JP2002099294A - Information processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To adequately convert individual character strings according to the genre of documents when the text information stated on a homepage is converted into the speech. SOLUTION: A call accepting means 1a accepts the call by a telephone 3 from a user. A speech recognizing means 1b recognizes the speech of the user sent from the telephone 3. A homepage information acquiring means 1c acquires the corresponding homepage information when a request for accessing the prescribed homepage is made by the speech recognizing means 1b. A keyword extracting means 1d extracts the prescribed keyword included in the homepage information. A permutation means 1e permutates the character strings associated with the keyword extracted by the keyword extracting means 1d to another character strings. A speech converting means 1f converts part or all of the text information subjected to the permutation of the character strings by the permutation means 1e to the speech.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing apparatus, and more particularly, to an information processing apparatus that reads homepage information described in a markup language and provides the information to a user.

[0002]

2. Description of the Related Art In recent years, with the expansion of the Internet and the enrichment of contents, it has become possible to download and use various information from a network.

[0003]

By the way, in order to use the Internet, for example, it is necessary to purchase a personal computer and contract with a so-called provider that provides an Internet connection service, so that some expense is required. In addition, since it is necessary to master the operation of the personal computer to some extent, it is hard to say that all persons can easily use it.

[0004] In particular, since visual information is mainly used on the Internet, it is difficult to say that it is a highly practical information source for people with visual impairments and those with low vision.

In order to solve such a problem, for example, a method has been proposed in which text information described on a homepage is converted into voice by voice synthesis and output from a user's telephone through a telephone line (Japanese Patent Laid-Open No. Hei 10 (1998)). −
164249).

However, there is a problem in that simply converting text information to speech in many cases does not sufficiently recognize its meaning. The present invention has been made in view of such a point, and an object of the present invention is to provide an information processing apparatus capable of reliably converting information existing on the Internet into a recognizable voice.

[0007]

According to the present invention, in order to solve the above-mentioned problems, in an information processing apparatus 1 shown in FIG. 1, which performs a process of reading homepage information described in a markup language and providing it to a user. A request to access a predetermined homepage by the call accepting means 1a for accepting a call from the user by the telephone 3, the voice recognizing means 1b for recognizing the user's voice transmitted from the telephone 3, and the voice recognizing means 1b. Is recognized, a homepage information acquiring unit 1c for acquiring corresponding homepage information, and a keyword extracting unit 1 for extracting a predetermined keyword included in the homepage information.
d, a replacing unit 1e for replacing a character string related to the keyword extracted by the keyword extracting unit 1d with another character string, and a part or all of the text information in which the character string is replaced by the replacing unit 1e. An information processing device 1 comprising:
Is provided.

[0008] Here, the call receiving means 1a receives a call from the telephone set 3 from a user. Voice recognition means 1b
Recognizes the user's voice transmitted from the telephone 3. The homepage information acquisition unit 1c is a voice recognition unit 1.
If it is recognized by b that a request to access a predetermined homepage has been made, the corresponding homepage information is acquired. The keyword extracting means 1d extracts a predetermined keyword included in the homepage information. The replacement unit 1e replaces a character string associated with the keyword extracted by the keyword extraction unit 1d with another character string. The voice conversion unit 1f voices part or all of the text information for which the character string has been replaced by the replacement unit 1e.

In an information processing apparatus for reading homepage information described in a markup language and providing the same to a user, a call receiving means for receiving a call from the user by a telephone, and a user voice transmitted from the telephone are provided. When the voice recognition unit recognizes that a request to access a predetermined homepage has been made by the voice recognition unit, the homepage information is included in the homepage information. Keyword extracting means for extracting a predetermined keyword, adding means for adding another character string to a character string associated with the keyword extracted by the keyword extracting means, and text information to which the character string has been added by the adding means. Voice means for converting part or all of the voice. The information processing apparatus is provided, wherein.

Here, the call accepting means accepts a call from the user by telephone. The voice recognition means recognizes the user's voice transmitted from the telephone. The homepage information obtaining means obtains the corresponding homepage information when the voice recognition means recognizes that a request to access a predetermined homepage has been made. The keyword extracting means extracts a predetermined keyword included in the homepage information. The adding means adds another character string to the character string associated with the keyword extracted by the keyword extracting means. The sounding means sounds part or all of the text information to which the character string has been added by the adding means.

