JP2004234095A - Portable terminal device and information retrieval providing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a portable terminal device and an information retrieval providing method for acquiring information matching interest of a user from a network, interpreting the information, and processing it into information matching the interest of the user for providing it by voice. <P>SOLUTION: This information retrieval providing method includes steps for: extracting interest information relating to the interest of the user; searching a site via a network according to the extracted interest information and reading information provided by the site; extracting a keyword from the information read from the site according to the interest information; generating a word representing information satisfying the user interest according to the extracted keyword; converting the word generated in the previous step into voice data; and uttering voice on the basis of the the converted voice data. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a mobile terminal device that acquires information from a network, interprets the acquired information, and transmits the information to a user, and an information search providing method.
[0002]
[Prior art]
For example, Patent Literature 1 discloses an invention of an information search system that performs interactive information exchange with a user via a mascot character. According to the technology described in Patent Literature 1, a user connects to an information search system via a network from a personal computer having a user interface unit, and the information search system reflects the registered user information in the search result. Then, the advice is further added, and the advice is provided to the user via a mascot character realized in the user interface unit. Since the information is provided through the mascot character in this way, even a beginner unfamiliar with a personal computer can operate with a familiarity.
[0003]
[Patent Document 1]
JP 2001-222538 A
[0004]
[Problems to be solved by the invention]
However, in the invention described in Patent Literature 1, information on the network is searched based on user information registered in a fixed manner, so that the user's tastes are diverse and only based on data at the time of registration. Furthermore, information that matches the individual's taste, which can be said to be fluid, is not always retrieved in a timely manner. In addition, although the method of providing information to the user is via the mascot character, the information is interpreted according to the user's taste by simply displaying the acquired information on the screen as it is or with further advice, and newly adding the user's taste. Is not provided to the user by voice.
[0005]
The present invention has been made in view of the above points, and obtains information that matches a user's personal taste from a network, interprets this information, and further processes the information into information that matches the user's taste to produce a voice. To provide a mobile terminal device and an information search providing method that can be provided by the method.
[0006]
[Means for Solving the Problems]
According to the first aspect of the present invention, there is provided a portable terminal device for extracting preference information associated with a user's preference, and searching or referring to a site based on the preference information from a network, and providing the site. Site search means for reading information; keyword extraction means for extracting a keyword based on the taste information from the information read from the site; and a phrase representing information for satisfying a user's taste based on the keyword is generated. It is characterized by comprising a phrase generation unit, a voice data generation unit that converts the phrase generated by the phrase generation unit into voice data, and a voice pronunciation unit that generates a voice based on the voice data.
[0007]
According to a second aspect of the present invention, in the portable terminal device according to the first aspect, the preference information extracting unit extracts the preference information from a bookmark in which a site address is registered or a browsing history of the site. It is characterized by:
[0008]
According to a third aspect of the present invention, in the portable terminal device according to the first aspect, the preference information extracting means extracts the preference information from a mail text described by a user or a received mail text received. It is characterized by.
[0009]
According to a fourth aspect of the present invention, in the portable terminal device according to the first aspect, the preference information extracting unit uses data input by the user as preference information.
[0010]
According to a fifth aspect of the present invention, in the portable terminal device according to any one of the first to fourth aspects, at least tone of the mascot character is set for each mascot character set on the portable terminal device. A vocabulary database is further defined, and the speech data generating means performs the conversion based on the vocabulary database.
[0011]
According to a sixth aspect of the present invention, in the portable terminal device according to any one of the first to fifth aspects, the voice data generating means is configured to determine a pitch when the voice is generated by the voice generating means. It is characterized in that audio data to which data is added is generated.
[0012]
An information retrieval providing method according to the present invention is a method executed by a computer system, comprising: a step of extracting taste information related to a user's taste; and a site based on the taste information from a network. Searching for information provided by the site, extracting a keyword from the information read from the site based on the preference information, and representing information for satisfying the user's preference based on the keyword. It is characterized by including a step of generating a phrase, a step of converting the phrase generated in the previous step into voice data, and a step of generating a voice based on the voice data.
