WO2022153823A1

WO2022153823A1 - Guiding device

Info

Publication number: WO2022153823A1
Application number: PCT/JP2021/047838
Authority: WO
Inventors: 義大石原
Original assignee: パイオニア株式会社
Priority date: 2021-01-14
Filing date: 2021-12-23
Publication date: 2022-07-21
Also published as: JPWO2022153823A1

Abstract

The present invention prevents conflict with a guidance from a fellow passenger and the like.　In a guiding device (10), a guiding unit (14) outputs guidance information according to a searched route. During this operation, a keyword analysis unit (12) acquires speech voice information and extracts a keyword related to a guidance, and a guidance voice control unit (13) acquires an analysis result of the speech voice information including the guidance-related keyword extracted by the keyword analysis unit (12). When the result of voice analysis indicates that the content represented by the speech voice information constitutes a guidance, the guidance voice control unit (13) prevents output of the guidance information from the guiding unit (14).

Description

Guidance device

The present invention relates to a guidance device including a guide unit that outputs guidance information along the searched route.

Guidance devices such as car navigation devices search for a route to a preset destination and provide guidance by voice or the like along the searched route.

Patent Document 1 describes the following inventions for the purpose of providing an easy-to-understand guide for the driver like a passenger. In the invention described in Patent Document 1, the passenger guides the driver. From the guide history of the guide history storage means, the driving situation feature amount at the time of guidance is calculated by the guide time driving situation feature amount calculation means, and the guide is classified into the classification that satisfies the driving situation feature amount with respect to the guide by the guide classification means. .. Then, the utterance content variable portion of the driving situation feature amount is replaced with a variable part symbol, the most frequent utterance content for each classification is selected by the utterance content selection means, and stored in the storage means as a guide rule.

Japanese Unexamined Patent Publication No. 2010-190773

Patent Document 1 provides an easy-to-understand guide like a passenger, but may provide guidance for reasons such as being familiar with the area where the passenger is actually traveling. In such a case, if the guidance by the guidance device is also performed, the guidance may conflict with the guidance of the passenger, and the driver may be confused. In order to eliminate such competition, conventionally, it has been necessary to reduce the volume of the guidance device or suspend the guidance.

One example of the problem to be solved by the present invention is to prevent competition with guidance for passengers and the like.

In order to solve the above problems, the invention according to claim 1 includes a guidance unit that outputs guidance information along the searched route, and a voice detection unit that acquires spoken voice information and detects keywords related to guidance. , The analysis result acquisition unit that acquires the analysis result of the spoken voice information including the keyword related to the guidance detected by the voice detection unit, and the voice analysis result acquired by the analysis result acquisition unit indicate the spoken voice information. When the content corresponds to guidance, it is characterized by including a guidance voice control unit that suppresses the output of the guidance information from the guidance unit.

The invention according to claim 8 is a guidance method executed by a guidance device including a guidance unit that outputs guidance information along the searched route, acquires spoken voice information, and detects keywords related to guidance. The voice detection step, the analysis result acquisition step of acquiring the analysis result of the spoken voice information including the keyword related to the guidance detected in the voice detection step, and the voice analysis result acquired in the analysis result acquisition step are described. When the content indicated by the spoken voice information corresponds to the guidance, it is characterized by including a guidance voice control step of suppressing the output of the guidance information from the guidance unit.

The invention according to claim 9 is characterized in that the guidance method according to claim 8 is executed by a computer as a guidance program.

The invention according to claim 10 is characterized in that the guidance program according to claim 9 is stored in a storage medium readable by a computer.

It is a schematic block diagram of the system which has the guide device which concerns on one Example of this invention. These are examples of words about places, words about actions, and words that call attention. It is a flowchart of the operation which shifts to a passenger guidance mode. It is a flowchart of the operation which ends the passenger guidance mode (guidance). It is a flowchart of the operation which ends the passenger guidance mode (warning).

Hereinafter, the guidance device according to the embodiment of the present invention will be described. The guidance device according to the embodiment of the present invention outputs guidance information along the route searched by the guidance unit. At this time, the voice detection unit acquires the utterance voice information, detects the keyword related to the guidance, and the analysis result acquisition unit acquires the analysis result of the utterance voice information including the keyword related to the guidance detected by the voice detection unit. Then, when the guidance voice control unit suppresses the output of the guidance information from the guidance unit when the content indicated by the spoken voice information corresponds to the guidance as a result of the voice analysis. By doing so, it is possible to detect the guidance of the passenger, and it is possible to prevent competition with the guidance of the passenger or the like.

