JP4036966B2 - Navigation system and method, and recording medium recording navigation software - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an improvement in technology related to navigation. More specifically, the present invention can easily specify an operation to be performed by voice recognition regardless of a menu hierarchy and an utterance order.
[0002]
[Prior art]
2. Description of the Related Art In recent years, navigation systems are known as electronic devices that automatically perform route guidance for moving bodies represented by automobiles. The navigation system calculates the current position (vehicle position) of the mounted vehicle (own vehicle) using radio waves from a satellite or gyroscope, etc., and displays the position of the vehicle on a display screen such as a liquid crystal display panel. While displaying the computer graphics on the map, it will guide you where to turn next.
[0003]
There is also known an example in which a voice recognition technique is applied to such a navigation system and the navigation system is operated by uttering (speaking) various predetermined phrases. In such speech recognition, various related technologies have been proposed, but typically, data such as feature parameters and waveforms representing features for each word to be recognized, that is, a recognition dictionary is prepared in advance. deep. The voice input from the microphone is converted into a digital signal, and the spoken phrase is recognized by pattern matching with the recognition dictionary described above.
[0004]
When the navigation system is controlled by such voice recognition, conventionally, various operations are called from a hierarchical menu. In such a configuration, necessary functions must be reached by following the hierarchical structure of the menu and uttering words determined step by step in accordance with announcements from the navigation system.
[0005]
In order to realize such an operation of the navigation system, the recognition dictionary described above is composed of a plurality of tables according to the hierarchical structure of the menu. Then, a table corresponding to the position in the menu is read, and only words in the table are subjected to speech recognition. Here, FIG. 11 is a conceptual diagram showing the structure of a table in a conventional recognition dictionary.
[0006]
In this example, on a so-called basic screen in which a map around the vehicle is displayed on the display screen, only words such as “menu” registered in the table T10 are to be recognized. For example, in order to perform an operation of “heading up”, by first saying “menu” on the basic screen, the table T20 that roughly divides the contents of the menu is set as a recognition target. "Speaks." Similarly, when the table T50 and the table T40 are traced and the table T50 becomes a recognition target, it is possible to say “heading up” for the first time.
[0007]
That is, conventionally, the flow of what words can be spoken in what order after the first utterance from the basic screen is fixed in accordance with the menu hierarchy. Also, in terms of what words are to be recognized, for example, words that can be uttered from the basic screen are determined in advance, and even if words can be uttered in the order of “A” → “B”, “ It was not possible to speak in the reverse order of “B” → “A”.
[0008]
[Problems to be solved by the invention]
However, in the conventional technology as described above, there is a problem in that a plurality of words must be uttered in a fixed order in order to perform one operation, and thus the operation cannot be performed efficiently. That is, in order to use a certain function, an operation method in which a plurality of words are uttered in accordance with an announcement or the like is easy to understand, for example, for beginners, but an intermediate operation becomes less necessary as it gets used. For this reason, the user wants to perform the next operation rather quickly, and an interface that can operate more efficiently has been awaited.
[0009]
Further, the conventional technology as described above recognizes the word that becomes the first command, and then executes a fixed flow of operation (flow) that follows. You can reach the operations and functions. For this reason, for various operations, the user must remember the first command as an entrance to reach the operation, and there is a potential demand for reducing such a burden.
[0010]
The present invention has been proposed to solve the problems of the prior art as described above, and its purpose is to easily indicate the desired operation by voice recognition irrespective of the menu hierarchy and the utterance order. It is to provide navigation technology.
[0011]
[Means for Solving the Problems]
  In order to achieve the above-mentioned object, the navigation system according to claim 1 is a first selection means for selecting which operation is to be performed by sequentially recognizing a predetermined phrase according to the menu hierarchy. And a second selection means for selecting an operation corresponding to the word and a process corresponding to the selected operation by recognizing a word used in the lowermost layer of the menu hierarchy other than the lowermost layer. And processing meansThe second selection means selects an operation for displaying a menu of a hierarchy one level lower than the current hierarchy when a phrase used in the lowest hierarchy is recognized by voice other than the lowest hierarchy. The first selecting means is for selecting an operation corresponding to the recognized word / phrase when the word / phrase to be used in the lowermost layer is voice-recognized in the lowermost layer, and the processing means is selected. In addition to processing according to the operation, when an operation for displaying a menu in a hierarchy one level lower than the current hierarchy is selected in the first selection means, a message corresponding to the operation is displayed on the display. It is characterized by.
