JP2016156993A - Information processing unit, control method of information processing unit, control program and storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To detect a voice including a name of a registration object person to instruct the registration object person to perform a predetermined operation.SOLUTION: An information processing unit (1) includes: a person's name extraction part (14) configured to extract a name of a registration object person from voice data of a voice including the name of the registration object person; a voice instruction generation part (15) configured to generate a voice instruction to the registration object person including the person's name extracted by the person's name extraction part (14); and a voice output part (32) configured to present the voice instruction to the registration object person.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus that presents an instruction to a target person so that the target person performs a specific operation, a control method for the information processing apparatus, a program, and a recording medium.

  2. Description of the Related Art Conventionally, a robot apparatus that can register a person's name and face using a dialogue function with a human as a recognition target is known.

  For example, Patent Document 1 searches for data using a face photograph, a person's name, and voice characteristics, and if the voice of the speaker is new, the speaker becomes a recognition target and registers the person's name and face. A robot apparatus that instructs to perform a specific operation such as giving a voice to a recognition target and giving the name a name and then saying a favorite food is described.

JP 2003-255989 A (published September 10, 2003)

  However, since the robot apparatus described in Patent Document 1 determines whether or not the speaker is a new recognition target based on whether or not the speaker's voice is new, the speaker's voice is not new. There is a problem that even if the voice includes the name of another person, the person is not recognized.

  For example, when a non-new (that is, recognized) speaker introduces a new recognition target or speaks to the recognition target, the technique described in Patent Document 1 does not provide a new voice for the speaker. Therefore, it may not be possible to correctly determine whether the person introduced or spoken by the speaker is a new recognition target or a recognized person. If this determination is wrong, a new recognition target person name cannot be recognized.

  The present invention has been made in view of the above points, and an object of the present invention is to instruct the subject to perform a predetermined operation when a voice including the subject's person name is detected. It is to realize an information processing apparatus capable of performing the processing, a control method for the information processing apparatus, and the like.

  In order to solve the above-described problem, an information processing apparatus according to an aspect of the present invention is an information processing apparatus including a voice input unit that receives voice input, and is input from the voice input unit. The identification information extraction unit extracts the identification information extraction unit that extracts the identification information of the target person from the voice data including the identification information, and the operation instruction that instructs the target person to perform a predetermined operation. An instruction generation unit that generates the identification information including the identification information, and an instruction presentation unit that presents the operation instruction to the target person.

  In order to solve the above problem, a control method for an information processing device according to an aspect of the present invention is a control method for an information processing device including a voice input unit that accepts voice input. A voice input step for receiving voice input including identification information of the target person, an identification information extraction step for extracting the target person identification information from the voice data of the voice received in the voice input step, and the target An instruction generation step for generating an operation instruction for instructing a person to perform a predetermined operation including the identification information extracted in the identification information extraction step, and the operation instruction generated in the instruction generation step. An instruction presentation step to be presented to the subject.

  According to one aspect of the present invention, there is an effect that when a voice including a person name of a target person is detected, the target person can be instructed to perform a specific operation.

It is a block diagram which shows an example of schematic structure of the information processing apparatus which concerns on this invention. It is a block diagram which shows an example of the hardware constitutions of information processing apparatus. It is a figure explaining the process which an information processing apparatus matches and registers the person name of a registration subject, and characteristic data. It is a figure which shows an example of the process which an information processing apparatus extracts the text of a person name from text data. It is a figure which shows an example of the audio | voice template which an information processing apparatus outputs. It is a flowchart explaining an example of the flow of a process in which an information processing apparatus registers a person name of a registration target person and feature data in association with each other.

Embodiment 1
Hereinafter, embodiments of the present invention will be described in detail.

(Process in which the information processing apparatus 1 registers a person to be registered)
First, in one embodiment of the present invention, a process of registering a person name (identification information) and feature data (unique information) of a registration target person (target person) that is a target to be registered by the information processing apparatus 1 in association with each other. This will be described with reference to FIG. FIG. 3 is a diagram illustrating processing in which the information processing apparatus 1 registers the person name of the registration target person and the feature data in association with each other.

  The information processing apparatus 1 accepts an input of a voice including a person name (last name, first name, etc.) of the person to be registered, extracts the person name of the person to be registered included in the voice, and determines the person name of the person to be registered. An included voice instruction is issued to instruct the person to be registered to perform a predetermined operation.

  The person name of the registration target person may be extracted when an input of a voice uttered by the registration target person is accepted, or when an input of a voice uttered by a person (such as the user U) different from the registration target person is accepted. It may be. Here, as an example of the voice uttered by the registration target person, there is a voice when the registration target person introduces himself / herself and gives a greeting by giving his / her name to another person. On the other hand, examples of voices uttered by a person different from the registration target person include voices when the user U introduces the registration target person to other persons, and when the user U introduces the registration target person to the information processing apparatus 1. And voices when the user U asks or speaks to the person to be registered. In addition, when the person name of a registration object person is contained in the sound which a registration object person himself utters, or the sound which a person different from a registration object person utters, such a sound has a sentence pattern of a predetermined format. Further, the name of the person to be registered extracted by the information processing apparatus 1 is not limited to a person name such as a surname or a name, as long as it is a name that the person to be registered recognizes as a name indicating itself. (Common name), alternative names, stage names, etc.