[0011] Further, in an information processing apparatus for performing a process of reading homepage information described in a markup language and providing the same to a user, a call accepting means for accepting a call from the user by a telephone, Speech recognition means for recognizing voice, homepage information acquisition means for acquiring corresponding homepage information when it is recognized that a request to access a predetermined homepage is made by the speech recognition means, Character string group extraction means for extracting a character string having a relationship of
For each character string group extracted by the character string group extraction means,
There is provided an information processing apparatus having:

The call accepting means accepts a call from the user by telephone. The voice recognition means recognizes voice transmitted from the telephone. The homepage information obtaining means obtains the corresponding homepage information when the voice recognition means recognizes that a request to access a predetermined homepage has been made. The character string group extracting means extracts character strings having a semantically relevant relationship from the homepage information as a group of character strings. The sounding means voices the character string group extracted by the character string group extracting means by the extracting means.

[0013]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a principle diagram for explaining the operation principle of the information processing apparatus according to the present invention. As shown in FIG. 1, an information processing apparatus 1 according to the present invention includes a call receiving unit 1a, a voice recognition unit 1b,
c, keyword extracting means 1d, replacing means 1e, and
It is constituted by the sounding means 1f.

The call receiving means 1a receives a "call" from the telephone set 3 by a user. The voice recognition means 1b
The voice transmitted from the telephone 3 is recognized. The homepage information acquisition unit 1c acquires the corresponding homepage information when the voice recognition unit 1b recognizes that a request to access a predetermined homepage has been made.

The keyword extracting means 1d extracts a predetermined keyword included in the homepage information. The replacement unit 1e replaces a character string associated with the keyword extracted by the keyword extraction unit 1d with another character string.

The voice converting means 1f voices a part or all of the text information in which the character string has been replaced by the replacing means 1e. The information processing device 1 is connected to a telephone 3 via a public network 2. The public network 2 is a telephone 3
An audio signal is transmitted and received between the information processing apparatus 1 and the information processing apparatus 1. The telephone 3 converts the utterance of the user into a corresponding electric signal and transmits the electric signal to the information processing apparatus 1 via the public network 2.

The Internet 4 transmits information such as texts, images, and voices between the information processing device 1 and the server 5. The server 5 is a web server, for example, an HTM
The homepage information described in a markup language such as L is transmitted from the information processing apparatus 1 in response to a request.

Next, the operation of the above principle diagram will be described. Now, assuming that the user goes off-hook on the handset of the telephone 3 and makes a call to the telephone number given to the information processing device 1, a call signal is sent to the information processing device 1 via the public network 2. .

The call receiving means 1a receives a call from the telephone 3. As a result, the communication line is closed between the telephone 3 and the information processing device 1, and communication can be performed between them.

After the communication line is closed in this way,
When the user of the telephone 3 utters, for example, "Connect to the homepage of company XX", this voice signal is sent to the voice recognition means 1b via the public network 2.

The voice recognition means 1b recognizes that the content of the utterance is a request for connection to the homepage of the company XX by voice recognition processing, and notifies the homepage information acquisition means 1c of the request.

The homepage information obtaining means 1c obtains homepage information (for example, information described in HTML) of the company X via the Internet 4 from the server 5.

The keyword extracting means 1d acquires a predetermined keyword from the text information included in the homepage information acquired from the homepage information acquiring means 1c. The keywords include, for example, “baseball”, “record”, “impressionism”, “computer” and the like for specifying the genre of the document described on the homepage.

If the character string "computer" is included in the homepage information of company XX, "computer" is extracted as a keyword. As a result, it is recognized that this home page is a page related to the computer.

The replacement unit 1e extracts a specific character string that needs to be replaced according to the genre included in the homepage information, and replaces the character string with another character string.
In the present example, the genre is “computer”, so if “ROM” exists in the document, it is replaced by “rom”.

The voice converting means 1f voices the text information replaced by the replacing means 1e and transmits the voice information to the telephone 3 via the public network 2. As a result, telephone 3
Can hear the voice corresponding to the text information. At this time, since the above-mentioned ROM is uttered as "Rom" instead of "ROM", it is possible to accurately understand the contents described in the text information.

