JPH11337366A - System and method for navigation as well as recording medium with recorded software for navigation - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the efficiency of operation by changing an answerback according to conditions, in a technique related to a navigation operation using a speech recognition operation. SOLUTION: In a processing part 41, a processing operation related to a navigation operation is performed according to words and phrases which are recognized by a speech recognition part 14. An answerback part 42 answers back a message from a display screen, a speech synthesizer circuit or the like installed in the processing part 41. A display control part 43 displays a basic screen and a menu screen. A control part 44 performs the change of a setting operation and the answerback of a predetermined message, and it displays what kinds of chices are available regarding the setting operation when a speech is uttered on the menu screen. In addition, the control part 44 changes the content of the answerback according to a condition.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to navigation using voice recognition, and more specifically,
The operation efficiency is improved by changing the answer back according to conditions.

[0002]

2. Description of the Related Art In recent years, a navigation system has been known as an electronic apparatus for automatically guiding a moving body represented by an automobile. The navigation system calculates the current position (own vehicle position) of the installed vehicle (own vehicle) using radio waves from artificial satellites and gyros, and calculates the current vehicle position on a display screen such as a liquid crystal display panel. While displaying computer graphics on a map, it guides the user where to turn next.

There is also known an example in which a speech recognition technique is applied to such a navigation system, and the navigation system is operated by uttering (uttering) various predetermined phrases. Although various related technologies have been proposed for such speech recognition, typically, data such as feature parameters and waveforms representing features of each word to be recognized, that is, a dictionary for recognition is prepared in advance. deep. Then, the speech input from the microphone is converted into a digital signal, and the utterance is recognized by performing pattern matching with the above-described recognition dictionary.

When the navigation system is controlled by such voice recognition, words determined in a step-by-step manner are sequentially spoken according to announcements from the navigation system while tracing the hierarchical structure of menus and the like. You have to reach the functionality you need.

[0005] In the middle of such an operation, a message such as an announcement as to what operation to perform next or an announcement as to the result of executing some processing is given on the synthesized voice or on the screen. Is output as a character string. In this manner, a message output by the navigation system in response to a user operation or outputting such a message is referred to as answerback.

Conventionally, with regard to the contents of the answer back, it is determined whether or not the answer back is performed for each recognized phrase, and the contents of the answer back are determined for each individual phrase. Also, what kind of operation is fixed to one type. further,
When the uttered word could not be recognized, a standard answer back such as "cannot be recognized" was output, regardless of what kind of operation was in progress.

[0007]

However, in a system in which operations such as utterance of a word are sequentially performed in order to perform a target process, as described above, a situation is determined according to the uttered word. If the same answer back is output regardless of the system, the system is slow to respond as the user gets used to it, and there is a problem that the user interface becomes less comfortable. In addition, when the same answer back is repeated, a user wastes time to understand and accept the answer back and a screen space for displaying other information, thereby reducing operation efficiency. There was also.

That is, while a certain phrase is uttered,
When the change caused by the execution of a certain operation is clearly visible on the screen, the answerback is annoying for the user, which impairs the operational comfort.

[0009] On the other hand, however, in such a system that does not give answer back in any situation, on the other hand, the user may encounter a situation where he or she does not know what to say next. Therefore, efficient operation becomes difficult.

[0010] In a system that performs a fixed operation for one phrase regardless of the situation, different phrases must be assigned to each operation. For this reason, the number of words that the user must remember is increased, and not only is the usability inferior, but also the problem is that the capacity of the recognition dictionary increases and the recognition accuracy decreases.

Furthermore, if the answer back and operation when the phrase is not recognized are fixed regardless of the situation, the user can simply know that the phrase was not recognized, and in that situation, Is not given a hint as to what operation to perform. Such a response in conventional systems is unkind,
There was a potential need for a navigation system that would be confusing to the user and easier to operate.

The present invention has been proposed in order to solve the above-mentioned problems of the prior art. It is an object of the present invention to change the presence / absence of answer back in a technology related to navigation using voice recognition. This is to improve the efficiency of the operation. Another object of the present invention is to facilitate operation by performing different processing according to conditions even when the same word is uttered. Another object of the present invention is to facilitate the operation by changing the contents of answerback according to conditions.