[0012]
  The navigation method of claim 2 is based on the view of the invention of claim 1 as a method, and is used for selecting which operation is to be performed by sequentially recognizing a predetermined phrase according to the menu hierarchy. FirstChoiceA second step for selecting an operation according to the step by recognizing a word used at the lowest level of the menu hierarchy at a level other than the lowest level.ChoicePerform steps and processing according to the selected operationprocessingAnd including stepsThe second selection step includes a process of selecting an operation for displaying a menu of a hierarchy one level lower than the current hierarchy when a phrase used in the lowest hierarchy is recognized by voice other than the lowest hierarchy, The first selecting step includes a process of selecting an operation corresponding to the recognized word / phrase when the word / phrase used in the lowermost layer is recognized by voice in the lowermost layer, and the processing step is the selected In addition to the processing according to the operation, when an operation for displaying a menu in the hierarchy one level lower than the current hierarchy is selected in the first selection step, a process for displaying a message corresponding to the operation on the display It is characterized by including.
[0013]
  The recording medium on which the navigation software according to claim 3 is recorded is the one in which the inventions of claims 1 and 2 are viewed from the viewpoint of software stored in the recording medium, and navigation software for performing navigation using a computer is provided. In the recorded recording medium, the software tells the computer which operation to perform by recognizing the predetermined phrases in order according to the menu hierarchy.A first selection process for selecting;By recognizing words used at the lowest level of the menu hierarchy at other than the lowest level, operations corresponding to the words can be performed.A second selection process for selecting,Processing according to the selected operationIn the second selection process, when the words used in the lowermost layer are recognized by voice other than the lowermost layer, an operation for displaying a menu in the next lower layer is performed. The first selecting process includes a process of selecting an operation corresponding to the recognized word / phrase when a word / phrase to be used in the lowermost layer is voice-recognized in the lowermost layer. The process corresponding to the selected operation displays a message corresponding to the operation on the display when an operation for displaying a menu in a hierarchy one level lower than the current hierarchy is selected in the first selection process. It is characterized by including the process to make.
[0014]
  Aspect as aboveNow, the wording used at the lowest level of the menu hierarchy is processed differently when it is said at the original lowest level and when it is directly named from other than that. For example, when a word indicating how to display a screen is told at the bottom of the menu hierarchy, displaying it together with other options gives you an opportunity to consider other options. When the name is directly named from, the screen display is switched accordingly and a message is output accordingly. In this way, since different processing is performed depending on the state of the same word / phrase, usability can be improved finely.
[0017]
DETAILED DESCRIPTION OF THE INVENTION
Next, an embodiment (hereinafter referred to as “embodiment”) of the navigation system of the present invention will be specifically described with reference to the drawings. In addition, about each figure used in the following description, the same code | symbol is attached | subjected about the same member as the figure demonstrated before that, and the same kind of member, and description is abbreviate | omitted.
[0018]
This embodiment is realized by using various hardware devices and a computer controlled by software. In this case, the software is created by combining instructions according to the description of this specification, and the method described in the prior art is used in common with the prior art described above. The software includes not only the program code but also data prepared in advance for use when executing the program code. And the software implement | achieves the effect of this invention by utilizing physical processing apparatuses, such as CPU and various chip sets incorporated in the navigation system.
[0019]
However, specific hardware and software configurations 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 by software. In addition, regarding the part that uses software, there are various types of software such as compilers, assemblers, and microprograms. Further, a recording medium on which software for realizing the present invention is recorded is an embodiment of the present invention alone.
[0020]
As described above, since there are various ways of realizing the present invention using a computer, the present invention and the implementation will be described below using virtual circuit blocks that implement individual functions included in the present invention and embodiments. The form will be described.
[0021]
[1. Configuration of First Embodiment]
In the first embodiment, both an operation of sequentially uttering by tracing the menu hierarchy and an operation of directly uttering a phrase representing the desired operation regardless of the menu hierarchy are possible. That is, in this first embodiment, as shown in FIG. 3, the hierarchy is sequentially changed from the screen displaying the map in the order of “menu” → “screen display” → “traveling direction” → “heading up”. It can also be operated later, and as shown in FIG. 4, it can also be shortcut by directly saying “Heading Up” from the screen displaying the map.