As described above, according to the embodiment of the present invention, the genre of the document is specified by the keyword included in the text information obtained from the desired homepage, and the genre of the document is specified. Accordingly, a specific character string is replaced with another character string and voiced, so that appropriate utterance is possible, and it is possible to encourage the user to understand.

Next, an embodiment of the present invention will be described. FIG. 2 is a diagram illustrating a configuration example of the embodiment of the present invention. In this figure, a telephone 10 is installed on a user side, converts a user's utterance into a corresponding electric signal, transmits the signal to an information processing device 12 via a public network 11, and has been transmitted from the information processing device 12. The audio signal is converted into a corresponding audio and output.

When a call is made from the telephone 10 via the public network 11, the information processing apparatus 12 closes the communication line with the telephone 10, and provides home page information in response to a voice request from the user. Is obtained from the server 17, and after performing predetermined processing, is converted to voice and transmitted to the telephone 10.

The Internet 16 is, for example, an HTTP (Hyper Text T) between the server 17 and the information processing apparatus 12.
ransfer Protocol), which transmits and receives homepage information including text, images, audio, and the like.

The server 17 is a web server,
It records homepage information described in ML etc.,
In response to a request from the information processing device 12, the corresponding page is read and provided.

FIG. 3 is a diagram showing a detailed configuration example of the information processing apparatus 12 shown in FIG. As shown in this figure, the information processing apparatus 12 is roughly divided into a voice response unit 13 for performing processing with the telephone 10, a browsing unit 14 for controlling download of homepage information, and an analysis of the downloaded homepage information. HTML analysis unit 1
5.

Here, the voice response unit 13 is a voice recognition unit 1
3a, dial recognition unit 13b, and voice synthesis unit 13
c. The voice recognition unit 13a recognizes a voice signal from the telephone 10 and performs a telephone operation analysis unit 14a.
To the recognition result.

When the dial of the telephone 10 is operated, the dial recognizing unit 13b recognizes the content of the operation,
Notify the telephone operation analysis unit 14a. Voice synthesizer 13c
Converts the text information supplied from the keyword extraction unit 15d into a corresponding audio signal under the control of the audio reproduction control unit 14b, and transmits the audio signal to the telephone 10 via the public network 11.

The browsing unit 14 includes a telephone operation analysis unit 14a, a voice reproduction control unit 14b, a hyperlink control unit 14c, and a control unit 14d in the same URL.

The telephone operation analysis unit 14a analyzes a request made by a user by voice or dial operation, and notifies the analysis result to the voice reproduction control unit 14b, the hyperlink control unit 14c, and the control unit 14d in the same URL. I do.

The voice reproduction control unit 14 b
c to control the speech synthesis processing. The hyperlink control unit 14c requests the server 17 to transmit predetermined homepage information.

The control unit 14d in the same URL moves from a predetermined line to the next line in the same homepage,
Controls movement to another paragraph. The HTML analysis unit 15 includes a component analysis unit 15a, a text extraction unit 15
b, a hypertext extraction unit 15c, and a keyword extraction unit 15d.

The component analysis unit 15a analyzes the components of the home page information. The text extracting unit 15b extracts text from homepage information based on the analysis result of the component analyzing unit 15a.

The hypertext extracting unit 15c extracts hypertext, which is a linked text, from the homepage information based on the analysis result of the component analyzing unit 15a.

The keyword extracting unit 15d extracts a keyword from text or hypertext and supplies the keyword to the speech synthesizing unit 13c. Next, the operation of the embodiment of the present invention will be described.

FIG. 4 is a flowchart for explaining the flow of processing from the time when the information processing device 12 receives a call from the telephone 10 to close a line, executes a predetermined process, and closes the line. . When this flowchart starts,
The following processing is performed. [S1] The information processing apparatus 12 proceeds to step S2 when receiving (calling) a call from the user, and otherwise repeats the same processing. [S2] The telephone operation analysis unit 14a receives, for example, a password transmitted by a user operating a dial, and performs user authentication as to whether or not the user is a valid user.

