JP2009163358A - Information processor, information processing method, program, and voice chat system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an information processor, an information processing method, a program and a voice chat system, allowing easy retrieval of contents gaining topicality in a chat after a chat end. <P>SOLUTION: This information processor has: a voice recognition part having a keyword list recording prescribed keywords, acquiring input voice as voice data, and voice-recognizing the acquired voice data; a keyword detection part detecting the keyword from a voice recognition result of the voice data based on the keyword list; a log information storage part recording a log wherein the detected keyword and a date when the keyword is detected are associated as log information; and a display control part making the detected keyword be displayed on a prescribed display part. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an information processing apparatus, an information processing method, a program, and a voice chat system.

  With the development of Internet-related technology, not only ordinary text-based chat but also voice chat (hereinafter also referred to as “voice chat”) can be realized between personal computers (PCs). It was.

  In addition, a system that enables smooth communication between users by sharing chat log data and information different from the log data among a plurality of users has been proposed (for example, Patent Document 1). reference.).

JP 2003-178016 A

  However, in the system as described above, when searching for the content that became a topic during the chat after the chat ends, it is necessary to read back the log data in which the chat conversation sentence is written. There was a problem that it was difficult to search for the contents.

  Therefore, the present invention has been made in view of such problems, and a purpose thereof is a new and improved information processing apparatus capable of easily searching for content that has become a hot topic in chat after the chat ends. An information processing method, a program, and a voice chat system are provided.

  In order to solve the above-described problem, according to an aspect of the present invention, there is provided an information processing apparatus having a keyword list in which a predetermined keyword is recorded. A speech recognition unit that recognizes speech data; a keyword detection unit that detects a keyword from speech recognition results of the speech data based on the keyword list; and the detected keyword and the date and time when the keyword was detected An information processing apparatus is provided that includes a log information storage unit in which a log associated with is recorded as log information, and a display control unit that displays the detected keyword on a predetermined display unit.

  In the keyword list, for each keyword recorded in the keyword list, a related keyword related to one keyword is recorded in association with the one keyword, and the related keyword is recorded in the log information storage unit. Log information may be further recorded, and the display control unit may further display the related keyword related to the detected keyword based on the keyword list.

  The information processing apparatus includes a keyword selection unit that determines whether a keyword displayed on the display unit is selected by the display control unit, and a detailed information search unit that searches for detailed information on the selected keyword by a predetermined method When the keyword is selected by the keyword selection unit, the display control unit further displays detailed information of the keyword searched by the detailed information search unit, and the log information storage unit The detailed information search unit may further record the log information of the keyword searched for the detailed information.

  The information processing device adds a predetermined point for each of the keywords detected by the keyword detection unit based on the log information recorded in the log information storage unit and is selected by the keyword selection unit A point calculation unit that adds a predetermined point for each keyword may be further included, and the points calculated by the point calculation unit may be recorded in the log information storage unit in association with each keyword.

  In order to solve the above-described problem, according to another aspect of the present invention, there is provided an information processing method in an information processing apparatus having a keyword list in which a predetermined keyword is recorded, wherein input speech is acquired as speech data. A speech recognition step for recognizing the acquired speech data; a keyword detection step for detecting a keyword from a speech recognition result of the speech data based on the keyword list; and the detected keyword and the keyword A log information recording step of recording, as log information, a log associated with the date and time when the error is detected.

  In order to solve the above problem, according to still another aspect of the present invention, there is provided a program for causing a computer to function as an information processing apparatus having a keyword list in which a predetermined keyword is recorded. A voice recognition function that acquires voice as voice data, recognizes the acquired voice data as voice, and a keyword detection function that detects a keyword from voice recognition results of the voice data based on the keyword list; A log information storage function for recording, as log information, a log in which the keyword is associated with the date and time when the keyword was detected, and a display control function for displaying the detected keyword on a predetermined display unit. A program for realizing this is provided.

  According to this configuration, the computer program is stored in the storage unit included in the computer, and is read and executed by the CPU included in the computer, thereby causing the computer to function as the information processing apparatus. A computer-readable recording medium in which a computer program is recorded can also be provided. The recording medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, a flash memory, or the like. Further, the above computer program may be distributed via a network, for example, without using a recording medium.

  In order to solve the above-described problem, according to still another aspect of the present invention, there is provided a voice chat system including a plurality of information processing apparatuses capable of performing voice chat, wherein at least one of the information processing apparatuses is a predetermined one. A keyword list in which keywords are recorded; an input voice is acquired as voice data; a voice recognition unit that recognizes the acquired voice data; and voice recognition of the voice data based on the keyword list A keyword detection unit for detecting a keyword from the results; a log information storage unit in which a log in which the detected keyword is associated with the date and time when the keyword was detected; and the detected keyword There is provided a voice chat system including a display control unit that displays a message on a predetermined display unit.

  The log information storage unit may aggregate the detected keywords in association with the partner and the date and time when the voice chat was performed.

  The information processing apparatus acquires voice data corresponding to voice input to another information processing apparatus that is a partner of the voice chat, and the voice recognition unit acquires the voice data acquired from the other information processing apparatus. May be recognized by voice.

  The keyword detection unit detects a keyword from a voice recognition result of the voice data acquired from the other information processing apparatus, and the log information storage unit stores the voice data acquired from the other information processing apparatus. The log information of the keyword detected from the voice recognition result may be recorded.

  The voice chat system further includes a keyword management server that manages the keywords detected by the information processing apparatus that has executed the voice chat, and the keyword management server receives the log information from the information processing apparatus, You may further provide the keyword total part which totals the said keyword based on the received said log information.

  The keyword management server has a product list in which products associated with the previous keyword managed by the keyword management server are recorded, and is described in the log information received from the information processing apparatus. The information processing apparatus may further include a product recommendation unit that collates the keyword with the product list and recommends the product recorded in the product list to the information processing apparatus.

  The keyword management server refers to the keyword aggregation result received, and the keyword having a high aggregation point in the voice chat from the log information acquired from each of the information processing devices performing the voice chat. And a related keyword registration unit for registering the extracted keyword as a related keyword.

  The voice chat system further includes a search server that allows the information processing apparatus to search for the keyword and an article related to the keyword, and the search server receives a search keyword searched in the search server for the information processing. The information processing apparatus may generate the keyword list based on the received search keyword.

  In order to solve the above problems, according to still another aspect of the present invention, a plurality of information processing devices capable of performing voice chat and control of the voice chat executed between the plurality of information processing devices are performed. And a keyword management server having a predetermined keyword list, wherein the information processing apparatus uses the input voice as voice data, and the voice data is the partner of the voice chat via the keyword management server. A voice conversation control unit that acquires voice data transmitted from the other information processing apparatus via the keyword management server, and the keyword management server includes the plurality of information processing apparatuses. A voice data mediating unit that mediates transmission / reception of voice data transmitted from the device; a voice recognition unit that recognizes the voice data; Based on the keyword list, a keyword detection unit that detects a keyword from the speech recognition result of the speech data, and a log in which the detected keyword is associated with the date and time when the keyword was detected is recorded as log information. A voice chat system including a log information storage unit.

  According to the present invention, information related to a keyword that existed in a chat conversation is recorded in association with the date and time when the keyword was detected. It is possible.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

(First embodiment)
<About voice chat system 10>
First, the voice chat system according to the first embodiment of the present invention will be described in detail with reference to FIG. FIG. 1 is an explanatory diagram for explaining a voice chat system 10 according to the present embodiment.

  The voice chat system 10 according to the present embodiment mainly includes a communication network 12, information processing devices 20A and 20B, a keyword management server 30, and a search server 40, as shown in FIG.

  The communication network 12 is a communication line network that connects the information processing apparatus 20, the keyword management server 30, and the search server 40 so that bidirectional communication or one-way communication is possible. The communication network 12 includes, for example, the public network such as the Internet, a telephone line network, a satellite communication network, a broadcast communication path, a WAN (Wide Area Network), a LAN (Local Area Network), an IP-VPN (Internet Protocol-). Virtual Private Network), Ethernet (registered trademark), a dedicated line network such as a wireless LAN, and the like, regardless of wired / wireless.

