Guide device

Abstract

This prevents conflicts with information provided by other passengers. [Solution] The guidance device 10 outputs guidance information along the route explored by the guidance unit 14. At this time, the keyword analysis unit 12 acquires spoken audio information and extracts keywords related to guidance, and the guidance voice control unit 13 acquires the analysis results of the spoken audio information containing the keywords related to guidance extracted by the keyword analysis unit 12. Then, if the guidance voice control unit 13 determines that the content indicated by the spoken audio information corresponds to guidance, it suppresses the output of guidance information from the guidance unit 14.

Description

【Technical Field】 【0001】 The present invention relates to a guiding device provided with a guiding unit that outputs guiding information along a searched route. to. 【Background Art】 【0002】 A guiding device such as a car navigation device searches for a route to a preset destination and guides along the searched route by voice or the like. 【0003】 Patent Document 1 describes the following invention for the purpose of providing an easy-to-understand guide like a passenger to a driver. The invention described in Patent Document 1 calculates a driving situation feature amount at the time of guidance by a driving situation feature amount calculation means from the guidance history of a guidance history storage means in which a passenger has guided a driver, and classifies the guidance into a classification in which the driving situation feature amount for the guidance satisfies a condition by a guidance classification means. Then, the variable part of the utterance content of the driving situation feature amount is replaced with a variable part symbol, the utterance content with the highest frequency for each classification is selected by an utterance content selection means, and stored in a storage means as a guidance rule. 【Prior Art Documents】 【Patent Documents】 【0004】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2010-190773 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0005】 Patent Document 1 describes a system that provides easy-to-understand guidance, similar to that of a passenger. However, there are cases where the passenger provides guidance due to their familiarity with the area being driven in. In such cases, if the guidance system is also providing guidance, it may conflict with the passenger's guidance and potentially confuse the driver. Conventionally, to resolve such conflicts, it was necessary to either lower the volume of the guidance system or temporarily pause the guidance. 【0006】 One example of a problem that this invention aims to solve is preventing conflicts with guidance from passengers or other users. [Means for solving the problem] 【0007】 To solve the above problems, the invention described in claim 1 is characterized by comprising: a guidance unit that outputs guidance information along a searched route; a voice detection unit that acquires spoken voice information and detects keywords related to guidance; an analysis result acquisition unit that acquires the analysis results of the spoken voice information including the keywords related to guidance detected by the voice detection unit; and a guidance voice control unit that, with respect to the analysis results, suppresses the output of the guidance information from the guidance unit if the content indicated by the spoken voice information corresponds to route guidance spoken by a passenger in the vehicle. 【0008】 The invention described in claim 10 is a guidance method performed by a guidance device equipped with a guidance unit that outputs guidance information along a searched route, characterized in that it includes: a voice detection step of acquiring spoken voice information and detecting keywords related to guidance; an analysis result acquisition step of acquiring the analysis result of the spoken voice information including the keywords related to guidance detected in the voice detection step; and a guidance voice control step of suppressing the output of the guidance information from the guidance unit if the content indicated by the spoken voice information corresponds to route guidance spoken by a passenger in the vehicle with respect to the analysis result acquired in the analysis result acquisition step. 【0009】 The invention described in claim 11 is characterized in that the guidance method described in claim 10 is executed by a computer as a guidance program. 