[0013]

In order to achieve the above-mentioned object, a first aspect of the present invention provides a means for recognizing spoken words by speech and a process related to navigation in accordance with the recognized words. A navigation system comprising means for performing the answering process and means for answering the message in accordance with the processing performed, wherein the navigation system includes control means for controlling whether to answer back in accordance with a predetermined condition. And The invention of claim 8 is
The invention of claim 1 is taken from the viewpoint of a method,
A navigation method including a step of voice-recognizing an uttered word, a step of performing navigation-related processing in accordance with the recognized word, and a step of answerbacking a message in accordance with the performed processing are determined in advance. The method includes a control step of controlling whether to perform answer-back according to the set condition. According to a fourteenth aspect of the present invention, the invention of the first and eighth aspects is viewed from the viewpoint of a recording medium on which computer software is recorded, and navigation software for navigating a moving object using a computer is recorded. On the recording medium, the software causes the computer to perform speech recognition of the spoken word, perform navigation-related processing according to the recognized word, and answer-back the message according to the performed processing. It is characterized in that whether to answer back or not is controlled according to the given condition. According to the invention of claims 1, 8, and 14, even when processing according to the same phrase, answerback is performed in accordance with the situation such as which screen was uttered in which situation and which phrase was uttered before that. They come and go. Thereby, while giving necessary information to the user, it is possible to eliminate an unnecessary answer back by a screen or a voice, to solve the troublesomeness of the operation, and to improve the efficiency of the operation.

According to a second aspect of the present invention, in the navigation system according to the first aspect, means for displaying a basic screen and a menu screen, and for each of the words, a message and a flag relating to the processing are stored. The control means, when the flag corresponding to the word is in a predetermined state, when the word is uttered on the basic screen, answers the message, and the word is displayed in the menu. When the message is uttered on the screen, the message is controlled not to answer back. According to a ninth aspect of the present invention, the invention of the second aspect is viewed from the viewpoint of a method. In the navigation method according to the eighth aspect, a step of displaying a basic screen, a step of displaying a menu screen, and For each phrase, a message involved in the processing,
And the flag is stored in advance, and the control step includes, when the flag corresponding to the word is in a predetermined state, answering the message when the word is uttered on the basic screen, When a word is uttered on the menu screen, the message is controlled not to answer back. According to the second and ninth aspects of the present invention, it is determined whether the presence or absence of answer back is changed between when speaking from a basic screen such as a map display around the own vehicle and when speaking from a menu screen such as a hierarchical menu. Control can be performed finely, so that excellent operation efficiency can be realized according to the content of the processing.

According to a third aspect of the present invention, there is provided a navigation system, comprising: means for recognizing a spoken word; and means for performing navigation-related processing in accordance with the recognized word.
Even when the same phrase is recognized, a control means is provided for controlling so as to perform a different process according to a predetermined condition. According to a tenth aspect of the present invention, there is provided the navigation method, wherein the invention of the third aspect is viewed from the viewpoint of a method, and a step of voice-recognizing an uttered word and phrase,
Steps to perform navigation-related processing according to the recognized words, and even if the same words are recognized,
Controlling to perform a different process according to a predetermined condition. According to a fifteenth aspect of the present invention, the inventions of the third and tenth aspects are viewed from the viewpoint of a recording medium on which computer software is recorded, in which navigation software for navigating a moving object using a computer is recorded. In the recording medium, the software causes the computer to perform speech recognition of the spoken word and perform processing related to navigation in accordance with the recognized word. Even when the same word is recognized, a predetermined condition is used. And different processing is performed according to According to the third, tenth, and fifteenth aspects of the present invention, even when the same word is recognized, different processing is performed depending on the situation such as on which screen and in which situation the speech was uttered and before that. Do. For this reason, it is less necessary for the user to memorize different words for each situation such as "this situation is the word", and the operation can be performed more intuitively, which facilitates the operation. Further, since the same word can be reused for different processing, versatility and flexibility are improved in creating a menu structure.

According to a fourth aspect of the present invention, in the navigation system according to the third aspect, there is provided means for displaying a basic screen and a menu screen. When uttered on the screen, change the settings and answer back a predetermined message, and when a phrase for changing the setting of the navigation system is uttered on the menu screen, The configuration is such that a setting screen indicating whether there is an appropriate option is displayed. According to the fourth aspect of the present invention, even if the same phrase for changing the setting such as the display color of the map is used, when the user directly speaks from the basic screen, the setting is changed and the message is backed up. And a setting screen showing what options are available for the setting. In other words, speaking directly from the basic screen is a familiar usage, so change the setting without showing other options on the setting screen, recognize the words and phrases, and confirm that the change was made. Notify the user with a message. On the other hand, uttering while following the menu screen is an unfamiliar usage, so on the setting screen you indicate what options are available and let you select it, and instead, you have changed the settings and selected the options. No message is output because it is clear from the setting screen. As described above, by performing different processing according to how much the user is used, the setting of the navigation system can be easily changed.

