JPWO2018061839A1 - Transmission apparatus, transmission method and transmission program - Google Patents

Abstract

Provide information according to your needs. A voice collecting unit for collecting voice and generating voice data indicating the voice, a voice keyword extraction unit for extracting a voice keyword which is a keyword included in the voice from the voice data, a voice from the voice data A voice feature extraction unit for extracting voice features including at least one of strength, speed, and intonation, and voice features extracted from a group of emotion keywords stored in advance based on the features of the voice A transmission program for realizing an emotion keyword selection unit for selecting an emotion keyword, and a transmission unit for transmitting the extracted voice keyword and the selected emotion keyword.

Description

  The present invention relates to a transmission device, a transmission method, and a transmission program.

  As a conventional information presentation apparatus, there is one described in Japanese Patent Application Laid-Open No. 2012-256183 (Patent Document 1). The above-mentioned conventional information presentation apparatus estimates the strength of the desire that the user currently has and the situation in which the user is currently placed, and by querying the database describing these combinations, Present items that can meet both the needs of the user and the situation in which the user is placed.

JP 2012-256183 A

  However, in the above-mentioned conventional information presentation apparatus, since it only estimates the strength of the desire of the user and the situation in which the user is placed, it has not always been possible to present information according to the needs of the user.

  The present invention has been made in view of such circumstances, and it is an object of the present invention to provide information according to the needs of the user.

  A transmission program according to an aspect of the present invention includes a voice collection unit that collects voice and generates voice data indicating the voice in a computer, and voice for extracting a voice keyword that is a keyword included in the voice from the voice data. A keyword extraction unit, a voice feature extraction unit for extracting voice features including at least one of voice strength, speed, and intonation from voice data, and emotion keyword groups stored in advance based on voice features Then, an emotion keyword selection unit for selecting an emotion keyword corresponding to the extracted voice feature and a transmission unit for transmitting the extracted speech keyword and the selected emotion keyword are realized.

  A transmitting apparatus according to another aspect of the present invention includes a voice collecting unit for collecting voice and generating voice data indicating the voice, and voice keyword extraction for extracting a voice keyword which is a keyword included in the voice from the voice data. A voice feature extraction unit that extracts voice features including at least one of voice strength, speed, and intonation from voice data, and emotion keyword groups stored in advance based on voice features, An emotion keyword selection unit that selects an emotion keyword corresponding to an extracted voice feature, and a transmission unit that transmits the extracted speech keyword and the selected emotion keyword.

  According to still another aspect of the present invention, there is provided a transmission method comprising: collecting voice and generating voice data indicating the voice; extracting a voice keyword, which is a keyword included in the voice, from the voice data; Extracting voice features including at least one of voice strength, speed, and intonation from data, and based on voice features, to voice features extracted from a group of prestored emotion keywords It includes selecting the corresponding emotion keyword, and transmitting the extracted voice keyword and the selected emotion keyword.

  According to the present invention, it is possible to provide information according to the needs of the user.

It is a figure which shows the structure of the search system 100 containing the transmission device 110 which concerns on one Embodiment of this invention. It is a figure which shows an example of the functional block with which the transmitter 110 is provided. It is a figure which shows Russell's emotion ring model and the keyword contained in it. It is a figure which shows an example of the functional block with which the search device 120 is provided. It is a figure which shows an example of the functional block with which the output device 130 is equipped. 6 is a flowchart showing an example of processing in the search system 100. It is a flowchart which shows a dictionary database update process.

  Hereinafter, an embodiment of the present invention will be described with reference to the attached drawings. FIG. 1 is a diagram showing the configuration of a search system 100 including a transmission device 110 according to an embodiment of the present invention. The search system 100 includes a transmission device 110, a search device 120, and an output device 130. The search system 100 according to the present embodiment performs a predetermined search based on the keyword extracted from the voice collected by the transmitting device 110 and the keyword corresponding to the emotion or atmosphere extracted from the voice, and the search result Is a system that outputs

  The transmission device 110 is a computer that transmits a predetermined keyword to the search device 120 based on the voice collected at the place where the transmission device 110 is placed. The transmission device 110 may be a computer installed in a facility or a store, or may be a computer (such as a smartphone or a tablet terminal) owned by a user who has visited the facility or the store. The transmitter comprises a processor, a memory and a communication interface. The transmitting device 110 can communicate with the search device 120 via, for example, a mobile telephone communication network or the Internet.

