Navigation apparatus, navigation system, method for navigation, and program

Abstract

To easily set a route on the basis of an answer generated by a generative AI.SOLUTION: A navigation apparatus according to an embodiment includes a controller. The controller extracts location information including at least a place name or a facility name from an answer generated by a generative AI in response to a question of a user, collates the extracted location information with a map database, and sets a route in which the location information collated with the map database serves as a destination or a waypoint.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The disclosed embodiments relate to a navigation device, a navigation system, a navigation method, and a program. [Background technology]

[0002] Conventionally, techniques have been proposed that allow a user to easily set a destination in a navigation device.

[0003] For example, Patent Document 1 discloses a technology in which, when a user opens a facility's homepage on the Internet, a destination setting button is displayed on the page, and when the user operates this button, information about the facility is sent to a navigation device, which automatically sets the destination.

[0004] Furthermore, Patent Document 2 discloses a technology for estimating a destination desired by a user based on keywords extracted from the user's speech, and setting the estimated destination as a destination.

[0005] In recent years, so-called generative AI (Artificial Intelligence), which automatically generates answers to user questions, has become popular. Generative AI can automatically generate travel plans and other information desired by users. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-187482 [Patent Document 2] Japanese Patent Application Laid-Open No. 2001-289661 Summary of the Invention [Problem to be solved by the invention]

[0007] However, currently, there is no technology that can set routes, including destinations and stopovers, in a navigation device based on a travel plan generated by a generation AI. Therefore, users must sequentially input location information, such as place names and facility names, included in the travel plan generated by the generation AI into the navigation device.

[0008] One aspect of the embodiment has been made in consideration of the above, and aims to provide a navigation device, navigation system, navigation method, and program that can easily set a route based on answers generated by a generation AI. [Means for solving the problem]

[0009] A navigation device according to one aspect of the embodiment includes a controller. The controller extracts point information including at least a place name or a facility name from an answer generated by a generation AI in response to a user's question. The controller also compares the extracted point information with a map database. The controller also sets a route that uses the point information compared with the map database as a destination or a stopover. [Effects of the Invention]

[0010] According to one aspect of the embodiment, location information is extracted from the answer given by the generation AI to the user's question, and the location information is compared with a map database before a route is set using the extracted location information, so that the route can be set automatically from the answer given by the generation AI. Therefore, according to one aspect of the embodiment, a route can be set easily based on the answer given by the generation AI. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a navigation system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of the navigation device according to the embodiment. [Figure 3]FIG. 3 is a diagram showing a processing sequence according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the user's utterance content, the response sentence of the generation AI, and the response sentence display screen. [Figure 5] FIG. 5 is a diagram showing an example of the set route display screen. [Figure 6] FIG. 6 is a diagram showing a processing sequence according to the modified example. [Figure 7] FIG. 7 is an explanatory diagram of the processing content in the processing sequence according to the modified example. [Figure 8] FIG. 8 is a diagram showing an example of a template used to generate a follow-up question. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of a navigation device, a navigation system, a navigation method, and a program disclosed in the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below.

[0013] In the following description, the generation AI is assumed to be a document generation AI that generates a text answer to a text question. In the following description, the navigation method according to the embodiment is assumed to be executed by a controller 15 (see FIG. 2) included in the navigation device 10 according to the embodiment.

[0014] In the following description, the navigation device 10 according to the embodiment is an example of a car navigation device installed in a vehicle. The navigation device according to the embodiment may be a smartphone or the like capable of executing application software having a navigation function.

[0015] In the following description, the terms "predetermined" and "specific" can be read as "predetermined."

[0016] (Example of a navigation system configuration) 1 is a diagram showing an example of the configuration of a navigation system 1 according to an embodiment. As shown in FIG. 1, the navigation system 1 includes navigation devices 10-1, 10-2, . . . 10-n (n is a natural number equal to or greater than 1) and a generation AI server 100.

[0017] Each navigation device 10 and the generation AI server 100 are connected to each other so as to be able to communicate with each other via a network N, such as the Internet, a mobile phone network, or a C-V2X (Cellular Vehicle to Everything) communication network.