[0013]
In the present invention, the preference information extraction means extracts preference information related to the user's preference, and the site search means searches or refers to a site from the network based on the preference information and reads out information provided by the site. . Then, when the keyword extracting unit extracts a keyword from the information read from the site based on the taste information, the phrase generating unit generates a phrase representing information for satisfying the user's taste based on the keyword. The generated phrase representing information for satisfying the user's taste is converted into voice data by the voice data generation unit, and the voice pronunciation unit generates a voice based on the voice data.
[0014]
In the invention described in claim 2, the preference information extracting means extracts the preference information from a bookmark in which a site address is registered or a browsing history of the site. In this case, the preference information is extracted from the mail text described by the user or the received mail text received. In the invention according to claim 4, data input by the user is used as the preference information.
In this way, a phrase representing information for satisfying the user's taste is generated based on the obtained taste information and is transcribed, so that the user can use his or her own taste without any trouble. It is possible to receive the information of interest that matches by voice.
[0015]
Further, in the invention according to claim 5, for each mascot character set on the portable terminal device, a vocabulary database that defines at least the tone of the mascot character is further provided, and the voice data generation means includes: Based on the vocabulary database, the phrase generated by the phrase generation unit is converted into voice data. As a result, the mascot character pronounces with each voice (for example, each tone) and becomes interesting and user-friendly.
Further, in the invention according to claim 6, the voice data generating means generates voice data to which pitch data at the time of generating a voice by the voice generating means is added. As a result, it is possible to change the pitch of the sound to be pronounced. For example, it is also possible to cause the sound to be pronounced like a humming song, which is more user-friendly.
[0016]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a schematic configuration of a mobile phone as an embodiment of the mobile terminal device of the present invention. The mobile terminal device of the present invention is not limited to a mobile phone, and may be configured using a PHS (registered trademark) (Personal handyphone system) or a mobile information terminal that can be wirelessly connected to a network.
[0017]
In FIG. 1, reference numeral 11 denotes a CPU (Central Processing Unit), which controls the operation of each unit of the portable terminal device 1 by executing various control programs.
A communication unit 12 demodulates a signal received by an antenna 12a provided in the communication unit 12, modulates a signal to be transmitted, and supplies the modulated signal to the antenna 12a.
The CPU 11 decodes a signal from a network such as the Internet demodulated by the communication unit 12 in accordance with a predetermined protocol, and processes information included in the signal or the information to suit the user's taste. Information (to be described later) and an image of the mascot character are displayed on the display unit 21 described below, and the sound source unit 16 with a voice synthesis function described below is synthesized by voice. The data to be transmitted to the access destination site is encoded by the CPU 11 according to a predetermined protocol, modulated by the communication unit 12, and then transmitted from the antenna 12a to the base station toward the access destination site. Is done.
[0018]
Reference numeral 13 denotes an audio processing unit. The telephone line signal demodulated by the communication unit 12 is decoded by the audio processing unit 13 and output from the speaker 14. On the other hand, the audio signal input from the microphone 15 is digitized and compression-encoded in the audio processing unit 13. The signal is modulated by the communication unit 12 and output from the antenna 12a to the base station of the mobile phone network. The audio processing unit 13 performs high-efficiency compression encoding / decoding of audio data by, for example, a CELP (Code Excited LPC) system or an ADPCM (adaptive differential PCM encoding) system.
[0019]
Reference numeral 16 denotes a sound source unit with a voice synthesizing function, which reproduces music data selected as a ringtone and emits the sound from a speaker 17. Also, when receiving audio data composed of information suitable for the user's taste (or information processed to meet the user's taste) and required parameters (hereinafter, the voice data includes the required parameters) ), And synthesizes this voice to generate a sound (speak) from the speaker 17. The speech synthesis by the sound source unit 16 with the speech synthesis function can be realized by applying, for example, a CSM speech synthesis technique disclosed in Japanese Patent Publication No. 58-53351 to an FM sound source.
Reference numeral 18 denotes an operation unit, which is an input unit that detects input from various buttons (not shown) including an alphanumeric button provided on the main body of the mobile phone 1 and other input devices.