  The search device 120 is a computer (server) that provides information to the user of the output device 130 based on the keyword received from the transmission device 110. The search device 120 comprises a processor, a memory, a database and a communication interface. The search device 120 can communicate with the transmission device 110 and the output device 130 via, for example, the Internet.

  The output device 130 is a computer that outputs a search result based on data (display data) provided from the search device 120. The output device 130 outputs, as a search result, a numerical value, a character, a video (image), an audio and the like to a display, a speaker and the like. The output device 130 is, for example, a smartphone, a tablet terminal, a personal computer or the like. The output device 130 comprises a processor, a memory and a communication interface. The output device 130 can communicate with the search device 120 via, for example, a mobile telephone communication network or the Internet.

  The output device 130 may output a predetermined operation based on the search result. The output device 130 may perform predetermined communication or control a motor, an actuator, a sensor or the like based on, for example, a search result.

  FIG. 2 is a diagram illustrating an example of functional blocks included in the transmission device 110. The transmission device 110 includes a voice collection unit 200, a voice keyword extraction unit 210, a dictionary database 220, a voice feature extraction unit 230, an emotion keyword selection unit 240, an emotion database 250, a transmission unit 260, and a dictionary database update. And an instruction generation unit 270.

  The transmission program is stored in the memory of the transmission device 110, and each function of the transmission device 110 (the voice collection unit 200, the speech keyword extraction unit 210, The dictionary database 220, the voice feature extraction unit 230, the emotion keyword selection unit 240, the emotion database 250, the transmission unit 260, and the dictionary database update instruction creation unit 270 are realized. The transmission program is read from the computer readable recording medium into the memory of the transmission device 110 and executed by the processor of the transmission device 110.

  The voice collection unit 200 collects voices emitted around the transmitter 110 and generates voice data indicating the voices. Specifically, the voice collection unit 200 converts voice collected by a microphone or the like into an electrical signal, and generates voice data by converting information indicated by the electrical signal into digital data. Further, the voice collection unit 200 may have a storage unit for temporarily storing the generated voice data. The storage unit is, for example, an existing storage that can be stored magnetically, electrically or optically, such as a hard disk drive (HDD), a solid state drive (SSD), a memory card, an optical disk, or a random access memory (RAM). It is an apparatus or a storage medium. The sound collection unit 200 may be a built-in microphone of the transmission device 110, or may be an external microphone (an external wired microphone or a wireless microphone). For example, a tablet terminal to which an external microphone is connected functions as the transmission device 110. The transmitter 110 may include a plurality of voice collection units 200. The transmitting device 110 may detect the relative position of the plurality of voice collecting units 200.

  The voice keyword extraction unit 210 extracts, from the voice data generated by the voice collection unit 200, a keyword included in the voice (hereinafter also referred to as a "voice keyword"). Specifically, the speech keyword extraction unit 210 first analyzes speech data and converts the speech into text data. Then, the speech keyword extraction unit 210 compares each word included in the text data with a word stored in advance in the dictionary database 220. Then, when each word included in the text data matches a word stored in advance in the dictionary database 220, the speech keyword extraction unit 210 extracts the word as a speech keyword.

  The voice feature extraction unit 230 extracts the feature of the voice from the voice data generated by the voice collection unit 200. In the present embodiment, the voice feature extraction unit 230 extracts at least one of the strength, speed and intonation of the voice, and the strength, speed or intonation, or a combination of two or more of them. It extracts as the feature of the voice concerned.

  The voice feature extraction unit 230 extracts the strength of the voice based on the magnitude of the amplitude of the voice signal indicated by the voice data. The voice feature extraction unit 230 extracts, for example, the average of the voice strength in a predetermined unit period as the voice strength. Also, the voice feature extraction unit 230 may extract the average of the strength of the voice including the predetermined number of characters, the number of words, or the number of sentences as the strength of the voice.

  Further, the voice feature extraction unit 230 extracts the speed of the voice based on the number of sounds of the words included in the voice. The voice feature extraction unit 230 extracts, for example, the number of sounds included in a predetermined unit period as the speed of the voice. Further, the voice feature extraction unit 230 may extract the number of characters, the number of words, or the number of sentences of the voice in a predetermined unit period as the speed of the voice.

