Information provision device, information provision method, and information provision program

Abstract

To provide an information provision device or the like capable of reliably providing necessary guidance information while reducing the amount of information as voice necessary for processing.SOLUTION: An information provision device comprises: a guidance voice output control section 1 and a loudspeaker 10 for outputting guidance voice; a microphone 11 and a voice collection transmission section 2 for collecting voice after an output start of the guidance voice; and the guidance voice output control section 1 and the loudspeaker 10 for outputting re-guidance voice corresponding to the guidance voice based on a determination result on whether specific voice is included in the collected voice.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present application relates to the technical fields of an information providing device, an information providing method, and an information providing program. More specifically, the present application relates to the technical fields of an information providing device, an information providing method, and a program for the information providing device that provide necessary information by sound output. [Background technology]

[0002] In recent years, in addition to the conventional on-board navigation devices that provide navigation guidance for vehicles and other moving objects, there has been active research and development into navigation systems that utilize portable terminal devices such as smartphones.

[0003] In this case, when utilizing the portable terminal device, due to limitations on the size of the display provided thereon, guidance using sounds including voice guidance becomes important. Patent Document 1 listed below is an example of a document disclosing prior art that addresses this background. The prior art disclosed in Patent Document 1 is configured to recognize, by voice recognition, the content of words that a passenger, such as a driver, has missed, among words spoken by the passenger, and then provide guidance again corresponding to the words that were not detected. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-87871 Summary of the Invention [Problem to be solved by the invention]

[0005] In the prior art described in Patent Document 1, the collection of voices emitted by passengers and the recognition of their contents are performed continuously. If the recognition is performed by an external server in order to reduce the processing load on the portable terminal device and the associated power consumption, the results of the recognition must be continuously transmitted to the external server. However, this results in a huge amount of communication between the external server and the terminal device, which results in problems such as a reduction in processing speed and difficulty in establishing new connections. Furthermore, even if the recognition is performed by the terminal device, there is a risk of an increased processing load.

[0006] Therefore, the present application has been made in consideration of the above-mentioned problems, and one example of the object of the application is to provide an information providing device, an information providing method, and a program for the information providing device that can reliably provide necessary guidance information while reducing the amount of audio information required for processing. [Means for solving the problem]

[0007] In order to solve the above problem, the invention described in claim 1 comprises a first output means for outputting the information to be provided by sound, a sound collection means for collecting sound after the output of the information to be provided has started, a second output means for outputting corresponding information corresponding to the information to be provided by sound based on a determination result as to whether a predetermined specific sound is included in the collected sound, and an addition means for, when an operation to output the information to be provided again is performed, adding a word extracted from the sound based on an analysis result of the sound collected up to the operation as a new specific sound, wherein the second output means is configured to output the corresponding information by sound based on a determination result as to whether the specific sound and the added new specific sound are included in the collected sound.

[0008] In order to solve the above problem, the invention of claim 9 is an information providing method executed in an information providing device including first output means, sound collection means, second output means, and adding means, the information providing method including a first output step of outputting information to be provided by sound from the first output means, a sound collection step of collecting sound after start of output of the information to be provided by the sound collection means, a second output step of outputting corresponding information corresponding to the information to be provided by the second output means by sound based on a determination result of whether a predetermined specific sound is included in the collected sound, and a second output step of outputting corresponding information by sound from the second output means in response to an instruction to output the corresponding information. and an adding step of, when an operation to output the provided information again is performed, adding, by the adding means, a word extracted from the sound based on the analysis result of the sound collected up to that operation, as the new specific sound. In the second output step, the corresponding information is configured to be output by sound from the second output means based on the determination result as to whether the specific sound and the added new specific sound are included in the collected sound.