  The information processing apparatus 20 performs voice chat (voice chat) with another information processing apparatus 20 connected via the communication network 12. Further, the information processing apparatus 20 requests the keyword management server 30 and the search server 40 connected to the communication network 12 to refer to various databases included in the keyword management server 30 via the communication network 12, Or request a search. Further, the other information processing apparatus 20 that performs voice chat may be connected via the communication network 12 as shown in the figure. For example, a USB (Universal Serial Bus) port may be used without using the communication network 12. Or i. It may be directly connected by an IEEE 1394 port such as Link, a SCSI (Small Computer System Interface) port, an RS-232C port, or the like.

  In the illustrated example, a desktop PC is shown as the information processing apparatus 20, but the information processing apparatus 20 according to the present embodiment may be a desktop PC or a notebook PC. In addition, the information processing apparatus 20 according to the present embodiment is not limited to such an example, and may be an information home appliance such as a television receiver or a home game machine, a mobile phone, or the like as long as it has a communication function via a network. A telephone, a PDA (Personal Digital Assistant), or the like can also be used. Further, the information processing apparatus 20 may be a portable device (Portable Device) that can be carried by a contractor, for example, a portable game machine, a PHS, a portable video / audio player, or the like.

  Further, in FIG. 1, only two information processing apparatuses 20 are connected to the communication network 12, but the present embodiment is not limited to the above case, and the information processing apparatus 20 is configured to communicate with the communication network 12. A plurality of connections may be made on the network 12.

  The keyword management server 30 is a server that manages, as a database, an original keyword list that is referred to when the information processing apparatus 20 extracts a predetermined keyword from the conversation content of voice chat. In the original keyword list managed by the keyword management server 30, various types of information such as a model describing the pronunciation, phoneme, and syllable chain relationship for the word as a keyword and a keyword category are described. In the keyword list managed by the keyword management server 30, for example, high-order search keywords of the search server, terms that are frequently used as blog topics, and the like are described as keywords. The keyword management server 30 is a dynamic database whose description is updated at any time in accordance with changes in high-order search keywords of search engines (search servers) and frequently used terms in blogs. It may be a static database. Furthermore, the keywords described in the keyword management server 30 may be processed by, for example, a PLSA (Probabilistic Lent Semantic Analysis) model or the like and converted into an appropriate topic vector form. Here, the topic vector is used to express an arbitrary topic in a vector space and determine the commonality of topics. In addition, recognition weight information described later may be added to the keywords described in the keyword management server 30. The keyword management server 30 will be described again in detail below.

  Here, the chain relationship between pronunciation, phonology, and syllable for the above word as a keyword refers to how each word described in the keyword management server 30 as a keyword is mutually related in terms of pronunciation, phonology, and syllable. This is a relationship indicating whether or not they are linked (connected). For example, a statistical word chain probability (n-gram or class n-gram), a generation grammar, a finite state can be used for describing such a chain relationship. There is an automaton.

  The search server 40 is a database such as a Web site that can search information disclosed on the Internet or the like or information that is not disclosed using keywords or the like. The search server 40 according to the present embodiment may be a full text search type that performs a full text search of information stored by a keyword, or may be a directory type that searches for information classified by category.

<Configuration of Information Processing Device 20>
Subsequently, the configuration of the information processing apparatus 20 according to the present embodiment will be described in detail with reference to FIG. 2. In the following description, the two information processing apparatuses 20 that perform voice chat will be described for convenience. The first information processing device 20A and the second information processing device 20B will be referred to. Further, the first information processing device 20A and the second information processing device 20B convert the voice of the user of each information processing device into sound data, and transmit the sound data to another information processing device that is a conversation partner of the voice chat. It shall be. FIG. 2 is a block diagram for explaining the configuration of the information processing apparatus 20A according to the present embodiment.

  As shown in FIG. 2, for example, the information processing apparatus 20A according to the present embodiment includes a voice input unit 201, a voice recognition unit 203, a voice conversation control unit 205, a voice output unit 207, and a keyword detection unit 209. The display control unit 211, the display unit 213, the keyword selection unit 215, the detailed information search unit 217, the point calculation unit 219, the communication unit 221, and the storage unit 223 are mainly provided.

  The voice input unit 201 is an interface for capturing a conversation in a voice chat, which is a voice uttered by a user of the first information processing apparatus 20A, into the first information processing apparatus 20A. It is composed of a microphone and a headset that are connected input devices. The user's conversation uttered toward the microphone or the headset is automatically and in real time taken into the first information processing apparatus 20A and converted into an audio signal as an electric signal, and voice recognition is performed via the voice input unit 201. Is transmitted to the unit 203.

  The voice recognition unit 203 generates voice data from the user's conversation that is voluntarily captured by the voice input unit 201 and transmitted in real time, and transmits the voice data to the voice conversation control unit 205 to be described later. Speech recognition is performed based on the speech data. The voice recognition unit 203 generates a word string corresponding to the generated voice data as a result of the voice recognition, and transmits the generated word string to the keyword detection unit 209 described later. Further, the voice recognition unit 203 may transmit the generated word string to the display control unit 211 described later. The voice recognition unit 203 will be described in detail below.

  The voice conversation control unit 205 controls voice chat performed with the second information processing apparatus 20 </ b> B connected via the communication network 12. The voice conversation control unit 205 receives the transmission of the voice data generated by the voice recognition unit 203, transmits the voice data to the second information processing device 20B via the communication unit 221, and from the second information processing device 20B. Audio data to be transmitted is received via the communication unit 221 and transmitted to the audio output unit 207. In addition, each time a voice chat is performed, the voice conversation control unit 205 associates the date and time when the voice chat was performed, an identifier that identifies the voice chat itself, and an identifier that represents the voice chat partner, and uses voice chat usage history information. May be stored in the storage unit 223.

  Note that the voice conversation control unit 205 may be configured by hardware specialized for voice conversation control, or may be provided as an application program such as a voice chat program.

  The audio output unit 207 is an interface that receives audio data of audio uttered by the user of the second information processing device 20B and takes it into the first information processing device 20A. For example, the audio output unit 207 is connected to the first information processing device 20A. Output devices such as speakers and earphones. Audio data from the second information processing device 20B received via the communication unit 221 to be described later is output to the user of the first information processing device 20A via the audio output unit 207.

  The keyword detection unit 209 determines whether or not the keyword stored in the keyword list storage unit 227 described later exists in the word string transmitted from the speech recognition unit 203, and the keyword exists. , The word corresponding to the keyword is output as a keyword. The keyword detection unit 209 may detect all corresponding keywords simultaneously when a plurality of keywords exist in one word string. Further, the keyword detection unit 209 transmits the keyword detected from the word string to the display control unit 211 described later. Further, the keyword detection unit 209 transmits the keyword detected from the word string to the point calculation unit 219 described later.

  Further, when the keyword associated with the detected keyword exists in the keyword list recorded in the keyword list storage unit 227, the keyword detection unit 209 associates the keyword with the keyword in addition to the detected keyword. The related keyword is transmitted to the display control unit 111 described later.

  The display control unit 211 searches for a keyword included in the voice chat conversation detected by the keyword detection unit 209 and a related keyword associated with the detected keyword, or a keyword searched by the detailed information detection unit 217 described later. Display control for displaying an article related to the result and the keyword on the display unit 213 is performed. Further, when information related to a product related to the keyword detected by the keyword detection unit 209 is provided from the keyword management server 30, display control for displaying information related to the provided product on the display unit 213 is performed.

  The display unit 213 is an output device such as a display provided in the information processing apparatus 20 and is controlled by the display control unit 211. Information that is display-controlled by the display control unit 211 is displayed on the display unit 213. Here, examples of the information controlled by the display control unit 211 include a keyword, a keyword search result, an article related to the keyword, and information related to a product related to the detected keyword.

