JP3818352B2 - Navigation device and storage medium - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a navigation apparatus and a storage medium having a voice recognition function for determining a question content.
[0002]
[Prior art]
Conventionally, as a navigation device having a voice recognition function, when a voice input is started, a list of voice recognition target words is displayed for a certain period of time to prevent occurrence of a recognition error (Japanese Patent Laid-Open No. 6-259091) ) When voice recognition is performed, a plurality of recognizable voices are displayed in a list or the like (Japanese Patent Laid-Open No. 9-114490). For example, Japanese Laid-Open Patent Publication No. 9-114491 has been proposed which displays a different mode for each category to which the voice belongs.
[0003]
[Problems to be solved by the invention]
A conventional navigation device with a voice recognition function is a system that searches from a dictionary of the device based on input voice and returns a response to a requested item. However, it is limited to those included in a dictionary which is a pre-registered word / phrase group. Therefore, the user needs to store words / phrases as “commands” in advance. In addition, in order to produce an interactive image, it is necessary to increase the number of words in the dictionary. However, because words entered by the user's thoughts are searched for all the words in the dictionary, the search takes time. There is a problem that it ends up.
[0004]
An object of the present invention is to solve the above-described problems, and it is an object of the present invention to reduce the amount of words to be stored by a user, improve the recognition rate, and speed up the response.
[0005]
[Means for Solving the Problems]
In a navigation device that recognizes input speech and performs guidance control according to a recognition result, the user's speech input response candidates are extracted with priority given based on a request for information retrieval by the user. A presentation means for prompting selection by speaking a high-priority candidate and presenting and outputting the other candidates in a list by the output means and prompting selection; and candidates presented and output by the presentation means And a determination presentation processing unit that determines a user's response inputted by voice based on the candidate, and a control unit that executes processing corresponding to the candidate to present information.
The present invention also provides a user's voice input response based on a request for information retrieval by a user in a storage medium storing a program for controlling a navigation device that recognizes the input voice and performs guidance according to the recognition result. A candidate is extracted by giving a priority, and a candidate having a high priority is prompted to make a selection by speaking, and the other candidates are presented and output to be displayed in a list by the output means to prompt the selection; A program is stored that includes a step of determining a user's response inputted by voice to a presented and output candidate based on the candidate, and a step of executing information corresponding to the candidate and presenting information. And
[0006]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing a configuration example of a navigation apparatus according to the present invention.
This device determines input speech by speech recognition, displays a determination presentation processing unit 100 for processing output speech, a speech input unit 101, a speech output unit 102, information for dialogue with users, and guidance information Display unit 103, dictionary 104 for determining the input voice, voice pattern 105 for confirming the contents of the question from the user, and related condition data 106 for presenting on the assumption of the user's response.
[0007]
As shown in FIG. 2, for example, the dictionary 104 stores words and phrases such as nearest, neighborhood search, facility, parking lot, convenience store, and gasoline tosund in an information storage medium. The input speech is determined by comparison, and as a comparison method, an appropriate method such as forward match, backward match, partial match, complete match, etc. is used.
[0008]
As shown in FIG. 3, the voice pattern 105 is a voice pattern for confirming the contents of the user's question. For example, answer “A” or “B”, answer “Yes” or “No”. Please use “Left” or “Right”, “1” or “2”.
[0009]
As shown in FIG. 4, the related condition data 106 is data to be output to the voice output unit 102 or the display unit 103 assuming a user's response to the question content. For example, as shown in FIG. If the previous search data is a convenience store using the previous search data, the convenience store is presented. Also, as shown in FIG. 4 (b), the number of search targets is added each time a search is performed, and the ranking with the highest number of searches is stored in a table, which is presented in descending order. For example, in the example of FIG. 4B, since rank 1 is a convenience store and rank 2 is a parking lot, a convenience store is presented first, otherwise a parking lot and then a gas station are presented. Further, as shown in FIG. 4C, related candidates corresponding to the type of the selected destination are previously stored as a table, and a response is assumed based on this data. For example, if the destination is a tourist destination, a hotel, bank, scenic spot, parking lot, gas station, souvenir shop, etc. If the destination is a business trip, a business hotel, post office, bank, destination is an amusement park Then, according to the type of destination, such as a parking lot and a convenience store, relevant candidates suitable for it are presented.