【0010】 The invention described in claim 12 is characterized in that the guidance program described in claim 11 is stored in a storage medium that can be read by a computer. [Brief explanation of the drawing] 【0011】 [Figure 1] This is a schematic diagram of a system having a guide device according to one embodiment of the present invention. [Figure 2] These are examples of words related to places, actions, and warnings. [Figure 3] This is a flowchart of the process for switching to passenger guidance mode. [Figure 4] This is a flowchart for the operation to terminate the passenger guidance mode (guidance). [Figure 5] This is a flowchart showing the procedure for ending the passenger guidance mode (warning). [Modes for carrying out the invention] 【0012】 The following describes a guidance device according to one embodiment of the present invention. In the guidance device according to one embodiment of the present invention, the guidance unit outputs guidance information along the searched route. At this time, the voice detection unit acquires spoken voice information and detects keywords related to guidance, and the analysis result acquisition unit acquires the analysis result of the spoken voice information that includes the guidance keywords detected by the voice detection unit. Then, if the guidance voice control unit determines that the content indicated by the spoken voice information corresponds to guidance, it suppresses the output of the guidance information from the guidance unit. In this way, guidance from passengers can be detected, and thus, conflicts with guidance from passengers can be prevented. 【0013】 Furthermore, the guidance voice control unit may identify guidance locations included in the spoken voice information based on the acquired analysis results, and suppress the output of guidance information up to the identified guidance locations. By doing so, the output of guidance information up to the guidance locations can be reliably suppressed. 【0014】 Furthermore, the voice guidance control unit may release the suppression of guidance information once the guidance point has been passed. In this way, the output of guidance information can be suppressed only for locations where the passenger wishes to receive guidance. 【0015】 Furthermore, the system may include a map information acquisition unit to acquire map information, and the guidance voice control unit may identify guidance locations based on the map information. By doing so, it becomes possible to identify guidance locations using intersection names and facility names (POI (Point of Interest) information, etc.) included in the map information, thereby enabling more accurate identification of guidance locations. 【0016】 Furthermore, if the spoken audio information is a combination of words related to location and words related to action, the analysis result acquisition unit may acquire an analysis result indicating that the content indicated by the spoken audio information corresponds to guidance. By doing so, guidance that combines location and action, such as "Turn right at the next intersection," can be detected. 【0017】 Furthermore, the voice detection unit also detects keywords related to warnings, and the acquisition unit acquires the analysis results of the spoken voice information that includes the warning keywords. The guidance voice control unit may also suppress the output of guidance information from the guidance unit if the voice analysis results acquired by the analysis result acquisition unit indicate that the content of the spoken voice information corresponds to a warning. In this way, if a passenger makes a warning such as "there are many people suddenly running out," this can be detected and the output of guidance information can be suppressed to prevent conflicts. 【0018】 Furthermore, if the spoken audio information combines words related to location and words that provide a warning, the analysis result acquisition unit may acquire an analysis result indicating that the content of the spoken audio information corresponds to a warning. In this way, it is possible to detect warnings that combine location and warning, such as "There are many pedestrians crossing at the next intersection." 【0019】 In addition, the guidance method according to an embodiment of the present invention acquires uttered voice information in a voice detection step, detects keywords related to guidance, and acquires an analysis result of the uttered voice information including the keywords related to guidance detected in the voice detection step in an analysis result acquisition step. Then, in a guidance voice control step, when the result of voice analysis indicates that the content indicated by the uttered voice information corresponds to guidance, the output of the guidance information from the guidance unit is suppressed. By doing so, it is possible to detect the guidance of a co-rider, and thus it is possible to prevent conflicts with the guidance of the co-rider or the like. 【0020】 In addition, the above-described guidance method may be executed by a computer as a guidance program. By doing so, it is possible to detect the guidance of a co-rider using a computer, and thus it is possible to prevent conflicts with the guidance of the co-rider or the like. 【0021】 In addition, the above-described guidance program may be stored in a computer-readable storage medium. By doing so, the program can be distributed not only when incorporated into a device but also as a single entity, and version updates and the like can be easily performed. 【Example】 【0022】 A guidance device according to an embodiment of the present invention will be described with reference to FIGS. 1 to 9. FIG. 1 is a schematic configuration diagram of a system including the guidance device according to the present embodiment. 