Further, the guidance voice control unit may specify the guidance point included in the utterance voice information based on the acquired analysis result, and suppress the output of the guidance information to the specified guidance point. By doing so, it is possible to surely suppress the output of the guidance information to the guidance point.

In addition, the guidance voice control unit may release the suppression of guidance information when passing through the guidance point. By doing so, it is possible to suppress the output of the guidance information only at the place where the passenger wants to guide.

Further, a map information acquisition unit for acquiring map information may be provided, and the guidance voice control unit may specify a guidance point based on the map information. By doing so, it becomes possible to specify the guide point by using the intersection name and facility name (POI (Point of Interest) information, etc.) included in the map information, and the guide point can be specified more accurately. be able to.

Further, when the spoken voice information is a combination of words related to the place and words related to the action, the analysis result acquisition unit may acquire the analysis result that the content indicated by the spoken voice information corresponds to the guidance. By doing so, it is possible to detect guidance that combines actions with places such as "turn right at the next intersection".

In addition, the voice detection unit also detects keywords related to warnings as keywords, the acquisition unit acquires the analysis result of utterance voice information including the keywords related to warnings, and the guidance voice control unit acquires the voice analysis acquired by the analysis result acquisition unit. Even if the result of the above indicates that the content indicated by the spoken voice information corresponds to a warning, the output of the guidance information from the guidance unit may be suppressed. By doing so, when the passenger gives a warning such as "there is a lot of popping out", it is possible to detect the warning and suppress the output of the guidance information to prevent the conflict.

Further, when the spoken voice information is a combination of words related to the place and words calling attention, the analysis result acquisition unit may acquire the analysis result that the content indicated by the spoken voice information corresponds to a warning. By doing so, it is possible to detect a warning that combines attention with a place such as "the next intersection has many pop-outs".

Further, in the guidance method according to the embodiment of the present invention, the utterance voice information is acquired in the voice detection process, the keyword related to the guidance is detected, and the utterance voice including the keyword related to the guidance detected in the voice detection step in the analysis result acquisition process. Get the analysis result of the information. Then, in the guidance voice control step, when the content indicated by the spoken voice information corresponds to the guidance as a result of the voice analysis, the output of the guidance information from the guidance unit is suppressed. By doing so, it is possible to detect the guidance of the passenger, and it is possible to prevent competition with the guidance of the passenger or the like.

Further, the above-mentioned guidance method may be executed by a computer as a guidance program. By doing so, since the guidance of the passenger can be detected by using the computer, it is possible to prevent the conflict with the guidance of the passenger or the like.

Further, the above-mentioned guidance program may be stored in a computer-readable storage medium. By doing so, the program can be distributed as a single unit in addition to being incorporated in the device, and version upgrades and the like can be easily performed.

The 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 a guidance device according to this embodiment.

The system shown in FIG. 1 includes a guidance device 10 and a server device 20. The guidance device 10 is provided in a vehicle such as an automobile. The guidance device 10 may be, for example, a car navigation device or a device such as a smartphone or tablet terminal that can be taken out of the vehicle.

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.

The voice input unit 11 inputs the voice spoken in the vehicle. The voice input unit 11 is composed of a microphone or the like. It is preferable that the microphone is installed at a position where not only the driver but also the passenger's spoken voice can be acquired. Therefore, the microphones may be provided not only at one place but also at a plurality of places in the vehicle.

The keyword analysis unit 12 acquires the utterance voice information output from the voice input unit 11 via the guidance voice control unit 13, and extracts (detects) keywords related to guidance or warning from the utterance voice information. That is, the keyword analysis unit 12 functions as a voice detection unit that acquires utterance voice information and detects keywords related to guidance.

The keyword analysis unit 12 has the keywords related to guidance or warning in advance as a database or the like. Keywords related to guidance or warning include, for example, general guidance words such as traffic lights, next intersections, names of facilities around the current position, action instructions such as turning right, turning right, and so on, and calling attention to jumping out and being difficult to see. Instructions are given. For the techniques such as voice recognition and natural language processing used in the keyword analysis unit 12 and the voice analysis unit 21 described later, the well-known techniques used in so-called smart speakers and AI speakers shall be applied. Can be done.