[0010]
Next, the search guidance process by voice input according to the present invention will be described with reference to FIG. This example is a processing flow showing an example of guiding a convenience store by the nearest search. In the figure, the user's voice is shown on the left and the navigation device's voice is shown on the right.
The voice input is started (step 1), and when the user pronounces “closest facility”, the navigation device starts the input voice determination process as “please wait” (step 2). Next, a response example for confirming the determination of the input voice is provided (step 3). This is performed, for example, by an utterance from the navigation device such as “Check the content of the question. Please answer“ Yes ”or“ No ”.” Next, the input voice determination result is confirmed (step 4), and the navigation device utters “Is the input voice nearest to search?”, And the user answers “Yes” or “No” (step) 5). Here, when “yes” is returned, the related conditions are confirmed (step 6). As shown in FIG. 4, the related condition is presented by narrowing down candidates based on the previous search data, the search frequency having a large number of searches, or the related candidates corresponding to the type of destination. Here, the “convenience store” searched last time is presented, and the user side answers “Yes” or “No”. When “No” is answered, for example, a parking lot with a large number of searches is presented. If there is an answer of “Yes”, “Start searching for“ convenience store ”in the vicinity” ”is uttered from the navigation device side (step 8), and then the search result is displayed (step 9). The search results are displayed by distinguishing the left and right sides of the route, such as “There is a convenience store within 3 km to the left of the road you are driving” and “There is a convenience store within 1 km to the right”. Present on the basis of ease. Next, the guidance facility is confirmed (step 10). Here, “We will give you route guidance to the facility. Please answer“ Left ”or“ Right ”. If the user side presents “left” and “right” to this, the user starts speaking by saying “starting guidance” based on this (step 12).
[0011]
In the guidance process in FIG. 5, related candidates are presented in a narrowed manner, and the user selects from the narrowed candidates. In this example, among the facility names shown in FIG. 4 (b), “Convenience store” selected and searched by the user last time and “Parking lot” with a large number of searches are presented as candidates (voice utterance), The user selects one of these. That is, all the possible responses (“convenience store”, “parking lot”, etc.) candidates are spoken to prompt selection.
[0012]
Furthermore, it can also be configured as follows.
When there are many candidates, even if all candidates are uttered from the navigation device side, the user may not be able to remember all the candidates. Selection is made by speaking a voice, and a list or the like is displayed on the display screen for other candidates to prompt the selection. For example, it narrows down to five candidates from the related candidates shown in FIG. Of these five candidates, the “convenience store” with the highest number of searches is set as the candidate with the highest priority. In this case, in step 6 of FIG. 5 (relevant condition confirmation processing), the voice on the navigation device side is “No. 1, convenience store, there are 4 other candidates. Please answer with a number.” On the screen, four candidates other than “Convenience Store” are displayed in a list together with numbers 2-5. When the desired candidate is other than “convenience store”, the user visually selects the display screen and utters and inputs the number. It is also possible to select candidates by extracting candidates with high priority, presenting the candidates in order, and letting the user answer whether or not the candidate is desired. In this case, in the process of step 6 in FIG. 5, the voice with the highest priority is extracted from the navigation device side (for example, “convenience store”), and “No. 1, is it a convenience store?“ Yes ”or“ No ” please answer. "Speaks." On the other hand, when the user answers “Yes”, “Convenience Store” is selected. If you answer “No”, the candidate with the next highest priority is extracted and uttered “No. 2, is it a parking lot?”. On the other hand, when the user answers “Yes”, “Parking” is selected. If you answer "No", the navigation device voice will say "I'm sorry. I'm not sure. I will give you another list. Please answer with a number." Candidates other than "" are displayed along with the number to prompt the user to select. When the user inputs a number by voice, a candidate corresponding to the number is selected.
[0013]
FIG. 6 is a diagram showing a display example when the user selects a reply.
In this example, “input” is displayed when the destination is determined, and “tell me” is displayed when the destination is not determined, and the user selects either of these. As shown in FIG. 6A, “input” and “tell me” are displayed in the same size on the map, and a character is displayed in the lower right corner to prompt the user to select one. When the destination is decided, the user selects “Input” and inputs voice. When the device recognizes that “Input” is input, the “Input” character is enlarged and highlighted on the screen. (FIG. 6B). On the other hand, when “Tell me” is selected when the destination is not decided, the character is displayed in a large size and highlighted (FIG. 6C), a list of destinations is displayed from the navigation device side, and the user can Select from. The highlighted display of the selected item may be performed by blinking the selected item or changing the thickness or color of the character, in addition to changing the size of the character.