  In the following, a face of a registration target person who has performed a predetermined operation according to an instruction is imaged, feature data is extracted from a face image F obtained by imaging the face of the registration target person, and the registration target person's feature data, person name, An information processing apparatus 1 that generates and manages registration data in association with each other will be described as an example. Here, the “feature data” of the registration target person is not limited to feature data extracted from the face image F of the registration target person, and is feature data extracted from fingerprint information, retina information, voiceprint information, and the like. Also good.

  In the following description, the case where the “predetermined operation” is an instruction to bring the face closer to the registration target person in order to acquire the face image F obtained by capturing the face of the registration target person will be described as an example. However, it is not limited to this. That is, the information processing apparatus 1 instructs the registration target person to perform a predetermined operation, but the “predetermined operation” is because the information processing apparatus 1 acquires unique information unique to the registration target person. It is not limited to this operation, and any operation may be performed. For example, in the case of an instruction for the information processing apparatus 1 to acquire the fingerprint information of the person to be registered, “contacting the finger with the scanner surface” may be instructed as a “predetermined operation”. Alternatively, “the user to be registered performs a predetermined operation input to the information processing apparatus 1” or “move to a predetermined position” may be instructed as a “predetermined operation”. In such a case, the “registration target person” is not limited to a target person registered in the information processing apparatus 1, and is an instruction target person (target person) who performs a predetermined operation in accordance with an instruction issued by the information processing apparatus 1. ).

  For example, as illustrated in FIG. 3A, the information processing apparatus 1 includes a voice input unit 31 and a voice output unit 32 (instruction presentation unit) that receive voice input, together with Mr. Suzuki and Mr. Sato. The voice “Users are Mr. Suzuki” uttered by the user U is acquired. Then, the information processing apparatus 1 uses “Suzuki”, which is the person name of the person to be registered, included in the voice uttered by the user U, and uses the voice instruction “Mr. Suzuki, Oh, “Please bring your face close.” Is output from the audio output unit 32.

  The information processing apparatus 1 further includes an imaging device 33, which captures an image of a face that is brought close after outputting a voice instruction. For example, as shown in FIG. 3B, when Mr. Suzuki who has heard the voice instruction approaches the information processing apparatus 1 and brings his face close to the information processing apparatus 1, the information processing apparatus 1 captures the face and displays (c) in FIG. A face image F as shown in FIG.

  As described above, the information processing apparatus 1 issues a voice instruction including the person name (for example, “Suzuki”) of the person to be registered included in the voice uttered by the user U, to the person to be registered with this person name. A predetermined operation such as bringing a face close is performed. In the example shown in (a) of FIG. 3, a plurality of persons (that is, user U, Mr. Suzuki, and Mr. Sato) are listening to a voice instruction from the information processing apparatus 1. A specific operation can be made to be performed by a specific registration target person by including the person name. By bringing a face close to a person with a person name (for example, “Mr. Suzuki”) included in the voice instruction, the face of the person to be registered can be correctly imaged without being mistaken for another person.

  The information processing apparatus 1 extracts one or a plurality of feature data from the face image F obtained by capturing the face of Mr. Suzuki whose face is brought close according to the voice instruction, and extracts the extracted feature data and the person name “ Registration data is generated in association with Mr. Suzuki, and this registration data is stored in the registration database 24 (see FIG. 1). The feature data is extracted from the face image F by, for example, the positions of the points P1 and P2 corresponding to the eyes of the face image F, the position of the point P3 corresponding to the nose, and the point P4 corresponding to the mouth (center of the mouth). This is done by calculating the position coordinates of each position of the point P5 (the right end of the mouth), the point P6 (the left end of the mouth), the distance between the points, and the like. Here, the position coordinates are coordinates corresponding to the position of each point in the coordinate system having the origin at a predetermined position (for example, the position of the lower left end) of the face image F. Note that the feature data to be extracted is not limited thereto, and arbitrary feature data such as the image data of the face image F itself, the face color, and the ear shape may be used as the registration data. Further, the face image F is not limited to a planar image, and may be a stereoscopic image.

  Note that although the information processing apparatus 1 includes the imaging device 33 and has been described by taking as an example the case where an instruction voice (operation instruction) is issued to bring the face closer in order to capture the face of the person to be registered, the instruction voice Is not limited to this. For example, after imaging the face of Mr. Suzuki, further voice instructions “Mr. Suzuki, please show me your ears” are also taken, and Mr. Suzuki ’s ear is also imaged, and the shape of the ear is added to the feature data. Also good. When the information processing apparatus 1 includes a fingerprint sensor, a voice instruction “Mr. Suzuki, please keep your finger in close contact with the scanner surface” may be issued to acquire Mr. Suzuki's fingerprint information as feature data.