[0018] The navigation device 10 is a car navigation device mounted on a vehicle. The navigation device 10 includes a controller 15 (see FIG. 2). The controller 15 executes the navigation method according to the embodiment.

[0019] In the navigation method according to the embodiment, the controller 15 extracts location information including at least a place name or a facility name from an answer generated by the generation AI in response to a question from a user U (see FIG. 3). The question at this time is, for example, a question from the user U about a driving plan or a travel plan, such as "Tell me some recommended driving courses in Hyogo Prefecture."

[0020] In this embodiment, a "question" may be in any form that requests an answer from the generation AI, and includes, for example, a request for an answer from the generation AI by means of an instruction or command. Also, "question" may be read as "enquiry" or "inquiry."

[0021] The controller 15 receives such a question through speech by the user U, converts the speech content into a text question, and transmits it to the generation AI (the generation AI server 100, described later).Then, the controller 15 extracts location information including at least the place name or facility name from the answer generated by the generation AI in response to the question.

[0022] Next, the controller 15 compares the extracted location information with the map DB (Database) 14c (see FIG. 2) used by the navigation device 10 for its navigation function. This comparison is performed because the generation AI only generates a "plausible" answer sentence, and does not necessarily provide an answer that is in accordance with actual geographical relationships or laws and regulations. In the navigation method according to the embodiment, this comparison ensures that the location information is at least actually registered in the map DB 14c of the navigation device 10.

[0023] Then, the controller 15 selects the spot information that has been checked against the map DB 14c. This makes it possible to set a route using the spot information that actually exists in the map DB 14c. Then, the controller 15 sets a route that uses the selected spot information as a destination or a waypoint.

[0024] The generation AI server 100 is a server device that functions as a generation AI. The generation AI server 100 is realized as, for example, a cloud server. The cloud server may be a public cloud or a private cloud.

[0025] The generation AI server 100 functions as a generation AI that generates an answer to a question from the navigation device 10 and transmits it to the navigation device 10 by reading and operating a generation AI model (not shown) as part of a program.

[0026] A generative AI model is, for example, a large-scale language model trained to predict and output the next token from a string of input tokens (basic units of text to be processed). Examples of generative AI models include transfer-based models and RNN (Recurrent Neural Network)-based models.

[0027] Examples of transfer-based models include, but are not limited to, Generative Pre-trained Transformer (GPT) and Bidirectional Auto Regressive Dialogues (BARD). Examples of RNN-based models include, but are not limited to, Receptance Weighted Key Value (RWKV).

[0028] (Example of configuration of navigation device) Next, a configuration example of the navigation device 10 will be described. Fig. 2 is a diagram showing a configuration example of the navigation device 10 according to the embodiment. As shown in Fig. 2, the navigation device 10 has a communication unit 11, an HMI (Human Machine Interface) unit 12, a sensor unit 13, a storage unit 14, and a controller 15.

[0029] The communication unit 11 is realized by a network adapter, etc. The communication unit 11 is wirelessly connected to the network N, and transmits and receives information to and from the generation AI server 100 via the network N.

[0030] The HMI unit 12 is a component that provides interface components related to input and output to the user U who uses the navigation device 10. The HMI unit 12 corresponds to an example of an "interface unit." The HMI unit 12 includes an input interface that accepts input operations from the user U. The HMI unit 12 also includes an output interface that presents visual information and audio information to the user U.

[0031] 2, for example, the HMI unit 12 includes a touch panel display 12a, a microphone 12b, and a speaker 12c. The touch panel display 12a corresponds to the input interface and output interface described above.

[0032] The touch panel display 12a displays an answer statement display screen that allows the user U to select location information that the user U wants to use as a destination or a waypoint from, for example, an answer statement by the generation AI. A specific example of the answer statement display screen will be described later with reference to FIG. 4. The touch panel display 12a also displays a set route display screen that allows the user U to modify the set route, for example. A specific example of the set route display screen will be described later with reference to FIG. 5.

[0033] Note that each operation component operated by the user U may be provided in the HMI unit 12 as a hardware component, rather than being displayed on the touch panel display 12a as a software component.