  Also, the voice feature extraction unit 230 extracts the intonation of the voice based on the change in the voice strength. For example, the voice feature extraction unit 230 divides a voice into a plurality of units, and extracts a change in strength in each unit and / or a change in strength between units as an expression of the voice. The unit of speech is, for example, words or clauses that constitute a sentence included in speech.

  The emotion keyword selection unit 240 converts the speaker's emotion or the atmosphere of the place indicated by the feature into a keyword based on the feature of the voice extracted by the voice feature extraction unit 230. For example, the emotion keyword selection unit 240 selects, from the emotion keyword group stored in advance in the emotion database 250, the emotion keyword corresponding to the feature of the voice extracted by the voice feature extraction unit 230. In addition, the emotion database 250 stores a large number of keywords related to emotions and moods in association with voice features. Specifically, the emotion database 250 associates each value (or a predetermined range of possible values) of the strength, speed and intonation of the voice, and a pattern of combinations of the values or ranges with each keyword. Store. Then, the emotion keyword selection unit 240 determines the feature of the voice extracted by the voice feature extraction unit 230, that is, the value (or the predetermined range in which the value can be taken) of the strength, the speed and the intonation of the voice. Alternatively, a predetermined keyword is selected from among a large number of keywords stored in the emotion database 250 based on the pattern of combination of ranges. The keywords stored in the emotion database 250 may be keywords included in a so-called Russell emotion ring model as shown in FIG.

  The emotion keyword selection unit 240 may select an emotion keyword further based on the biometric information of the speaker who has emitted the collected voice, in addition to the feature of the voice extracted by the voice feature extraction unit 230. The emotion keyword selection unit 240 estimates the emotion of the speaker based on biological information such as the temperature, heart rate, pulse, brain waves, skin conductance level of the speaker, and selects a keyword corresponding to the estimated emotion. You may The speaker's biometric information may be obtained from a sensor connected to the transmitting device 110 or may be obtained from an external device of the transmitting device 110 through, for example, a network.

  The voice feature extraction unit 230 may extract an index related to the degree of positive or negative of the utterance from the waveform of the voice data. For example, using the Empath (registered trademark), the voice feature extraction unit 230 can extract an index related to the degree of positive or negative of speech from the waveform of voice data. Empath analyzes the physical characteristics of the waveform of the voice data, and calculates the judgment value in 50 steps for each item of normality, anger, joy, sadness and spirit level. The voice feature extraction unit 230 can extract an index related to the degree of positive or negative of the utterance based on the result calculated as described above. As described above, a technology for calculating a determination value relating to emotion or mood from a waveform of voice data is called voice mood analysis technology. Items determined using voice mood analysis techniques are not limited to normality, anger, joy, sadness and vigor, but may include any item related to emotion. The emotion database 250 may store an index related to the degree of affirmation or denial of speech in association with each emotion keyword. The emotion keyword selection unit 240 may select, from the emotion database 250, the emotion keyword corresponding to the index related to the degree of positive or negative of the utterance extracted by the voice feature extraction unit 230.

  The transmitting unit 260 transmits the speech keyword extracted by the speech keyword extraction unit 210 and the emotion keyword selected by the emotion keyword selection unit 240 to the search device 120. For example, the transmitting unit 260 indicates that a predetermined period has elapsed since the voice collecting unit 200 collected voice, that the strength of the recorded voice extracted by the voice feature extracting unit 230 exceeds a predetermined value, the voice keyword In response to the extraction unit 210 extracting a predetermined word, the speech keyword extracted by the speech keyword extraction unit 210 and the emotion keyword selected by the emotion keyword selection unit 240 are transmitted to the search device 120. The predetermined word is, for example, "search" or the like.

  The transmitting unit 260 may further transmit environment information or biometric information to the search device 120 in addition to the speech keyword and the emotion keyword. The environmental information is, for example, information on a place or space where the transmission device 110 is placed, such as position, temperature, humidity, illuminance, shaking and the like. Environmental information is acquired by measuring devices, such as GPS, a temperature sensor, a humidity sensor, an illumination sensor, an acceleration sensor, and an infrared sensor. The transmission unit 260 may directly acquire environmental information and biological information from the measurement device, or may indirectly acquire it via a network or the like.