[0009] In order to solve the above problem, the invention described in claim 10 is an information provision program that causes a computer to function as a first output means that outputs the information to be provided by sound, a sound collection means that collects sound after the output of the information to be provided has started, a second output means that outputs corresponding information corresponding to the information to be provided by sound based on the determination result of whether a predetermined specific sound is included in the collected sound, and an addition means that, when an operation to output the information to be provided again is performed, adds a word extracted from the sound based on the analysis result of the sound collected up to the operation as a new specific sound, and is configured to cause the computer that functions as the second output means to function to output the corresponding information by sound based on the determination result of whether the specific sound and the added new specific sound are included in the collected sound. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a schematic configuration of an information providing apparatus according to an embodiment; [Figure 2] 1 is a block diagram showing a schematic configuration of a navigation system according to an embodiment of the present invention; [Figure 3] 1A and 1B are block diagrams showing the general configuration of a terminal device and the like according to an embodiment of the present invention, in which FIG. 1A is a block diagram showing the general configuration of the terminal device, and FIG. 1B is a block diagram showing the general configuration of a server according to the embodiment of the present invention. [Figure 4] 10 is a flowchart illustrating a navigation process according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Next, an embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a block diagram showing a schematic configuration of an information providing device according to the embodiment.

[0012] As shown in FIG. 1, the information providing device S according to the embodiment is configured to include a first output means 1, a sound collection means 2, and a second output means 3.

[0013] In this configuration, the first output unit 1 outputs the information to be provided by sound. An example of this information to be provided is guidance information for guiding a moving body such as a vehicle.

[0014] On the other hand, the sound collection means 2 collects the sound after the first output means 1 starts outputting the provided information.

[0015] The second output means 3 outputs corresponding information corresponding to the provided information by sound, based on the determination result of whether a predetermined specific sound is included in the sound collected by the sound collection means 2. In this case, the specific sound is, for example, a specific sound such as "Huh?" or "Eh?" uttered by a passenger of the vehicle to indicate that they missed something or that they would like to hear it again.

[0016] As described above, according to the operation of the information providing device S of the embodiment, corresponding information corresponding to the provided information is output by sound based on the determination result of whether a specific sound is included in the sound after the output of the provided information starts. Therefore, the amount of information collected as sound can be reduced while reliably providing the provided information. [Example]

[0017] Next, specific examples corresponding to the above-described embodiments will be described with reference to Figures 2 to 4. The examples described below are examples in which the present invention is applied to route guidance using sound (voice) in a navigation system consisting of a terminal device and a server connected to each other via a network such as the Internet so that data can be exchanged between them.

[0018] Fig. 2 is a block diagram showing the general configuration of a navigation system according to an embodiment, Fig. 3 is a block diagram showing the general configuration of a terminal device according to an embodiment, and Fig. 4 is a flowchart showing navigation processing according to an embodiment. In Fig. 3, some of the components of the embodiment corresponding to the components of the information providing device S according to the embodiment shown in Fig. 1 are given the same component numbers as those of the components of the information providing device S.

[0019] 2, the navigation system SS of the embodiment is configured with one or more terminal devices T1, T2, T3, ..., Tn (n is a natural number), each of which is operated by a passenger (more specifically, a driver or passenger) of a moving body such as a vehicle within the moving body; a server SV; and a network NW, such as the Internet, that connects the terminal devices T1, T2, T3, ..., Tn and the server SV so that data can be exchanged. In the following description, when describing configurations common to the terminal devices T1 to Tn, these will be collectively referred to as "terminal device T." In this case, the terminal device T is specifically realized as, for example, a so-called smartphone or a tablet-type terminal device.

[0020] In this configuration, each terminal device T independently exchanges various data with the server SV via the network NW to provide travel guidance to passengers using the terminal device T. The data exchanged at this time includes search data for searching for a route the vehicle should travel and guidance data for after the vehicle has started traveling along the searched route. Due to limitations on the size of the display provided on the terminal device T, limitations on processing load, or to avoid gazing at the screen, the navigation system SS primarily provides travel guidance to the passengers using voice or sound. For this reason, the guidance data transmitted from the server SV to each terminal device T includes voice or sound guidance data. In the following description, this voice guidance data will be simply referred to as "guidance voice data."