[0034] The microphone 12b corresponds to an input interface for the voice uttered by the user U. The speaker 12c corresponds to an output interface for the navigation voice from the navigation device 10.

[0035] The sensor unit 13 is a group of various sensors mounted on the navigation device 10. The sensor unit 13 includes at least a GPS (Global Positioning System) sensor 13a. The GPS sensor 13a measures the GPS position of the vehicle.

[0036] In addition to the sensor unit 13, the navigation device 10 is also connected to an on-board sensor 5, which is a group of various sensors mounted on the vehicle. The on-board sensor 5 includes, for example, a G sensor, a vehicle speed sensor, an accelerator sensor, a brake sensor, etc. The on-board sensor 5 is connected to the navigation device 10 via an on-board network such as a CAN (Controller Area Network).

[0037] The storage unit 14 is realized by a storage device such as a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), etc. In the example of Fig. 2, the storage unit 14 stores a voice recognition model 14a, generated AI interface information 14b, a map DB 14c, and route setting information 14d.

[0038] The speech recognition model 14a is a learning model used for speech recognition of the speech of the user U input via the microphone 12b. The speech recognition model 14a is, for example, a Hidden Markov Model (HMM) or a Deep Neural Network (DNN) model. The speech recognition model 14a may be a composite model of the HMM and the DNN model.

[0039] The generation AI interface information 14b is information about an interface for exchanging questions and corresponding answers based on the user U's speech content converted into text using the speech recognition model 14a with the generation AI. The generation AI interface information 14b includes, for example, an API (Application Programming Interface) for the paired generation AI.

[0040] The map DB 14c is a database of map information used by the navigation device 10 in its navigation function. The map DB 14c includes a database of location information including at least place names or facility names. The route setting information 14d stores setting information for a route that is set based on location information selected by the user U.

[0041] The controller 15 corresponds to a so-called processor. The controller 15 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphical Processing Unit), or the like. The controller 15 executes a program according to an embodiment (not shown) stored in the storage unit 14, using RAM as a work area. The controller 15 can also be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0042] (Processing sequence according to the embodiment) The controller 15 executes information processing according to the processing sequences shown in Figure 3 and Figure 6. Next, the information processing according to these processing sequences will be explained in order. First, Figure 3 is a diagram showing the processing sequence according to the embodiment.

[0043] First, the user U performs an operation to start the AI ​​chat mode via the HMI unit 12 or the like (step S101). Then, a start command is input to the navigation device 10 (step S102), and the navigation device 10 transitions to the AI ​​chat mode (step S103). The AI ​​chat mode is a mode that allows exchange of questions and answers with the generation AI server 100.

[0044] Then, when the user U speaks a question (step S104), the spoken content is input to the navigation device 10 via the microphone 12b (step S105). The controller 15 of the navigation device 10 converts the input spoken content into text using the voice recognition model 14a, and generates a question (step S106).

[0045] Then, the controller 15 transmits the generated question to the generation AI server 100 (step S107). The generation AI server 100 receives the question and generates an answer corresponding to the question using the generation AI model (step S108), and transmits the answer to the navigation device 10 (step S109).

[0046] The controller 15 of the navigation device 10 receives this answer message and compares it with the map DB 14c to extract point information (step S110). Then, the controller 15 generates an answer message display screen based on the extracted point information (step S111) and presents it to the user U via the touch panel display 12a (step S112). The user U selects point information to be used as a destination or a waypoint via this answer message display screen (step S113).

[0047] To make the explanation above easier to understand, specific examples of the user U's utterance, the generation AI's response, and the response display screen are shown in Figure 4. Figure 4 shows an example of the user U's utterance, the generation AI's response, and the response display screen.

[0048] 4, assume that the user U utters, for example, "Tell me some recommended driving courses in Hyogo Prefecture" in step S104. In response, the generation AI server 100 generates a response sentence as shown in FIG. 4 in steps S108 and S109 and transmits it to the navigation device 10.

[0049] The controller 15 of the navigation device 10 receives this reply and compares it with the map DB 14c to extract location information that matches at least the place name or facility name. Here, it is assumed that the controller 15 has extracted the location information, for example, "Kobe City, Hyogo Prefecture" and "Himeji Castle" contained in the reply shown in Figure 4.