[0022]
[1-1. Overall configuration)
First, FIG. 1 is a conceptual diagram showing an example of what kind of hardware the embodiment can be configured on. In this example, the voice recognition unit V and the navigation unit N are connected to each other, and a part of hardware used for realizing this embodiment is shown.
[0023]
Among these, the recognition dictionary V2 is stored in the ROM (V1) in the voice recognition unit V. The navigation unit N has a CD-ROM drive, and the CD-ROM (N1) inserted in the CD-ROM drive includes various data in addition to application programs for realizing the functions of the navigation system. A database N3 is recorded. An application program N4 for realizing the functions of the navigation system of this embodiment is read from the CD-ROM (N1) and recorded in the flash memory N2.
[0024]
FIG. 2 is a functional block diagram showing a specific configuration of this embodiment realized by using hardware as shown in FIG. That is, this embodiment includes an absolute position / orientation detection unit 1, a relative orientation detection unit 2, a vehicle speed detection unit 3, a main CPU and its peripheral circuit 4, a memory group M, a display unit 10, and an input unit. 11, a CD-ROM control unit 12, an FM multiplex reception and processing unit 13, and a voice recognition unit 14.
[0025]
Among them, the absolute position / orientation detecting unit 1 receives GPS radio waves transmitted from GPS satellites, and thereby calculates absolute position coordinates and directions on the ground surface for the current position of the automobile (own vehicle). It is. The relative orientation detection unit 2 is a part that detects the relative orientation of the automobile using a gyroscope or the like. The vehicle speed detection unit 3 is a part that calculates the vehicle speed by processing vehicle speed pulses obtained from the automobile.
[0026]
The CD-ROM control unit 12 is a part 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 an FM broadcast of a radio by switching a plurality of antennas according to the reception state. The speech recognition unit 14 is a speech recognition unit including feature parameters and waveform data representing features for each word to be recognized, that is, a recognition dictionary 43, and converts speech input from a microphone into a digital signal. This is a part for recognizing the uttered word / phrase by pattern matching with the recognition dictionary 43.
[0027]
[1-2. Role of main CPU and its peripheral circuits]
Further, the main CPU and its peripheral circuit 4 are parts that serve as a control circuit for controlling the entire navigation system, and the first selection unit 41 and the second selection unit 44 are operated by the above-described software. And the processing unit 45.
[0028]
Among these, the 1st selection part 41 is a 1st selection means for selecting which operation is performed by carrying out the voice recognition of the predetermined phrase according to a menu hierarchy in order. Here, it is assumed that voice recognition is performed by the voice recognition unit 14, and the contents of the menu hierarchy described above are prepared as menu hierarchy data 42.
[0029]
Further, the second selection unit 44 recognizes a word used in the lowermost layer of the menu hierarchy described above by voice recognition other than the lowermost layer, thereby selecting second selection means for selecting an operation according to the word. It is. The processing unit 45 is processing means that performs processing according to the operation selected by the first selection unit 41 or the second selection unit 44. The processing unit 45 is configured to perform different processing for the words and phrases used in the lowermost layer, depending on whether the speech recognition is performed in the lowermost layer or in other than the lowermost layer. Has been.
[0030]
Although not shown, the main CPU and its peripheral circuit 4 may display the current position of the vehicle on a computer graphics map using the calculated vehicle position, Other processing units that perform various navigation processes such as providing route guidance in response to instructions from the user, and using a user interface (not shown) including an I / O control circuit and a driver, a variety of information It is configured to perform input / output. The main CPU and its peripheral circuit 4 use the memory group M, the display unit 10, and the input unit 11 when performing such various processes.
[0031]
[1-3. Other configurations
That is, the memory group M includes various memories necessary for the operation of the navigation system of this embodiment, that is, the ROM 5 storing the BIOS and the bootup program, the DRAM 6 used for the work area, the cache, the buffer, and the like. SRAM 7 for use in video and VRAM 8 for use in video display are included.
[0032]
The display unit 10 is a part for outputting various types of information such as maps and operation menus using a liquid crystal display panel, a voice synthesizer, and the like. The input unit 11 is used by the user for various information such as instructions and destinations. It is a part for inputting.
[0033]
[2. Operation of First Embodiment]
The first embodiment configured as described above operates as follows.
