Information processing system
The system addresses the challenge of generating accurate user responses by utilizing geographically dispersed data stores to determine suitable storage means, ensuring precise answers based on location and vehicle-specific data.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2024-12-25
- Publication Date
- 2026-07-07
Smart Images
Figure 2026113110000001_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the technical field of information processing systems.
Background Art
[0002] As a system of this kind, a system that acquires information related to a vehicle is known. For example, Patent Document 1 discloses a technique for acquiring traffic information, weather information, detailed weather information, and usage history information and creating a generation distribution map of vehicle users.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] A system that answers a user's question using a large language model (LLM) constructed by a large amount of data and deep learning technology may be mounted on a vehicle. However, the weather and traffic conditions vary depending on the area where the vehicle is traveling, and the vehicle state and driver characteristics also differ from vehicle to vehicle. Therefore, it is difficult to generate a highly accurate answer considering the above various characteristics with only a single common model.
[0005] This disclosure has been made in view of the above problems, and an object thereof is to provide an information processing system capable of outputting an appropriate answer to a question regarding a user.
Means for Solving the Problems
[0006] An information processing system according to one aspect of this disclosure comprises: a plurality of storage means that are geographically dispersed and collect and store information relating to at least the locations where they are located; a question information acquisition means for acquiring question information relating to a user; a determination means for determining a suitable storage means from among the plurality of storage means that is suitable for generating an answer to the question information; an extraction means for extracting generation information for generating the answer from the suitable storage means; a generation means for generating the answer based on the question information and the generation information; and an output means for outputting the answer to the user. [Brief explanation of the drawing]
[0007] [Figure 1] This is a block diagram showing the hardware configuration of the information processing system according to the embodiment. [Figure 2] This is a block diagram showing the functional configuration of the information processing system according to the embodiment. [Figure 3] This is a flowchart showing the operation flow of the information processing system according to the embodiment. [Modes for carrying out the invention]
[0008] The following describes an embodiment of the information processing system with reference to the drawings.
[0009] (Hardware configuration) First, the hardware configuration of the information processing system according to the embodiment will be described with reference to Figure 1. Figure 1 is a block diagram showing the hardware configuration of the information processing system according to the embodiment.
[0010] In Figure 1, the information processing system 1 according to this embodiment is configured to include an in-vehicle device 10 and a plurality of data stores 50. The in-vehicle device 10 is a device mounted on a vehicle. On the other hand, the data stores 50 are devices installed outside the vehicle. The in-vehicle device 10 and the data stores 50 are configured to communicate with each other via wireless communication.
[0011] The in-vehicle device 10 comprises a computing device 110, a storage device 120, a communication device 130, an input device 140, and an output device 150. The computing device 110, storage device 120, communication device 130, input device 140, and output device 150 are connected to each other via a data bus. All of the devices included in the in-vehicle device 10 described above may be mounted in the vehicle. However, some of the devices included in the in-vehicle device 10 may be mounted in the vehicle, while the remaining devices are installed outside the vehicle.
[0012] The arithmetic unit 110 is configured to perform various arithmetic processes in the in-vehicle device 10. The arithmetic unit 110 may have a processor. The arithmetic unit 110 may have a single processor or may have multiple processors. In other words, the arithmetic unit 110 may have one or more processors. The processor may be a multi-core processor. If the arithmetic unit 110 has a single processor that is a multi-core processor, then logically, the arithmetic unit 110 can be said to have multiple processors.
[0013] The processor in the arithmetic unit 110 may be at least one of the following: a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), and a TPU (Tensor Processing Unit).
[0014] The storage device 120 may be at least one of the following: RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, magneto-optical disk drive, SSD (Solid State Drive), and optical disk array. In other words, the storage device 120 may be implemented by a single device or by multiple devices.
[0015] The storage device 120 is capable of storing desired data. The storage device 120 may store the computer program CP that the arithmetic unit 110 will execute. The storage device 120 may temporarily store data that the arithmetic unit 110 will use temporarily when the arithmetic unit 110 is executing the computer program CP.
[0016] The computer program CP may be recorded on a computer-readable and non-temporary recording medium. In this case, the computer program CP may be stored in the storage device 120 by reading the recording medium using a recording medium reading device (not shown) provided by the in-vehicle device 10. At least one of the following may be used as the recording medium: an optical disc, a magnetic medium, a magneto-optical disc, a semiconductor memory, and any other medium capable of storing a program. The computer program CP may also be obtained from an external device (not shown) of the in-vehicle device 10 via a communication device 130. In other words, the computer program CP may be downloaded from an external device to the storage device 120 of the in-vehicle device 10.
[0017] The arithmetic unit 110 (for example, a processor) may execute the processing that the in-vehicle device 10 should perform together with the memory device 120 in which the computer program CP is stored (in other words, together with the memory device 120 and the computer program CP stored in the memory device 120). For example, by the arithmetic unit 110 executing the computer program CP, a logical functional block for executing the processing that the in-vehicle device 10 should perform may be realized within the arithmetic unit 110 (for example, within the processor).