  The keyword selection unit 215 determines whether the keyword displayed on the display unit 213, the keyword search result, the article related to the keyword, the information related to the product related to the detected keyword, and the like have been selected. Specifically, the keyword selection unit 215 detects the operation of a position specifying object such as a cursor key or a mouse pointer provided in the input device of the information processing apparatus 20A, and determines whether the keyword or the like has been selected. . If it is determined that the keyword or the like displayed on the display unit 213 is selected, the keyword selection unit 215 records the selected keyword or the like in association with the date and time selected in the log information storage unit 255 of the storage unit 223. To do. Further, the keyword selection unit 215 transmits the selected keyword or the like to the detailed information search unit 217 to be described later, and requests to acquire detailed information regarding the selected keyword or the like. Further, the keyword selection unit 215 transmits the selected keyword or the like to the point calculation unit 219 described later.

  The detailed information search unit 217 associates the keyword and the related keyword transmitted from the keyword detection unit 209 with the time when the keyword is transmitted from the keyword detection unit 237, and stores the associated information in the storage unit 251 described later. Further, the detailed information search unit 217 accesses the search server 40 via the communication unit 221 and performs an information search for the keyword transmitted from the keyword extraction unit 237, and acquires a keyword search result and an article related to the keyword. . The detailed information search unit 217 stores the obtained search result in the log information storage unit 225 of the storage unit 225 and transmits it to the display control unit 211. Here, the search result acquired by the detailed information search unit 217 by the search server 40 is metadata related to information such as the title, URL, and genre of information in the search server 40 related to the search keyword.

  Further, when the keyword selection unit 215 notifies that a more detailed information is selected for a specific keyword or an article related to the keyword, the detailed information search unit 217 accesses the search server 40 via the communication unit 221. Further, detailed information is acquired, and the specific keyword notified from the keyword selection unit 215 is stored in the log information storage unit 225 of the storage unit 223.

  Each time the keyword is detected from the conversation content of the voice chat, the point calculation unit 219 gives a predetermined score (point) to the detected keyword. In addition, when the keyword selection unit 215 transmits that the detected keyword has been selected, the point calculation unit 219 further adds a predetermined score to the selected keyword. Furthermore, when a related keyword associated with the detected keyword is selected, the point calculation unit 219 gives a predetermined score to the selected related keyword.

  For example, when a predetermined keyword is detected in the voice conversation, the point calculation unit 219 adds, for example, 5 points to the detected keyword as a point, and when this keyword is selected, further 10 points are added. Add as points. In addition, when a related keyword associated with the detected keyword is selected, 10 points are added to the related keyword.

  The number of points added to the keyword may be a fixed value as in the above example, or the number of points to be added may be changed based on the weighting coefficient assigned to the keyword. .

  The point calculation unit 219 records the calculated points in the log information storage unit 225 described later in association with the corresponding keyword.

  In addition, the point calculation unit 219 transmits various log information recorded in the log information storage unit 225 to the keyword management server 30 at predetermined intervals. Further, the point calculation unit 219 may transmit log information to the keyword management server 30 with reference to the log information storage unit 225 in response to a request from the keyword management server 30.

  Here, the point added to the keyword may be displayed on the display unit 213 every time the point is changed during the voice chat, or may be displayed on the display unit 213 after the voice chat ends. . In addition, the point added to the keyword can be displayed at an arbitrary timing by a user operation of the information processing apparatus 20.

  The communication unit 221 is a communication device provided in the first information processing apparatus 20A, for example, and each processing unit of the first information processing apparatus 20A is a device external to the first information processing apparatus 20A via the communication network 12. And the like, such as the keyword management server 30, the search server 40, the second information processing apparatus 20B, and the like. Note that the communication unit 221 can also transmit and receive information to and from other information processing apparatuses directly connected to the first information processing apparatus 20A without using the communication network 12.

  The storage unit 223 is a storage device provided in the first information processing apparatus 20A, for example, and stores data such as keywords detected by the keyword detection unit 209. In addition to these data, it is also possible to store recognition results such as voice data and word strings generated by the voice recognition unit 203, various databases, and the like. Furthermore, in addition to these data, the first information processing apparatus 20A can appropriately store various parameters, the progress of processing, and the like that need to be saved when performing some processing. The storage unit 223 is freely read and written by the voice recognition unit 203, the voice conversation control unit 205, the keyword detection unit 209, the keyword selection unit 215, the detailed information search unit 217, the point calculation unit 219, and the like. It is possible. The storage unit 223 further includes a log information storage unit 225 and a keyword list storage unit 227.

  The log information storage unit 225 is a storage unit in which a keyword log detected from the speech recognition result by the keyword detection unit 209 is recorded as log information. Here, the keyword log is information in which a certain keyword is associated with the date and time when this keyword was detected. In the log information storage unit 225, in addition to the log information related to the detected keyword, keyword selection log information related to the keyword further selected by the user after detection, and log information related to the related keyword related to the detected keyword In addition, product recommendation log information recorded when receiving a recommendation of a product associated with the detected keyword is recorded. The log information storage unit 225 will be described in detail later.

  Various log information recorded in the log information storage unit 225 is periodically transmitted to the keyword management server 30 and used for processing executed by the keyword management server 30. The log information recorded in the log information storage unit 225 may be transmitted to the keyword management server 30 by the user of the information processing apparatus 20 at an arbitrary timing. Furthermore, the log information recorded in the log information storage unit 225 can be freely referred to by the user of the information processing apparatus 20.

  The keyword list storage unit 227 is a storage unit in which a keyword list to be referred to when the keyword detection unit 209 detects a keyword from the speech recognition result is recorded. The keyword list recorded in the keyword list storage unit 227 is acquired by the information processing apparatus 20 from the keyword management server 30. The keyword list recorded in the keyword list storage unit 227 is periodically updated by the information processing apparatus 20 with reference to the keyword management server 30. Further, the speech recognition unit 203 may update the content of the recognition database 257 used for speech recognition with reference to the keyword list storage unit 227. Further, the information processing apparatus 20 may acquire a search keyword searched by the search server 40 from the search server 40, and generate / update a keyword list based on the acquired search keyword. In this case, the information processing apparatus 20 generates a keyword list from the search server 40 using, for example, a high-order search keyword list ranked according to the frequency of the search performed in the search server. It is preferable to perform the update. By generating / updating a keyword list using such a method, it becomes possible to preferentially detect vocabularies related to recent topics that are easy for users to talk about in voice chat.

  In the keyword list recorded in the keyword list storage unit 227, a related keyword that is a keyword related to one keyword is recorded in association with the one keyword, and the related keyword is associated. When a keyword is detected, in addition to the detected keyword, a related keyword associated with the detected keyword is also selected.

[About the voice recognition unit 203]
Next, the speech recognition unit 203 according to the present embodiment will be described in detail with reference to FIG. FIG. 3 is a block diagram for explaining the speech recognition unit 203 according to the present embodiment.

  As illustrated in FIG. 3, the speech recognition unit 203 according to the present embodiment includes, for example, an AD conversion unit 251, a feature parameter extraction unit 253, a matching unit 255, and a recognition database 257.

  The AD conversion unit 251 samples and quantizes an audio signal that is an analog signal transmitted from the audio input unit 201, and converts the sampled audio signal into audio data that is a digital signal. When the conversion to the voice data is completed, the AD conversion unit 251 transmits the generated voice data to the voice conversation control unit 205 and the feature parameter extraction unit 253. Further, the AD conversion unit 251 may store the generated audio data in the storage unit 223.

  The feature parameter extraction unit 253 performs, for example, a mel frequency cepstrum coefficient (MFCC) and its time difference parameter, spectrum, power linearity for each appropriate frame of the audio data generated by the AD conversion unit 251. Feature parameters such as prediction coefficients, cepstrum coefficients, and line spectrum pairs are extracted. When the feature parameter extraction ends, the feature parameter extraction unit 253 transmits the extracted feature parameter to the matching unit 255 described later. Note that the feature parameter extraction unit 253 may store various feature parameters extracted from the audio data in the storage unit 223.