(1) First, the recognition dictionary 43 includes all data of words used in each level of the menu so that all words can be always recognized even when the menu level is traced. Keep it.
[0034]
(2) When the user utters, the speech recognition unit 14 recognizes the spoken phrase using the recognition dictionary 43, and assigns the number of the phrase to the first selection unit 41 and the second selection unit 44. hand over. Here, the operations of the first selection unit 41 and the second selection unit 44 are realized by an application program that realizes the function of the navigation system.
[0035]
(3) That is, in these application programs, a process corresponding to what number is 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 number of words is basically one-to-one with the number.
[0036]
For example, it is assumed that there is a menu in which the word “system” can be spoken in the middle of the menu hierarchy, and when the word is spoken, a menu in the next lower hierarchy is displayed. In such a case, even when the phrase “system” is spoken in the “medium” menu hierarchy described above, it is spoken in a state where a map around the vehicle is displayed, for example. In all cases, the same “menu one level lower” described above is displayed.
[0037]
However, since the words at the bottom of the menu hierarchy are specific operations, they are programmed to change movement depending on whether they are said directly on the map or next to other words on the menu. Keep it.
[0038]
For example, FIGS. 3A to 3E are conceptual diagrams showing a flow of reaching the operation of “heading up” by sequentially uttering predetermined words and phrases according to the menu hierarchy. In the screen (d) displayed by speaking, it is displayed that there is an option of “North Up” in addition to “Heading Up”.
[0039]
On the other hand, FIGS. 4 (a) and 4 (b) show an example in which an operation “heading up” is easily performed by simply speaking “heading up” directly from a screen displaying a road map around the vehicle. In this example, in the screen (b) after speaking “heading up” in this example, the other options described above are not displayed, but a message indicating that the traveling direction is heading up is displayed.
[0040]
(4) In the database N3, information necessary when the application program described above executes processing corresponding to a given word number, such as a message to be output on the screen, is displayed for each word number. Correspondingly, the application program uses the CD-ROM control unit 12 to execute processing according to the phrase while reading this data as appropriate.
[0041]
Here, FIG. 5 is a conceptual diagram showing an example in which the phrase numbers recognized using the recognition dictionary 43 are processed by the application program described above. In this example, the phrase “GAMEN HYOUJI” recognized using the recognition dictionary 43 is passed to the application program as the number 8 and the phrase “Heading Up” is passed as the number 19 as a phrase.
[0042]
Then, by the function of this application program, the next level of the menu is displayed for No. 8 “GAME HYUK”. On the other hand, as for “Heading Up” of No. 19, different screens will be displayed depending on whether or not it is spoken directly from the map as described above. Information such as a message such as “heading up the direction” is stored in the database N3 in correspondence with each word number.
[0043]
In addition, as shown in FIG. 5 for “No. 8”, it is also possible to recognize a phrase for calling the next state from a state in the middle of the menu hierarchy, and to perform processing according to the phrase. In this case, there is a correspondence relationship that a certain phrase for calling a certain part of the menu should be uttered in a specific state in the menu hierarchy. Then, if such a phrase is uttered in a state where it originally corresponds, the first selection unit 41 recognizes the utterance using the voice recognition unit 14, but other states, for example, around the own vehicle When such a word is uttered from the state where the map is displayed, the second selection unit 44 recognizes the word using the voice recognition unit 14.
[0044]
[3. Effects of the first embodiment]
As described above, in the first embodiment, even an inexperienced beginner can easily operate without being confused by the utterance order of words and phrases by the basic operation method of sequentially tracing the hierarchical structure of the menu. On the other hand, a familiar user does not have to follow the hierarchical structure of such menus in order. In other words, regardless of the state of the screen, such as whether it is in the middle of a menu, the desired function can be easily achieved by directly speaking the phrase when selecting a specific operation at the bottom layer directly like a single command. It can be used. For this reason, a hierarchical menu can be shortcut (omitted / skip), improving usability.
[0045]
In the first embodiment, a phrase for calling the next state from a state in the middle of the menu hierarchy can be used in a state different from that state, a screen display state other than the menu layer, and the like. For this reason, for example, a part of the menu hierarchy that is desired to be used can be called directly without going through the upper hierarchy, or moved from one part of the menu hierarchy to another part in parallel without returning to the upper hierarchy. Various operations are possible.