The guidance voice control unit 13 acquires the utterance voice information input from the voice input unit 11 and outputs the utterance voice information to the keyword analysis unit 12. When the keyword analysis unit 12 determines that a keyword related to guidance or warning has been spoken, the guidance voice control unit 13 outputs the spoken voice information to the server device 20. Then, when the result of the voice analysis in the server device 20 is received and the result is "guidance" or "warning", the guidance voice control unit 13 shifts to the passenger guidance mode and guides the guidance unit 14. And suppress the output of the sound related to the warning. That is, in the guidance voice control unit 13, the analysis result acquisition unit that acquires the analysis result of the utterance voice information including the keyword related to the guidance detected by the voice detection unit and the voice analysis result acquired by the analysis result acquisition unit are the utterance. When the content indicated by the voice information corresponds to the guidance, it functions as a guidance voice control unit that suppresses the output of the guidance information from the guidance unit.

Further, the guidance voice control unit 13 asks the driver whether or not the passenger guidance mode can be continued if the guidance by the passenger continues after passing the relevant part such as the intersection included in the utterance voice information. If it is possible, the passenger guidance mode is continuously maintained, and if it is not possible or there is no continuation of the utterance, the passenger guidance mode is terminated. That is, the suppression of guidance information is released.

As is well known, the guidance unit 14 searches for a route to the destination, generates information (guidance information) that guides the driver or the like along the searched route, and outputs the information (guidance information) from the voice output unit 15 or the like. Further, when the guidance voice control unit 13 shifts to the passenger guidance mode, the guidance unit 14 suppresses the output of the voice related to the guidance and warning.

The voice output unit 15 outputs voice or the like related to the guidance information generated by the guidance unit. In addition, the voice output unit 15 also outputs a voice for which the guidance voice control unit 13 asks whether or not the passenger guidance mode can be continued. The audio output unit 15 is composed of a speaker or the like. Of course, the speaker is installed in the vehicle.

The server device 20 is a well-known server computer, and can communicate 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.

The voice analysis unit 21 analyzes the utterance voice information transmitted from the guidance voice control unit 13. The voice analysis unit 21 determines that the content of the spoken voice information is one of "guidance", "warning", and "other" from the context. Then, the classification result is returned (transmitted) to the guidance voice control unit 13.

Regarding the determination of "guidance", "warning", and "others" in the voice analysis unit 21, if words related to the place and words related to the action are included, it is determined to be "guidance". If the word related to the place and the word calling attention are included, it is judged as "warning". If neither "guidance" nor "warning" is applicable, it is judged as "other".

Here, examples of words related to places, words related to actions, and words calling attention are shown in the table of Fig. 2. Of course, it is not limited to the words shown in FIG.

Further, when determining a word related to a place, the voice analysis unit 21 refers to the map information 22 and collates it with the place name, POI information, etc. around the current position, and if there is a match, the place. Judge as a word related to. If it is determined to be "guidance" or "warning", the result of collation with the map information 22 is transmitted to the guidance voice control unit 13 together with the determination result. The collation result includes a place name, an intersection name, a facility name, a latitude / longitude, and the like of a point that collates with the map information 22 and matches. The points and the like that collate with the map information 22 are the points (instructed points) instructed by the passenger in the guidance. The guidance voice control unit 13 can specify the guidance point included in the utterance voice information by receiving the information of the instruction point.

Map information 22 is map information possessed by a navigation device or the like, and includes place names, intersection names, facility names, and the like. The map information 22 also includes so-called POI information.

Next, the operation (guidance method) of the guidance device 10 having the above-described configuration will be described with reference to the flowcharts of FIGS. 3 to 5. The guide program can be obtained by configuring the flowcharts of FIGS. 3 to 5 as a program executed by a computer equipped with a CPU or the like.

FIG. 3 is a flowchart of the operation of shifting to the passenger guidance mode. First, the keyword analysis unit 12 acquires the utterance voice information input from the voice input unit 11 via the guidance voice control unit 13 and performs keyword analysis (step S11).

The keyword analysis unit 12 determines whether or not a keyword related to guidance or warning has been extracted as a result of keyword analysis (step S12). If the keyword related to the guidance or warning is not extracted (step S12; NO), the utterance is considered not to be guidance by a passenger or the like, and the process returns to step S11.