[0021] Next, the configuration and operation of each terminal device T and server SV will be described with reference to FIG. 3. First, as shown in FIG. 3(a), each terminal device T of the embodiment includes an interface 5, a processing unit 6 including a CPU, RAM (Random Access Memory), ROM (Read Only Memory), etc., a memory 8 including a volatile area and a non-volatile area, an operation unit 9 including a touch panel and operation buttons, a speaker 10, a microphone 11, a sensor unit 12 including a GPS (Global Positioning System) sensor and / or an autonomous sensor, etc., and a display 13 including a liquid crystal or organic EL (Electro Luminescence) display, etc. The processing unit 6 also includes a route search unit 7, a guidance voice output control unit 1, and a sound collection and transmission unit 2. In this case, the route setting unit 7, the guidance voice output control unit 1, and the sound collection and transmission unit 2 may each be realized by a hardware logic circuit including the CPU, etc., constituting the processing unit 6, or may be realized in software by the CPU, etc., reading and executing a program corresponding to a flowchart showing the processing of the terminal device T among the navigation processing of the embodiment described below. Furthermore, the guidance voice output control unit 1 and the speaker 10 correspond to an example of the first output means 1 and the second output means 3 of the embodiment, the microphone 11 and the sound collection and transmission unit 2 correspond to an example of the sound collection means 2 of the embodiment and an example of the "transmission means" of the present application, and the interface 5 corresponds to an example of the "acquisition means" of the present application. Also, as shown by the dashed line in Figure 3(a), the guidance voice output control unit 1 and the speaker 10, as well as the microphone 11 and the sound collection and transmission unit 2, constitute an example of the information provision device S of the embodiment.

[0022] In the above configuration, the interface 5 controls the exchange of data with the server SV via the network NW under the control of the processing unit 6. Meanwhile, the sensor unit 12 generates sensor data indicating the current position, moving speed, moving direction, etc. of the terminal device T (in other words, the current position, moving speed, moving direction, etc. of the passenger operating the terminal device T or the moving object on which the passenger is riding) using the GPS sensor and / or an independent sensor, and outputs the sensor data to the processing unit 6. Under the control of the processing unit 6, the route search unit 7 transmits the sensor data and destination data input from the operation unit 9 (i.e., destination data indicating the destination to which the moving object on which the passenger operating the terminal device T is riding should move) as search data to the server SV via the interface 5 and the network NW. Thereafter, the route search unit 7 acquires route data indicating the search result of the route from the current position indicated by the sensor data to the destination indicated by the destination data via the network NW and the interface 5.

[0023] Thereafter, the processing unit 6 uses the acquired route data to exchange the guidance data (including the sensor data at that time) with the server SV, and guides the movement of the mobile object along the searched route. At this time, the guidance voice output control unit 1 outputs (emits sound) a guidance voice corresponding to the guidance voice data included in the guidance data acquired from the server SV via the network NW and the interface 5 to the passenger via the speaker 10. This guidance voice corresponds to an example of "provided information" in the present application. In addition, when re-guidance voice data of an embodiment described below is acquired from the server SV via the network NW and the interface 5, the guidance voice output control unit 1 outputs a re-guidance voice corresponding to the re-guidance voice data to the passenger via the speaker 10. This re-guidance voice corresponds to an example of "corresponding information" in the present application.

[0024] Meanwhile, under the control of the processing unit 6, the sound collection and transmission unit 2 collects sounds from within the vehicle after the start of output of the guidance voice via the microphone 11, generates sound collection data corresponding to the collected sounds, and transmits the data to the server SV via the interface 5 and the network NW. While sound collection within the vehicle itself may have been performed before the start of output of the guidance voice, the sound collection data to be transmitted to the server SV is generated from sounds collected after the start of output of the guidance voice. Concurrently, when an input operation of data necessary for guidance of the vehicle, including the destination, is performed on the operation unit 9, the operation unit 9 generates an operation signal (including the destination data) corresponding to the input operation and transmits it to the processing unit 6. Accordingly, the processing unit 6 controls the route setting unit 7, the guidance voice output control unit 1, and the sound collection and transmission unit 2, and executes the process of the terminal device T among the navigation processes of the embodiment. At this time, the processing unit 6 executes the process while temporarily or non-volatilely storing the data necessary for the process in the memory 8. Furthermore, a guidance image or the like as a result of the process is displayed on the display 13.

[0025] 3(b), the server SV of the embodiment is configured with an interface 20, a processing unit 21 including a CPU, RAM, ROM, etc., and a recording unit 22 consisting of an HDD (Hard Disc Drive) or an SSD (Solid State Drive), etc. The processing unit 21 is also configured with a route setting unit 21a, a guidance voice generating unit 21b, and a voice recognition unit 21c. In this case, the route setting unit 21a, the guidance voice generating unit 21b, and the voice recognition unit 21c may each be realized by a hardware logic circuit including the CPU, etc., that constitutes the processing unit 21, or may be realized in software by the CPU, etc., reading and executing a program corresponding to a flowchart showing the processing as the server SV among the navigation processing of the embodiment described below.