  Based on the various feature parameters transmitted from the feature parameter extraction unit 253, the matching unit 255 refers to the recognition database 257, which will be described later, as appropriate, and the voice input to the voice input unit 201 (that is, conversation in voice chat). A word string closest to (content) is generated as a speech recognition result. A method for generating a word string will be described later. When the generation of the word string is completed, the matching unit 255 transmits the generated word string to the keyword detection unit 209. The matching unit 255 may store the generated word string in the storage unit 223.

Note that the matching unit 255 can perform matching using a technique such as a Viterbi decoder based on a beam search or a stack decoder based on an A ^* search, for example, so-called keyword spotting. It is also possible to perform matching using the above method. In addition, when “recognition weight” information described later is added to various word dictionaries referred to by the matching unit 255, the recognition results may be ranked after weighting a language score described later. Is possible. Here, the recognition weight information is information in which a recognition weight, which is a correction coefficient (weighting coefficient) used when calculating the language score, is described, and the larger the recognition weight, the more the language score The correction value becomes a large value and is easily adopted as a recognition result. For example, a keyword having a recognition weight of 10 is recognized as a voice with a 10 times higher probability than a keyword having a recognition weight of 1 (that is, an unweighted keyword).

  In determining the recognition weight, for example, ranking information in the keyword list acquired from the search server 40, the frequency of keywords appearing during the output of the speech recognition result, and the like can be used. Since the keyword list includes some top search keywords in the search server 40, for example, ranking is performed in order from the most searched keyword, and predetermined recognition weights are set in order from the top ranking. It is possible to add. Specifically, it is possible to obtain a recognition weight by adding a predetermined coefficient in order from the most searched keyword and multiplying the added coefficient by the normalized keyword frequency. Further, instead of the search server 40, a thesaurus, an ontology database, an encyclopedia, a national language dictionary, a morphological analysis tool, or the like stored in an arbitrary server connected via the communication network 12 may be used. The search server 40 may be used in combination with the thesaurus, ontology database, encyclopedia, Japanese dictionary, morphological analysis tool, and the like.

  In determining the recognition weight, information on whether or not the user of the first information processing apparatus 20A has performed a search using the search server 40 regarding the keyword of the speech recognition result, the user's preference of the first information processing apparatus 20A, and the like. It is possible to use.

  The recognition database 257 is a database that stores various models, rules, and the like used by the matching unit 255 to generate word strings. The recognition database 257 includes, for example, a recognized word dictionary storage unit, an acoustic model storage unit, a language model storage unit, a phoneme list, and a kana phoneme conversion rule. The matching unit 255 performs voice recognition by using various databases described in the recognition database 309.

  Here, in the recognized word dictionary storage unit, for example, attribute information describing a part of speech or genre of a word such as a noun or a verb, word weighting information used when calculating a language score, a language model storage unit A category included in the recorded language model and information on a word included in the category are described in association with each other.

  The acoustic model storage unit stores an acoustic model that represents the acoustic features of individual phonemes of the speech that is recognized. Here, the above acoustic model is a model that expresses the acoustic features of speech for each phonetic symbol such as a vowel or consonant. The speech data of the input speech and the recognition candidate word are similar as sounds. It is used when collating with a focus on sex. As the acoustic model, for example, a Hidden Markov Model (HMM) can be used, but the acoustic model according to the present embodiment is not defined in the above HMM.

  The language model storage unit is a language that describes information (chain information) indicating how each word registered in each word dictionary in the recognized word dictionary storage unit is linked (connected). Remember the model. Examples of the description method include statistical word chain probabilities (n-gram and class n-gram), generation grammar, finite state automaton (FSA), and the like.

  The phoneme list is a list of phoneme symbols used in the recognition database 257. The phoneme list represents one phoneme (corresponding to) one symbol.

  The kana phoneme conversion rule is a rule for converting a kana character string into a phoneme sequence. By storing the kana phoneme conversion rules, the recognition word dictionary storage unit can hold a kana character string that is independent of the phoneme sequence as pronunciation information.

[About log information storage unit 225]
Next, the log information storage unit 225 according to the present embodiment will be described in detail with reference to FIGS. 4 and 5. FIG. 4 is an explanatory diagram for explaining the log information storage unit 225 according to the present embodiment, and FIG. 5 is for explaining an example of log information recorded in the log information storage unit 255 according to the present embodiment. It is explanatory drawing of.

  For example, as shown in FIG. 4, the log information storage unit 225 according to the present embodiment records voice recognition log information, keyword selection log information, related keyword selection log information, product recommendation log information, and the like. .

  The voice recognition log information is log information related to the keyword detected by the keyword detection unit 209 from the voice recognition result. In addition, log information related to related keywords associated with the keywords detected by the keyword detection unit 209 may be recorded in the voice recognition log information. The keyword selection log information is log information related to what is selected from the keywords and the like displayed on the display unit 213. The related keyword selection log information is log information related to selection of a related keyword associated with the keyword detected by the keyword detection unit 209. The product recommendation log information is log information related to product recommendation information transmitted from the keyword management server 30.

  In these log information, a keyword or the like related to each log information and the date and time when the keyword is detected or selected are associated and recorded. In addition to these pieces of information, various pieces of information may be recorded in association with keywords.

  For example, as shown in FIG. 5, the speech recognition log information includes the detected keyword, the date and time when the keyword was detected, information about the conversation partner (community) of the voice chat from which the keyword was detected, Points added to the keywords are recorded in association with each other. Here, the information related to the conversation partner of the voice chat may be identification data such as the user ID of the conversation partner, or the user name or nickname of the conversation partner. Further, it may be information such as an IP address assigned to the information processing apparatus of the conversation partner. Further, not only the information shown in FIG. 5 but also identification information related to the voice chat in which the keyword is detected may be further added to the voice recognition log information.

  The keyword selection log information, the related keyword selection log information, the product recommendation log information, etc., for example, may have the same data structure as the voice recognition log information shown in FIG. 5, and are specific to each log information. It may have a data structure.

  Note that the configuration of the second information processing apparatus 20B is substantially the same as the configuration of the first information processing apparatus 20A, and thus the description thereof is omitted.

  Heretofore, an example of the function of the information processing apparatus 20 according to the present embodiment has been shown. Each component described above may be configured using a general-purpose member or circuit, or may be configured by hardware specialized for the function of each component. In addition, the CPU or the like may perform all functions of each component. Therefore, it is possible to appropriately change the configuration to be used according to the technical level at the time of carrying out the present embodiment.

  The display control unit 211, the detailed information search unit 217, the point calculation unit 219 and the like may be configured by hardware specialized for each function, and are provided as application programs such as a voice recognition program. Also good.

  In addition, the voice recognition unit 203 may acquire voice data from the second information processing apparatus 20 that is a voice chat conversation partner, and may perform voice recognition of the conversation contents spoken by the voice chat conversation partner. Further, the keyword detection unit 209 may detect a keyword from the speech recognition result of the content spoken by the conversation partner, and record the detection result in the log information storage unit 225. Further, the point calculation unit 219 may perform a point calculation process on a keyword or the like detected from the conversation contents spoken by the voice chat conversation partner.

<About the voice recognition processing in the voice recognition unit 203>
Next, the speech recognition process in the speech recognition unit 203 according to the present embodiment will be described in detail with reference to FIG. FIG. 5 is a flowchart for explaining an example of the voice recognition processing according to the present embodiment.

  The voice recognition process described below is started when voice is input to the voice input unit 201 such as a microphone from the user of the first information processing apparatus 20A.

  The voice signal generated by the voice input unit 201 is first converted into voice data that is a digital signal by the AD conversion unit 251 and transmitted to the feature parameter extraction unit 253 (step S101). At this time, the AD conversion unit 251 may store the generated audio data in the storage unit 223. Next, the feature parameter extraction unit 253 to which the voice data is transmitted extracts a feature quantity such as a mel cepstrum from the transmitted voice data (step S103). For the feature parameter extraction, various analysis methods such as cepstrum analysis, linear prediction analysis, and analysis based on an auditory filter using MFCC coefficients can be used. The feature parameter extraction unit 253 may store various feature parameters extracted from the audio data in the storage unit 223.