On the other hand, when a keyword related to guidance or warning is extracted (step S12; YES), the guidance voice control unit 13 transmits the spoken voice information to the server device 20, and the voice analysis unit 21 performs voice analysis (step S12; YES). Step S13). As described above, the voice analysis unit 21 outputs any of the “guidance”, “warning”, and “other” results of the voice analysis to the guidance voice control unit 13. At this time, as described above, the place names and the like of the points that match with the map information 22 are also output.

Next, the guidance voice control unit 13 determines whether the received voice analysis result is "guidance" (step S14). If the result of the voice analysis is "guidance" (step S14; YES), the guidance voice control unit 13 shifts to the 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 proceeds to step S16 without shifting to the passenger guidance mode (guidance). The passenger guidance mode (guidance) suppresses the voice output of the output of the guidance unit 14 related to the route guidance.

Next, the guidance voice control unit 13 determines whether the received voice analysis result is a "warning" (step S16). If the result of the voice analysis is "warning" (step S16; YES), the guidance voice control unit 13 shifts to the passenger guidance mode (warning) (step S17). On the other hand, if the result of the voice analysis is not "warning" (step S16; NO), the guidance voice control unit 13 proceeds to step S18 without shifting to the passenger guidance mode (warning). The passenger guidance mode (warning) suppresses the voice output of the output of the guidance unit 14 related to the warning at the designated portion.

Next, the guidance voice control unit 13 determines whether or not the operation is completed, such as turning off the power of the guidance device 10 or terminating the application or the like that executes this flowchart (step S18). If the operation is completed (step S18; YES), the flowchart is terminated, and if the operation is not completed (step S18; NO), the process returns to step S11.

Since the passenger guidance mode (guidance) and the passenger guidance mode (warning) are not in an exclusive relationship, there are cases where the passenger guidance mode (guidance) and the passenger guidance mode (warning) are used. For example, if the passenger is in the guidance mode and is already in the passenger guidance mode (guidance) and says "the next curve has poor visibility", the passenger guidance mode (guidance) and the passenger guidance mode (warning) It becomes.

Further, in the flowchart of FIG. 3, when the result of the voice analysis is "Other", step S18 is executed without either the passenger guidance mode (guidance) or the passenger guidance mode (warning).

As is clear from the above description, step S11 functions as a voice detection process, step S13 functions as an analysis result acquisition process, and step S15 functions as a guidance voice control process.

FIG. 4 is a flowchart of the operation of ending the passenger guidance mode (guidance). First, the guidance voice control unit 13 determines whether or not the passenger guidance mode (guidance) is currently set (step S21). If the passenger guidance mode (guidance) is not currently set (step S21; NO), step S21 is repeated.

On the other hand, when the passenger guidance mode (guidance) is currently set (step S21; YES), the guidance voice control unit 13 determines whether or not the designated portion has been passed (step S22). The passage of the instruction point is based on the map information (not shown) and the current position of the guidance device 10 based on the information such as the points that collate with the map information 22 and match with the map information 22 received from the voice analysis unit 21 (server device 20). It may be determined by collating with.

When the guidance voice control unit 13 determines that it does not pass through the instructed portion (step S22; NO), it repeats step S22 and waits until it passes through the instructed portion. That is, the passenger guidance mode is continued until the designated portion is passed. That is, the guidance voice control unit 13 identifies the instruction point (guidance point) included in the utterance voice information based on the acquired analysis result, and suppresses the output of the guidance information to the specified instruction point (guidance point). ing.

On the other hand, if it is determined that the designated portion has been passed (step S22; YES), the guidance voice control unit 13 determines whether or not the utterance of "end" has been heard (step S23). The user of the guidance device 10 is informed in advance by means of a manual, guidance voice, or the like that the passenger guidance mode ends by saying "end". Therefore, the guidance voice control unit 13 can end the passenger guidance mode by determining whether or not the utterance of "end" has been heard. In listening to the utterance of "end", the utterance voice information input from the voice input unit 11 may be analyzed by the keyword analysis unit 12 in the same manner as in the keyword analysis.

When the guidance voice control unit 13 hears the utterance of "end" (step S23; YES), the guidance voice control unit 13 ends the passenger guidance mode (guidance) (step S26).

On the other hand, if the utterance of "end" is not heard (step S23; NO), the guidance voice control unit 13 determines whether the utterance is continuing (step S24). That is, if the guidance by the passenger continues, the passenger guidance mode (guidance) is continued, and if not, the passenger guidance mode (guidance) is terminated. It should be noted that the continuation of utterance may be determined by the detection time of the silent (no utterance) state.