[0026] In the above configuration, the recording unit 22 non-volatilely stores navigation data such as map data and the above-mentioned voice guidance data required for providing guidance on the movement of each mobile object in which a passenger using each terminal device T connected to the server SV via the network NW is riding. Meanwhile, under the control of the processing unit 21, the interface 20 controls the exchange of data with each terminal device T via the network NW. Also, under the control of the processing unit 21, the route setting unit 21c searches for the route to the destination indicated by the destination data based on the destination data and the sensor data acquired from any terminal device T, and transmits the route data indicating the search result to the terminal device T that has transmitted the destination data and the sensor data. As a result, the terminal device T provides route guidance based on the route data.

[0027] During the guidance, the guidance voice generation unit 21b generates the guidance voice data in accordance with the timing of guidance on the route and transmits it to the terminal device T used by the passenger of the vehicle to be guided via the interface 20 and the network NW. As a result, a guidance voice corresponding to the guidance voice data is output (emitted as sound) to the passenger through the speaker 10 of the terminal device T. Meanwhile, when the collected sound data corresponding to the sound collected after the start of output of the guidance voice corresponding to the guidance voice data is transmitted, the voice recognition unit 21c performs voice recognition on the collected sound data using a preset method. At this time, the voice recognition unit 21c determines whether the sound corresponding to the collected sound data includes a specific sound of a preset embodiment indicating that the previously output guidance voice was inaudible. The specific voice is, for example, "Huh?", "Eh?", "I can't hear you," "What?", "Once more," or "One more time," indicating that the voice was missed or that the passenger wishes to hear it again. The speaker may be either the passenger using the terminal device T or another passenger in the vehicle in which the passenger is riding. The voice recognition unit 21c determines whether the specific voice is included in the sound corresponding to the sound collection data by subtracting (removing) the guidance voice from the sound corresponding to the sound collection data. If it is determined that the specific voice is included in the sound corresponding to the sound collection data, the guidance voice generation unit 21b generates re-guidance voice data corresponding to the guidance voice data that is equivalent to the guidance voice output at the timing corresponding to the timing when the sound collection data was generated, and transmits the re-guidance voice data to the terminal device T used by the passenger of the vehicle to be guided via the interface 20 and the network NW.

[0028] At this time, the relationship between the guidance voice (hereinafter simply referred to as "guidance voice") that was output at the timing corresponding to the timing at which the sound collection data was generated and the re-guidance voice corresponding to the above-mentioned re-guidance voice data will be, for example, one or more of the following relationships i) to v). i) The guidance voice and the re-guidance voice are identical in content, speed, volume, etc. ii) The volume of the re-guidance voice is louder than the volume of the guidance voice. iii) The output speed of the re-guidance voice is slower than the output speed of the guidance voice. iv) The voice quality of the re-guidance voice is different from that of the guidance voice (for example, the guidance voice is a male voice and the re-guidance voice is a female voice). v) The guidance voice is in a simplified form (abbreviated form), whereas the re-guidance voice is in the unabbreviated form.

[0029] Next, the navigation process of the embodiment executed in the navigation system of the embodiment having the above-described configuration and functions will be specifically described with reference to FIGS.

[0030] The navigation process of the embodiment is initiated, for example, when a guidance instruction operation, such as a guidance instruction operation for guiding the movement of the target moving body along a route, is performed on the operation unit 9 of a terminal device T of the embodiment used by a passenger aboard a moving body that is the target of travel guidance (hereinafter simply referred to as a "target moving body"). In the following description, the terminal device T will be referred to as the "target terminal device T" as appropriate. Then, as shown in the corresponding flowchart in FIG. 4, when the guidance instruction operation is performed on the operation unit 9 of the target terminal device T, the route search unit 7 of the processing unit 6 of the target terminal device T exchanges the search data with the route search unit 21a of the server SV and searches for a route along which the target moving body should travel (step S1). At this time, the route search unit 21a of the server SV is always waiting for the transmission of the search data from any of the terminal devices T currently connected to the server SV via the network NW. When the search data is transmitted from the target terminal device T, the route search unit 21a performs a route search based on the search data and transmits the route data as the search result to the route search unit 7 of the target terminal device T via the network NW (step S15).