  When the feature amount is extracted by the feature parameter extraction unit 253, the matching unit 255 refers to the recognition word dictionary stored in the recognition word dictionary storage unit of the recognition database 257, and the word represented by the symbol in this dictionary Are connected to generate a word string (step S105). Thereafter, the matching unit 255 calculates an acoustic score for the generated word string based on the acoustic model stored in the acoustic model storage unit in the recognition database 257 (step S105). Here, the acoustic score is a score that represents how close (acoustically) a word string that is a candidate of the speech recognition result and the input voice are (acoustically) as sound, and the higher the acoustic score, the generated word string Means acoustically close to the input voice.

  When the acoustic score is calculated based on the feature parameter, the matching unit 255 selects a predetermined number of word strings having a high acoustic score based on the obtained acoustic score (step S107). Note that the matching unit 255 may store the calculated acoustic score, the selected word string, and the like in the storage unit 223.

  When the calculation of the acoustic score is completed, the matching unit 255 calculates the language score of each word string selected in Step S107 using the language model stored in the language model storage unit in the recognition database 257 (Step S107). S109). For example, when using grammar or finite state automan from various language models stored in the language model storage unit, the language score can be obtained when the word string can be accepted by the language model. Is “1” and when it cannot be accepted, the language score is “0”.

  Note that when the language model can accept the generated word string, the matching unit 255 may leave the word string selected in step S107 and accept the generated word string although the language is also available. If not, the word string selected in step S107 may be deleted.

  When a statistical language model such as n-gram or class n-gram is used as the language model, the generation probability of the word string is used as the language score. Note that the matching unit 255 may store the calculated language score or the like in the storage unit 223.

  The language model according to the present embodiment calculates a language score using a fixed word dictionary and a variable word dictionary stored in the recognition word dictionary storage unit 401 in the recognition database 309. Since the proper nouns that change with the times are described as they are updated, words that are frequently talked about in voice chat or the like can also be used as the language score calculation target.

  When the calculation of both the acoustic score and the language score is completed, the matching unit 255 sorts each word string by integrating the acoustic score calculated in step S105 and the language score calculated in step S109. The word string with the largest score is determined as a recognition result (step S111). That is, for example, the matching unit 255 maximizes the product of the acoustic score obtained from the acoustic model and the language score obtained from the language model, the sum of the logarithm of the acoustic score and the logarithm of the language score, or the like. A word string is determined as a recognition result. In addition, when word recognition weight information is added to various word dictionaries used in the language model, a language score in consideration of the recognition weight information may be used.

  As a result, the most appropriate word string acoustically and linguistically is determined as the recognition result. When the most appropriate word string is determined as the recognition result, the matching unit 255 transmits the determined recognition result to the keyword detection unit 209 (step S113). Further, the matching unit 255 may store the word string that is the determined recognition result in the storage unit 223.

<About contents displayed on display unit 213>
Next, the contents displayed on the display unit 213 of the information processing apparatus 20 according to the present embodiment will be described in detail with reference to FIGS. 7A and 7B. 7A and 7B are explanatory diagrams for explaining the contents displayed on the display unit 213 according to the present embodiment.

  For example, as shown in FIG. 7A, the keywords recognized by the voice recognition unit 203 and detected by the keyword detection unit 209 are displayed as a keyword display window 263 in the display screen 261 of the display unit 213. This keyword display window 263 is generated a new window every time a keyword is detected in the speech recognition result. Further, the detected keyword is associated with the date and time when the keyword is detected, and is recorded in the log information storage unit 225 as log information.

  As shown in FIG. 7B, for example, the contents displayed in each window 263 include a detected keyword display area 265 in which the detected keyword is displayed, and a related keyword in which a related keyword associated with the detected keyword is displayed. A display area 267, a related article display area 269 in which a related article obtained by searching the detected keyword by the search server 40 is displayed, and product information related to the keyword transmitted from the keyword management server 30 are displayed. Product information display area 271 to be displayed.

  The contents displayed in each display area are linked with metadata such as a URL in which detailed information related to the contents is described, and the user of the information processing device 20 can specify the position of a cursor key, a mouse pointer, or the like. By operating the object and clicking these display areas, it is possible to select the contents displayed in each display area.

  The display format of each window 263 is not limited to the above case. For example, only the detected keyword 265 and the related keyword 267 associated with the detected keyword are displayed in each window 263, and the keyword 265 is displayed. When is selected by clicking or the like, related articles 269 and product information 271 related to the selected keyword may be newly displayed.

<Configuration of Keyword Management Server 30>
Next, the configuration of the keyword management server 30 according to the present embodiment will be described in detail with reference to FIG. FIG. 8 is a block diagram for explaining the configuration of the keyword management server 30 according to the present embodiment.

  For example, as shown in FIG. 8, the keyword management server 30 according to the present embodiment includes a keyword totaling unit 301, a related keyword registration unit 303, a product recommendation unit 305, a communication unit 307, and a storage unit 309. Prepare mainly.

  The keyword totaling unit 301 acquires log information stored in the information processing apparatus 20 connected to the keyword management server 30 via the communication network 12 and totals the keywords described in the log information. Here, the totaling of keywords means that the keywords described in the log information acquired from each information processing apparatus 20 are collected and the points associated with each keyword are collected. When the same keyword exists in log information acquired from different information processing apparatuses 20, the keyword totaling unit 301 adds points acquired from the respective information processing apparatuses 20, and adds the acquired points to the calculated keywords. Let the associated point.

  The keyword totaling result by the keyword totaling unit 301 is recorded in the storage unit 309 described later. Further, the result of the keyword aggregation is transmitted to a related keyword registration unit 303 and a product recommendation unit 305, which will be described later, and is used for processing executed by each processing unit. In addition, the keyword totaling unit 301 may transmit the log information before aggregation acquired from each information processing apparatus 20 to the related keyword registration unit 303 and the product recommendation unit 305. The keyword totaling process executed by the keyword totaling unit 301 will be described in detail later.

  The related keyword registration unit 303 additionally registers a related keyword in a keyword list recorded in the storage unit 309 described later, based on the keyword aggregation result transmitted from the keyword aggregation unit 301. Further, when the keyword list is updated, the related keyword registration unit 303 may transmit the updated keyword list to each information processing apparatus 20. Further, the related keyword registration unit 303 may transmit the keyword list recorded in the storage unit 309 to the information processing device 20 in response to the keyword list acquisition request transmitted from the information processing device 20. The related keyword registration process executed by the related keyword registration unit 303 will be described in detail later.

  The product recommendation unit 305 refers to a product list recorded in the storage unit 309, which will be described later, and is described in the log information acquired from each information processing device 20 transmitted from the keyword totaling unit 301 or the keyword totaling result. To find out if the keyword is listed in the product list. In the product list, a plurality of pieces of information related to products related to the keyword are associated with one keyword. Here, examples of the information on the product include a product name, a product model number, and a URL of a home page introducing the product.

  The product recommendation unit 305 compares the product list with the log information and the total result of the log information. If the keyword registered in the product list exists in the log information or the like, the product recommendation unit 305 associates the keyword with the keyword. Information about the product being used is notified to the information processing apparatus 20 that has detected the keyword.

  Further, the product recommendation unit 305 notifies the information processing apparatus 20 of information related to the products registered in the product list (for example, product names, product abbreviations, nicknames, product model numbers, etc.) as related keywords, and the information processing apparatus You may display on 20 windows.

  The communication unit 307 is a communication device provided in the keyword management server 30 and mediates transmission / reception of information performed by each processing unit of the keyword management server 30 with each information processing device 20 via the communication network 12. Note that the communication unit 307 can transmit / receive information to / from each information processing apparatus or the like directly connected to the keyword management server 30 without using the communication network 12.