According to a fifth aspect of the present invention, there is provided a means for recognizing a spoken word, a means for performing navigation-related processing in accordance with the recognized word, and a means for answerbacking a message in accordance with the performed processing. And a control means for changing the contents of a message to be answered according to a predetermined condition. Claim 1
According to a first aspect, the invention of claim 5 is viewed from the viewpoint of a method. In the first aspect, a step of voice-recognizing an uttered word and a step of performing a process related to navigation according to the recognized word are included; A navigation method that includes a step of answerbacking a message according to the performed processing, characterized in that the method includes a step of changing the content of the message to be answered back according to a predetermined condition. Claims 5 and 1
According to the first aspect of the invention, by changing the content of the answer-backed message to an accurate content according to the situation, the user can easily understand the content to be uttered next, and the operation efficiency is improved.

According to a sixth aspect of the present invention, there is provided the navigation system according to the fifth aspect, further comprising means for storing a message to be output when the phrase is recognized, for each of the phrases. I do. Claim 1
According to a second aspect, the invention of the sixth aspect is viewed from the viewpoint of a method. In the navigation method according to the eleventh aspect, a message to be output when the phrase is recognized is provided for each of the phrases. It is characterized in that it is stored in advance. In the invention of claims 6 and 12,
In a case where a series of processes is started by the utterance of a word, the user can be informed of what should be uttered next by a message corresponding to the word, thereby facilitating the operation.

According to a seventh aspect of the present invention, in the navigation system according to the fifth or sixth aspect, a message to be output when another word spoken subsequent to the recognition of the word cannot be recognized. And means for storing each of the words. According to a thirteenth aspect of the present invention, the invention of the seventh aspect is viewed from the viewpoint of a method. In the navigation method according to the eleventh or twelfth aspect, another word uttered after the word is recognized is recognized. A message to be output when recognition is not possible is stored in advance for each of the phrases. The invention of claim 16 is
The invention according to claims 7 and 13 is regarded as a recording medium on which computer software is recorded. In a recording medium on which navigation software for navigating a moving object using a computer is recorded, the software is The computer causes the spoken word to be speech-recognized, performs navigation-related processing in accordance with the recognized word, causes the message to be answered according to the performed processing, and outputs when the word is recognized. And a message to be output when another word spoken after the word was recognized could not be recognized, and stored in advance for each of the words. Using the message of Characterized in that it makes changing the contents of the message to click. According to the seventh, thirteenth, and sixteenth aspects of the present invention, the content of the message to be answered when the phrase cannot be recognized changes according to the preceding phrase. In other words, a series of processes is started by the preceding phrase, but even if the user does not recognize the phrase, for example, by uttering an incorrect phrase, it is necessary to determine what should be originally uttered. That is, the user can be notified by a message according to the content of the process. For this reason, it is not necessary to output instructions such as notes to the user so that they are listed at once, and an easy-to-use user interface is realized.

[0020]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, an embodiment of a navigation system according to the present invention (hereinafter referred to as "embodiment") will be specifically described with reference to the drawings. In each of the drawings used in the following description, the same members and members of the same type as those in the drawings described earlier are denoted by the same reference numerals, and description thereof will be omitted.

This embodiment is realized using various hardware devices and a computer controlled by software. In this case, the software is created by combining the instructions according to the description in this specification, and the common parts with the above-described prior art use the technique described in the prior art. Further, the software includes not only program codes but also data prepared in advance for use in executing the program codes. The software realizes the effects of the present invention by utilizing a physical processing device such as a CPU and various chipsets incorporated in the navigation system.

However, the specific hardware and software configuration for realizing the present invention can be variously changed. For example, depending on the circuit configuration and the processing capability of the CPU, a certain function may be realized by a physical electronic circuit such as an LSI, or may be realized by software. Regarding the part that uses software, various forms of software, such as a compiler, an assembler, and a microprogram, can be considered. A recording medium on which software for realizing the present invention is recorded is also an aspect of the present invention by itself.

As described above, there are various possible modes for realizing the present invention using a computer. In the following, a virtual circuit block for realizing individual functions included in the present invention and the embodiments will be described. The invention and embodiments will be described.

[1. Configuration of First Embodiment] The first embodiment relates to a navigation system capable of performing both an operation of sequentially uttering following a menu hierarchy and an operation of directly speaking a word representing an operation desired regardless of the menu hierarchy. Things.

That is, in the first embodiment, as shown in FIG. 3, from the screen displaying the map, "menu" → "setting" → "screen display" → "progress direction" → "heading up" As shown in FIG. 4, when the operation is sequentially performed in accordance with the hierarchy and when the shortcut is directly performed from the screen displaying the map by saying “heading up”, the processing performed and the message are answered. This is an example in which whether or not they are backed up is different.

[1-1. FIG. 1 is a conceptual diagram showing an example of what kind of hardware this embodiment can be constructed on. In this example, a voice recognition unit V and a navigation unit N are connected to each other, and show a part of hardware used for realizing this embodiment.