[0031] Thereafter, when guidance for movement along the route is started by, for example, an operation to start movement on the operation unit 9 of the target terminal device T, the processing unit 6 of the target terminal device T and the processing unit 21 of the server SV start providing guidance along the route searched in steps S1 and S15 while exchanging the above-mentioned guidance data via the network NW (steps S2, S16).

[0032] Next, the guidance voice output control unit 1 of the target terminal device T waits for the transmission of the guidance voice data from the server SV (step S3) after the guidance has started in the above step 2. If the guidance voice data is not transmitted during the waiting in step S3 (step S3: NO), the processing unit 6 of the target terminal device T proceeds to step S11, which will be described later.

[0033] In parallel with this, the guidance voice generation unit 21b of the server SV transmits the above guidance voice data to the target terminal device T via the network NW at the necessary timing during the route guidance (step S17). Then, the guidance voice output control unit 1 of the target terminal device T, which has acquired the guidance voice data (step S3: YES), outputs a guidance voice corresponding to the received guidance voice data (e.g., a guidance voice such as "Please proceed to the right lane of the three lanes ahead") via the speaker 10 (step S4). Thereafter, the sound collection and transmission unit 2 of the target terminal device T generates the collected sound data corresponding to the sound collected within the target moving body at least after the start of output of the above guidance voice, and starts transmitting the collected sound data to the server SV via the network NW (step S5). Thereafter, the guidance voice output control unit 1 determines whether the output of the guidance voice that was being output at that time has ended (step S6). If the output is still continuing (step S6: NO), the process returns to step S5 and continues generating and transmitting the collected sound data. Thereafter, when the output of the guidance voice has finished (step S6: YES), the sound collection and transmission unit 2 continues to generate and transmit the sound collection data for a predetermined time (step S7, step S7: NO), and when the predetermined time has elapsed (step S7: YES), it ends the generation and transmission of the sound collection data (step S8).

[0034] On the other hand, after transmitting the guidance voice data in step S17, the processing unit 21 of the server SV waits for the transmission of the collected voice data from the target terminal device T (step S18, step S18: NO). If the collected voice data is transmitted during the standby period in step S18 (step S18: YES), the voice recognition unit 21c performs voice recognition on the sound corresponding to the transmitted collected voice data, and determines whether the specific voice is included in the sound (step S19). If the specific voice is not included in the determination in step S19 (step S19: NO), the processing unit 21 returns to step S17 and continues providing route guidance.

[0035] On the other hand, if the determination in step S19 indicates that the specific voice is included in the sound corresponding to the collected sound data (step S19: YES), the guidance voice generation unit 21a generates re-guidance voice data corresponding to the re-guidance voice corresponding to the guidance voice corresponding to the guidance voice data transmitted in step S17, and transmits the generated data to the target terminal device T via the network NW (step S20). The re-guidance voice corresponding to the re-guidance voice data transmitted at this time has a relationship with the guidance voice corresponding to the guidance voice data transmitted in step S17, for example, as described in any one or more of i) to v) above. Thereafter, the processing unit 21 determines whether or not to terminate the route guidance as the navigation processing of the embodiment due to reasons such as the target moving object having reached its destination (step S21). If the determination in step S21 indicates that the route guidance should not be terminated (step S21: NO), the processing unit 21 returns to step S17 and continues to perform route guidance. On the other hand, if the determination in step S21 indicates that the route guidance should be terminated (step S21: YES), the processing unit 21 terminates the route guidance as is.