[0020]
Reference numeral 19 denotes a RAM (Random Access Memory), which is a work area for the CPU 11, a storage area for downloaded music data and accompaniment data, a mail data storage area for storing received e-mail data, A storage area for storing information downloaded from the site and data obtained by processing this information, a storage area for storing bookmarks for registering site addresses, and a site browsing history consisting of data such as the address of the site visited and its title. Is further set, and a user preference information database described later is stored.
[0021]
Reference numeral 20 denotes a ROM (Read Only Memory). The ROM 20 includes various telephone function programs for controlling outgoing / incoming calls, a program for assisting music reproduction processing, a mail transmitting / receiving function program for controlling transmission / reception of e-mail, and a mail transmission / reception function program executed by the CPU 11. A program for connecting to a network, such as a program, and information therefor, a program for registering taste information related to a user's taste in a user taste information database, and a program that matches a user's taste from a network based on this user taste information database Various programs such as a program for acquiring information, interpreting it and processing it into words representing information to satisfy the user's taste, a program for assisting speech synthesis processing, and a mascot to be further displayed on the display unit 21 described below. CG (Computer Graphics) Data, a Japanese dictionary database described later, a vocabulary database including data defining parameters (required parameters) defining words and phrases defining the tone of the mascot character, and volume and pitch when the voice is synthesized. Are stored.
[0022]
The display unit 21 is formed of an LCD (Liquid Crystal Display) or the like, and is controlled by the CPU 11 to display a menu or the like, information downloaded from a site, an image of a mascot character, and the user's preference. It is a display for displaying the displayed information and the like and displaying according to the operation of the operation unit 18.
Reference numeral 22 denotes a vibrator for notifying the user of the incoming call by vibrating the main body of the mobile phone 1 in place of a ring tone at the time of an incoming call, and for giving a vibration when asking the user for information search as described later.
Each functional block exchanges data and instructions via the bus 30.
The mobile phone 1 according to the present embodiment is configured as described above.
[0023]
The mobile phone 1 according to the present embodiment acquires information suitable for the user's taste from a site on the network, interprets this information, and processes the word into a word representing information for satisfying the user's taste. It is a feature. The extraction of the preference information related to the user's preference and the storage thereof will be described here.
In the present embodiment, the CPU 11 extracts or receives input of preference information and registers it in the user preference information database by the following three methods (see FIG. 2).
[0024]
{Circle around (1)} Words registered in the Japanese dictionary database are extracted from a character string included in a mail sentence created by the user or a received mail sentence, and words that appear more frequently are registered as taste information in the user taste information database.
{Circle around (2)} Register the address (IP address or URL (Uniform Resource Locator) and the title of a site with a high number of browsing from the user's site browsing history in the user preference information database.
{Circle around (3)} The user himself / herself directly inputs words, character strings, and site addresses of matters of interest and registers them in the user preference information database.
[0025]
Here, the user preference information database, the Japanese dictionary database and the vocabulary database will be described in detail.
In the user preference information database, as described above, words / character strings related to the user's preference, the address of the site, and the title thereof are appropriately registered as the preference information. Note that the preference information registered in the user preference information database is registered with a weight according to the degree to which the information frequently appears. For example, the frequency of appearance or input is set as the weight of the preference information and registered in association with the preference information. By doing so, it is possible to prioritize the selection of the preference information according to the weight.
[0026]
In the Japanese dictionary database, related words are registered for each genre, and sentences (or phrases) that are related pronunciation patterns are registered for each word. For example, in the genre “weather”, words such as “sunny”, “cloudy”, “rain”,... Are registered, and for the word “rain”, “take an umbrella as a sentence that becomes a pronunciation pattern. "Is registered. Further, in each genre, words that are pronunciation patterns to be pronounced when the mobile terminal device 1 consults the user for information retrieval are registered. In addition, the phrase serving as the pronunciation pattern is added to a word / character string registered in the interest information database or the title of the site, and becomes a sentence of a pronunciation pattern for information search and consultation. For example, in the genre “weather”, a word that is a pronunciation pattern “pronounced” (pronounced when consulting information retrieval) is registered, and the title of the site registered in the preference information database “Shizuoka tomorrow” When “Prefecture Weather Forecast” is selected, “Tomorrow's Shizuoka Prefecture Weather Forecast?” With “See?” Is added to the pronunciation pattern sentence to the user for information search. Become.