【0023】 The system shown in FIG. 1 includes a guidance device 10 and a server device 20. The guidance device 10 is provided inside a vehicle such as an automobile. The guidance device 10 may be, for example, a car navigation device, or may be a device that can be taken out of the vehicle, such as a smartphone or a tablet terminal. 【0024】 As shown in FIG. 1, the guidance device 10 includes a voice input unit 11, a keyword analysis unit 12, a guidance voice control unit 13, a guidance unit 14, and a voice output unit 15. 【0025】 The voice input unit 11 receives voices spoken inside the vehicle. The voice input unit 11 consists of a microphone and the like. It is preferable to install the microphone in a position where it can capture the voices of not only the driver but also the passengers. For this reason, the microphone may be installed in multiple locations inside the vehicle, not just one. 【0026】 The keyword analysis unit 12 acquires spoken audio information output from the voice input unit 11 via the guidance voice control unit 13 and extracts (detects) keywords related to guidance or warnings from the spoken audio information. In other words, the keyword analysis unit 12 functions as a voice detection unit that acquires spoken audio information and detects keywords related to guidance. 【0027】 The keyword analysis unit 12 has a database of keywords related to guidance or warnings. Examples of keywords related to guidance or warnings include general guidance words such as "the traffic light there" and "the next intersection," as well as names of facilities around the current location, action instructions such as "turn right," "turn right," and "continue," and warnings such as "suddenly appearing" and "difficult to see." The speech recognition and natural language processing technologies used in the keyword analysis unit 12 and the speech analysis unit 21 (described later) can be the same well-known technologies used in so-called smart speakers and AI speakers. 【0028】 The guidance voice control unit 13 acquires utterance voice information input from the voice input unit 11 and outputs the utterance voice information to the keyword analysis unit 12. If the keyword analysis unit 12 determines that a keyword related to guidance or a warning has been uttered, the guidance voice control unit 13 outputs the utterance voice information to the server device 20. The guidance voice control unit 13 then receives the result of the voice analysis from the server device 20, and if the result is "guidance" or "warning", it switches to passenger guidance mode and causes the guidance unit 14 to suppress the output of voice related to guidance or warnings. In other words, the guidance voice control unit 13 functions as an analysis result acquisition unit that acquires the analysis result of utterance voice information containing a keyword related to guidance detected by the voice detection unit, and as a guidance voice control unit that suppresses the output of guidance information from the guidance unit if the result of the voice analysis acquired by the analysis result acquisition unit indicates that the content of the utterance voice information corresponds to guidance. 【0029】 Furthermore, after passing a relevant location such as an intersection included in the spoken voice information, the guidance voice control unit 13 asks the driver whether they wish to continue the passenger guidance mode if the passenger guidance continues. If the driver agrees, the passenger guidance mode is maintained; if the driver disagrees or there is no further speaking, the passenger guidance mode is terminated. In other words, the suppression of guidance information is released. 【0030】 As is well known, the guidance unit 14 searches for a route to the destination and generates information (guidance information) to guide the driver, etc., along the searched route, and outputs it from the voice output unit 15, etc. In addition, when the guidance voice control unit 13 switches to passenger guidance mode, the guidance unit 14 suppresses the output of voices related to guidance and warnings. 【0031】 The audio output unit 15 outputs audio related to the guidance information generated by the guidance unit. The audio output unit 15 also outputs audio from the guidance audio control unit 13 asking whether the passenger guidance mode should be continued. The audio output unit 15 is composed of a speaker, etc. This speaker is, of course, installed in the vehicle. 【0032】 The server device 20 is a well-known server computer and is capable of communicating with the guidance device 10 via a network N such as the Internet. The server device 20 includes a voice analysis unit 21 and map information 22. 【0033】 The voice analysis unit 21 analyzes the spoken voice information transmitted from the guidance voice control unit 13. The voice analysis unit 21 determines from the context whether the content of the spoken voice information is "guidance," "warning," or "other." It then returns (transmits) the classification result to the guidance voice control unit 13. 