[0046]
Further, in the first embodiment, different processing is performed for a phrase used in the lowest layer of the menu hierarchy, when it is said in the original lowest layer and when it is directly named from other than that. That is, since different processing is performed depending on the state of the same word / phrase, usability can be improved finely.
[0047]
[4. Second Embodiment]
In the navigation system having the same configuration as the first embodiment, the second embodiment is the same as having to speak a plurality of words in order in a menu hierarchy by simply saying one predetermined word. It is something to be processed. Here, an example of listing facilities existing around the host vehicle is shown as one of the processes for searching for a destination.
[0048]
First, in the second embodiment, as illustrated in FIG. 6, a recognition dictionary 431 having a configuration including a plurality of tables is prepared. As an example, when processing such as searching for and displaying “Kariyo Hinten” of the vehicle “Shuchen” is performed, for example, in a normal operation flow according to the menu hierarchy, “Shuhen” in the table T11 of FIG. When the phrase is recognized, the number is passed from the speech recognition unit V to the application program N4 of the navigation unit N (FIG. 1).
[0049]
Then, in the database N3 in the CD-ROM, the table name (in this case, the table T21) to be recognized next and the message character string to be displayed are stored in correspondence with the recognized word number. The application program N4 reads the information and outputs a message on the screen or by voice, or notifies the voice recognition unit V of the next recognition target table (in this case, the table T21). The voice recognition unit V reads the table T21 into the memory as the next recognition target table and waits for a command.
[0050]
In this way, item names such as facilities are listed in the newly recognized table T21. In this case, as described above, as a message on the screen or voice output from the application program N4, a message for guiding the utterance of an item name such as “Kariyo Hinten”, for example, “Next item name ”, Etc., and the user utters the item name such as“ Kariyo Hinten ”according to the message.
[0051]
When “car hinting” is recognized in this way, the application program N4 obtains necessary information from the database N3 on the CD-ROM (N1) and outputs a message etc. at the same time as before, and simultaneously List supplies stores. The flow of processing according to the menu hierarchy is shown on the left side of FIG.
[0052]
Further, in this second embodiment, in order to shortcut the operation according to the menu hierarchy as described above, as shown in FIG. 6, a phrase such as “Shuhen no Kyo Hinten” is also prepared in the table T11. Keep it. This word / phrase is a combination of a series of processes in which a plurality of words / phrases must be uttered sequentially in accordance with the menu hierarchy.
[0053]
For example, when the user utters and recognizes this “Shuhen no Kyo Hinten”, the application program N4 acquires necessary information from the database N3 on the CD-ROM as before, and Carry out processes such as listing car supply stores.
[0054]
Further, in the procedure shown on the left side of FIG. 7, the user selects a store closest to the current location from the list of results of searching for nearby car supply stores (steps 71 to 73) (step 74) (step 75). In this example, the store is set as the destination (steps 76 to 78). Therefore, the phrase “Ichibanchi Kaiker Yohinten” is stored in the table 1 of the recognition dictionary 431 as a phrase for performing the same processing by automatically selecting the store closest to the current location. It shall be.
[0055]
When using this phrase, as shown on the right side of FIG. 7, simply speaking “Ichibanchi Kaikar Yohinten” (step 81), the car accessory store closest to the vehicle is searched (step 83). A route is set with the store as the destination (step 88). As a result, when compared with the example according to the menu hierarchy shown on the left side of FIG. 7, steps 71, 72, 75, and 77 are performed by only one step 81, and steps 74 and 76 are unnecessary depending on the processing contents. .
[0056]
As described above, in the second embodiment, when processing is performed by uttering a number of words and phrases, it can be done by speaking a predetermined word and phrase, so that the navigation system can be operated more efficiently. Is done.
[0057]
[5. Third Embodiment]
In the navigation system having the same configuration as the first embodiment and the second embodiment described above, the third embodiment is determined in advance according to which words and phrases are recognized in succession. The selected operation is selected and error handling is performed. In the third embodiment, as in the second embodiment, an example of processing for searching for facilities around the host vehicle is taken as an example, and the order in which words are spoken is shown as an example.
[0058]
Here, FIG. 8 is a conceptual diagram showing the tables constituting the recognition dictionary 432 in the third embodiment, and the two tables in the second embodiment shown in FIG. 6 are called “Kayo Hinten” and “Suhen”, respectively. The words G1 and G2 are added. Of these tables, in the initial state where the navigation system is activated, the first table T12 is the target of speech recognition.