The ROM in the voice recognition unit V
(V1) stores a recognition dictionary V2. Also,
There is a CD-ROM drive in the navigation unit N, and the CD-ROM drive inserted in this CD-ROM drive
In the D-ROM (N1), a database N3 including various data is recorded in addition to the application programs for realizing the functions of the navigation system. The application program N4 for realizing the function of the navigation system of this embodiment is a CD.
-Read from the ROM (N1) and
2 is recorded.

FIG. 2 is a functional block diagram showing a specific configuration of this embodiment realized using hardware as shown in FIG. That is, in this embodiment, an absolute position / azimuth detecting unit 1, a relative azimuth detecting unit 2, a vehicle speed detecting unit 3, a main CPU and its peripheral circuits 4, a memory group M, an output unit 10, an input unit 11 and
CD-ROM control unit 12, FM multiplex reception and processing unit 1
3 and a voice recognition unit 14.

Of these, the absolute position / azimuth detecting unit 1
This is a means for calculating the absolute position coordinates and azimuth of the current position of the automobile (own vehicle) on the ground surface by receiving the GPS radio wave transmitted from the PS satellite. The relative azimuth detecting unit 2 is a part that detects the relative azimuth of the vehicle using a gyro or the like. The vehicle speed detection unit 3 is a part that calculates a vehicle speed by processing a vehicle speed pulse obtained from the vehicle.

The CD-ROM control section 12 is a section for reading various information such as a navigation system program and road map data from the CD-ROM. The FM multiplex reception and processing unit 13 is a part that receives a FM broadcast of a radio by switching a plurality of antennas according to a reception state. The speech recognition unit 14 is a speech recognition unit including a feature parameter or waveform data representing a feature of each phrase to be recognized, that is, a recognition dictionary 141 (corresponding to the recognition dictionary V2 in FIG. 1).
By converting the voice input from the microphone into a digital signal and performing pattern matching with the dictionary for recognition 141,
This is a means for recognizing the uttered phrase.

[1-2. Role of Main CPU and its Peripheral Circuit] The main CPU and its peripheral circuit 4 are parts that play a role of a control circuit for controlling the entire navigation system. It plays the role of the answer back unit 42, the display control unit 43, and the control unit 44.

The processing section 41 is a means for performing processing related to navigation in accordance with the words and phrases recognized by the voice recognition section 14. The answerback unit 42 is a means for answerbacking a message from a display screen or a voice synthesis circuit provided in the output unit 10 in accordance with the processing performed by the processing unit 41.

The display control section 43 is a section for controlling what content is displayed on the display screen provided in the output section 10. The display control section 43 displays a map around the own vehicle on such a display screen. Means for displaying a basic screen and a menu screen for displaying various stages of a hierarchical menu.

The control unit 44 has the following three roles. The first role is to control whether or not to answer back according to a predetermined condition. Here, the CD-ROM control unit 12
Has a record corresponding to each of the phrases, and each record stores a message and a flag used in a process corresponding to the phrase.

Specifically, the control unit 44 performs the following control on the answer back unit 42 when the above-mentioned flag is in a predetermined state, that is, when the flag has a value. . That is, when the word corresponding to the flag is uttered on the basic screen displayed by the display control unit 46, the control unit 44 causes the message described above to answer-back, and the word is sent to the display control unit 46. When the user speaks on the displayed menu screen, control is performed so that the message is not answered. The second role of the control unit 44 is to control the processing unit 41 so as to perform different processing according to a predetermined condition even when the same phrase is recognized.

In other words, the control unit 44 combines the first and second roles with the processing unit 41 and the answerback unit 4.
2, the following control is performed. That is, when a phrase such as “heading up” for changing the setting of the navigation system is uttered on the basic screen, the control unit 44 changes the setting and performs answerback of a predetermined message. Let On the other hand, when a word for changing the setting of the navigation system is uttered on the menu screen, the control unit 44 displays a setting screen indicating what options are available for the setting.

The third role of the control unit 44 is to change the contents of the message to be answered according to a predetermined condition. That is, the messages stored in the record for each phrase in the database N3 are, specifically, the following two types of messages composed of character strings. One is a message to be output when the word is recognized, and the other is to be output when another word spoken subsequent to the recognition of the word cannot be recognized. This message is referred to as a NOT message.

For example, in a record corresponding to the phrase "hotel", a first message such as "please say the name of the hotel" and a NOT message such as "do you designate by the official name?" It is conceivable to keep it.

It should be noted that, in addition to the above, the processing unit 41
Utilizing the calculated own-vehicle position, the present position of the car is displayed on a computer graphics map, and various navigation processes such as providing route guidance in accordance with a user instruction are performed. And I
It is configured to input and output various information using a user interface (not shown) including an / O control circuit and a driver. Further, the main CPU and its peripheral circuit 4 perform the above-described various processes when the memory group M
And an output unit 10 and an input unit 11.