【0034】 In determining whether a voice is "guidance," "warning," or "other" in the voice analysis unit 21, if it contains words related to a location and words related to an action, it is determined to be "guidance." If it contains words related to a location and words that draw attention, it is determined to be "warning." If it does not fall under either "guidance" or "warning," it is determined to be "other." 【0035】 Here, examples of words related to location, words related to action, and words that draw attention are shown in the table in Figure 2. Of course, the words are not limited to those listed in Figure 2. 【0036】 Furthermore, when determining location-related words, the voice analysis unit 21 refers to the map information 22 and compares it with place names, POI information, etc., around the current location. If a match is found, it determines that the word is location-related. Also, if it is determined to be "guidance" or "warning," it transmits the result of this comparison with the map information 22 along with the determination result to the guidance voice control unit 13. This comparison result may include place names, intersection names, facility names, or latitude and longitude of the location that matches the map information 22. These locations that match the map information 22 are the locations (instructed locations) that the passenger has indicated during guidance. By receiving this information about the instruction locations, the guidance voice control unit 13 can identify the guidance locations included in the spoken voice information. 【0037】 Map information 22 is map information possessed by navigation devices, etc., and includes place names, intersection names, facility names, etc. This map information 22 also includes so-called POI information. 【0038】 Next, the operation (guidance method) of the guidance device 10 with the above configuration will be explained with reference to the flowcharts in Figures 3 to 5. Note that the flowcharts in Figures 3 to 5 can be configured as a guidance program to be executed on a computer equipped with a CPU, etc. 【0039】 Figure 3 is a flowchart of the operation to transition to passenger guidance mode. First, the keyword analysis unit 12 acquires the spoken voice information input from the voice input unit 11 via the guidance voice control unit 13 and performs keyword analysis (step S11). 【0040】 The keyword analysis unit 12 determines whether keywords related to guidance or warnings have been extracted as a result of the keyword analysis (step S12). If no keywords related to guidance or warnings are extracted (step S12; NO), the system returns to step S11, assuming that the utterance is not guidance from a passenger or the like. 【0041】 On the other hand, if keywords related to guidance or warnings are extracted (step S12; YES), the guidance voice control unit 13 transmits the spoken voice information to the server device 20, where the voice analysis unit 21 performs voice analysis (step S13). As described above, the voice analysis unit 21 outputs either "guidance," "warning," or "other" as the result of the voice analysis to the guidance voice control unit 13. At this time, as described above, the place names of locations that match when compared with the map information 22 are also output. 【0042】 Next, the guidance voice control unit 13 determines whether the result of the received voice analysis is "guidance" (step S14). If the result of the voice analysis is "guidance" (step S14; YES), the guidance voice control unit 13 switches to passenger guidance mode (guidance) (step S15). On the other hand, if the result of the voice analysis is not "guidance" (step S14; NO), the guidance voice control unit 13 does not switch to passenger guidance mode (guidance) and proceeds to step S16. In passenger guidance mode (guidance), the voice output of the guidance unit 14 related to route guidance is suppressed. 【0043】 Next, the guidance voice control unit 13 determines whether the result of the received voice analysis is a "warning" (step S16). If the result of the voice analysis is a "warning" (step S16; YES), the guidance voice control unit 13 switches to passenger guidance mode (warning) (step S17). On the other hand, if the result of the voice analysis is not a "warning" (step S16; NO), the guidance voice control unit 13 does not switch to passenger guidance mode (warning) and proceeds to step S18. In passenger guidance mode (warning), the voice output of the guidance unit 14 related to warnings at specified locations is suppressed. 【0044】 Next, the guidance voice control unit 13 determines whether the operation of the guidance device 10 has ended, such as turning off the power or terminating the application that executes this flowchart (step S18). If the operation has ended (step S18; YES), this flowchart is terminated; otherwise, the process returns to step S11. 【0045】 Note that the passenger guidance mode (guidance) and the passenger guidance mode (warning) are not mutually exclusive, so it is possible to be in both passenger guidance mode (guidance) and passenger guidance mode (warning) simultaneously. For example, if a passenger is already in passenger guidance mode (guidance) and says something like "The next curve has poor visibility," then both passenger guidance mode (guidance) and passenger guidance mode (warning) will be activated. 