If the utterance is not continued (step S24; NO), the guidance voice control unit 13 ends the passenger guidance mode (guidance) (step S26).

On the other hand, if the utterance continues (step S24; YES), the guidance voice control unit 13 asks the driver or the like whether or not the passenger guidance mode (guidance) can be continued (step S25). For example, the guidance voice control unit 13 outputs a voice such as "Do you want to continue the guidance by the passenger?" From the voice output unit 15. The answer should be, for example, "yes" or "no".

If the guidance voice control unit 13 returns to step S21 and re-determines the end when the continuation of the passenger guidance mode (guidance) becomes "Yes" as a result of the question (step S25; YES). .. On the other hand, when the continuation of the passenger guidance mode (guidance) becomes "No", the passenger guidance mode (guidance) is terminated (step S26). The answer to the question is not limited to the driver but may be a passenger.

When the passenger guidance mode (guidance) is terminated in step S26, the suppression of the output of the guidance voice or the like is released, and the output of the guidance voice or the like from the guidance unit 14 is resumed. If, as a result of the guidance by the passenger, the vehicle travels on a route different from the route searched by the guide unit 14, the vehicle is automatically rerouted.

Further, in the flowchart of FIG. 4, the end of the passenger guidance mode (guidance) is detected by the three determinations of steps S23 to S25, but any one or two may be used.

Further, steps S23 to S25 are executed when it is determined in step S22 that the designated portion has been passed. That is, the guidance voice control unit 13 releases the suppression of the guidance information when the instruction point (guidance point) is passed.

FIG. 5 is a flowchart of the operation of ending the passenger guidance mode (warning). In the passenger guidance mode (warning), only step S21, step S22, and step S26 of FIG. 4 are configured. In FIG. 4, steps S21A and step S26A are described because the passenger guidance mode has been changed from (guidance) to (warning). The operation is substantially the same.

FIG. 5 shows guidance (warning) to a specific point in the passenger guidance mode (warning), and it is considered that the mode may be terminated if the warning point (instruction point) is passed. The determination as in steps S23 to S25 of the above is omitted.

Even in the passenger guidance mode (warning), the process may be terminated by listening to "end" as in step S23 of FIG. Further, the passenger guidance mode (guidance) may be set as a flowchart as shown in FIG.

According to this embodiment, the guidance device 10 outputs guidance information along the route searched by the guidance unit 14. At this time, the keyword analysis unit 12 acquires the utterance voice information and extracts the keyword related to the guidance, and the guidance voice control unit 13 acquires the analysis result of the utterance voice information including the keyword related to the guidance extracted by the keyword analysis unit 12. Then, when the guidance voice control unit 13 suppresses the output of the guidance information from the guidance unit 14 when the content indicated by the spoken voice information corresponds to the guidance as a result of the voice analysis. By doing so, it is possible to detect the guidance of the passenger, and it is possible to prevent competition with the guidance of the passenger or the like.

Further, the guidance voice control unit 13 identifies the guidance point included in the utterance voice information based on the acquired analysis result, and suppresses the output of the guidance information to the specified point. By doing so, it is possible to surely suppress the output of the guidance information to the guidance point.

In addition, the guidance voice control unit 13 releases the suppression of guidance information when the guidance point is passed. By doing so, it is possible to suppress the output of the guidance information only at the place where the passenger wants to guide.

Further, when the spoken voice information is a combination of words related to the place and words related to the action, the guidance voice control unit 13 may acquire an analysis result that the content indicated by the spoken voice information corresponds to the guidance. By doing so, it is possible to detect guidance that combines actions with places such as "turn right at the next intersection".

The keyword analysis unit 12 also extracts keywords related to warnings as keywords, and the guidance voice control unit 13 also acquires analysis results of spoken voice information including keywords related to warnings. Then, the guidance voice control unit 13 suppresses the output of the guidance information from the guidance unit 14 even when the acquired voice analysis result indicates that the content indicated by the utterance voice information corresponds to a warning. By doing so, when the passenger gives a warning such as "there is a lot of popping out", it is possible to detect the warning and suppress the output of the guidance information to prevent the conflict.

Further, when the spoken voice information is a combination of words related to the place and words calling attention, the guidance voice control unit 13 has acquired the analysis result that the content indicated by the spoken voice information corresponds to a warning. By doing so, it is possible to detect a warning that combines attention with a place such as "the next intersection has many pop-outs".