[0036] On the other hand, after completing the generation and transmission of the collected sound data in step S8, the guidance voice output control unit 1 of the target terminal device T waits for the transmission of the re-guidance voice data from the server SV (step S9). If the re-guidance voice data is not transmitted during the waiting period of step S9 (step S9: NO), the processing unit 6 of the target terminal device T proceeds to step S11, which will be described later. On the other hand, if the re-guidance voice data is transmitted during the waiting period of step S9 (step S9: YES), the guidance voice output control unit 1 of the target terminal device T outputs a re-guidance voice corresponding to the received re-guidance voice data (the re-guidance voice corresponding to the guidance voice output in step S4) via the speaker 10 (step S10). Thereafter, the processing unit 6 of the target terminal device T determines whether or not to terminate the route guidance as the navigation processing of the embodiment, for example, for the same reason as in step S21 (step S11). If the determination in step S11 is that the route guidance should not be terminated (step S11: NO), the processing unit 6 returns to step S3 and continues the route guidance. On the other hand, in the determination of step S11, if the route guidance is to be ended (step S11: NO), the processing unit 6 ends the route guidance.

[0037] As described above, according to the navigation process of the embodiment, a re-guidance voice corresponding to the guidance voice is output based on the determination result of whether a specific voice is included in the sound after the output of the guidance voice has started (see step S10, step S19, and step S20 in FIG. 4). Therefore, the amount of information as collected sound can be reduced while ensuring that the passengers can recognize the content of the guidance voice.

[0038] In addition, sound collection data corresponding to the collected sound is sent to the server SV, and re-guidance voice data based on the determination result of whether or not a specific sound corresponding to the sound collection data exists is obtained and output as re-guidance voice (see Figure 4).Therefore, processing in the server SV can reliably provide the necessary guidance while reducing the amount of information in the collected sound and the processing load on the terminal device T.

[0039] Furthermore, since sounds are collected until a predetermined time has elapsed after the output of the guidance voice has ended (see steps S5 to S8 in FIG. 4), sounds containing necessary specific voices can be collected.

[0040] Furthermore, if the content of the re-guidance voice is the same as the content of the guidance voice (for example, see i) above), the necessary content of the guidance voice can be reliably recognized.

[0041] Furthermore, when the re-guidance voice is output at a volume louder than the volume at which the guidance voice is output (see, for example, ii) above), the content of the re-guidance voice corresponding to the guidance voice can be reliably recognized.

[0042] In the navigation processing of the above-described embodiment, the specific voice is assumed to be a voice from either a passenger using the target terminal device T (e.g., the driver of the target moving body) or another passenger riding in the target moving body with the passenger. However, in addition to this, for example, if past voice recognition results of the passenger using the target terminal device T are recorded in the target terminal device T or the server SV, the server SV may be referenced to detect only the specific voice uttered by the passenger using the target terminal device T (see step S19 in FIG. 4). In this case, the passenger can be reliably made to recognize the content of the re-guidance voice corresponding to the guidance voice based on the specific voice of the passenger.

[0043] Furthermore, in the navigation processing of the above-described embodiment, the determination of whether a specific voice is included (see step S19 in FIG. 4 ) and the generation and output of re-guidance voice data (step S20 in FIG. 4 ) are performed by the processing unit 21 of the server SV. However, it is also possible to configure the determination of whether a specific voice is included and the generation and output of re-guidance voice data to be performed entirely by the target terminal device T. In this case, it is preferable to have an external server perform only the search for the route along which the target moving object will travel and the generation of the corresponding guidance voice data. In this case, the target terminal device T determines whether a specific voice is included and generates and outputs the re-guidance voice based on the determination result. Therefore, even if connection to the external server cannot be established due to, for example, an inability to connect to the network NW, the processing in the target terminal device T can reduce the amount of information collected as sound while still allowing the content of the guidance voice to be recognized reliably.

[0044] Furthermore, it is also possible to record programs corresponding to each flowchart shown in FIG. 4 on a recording medium such as an optical disk or a hard disk, or to obtain them via a network such as the Internet, and then read and execute them on a general-purpose microcomputer or the like, thereby causing the microcomputer or the like to function as the processing unit 6 or processing unit 21 according to the embodiment.

[0045] Furthermore, the specific voice indicating that the guidance voice was not audible may be changed using known means such as machine learning. More specifically, for example, if the voice analysis results of the embodiment do not include the specific voice and therefore no re-guidance voice is provided, but the passenger operates the terminal device to play the guidance voice again, a word (term, etc.) is extracted based on the voice analysis results previously obtained, and a candidate flag for the specific voice is set for the extracted result. Then, by configuring the word to be added to the specific voice when multiple candidate flags are set, the specific voice can be added later. Similarly, a button for stopping the voice being played may be provided, and the specific voice may be deleted by setting a deletion flag for the corresponding specific voice. Furthermore, the specific voice may be configured to distinguish (identify) individual passengers based on their voices or information specific to the terminal device, and a specific voice tailored to each individual may be set.