【0046】 Furthermore, in the flowchart of Figure 3, if the result of the voice analysis is "Other," neither passenger guidance mode (guidance) nor passenger guidance mode (warning) will be activated, and step S18 will be executed. 【0047】 As is clear from the above explanation, step S11 functions as a voice detection process, step S13 as an analysis result acquisition process, and step S15 as a guidance voice control process. 【0048】 Figure 4 is a flowchart of the operation to terminate the passenger guidance mode (guidance). First, the guidance voice control unit 13 determines whether the system is currently in passenger guidance mode (guidance) (step S21). If the system is not currently in passenger guidance mode (guidance) (step S21; NO), step S21 is repeated. 【0049】 On the other hand, if the system is currently in passenger guidance mode (guidance) (step S21; YES), the guidance voice control unit 13 determines whether the indicated location has been passed (step S22). The passing of the indicated location can be determined by comparing the map information (not shown) held by the guidance device 10 with the current location, based on information such as the location that matches the map information 22 received from the voice analysis unit 21 (server device 20). 【0050】 If the guidance voice control unit 13 determines that the vehicle will not pass the indicated location (step S22; NO), it repeats step S22 and waits until the vehicle passes the indicated location. In other words, it continues the passenger guidance mode until the vehicle passes the indicated location. Specifically, the guidance voice control unit 13 identifies the indicated location (guidance point) included in the spoken voice information based on the acquired analysis results and suppresses the output of guidance information up to the identified indicated location (guidance point). 【0051】 On the other hand, if it is determined that the indicated location has been passed (step S22; YES), the guidance voice control unit 13 determines whether it has heard the utterance "end" (step S23). Users of the guidance device 10 are informed in advance through the instruction manual and guidance voice that the passenger guidance mode ends when the utterance "end" is heard. Therefore, the guidance voice control unit 13 can end the passenger guidance mode by determining whether it has heard the utterance "end". The utterance "end" can be heard by analyzing the utterance voice information input from the voice input unit 11 in the keyword analysis unit 12, similar to keyword analysis. 【0052】 If the guidance voice control unit 13 hears the utterance "end" (step S23; YES), it terminates the passenger guidance mode (guidance) (step S26). 【0053】 On the other hand, if the utterance "end" is not heard (step S23; NO), the guidance voice control unit 13 determines whether the utterance is continuing (step S24). In other words, if the guidance by the passenger is continuing, the passenger guidance mode (guidance) is continued; otherwise, the passenger guidance mode (guidance) is terminated. Note that the continuation of the utterance may also be determined by the detection time of silence (no utterance). 【0054】 If the voice guidance control unit 13 does not continue speaking (step S24; NO), it terminates the passenger guidance mode (guidance) (step S26). 【0055】 On the other hand, if the speech continues (step S24; YES), the guidance voice control unit 13 asks the driver or other person whether they wish to continue the passenger guidance mode (guidance) (step S25). For example, the guidance voice control unit 13 outputs a voice message such as "Do you want to continue the passenger guidance?" from the voice output unit 15. The answer should be, for example, "yes" or "no". 【0056】 If the guidance voice control unit 13 determines, as a result of the inquiry, that it is "yes" to continuing the passenger guidance mode (guidance) (step S25; YES), it returns to step S21 and re-determines whether to terminate. On the other hand, if it determines, "no" to continuing the passenger guidance mode (guidance), it terminates the passenger guidance mode (guidance) (step S26). Note that the answer to the inquiry may come from a passenger, not just the driver. 【0057】 In step S26, when the passenger guidance mode (guidance) ends, the suppression of the output of guidance voices, etc. is released, and the output of guidance voices, etc. from the guidance unit 14 resumes. If, as a result of the passenger's guidance, the vehicle ends up traveling on a different route than the one searched by the guidance unit 14, the vehicle will automatically reroute. 【0058】 Furthermore, in the flowchart of Figure 4, the end of the passenger guidance mode (guidance) was detected by three decisions in steps S23 to S25, but it may be done with just one or two of these decisions. 【0059】 Furthermore, steps S23 to S25 are executed when it is determined in step S22 that the indicated location has been passed. In other words, the guidance voice control unit 13 releases the suppression of guidance information when the indicated location (guidance point) has been passed. 