  The dictionary database update instruction creating unit 270 creates an instruction for updating the dictionary database 220 (a dictionary database update instruction). The dictionary database update instruction is created at a predetermined timing. Here, the predetermined trigger may be when the hit rate of the dictionary database 220 falls below a predetermined threshold, or may be a predetermined constant interval. The hit rate means the ratio of keywords that have been determined to be included in the voice collected by the voice collection unit 200 among all the keywords registered in the dictionary database 220. The transmitting unit 260 transmits the dictionary database update instruction created by the dictionary database update instruction creating unit 270 to the search device 120.

  FIG. 4 is a diagram illustrating an example of functional blocks included in the search device 120. The search device 120 includes a reception unit 300, a search execution unit 310, a database 320, a transmission unit 330, a keyword database 340, an estimation unit 350, and a dictionary database creation unit 360. The search device 120 is a search engine which searches for information stored in the database 320 based on a predetermined keyword, and transmits the search result to the output device 130. The search device 120 may receive a speech keyword transmitted from the transmission device 110 and accumulate the information to estimate the topic from the accumulated speech keyword. If the speech keyword is, for example, "handle", "brake", "tire" or the like, it can be inferred that a topic related to "car" is made. The inferred topic is provided to, for example, an advertiser. Further, in response to the dictionary database update instruction from the transmitter 110, the search device 120 also performs a process of updating the dictionary database 220.

  The memory of the search device 120 stores a search program that causes the search device 120 to execute a search process based on the speech keyword and the emotion keyword. The search device is obtained by cooperation of the hardware resources of the search device 120 and the search program. The respective functions of 120 (the receiving unit 300, the search execution unit 310, the database 320, the transmitting unit 330, the keyword database 340, the estimating unit 350, and the database creating unit 360) are realized. The search program is read from the computer readable recording medium into the memory of the search device 120 and executed by the processor of the search device 120.

  The receiving unit 300 receives the speech keyword and the emotion keyword transmitted by the transmission device 110. Further, the receiving unit 300 may further receive environment information and biometric information in addition to the speech keyword and the emotion keyword transmitted by the transmission device 110. The receiving unit 300 receives the dictionary database update instruction transmitted by the transmitting device 110.

  The search execution unit 310 searches the database 320 based on the speech keywords and emotion keywords received by the reception unit 300 and / or the environment information and / or the biometric information. In the present embodiment, the speech keyword, the emotion keyword, the environment information, and the biometric information are all text data, and the search execution unit 310 is, for example, text data used for a search among the information stored in the database 320. Information including any of the above is extracted as a search result. The information is, for example, text data or the like included in the website.

  The transmission unit 330 transmits the search result extracted by the search execution unit 310 to the output device 130 through the network. The transmitting unit 330 transmits, for example, the URL of the website extracted by the search execution unit 310, text data, image data, and the like included in the website as a search result to the output device 130.

  The keyword database 340 stores speech keywords received through the receiver 300. The estimation unit 350 estimates a related term of the speech keyword stored in the keyword database 340 in response to the dictionary database update instruction received through the reception unit 300. The term related to the speech keyword means a term that is frequently used simultaneously with the speech keyword, and such a term is also called "co-occurring word". Co-occurring words do not necessarily mean synonymous terms. The estimation unit 350 is, for example, a co-occurrence word search tool to which artificial intelligence is applied. As such a co-occurrence word search tool, for example, there is known one which performs morphological analysis on the content of a web page which is higher than the search results such as Google and Yahoo, and presents words and phrases frequently appearing in the same document as co-occurrence words. ing. Morphological analysis is a sequence of morphemes (the smallest units having meaning in a language) based on information such as natural language text data without annotations of grammatical information, grammar of the target language, and part of speech of words called a dictionary. It means the task of decomposing it into two and determining the part of speech of each morpheme.

  The dictionary database creation unit 360 updates the dictionary database 220 in response to the dictionary database update instruction received through the reception unit 300. The dictionary database creation unit 360 creates the updated dictionary database 220 based on the speech keywords stored in the keyword database 340 and the related words estimated by the estimation unit 350. The updated dictionary database 220 registers voice keywords that have been extracted from the voice collected by the voice collection unit 200 and their related words as keywords. Among keywords registered in the dictionary database 220 before update, speech keywords that have not been extracted from the speech collected by the speech collection unit 200 are deleted from the dictionary database 220 after update. By repeating such update processing, the hit rate of the dictionary database 220 can be increased.