[0050] Then, the controller 15 generates an answer display screen based on the location information. Specifically, as shown in Fig. 4, the controller 15 generates an answer display screen including, for example, an answer display area R1 and a location information selection area R2, and presents it on the touch panel display 12a.

[0051] The answer sentence display area R1 displays the answer sentence received from the generation AI server 100, and also highlights each location information extracted from the answer sentence. Here, an example is shown in which each extracted location information is displayed large and highlighted with an underline.

[0052] In addition, in the location information selection area R2, each piece of extracted location information is displayed as, for example, a GUI (Graphical User Interface) so that the user U can select each piece of extracted location information. Here, for example, an example is shown in which "Kobe City, Hyogo Prefecture" is selected by the user U's touch operation and displayed in reverse video.

[0053] Note that multiple selections can be made for each location information. In other words, in the example of FIG. 4, if "Himeji Castle" is subsequently touched, "Himeji Castle" is also displayed in reverse video and selected along with "Kobe City, Hyogo Prefecture." If the selected location information is touched again, for example, the selection is cancelled. Then, if the user U touches the decision button B1, the selection is confirmed. This allows the user U to easily and arbitrarily select location information extracted from the answer of the generation AI. Note that the answer display screen shown in FIG. 4 is merely an example, and the layout, etc. may be arbitrary as long as it has the same function as the answer display screen of FIG. 4.

[0054] Returning to the explanation of Fig. 3, the point information selected by the user U in step S113 is input to the controller 15 of the navigation device 10 (step S114). The controller 15 uses its navigation function to set a route that uses the input point information as a destination or a waypoint (step S115).

[0055] Then, the controller 15 presents the user U with a set route display screen showing the details of the route set in step S115 (step S116). Here, the user U checks whether or not there are any corrections (step S117), and if there are any corrections (step S117, Yes), makes the route corrections through the set route display screen (step S118).

[0056] Here, Fig. 5 is a diagram showing an example of a set route display screen. In step S116, the controller 15 presents, for example, a set route display screen as shown in Fig. 5 on the touch panel display 12a. The set route display screen includes, for example, a set route display area R3 and a point information correction area R4.

[0057] The set route display area R3 displays the details of the route set by the controller 15 in step S115. Furthermore, the point information correction area R4 displays a GUI that allows the deletion or modification of each point information included in the set route. When the user U performs a modification operation, such as deleting or modifying, for each point information in this point information correction area R4 and touches the modification button B2, the route modification details are finalized. Note that the set route display screen shown in FIG. 5 is merely an example, and the layout, etc., may be arbitrary as long as it has the same functions as the set route display screen of FIG. 5.

[0058] Returning to the explanation of Fig. 3, the corrections confirmed by the user U in step S118 are input to the controller 15 of the navigation device 10 (step S119). The controller 15 sets a route that reflects the input corrections, and starts navigation (step S120). On the other hand, if no corrections are made in step S117 (step S117, No), the controller 15 starts navigation using the route set in step S115 (step S120).

[0059] (Processing sequence according to the modified example) Next, a processing sequence according to a modified example will be described. Fig. 6 is a diagram showing the processing sequence according to the modified example. Fig. 7 is an explanatory diagram of the processing content in the processing sequence according to the modified example. Fig. 8 is a diagram showing an example of a template used to generate a follow-up question.

[0060] Note that Fig. 6 corresponds to the processing sequence shown in Fig. 3, and therefore the following description will mainly focus on the differences from Fig. 3. As shown in Fig. 6, in the processing sequence according to the modified example, the navigation system 1 first executes steps S101 to S106 shown in Fig. 3.

[0061] Then, the controller 15 of the navigation device 10 that generated the question in step S106 checks this question against the map DB 104c and extracts the location information included in the question (step S201).

[0062] At this time, if the question contains a keyword indicating a specific location, such as "from home" or "from here," the controller 15 also extracts location information related to this specific location. For example, in the case of "from home," the controller 15 extracts location information related to the home registered in the navigation device 10. Furthermore, in the case of "from here," the controller 15 extracts location information related to the current location measured by the GPS sensor 13a.