[1-3. Other Configurations] That is, the memory group M includes various memories necessary for the operation of the navigation system according to the present embodiment, that is, the ROM 5 storing a BIOS, a boot-up program, and the like.
It includes a DRAM 6 used for a work area, an SRAM 7 as a nonvolatile memory for recording information such as a registration file, and a VRAM 8 used for video display.

The output unit 10 is a unit for outputting various information such as a map and an operation menu using a liquid crystal display panel, a voice synthesizer, or the like. It is a part for inputting various information.

[2. Operation of the First Embodiment] The first embodiment configured as described above operates as follows. [2-1. Contents of recognition dictionary] First, recognition dictionary 141
Contains all the data of the words and phrases used in each level of the menu, and always displays all the data on the basic screen such as displaying the map around the vehicle, even when operating through the menu level. Is recognizable.

This means that when a menu is not displayed on the screen, a word used in a certain part of the menu is recognized even if it is spoken. Similarly, a certain part of the menu hierarchy is displayed. This means that even if you utter words used in other parts that are not displayed unless you branch in the other direction on the main menu side, it will be recognized.

[2-2. Recognition of Words] Then, when there is an utterance from the user, the voice recognition unit 14
And recognizes the uttered phrase, and passes the number of the phrase to the main CPU and its peripheral circuit 4. Here, the operations of the main CPU and its peripheral circuit 4 are realized by an application program for realizing the functions of the navigation system.

[2-3. Processing by Application Program] That is, in these application programs, processing corresponding to the number received as a phrase number is programmed in advance, and the movement is executed. In this case, what kind of operation is programmed for each word number basically has a one-to-one correspondence with the number.

For example, it is assumed that there is a menu in which a word "system" can be uttered in a certain part of the menu hierarchy, and when the word is uttered, a menu of the next lower layer is displayed. In such a case, when the phrase "system" is uttered in the menu hierarchy of the above-described portion, or when the other is uttered while displaying a map around the own vehicle, for example, Also, the same “menu one level lower” described above is displayed.

[2-4. Example of operation by utterance] However, since the words at the bottom of the menu hierarchy are for specific operations, it depends on whether they are said directly on the map or next to other words on the menu Program to change the movement.

For example, FIGS. 3A to 3F are conceptual diagrams showing a flow of arriving at an operation "heading up" by sequentially uttering predetermined words in accordance with a menu hierarchy. The setting screen (e) displayed by speaking the “direction” indicates that there is an option of “north up” in addition to “heading up”.

On the other hand, FIGS. 4 (a) and 4 (b) show that the operation of "heading up" can be easily performed by simply speaking "heading up" directly from the basic screen displaying the road map around the own vehicle. In this example, on the screen (b) after "Heading Up" is spoken, the other options described above are not displayed, and a message indicating that the traveling direction is set to Heading Up is displayed. Have been.

In the database N3, information required when the application program executes the process corresponding to the given phrase number, such as a message output on the screen, is associated with each phrase number. Since the data is stored as described above, the application program uses the CD-ROM control unit 12 to appropriately read the data and execute a process corresponding to the phrase.

FIG. 5 is a conceptual diagram showing an example in which the number of a phrase recognized using the recognition dictionary 141 is processed by the above-described application program. In this example, the word “Gamen leopard” recognized using the recognition dictionary 141 is passed to the application program as the number 8 and the word “heading up” is passed to the application program as the number 19.

As described above, the phrase code of the recognized phrase is sent from the speech recognition unit 14 to the main CPU and its peripheral circuits 4.
The control unit of the main CPU and its peripheral circuit 4 determines whether or not to perform answerback according to predetermined conditions and what kind of processing is to be performed by the answerback unit 42 and the processing. The section 41 is controlled.

More specifically, for the 19th "heading up", as shown in FIG. 5, when the user speaks on the basic screen, the setting is changed and a predetermined message answer back is performed. . On the other hand, when the same word is uttered on the menu screen, a setting screen indicating what options are available for the setting is displayed.

Thus, the same "heading up"
Even if you say the phrase, a different screen will be displayed depending on whether or not it was spoken directly from the map (basic screen). . "Is read out from the database N3 in association with each word number.

[2-5. Control by Flag] In the database N3, as described above, records that change the presence / absence of answer back between the case where the utterance is made from the menu screen and the case where the utterance is made directly from the basic screen are stored in the record for each phrase. Among them, a predetermined specific value is set in the flag. Then, the application program does not answer back when the word of this flag has the specific value described above when uttered from the menu screen, but does not answer back when it is generated directly from the basic screen. The presence or absence of answer back is changed.

[3. Effect of First Embodiment] As described above, in the first embodiment, even when processing according to the same word or phrase is performed, the control unit 44 operates to determine which screen and in which situation the utterance was made, The answerback unit 42 outputs or does not output the answerback according to the situation such as which word is spoken. Thereby, while giving necessary information to the user, it is possible to eliminate an unnecessary answer back by a screen or a voice, to solve the troublesomeness of the operation, and to improve the efficiency of the operation.