Note that this authentication processing can be omitted. [S3] If the voice recognition unit 13a has input the user's voice, the process proceeds to step S4; otherwise, the same process is repeated. [S4] The voice recognition unit 13a performs a process of recognizing the received voice. [S5] The browsing unit 14 executes a process corresponding to the recognition result in step S4. Note that, specifically, when a connection request to a predetermined homepage is made, the hyperlink control unit 14c executes downloading of the corresponding homepage. [S6] The information processing apparatus 12 determines whether or not to end the processing. If the processing is ended, the process proceeds to step S7. Otherwise, the process returns to step S3 and repeats the same processing.

For example, it is determined whether or not the user disconnects the communication line by hooking the handset of the telephone 10 on. If the user disconnects the communication line, the process is terminated, and the process proceeds to step S7. [S7] The information processing device 12 executes a process of disconnecting the communication line connected to the telephone 10.

According to the above-described processing, the user operates the telephone 10
It is possible to cause the information processing device 12 to execute a process according to the content uttered via the dial or the operation content of the dial. Next, a description will be given of a process of replacing a predetermined character string included in text information of a homepage with an appropriate character string according to the genre of the document.

FIG. 5 is a flowchart illustrating an example of a process for replacing a character string according to the genre of a document.
When this flowchart is started, the following processing is executed. [S20] The hyperlink control unit 14c acquires homepage information related to the predetermined homepage requested by the user's voice.

For example, a home page as shown in FIG. 6 is obtained in response to a user request. [S21] The component analysis unit 15a analyzes the attribute of the acquired homepage information.

In the example shown in FIG. 6, the display area 30a of the window 30 is composed of "genre: motor sports ..." as text information and a car image. Obtained as an attribute of [S22] The text extraction unit 15b performs the component analysis unit 1
The text information is extracted from the homepage information based on the analysis result of 5a.

In the example of FIG. 6, "genre: motor sports ..." is acquired as text information. [S23] The keyword extracting unit 15d extracts a keyword from the homepage information.

Specifically, the keyword extracting unit 15d
The keywords corresponding to the first to fourth search words in the table shown in FIG. 7 are extracted. Note that, in this table, the word before the replacement at the left end is the word to be replaced,
The word after replacement is the word after replacement. Also, the first
The fourth search word is a keyword for determining the genre of the document.

In the example of FIG. 6, since the keyword "motor sports" is included in the text information, the second and third elements of the table are applicable items. [S24] The speech synthesizing unit 13c outputs the keyword
With reference to the keyword supplied from d, the word before replacement is replaced with the word after replacement.

In the example of FIG. 6, the text information includes "F
Since “1” and “GP” are included, these are replaced with “F1” and “Grand Prix”, respectively. [S25] The speech synthesis unit 13c determines whether or not all the replacement processes have been completed.
Otherwise, the process returns to step S23 to repeat the same processing. [S26] The speech synthesizer 13c converts the text information, for which the replacement process has been completed, into speech, and transmits the speech to the telephone 10.

In the example shown in FIG. 6, the text "F1 GP final qualifying result" is converted into the voice "F1 Grand Prix Rehearsal". By the way, FIG.
In the example of the above, “2000/6/20” indicating the date is displayed on the right side of the title “F1 GP final qualifying result”. Such a display can be replaced by the above-described processing. Specifically, when three numbers are arranged separated by a slash “/”, the first slash is set to “year” and the second slash is set to “year”.
Make sure that the slash is read as "month". Further, if "day" is added at the end after such replacement, a natural utterance is obtained. Various other examples of such an example can be considered. For example, when a character string "1/3" indicating a page is displayed at the bottom of the page, this is replaced with "Sambun noichi". , "Page" at the end, and so on.

In the above embodiment, the genre of the document is specified first by using the search word as a keyword. However, after the search for the word before replacement is performed first, it is determined whether a keyword corresponding to the search word exists. Needless to say, the determination may be made. The search word is 4
Needless to say, there may be more than one.

Next, the operation of the second embodiment of the present invention will be described. Note that the configuration example of the second embodiment of the present invention is the same as the case of FIGS.