【0060】 Figure 5 is a flowchart of the operation to terminate the passenger guidance mode (warning). In the case of passenger guidance mode (warning), it consists only of steps S21, S22, and S26 in Figure 4. In Figure 4, steps S21A and S26A are written, but this is because the passenger guidance mode has been changed from (guidance) to (warning). The operation is substantially the same. 【0061】 In Figure 5, in passenger guidance mode (warning), the guidance (warning) is directed to a specific point, and it is considered that the mode may be terminated once the warning point (indicated location) is passed. Therefore, the determination steps S23 to S25 in Figure 4 are omitted. 【0062】 In addition, even in passenger guidance mode (warning), the system may be terminated by hearing "end" as in step S23 of Figure 4. Furthermore, the passenger guidance mode (guidance) may be represented as a flowchart as shown in Figure 5. 【0063】 In this embodiment, the guidance device 10 outputs guidance information along the route explored by the guidance unit 14. At this time, the keyword analysis unit 12 acquires spoken voice information and extracts keywords related to guidance, and the guidance voice control unit 13 acquires the analysis results of the spoken voice information containing the keywords related to guidance extracted by the keyword analysis unit 12. Then, if the guidance voice control unit 13 determines that the content indicated by the spoken voice information corresponds to guidance, it suppresses the output of guidance information from the guidance unit 14. In this way, guidance from passengers can be detected, and thus, conflicts with guidance from passengers can be prevented. 【0064】 Furthermore, the guidance voice control unit 13 identifies guidance points included in the spoken voice information based on the acquired analysis results and suppresses the output of guidance information up to the identified points. In this way, the output of guidance information can be reliably suppressed up to the guidance points. 【0065】 Furthermore, the guidance voice control unit 13 releases the suppression of guidance information once the guidance point has been passed. In this way, the output of guidance information can be suppressed only for locations where the passenger wishes to receive guidance. 【0066】 Furthermore, if the spoken voice information combines words related to location and words related to action, the guidance voice control unit 13 may obtain an analysis result indicating that the content indicated by the spoken voice information corresponds to guidance. In this way, guidance that combines location and action, such as "Turn right at the next intersection," can be detected. 【0067】 Furthermore, the keyword analysis unit 12 also extracts keywords related to warnings, and the guidance voice control unit 13 acquires the analysis results of the spoken voice information that includes the warning keywords. The guidance voice control unit 13 also suppresses the output of guidance information from the guidance unit 14 if the content of the spoken voice information indicated by the acquired voice analysis results corresponds to a warning. In this way, if a passenger gives a warning such as "there are a lot of people suddenly running out into the road," the system can detect this and suppress the output of guidance information to prevent conflicts. 【0068】 Furthermore, when spoken audio information combines words related to location with words that provide a warning, the guidance voice control unit 13 obtains an analysis result indicating that the content of the spoken audio information corresponds to a warning. In this way, it is possible to detect warnings that combine location and caution, such as "There are many people running out into the street at the next intersection." 【0069】 In the above-described embodiment, the server device 20 holds the map information 22, and the identification of the instruction location is substantially performed by the server device 20. However, the instruction location may also be identified by the guidance device 10. If the guidance device 10 is a car navigation system, it often has map information (including POI information), and even if it is a navigation application, it can access map information etc. via an external server, so the guidance device 10 can identify the instruction location based on that information. That is, the guidance device 10 is equipped with a map information acquisition unit that acquires map information, and the guidance voice control unit 13 identifies the guidance location based on the map information. 【0070】 Furthermore, the system may operate similarly not only for the speech of passengers, but also for the sounds of other devices besides the guidance device 10. For example, if the guidance device 10 is an aftermarket addition, it can prevent conflicts with sounds from devices originally installed in the vehicle. 【0071】 Furthermore, in the embodiment described above, the server device 20 performed the functions of the voice analysis unit 21, but the guidance device 10 may incorporate functions equivalent to those of the voice analysis unit 21. By doing so, communication with the outside becomes unnecessary, and even in places where communication is unstable, such as inside tunnels, the output of guidance information can be suppressed if there is guidance from a passenger. 