[0046] Furthermore, although this embodiment has been given as an example of application to navigation, the present invention is not limited to this and can be applied to devices with voice recognition functions, such as for listening back when reading out weather forecasts or news on a smart speaker or smartphone. [Explanation of symbols]

[0047] 1 First output means (guidance voice output control unit) 2. Sound collection means (sound collection and transmission unit) 3. Second output means 6, 21 Processing section 10 Speakers 21b Guidance voice generation unit 21c Voice Recognition Unit S Information provision device T, T1, T2, T3, Tn terminal equipment SV Server

Claims

1. a first output means for outputting the information to be provided by sound; a sound collection means for collecting a sound after the start of output of the provided information; a second output means for outputting, by sound, corresponding information corresponding to the provided information based on a determination result as to whether a predetermined specific sound is included in the collected sound; an adding means for adding, when an operation to output the provided information again is performed, a word extracted from the sound based on an analysis result of the sound collected up until the operation is performed, as a new specific sound; Equipped with The second output means outputs the corresponding information by sound based on the determination result of whether the specific sound and the newly added specific sound are included in the collected sound.

2. 2. The information providing device according to claim 1, a transmitting means for transmitting sound data corresponding to the collected sound to an external device; an acquisition means for externally acquiring the correspondence information based on the determination result corresponding to the transmitted sound data; Further provided with The information providing device is characterized in that the second output means outputs the acquired corresponding information by sound.

3. 2. The information providing device according to claim 1, a determination means for determining whether the specific sound and the newly added specific sound are included in the collected sound; a generating unit that generates the correspondence information based on the determination result by the determining unit; Further provided with The information providing device is characterized in that the second output means outputs the generated corresponding information by sound.

4. 4. The information providing device according to claim 1, The information providing device is characterized in that the sound collecting means collects sounds until a predetermined time has elapsed after the output of the provided information by sound has ended.

5. 5. The information providing device according to claim 1, The information providing device is characterized in that the content of the corresponding information is the same as the content of the provided information.

6. 5. The information providing device according to claim 1, 1. An information providing device, wherein the corresponding information corresponding to the provided information of simplified content is the provided information of unsimplified content.

7. 7. The information providing device according to claim 1, The information providing device is characterized in that the second output means outputs the corresponding information by sound at a volume that is louder than the volume at which the first output means outputs the provided information.

8. 8. The information providing device according to claim 1, The information providing device is characterized in that the specific voice is a voice of a person who receives the provided information.

9. An information providing method executed in an information providing device including a first output means, a sound collecting means, a second output means, and an adding means, a first output step of outputting the information to be provided by sound from the first output means; a sound collection step of collecting sound by the sound collection means after the start of output of the provided information; a second output step of outputting, by the second output means, corresponding information corresponding to the provided information based on a determination result as to whether a predetermined specific sound is included in the collected sound; an adding step of adding, by the adding means, new specific sounds based on the sounds collected up to the instruction to output the correspondence information, and using the new specific sounds to generate the determination result after the addition; an adding step of adding, when an operation to re-output the provided information is performed, a word extracted from the sound based on an analysis result of the sound collected up until the operation is performed, as a new specific sound by the adding means; Including, In the second output step, the corresponding information is output by sound from the second output means based on the determination result of whether the specific sound and the newly added specific sound are included in the collected sound.

10. Computer, a first output means for outputting the information to be provided by sound; a sound collection means for collecting sound after the start of output of the provided information; a second output means for outputting, by sound, corresponding information corresponding to the provided information based on a determination result as to whether a predetermined specific sound is included in the collected sound; and an adding means for adding, when an operation to re-output the provided information is performed, a word extracted from the sound based on an analysis result of the sound collected up until the operation, as a new specific sound; An information providing program that functions as An information providing program characterized by causing the computer functioning as the second output means to function to output the corresponding information by sound based on the determination result of whether the specific sound and the newly added specific sound are included in the collected sound.

Images