  The transmitting unit 330 transmits the updated dictionary database 220 to the transmitting device 110. The transmitter 110 that has received the updated dictionary database 220 replaces the dictionary database 220 before update with the dictionary database 220 after update.

  FIG. 5 is a diagram illustrating an example of functional blocks included in the output device 130. The output device 130 includes a search result receiving unit 400 and a search result output unit 410. In the output device 130, the search result receiving unit 400 receives the search result transmitted by the search result transmitting unit 330, and the search result output unit 410 receives the received search result as a numerical value, a character, a video (image), a voice, etc. Output through a display or a speaker.

  An output program is stored in the memory of the output device 130, and each function of the output device 130 (search result receiving unit 400, and search result output unit is realized by cooperation between the hardware resources of the output device 130 and the output program. 410) is realized. The output program is read from the computer readable recording medium into the memory of the output device 130 and executed by the processor of the output device 130.

  FIG. 6 is a flowchart showing an example of processing in the search system 100.

  First, the voice collection unit 200 collects voices emitted around the transmission device 110, and generates voice data indicating the voices (S600). The voice collection unit 200 generates this voice data, for example, when voices of “Today is hot” are collected from one or more speakers. Next, the speech keyword extraction unit 210 extracts speech keywords from the speech data (S601). For example, the speech keyword extraction unit 210 extracts a word “hot” as speech keyword from speech data “It is hot today”. Next, the voice feature extraction unit 230 extracts the feature of the voice from the voice data generated by the voice collection unit 200 (S602). The voice feature extraction unit 230 extracts, for example, the strength, speed, and intonation of the voice in the voice “It is hot today.”

  Next, the emotion keyword selection unit 240 selects an emotion keyword indicating the speaker's emotion or the atmosphere of the place based on the voice feature extracted by the voice feature extraction unit 230 (S603). The emotion keyword selection unit 240 is stored, for example, in the emotion database 250 as an emotion keyword corresponding to a pattern combining the voice strength, speed, and intonation value in the voice "Today is hot." Select the "frustration" that was Next, the transmission unit 260 transmits the speech keyword extracted by the speech keyword extraction unit 210 and the emotion keyword selected by the emotion keyword selection unit 240 to the search device 120 (S604). The transmitting unit 260 transmits “hot” and “frustration” to the search device 120 as the speech keyword and the emotion keyword, respectively. In addition, the transmitting unit 260 is position information indicating "outside of Nagaokakyo Station at Kamitome 1-chome, Nagaokakyo City, Kyoto Prefecture" where the transmitting device 110 is placed, and "36 ° C" which is the temperature at the relevant place. , It transmits to the search device 120 as environmental information.

  Next, the keyword receiving unit 300 receives the voice keyword, the emotion keyword, and the environment information transmitted by the transmitting device 110 (S605). For example, the keyword receiving unit 300 uses “hot” and “irritated” as speech keywords and emotion keywords, respectively, and also indicates position information and temperature “36 outside of Nagaokakyo Station in Kamifu 1-chome, Nagaokakyo City, Kyoto Prefecture”. "° C" is received as environmental information. Next, the search execution unit 310 searches the database 320 based on the speech keyword and emotion keyword received by the keyword reception unit 300 and the environment information (S606). For example, based on these keywords and environmental information, the search execution unit 310 has a speaker who issued a voice saying "It is hot today." "Outside of Nagaokakyo Station at Kamitome 1-chome, Nagaokakyo City, Kyoto Prefecture" In the temperature "36 ° C", it is judged that the word "hot" is emitted with the feeling "frustration". Then, the search execution unit 310 searches for “a store providing a cold drink at a radius of 100 m of“ Nagaokakyo Station at Kamitome 1-chome, Nagaokakyo City, Kyoto Prefecture ”. Next, the search result transmission unit 330 transmits the search result extracted by the search execution unit 310 to the output device 130 through the network (S607). The search result transmission unit 330 outputs, for example, as a search result, a list of websites of stores corresponding to "a store providing cold drinks at a radius of 100 m of" Nagaokakyo Station at Kamitome 1-chome, Nagaokakyo City, Kyoto Prefecture ". Send to device 130.

