JP2005316022A - Navigation device and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To enable setting of a place without uttering made toward a voice recognition device consciously. <P>SOLUTION: A navigation device is provided with a storage means (5) which stores map data including names of places, a recording means (11) which records the contents of conversation, a voice recognition means (12) which recognizes the contents of the conversation recorded in the recording means (11) when a voice recognition button (3) is operated, an analysis means (13) which analyzes character string data obtained by the voice recognition of the voice recognition means and a control means (14) which extracts place information by comparing the analyzed data of the analysis means with the place name data stored in the storage means. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a navigation apparatus and a program provided with voice recognition means.

In a conventional navigation device, a device that recognizes a user's speech and selects a guidance target has been proposed (Patent Document 1). In such a conventional device, for example, when a point where the user wants to go in a passenger's conversation comes out, the user wants to go again by speaking and recognizing the place where he wants to go. Become.
JP 2003-329476 A

  However, in the method such as Patent Document 1, it is necessary to speak again toward the voice recognition device of the navigation device, even though the point where the user wants to go in the conversation has come out. Since it is unnatural to speak to the navigation device, it was not easy to use.

An object of the present invention is to solve the above-described problems, and an object of the present invention is to make it possible to extract point information by recognizing speech from the content of a normal conversation in a natural conversation.
For this purpose, the present invention provides a storage means for storing map data including a point name, a recording means for recording the contents of conversation, and a conversation recorded by the recording means when the voice recognition button is operated. Voice recognition means for recognizing contents, analysis means for analyzing character string data obtained by voice recognition by the voice recognition means, data analyzed by the analysis means, and point name data stored in the storage means And a control means for extracting point information.
According to the present invention, in the program installed in the navigation device having voice recognition means, the step of recording the contents of the conversation by the recording means, and when the voice recognition button is operated, the contents of the recorded conversation are recognized by the voice recognition. A step of recognizing speech by means, a step of analyzing character string data obtained by speech recognition by the speech recognition means, and a step of extracting point information by comparing the analyzed data with point name data. And

  According to the present invention, a point name that naturally appears in a conversation can be used, so that the user can consciously set a point without speaking to the voice recognition device.

Hereinafter, embodiments will be described.
FIG. 1 is a diagram illustrating an example of a navigation device according to the present embodiment. As a navigator processing means, a map display process, a route search process, a display / voice guidance process necessary for route guidance, a voice recognition process and a sentence analysis, and a central processing unit 1 for controlling the entire system, departure and destination, registration Input device 2 composed of a keyboard, mouse, joystick, microphone, etc. for inputting information such as points, operation button 3 for starting speech recognition, current position detection device 4 for detecting information on the current position of the host vehicle, map Data, point data, navigation data necessary for route search, display / voice guidance data necessary for route guidance, and programs for displaying maps, route searching, voice guidance, etc. (applications and / or OS) and other information storage device 5, a display for outputting information on route guidance, a speaker, etc. Output device 6, for example, information relating to traveling of the vehicle, such as road information and traffic information, detecting information relating to the current position of the vehicle, and further transmitting and receiving information relating to the current position It is configured.

  The central processing unit 1 according to the present embodiment includes a recording unit 11 that records contents of conversations that drivers and passengers naturally have in the vehicle, and a conversation that is recorded when a voice recognition operation button is operated. The voice recognition means 12 for recognizing the content of the voice, the analysis means 13 for analyzing the character string data obtained by the voice recognition, and the point name data stored in the information storage device 5 are read and analyzed by the analysis means 13 Control means 14 for extracting point information in comparison with data is provided.

  For example, the recording unit 11 records the conversation contents in a memory (buffer) in units of several minutes and sequentially updates the contents. The voice recognition unit 12 is, for example, 1 when the voice recognition operation button is operated. Voice recognition of the conversation content is performed retroactively for a minute, and character string data obtained as a result is analyzed by the analyzing means 13 and cut out for each word. By comparing the words thus obtained with the contents of the point name database, it is possible to extract point information that has come out in a natural conversation, and use this to set points.

Next, the flow of processing for extracting point information using the recorded conversation contents will be described with reference to FIG.
In FIG. 2A, it is assumed that user A and user B have the following conversation.

User A: How about work recently? User B: Busy User A: That's right. I want to eat delicious food.

User B: How about the ramen shop Hanjoten?
User A: This content is recorded as it is and stored in the buffer. Then, if the voice recognition button is operated after “Like”, for example, the conversation content for one minute is read from the buff before the button is pushed back, and voice recognition is performed. It is assumed that character string data “How about the ramen shop Hanjoten?” Was obtained by this voice recognition (FIG. 2B).

  The analysis means analyzes the text of the character string data, and cuts out the words for each word such as “Previous: Going: Ramen shop: No: Hanjoten: What: How?” (FIG. 2C). Then, the extracted word is compared with the point name database (FIG. 2D) stored in the information storage device 5, and the point information is extracted, so that it is automatically registered as the destination candidate. In this comparison, if there are a plurality of matches or similar ones, if these are displayed in a list and the user selects them, the user can easily select the destination by simply selecting from the candidates that appear in the conversation when actually going. Etc. can be set.

FIG. 3 is a diagram showing a process flow for extracting point information.
The conversation between users is recorded as voice data in the buffer (step S1), it is determined whether or not a voice recognition operation is performed (step S2), and when the voice recognition button is operated, the recorded data in the buffer is recognized as voice (step S1). S3). Then, the character string data obtained by the speech recognition is analyzed (step S4) and cut out for each word. Then, each word and the point name database are compared, a list of matching place names is displayed (step S5), and the user selects and sets a desired one from these.

  According to the present invention, since the user can consciously perform the point setting without speaking to the voice recognition apparatus, the industrial utility value is extremely large.

It is a figure which shows the example of the navigation apparatus which concerns on this embodiment. It is a figure explaining extraction processing of point information by voice recognition and sentence analysis. It is a figure which shows the extraction process flow of point information.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Central processing unit, 2 ... Input device, 3 ... Operation button, 4 ... Current position detection device, 5 ... Information storage device, 6 ... Output device, 7 ... Information transmission / reception device, 11 ... Recording means, 12 ... Voice recognition means , 13 ... analysis means, 14 ... control means.

Claims (2)

Storage means for storing map data including the location name;
A recording means for recording the content of the conversation;
Voice recognition means for recognizing the content of the conversation recorded in the recording means when the voice recognition button is operated;
Analyzing means for analyzing character string data obtained by voice recognition by the voice recognition means;
Control means for extracting point information by comparing the data analyzed by the analyzing means and the point name data stored in the storage means;
A navigation device comprising: In a program installed in a navigation device provided with voice recognition means,
Recording the conversation content by means of recording;
When the voice recognition button is operated, the step of recognizing the recorded conversation by the voice recognition means;
Analyzing character string data obtained by voice recognition by the voice recognition means;
A step of extracting point information by comparing the analyzed data with point name data;
The program characterized by having.

Images