First, as a story at a pre-stage before starting a description of a specific process, consider a case where a home page as shown in FIG. In the homepage shown in this figure, the display area 40a of the window 40 includes
The menu items include the hyperlinked text strings "Ink Painting", "Oil Painting", "Sculpture", "Watercolor Painting",
“Prints”, “etching”, and “others” are displayed. Therefore, when such menu items are converted to voice, the voice “menu” is followed by the voice “suibokuga”, the voice “Abrae”, and so on. However, it is incomprehensible from hearing such sounds that these sounds are menu selection items. Therefore, in the present embodiment, an item with a hyperlink is treated as a group of character strings, and a predetermined explanatory sentence (for example, “Next,
Read the menu. There are seven choices. )) And uttering a group of character strings collectively, it is possible to provide a user-friendly environment.

Next, a flow chart for explaining an example of processing for enabling the above operation will be described with reference to FIG. When the flowchart shown in FIG. 9 is started, the following processing is executed. [S40] The hyperlink control unit 14c requests acquisition of homepage information requested by voice from the user. [S41] The component element analysis unit 15a analyzes the elements of the homepage information transmitted from the server 17 by the processing in step S40.

Here, the element means an element surrounded by an HTML tag. [S42] The component analysis unit 15a extracts an element. [S43] The component analyzing unit 15a determines whether or not the tag is a tag with <HREF> indicating a hyperlink. If so, the process proceeds to step S44; otherwise, the process proceeds to step S45. . [S44] The component analysis unit 15a counts the number n of <HREF> elements, and returns to step S43.

In the example of FIG. 8, the number of texts with hyperlinks is ink painting and the other seven, so the number n of elements is "7". [S45] The component analysis unit 15a calculates the number of elements n
Through the text extraction unit 15b to the speech synthesis unit 13c
Output to [S46] The component analysis unit 15a extracts a fixed text.

That is, in the example of FIG. 8, "ink painting" and others are extracted as fixed text. [S47] The component analysis unit 15a adds an explanatory note before and after the fixed text. For example, in the example of Fig. 8, before the fixed text "ink painting" and others, "Next, read the menu. There are seven selection items." Do you want to add? " [S48] The voice synthesizer 13c voices the fixed text to which the description is added.

In the example shown in FIG. 8, the sound "Tsugini, menu @ Yomiagemas. Sentakukomokuhananatsudesu" is uttered, followed by the sound "Suibokuga, Aburae, ...", and finally the sound "Ijo Nonanatsudes" .Drecentakshimasuka. "Is spoken.

According to the above-described embodiment, when a plurality of texts with hyperlinks are displayed, these are grouped into a group of character strings, and an explanatory sentence is added before and after the group to collectively. Since the user speaks, a group of character strings such as menu selection items can be presented to the user in an easy-to-understand manner.

Next, a third embodiment of the present invention will be described. Note that the configuration example of the third embodiment of the present invention is the same as that of FIGS. First, as a pre-stage story before starting a description of a specific process, for example, consider a case where a home page as shown in FIG. In the homepage shown in this figure, a table indicating the stock market is displayed in the display area 50a of the window 50. When such a table is vocalized, first, "code" indicating the element name, "brand name", "open price", "high price", "low price" are uttered,
Each element will be uttered in order from left to right and from top to bottom. However, it is difficult to recognize what kind of element corresponds to a certain element by simply converting the table to speech. Therefore, in the third embodiment of the present invention, when each element is uttered, the element name is uttered before that element to avoid such a problem.

Next, a flow chart for explaining the flow of processing for realizing the above operation will be described with reference to FIG. [S60] The hyperlink control unit 14c reads homepage information requested by voice from the user. [S61] The component element analysis unit 15a analyzes the elements of the homepage information transmitted from the server 17 by the processing in step S60. [S62] The component analysis unit 15a determines whether or not the element tag is a table tag. If the element tag is a table tag, the process proceeds to step S63; otherwise, the process proceeds to step S68. [S63] The component analysis unit 15a determines whether or not the elements in each column are the same, that is, whether or not the table is a table composed of the same elements. Otherwise, the process proceeds to step S68.

Here, it is determined whether or not the elements of the column are the same.
The determination is made based on whether data of the same format (numerals, kanji, kana, alphanumerics, etc.) are arranged, or whether the lengths of the data are the same or similar.