  The storage unit 309 is, for example, a storage device provided in the keyword management server 30, and includes a keyword list, an aggregation result regarding log information aggregated by the keyword aggregation unit 301, and a product list in which keywords and information regarding products are associated with each other. Memorize etc. In addition to these databases, various databases that can be used by the keyword management server 30 can also be stored. Furthermore, in addition to these data, the keyword management server 30 can appropriately store various parameters that need to be saved when performing some processing, the progress of processing, and the like. The storage unit 309 can be freely read and written by the keyword totaling unit 301, the related keyword registration unit 303, the product recommendation unit 305, and the like.

  The keyword list and product list recorded in the storage unit 309 may be updated by the keyword management server 30 at predetermined intervals with reference to the search server 40 or the like. The keyword list and product list may be updated by the administrator of the keyword management server 30.

<Keyword aggregation process>
Next, the keyword aggregation processing by the keyword management server 30 according to the present embodiment will be described in detail with reference to FIGS. 9A to 9D. FIG. 9A is an explanatory diagram for describing log information acquisition processing performed by the keyword management server 30 according to the present embodiment. FIG. 9B is an explanatory diagram for describing an example of a screen for acquiring a keyword aggregation result performed by the keyword management server 30 according to the present embodiment. FIG. 9C and FIG. 9D are explanatory diagrams for explaining a display example of a keyword totaling result.

  For example, as illustrated in FIG. 9A, the keyword totaling unit 301 of the keyword management server 30 acquires log information recorded in each information processing apparatus 20, and voice recognition log information recorded in the acquired log information The keyword selection log information, the related keyword selection log information, and the product recommendation log information are recorded in the storage unit 309.

  Thereafter, the keyword totaling unit 301 totals the information on the keywords and products recorded in the respective log information for each type of log information, and records the totaled result in the storage unit 309.

  In addition, all the information described in the log information, such as the keywords described in the speech recognition log information, the keyword selection log information and the related keyword selection log information, and the points associated with these keywords, It may be used for updating a keyword list or a product list managed by the server 30. Information recorded in the product recommendation log information may also be used to update information about the product.

  In addition, information regarding keywords and the like collected on the keyword management server 30 can be freely acquired by the information processing apparatus 20. For example, as shown in FIG. 9B, a condition for searching for the keyword aggregation result is input to the condition entry field 277 of the search window 275 displayed on the display unit 213 of the information processing apparatus 20. By selecting the object 279, the information processing apparatus 20 can acquire the aggregation result from the keyword management server 30. Here, as an example of the condition input in the condition entry field 277, for example, “no condition (that is, display all)”, search based on “date”, search based on “voice chat partner”, “region” A search based on “information” can be cited. In addition to these search conditions, the user of the information processing apparatus 20 can enter an arbitrary search condition.

  For example, when the date is used as a search condition, as shown in FIG. 9C, keywords that satisfy the search condition are displayed in a ranking format according to the size of points associated with the keyword. For example, when a voice chat partner is used as a search condition, as shown in FIG. 9D, keywords that satisfy the search condition are displayed in a ranking format according to the size of points associated with the keyword. .

  As described above, in the voice chat system according to the present embodiment, it is possible to easily search for a keyword that satisfies a specific condition. You can easily know how often you used voice chat. That is, by performing such search processing, the user of the information processing apparatus 20 can easily know the proportion of a specific topic in the voice chat log.

<Registering related keywords>
Next, the related keyword registration process executed by the keyword management server 30 according to the present embodiment will be described in detail with reference to FIGS. 10A and 10B. FIG. 10A is an explanatory diagram for describing a related keyword registration process executed by the keyword management server 30 according to the present embodiment, and FIG. 10B shows related keyword execution executed by the keyword management server 30 according to the present embodiment. It is a flowchart for demonstrating a registration process.

  First, the keyword totaling unit 301 of the keyword management server 30 acquires log information from each information processing apparatus 20 as shown in FIG. 9A (step S201). Subsequently, the related keyword registration unit 303 generates a related word group list 351 for each keyword genre based on the acquired log information (step S203). For example, as shown in FIG. 10A, the keywords A to F associated with the genre “baseball” are collected, and a related word group list 351 of the genre “baseball” is generated. Similarly, the keywords a to f associated with the genre “soccer” are collected, and a related word group list 351 of the genre “soccer” is generated.

  Next, the related keyword registration unit 303 of the keyword management server 30 searches the high-order keywords described in the keyword search ranking with reference to the tabulation results recorded in the storage unit 309 and the search server 40 (step S205). ). The related keyword registration unit 303 determines whether there is a keyword described in the generated related word group list 351 among the searched keywords (step S207). If there is an upper selection keyword in the related word group list 351, the word in the related word group list 351 that exists in the upper selection keyword is registered in the related keyword of another related word group (step S209). Update the keyword list. If there is no higher selection keyword in the related word group list 351, the related keyword registration unit 303 ends the registration process.

  For example, in the related word group list 351 related to baseball shown in FIG. 10A, when the keyword A and the keyword B are higher selection keywords, the keyword A and the keyword B are associated as related keywords of the keywords C to F. , Update the keyword list. In addition, in the related word group list 351 related to soccer shown in FIG. 10A, when the keyword c and the keyword e are the top selection keywords, the keyword c is used as the related keyword of the keyword a, the keyword b, the keyword d, and the keyword f. And the keyword e are associated, and the keyword list is updated.

  The new keyword list generated by the processing as described above is transmitted to the information processing apparatus 20 and stored in the keyword list storage unit 227 of the information processing apparatus 20.

  By performing such processing, for example, when the keyword C relating to baseball is detected by the keyword detection unit 209, the keyword A and the keyword B are displayed together as related keywords.

  Further, the related keyword registration unit 303 of the keyword management server 30 may register keywords having high points in the same chat as related keywords. For example, as a result of the keyword totaling unit 301 of the keyword management server 30 totaling keyword points for each chat, a predetermined number of chats with high keywords for keywords belonging to the genre “environment” together with keywords belonging to the genre “car” If there is, the related keyword registration unit 303 is highly related to the keywords “car” and “environment” (that is, the topic of “car” is often spoken with the topic of “environment”. And keywords belonging to each other's genres may be registered as related keywords.

<Modification of Information Processing Device 20>
Subsequently, a modification of the information processing apparatus 20 according to the present embodiment will be briefly described with reference to FIGS. 11A to 11D. FIG. 11A is a simplified block diagram for explaining the speech recognition method of the information processing apparatus according to the present embodiment. FIG. 11B to FIG. 11D are simplified block diagrams for explaining modifications of the speech recognition method of the information processing apparatus according to the present embodiment. 11A to 11D illustrate only a part of the processing units of the information processing apparatus 20 in the present embodiment, but are illustrated in the information processing apparatuses illustrated in FIGS. 11A to 11D. It goes without saying that, for example, the processing unit shown in FIG. 2 is provided in addition to the processing unit.

  In the description of the information processing apparatus 20 according to the above-described embodiment, as illustrated in FIG. 11A, each of the first information processing apparatus 20A and the second information processing apparatus 20B that performs voice chat is issued by the user. The case where the voice is captured and recognized by the speech recognition unit 203 and the keyword detected by the keyword detection unit 209 is recorded in the log information storage unit 225 has been described. In the information processing apparatus 20 according to the present embodiment, Such a modification can also be implemented.

[First Modification]
In the first modification shown in FIG. 11B, each of the information processing apparatuses 20A and 20B that conducts a voice chat transmits the voice uttered by the user of the information processing apparatus to the other information processing apparatus as it is, and information on the other party The case where the voice which the user of the processing apparatus uttered is recognized and output is shown. That is, for example, a voice uttered by the user of the first information processing apparatus 20A is transmitted as it is to the second information processing apparatus 20B via the voice conversation control unit 205 and the communication unit 221 and is recognized by the second information processing apparatus 20B. Is output. Similarly, the voice uttered by the user of the second information processing device 20B is directly transmitted to the first information processing device 20A via the voice conversation control unit 205 and the communication unit 221 and is recognized by the first information processing device 20A. Is output. In the present modification, voice recognition and keyword detection are performed in each of the first information processing device 20A and the second information processing device 20B, and information about the keywords is recorded in the log information storage unit 225.