In particular, in the first embodiment, it is determined whether the presence or absence of answer back is changed between when speaking from a basic screen such as a map display around the own vehicle and when speaking from a menu screen such as a hierarchical menu. Since the control unit 44 can finely control with the flag stored in the database N3, excellent operation efficiency can be realized according to the content of the processing.

Specifically, in the first embodiment, even if the same word for changing the setting such as the display color of the map is used, the control unit 4
By the function of 4, when speaking directly from the basic screen, the setting is changed and the message is backed up,
When the user speaks from the menu screen, a setting screen indicating what options are available for the setting is displayed. In other words, speaking directly from the basic screen is a familiar usage, so change the setting without showing other options on the setting screen, recognize the words and phrases, and confirm that the change was made. Notify the user with a message.

On the other hand, uttering while following the menu screen is an unfamiliar usage, so that the user can select and show what options are available on the setting screen. The message is not output because the selection is clear from the setting screen. in this way,
By performing different processing depending on how familiar the user is, it becomes easier to change the settings of the navigation system.

[4. Second Embodiment] A second embodiment is an example in which a different processing is performed according to a condition even when the same word is recognized in a navigation system configured substantially the same as the first embodiment described above. It is.

That is, in the second embodiment, when there is a menu item or a process that can be expressed by the same phrase, only one phrase data is stored in the recognition dictionary of the voice recognition unit 14. When the phrase is recognized and the phrase code is passed to the main CPU and its peripheral circuit 4, the control unit 44 determines which screen is displayed at that time.
Different operations programmed as the processing unit 41 are selectively used depending on the condition of the screen and what the last (last) recognized word is.

[4-1. (If scrolling)
FIG. 6 is a flowchart showing an example in which different processing is performed in accordance with the condition even when the same phrase is uttered. That is, the voice recognition unit 14 uses the same “mokuteki”
Even if you recognize the phrase (destination) (step 1
1) When the map is displayed on the screen where the map is displayed instead of the menu screen (step 12), and the location is displayed on the map by scrolling (moving) to another location other than the current vehicle position. (Step 1
3), the control unit 44 controls the processing unit 41 to perform a process of setting a traveling route with the currently displayed location as a destination (step 14).

[4-2. When scrolling is not being performed] On the other hand, when a map is not displayed (step 12), for example, when a hierarchical menu is displayed or when the vehicle is not scrolling from the current position (step 1).
3) If the same phrase "mokuteki" is recognized,
A portion corresponding to the phrase in the hierarchical menu is displayed (step 15).

[4-3. Effect of Second Embodiment] As described above, in the first embodiment and the second embodiment, even when the same word is recognized, which screen is used in which situation and which word is uttered before that. Different processing is performed depending on the situation such as whether or not the processing has been performed. For this reason, it is less necessary for the user to memorize different words for each situation such as "this situation is the word", and the operation can be performed more intuitively, which facilitates the operation. Further, since the same word can be reused for different processing, versatility and flexibility are improved in creating a menu structure.

[5. Third Embodiment] In the third embodiment, in a navigation system having substantially the same configuration as that of the first and second embodiments, the same situation that a spoken word cannot be recognized is recognized before the navigation system. In this example, a different message is answer-backed depending on the condition of the phrase.

Here, data of various facilities such as a hotel, an amusement park, a family restaurant (family restaurant) are registered in the database N3, and the preceding utterance "hotel" is recognized, and several hotels are displayed in a list. The user then selects one of the hotels by speaking the name of the hotel.

[5-1. Selection of Record] FIG. 7 is a flowchart showing a processing procedure in such a case. That is, when the voice recognition unit 14 recognizes the word "hotel" (step 21), the main CPU and its peripheral circuit 4 and the application program of the navigation system running thereon receive the word code as a recognition result.

Then, the control section 44 performs, for example, a process of extracting some hotel data from the database N3 as a process corresponding to the phrase code, and selects a record corresponding to the phrase on the database N3. (Step 22). The records on the database N3 include, in addition to the hotel records, an amusement park, a family restaurant, a convenience store, and a gas station, in accordance with which words the user utters and what kind of facility is selected. There can be various records.

Here, the control unit 44 selects the record RX corresponding to the "hotel" selected in this way (step 22). Such a selection can be made by retrieving the corresponding record from the database N3 based on the recognized phrase code.

[5-2. Output and utterance of message] Then, the answer back unit 42 displays the message M1 included in the record RX, that is, "Please say the name of the hotel", on the screen or outputs it by voice synthesis, that is, answer back ( Step 23).

