, for example, but is not limited to, an ASIC (Application Specific Integrated Circuit). The control unit 15 controls the overall operation of the information processing device 10.

[0026] The sensor unit 16 includes a plurality of sensors installed in the vehicle that are necessary to acquire vehicle information, such as a steering angle sensor, an acceleration sensor, a vehicle speed sensor, a position sensor, a gyro sensor, etc. The sensor unit 16 may be compatible with, for example, a GPS (Global Positioning System) or the like.

[0027] The photographing unit 17 includes one or more cameras mounted on the vehicle and capable of photographing the periphery or interior of the vehicle. In this embodiment, the photographing unit 17 may be used to acquire an image of the user required to acquire vehicle information or user information.

[0028] (Operation flow of information processing device) The operation of the information processing device 10 according to this embodiment will be described with reference to FIG.

[0029] S100: The control unit 15 of the information processing device 10 detects the occurrence of one or more events based on vehicle information acquired from the vehicle.

[0030] The "one or more events" refers to any one or more events that may occur between the time the user gets into the vehicle and the time the user gets out of the vehicle. The one or more events may include, for example, a passenger (e.g., a child) starting to cry, the driver being distracted, and the driver being tired.

[0031] "Vehicle information" is any information that can be acquired at predetermined intervals or in real time using on-board devices such as the input unit 13, the sensor unit 16, and the photographing unit 17. The vehicle information may include, for example, images and voices of the user, various vehicle conditions (position, vehicle speed, shift position, etc.), and route information. It may be predetermined which vehicle information is to be acquired for each of one or more events.

[0032] S101: The control unit 15 acquires user information and prompt generation information corresponding to the detected event.

[0033] The "user information" may include, for example, the user's status, schedule, driving history, family structure, age, gender, and preferences, but may also include any information about the user, without being limited to these. The control unit 15 may also acquire the user information by referencing information managed by another application, such as schedule information in Microsoft Outlook. It may also be predetermined which user information to acquire for each of one or more events.

[0034] "User status information" may include, for example, the user's current status, such as whether the user is crying, tired, dazed, or has a cold, or information about the user's health, such as whether the user has a chronic illness, but may also include any information regarding the user's status, without being limited to these.

[0035] "User schedule information" may include, for example, information about the user's actions on the previous day, sleep time, etc., but may also include any information indicating the user's actions, without being limited to these.

[0036] The "information on the user's driving history" may include, for example, information such as the user's driving time on the previous day, destination, etc., but may also include any information indicating the user's driving history, without being limited to these. Note that the information on the user's driving history may also be a history of any information acquired using in-vehicle devices such as the input unit 13, the sensor unit 16, and the photographing unit 17.

[0037] "User's family information" may include information about the user's wife or husband, children, parents, etc. The user's family information may also include information about pets.

[0038] "User preference information" may include, for example, information about the user's favorite foods, music, and hobbies, but may also include any information related to the user's preferences, without being limited to these. Preference information may also include information about things the user dislikes. For example, preference information may include information about the user's least favorite foods, music, etc.

[0039] The "prompt generation information" may be a prompt template that includes an instruction to output an action for an event and an instruction to take the acquired user information into consideration when determining the action. The prompt template may be stored in advance in the storage unit 14. Alternatively, the prompt template may be created using a second language model stored in the storage unit 14. Specifically, the control unit 15 may input information about the detected event into the second language model, and use the output from the second language model in response to the input as the prompt template.

[0040] S102: The control unit 15 uses the acquired user information and prompt generation information to generate a prompt for causing the language model server 20 to output an action for the detected event.

[0041] Specifically, the control unit 15 generates the prompt by embedding the acquired user information in a portion of a prompt template that is to be taken into consideration when determining an action. Alternatively, the control unit 15 may input information about the detected event and the acquired user information into a second language model, and output from the second language model in response to the input as the prompt.

[0042] S103: The control unit 15 inputs the prompt to the language model server 20.

[0043] S104: The control unit 15 executes an action based on the output of the language model server 20 in response to the prompt.