[0014]
FIG. 7 is a diagram showing a configuration example of a navigation device equipped with a voice guidance processing function.
Input device 1 for inputting information relating to route guidance, current position detecting device 2 for detecting information relating to the current position of the host vehicle, navigation data necessary for calculating the route, display / voice guidance data necessary for route guidance, voice Information storage device 3 in which data and a program (application and / or OS) for performing dialogue by input are recorded, display / voice guidance processing necessary for route search processing and route guidance, and dialogue by voice input The central processing unit 4 for controlling the entire system, further information such as road information and traffic information relating to the traveling of the vehicle, detection of information relating to the current position of the vehicle, and further information relating to the current position. An information transmitting / receiving device 5 that transmits and receives information and an output device 6 that outputs information on route guidance are configured.
[0015]
The input device 1 has a function of inputting a destination and instructing the central processing device 4 to perform a navigation process according to the driver's will. As means for realizing the function, a touch switch, a remote controller, or the like that inputs a destination by a telephone number or coordinates on a map or requests route guidance can be used. Further, the present invention includes a device for performing dialogue by voice input, and functions as a voice input device. A recording card reader for reading data recorded on an IC card or a magnetic card can also be added. In addition, an information center that stores data necessary for navigation and provides information via a communication line at the request of the driver, and a portable type having data such as map data, destination data, simple maps, and building shape maps A data communication device for exchanging data with an information source such as an electronic device can be added.
[0016]
The current position detection device 2 obtains the current position information of the vehicle using a satellite navigation system (GPS), an absolute direction sensor that detects the traveling direction of the vehicle in an absolute direction by using, for example, geomagnetism, a vehicle For example, a steering sensor, a relative azimuth sensor that detects the relative azimuth by using a gyro sensor, for example, a distance sensor that detects the travel distance of the vehicle from the rotational speed of the wheel.
[0017]
The information storage device 3 is an external storage device that stores navigation programs and data, and includes, for example, a CD-ROM. The program is a program for performing processing such as route search, the processing program shown in the flowchart described in this embodiment, the display output control necessary for route guidance, the program necessary for dialogue by voice input, the data necessary for it, and voice A program for performing voice output control necessary for guidance and data necessary for the guidance, a program for performing search and guidance notification via anthropomorphic characters, and data necessary for the program are stored. The stored data includes map data, search data, guidance data, map matching data, destination data, registration point data, road data, genre-specific data, landmark data, character data, etc. All necessary data is stored. The present invention can also be applied to a type in which only data is stored in a CD-ROM and the program is stored in a central processing unit.
[0018]
The central processing unit 4 includes a CPU 40 that executes various arithmetic processes, a flash memory 41 that reads and stores a program from a CD-ROM of the information storage device 3, a program that performs program checking and update processing for the flash memory 41 (program reading means) ), The coordinates of the set destination point, and the road name code No. The RAM 43 temporarily stores the searched route guidance information and the data being processed. In addition to this, although not shown in the figure, dialogue processing by voice input from the input device 1 is performed, or voice, phrase read out from the information storage device 3 based on a voice output control signal from the CPU is one. A speech processor that synthesizes a set of sentences, sounds, etc., converts them into analog signals and outputs them to a speaker, a communication interface for exchanging input / output data by communication, and a sensor input interface for capturing sensor signals of the current position detection device 2 In addition, it has a clock for entering date and time in internal diagnosis information. Note that a program for performing the above-described update processing may be stored in an external storage device.
The program according to the present invention and other programs for executing navigation may all be stored in a CD-ROM which is an external storage medium, or a part or all of these programs may be stored in the ROM 42 on the main body side. Good.
[0019]
Various navigation functions are realized by inputting data and programs stored in the external storage medium as external signals to the central processing unit of the navigation apparatus main body and performing arithmetic processing.
[0020]
The navigation device of the present invention has a relatively large capacity flash memory 41 for reading a program from a CD-ROM of an external storage device as described above, and a small program that stores a program for starting up a CD (program reading means). A ROM 42 having a capacity is incorporated. The flash memory 41 is a non-volatile storage unit that retains stored information even when the power is turned off. Then, as a CD start-up process, a program in the ROM 42 as a program reading means is activated and the program stored in the flash memory 41 is checked, and the CD-ROM disc management information and the like of the information storage device 3 are read. The program loading process (update process) is performed based on this information and the state of the flash memory 41.