[0018] The communication device 130 is configured to communicate with devices outside the in-vehicle device 10. The communication device 130 may use wired communication or wireless communication.
[0019] The input device 140 is a device capable of receiving input of information to the in-vehicle device 10 from the outside. The input device 140 may include an operating device (e.g., a keyboard, a mouse, a touch panel, etc.) that can be operated by the user of the in-vehicle device 10. The input device 140 may include a recording medium reader that can read information recorded on a detachable recording medium for the in-vehicle device 10, such as a USB (Universal Serial Bus) memory. When information is input to the in-vehicle device 10 via the communication device 130 (in other words, when the in-vehicle device 10 acquires information via the communication device 130), the communication device 130 may function as an input device.
[0020] The output device 150 is a device capable of outputting information to the outside of the in-vehicle device 10. The output device 150 may have a display device capable of outputting visual information such as characters and images as the above information. The output device 150 may also have a speaker capable of outputting auditory information such as sound as the above information. The output device 150 may be configured to output the above information (e.g., control information of other devices, etc.) to other devices. The output device 150 may be able to output information to a detachable recording medium for the in-vehicle device 10, such as a USB memory. When the in-vehicle device 10 outputs information via the communication device 130, the communication device 130 may function as an output device.
[0021] The data store 50 stores various kinds of knowledge (data), and exchanges data by communicating with the above-described in-vehicle device 10. Here, for the sake of convenience of explanation, three data stores 50a, 50b, and 50c are illustrated, but the number of data stores is not particularly limited. The data stores 50 are geographically distributed. For example, the data stores 50 may be arranged in units of prefectures, municipalities, or predetermined areas. More specifically, the data store 50 may be an edge terminal installed at base stations, gas stations, charging stations, etc. in various places. Also, recording devices mounted on each of a plurality of vehicles may function as the data store 50.
[0022] The data store 50 has common knowledge and unique knowledge. The common knowledge is knowledge shared among multiple data stores 50. Therefore, the shared knowledge is knowledge not related to the location where the data stores 50 are located. The shared knowledge is shared, for example, by the data stores 50 communicating directly or indirectly with each other. The unique knowledge is knowledge that each data store 50 uniquely has and is knowledge related to the location where the data store 50 is located. Specifically, the unique knowledge may be information specialized for the area where the data store is located (for example, information regarding the weather, traffic conditions, stores, etc. in the area). The data store 50 may have a function of automatically collecting unique knowledge. Note that among the data stores 50, there may be those that have only common knowledge. Also, among the data stores 50, there may be those that have only unique knowledge.
[0023] <Functional Configuration> Next, with reference to FIG. 2, the functional configuration of the information processing system 1 according to the embodiment will be described. FIG. 2 is a block diagram showing the functional configuration of the information processing system according to the embodiment.
[0024] In FIG. 2, the information processing system 1 is configured as a system that outputs an answer to a question regarding a user who uses a vehicle. The in-vehicle device 10 in the information processing system 1 includes, as components for realizing its functions, a question information acquisition unit 210, a vehicle information acquisition unit 220, a data store determination unit 230, a generation information extraction unit 240, an answer generation unit 250, and an answer output unit 260. Note that each of the question information acquisition unit 210, the vehicle information acquisition unit 220, the data store determination unit 230, the generation information extraction unit 240, the answer generation unit 250, and the answer output unit 260 may be a processing block realized by the arithmetic device 110 described above.
[0025] The question information acquisition unit 210 is configured to acquire question information about the user. The question information about the user may be, for example, information about a question entered by the user. In this case, the question information acquisition unit 210 may acquire the question information based on the user's input operation (for example, the operation of entering the text of the question). Alternatively, the question information acquisition unit 210 may acquire the question information by recognizing the voice spoken by the user. Furthermore, the question information about the user may also be instruction information entered from various devices when providing push-type suggestions to the user. For example, the question information may be instruction information for suggesting a driving route to the user.
[0026] The vehicle information acquisition unit 220 is configured to acquire vehicle information stored in the vehicle used by the user. The vehicle information may include at least one of the following: location information relating to the vehicle's position, status information relating to the vehicle's condition, and driving specificity information relating to the driving characteristics of the vehicle's driver. The vehicle information acquisition unit 220 may also acquire vehicle information in real time from various sensors and the like installed in the vehicle.
[0027] The data store determination unit 230 is configured to determine a data store 50 suitable for generating an answer (hereinafter referred to as the "suitable data store") based on the question information acquired by the question information acquisition unit 210. Specifically, the data store determination unit 230 determines from among multiple data stores 50 which data store information suitable for generating an answer to the question information. For example, if the question information requests region-specific information such as "information regarding road closures due to snowfall," the data store determination unit 230 may determine a data store 50 that stores the corresponding region information as proprietary knowledge as the suitable data store. The data store determination unit 230 may determine multiple data stores 50 as suitable data stores.