[0044] Execution of an "action" means causing each device of the information processing device 10 or the content server 30 to take an action or output an execution command in response to the prompt output from the language model server 20. The "action" may include, for example, playing specific music, playing a specific video, and providing route guidance to a rest area such as a service area, but may also include any action that can be performed using each device of the information processing device 10 or the content server 30, without being limited to these.

[0045] The operation of this embodiment is performed by executing the above steps, but to explain the operation more specifically, a specific example will be used below.

[0046] A first example will be described in which the event is that a child has started crying. In this case, the vehicle information used in S100 may be an image or audio of the child. The control unit 15 detects that the child has started crying from an image of the child captured by the image capturing unit 17. Alternatively, the control unit 15 may detect the child's crying using the microphone of the input unit 13. Next, in S101, the control unit 15 acquires user information corresponding to the event that the child has started crying, including information on the child's condition, age, gender, and preferences, and prompt generation information. Next, in S102, if the prompt generation information is, for example, "Your child is crying. Please consider the following points and implement appropriate measures," the control unit 15 generates a prompt by adding the information on the child's condition, age, gender, and preferences to the prompt generation information. Next, in S103, the control unit 15 inputs the prompt to the language model server 20. At this time, it is assumed that the various pieces of information added to the prompt generation information are that the child's condition is crying, the child's age is 5 years old, the child's gender is male, and the child's preference is that he or she loves anime programs. Suppose the output of the language model server 20 in response to the prompt is, for example, "Why not try playing a video of children's anime program A?" In this case, in S104, the control unit 15 may connect to the content server 30 or search the storage unit 14 to acquire the video, and then perform the action by playing back the motion using the display and speaker of the output unit 12.

[0047] Next, a second example will be described in which the event is that the driver is tired. In this case, the vehicle information used in S100 may be an image of the driver, various vehicle conditions (position, vehicle speed, shift position, etc.), and route information. For example, the control unit 15 may detect that the driver is tired from the driver's body or eye movements in the image of the driver captured by the image capture unit 17, or various vehicle conditions acquired by the sensor unit 16. Next, in S101, the control unit 15 acquires user information corresponding to the event that the driver is tired, such as information on the driver's schedule and driving history, and prompt generation information. Next, in S102, if the prompt generation information is, for example, "The driver is tired. Consider the following points and continue driving without taking a break, or if you should take a break, please provide location information for a rest point," the control unit 15 generates a prompt by adding information on the driver's schedule and driving history, as well as the vehicle's position and route information included in the vehicle information, to the prompt generation information. Next, in S103, the control unit 15 inputs the prompt to the language model server 20. In this case, the various information added to the prompt generation information may include the driver's schedule indicating that he slept for three hours yesterday, his driving history indicating that he drove round trip from Tokyo to Osaka yesterday, his vehicle's location indicating Hachioji, and route information indicating that he drove to Nagoya with a remaining distance of 340 km. The output of the language model server 20 in response to the prompt may include, for example, location information of the Ishikawa parking area. In this case, the control unit 15 may execute an action in S104 by displaying a route from the vehicle's current location to the Ishikawa parking area on the display of the output unit 12. The control unit 15 may also output a sound, using the speaker of the output unit 12, suggesting that the driver take a rest at a parking area.

[0048] Alternatively, suppose the various information added to the prompt generation information includes the driver's schedule indicating that the driver slept for 7 hours yesterday, the driving history indicating that there was no driving history yesterday, the vehicle's location indicating Hachioji, and the route information indicating that the route is to Mt. Takao with a remaining distance of 7 km. The output of the language model server 20 in response to the prompt may be, for example, that it is okay to continue driving without taking a break, but that the driver needs to be careful. In this case, the control unit 15 may execute an action in S104 by using the display or speaker of the output unit 12 to output a displayed or audio message that warns the driver about a lack of concentration while driving.

