JP2009271785A - Information provision method, device, and computer-readable recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide information in which user information is considered even when a user does not intentionally input user information. <P>SOLUTION: This information providing method includes: acquiring a voice generated by a user; extracting text as a keyword by referring to a voice recognition database in which information for voice recognition is stored: extracting user information by analyzing the voice by referring to a user information database in which user information is stored; and retrieving the information database to which meta data have been applied based on the extracted keyword and user information; and outputting the retrieval result. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an information providing method and apparatus and a computer-readable recording medium, and in particular, using a voice input, obtains a search keyword and a user profile or situation (hereinafter referred to as user information), The present invention relates to an information providing method and apparatus for providing information to a user from a database to which metadata is assigned using these as search queries, and a computer-readable recording medium.

  FIG. 6 shows an example of a conventional information retrieval apparatus. As shown in the figure, in view of the keywords given by the user and the user information (gender, age, etc.) stored in advance, these are used as search queries, and the metadata is searched for in the information search unit 3 using metadata. There has been reported a technique for searching for information that matches a user's input condition from the database 4 to which is provided and providing the search result (see, for example, Patent Document 1).

In addition, a method of making an input sound is also reported (for example, see Patent Document 2).
JP 2003-281178 A Japanese Patent No. 3683504

  However, the conventional information providing technology considering the user information described above is that the user is conscious of himself / herself, such as pre-registering the user information or clearly indicating that the input is the user information. There is a problem that it is necessary to input manually and the burden on the user is heavy.

  The present invention has been made in view of the above points, and provides an information providing method and apparatus capable of providing information in consideration of user information without requiring the user to input user information consciously, and a computer readable medium. An object is to provide a recording medium.

  FIG. 1 is a diagram for explaining the principle of the present invention.

The present invention (Claim 1) is an information providing method for searching and providing information based on an input search formula,
The voice input means acquires the voice generated by the user (step 1),
The voice recognition means extracts the voice as a keyword with reference to a voice recognition database storing information for voice recognition (step 2),
The voice analysis means analyzes the voice with reference to the user information database in which the user information is stored, and extracts the user information (step 3).
Based on the extracted keyword and user information, the search means searches the information database to which metadata is added (step 4),
The information presenting means outputs the retrieved result (step 5).

  FIG. 2 is a principle configuration diagram of the present invention.

The present invention (Claim 2) is an information providing apparatus for searching and providing information based on an input search formula,
Keyword input means 10 for acquiring the voice generated by the user;
Utterance content text converting means 20 for extracting speech as a keyword by referring to a speech recognition database 30 in which information for speech recognition is stored;
A user information extracting means 40 for analyzing the voice with reference to the user information database 50 storing the user information and extracting the user information;
Based on the extracted keyword and user information, an information search means 60 for searching the information database 70 to which metadata is attached;
And an information presenting means 80 for outputting the result retrieved by the information retrieving means 60.

  The present invention (Claim 3) is a computer-readable recording medium storing an information providing program for causing a computer to function as each means constituting the information providing apparatus according to Claim 2.

  As described above, according to the present invention, when a keyword is input by voice, the keyword is determined by voice recognition. On the other hand, voice analysis is performed to determine a user profile (gender, age, etc.). Thus, since the search keyword and the user profile are prepared, the user profile can be easily created and searched by performing information search using the conventional technique.

Moreover, the information provider can provide information by narrowing down the target of the user, such as advertisement distribution, and is efficient.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  FIG. 3 shows an apparatus configuration according to an embodiment of the present invention.

  The information providing apparatus shown in FIG. 1 includes a voice keyword input unit (hereinafter referred to as “keyword input unit”) 10, a voice recognition unit 20, a voice recognition DB 30, a voice analysis unit 40, a user information DB 50, and information by metadata. The search unit 60 is composed of a DB to which metadata is assigned (hereinafter referred to as “DB with metadata”) 70, and an information presentation unit 80.

  FIG. 4 is a flowchart of the operation in one embodiment of the present invention.

  The keyword input unit 10 receives a keyword input by voice (step 101).