In the above-described embodiment, the server device 20 has the map information 22, and the server device 20 substantially specifies the designated location, but the guide device 10 may specify the designated location. The guidance device 10 often has map information (including POI information) if it is a car navigation device, and even a navigation application or the like can access the map information or the like by an external server or the like. The instruction point can be specified on the guide device 10 side based on the information. That is, the guidance device 10 includes a map information acquisition unit that acquires map information, and the guidance voice control unit 13 specifies a guidance point based on the map information.

Further, the operation may be performed in the same manner not only for the voice of a passenger or the like but also for the voice of a device other than the guidance device 10. For example, when the guidance device 10 is retrofitted, it is possible to prevent competition with voice from a device originally provided in a vehicle or the like.

Further, in the above-described embodiment, the function of the voice analysis unit 21 is executed by the server device 20, but the function equivalent to the voice analysis unit 21 may be incorporated into the guidance device 10. By doing so, it is not necessary to communicate with the outside, so it is possible to suppress the output of guidance information when there is guidance by a passenger even in a place where communication is unstable such as in a tunnel. ..

Further, when the server device 20 executes the function of the guidance unit 14, the server device 20 may also have the functions of the keyword analysis unit 12 and the guidance voice control unit 13. In this case, all the spoken voice information input from the voice input unit 11 is output to the server device 20.

Further, the present invention is not limited to the above examples. That is, those skilled in the art can carry out various modifications according to conventionally known knowledge within a range that does not deviate from the gist of the present invention. Even with such a modification, as long as the guide device of the present invention is still provided, it is, of course, included in the category of the present invention.

10 Guidance device 12 Keyword analysis unit 13 Guidance voice control unit 14 Guidance unit 20 Server device 21 Voice analysis unit 22 Map information

Claims

A guide unit that outputs guidance information along the searched route, and
A voice detection unit that acquires spoken voice information and detects keywords related to guidance,
An analysis result acquisition unit that acquires an analysis result of the utterance voice information including a keyword related to the guidance detected by the voice detection unit, and an analysis result acquisition unit.
The voice analysis result acquired by the analysis result acquisition unit includes a guidance voice control unit that suppresses the output of the guidance information from the guidance unit when the content indicated by the utterance voice information corresponds to guidance. A guidance device characterized by the fact that.
The guidance voice control unit identifies a guidance point included in the utterance voice information based on the acquired analysis result, and suppresses the output of the guidance information to the specified guidance point. Item 1. The guidance device according to item 1.
The guidance device according to claim 2, wherein the guidance voice control unit releases the suppression of the guidance information when passing through the guidance point.
Equipped with a map information acquisition unit to acquire map information
The guidance device according to claim 2 or 3, wherein the guidance voice control unit identifies the guidance point based on the map information.
When the spoken voice information is a combination of words related to a place and words related to an action, the analysis result acquisition unit is characterized in that the analysis result that the content indicated by the spoken voice information corresponds to guidance is acquired. The guidance device according to any one of claims 1 to 4.
The voice detection unit also detects a keyword related to a warning as the keyword, and the voice detection unit also detects the keyword.
The acquisition unit also acquires the analysis result of the utterance voice information including the keyword related to the warning.
The guidance voice control unit suppresses the output of the guidance information from the guidance unit even when the voice analysis result acquired by the analysis result acquisition unit corresponds to a warning in the content indicated by the utterance voice information.
The guide device according to any one of claims 1 to 5, wherein the guide device is characterized in that.
When the spoken voice information is a combination of words related to a place and words calling attention, the analysis result acquisition unit is characterized in that it acquires an analysis result that the content indicated by the spoken voice information corresponds to a warning. The guidance device according to claim 6.
It is a guidance method executed by a guidance device equipped with a guidance unit that outputs guidance information along the searched route.
A voice detection process that acquires spoken voice information and detects keywords related to guidance,
An analysis result acquisition step of acquiring an analysis result of the utterance voice information including a keyword related to the guidance detected in the voice detection step, and an analysis result acquisition step.
Regarding the result of the voice analysis acquired in the analysis result acquisition step, when the content indicated by the utterance voice information corresponds to the guidance, a guidance voice control step for suppressing the output of the guidance information from the guidance unit, and a guidance voice control step.
A guidance method characterized by including.
A guidance program characterized in that the guidance method according to claim 8 is executed by a computer.
A computer-readable storage medium comprising storing the guidance program according to claim 9.