[0049] As described above, the information processing device 10 according to this embodiment detects the occurrence of one or more events based on vehicle information acquired from a vehicle. Next, the information processing device 10 acquires user information and prompt generation information corresponding to the detected event. Next, the information processing device 10 uses the acquired user information and prompt generation information to generate a prompt for causing the language model server 20 to output an action for the detected event. Next, the information processing device 10 inputs the prompt to the language model server 20. Then, the information processing device 10 executes an action based on the output of the language model server 20 in response to the prompt.

[0050] According to this configuration, a created prompt is input into a first language model using user information and prompt generation information corresponding to the detected event, and an action is executed based on the output of the first language model in response to the prompt. Therefore, for example, if there is a child passenger in the vehicle and the child starts crying, it is more likely that an action can be executed in response to the occurring event, taking into account the user's state, characteristics, preferences, etc., such as playing a popular video of content that the child likes. Therefore, according to this embodiment, the technology for providing a driving environment tailored to the user is improved in that it is more likely that an action can be executed in response to the occurring event, taking into account the user's state, characteristics, preferences, etc.

[0051] Although the present disclosure has been described based on the drawings and examples, it should be noted that those skilled in the art may make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each component or step can be rearranged so as not to be logically inconsistent, and multiple components or steps can be combined or divided into one.

[0052] For example, in the above-described embodiment, the configuration and operation of the information processing device 10 may be distributed among a plurality of computers that can communicate with each other.

[0053] Also, for example, in the above-described embodiment, the control unit 15 may acquire the user's reaction to the action executed in S104. In this case, the control unit 15 may update the user information based on the user's reaction.

[0054] Specifically, the control unit 15 uses any device of the information processing device 10 to acquire an in-vehicle environmental change related to the user's reaction after S104 is executed. For example, assume that the event is the first example described above. In this case, after S104, the control unit 15 acquires any environmental change that is considered to have caused a negative reaction from the child, including, but not limited to, whether the child stops crying, whether the driver or passenger mutes the speaker volume, or whether the driver or passenger stops playing the video. If a negative environmental change is acquired, the control unit 15 may update the child's preference information stored in the storage unit 14 to information indicating that the child does not like anime program A. On the other hand, if a negative environmental change is not acquired, the control unit 15 may update the child's preference information stored in the storage unit 14 to information indicating that the child likes anime program A.

[0055] Also, for example, in the above-described modified example, if the user's reaction is negative, the control unit 15 may further use the user's reaction to generate a prompt in S102 and execute S103 and S104 again.

[0056] For example, suppose the event is the first example described above, and a change in the environment that is considered negative has been acquired. In this case, the control unit 15 may generate a prompt in S102 by adding to the prompt generation information not only the child's state of crying, the child's age of 5, the child's gender of male, and the child's preference of loving anime programs, but also the fact that anime program A is not a favorite. Alternatively, the control unit 15 may generate a prompt that includes an instruction to output an alternative because anime program A is not a favorite.

[0057] Also, for example, in the above-described embodiment, each of the one or more events may include a priority, and if two or more of the one or more events occur simultaneously, the control unit 15 may generate a prompt further based on the respective priorities of the two or more events.

[0058] For example, suppose that the above-described first and second examples occur simultaneously, and the second example has a higher priority than the first example. In this case, the control unit 15 may prioritize the event of the second example and execute the process.

[0059] For example, the priority may be expressed in a numerical format using integers in any range, such as 5 to 1, in descending order of priority. Also, instead of numbers, the priority may be expressed in alphabetical rank format, such as S, A, B, C, D, in descending order of priority, or may be expressed as letters, such as "high," "medium," and "low." Also, the priority may be changeable.

[0060] Also, for example, an embodiment is possible in which a general-purpose computer functions as the information processing device 10 according to the above-described embodiment. Specifically, a program describing the processing content for realizing each function of the information processing device 10 according to the above-described embodiment is stored in the memory of the general-purpose computer, and the program is read and executed by a processor. Therefore, the present disclosure can also be realized as a program executable by a processor, or a non-transitory computer-readable medium storing the program.