The reason for judging the identity of the elements in the column in this way is to prevent the conversion of voice by adding element names to different elements. [S64] The component analyzing unit 15a determines whether or not the leading “tr” tag has been detected. If the leading tr tag has been detected, the process proceeds to step S65. Otherwise, the process proceeds to step S66. Proceed to.

FIG. 12 shows an HT corresponding to the display example of FIG.
FIG. 3 is a diagram illustrating an example of an ML document. As shown in this figure,
Since the tag indicating the element name of the table is arranged at the top and is surrounded by the tag <tr> and the tag <tr />, when the first tag <tr> is detected, The process proceeds to step S65 assuming that the name is a name. [S65] The component analysis unit 15a saves each piece of text data corresponding to the element name, and returns to step S64.

In the example shown in FIG. 10, the text "code", "brand name" and others are saved. [S66] The component analysis unit 15a determines whether the end of the table tag has been reached. In the example shown in FIG. 12, the table definition starts with <table> and </ table>
, So if </ table> is detected,
It is determined that the table has ended, and the process proceeds to step S68. Otherwise, the process proceeds to step S67. [S67] The component element analysis unit 15a checks each save data
A process for synthesizing each text is executed, and step S64 is performed.
Return to

In the example of FIG. 10, for example, the element name “code” and “4062” are synthesized. [S68] The speech synthesis unit 13c executes a process of converting the synthesized text into speech.

As a result, in the example of FIG. 10, for the element on the first line, “code 4062 Meigaramei Marbatkinzoku Hajimene 1985 Takane 2020
Yasune 1928 "will be uttered.

According to the above-described embodiment, when a home page on which a table is described is vocalized, an element name is uttered before each element is uttered. It is possible for the user to easily recognize.

In the above embodiment, the case where the element names are given only to the column elements has been described as an example.
The same processing can be applied to a case where only a row element is added. If an element name is added to both a column element and a row element, speak the column element name, the row element name, or the row element name and the column element name in that order, and then speak the element. What should I do?

Finally, the above processing functions can be realized by a computer. In this case, the processing contents of the functions that the information processing apparatus should have are described in a program recorded on a computer-readable recording medium, and the above processing is realized by the computer by executing the program on the computer. Is done. Examples of the computer-readable recording medium include a magnetic recording device and a semiconductor memory. When distributing to the market,
The program is stored and distributed in a portable recording medium such as a CD-ROM (Compact Disk Read Only Memory) or a flexible disk, or stored in a storage device of a computer connected via a network, and is stored in another storage device via the network. It can also be transferred to a computer. When the program is executed by the computer, the program is stored in a hard disk device or the like in the computer, and is loaded into the main memory and executed.

[0074]

As described above, according to the present invention, in an information processing apparatus for reading homepage information described in a markup language and providing the same to a user, call receiving means for receiving a call from a user by a telephone is provided. Voice recognition means for recognizing a user's voice transmitted from the telephone, and homepage information for acquiring corresponding homepage information when the voice recognition means recognizes that a request to access a predetermined homepage has been made. Obtaining means, keyword extracting means for extracting a predetermined keyword included in the homepage information, replacing means for replacing a character string associated with the keyword extracted by the keyword extracting means with another character string, and replacing means Sounds part or all of the text information for which the string And sound means for reduction, since to have, depending on the genre of the document, it is possible to sound appropriately strings.

Also, in an information processing apparatus for reading homepage information described in a markup language and providing the same to a user, a call receiving means for receiving a call from a telephone from a user; Speech recognition means for recognizing the voice, when the speech recognition means recognizes that a request to access a predetermined homepage has been made, homepage information acquisition means for acquiring the corresponding homepage information, and Keyword extracting means for extracting a predetermined keyword, adding means for adding another character string to a character string associated with the keyword extracted by the keyword extracting means, and text having a character string added by the adding means. Voice means for converting part or all of the information into voice. This makes it possible for a user to easily recognize the original meaning by adding another character string that supplements a character string that is difficult to understand only by voice conversion. Become.

Further, in an information processing apparatus for reading homepage information described in a markup language and providing the information to a user, a call receiving means for receiving a call from the user by a telephone, Speech recognition means for recognizing voice, homepage information acquisition means for acquiring corresponding homepage information when it is recognized that a request to access a predetermined homepage is made by the speech recognition means, Character string group extraction means for extracting a character string having a relationship of
For each character string group extracted by the character string group extraction means,
Since it has a voice conversion means for voice conversion, it is possible to voice the homepage in an easily understandable manner.