[0021]
The information transmitter / receiver 5 is a GPS receiver that acquires information using a satellite navigation system (GPS), a VICS information receiver that acquires information using FM multiplex broadcasting, radio wave beacons, optical beacons, etc. By using a telephone, a personal computer, etc., it is composed of an information center (for example, ATIS) and a data transmitting / receiving device for bidirectionally communicating information with other vehicles.
[0022]
The output device 6 has a function of outputting guidance information by voice and / or a screen when the driver needs it, and printing out data subjected to navigation processing by the central processing unit 4. For this purpose, input data is displayed on the screen, a display that displays a route guidance screen, a printer that prints out data processed by the central processing unit 4 or data stored in the information storage unit 3, and voice guidance for route guidance. A speaker for output is provided.
[0023]
The display is composed of a simple liquid crystal display, etc., and an enlarged intersection screen based on map data and guidance data processed by the central processing unit 4, destination name, time, distance, direction arrow, dialogue by voice input Display questions and responses, highlight necessary items, and anthropomorphic characters. Since the image data sent to the display is binary image data (bitmap data), a communication line used for serial communication or the like is used instead of a dedicated image signal line. A communication line can also be used. The display is provided with a memory that temporarily holds bitmap data.
[0024]
This display is provided in an instrument panel in the vicinity of the driver's seat, and the driver can check the current location of the host vehicle and obtain information on the route from now on by looking at the display. Although not shown in the figure, a tablet including a touch panel, a touch screen, etc. may be used on the display screen, and the point input, road input, etc. can be performed by touching the screen or tracing the screen. Good.
[0025]
【The invention's effect】
As described above, according to the present invention, a question form on the navigation device side is configured so that a candidate for a possible user response can be narrowed down and presented so that the user can respond in a selected format. By displaying the response and highlighting the necessary item parts, it is possible to reduce the number of words to be memorized in advance on the device side, and the amount of words to be memorized by the user is reduced. It is possible to search inside, improve the recognition rate, speed up the response, and reduce the interaction load.
[Brief description of the drawings]
FIG. 1 is a diagram showing a configuration example of a vehicle navigation apparatus according to the present invention.
FIG. 2 is a diagram illustrating a dictionary.
FIG. 3 is a diagram for explaining a question content confirmation pattern;
FIG. 4 is a diagram for explaining a related condition for narrowing down user response candidates;
FIG. 5 is a diagram for explaining the nearest facility guidance processing flow;
FIG. 6 is a diagram illustrating a display example of a question for a user.
FIG. 7 is a diagram showing a configuration example of a navigation device of the present invention.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Input device, 2 ... Current position detection device, 3 ... Information storage device, 4 ... Central processing unit, 5 ... Information transmission / reception device, 6 ... Output device

Claims (7)

In a navigation device that recognizes input voice and performs guidance control according to the recognition result,
Based on the request for information retrieval by the user to extract the candidate of the user's voice input response by prioritizing, encourage selection by voice utterance higher priority candidate list by the output means for the other candidate Presenting means for displaying and prompting for selection ;
Determination presentation processing means for determining a user's response inputted by voice to the candidate presented and output by the presenting means based on the candidate;
A navigation device comprising: control means for executing processing corresponding to the candidate and presenting information.   The navigation apparatus according to claim 1, wherein the candidate is previous search data.   The navigation apparatus according to claim 1, wherein the candidate is data having a large number of searches. 2. The navigation apparatus according to claim 1 , further comprising means for setting a destination, wherein the candidate is data related to the set destination . The granted priority candidates are previous search data, the navigation apparatus according to claim 1, characterized in that the order of more data with the number of searches.   The navigation apparatus according to claim 1, wherein the candidate is information of an alternative method, and an item portion related to the input voice information is highlighted. In a storage medium storing a program for recognizing an input voice and controlling a navigation device that performs guidance according to a recognition result,
Based on the request for information retrieval by the user to extract the candidate of the user's voice input response by prioritizing, encourage selection by voice utterance higher priority candidate list by the output means for the other candidate Presenting and displaying to prompt for selection ;
Determining a user's response inputted by voice to the presented candidate based on the candidate;
Executing a process corresponding to the candidate to present information;
A computer-readable storage medium storing a program having

Images