  Next, the search result receiving unit 400 receives the search result transmitted by the search result transmitting unit 330 (S608). Then, the search result output unit 410 outputs the received search result through a display, a speaker or the like (S609). For example, the output device 130 outputs a list of websites of stores corresponding to “stores that provide cold drinks at a radius of 100 m of“ Kyoto nagaokakyo city 1 foot, Nagaokakyo station ””. Display on the display provided. In this example, for example, the position information indicates not "outside of Nagaokakyo Station in Kamigaoka, Nagaokakyo City, Kyoto Prefecture" but "Building of No. 10, No. 1 of Nagaokakyo City, Kyoto Prefecture" and temperature "36 If the search execution unit 310 indicates that "It is hot today," the word "Hot" is the word "hot" in the building, and the search execution unit 310 indicates that the temperature is "28 ° C". It may be judged that it is emitted with the feeling of "frustration" in In this case, the search execution unit 310 may search for "that the temperature of the building can be controlled" and control the air conditioning may be output as a search result. In this case, for example, the search result output unit 410 outputs that the set temperature of the air conditioning is changed to “25 ° C.”.

Next, the flow of the dictionary database update process will be described with reference to FIG.
The transmission device 110 creates a dictionary database update instruction at a predetermined timing (S700), and transmits this to the search device 120 (S701). When the search device 120 receives the dictionary database update instruction (S702), the search device 120 acquires a speech keyword from the keyword database 340 (S703), and estimates a related term of the speech keyword (S704). Next, the search device 120 creates the updated dictionary database 220 based on the speech keyword and its related words (S 705), and transmits this to the transmission device 110 (S 706). When the transmitting device 110 receives the updated dictionary database 220 (S 707), the transmitting device 110 updates the dictionary database 220 by replacing the old dictionary database 220 with the updated dictionary database 220 (S 708).

  The exemplary embodiments of the present invention have been described above. According to the present embodiment, the voice is collected to generate voice data indicating the voice, the voice keyword which is the keyword included in the voice is extracted from the voice data, and the voice strength, speed and A voice feature including at least one of intonation is extracted, and based on the voice feature, an emotion keyword corresponding to the extracted voice feature is selected from a pre-stored emotion keyword group, and the extracted voice is extracted. Send keywords and selected emotional keywords. As a result, the search can be performed based on both the word and emotion extracted from the voice, so that information according to the needs of the speaker who has made the voice can be provided.

  Further, in the present embodiment, keywords included in Russell's emotion circular model may be stored as a keyword group. This makes it possible to more accurately extract the speaker's emotions.

  Further, in the present embodiment, when a word included in the speech matches any of the words stored in the dictionary database, the word may be extracted as the speech keyword. This can reduce the load on the algorithm for extracting speech keywords.

  Also, in the present embodiment, a predetermined period has elapsed since the voice collection unit collected voice, the strength of the voice extracted by the voice feature extraction unit exceeded a predetermined value, or voice keyword extraction The speech keyword and the selected emotion keyword may be transmitted in response to the section extracting a predetermined word. This can further increase the accuracy of the search.

  Further, in the present embodiment, a search result by a predetermined search may be output. Thereby, the search result can be transmitted to the speaker or reflected in the environment in which the speaker is placed.

  The dictionary database 220 is updated based on the speech keywords extracted from the speech collected by the speech collection unit 200 and the related words, as those matching the speech keywords registered in the dictionary database 220. Can increase the hit rate of Thereby, the dictionary database 220 can be optimized. By optimizing the dictionary database 220, it is appropriately determined whether a product or service is actually popular based on the voice collected by the voice collection unit 200 (for example, the voice actually uttered by the customer). be able to. Further, since the voice collected by the voice collection unit 200 is the voice actually collected at the place where the transmission device 110 is placed, the product or service is not based on the evaluation on the Internet but based on the evaluation in the real world. It can be determined whether or not it is actually in vogue. Moreover, since unnecessary keywords are deleted from the dictionary database 220 by repeating the update of the dictionary database 220, the storage capacity of the dictionary database 220 may be small. As a result, it is possible to miniaturize the transmitter 110 and reduce the power consumption.