[Second Modification]
The second modification shown in FIG. 11C shows a case where any one of the information processing apparatuses performs all speech recognition, and the other information processing apparatus does not perform keyword detection or the like. In this case, for example, the first information processing apparatus 20A performs all voice recognition, and the second information processing apparatus 20B performs only voice chat control. The voice uttered by the user of the first information processing apparatus 20A undergoes voice recognition by the voice recognition unit 203 and keyword detection by the keyword detection unit 209, and is transmitted to the second information processing apparatus 20B. Further, the voice uttered by the user of the second information processing device 20B is transmitted to the first information processing device 20A as it is, and is recognized by the voice recognition unit 203 of the first information processing device 20A. Detection is performed.

  Although FIG. 11C illustrates the case where the first information processing apparatus 20A performs all speech recognition, the second information processing apparatus 20B may perform all speech recognition. FIG. 11C shows a case where two independent speech recognition units are provided in the first information processing apparatus 20A, but one speech recognition unit may perform the above processing. This modification as described above is used when, for example, the processing capability of one information processing device is significantly superior to the processing capability of the other information processing device, or when it is significantly inferior. Is possible.

[Third Modification]
In the third modification shown in FIG. 11D, both information processing apparatuses do not perform voice recognition and keyword detection processing at all, and the keyword management server 30 that mediates connection between the respective information processing apparatuses performs voice recognition and keyword detection. This shows a case where the detection process is performed. In this case, the voice uttered by the user of the first information processing apparatus 20A is transmitted to the keyword management server 30 as it is, is recognized by the voice recognition unit 323 of the server 30, and is transmitted to the second information processing apparatus 20B. . Further, the voice uttered by the user of the second information processing device 20B is transmitted to the server 30 as it is, is recognized by the voice recognition unit 323 of the server 30, and is transmitted to the first information processing device 20A. The keyword detection unit 325 of the keyword management server 30 detects a predetermined keyword from the speech recognition result while referring to the keyword list. The keyword detection result is transmitted to both the first information processing apparatus 20A and the second information processing apparatus 20B. Further, the detected keyword is recorded in the log information storage unit 327.

  This modification as described above can be used, for example, when the processing capabilities of both information processing apparatuses are inferior.

<Hardware Configuration of Information Processing Apparatus 20>
Next, the hardware configuration of the information processing apparatus 20 according to the present embodiment will be described in detail with reference to FIG. FIG. 12 is a block diagram for explaining a hardware configuration of the information processing apparatus 20 according to the present embodiment.

  The information processing apparatus 20 mainly includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 903, a RAM (Random Access Memory) 905, a host bus 907, a bridge 909, an external bus 911, An interface 913, an input device 915, an output device 917, a storage device 919, a drive 921, a connection port 923, and a communication device 925 are provided.

  The CPU 901 functions as an arithmetic processing unit and a control unit, and controls all or a part of the operation in the information processing apparatus 20 according to various programs recorded in the ROM 903, the RAM 905, the storage device 919, or the removable recording medium 927. The ROM 903 stores programs used by the CPU 901, calculation parameters, and the like. The RAM 905 primarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 907 constituted by an internal bus such as a CPU bus.

  The host bus 907 is connected to an external bus 911 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 909.

  The input device 915 is an operation unit operated by the user, such as a mouse, a keyboard, a touch panel, a button, a switch, and a lever. Further, the input device 915 may be, for example, remote control means (so-called remote control) using infrared rays or other radio waves, or an external connection device such as a mobile phone or a PDA corresponding to the operation of the information processing device 20. 929 may be used. Furthermore, the input device 915 includes an input control circuit that generates an input signal based on information input by a user using the above-described operation means and outputs the input signal to the CPU 901, for example. A user of the information processing apparatus 20 can input various data and instruct a processing operation to the information processing apparatus 20 by operating the input device 915.

  The output device 917 is, for example, a display device such as a CRT display device, a liquid crystal display device, a plasma display device, an EL display device and a lamp, a sound output device such as a speaker and headphones, a printer device, a mobile phone, a facsimile, etc. It is comprised with the apparatus which can notify the information which carried out visually or audibly to a user. The output device 917 outputs, for example, results obtained by various processes performed by the information processing device 20. Specifically, the display device displays the results obtained by various processes performed by the information processing device 20 as text or images. On the other hand, the audio output device converts an audio signal composed of reproduced audio data, acoustic data, and the like into an analog signal and outputs the analog signal.

  The storage device 919 is a data storage device configured as an example of a storage unit of the information processing device 20, and includes, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or It is composed of a magneto-optical storage device or the like. The storage device 919 stores programs executed by the CPU 901 and various data, and acoustic signal data and image signal data acquired from the outside.

  The drive 921 is a recording medium reader / writer, and is built in or externally attached to the information processing apparatus 20. The drive 921 reads information recorded on a removable recording medium 927 such as a mounted magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 905. In addition, the drive 921 can write a record on a removable recording medium 927 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory. The removable recording medium 927 is, for example, a DVD medium, an HD-DVD medium, a Blu-ray medium, a compact flash (registered trademark) (CompactFlash: CF), a memory stick, or an SD memory card (Secure Digital memory card). Further, the removable recording medium 927 may be, for example, an IC card (Integrated Circuit card) on which a non-contact IC chip is mounted, an electronic device, or the like.

  The connection port 923 includes, for example, a USB (Universal Serial Bus) port, i. A port for directly connecting devices such as an IEEE 1394 port such as Link, a SCSI (Small Computer System Interface) port, an RS-232C port, an optical audio terminal, an HDMI (High-Definition Multimedia Interface) port, etc. is there. By connecting the external connection device 929 to the connection port 923, the information processing apparatus 20 acquires the acoustic signal data and the image signal data directly from the external connection device 929, or the acoustic signal data and the image signal to the external connection device 929. Or provide data.

  The communication device 925 is a communication interface configured with, for example, a communication device for connecting to the communication network 12. The communication device 925 is, for example, a wired or wireless LAN (Local Area Network), Bluetooth, or WUSB (Wireless USB) communication card, an optical communication router, an ADSL (Asymmetric Digital Subscriber Line) router, or various types. It is a modem for communication. The communication device 925 can transmit and receive an acoustic signal and the like with the Internet and other communication devices, for example. The communication network 12 connected to the communication device 925 is configured by a wired or wireless network, and may be, for example, the Internet, a home LAN, infrared communication, radio wave communication, satellite communication, or the like. .

  Heretofore, an example of the hardware configuration capable of realizing the function of the information processing apparatus 20 according to each embodiment of the present invention has been shown. Each component described above may be configured using a general-purpose member, or may be configured by hardware specialized for the function of each component. Therefore, it is possible to change the hardware configuration to be used as appropriate according to the technical level at the time of carrying out this embodiment.

  Note that the hardware configuration of the keyword management server 30 according to the present embodiment is substantially the same as the hardware configuration of the information processing apparatus 20 according to the present embodiment, and thus detailed description thereof is omitted.

  As mentioned above, although preferred embodiment of this invention was described referring an accompanying drawing, it cannot be overemphasized that this invention is not limited to this example. It will be apparent to those skilled in the art that various changes and modifications can be made within the scope of the claims, and these are naturally within the technical scope of the present invention. Understood.

  For example, in the above-described embodiment, the case where the related keyword registration process is performed by the keyword management server 30 has been described. However, the related keyword registration process may be performed by the information processing apparatus 20.