[0063] Then, the controller 15 transmits the question to the generation AI server 100 (step S202). Upon receiving the question, the generation AI server 100 generates an answer corresponding to the question using the generation AI model (step S203) and transmits the answer to the navigation device 10 (step S204).

[0064] The controller 15 of the navigation device 10 receives the answer sentence and compares the answer sentence with the map DB 14c to extract location information (step S205). At this time, in the processing sequence according to the modified example, the controller 15 executes processing based on the location information extracted from the question sentence in step S201.

[0065] Specifically, as shown in Fig. 7, the controller 15 further narrows down the location information based on keywords included in the question sentence, for example, thereby making it possible to exclude unnecessary location information included in the answer sentence.

[0066] As an example, the controller 15 extracts point information within a predetermined distance from the specific point extracted from the question, as shown in Fig. 7. Specifically, the range of the map DB 14c against which point information is compared is narrowed based on keywords included in the question, or point information within a predetermined distance from the specific point is extracted from the point information compared with the map DB 14c. This makes it possible to exclude point information included in the answer that is too far from the specific point from selection candidates.

[0067] Furthermore, when there are multiple pieces of spot information that have been filtered and compared with the map DB 14c in this way, the controller 15 weights them, for example, according to the distance from the specific spot mentioned above, as shown in Fig. 7, and prioritizes them as selection candidates in descending order of the weighted score value. Specifically, a predetermined number of pieces of spot information are extracted as selection candidates in descending order of the score value, or spot information whose score value exceeds a predetermined reference value is extracted as selection candidates. This makes it easier for the user U to select spot information that is easy to get to from a specific spot.

[0068] Furthermore, the answer sentences generated by the generation AI are so-called "plausible" sentences (that appear to be written by a human) generated by a language model, and are not necessarily based on reality. Therefore, the controller 15, for example, determines the validity of the answer sentence as shown in FIG. 7, and if the answer sentence is invalid, asks the generation AI a question again. Specifically, the controller 15 determines that the answer sentence is invalid if, for example, the answer sentence contains location information that cannot be matched with the map DB 14c.

[0069] Furthermore, the controller 15 determines that the route is invalid if, for example, a valid route including the selected location information cannot be set. The case where a valid route cannot be set refers to, for example, a case where a route is set using location information selected by the user U, but the travel distance is too long, resulting in an unrealistic itinerary, or a case where a section subject to legal restrictions is included, resulting in a violation of the law.

[0070] If it is determined that the answer is invalid, the controller 15 generates a re-question requesting correction of the answer and sends it to the generation AI server 100. Requesting correction of the answer means, in other words, requesting additional information to fill in the invalid points.

[0071] When generating a follow-up question, the controller 15 generates the follow-up question using a fixed phrase such as that shown in FIG. 8. For example, if the controller 15 cannot match the location information included in the answer with the map DB 14c, the controller 15 uses fixed phrases such as "Please tell me the address of ***" or "*** is not in ** prefecture," as shown in FIG. 8. Furthermore, if the controller 15 cannot set a valid route, the controller 15 uses fixed phrases such as "Please make the distance within ** hours," or "Please avoid areas under legal restrictions." By generating a follow-up question using such fixed phrases and receiving a response from the generation AI server 100, it is possible to easily and automatically obtain more valid, i.e., more realistic, information.

[0072] Returning to the explanation of Fig. 6, after step S205, the controller 15 of the navigation device 10 determines whether or not the answer has the aforementioned validity (step S206). Here, if the answer text contains point information that cannot be collated with the map DB 14c, the controller 15 determines that the answer text has no validity. If the answer text has validity (step S206, Yes), the controller 15 executes steps S111 to S120 shown in Fig. 3.

[0073] If the query is not valid (step S206, No), the controller 15 generates a follow-up question regarding the additional information using a template (step S211). Then, the controller 15 transmits the follow-up question to the generation AI server 100 (step S212). Upon receiving the follow-up question, the generation AI server 100 generates an answer corresponding to the follow-up question using a generation AI model (step S213) and transmits the answer to the navigation device 10 (step S214).