[0061] Some embodiments of the present disclosure will be described below as examples, however, it should be noted that the embodiments of the present disclosure are not limited to these examples. [Appendix 1] A method executed by an information processing device, Detecting an occurrence of any of one or more events based on vehicle information obtained from the vehicle; obtaining user information and prompt generation information responsive to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; performing an action based on an output of the first language model in response to the prompt; A method comprising: [Appendix 2] 2. The method of claim 1, comprising: generating the prompt generation information in response to the detected event using a second language model stored in the information processing device; The method further comprises: [Appendix 3] 10. The method according to claim 1 or 2, The method, wherein the vehicle information includes an image of the user, a voice of the user, a state of the vehicle, and route information for the vehicle. [Appendix 4] 4. The method of any one of claims 1 to 3, comprising: The action is Playing specific music, Playing certain videos, and Providing route guidance to rest areas, A method comprising: [Appendix 5] 5. The method of any one of claims 1 to 4, comprising: Obtaining a reaction of the user to the performed action; updating the user information based on the user's response; The method further comprises: [Appendix 6] 6. The method of any one of claims 1 to 5, comprising: Obtaining a reaction of the user to the performed action; Further comprising: If the user's response is negative, the information processing device further uses the user's response to generate the prompt. [Appendix 7] 7. The method of any one of claims 1 to 6, comprising: each of the one or more events includes a priority; When two or more events among the one or more events occur simultaneously, the information processing device generates the prompt further based on respective priorities of the two or more events. [Appendix 8] An information processing device, Detecting an occurrence of one or more events based on vehicle information obtained from the vehicle; Obtaining user information and prompt generation information according to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; a control unit that performs an action based on an output of the first language model in response to the prompt; An information processing device comprising: [Appendix 9] 9. The information processing device according to claim 8, a storage unit for storing a second language model; Further provided with The control unit uses the second language model to create the prompt generation information according to the detected event. [Appendix 10] 10. The information processing device according to claim 8 or 9, An information processing device, wherein the vehicle information includes an image of the user, a voice of the user, a state of the vehicle, and route information of the vehicle. [Appendix 11] An information processing device according to any one of Supplementary Notes 8 to 10, The action is Playing specific music, Playing certain videos, and Providing route guidance to rest areas, An information processing device comprising: [Appendix 12] An information processing device according to any one of Supplementary Notes 8 to 11, The control unit Obtaining a reaction of the user to the performed action; An information processing device that updates the user information based on a reaction of the user. [Appendix 13] An information processing device according to any one of Supplementary Notes 8 to 12, The control unit Obtaining a reaction of the user to the performed action; If the user's reaction is negative, the information processing device further uses the user's reaction to generate the prompt for causing the first language model to output the action for the detected event. [Appendix 14] An information processing device according to any one of Supplementary Notes 8 to 13, each of the one or more events includes a priority; The control unit When two or more events out of the one or more events occur simultaneously, the information processing device generates the prompt further based on the respective priorities of the two or more events. [Appendix 15] A system including an information processing device and a language model server storing a first language model, The information processing device includes: Detecting an occurrence of one or more events based on vehicle information obtained from the vehicle; Obtaining user information and prompt generation information according to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; The language model server outputting the first language model in response to the prompt; The information processing device includes: The system performs an action based on the output. [Appendix 16] 16. The method of claim 15, The information processing device uses a second language model stored in the information processing device to create the prompt generation information in response to the detected event. [Appendix 17] 17. The system of claim 15 or 16, The system, wherein the vehicle information includes an image of the user, a voice of the user, a state of the vehicle, and route information of the vehicle. [Appendix 18] 18. The system of any one of claims 15 to 17, further comprising: The action is Playing specific music, Playing certain videos, and Providing route guidance to rest areas, Including, the system. [Appendix 19] 19. The system of any one of claims 15 to 18, further comprising: The information processing device includes: Obtaining a reaction of the user to the performed action; The system updates the user information based on the user's response. [Appendix 20] 20. The system of any one of claims 15 to 19, further comprising: The information processing device includes: Obtaining a reaction of the user to the performed action; If the user's response is negative, the system further uses the user's response to generate the prompt for causing the first language model to output the action for the detected event. [Explanation of symbols]