It is explanatory drawing for demonstrating the voice chat system which concerns on the 1st Embodiment of this invention. It is a block diagram for demonstrating the structure of the information processing apparatus which concerns on the embodiment. It is a block diagram for demonstrating the speech recognition part which concerns on the same embodiment. It is explanatory drawing for demonstrating the log information storage part which concerns on the same embodiment. It is explanatory drawing for demonstrating an example of the log information which concerns on the embodiment. It is a flowchart for demonstrating an example of the speech recognition process which concerns on the embodiment. It is explanatory drawing for demonstrating the content displayed on the display part which concerns on the same embodiment. It is explanatory drawing for demonstrating the content displayed on the display part which concerns on the same embodiment. It is a block diagram for demonstrating the structure of the keyword management server which concerns on the same embodiment. It is explanatory drawing for demonstrating the log information acquisition process which the keyword management server which concerns on the embodiment performs. It is explanatory drawing for demonstrating an example of the screen which acquires the totalization result of the keyword which the keyword management server 30 concerning the embodiment performed. It is explanatory drawing for demonstrating the example of a display of the total result of a keyword. It is explanatory drawing for demonstrating the example of a display of the total result of a keyword. It is explanatory drawing for demonstrating the registration process of the related keyword which concerns on the same embodiment. It is a flowchart for demonstrating the registration process of the related keyword which concerns on the embodiment. It is the simplified block diagram for demonstrating the speech recognition method of the information processing apparatus which concerns on the embodiment. It is the simplified block diagram for demonstrating the 1st modification of the speech recognition method of the information processing apparatus which concerns on the embodiment. It is the simplified block diagram for demonstrating the 2nd modification of the speech recognition method of the information processing apparatus which concerns on the embodiment. It is the simplified block diagram for demonstrating the 3rd modification of the speech recognition method of the information processing apparatus which concerns on the embodiment. It is a block diagram for demonstrating the hardware constitutions of the information processing apparatus which concerns on the embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Voice chat system 12 Communication network 20 Information processing apparatus 30 Keyword management server 40 Search server 201 Voice input part 203 Voice recognition part 205 Voice conversation control part 207 Voice output part 209 Keyword detection part 211 Display control part 213 Display part 215 Keyword selection part 217 Detailed information search unit 219 Point calculation unit 221 Communication unit 223 Storage unit 225 Log information storage unit 227 Keyword list storage unit 251 AD conversion unit 253 Feature parameter extraction unit 255 Matching unit 257 Recognition database 261 Display screen 263 Keyword display window 265 Detection Keyword display area 267 Related keyword display area 269 Related article display area 271 Product information display area 275 Search window 277 Condition entry field 279 Display start object Transfected 301 keyword totaling unit 303 related keyword registration unit 305 product recommendation unit 307 communication unit 309 storage unit 321 voice data mediation section 323 speech recognition unit 325 keyword detection unit 327 the log information storage unit 351 associated word group list

Claims (15)

An information processing apparatus having a keyword list in which predetermined keywords are recorded,
A voice recognition unit that acquires input voice as voice data and recognizes the acquired voice data;
A keyword detection unit that detects a keyword from the speech recognition result of the speech data based on the keyword list;
A log information storage unit in which a log associated with the detected keyword and the date and time when the keyword was detected is recorded as log information;
A display control unit for displaying the detected keyword on a predetermined display unit;
An information processing apparatus comprising: In the keyword list, for each keyword recorded in the keyword list, a related keyword related to one keyword is recorded in association with the one keyword,
In the log information storage unit, log information of the related keyword is further recorded,
The information processing apparatus according to claim 1, wherein the display control unit further displays the related keyword related to the detected keyword based on the keyword list. The information processing apparatus includes:
A keyword selection unit that determines whether the keyword displayed on the display unit is selected by the display control unit;
A detailed information search unit for searching the detailed information of the selected keyword by a predetermined method;
Further comprising
When the keyword is selected by the keyword selection unit, the display control unit further displays the detailed information of the keyword searched by the detailed information search unit,
The information processing apparatus according to claim 1, wherein the log information storage unit further records the log information of the keyword for which the detailed information search unit has searched the detailed information. The information processing apparatus includes:
Based on the log information recorded in the log information storage unit, a predetermined point is added for each keyword detected by the keyword detection unit, and a predetermined point is determined for each keyword selected by the keyword selection unit. A point calculation unit for adding points;
The information processing apparatus according to claim 3, wherein the log information storage unit records the points calculated by the point calculation unit in association with each keyword. An information processing method in an information processing apparatus having a keyword list in which predetermined keywords are recorded,
A voice recognition step of acquiring the input voice as voice data, and voice recognition of the acquired voice data;
A keyword detection step of detecting a keyword from the voice recognition result of the voice data based on the keyword list;
A log information recording step for recording, as log information, a log in which the detected keyword is associated with the date and time when the keyword was detected;
An information processing method comprising: A program for causing a computer to function as an information processing apparatus having a keyword list in which predetermined keywords are recorded,
A voice recognition function for acquiring input voice as voice data, and voice recognition of the acquired voice data;
A keyword detection function for detecting a keyword from the voice recognition result of the voice data based on the keyword list;
A log information storage function for recording, as log information, a log associated with the detected keyword and the date and time when the keyword was detected;
A display control function for displaying the detected keyword on a predetermined display unit;
A program to make a computer realize. A voice chat system comprising a plurality of information processing devices capable of performing voice chat,
At least one of the information processing devices includes:
It has a keyword list in which predetermined keywords are recorded,
A voice recognition unit that acquires input voice as voice data and recognizes the acquired voice data;
A keyword detection unit that detects a keyword from the speech recognition result of the speech data based on the keyword list;
A log information storage unit in which a log associated with the detected keyword and the date and time when the keyword was detected is recorded as log information;
A display control unit for displaying the detected keyword on a predetermined display unit;
A voice chat system comprising: The voice chat system according to claim 7, wherein the log information storage unit aggregates the detected keywords in association with a partner and a date and time when voice chat was performed. The information processing apparatus includes:
Obtaining voice data corresponding to the voice input to the other information processing apparatus as the voice chat partner;
The voice chat system according to claim 7, wherein the voice recognition unit recognizes the voice data acquired from the other information processing apparatus. The keyword detection unit detects a keyword from a voice recognition result of the voice data acquired from the other information processing apparatus;
10. The voice according to claim 9, wherein the log information of a keyword detected from a voice recognition result of voice data acquired from the other information processing apparatus is recorded in the log information storage unit. Chat system. The voice chat system further includes a keyword management server that manages the keywords detected by the information processing apparatus that has executed the voice chat,
The said keyword management server is provided with the keyword total part which receives the said log information from the said information processing apparatus, and totals the said keyword based on the received said log information, The characterized by the above-mentioned. Voice chat system. The keyword management server
A product list in which products associated with the previous term keyword managed by the keyword management server are recorded;
A product for recommending the product recorded in the product list to the information processing device by collating the keyword described in the log information received from the information processing device with the product list The voice chat system according to claim 7, further comprising a recommendation unit. The keyword management server
Referring to the received aggregation results of the keywords, a keyword having a high aggregation point in the voice chat is extracted from the log information acquired from each of the information processing devices performing the voice chat, and extracted. The voice chat system according to claim 11, further comprising a related keyword registration unit that registers the keyword as a related keyword. The voice chat system further includes a search server that allows the information processing apparatus to search for the keyword and an article related to the keyword,
The search server transmits a search keyword searched in the search server to the information processing apparatus,
The voice chat system according to claim 7, wherein the information processing apparatus generates the keyword list based on the received search keyword. A plurality of information processing devices capable of performing voice chat;
While performing control of the voice chat executed between the plurality of information processing devices, a keyword management server having a predetermined keyword list;
Including
The information processing apparatus includes:
The input voice is set as voice data, and the voice data is transmitted to the other information processing apparatus that is the voice chat partner via the keyword management server, and the other information processing is performed via the keyword management server. A voice conversation control unit for acquiring voice data transmitted from the device;
The keyword management server
An audio data mediation unit that mediates transmission / reception of audio data transmitted from the plurality of information processing devices;
A voice recognition unit for voice recognition of the voice data;
A keyword detection unit that detects a keyword from the speech recognition result of the speech data based on the keyword list;
A log information storage unit in which a log associated with the detected keyword and the date and time when the keyword was detected is recorded as log information;
A voice chat system comprising:

Images