[0074] The controller 15 of the navigation device 10 receives this reply message and links the additional information included in the reply message to the location information (step S215).Then, the controller 15 executes steps S111 to S120 shown in FIG.

[0075] Although not shown in FIG. 6, when determining the validity based on whether a valid route can be set, the controller 15 sets the route in step S115, and then determines the validity in step S206.

[0076] (Conclusion) As described above, the navigation device 10 according to the embodiment includes the controller 15. The controller 15 extracts spot information including at least a place name or a facility name from the answer generated by the generation AI in response to the question of the user U. The controller 15 also compares the extracted spot information with the map DB 14c. The controller 15 also sets a route that uses the spot information compared with the map DB 14c as a destination or a waypoint.

[0077] According to the navigation device 10 of the embodiment, point information required for route setting is extracted from the answer of the generation AI to the question of the user U, and the point information is collated with the map DB 14c, and then the route is set using this point information. This makes it possible to automatically set a route from the answer of the generation AI. Therefore, according to the navigation device 10 of the embodiment, a route can be easily set based on the answer generated by the generation AI.

[0078] In the above-described embodiment, an example was described in which the generation AI was a document generation AI. However, the generation AI may also be, for example, a voice generation AI that accepts a question by voice and returns a response by voice. In this case, the controller 15 uses the API of the generation AI to send the spoken voice of the question asked by the user U to the generation AI server 100. The generation AI server 100 returns a response to the question by voice to the navigation device 10, and the controller 15 of the navigation device 10 converts this response into text as a response sentence using the speech recognition model 14a. The controller 15 then extracts location information based on this response sentence.

[0079] Further advantages and modifications will readily occur to those skilled in the art. Therefore, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents. [Explanation of symbols]

[0080] 1. Navigation system 10 Navigation devices 11 Communications Department 12 HMI section 12a Touch panel display 12b Microphone 12c speaker 13 Sensor section 13a GPS sensor 14 Storage section 14a Speech Recognition Model 14b Generated AI interface information 14c Map DB 14d Route setting information 15 Controller 100 Generation AI Server N Network U User

Claims

1. Extracting location information including at least a place name or a facility name from the answer generated by the generation AI in response to the user's question; The extracted location information is compared with a map database; a controller that sets a route using the location information checked against the map database as a destination or a waypoint; A navigation device comprising:

2. an interface unit that presents the location information checked against the map database so that the user can select it; Equipped with The controller setting a route with the location information selected by the user via the interface unit as a destination or a stopover; The navigation device according to claim 1 .

3. The controller further narrowing down the location information based on keywords included in the user's question, and setting a route using the narrowed down location information as a destination or a stopover; The navigation device according to claim 1 .

4. The controller setting a route with the location information within a predetermined distance from the specific location indicated by the keyword as a destination or a stopover; The navigation device according to claim 3 .

5. The controller weighting the spot information checked against the map database according to the distance from the specific spot, and setting a route having a predetermined number of the spot information in descending order of the score value obtained by the weighting, or a route having the spot information with a score value equal to or greater than a predetermined value as a destination or a stopover; 5. The navigation device according to claim 4.

6. The controller If there is any point information that cannot be matched with the map database, or if a valid route including the selected point information cannot be set, a re-question is generated requesting correction of the answer and sent to the generation AI. The navigation device according to claim 1 .

7. A generating AI and a navigation device, The generated AI is When receiving a question from the user from the navigation device, generate an answer to the question and transmit it to the navigation device; The navigation device When the question is input by the user, the question is sent to the generation AI; receiving the answer to the question from the generating AI; extracting location information including at least a place name or a facility name from the response; The extracted location information is compared with a map database; setting a route with the location information checked against the map database as a destination or a stopover; Navigation system.

8. A navigation method executed by a navigation device, comprising: Extracting location information including at least a place name or a facility name from an answer generated by the generation AI in response to a user's question; comparing the extracted location information with a map database; setting a route with the location information checked against the map database as a destination or a waypoint; Navigation methods including:

9. Extracting location information including at least a place name or a facility name from an answer generated by the generation AI in response to a user's question; comparing the extracted location information with a map database; setting a route with the location information checked against the map database as a destination or a waypoint; A program that causes a computer to execute the following.

Images