  The speech recognition unit 20 converts the spoken keyword into text by referring to the speech recognition DB 30 in which information for recognizing speech such as a speech dictionary is stored in the input speech, and stores the text in the text memory 21 (step) 102).

  The voice analysis unit 40 extracts user information from the input voice by referring to the user information DB 50 and stores it in the user information memory 41 (step 103). The contents extracted by the voice analysis unit 40 can be considered variously such as gender, age, emotion, surrounding situation, etc., and the analysis method is not particularly limited as to how to analyze the voice and what to extract. There is a method of analysis using a plurality of types of acoustic models classified by sex, age, and the like.

  Note that step 102 and step 103 are performed simultaneously.

  The information search unit 60 using metadata reads a keyword from the text memory 21 and user information from the user information memory 41, and searches for information using existing technology from the metadata-added DB 70 to which metadata such as attributes has been assigned in advance. Process. At this time, the metadata-added DB 70 is searched for the keyword acquired from the text memory 21 and the user information acquired from the user information memory 41 using an AND condition or an OR condition (step 104).

  The information presentation unit 80 acquires the result retrieved by the information retrieval unit 60 and outputs the result to a display device or the like (step 105).

  A specific example of the above configuration will be shown below.

  FIG. 5 is a diagram showing an example in which the present invention is applied to an advertisement distribution apparatus.

  When speech is input from the speech input unit 10, the speech recognition unit 20 searches the speech recognition DB 30 based on the input speech and extracts keywords. The Web search unit 110 acquires Web information by searching Web information (Web site) from the extracted keywords. On the other hand, the voice analysis unit 40 extracts user information by voice analysis processing. The advertisement search unit 60 acquires an advertisement from the advertisement DB 70 provided with metadata using the keyword extracted by the voice recognition unit 20 and the user information extracted by the voice analysis unit 40. The advertisement presenting unit 80 presents the advertisement, and the web information presenting unit 130 presents the search result of the website on the display means of the user.

  By this processing, the user can receive advertisements that match the information to be searched and the user information of the user.

  3 and 5 can be constructed as a program, installed in a computer used as an information providing apparatus, executed, or distributed via a network.

  Further, the constructed program can be stored in a portable storage medium such as a hard disk, a flexible disk, or a CD-ROM, and can be installed or distributed in a computer.

  The present invention is not limited to the above-described embodiment, and various modifications and applications can be made within the scope of the claims.

  The present invention can be applied to information retrieval based on a retrieval formula and technology for retrieving advertisement information.

It is a figure for demonstrating the principle of this invention. It is a principle block diagram of this invention. It is a block diagram of the information provision apparatus in one embodiment of this invention. It is a flowchart of the operation | movement in one embodiment of this invention. It is an example which applied this invention to the advertisement delivery apparatus. It is a block diagram of the search device of a prior art.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Keyword input means, Keyword input part 20 Utterance content text conversion means, Speech recognition part 30 Speech recognition database 40 User information extraction means, Speech analysis part 50 User information database 60 Information search means, information search part 70 Database with metadata , Metadata giving database 80 search result presenting means, information presenting unit 110 web retrieving unit 120 web information 130 web information presenting unit

Claims (3)

An information providing method for searching and providing information based on an input search formula,
The voice input means acquires the voice generated by the user,
The voice recognition means extracts the voice as a keyword by referring to a voice recognition database in which information for voice recognition is stored,
The voice analysis means analyzes the voice with reference to a user information database in which user information is stored, and extracts user information.
A search means searches an information database to which metadata is given based on the extracted keyword and the user information,
An information providing method, wherein the information presenting means outputs the retrieved result. An information providing device for searching and providing information based on an input search formula,
Voice input means for acquiring voice generated by the user;
Utterance content text converting means for extracting the speech as a keyword with reference to a speech recognition database in which information for speech recognition is stored;
User information extracting means for analyzing the voice with reference to a user information database storing user information and extracting user information;
Based on the extracted keyword and the user information, an information search means for searching an information database provided with metadata;
Information presenting means for outputting the result retrieved by the information retrieving means;
An information providing apparatus comprising:   A computer-readable recording medium storing an information providing program for causing a computer to function as each means constituting the information providing apparatus according to claim 2.

Images