[0062] 1 System 10. Information processing equipment 11 Communications Department 12 Output section 13 Input section 14 Storage section 15 Control Unit 16 Sensor section 17 Photography Department 20 Language Model Server 30 Content Server 40 Network

Claims

1. A method executed by an information processing device, Detecting an occurrence of any of one or more events based on vehicle information obtained from the vehicle; obtaining user information and prompt generation information responsive to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; performing an action based on an output of the first language model in response to the prompt; A method comprising:

2. 10. The method of claim 1, generating the prompt generation information in response to the detected event using a second language model stored on the information processing device; The method further comprises:

3. 10. The method of claim 1, The method, wherein the vehicle information includes an image of the user, a voice of the user, a state of the vehicle, and route information for the vehicle.

4. 10. The method of claim 1, The action is Playing specific music, Playing certain videos, and Providing route guidance to rest areas, A method comprising:

5. 10. The method of claim 1, Obtaining a reaction of the user to the performed action; updating the user information based on the user's response; The method further comprises:

6. 10. The method of claim 1, Obtaining a reaction of the user to the performed action; Further comprising: If the user's response is negative, the information processing device further uses the user's response to generate the prompt.

7. 10. The method of claim 1, each of the one or more events includes a priority; When two or more events among the one or more events occur simultaneously, the information processing device generates the prompt further based on respective priorities of the two or more events.

8. An information processing device, Detecting the occurrence of any one or more events based on vehicle information acquired from the vehicle; Obtaining user information and prompt generation information according to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; a control unit that performs an action based on an output of the first language model in response to the prompt; An information processing device comprising:

9. 9. The information processing device according to claim 8, a storage unit for storing a second language model; Further provided with The control unit uses the second language model to create the prompt generation information according to the detected event.

10. 9. The information processing device according to claim 8, An information processing device, wherein the vehicle information includes an image of the user, a voice of the user, a state of the vehicle, and route information of the vehicle.

11. 9. The information processing device according to claim 8, The action is Playing specific music, Playing certain videos, and Providing route guidance to rest areas, An information processing device comprising:

12. 9. The information processing device according to claim 8, The control unit Obtaining a reaction of the user to the performed action; An information processing device that updates the user information based on a reaction of the user.

13. 9. The information processing device according to claim 8, The control unit Obtaining a reaction of the user to the performed action; If the user's reaction is negative, the information processing device further uses the user's reaction to generate the prompt for causing the first language model to output the action for the detected event.

14. 9. The information processing device according to claim 8, each of the one or more events includes a priority; The control unit When two or more events among the one or more events occur simultaneously, the information processing device generates the prompt further based on the respective priorities of the two or more events.

15. A system including an information processing device and a language model server storing a first language model, The information processing device includes: Detecting the occurrence of any one or more events based on vehicle information acquired from the vehicle; Obtaining user information and prompt generation information according to the detected event; generating a prompt for causing a first language model to output an action for the detected event using the acquired user information and the prompt generation information; inputting the prompt into the first language model; The language model server outputting the first language model in response to the prompt; The information processing device includes: The system performs an action based on the output.

16. 16. The method of claim 15, The information processing device uses a second language model stored in the information processing device to create the prompt generation information in response to the detected event.

17. 16. The system of claim 15, The system, wherein the vehicle information includes an image of the user, a voice of the user, a state of the vehicle, and route information of the vehicle.

18. 16. The system of claim 15, The action is Playing specific music, Playing certain videos, and Providing route guidance to rest areas, Including, the system.

19. 16. The system of claim 15, The information processing device includes: Obtaining a reaction of the user to the performed action; The system updates the user information based on the user's response.

20. 16. The system of claim 15, The information processing device includes: Obtaining a reaction of the user to the performed action; If the user's response is negative, the system further uses the user's response to generate the prompt for causing the first language model to output the action for the detected event.

Images