【0072】 Furthermore, if the server device 20 is performing the functions of the guidance unit 14, the server device 20 may also perform the functions of the keyword analysis unit 12 and the guidance voice control unit 13. In this case, all spoken voice information input from the voice input unit 11 is output to the server device 20. 【0073】 Furthermore, the present invention is not limited to the embodiments described above. That is, those skilled in the art can implement the invention in various ways, without departing from the core principles, in accordance with conventionally known knowledge. Such modifications, as long as they still incorporate the guiding device of the present invention, are of course included within the scope of the present invention. [Explanation of symbols] 【0074】 10 Guide device 12 Keyword Analysis Section 13. Guidance Voice Control Unit 14 Information Department 20 Server Devices 21. Voice Analysis Unit 22 Map Information

Claims

[Claim 1] A guidance unit that outputs guidance information along the explored route, A voice detection unit that acquires spoken audio information and detects keywords related to guidance, An analysis result acquisition unit acquires the analysis result of the spoken voice information, which includes the keyword related to the guidance detected by the voice detection unit, Regarding the analysis results, if the content indicated by the spoken voice information corresponds to route guidance uttered by a passenger in the vehicle, the voice guidance control unit suppresses the output of the guidance information from the guidance unit. A guide device characterized by comprising: [Claim 2] The guidance device according to claim 1, wherein the guidance voice control unit suppresses the output of the guidance information by reducing the volume when outputting the guidance information. [Claim 3] The guidance device according to claim 1, wherein the suppression of the output of the guidance information by the guidance voice control unit includes temporarily suspending the output of the guidance information. [Claim 4] The guidance device according to claim 1, characterized in that the guidance voice control unit identifies guidance points included in the spoken voice information based on the acquired analysis results and suppresses the output of the guidance information up to the identified guidance points. [Claim 5] The guidance device according to claim 4, characterized in that the guidance voice control unit releases the suppression of the guidance information when the guidance point is passed. [Claim 6] Equipped with a map information acquisition unit that acquires map information, The guidance device according to claim 4 or 5, characterized in that the guidance voice control unit identifies the guidance location based on the map information. [Claim 7] The guidance device according to any one of claims 1 to 6, characterized in that when the spoken voice information is a combination of words relating to a place and words relating to an action, the analysis result acquisition unit acquires an analysis result indicating that the content indicated by the spoken voice information corresponds to the route guidance. [Claim 8] The aforementioned voice detection unit also detects keywords related to warnings as keywords, The analysis result acquisition unit also acquires the analysis results of the spoken audio information, which includes the keywords related to the warning. The guidance voice control unit suppresses the output of the guidance information from the guidance unit even if the content indicated by the spoken voice information corresponds to a warning, based on the analysis results acquired by the analysis result acquisition unit. A guide device according to any one of claims 1 to 7. [Claim 9] The guidance device according to claim 8, characterized in that when the spoken voice information is a combination of a word relating to a place and a word to warn, the analysis result acquisition unit acquires an analysis result indicating that the content indicated by the spoken voice information corresponds to a warning. [Claim 10] A guidance method performed by a guidance device equipped with a guidance unit that outputs guidance information along a explored path, A voice detection process that acquires spoken audio information and detects keywords related to guidance, An analysis result acquisition step is to acquire the analysis result of the spoken voice information which includes the keyword related to the guidance detected in the voice detection step, If the content of the spoken voice information obtained in the analysis result acquisition step corresponds to route guidance spoken by a passenger in the vehicle, the guidance voice control step suppresses the output of the guidance information from the guidance unit. A guidance method characterized by including [Claim 11] A guidance program characterized by causing a computer to execute the guidance method described in claim 10. [Claim 12] A computer-readable storage medium characterized by storing the guidance program described in claim 11.

Images