[0027]
In the vocabulary database, a sentence (or phrase) assigned to each mascot character and having an expression suitable for each character is associated with a sentence (or phrase) that is a pronunciation pattern registered in the Japanese dictionary database. Registered. For example, “Go” (or “Take an umbrella”) is associated with a certain mascot character and “Let's go” (or “Take an umbrella”) is registered. The vocabulary database further registers, for each mascot character, parameters for defining a pitch, a volume, and the like when a sentence (or phrase) is to be generated, and the parameters to be provided to the sound source unit 16 with a voice synthesis function. If the sentence to be the pronunciation pattern is to be pronounced as a song, for example, the pitch and volume corresponding to the song are added and registered in advance.
[0028]
Next, the operation of the mobile phone 1 according to the present embodiment thus configured will be described with reference to the flowchart of FIG. In addition, the operations at the time of outgoing / incoming by a normal telephone function, the operations related to transmission / reception of an e-mail, access to a site on the Internet, and the like are well-known techniques, and descriptions thereof are omitted. In addition, it is assumed that the preference information related to the user's preference has already been registered in the user preference information database.
[0029]
First, it is determined whether or not a trigger signal to be randomly generated has been generated (step S01).
If the determination is Yes, that is, if it is determined that there is a trigger signal, the process proceeds to step S02. On the other hand, if the determination is No, that is, if it is determined that there is no trigger signal, the process proceeds to step S03.
In step S03, it is determined whether or not a trigger signal has been generated by the user (by a user operation). If the determination is Yes, that is, if there is a trigger signal from the user, the process proceeds to step S02. On the other hand, if the determination is No, that is, if there is no trigger signal from the user, the process returns to step S01.
[0030]
Here, the process proceeds to step S02 according to the determination in step S02 or step S03. In step S02, the taste information such as the word / character string or the address of the site and the title from the above-mentioned user taste information database is determined according to the weight. This is selected and displayed on the display unit 21 (at this time, the vibrator 22 may be further vibrated), and the pronunciation registered in the Japanese dictionary database (for each genre) in this taste information or the taste information. A sentence to which a phrase serving as a pattern is added is uttered by speech synthesis, and a user is asked for information retrieval. In this case, the preference information is selected, for example, in the user preference information database in order from preference information having the largest weight.
Next, when the operation of the operation unit 18 is performed by the user and an operation for affirming the information search (Yes) is performed in step S04, the answer is determined to be Yes and the process proceeds to step S05, while the information search is denied. When the operation of (No) is performed, the answer is determined to be No, and the process returns to step S01.
[0031]
If the user performs an operation of affirming (Yes) the information search, the process proceeds to step S05. In step S05, a site search is executed from the presented word or character string (or site address). In the case of words or character strings, the address of a related site is obtained using a so-called search engine. In the case of using the address of the site, since this address is used as it is, the process proceeds to the next step S06.
[0032]
Next, in step S06, the site searched in step S05 is accessed, and information provided by this site is downloaded.
Then, in the next step S07, a word (or a plurality of words) of a specific genre to which the word or character string (or site title) in the Japanese dictionary database belongs is extracted (picked up) from the downloaded information. . Hereinafter, the words and phrases extracted here will be referred to as keywords of the in-site information.
[0033]
Next, it is determined whether or not the keyword of the in-site information has been extracted from the information downloaded from the site (step S08).
In this determination, if it is determined that the keyword of the site information has been extracted (successful pickup), the process proceeds to step S09. On the other hand, in this determination, No, that is, the keyword of the site information can be extracted. If it is determined that there is no such information, the process proceeds to step S10.
In step S09, a sentence of a pronunciation pattern to be pronounced is determined from the corresponding genre in the Japanese dictionary database. Here, for example, a sentence having a pronunciation pattern corresponding to a phrase having a high appearance frequency among the phrases (words) extracted in step S07 is selected. On the other hand, in step S10, since the keyword of the in-site information has not been extracted, all texts described in the accessed site are determined as sentences to pronounce (sentences of pronunciation patterns).