[Brief description of the drawings]

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

FIG. 2 is a diagram illustrating a configuration example of an embodiment of the present invention.

FIG. 3 is a detailed configuration example of the information processing apparatus shown in FIG. 2;

FIG. 4 is a flowchart illustrating an example of a process from receiving a call to disconnecting the call in the embodiment shown in FIG. 3;

FIG. 5 is a flowchart illustrating an example of a character string replacement process.

FIG. 6 is a display example of a homepage to be processed in the flowchart shown in FIG. 5;

FIG. 7 is an example of a table for replacing a character string.

FIG. 8 is a display example of a home page including hypertext.

FIG. 9 is a flowchart illustrating an example of a process of extracting a hypertext as a group of character strings, inserting an explanatory sentence before and after, and speaking.

FIG. 10 is a display example of a home page including a table.

FIG. 11 is a flowchart illustrating an example of a process of speaking an element name before speaking a table element.

FIG. 12 is an HTM corresponding to the homepage shown in FIG.
It is an example of an L document.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Information processing apparatus 1a Call accepting means 1b Speech recognition means 1c Homepage information acquisition means 1d Keyword extraction means 1e Substitution means 1f Voice conversion means 2 Public network 3 Telephone 4 Internet 5 Server 10 Telephone 11 Public network 12 Information processing apparatus 13 Voice response unit 13a Voice recognition unit 13b Dial recognition unit 13c Voice synthesis unit 14 Browsing unit 14a Telephone operation analysis unit 14b Voice reproduction control unit 14c Hyperlink control unit 14d Control unit within the same URL 15 HTML analysis unit 15a Component analysis unit 15b Text extraction unit 15c Hypertext extractor 15d Keyword extractor 16 Internet 17 Server

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G06F 17/30 310 G06F 17/30 370Z 5K051 370 H04M 3/00 B 5K101 G10L 15/00 3/42 P 15 / 28 3/493 21/06 3/50 A H04M 3/00 11/00 303 3/42 G10L 3/00 E 3/493 551P 3/50 S 11/00 303 F term (reference) 5B075 KK07 ND16 PP07 PP13 PP22 PQ04 PQ36 PR06 UU40 5D015 KK01 5D045 AA20 AB26 5K015 AA07 AB01 AE01 AF08 5K024 AA21 BB01 BB02 CC01 CC10 DD01 GG01 5K051 AA08 BB02 CC01 DD01 GG03 GG17 HH15 HH19 5K101 NN02NN01

Claims (13)