[0028] Furthermore, if vehicle information has been acquired by the vehicle information acquisition unit 220, the data store determination unit 230 may determine a suitable data store using the vehicle information in addition to the query information. For example, if the vehicle information indicates that the vehicle's fuel level is low, the data store determination unit 230 may determine the data store 50, which stores information about nearby gas stations as proprietary knowledge, as the suitable data store.
[0029] The generation information extraction unit 240 is configured to query the suitable data stores determined by the data store determination unit 230 and extract information (hereinafter referred to as "generation information") for generating answers to the query information. If multiple suitable data stores have been determined, the generation information extraction unit 240 may extract the generation information by querying multiple data stores 50.
[0030] The answer generation unit 250 is configured to generate answers to question information using the generation information extracted by the generation information extraction unit 240. The answer generation unit 250 may generate answers using, for example, a pre-machine-trained model. This model may take the question information and generation information as input and output an answer. The model generated by the answer generation unit 250 may be, for example, a large-scale language model (LLM).
[0031] The answer output unit 260 is configured to output answers to the question information generated by the answer generation unit 250. The answer output unit 260 may output the answers via the output device 150. For example, the answer output unit 260 may output messages using a display or speaker provided in the vehicle.
[0032] (Flow of operations) Next, the operation flow of the information processing system 1 according to the embodiment will be described with reference to Figure 3. Figure 3 is a flowchart showing the operation flow of the information processing system according to the embodiment.
[0033] As shown in Figure 3, when the operation of the information processing system 1 according to the embodiment begins, the first question information acquisition unit 210 acquires question information about the user (step S101). The vehicle information acquisition unit 220 then acquires vehicle information from the vehicle used by the user (step S102).
[0034] Next, the data store determination unit 230 determines a suitable data store based on the question information obtained by the question information acquisition unit 210 and the vehicle information obtained by the vehicle information acquisition unit 220 (step S103). Then, the generation information extraction unit 240 queries the suitable data store determined by the data store determination unit 230 and extracts generation information to generate an answer to the question information (step S104).
[0035] Next, the answer generation unit 250 generates an answer to the question information based on the question information acquired by the question information acquisition unit 210 and the generation information extracted by the generation information extraction unit 240 (step S105). Then, the answer output unit 260 outputs the answer generated by the answer generation unit 250 to the user (step S106).
[0036] (Technical effects) Next, the technical effects obtained by the information processing system 1 according to this embodiment will be described.
[0037] As explained in Figures 1 to 3, in the information processing system 1 according to this embodiment, a suitable data store for generating answers to question information is determined from among multiple data stores 50. In this way, highly accurate answers to questions about the user can be generated and output.
[0038] In particular, when generating responses to vehicle users, the information required may vary depending on where the vehicle is traveling. For example, information regarding weather and traffic conditions requires the use of region-specific information. In this embodiment, however, a data store 50 is selected as the appropriate data store from among multiple geographically dispersed data stores 50, according to the question information. This makes it possible to generate appropriate responses even if the question information requires information specific to the region where the vehicle is traveling.
[0039] This disclosure is not limited to the embodiments described above and may be modified as appropriate without contradicting the gist or idea of the invention as can be inferred from the claims and the specification as a whole. Information processing systems with such modifications are also included within the technical scope of the present invention. [Explanation of Symbols]
[0040] 1…Information processing system, 10…In-vehicle device, 50…Data store, 110…Calculation unit, 120…Storage device, 130…Communication device, 140…Input device, 150…Output device, 210…Question information acquisition unit, 220…Vehicle information acquisition unit, 230…Data store determination unit, 240…Information extraction unit for generation, 250…Answer generation unit, 260…Answer output unit
Claims
1. Multiple storage means that are geographically dispersed and collect and store information related to at least the locations where they are located, A means for obtaining question information about a user, A determination means for determining a suitable storage means from among the plurality of storage means that is suitable for generating an answer to the question information, An extraction means for extracting generation information for generating the answer from the aforementioned suit storage means, A generation means for generating the answer based on the question information and the generation information, Output means for outputting the aforementioned answer to the user, An information processing system equipped with the following features.
2. The system further includes a means for acquiring vehicle information stored in the vehicle used by the user, The determination means determines the suitability storage means based on the question information and the vehicle information. The information processing system according to claim 1.
3. The vehicle information includes at least one of the following: location information relating to the vehicle's position, state information relating to the vehicle's condition, and driving characteristics information relating to the driving characteristics of the vehicle's driver. The information processing system according to claim 2.
4. The aforementioned multiple storage means store both unique knowledge, which is information related to the location where they are placed, and common knowledge, which is not related to the location where they are placed. The aforementioned common knowledge is shared among the multiple storage means. The information processing system according to any one of claims 1 to 4.
5. The generation means generates the answer by inputting the question information and the generation information into a large-scale language model. The information processing system according to any one of claims 1 to 3.