The user can use the answer back to
Since it is understood that the name of the hotel should be uttered, the phrase indicating the name of the hotel is uttered. Then, the speech recognition unit 14 attempts the recognition (step 24), and when the phrase is recognized (step 25), the processing unit 41 outputs the recognized map around the hotel to the output unit 1 via the display control unit 46.
0 is displayed on the display screen (Step 26).

[5-3. Processing when not recognized)
On the other hand, when the user utters an incorrect phrase, the speech recognition unit 1
Since there is no word in the recognition dictionary 141 corresponding to the uttered word in the recognition dictionary 141, a code indicating that the word could not be recognized is sent from the voice recognition unit 14. In this case, according to the control of the control unit 44, the answer back unit 4
2 is the message M2 included in the selected record RX, that is, "Is the instruction designated by the official name?"
Is output (step 27).

As a result, the user is given a hint for speaking a correct phrase, and can try an efficient operation such as speaking a phrase that is considered to be a formal name.

[5-4. Other examples of messages] Of course, the messages included in the record may be prepared differently depending on what kind of facility is selected. For example, "On-Dry Adjust" (volume adjustment On the screen where the volume is adjusted by uttering the phrase "), if the uttered phrase cannot be recognized, a NOT such as" Please say loud or loud "
Answerback the message. Another example of a NOT message corresponding to “hotel” is “Do you have“ hotel ”in the head? And so on.

In addition to the messages included in the selected record, such as these messages M1 and M2,
It is possible to prepare a common fixed message on the screen related to the search, and if the message included in the selected record and such a fixed message are alternately output, more hints will be given to the user That means
A better user interface.

[5-5. Effect of Third Embodiment] As described above, in the third embodiment, the contents of the message to be answered are changed to accurate contents according to the situation by the operation of the database N3 and the control unit 44. The contents to be uttered next can be easily understood, and the operation efficiency is improved.

In particular, in the third embodiment, when a certain series of processing is started by the utterance of a word, it is possible to inform the user of what should be uttered next by a message corresponding to the word. Operation can be easily performed.

Specifically, in the third embodiment, the content of a message to be answered when a phrase cannot be recognized changes according to the preceding phrase. That is,
The preceding phrase triggered a series of actions,
Even in the case where the user does not recognize the word, for example, by uttering a wrong word, the user can be notified of what should be uttered by a preceding word, that is, a message corresponding to the content of the processing. For this reason, it is not necessary to output instructions such as notes to the user so that they are listed at once, and an easy-to-use user interface is realized.

In particular, if the respective inventions as exemplified in the first to third embodiments are used in combination, even when the same word is uttered, the contents of the processing based on the word and the answer back of the word The content of the answer back when the content or phrase cannot be recognized changes.

Therefore, regarding the user interface using voice recognition, not only can the navigation system guide the user in an easy-to-understand manner to reduce confusion, but it is also easy for beginners and efficient and troublesome for experienced users. A user interface can be realized. As a result, the navigation system can be operated as if talking with a human, and an intuitive user interface can be realized.

[6. Other Embodiments] The present invention is not limited to the above-described embodiments, but includes other embodiments as exemplified below. For example, the navigation system of the present invention can be used not only for a so-called car navigation system mounted on an automobile, but also for other types of moving objects such as motorcycles.

In the embodiment described above, the NOT messages are stored in the database N3 one by one for each word and phrase, but the format of the database is free. In addition, two or more NOT messages can be prepared for each phrase, and when a state in which the phrase cannot be recognized continues, these messages can be sequentially displayed. Further, the message or the NOT message may not be stored in the database but may be stored in the application program.

Further, a specific algorithm of speech recognition,
The words to be recognized, the contents of the answer back, the contents of the basic screen and menu screen, the format of the flag, whether to perform answer back and the contents of the conditions for changing the contents, etc.
The invention is not limited to the examples described in the embodiments, and can be freely determined.

[0084]

As described above, according to the present invention, it is possible to improve the operation efficiency by changing the answer back according to the conditions.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a hardware configuration according to a first embodiment of the present invention.

FIG. 2 is a functional block diagram showing a specific configuration of the first embodiment of the present invention.

FIG. 3 is a conceptual diagram showing an operation procedure when sequentially uttering words while following a hierarchically configured menu screen in the first embodiment of the present invention.

FIG. 4 is a conceptual diagram showing an operation procedure when directly speaking a word at the bottom of a menu hierarchy from a basic screen displaying a map in the first embodiment of the present invention.

FIG. 5 is a conceptual diagram showing that processing according to the number of a recognized phrase is performed in the first embodiment of the present invention.

FIG. 6 is a flowchart illustrating an example of a processing procedure according to the second embodiment of the present invention.

FIG. 7 is a flowchart illustrating an example of a processing procedure according to a third embodiment of the present invention.