  In addition, each embodiment described above is for making an understanding of this invention easy, and is not for limiting and interpreting this invention. The present invention can be modified / improved without departing from the gist thereof, and the present invention also includes the equivalents thereof. That is, those in which persons skilled in the art appropriately modify the design of each embodiment are also included in the scope of the present invention as long as they have the features of the present invention. For example, each element included in each embodiment and its arrangement, material, conditions, shape, size, and the like are not limited to those illustrated, and can be appropriately changed. Each embodiment is an exemplification, and it goes without saying that partial replacement or combination of the configurations shown in different embodiments is possible, and these are also included in the scope of the present invention as long as they include the features of the present invention. .

DESCRIPTION OF SYMBOLS 100 ... Search system, 110 ... Transmission apparatus, 120 ... Search apparatus, 130 ... Output apparatus, 200 ... Speech collection part, 210 ... Speech keyword extraction part, 220 ... Dictionary database, 230 ... Speech feature extraction part, 240 ... Emotion keyword selection Part 250 250 emotion database 260 transmitter 300 keyword receiver 310 search executor 320 database 330 search result transmitter 400 search result receiver 410 search result output unit

Claims (11)

On the computer
A voice collecting unit that collects voice and generates voice data indicating the voice;
A speech keyword extraction unit that extracts speech keywords that are keywords included in the speech from the speech data;
A voice feature extraction unit for extracting features of the voice including at least one of strength, speed, and intonation of the voice from the voice data;
An emotion keyword selection unit for selecting an emotion keyword corresponding to the extracted voice feature from a previously stored emotion keyword group based on the voice feature;
A transmitter configured to transmit the extracted speech keyword and the selected emotion keyword;
Transmission program to realize. The transmission program according to claim 1, wherein
Causing the computer to further realize an emotion database that stores keywords included in Russell's emotion ring model as the keyword group;
Send program. The transmission program according to claim 1 or 2, wherein
Causing the computer to further realize a dictionary database in which a plurality of words are stored in advance;
The speech keyword extraction unit extracts the word as the speech keyword when a word included in the speech matches any of the words stored in the dictionary database.
Send program. The transmission program according to any one of claims 1 to 3, wherein
The transmitting unit transmits the voice keyword and the selected emotion keyword in response to a lapse of a predetermined period after the voice collecting unit collects the voice.
Send program. The transmission program according to any one of claims 1 to 3, wherein
The voice feature extraction unit extracts at least the strength of the voice as the feature of the voice,
The transmitting unit transmits the voice keyword and the selected emotion keyword in response to the voice strength extracted by the voice feature extraction unit exceeding a predetermined value.
Send program. The transmission program according to any one of claims 1 to 3, wherein
The transmitting unit transmits the speech keyword and the selected emotion keyword in response to the speech keyword extraction unit extracting a predetermined word.
Send program. The transmission program according to any one of claims 1 to 6, wherein
Causing the computer to further realize an output unit that outputs a search result by the predetermined search;
Send program. A voice collecting unit that collects voice and generates voice data indicating the voice;
A speech keyword extraction unit that extracts speech keywords that are keywords included in the speech from the speech data;
A voice feature extraction unit for extracting features of the voice including at least one of strength, speed, and intonation of the voice from the voice data;
An emotion keyword selection unit for selecting an emotion keyword corresponding to the extracted voice feature from a previously stored emotion keyword group based on the voice feature;
A transmitter configured to transmit the extracted speech keyword and the selected emotion keyword;
Transmitter equipped with Collecting voice and generating voice data indicative of the voice;
Extracting an audio keyword which is a keyword included in the audio from the audio data;
Extracting features of the voice from the voice data, the voice characteristics including at least one of strength, speed, and intonation of the voice;
Selecting an emotion keyword corresponding to the feature of the voice extracted from a group of emotion keywords stored in advance based on the feature of the voice;
Transmitting the extracted speech keyword and the selected emotion keyword. The transmitter according to claim 8, wherein
The transmission device transmits the position information of the transmission device. A search apparatus for executing a search process based on the speech keyword and the emotion keyword according to claim 3, wherein
A keyword database storing the speech keywords;
A receiving unit that receives an instruction to update the dictionary database from the computer;
An estimation unit configured to estimate a related term of the speech keyword stored in the keyword database in response to the update instruction received through the reception unit;
A dictionary database creation unit for creating an updated dictionary database based on the speech keywords stored in the keyword database and the inferred related words;
A transmitter for transmitting the updated dictionary database to the computer;
A search device comprising

Images