[Claims] 1. An information processing apparatus for reading homepage information described in a markup language and providing it to a user, comprising: a call accepting unit for accepting a call from a user by a telephone; and a user transmitted from the telephone. Voice recognition means for recognizing the voice of the user; homepage information obtaining means for obtaining corresponding homepage information when it is recognized that a request to access a predetermined homepage has been made by the voice recognition means; Keyword extraction means for extracting a predetermined keyword included in the keyword information; substitution means for replacing a character string associated with the keyword extracted by the keyword extraction means with another character string; Speech some or all of the replaced text information An information processing apparatus, comprising: a voice generator. 2. The information processing apparatus according to claim 1, wherein the keyword is a word considered to indicate an attribute of predetermined text information included in the homepage. 3. A computer-readable recording medium storing a program for causing a computer to read homepage information described in a markup language and provide the same to a user. Call accepting means; voice recognizing means for recognizing a user's voice transmitted from the telephone; when the voice recognizing means recognizes that a request to access a predetermined homepage has been made, the corresponding homepage information is displayed. Homepage information acquisition means to acquire, keyword extraction means to extract a predetermined keyword included in the homepage information, substitution means to replace a character string related to a keyword extracted by the keyword extraction means with another character string The replacement means Therefore speech means, computer-readable recording a program to function as a recording medium for audio of some or all of the text information substitution is made of a string. 4. A program which causes a computer to read homepage information described in a markup language and provide the same to a user, the computer comprising: a call receiving unit for receiving a call from the user via a telephone; Voice recognition means for recognizing the voice of the user who has received, when the voice recognition means recognizes that a request to access a predetermined homepage has been made, homepage information obtaining means for obtaining corresponding homepage information; Keyword extracting means for extracting a predetermined keyword included in information; replacing means for replacing a character string associated with the keyword extracted by the keyword extracting means with another character string; replacing a character string by the replacing means Of the text information Program for causing to function part or all as, audio means for voiced. 5. An information processing apparatus for reading homepage information described in a markup language and providing the same to a user, comprising: a call accepting unit for accepting a call from a telephone from a user; Voice recognition means for recognizing voice; homepage information obtaining means for obtaining corresponding homepage information when it is recognized that a request to access a predetermined homepage has been made by the voice recognition means; Keyword extracting means for extracting a predetermined keyword included; adding means for adding another character string to a character string related to the keyword extracted by the keyword extracting means; Voice to convert part or all of the added text information An information processing apparatus, comprising: 6. A computer-readable recording medium on which a program for causing a computer to read homepage information described in a markup language and provide the same to a user is provided. Call accepting means; voice recognizing means for recognizing a user's voice transmitted from the telephone; when the voice recognizing means recognizes that a request to access a predetermined homepage has been made, the corresponding homepage information is displayed. Means for acquiring homepage information to be acquired; keyword extraction means for extracting a predetermined keyword included in the homepage information; and addition of another character string to a character string related to the keyword extracted by the keyword extraction means. Means, said addition A computer-readable recording medium characterized in that the functioning of the part or all of the text information is a character string added by stage speech means for voice as,. 7. A program for causing a computer to read homepage information described in a markup language and provide the same to a user, the program comprising: a call receiving unit for receiving a call from the user by a telephone; Voice recognition means for recognizing the voice of the user who has received, when the voice recognition means recognizes that a request to access a predetermined homepage has been made, homepage information obtaining means for obtaining corresponding homepage information; Keyword extracting means for extracting a predetermined keyword included in the information; adding means for adding another character string to a character string associated with the keyword extracted by the keyword extracting means; Of the added text information Program for causing to function part or all as, audio means for voiced. 8. An information processing apparatus for performing a process of reading homepage information described in a markup language and providing the same to a user, comprising: a call accepting unit for accepting a call from a user by a telephone; and a user transmitted from the telephone. Voice recognition means for recognizing the voice of the user; homepage information obtaining means for obtaining corresponding homepage information when it is recognized that a request to access a predetermined homepage has been made by the voice recognition means; Character string group extraction means for extracting a character string having a semantically relevant from the group as a group of character strings, and voice conversion means for vocalizing in units of the character string group extracted by the character string group extraction means, An information processing apparatus, comprising: 9. The method according to claim 8, wherein when a group of character strings with hyperlinks is present, the character string group extracting unit extracts these character strings as one character string group. An information processing apparatus according to claim 1. 10. A related character string adding means for adding a predetermined character string related to the character string group before or after the character string group, wherein the voice conversion means adds the related character string. The information processing apparatus according to claim 8, wherein the group of character strings is converted to speech. 11. The character string group is a character string group forming a table, and the related character string adding means adds an element name forming the table before or after each element. The information processing apparatus according to claim 10, wherein 12. A computer-readable recording medium storing a program for causing a computer to read homepage information described in a markup language and provide the same to a user. Call accepting means; voice recognizing means for recognizing a user's voice transmitted from the telephone; when the voice recognizing means recognizes that a request to access a predetermined homepage has been made, the corresponding homepage information is displayed. Homepage information acquisition means to be acquired; a character string group extraction means for extracting a character string having semantic relevance from the homepage information as a group of character strings; and a character string group extracted by the character string group extraction means. Voice conversion means for voice, A computer-readable recording medium a program for. 13. A program that causes a computer to read homepage information described in a markup language and provide the same to a user, the computer comprising: a call receiving unit that receives a call from the user via a telephone; Voice recognition means for recognizing the voice of the user who has received, when the voice recognition means recognizes that a request to access a predetermined homepage has been made, homepage information obtaining means for obtaining corresponding homepage information; Character string group extracting means for extracting a character string having a semantically relevant information from the information as a group of character strings; and sounding means for vocalizing each character string group extracted by the character string group extracting means. A program characterized by causing