[0034]
In step S11, the sentence of the pronunciation pattern determined as described above is converted into a tone of a tone corresponding to the corresponding mascot character as described above, and voice data to which the corresponding parameters such as volume and pitch are added is generated. Then, it is supplied to the sound source unit 16 with the voice synthesis function.
In step S <b> 12, the sound source unit 16 with the voice synthesis function performs voice synthesis based on the supplied voice data and emits sound from the speaker 17. At this time, the mascot character and the sentence converted in step S11 are displayed on the display unit 21 under the control of the CPU 11.
Note that the operation flow described above is an example, and is not limited to the above processing flow. For example, in Step S08, when it is determined as No (the keyword of the information in the site could not be extracted), another site is accessed and the same pickup process is performed, and the same process is repeated a preset number of times. Even if the pickup is not successful, the process may proceed to step S10.
[0035]
Here, a specific example of the operation of the mobile phone 1 will be described.
[Example 1]
In the user preference information database, preference information whose site address and its title are "weather forecast for Shizuoka tomorrow" is registered, and when this title is selected, "would you like to see the weather forecast for tomorrow's Shizuoka Prefecture?" And ask the user to search for information.
In response to this, when the user receives an answer of Yes, the user accesses a site whose title is “Tomorrow's Shizuoka Prefecture Weather Forecast” and reads information provided by this site. The information read at this time is
Shizuoka weather forecast tomorrow
Rain Probability of rain 70%
Then, “weather” is extracted from the Japanese dictionary database classified into genres (see FIG. 4) as a keyword of the information in the site, and the words included in the genre of “weather” are further registered. By using the keyword "rain" as a keyword, a pronunciation pattern of "take an umbrella" registered and associated with this "rain" is obtained.
Then, the pronunciation pattern of "Take an umbrella" is converted from the vocabulary database into words defined for the mascot character to be used. For example, in a certain mascot character, the pronunciation pattern of “Take an umbrella” is converted to “Take an umbrella” and pronounced “Take an umbrella”. In another mascot character, for example, it is converted to "let's carry an umbrella" and pronounced.
[0036]
[Example 2]
In this example, when "fortune-telling" is selected as the taste information, an information search is performed, for example, "Do you want to know fortune-telling?"
In response to this, when the user receives an answer of Yes from the user, the site is searched using “divination” as a search keyword. At this time, a site search is performed using a so-called search engine. Then, one of the hit sites is accessed, and the information provided by the site is read.
[0037]
Then, words in the site are picked up based on the words registered in the genre-categorized Japanese dictionary database (see FIG. 5). At this time, if “lucky color” included in the “fortune-telling” genre is picked up, the pronunciation pattern sentence “lucky color is“ color ”registered corresponding to“ lucky color ”registered in the Japanese dictionary database Is ". The “color” included in the pronunciation pattern sentence can be selected, and “blue”, “red”, “pink”... Are registered for the “color”. When the site information is searched based on the item list of “color”, and the word “pink” is detected, it is recognized as corresponding to this “color”, and the pronunciation pattern of “lucky color is pink” is obtained.
[0038]
Then, from the vocabulary database, the pronunciation pattern of “Lucky color is pink” is converted into a word defined for the mascot character, and “Lucky color is pink” is pronounced.
In each of the above embodiments, the pronunciation pattern sentence is obtained based on each database. However, if the pronunciation pattern sentence cannot be obtained as described above, the text in the site is output as it is as described above. I do.
[0039]
As described above, the embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes a configuration and the like without departing from the gist of the present invention. For example, the present invention may be realized by a mode in which the processes of steps S01 to S11 in the above-described embodiment are performed by a host computer on a network, that is, a host computer on a network and a portable terminal device capable of accessing the host computer. Good. In this case, data such as the user preference information database, the Japanese dictionary database, and the vocabulary database stored in the portable terminal device in the above embodiment are stored in the host computer, and the user preference information database is stored for each user. Interest information is registered. Then, between the host computer and the portable terminal device, a result of processing performed on one side and required on the other side (or a signal or information emitted from one side to the other side) is provided from one side to the other by communication. Speech data corresponding to the mascot character, which is the result of the final processing, is provided from the host computer to the portable terminal device, and the portable terminal device produces sound by speech synthesis.