[0059]
Then, when a predetermined phrase out of the phrases registered in the first table T12, that is, “shuhen” here is recognized as a voice, the voice recognition target is switched to the second table T22, and then the voice recognition is performed. For the word / phrase, an operation determined in advance based on the second table T22 is selected or error processing is performed.
[0060]
Here, in the third embodiment, a processing procedure for performing such processing using a table is generalized and shown in FIG. That is, in the example of FIG. 8, the number of tables is two, but the number of tables may be three or more, and this case will be described with reference to FIG. Here, the table symbols are abstracted and indicated by 1, 2, and 3.
[0061]
That is, the user speaks the words in Table 1 (step 91), and if the word W1 is a word W1, the speech recognition target is switched to Table 2 (step 93), and the user speaks the words in Table 2 In response (step 94), processing is performed (step 95). For example, when there is a table 3 in addition to the table 2, processing using the table 3 is performed when another word / phrase W2 is uttered (steps 97 and after).
[0062]
Next, FIG. 10 is a flowchart showing a specific procedure when the procedure generalized in FIG. 9 is applied to an example in the third embodiment. That is, in this procedure, the word “Shu Heng” in the table T12 is first recognized (step 101), and the table T22 is subject to speech recognition (steps 102 and 103). For example, if the phrase is “Kaiyou Hinten” (step 104), a process such as searching for a car accessory store around the vehicle is performed (step 105). If the application program is recognized, an alarm is processed (step 106) by, for example, beeping the application program, and the process returns to step 104.
[0063]
Contrary to the example illustrated in FIG. 10, for example, when the phrase “Kayo Hinten” in the table T <b> 12 illustrated in FIG. 8 is recognized first, the phrase “Shuhen” in the table T <b> 22 is the following phrase: It makes sense. For this reason, when “Shu Heng” is spoken, processing such as listing up nearby car supply stores is performed, but conversely, the same phrase “Kay You Hin” spoken from within table T12 is again displayed. If it is spoken, error processing is performed. That is, in the programming in the third embodiment, programming is performed for each phrase so that the application program monitors the phrase recognized immediately before and changes the operation based on the next recognized phrase.
[0064]
In addition, since each word registered in each table is associated with a message used for processing after the word is spoken, for example, the table is switched according to the preceding word. Can not be recognized, advice or prompting with different contents can be output to the user according to the contents of the preceding word.
[0065]
As described above, according to the third embodiment, what kind of processing is performed on the next recognized phrase depending on which phrase is recognized one time ago, and whether an error is caused. Etc. are judged. For this reason, as long as the meaning of what you want to do is understood, the utterance order according to the menu hierarchy can be determined in advance, and the reverse utterance order or partially omitted utterance order can be determined in advance. The degree increases and the operation becomes easy.
[0066]
In the third embodiment, since the relationship between words spoken in succession can be determined with a simple configuration of switching the table to be recognized according to the recognized words and phrases, the implementation is easy. .
[0067]
In addition, the user does not get confused about the utterance order by such an operation method not limited to the utterance order, and a more flexible and natural operation is realized in the user interface for speech recognition. For this reason, various operations can be performed immediately, and driving safety is further improved.
[6. Other Embodiments]
The present invention is not limited to the embodiment described above, and 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 mobile objects such as a two-wheeled vehicle.
[0068]
In addition, the structure of the menu hierarchy and the number of hierarchies are free. For example, the menu hierarchy can be reached in any direction to reach the “lowermost layer”. It may be different in the number of ranks counted from the entrance of the hierarchy. In addition, regarding the words and phrases used in the lowest layer, when it is configured to perform different processing depending on whether the voice is recognized in the lowest layer or the voice is recognized in other than the lowest layer, not all the words and phrases in the lowest layer There is no need for such a configuration.
[0069]
“Predetermined single word” means that the same processing as when a plurality of words are uttered in order according to the menu hierarchy is combined into a single word. Of course, it is possible to register more than one at the same time. In the above-described embodiment, an example in which two words are recognized in succession has been described. However, the navigation system can be controlled based on the order in which three or more words are recognized.