[Explanation of symbols]

 V: Voice recognition unit V1: ROM V2: Recognition dictionary N: Navigation unit N1: CD-ROM N2: Flash memory N3: Database N4: Application program 1: Absolute position / direction detection unit 2: Relative direction detection unit 3: Vehicle speed Detector 4 Main CPU and its peripheral circuits M Memory group 5 ROM 6 DRAM 7 SRAM 8 VRAM 10 Output unit 11 Input unit 12 CD-ROM control unit 13 FM multiplex reception and processing unit 14 ... Speech recognition unit 141 ... Recognition dictionary 41 ... Processing unit 42 ... Answer unit 43 ... Display control unit 44 ... Control unit

Claims (16)

[Claims] 1. A means for recognizing an uttered word by voice, means for performing a process related to navigation in accordance with the recognized word, and means for answerbacking a message in accordance with the executed process. A navigation system, comprising: a control unit that controls whether to perform answer-back according to a predetermined condition. 2. A means for displaying a basic screen and a menu screen, and means for storing, for each of the words, a message relating to the processing and a flag, wherein the control means comprises: When the corresponding flag is in a predetermined state, the message is answered when the word is uttered on the basic screen, and the message is not answered when the word is uttered on the menu screen. The navigation system according to claim 1, wherein the control is performed in the following manner. 3. A means for recognizing an uttered word and a means for performing navigation-related processing in accordance with the recognized word. Even if the same word is recognized, the means is determined according to a predetermined condition. A navigation system comprising control means for performing control so as to perform different processing. 4. A means for displaying a basic screen and a menu screen, wherein the control means, when a word for changing a setting of a navigation system is uttered on the basic screen, changes the setting, and When a word for changing the setting of the navigation system is uttered on the menu screen, a setting screen indicating what options are available for the setting is displayed. 4. The navigation system according to claim 3, wherein: 5. Means for recognizing a spoken word by voice, means for performing processing related to navigation in accordance with the recognized word, and means for answerbacking a message in accordance with the performed processing. A navigation system, comprising: a control unit that changes the contents of a message to be answered in response to a predetermined condition. 6. The navigation system according to claim 5, further comprising means for storing a message to be output when said phrase is recognized, for each of said phrases. 7. A means for storing, for each of said phrases, a message to be output when another phrase spoken subsequent to recognition of said phrase cannot be recognized. The navigation system according to claim 5 or 6, wherein 8. A navigation system comprising: a step of recognizing a spoken word; a step of performing a navigation-related process according to the recognized word; and a step of answerbacking a message according to the performed process. A navigation method, comprising: a control step of controlling whether to answer back according to a predetermined condition. 9. A step of displaying a basic screen, a step of displaying a menu screen, a message and a flag relating to the processing are stored in advance for each of the phrases, and the step of controlling includes: If the flag corresponding to the word is in a predetermined state, the message is answered when the word is uttered on the basic screen,
9. The navigation method according to claim 8, wherein when the word is uttered on the menu screen, the message is controlled not to answer back. 10. A step of voice-recognizing an uttered word and a step of performing navigation-related processing in accordance with the recognized word. Even if the same word is recognized, the same is performed in accordance with a predetermined condition. Controlling the vehicle to perform a different process. 11. A navigation system comprising: a step of recognizing an uttered word by voice; a step of performing a navigation-related process according to the recognized word; and a step of answerbacking a message according to the performed process. A navigation method, comprising: changing a content of a message to be answered according to a predetermined condition. 12. The navigation method according to claim 11, wherein a message to be output when the phrase is recognized is stored in advance for each of the phrases. 13. A message to be output when another word uttered subsequent to recognition of said word is not recognized is stored in advance for each of said words. The navigation method according to claim 11 or 12, wherein the navigation method is performed. 14. A recording medium on which navigation software for navigating a moving object by using a computer is recorded. The software causes the computer to recognize a spoken word by voice, and recognizes a process related to navigation. A record that records navigation software, characterized in that it is performed according to a given word, a message is backsacked according to the processing performed, and whether or not the backsack is controlled according to a predetermined condition. Medium. 15. A recording medium on which navigation software for navigating a moving object using a computer is recorded. The software causes the computer to recognize a spoken word by speech, and recognizes a process related to navigation. A recording medium on which navigation software is recorded, wherein the navigation software is performed in accordance with a given word and, even when the same word is recognized, different processing is performed in accordance with a predetermined condition. 16. A recording medium on which navigation software for navigating a moving object using a computer is recorded. The software causes the computer to recognize a spoken word by voice and recognizes a process related to navigation. A message to be answered according to the processing performed, a message to be output when the word is recognized, and a message to be output following the recognition of the word. And a message to be output when the phrase is not recognized is stored in advance for each of the phrases, and using these messages, a message to be answered according to a predetermined condition is used. Navigation software characterized by changing content Recording medium on which