[0040]
Further, the present invention records an operation flow shown in FIG. 3 or a program for realizing a processing function similar to this operation flow on a computer-readable recording medium, and stores the program recorded on the recording medium in a computer system. , And may be realized by executing. Here, the “computer system” includes an OS and hardware such as peripheral devices.
[0041]
The “computer-readable recording medium” refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, and a CD-ROM, and a storage device such as a hard disk built in a computer system. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) inside a computer system serving as a server or a client when a program is transmitted through a network such as the Internet or a communication line such as a telephone line. In addition, programs that hold programs for a certain period of time are also included.
[0042]
Further, the above program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
Further, the program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.
[0043]
【The invention's effect】
As described above in detail, according to the present invention, a phrase representing information for satisfying the user's taste is generated based on the extracted taste information, and the word is vocalized. It is possible to receive interesting information that matches the user's taste by voice without any trouble.
According to the present invention, each mascot character displayed on the screen further has a vocabulary database that defines at least the tone of the mascot character, and the voice data generation unit generates the vocabulary based on the vocabulary database. By converting the words and phrases into voice data, the mascot character displayed on the screen sounds with each voice (for example, each tone) and becomes interesting and user-friendly.
Further, according to the present invention, the voice data generating means generates voice data to which pitch data at the time of generating a voice by the voice generating means is added, thereby giving a change in pitch to the voice to be generated. For example, it is possible to make a pronunciation like a humming song, which is more user-friendly.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a schematic configuration of a mobile phone as an embodiment of a mobile terminal device of the present invention.
FIG. 2 is a diagram illustrating extraction of taste information related to a user's taste and storage thereof in the embodiment.
FIG. 3 is a flowchart illustrating an operation of the mobile phone according to the embodiment.
FIG. 4 is an example of the contents of a Japanese dictionary database for explaining the first embodiment.
FIG. 5 is an example of the contents of a Japanese dictionary database for explaining Embodiment 2.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Mobile telephone (portable terminal device), 11 ... CPU, 12 ... Communication part, 12a ... Antenna, 13 ... Sound processing part, 14, 17 ... Speaker, 15 ... Microphone, 16 ... Sound source with sound synthesis function, 18 ... Operation Unit, 19 RAM, 20 ROM, 21 display unit, 22 vibrator, 30 bus

Claims (7)

A preference information extracting means for extracting preference information related to the preference of the user;
A site search means for searching or referencing a site based on the taste information from a network and reading information provided by the site;
Keyword extraction means for extracting a keyword based on the interest information from information read from the site,
A phrase generation unit that generates a phrase representing information for satisfying a user's taste based on the keyword;
Voice data generating means for converting the phrase generated by the phrase generating means into voice data,
A mobile terminal device comprising: a voice generating means for generating a voice based on the voice data. The taste information extracting means,
The mobile terminal device according to claim 1, wherein the preference information is extracted from a bookmark in which a site address is registered or a browsing history of the site. The taste information extracting means,
2. The portable terminal device according to claim 1, wherein the preference information is extracted from a mail text described by a user or a received mail text received. The taste information extracting means,
The mobile terminal device according to claim 1, wherein the data input by the user is used as the preference information. Each mascot character set on the portable terminal device further has a vocabulary database that defines at least the tone of the mascot character,
The audio data generating means includes:
The mobile terminal device according to claim 1, wherein the conversion is performed based on the vocabulary database. The audio data generating means,
The portable terminal device according to any one of claims 1 to 5, further comprising generating voice data to which data of a pitch at which a voice is generated by the voice generating means is added. A method performed by a computer system, comprising:
Extracting preference information related to the user's preference;
A step of searching a site based on the taste information from a network and reading information provided by the site;
Extracting, from the information read from the site, a keyword based on the interest information;
Generating a phrase representing information for satisfying the user's taste based on the keyword;
Converting the phrase generated in the previous step into audio data;
Generating a voice based on the voice data.

Images