[0070]
【The invention's effect】
As described above, according to the present invention, an operation to be performed can be easily instructed by voice recognition regardless of the menu hierarchy and the utterance order.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a hardware configuration of 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 a phrase is sequentially uttered by tracing a menu hierarchy 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 lowest level of a menu hierarchy from a screen displaying a map in the first embodiment of the present invention.
FIG. 5 is a conceptual diagram showing that processing according to a recognized word number is performed in the first embodiment of the present invention.
FIG. 6 is a conceptual diagram showing the configuration of a recognition dictionary in the second embodiment of the present invention.
FIG. 7 is a flowchart showing a processing procedure in the second embodiment of the present invention.
FIG. 8 is a conceptual diagram showing the configuration of a recognition dictionary in the third embodiment of the invention.
FIG. 9 is a flowchart generally showing a processing procedure in the third embodiment of the present invention.
FIG. 10 is a flowchart specifically showing a processing procedure in the third embodiment of the present invention.
FIG. 11 is a conceptual diagram showing an example of a conventional recognition dictionary.
[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 / azimuth detector
2 ... Relative bearing detector
3 ... Vehicle speed detector
4 ... Main CPU and its peripheral circuits
M ... Memory group
5 ... ROM
6 ... DRAM
7 ... SRAM
8 ... VRAM
10 ... Display section
11 ... Input section
12 ... CD-ROM controller
13 ... FM multiplex reception and processing unit
14 ... Voice recognition unit
41 ... 1st selection part
42 ... Menu hierarchy data
43, 430, 431, 432 ... Recognition dictionary
T ... Table
44 ... Second selection unit
45. Processing section

Claims (3)

A first selection means for selecting which operation is to be performed by sequentially recognizing predetermined phrases according to the menu hierarchy;
A second selection means for selecting an operation corresponding to the phrase by recognizing a phrase to be used in the lowest layer of the menu hierarchy at a place other than the lowest layer;
Processing means for performing processing according to the selected operation ,
The second selection means is for selecting an operation for displaying a menu of a hierarchy one level lower than the current hierarchy when a phrase used in the lowest hierarchy is recognized in a voice other than the lowest hierarchy,
The first selecting means is for selecting an operation corresponding to the recognized word / phrase when the word / phrase to be used in the lowermost layer is voice-recognized in the lowermost layer.
In addition to the processing according to the selected operation, the processing means responds to the operation when the first selection means selects an operation for displaying a menu of a hierarchy one level lower than the current hierarchy. A navigation system characterized by displaying a message to be displayed on a display. A first selection step for selecting which operation is to be performed by sequentially recognizing predetermined phrases according to the menu hierarchy;
A second selection step for selecting an operation corresponding to the phrase by recognizing a phrase used in the lowest layer of the menu hierarchy other than the lowest layer;
A processing step for performing processing according to the selected operation ,
The second selection step includes a process of selecting an operation for displaying a menu of a hierarchy one level lower than the current hierarchy when a word / phrase used in the lowest hierarchy is recognized by voice other than the lowest hierarchy,
The first selection step includes a process of selecting an operation corresponding to the recognized word / phrase when the word / phrase to be used in the lowermost layer is voice-recognized in the lowermost layer,
In addition to processing according to the selected operation, the processing step corresponds to the operation in the case where an operation for displaying a menu of a hierarchy one level lower than the current hierarchy is selected in the first selection step. The navigation method characterized by including the process which displays the message to perform on a display. In a recording medium recording navigation software for performing navigation using a computer, the software is stored in the computer.
A first selection process for selecting which operation to perform by sequentially recognizing a predetermined phrase according to the menu hierarchy ;
A second selection process for selecting an operation according to the phrase by recognizing a phrase used in the lowermost layer of the menu hierarchy at a position other than the lowermost layer ;
The process according to the selected operation is executed,
The second selection process includes a process of selecting an operation for displaying a menu in a hierarchy one level lower than the current hierarchy when a phrase used in the lowest hierarchy is recognized in a voice other than the lowest hierarchy. ,
The first selecting process includes a process of selecting an operation corresponding to the recognized word / phrase when a word / phrase to be used in the lowermost layer is recognized by voice in the lowermost layer,
The process corresponding to the selected operation is performed by displaying a message corresponding to the operation when the operation for displaying the menu of the hierarchy one level lower than the current hierarchy is selected in the first selection process. The recording medium which recorded the software for navigation characterized by including the process displayed on the.

Images