  In addition, an example in which an operation instruction for imaging the face of a registration target person is issued as a voice has been described. However, the output of the operation instruction is not limited to voice output, and a predetermined operation is performed on the registration target person. As long as the output method can be presented as described above, any method may be used. For example, the operation instruction may be displayed as a character string on a display device (not shown).

(Hardware configuration of information processing apparatus 1)
First, the hardware configuration of the information processing apparatus 1 will be described with reference to FIG. FIG. 2 is a block diagram illustrating an example of a hardware configuration of the information processing apparatus 1. For convenience of explanation, descriptions of other functions that the information processing apparatus 1 can have, such as an operation control unit that controls the posture and the like, and a communication unit that performs data communication, are omitted.

  The information processing apparatus 1 includes a voice input unit 31, a voice output unit 32, an imaging device 33, a control unit 10, and a storage unit 20. The control unit 10 performs control so as to execute processing of each function included in the information processing apparatus 1, and acquires the sound input from the sound input unit 31 and the captured image R captured by the image capturing device 33. Further, predetermined processing is executed with reference to the control unit 10, the recognition dictionary 21, the morphological analysis dictionary 22, and the instruction template database 23 (see FIG. 1) stored in the storage unit 20 as appropriate. Further, the control unit 10 stores the generated registration data in the registration database 24.

(Configuration of information processing apparatus 1)
Next, the configuration of the information processing apparatus 1 will be described with reference to FIG. FIG. 1 is a block diagram illustrating an example of a schematic configuration of the information processing apparatus 1. As already described with reference to FIG. 2, the information processing apparatus 1 includes the audio input unit 31, the audio output unit 32, the imaging device 33, the control unit 10, and the storage unit 20. The control unit 10 that controls each function included in the information processing apparatus 1 further includes a text unit 11, a morpheme analyzer 12, an introduction sentence extraction unit 13, a person name extraction unit 14 (identification information extraction unit), and a voice instruction generation unit. 15 (instruction generation unit), imaging device control unit 16, feature data extraction unit 17 (unique information extraction unit), and registered data management unit 18. The storage unit 20 includes a recognition dictionary 21, a morphological analysis dictionary 22, an instruction template database 23, and a registration database 24 (storage unit).

  The voice input unit 31 is a microphone that accepts voice input. The voice data input from the voice input unit 31 is sent to the text unit 11.

  The audio output unit 32 is a speaker that outputs audio data as audio. The voice output unit 32 outputs voice data of the voice instruction acquired from the voice instruction generation unit 15.

  The imaging device 33 is a digital camera that acquires image data. For example, the imaging device 33 is a camera module that captures an imaging target using a CCD sensor, a CMOS sensor, or the like. Note that the image captured by the imaging device 33 is not limited to a two-dimensional image, and may be a three-dimensional image.

  The text unit 11 calculates the acoustic feature amount of the voice data input from the voice input unit 31 and converts the voice data into text data while referring to the recognition dictionary 21. The recognition dictionary 21 defines an acoustic model and a language model, and the text conversion unit 11 assigns a text corresponding to each acoustic feature amount and converts voice data into text data. Specifically, the recognition dictionary 21 represents what frequency characteristics the voice included in the voice data has, and correspondence between a large number of voice waveform samples and corresponding text data. Relationships are defined. The text unit 11 searches the recognition dictionary 21 and identifies text corresponding to the voice that matches the calculated acoustic feature amount. The text unit 11 sends the text data to the morpheme analyzer 12.

  The morpheme analyzer 12 decomposes the text data acquired from the text unit 11 into morphemes. A morpheme is the smallest linguistic unit that has meaning and is a component that indicates a grammatical relationship. The morpheme analysis unit 12 decomposes the text data into each grammatical component with reference to the morpheme analysis dictionary 22 and specifies the grammatical relationship between the respective components. The morpheme analyzer 12 outputs the analysis result to the introductory sentence extractor 13 together with the text data to be analyzed. A specific example of the morphological analysis in the text data in which the morphological analysis unit 12 converts the voice that the user U introduces the registration target into text will be described later.

  The introductory sentence extracting unit 13 extracts a sentence including the name of the person to be registered from text data (text) generated by speech recognition based on the result of morphological analysis. When the registration target person introduces himself / herself to a person different from the registration target person or a person different from the registration target person introduces the registration target person to a third party or the information processing apparatus 1 Introductory text may be extracted from For example, an introductory sentence that the person to be registered introduces, such as “I am Suzuki.” Or a person (for example, user U) who is different from the person to be registered, such as “This is Mr. Suzuki”. The introductory text that introduces the subject has a specific form that is characteristic of the introductory text, such as the person name “Suzuki” placed after the first or third person pronouns (I, I, him, here, etc.) Yes. The format of the introduction sentence including the person name of the person to be registered is not limited to this. For example, Mr. Suzuki, who is the subject of registration, omits the first-person pronouns when introducing himself to User U and Mr. Sato. The text data generated from the speech such as “has a predetermined form including the person name of the person to be registered, and may be extracted as an introduction sentence. The introductory sentence extracting unit 13 extracts text data having a sentence pattern of a predetermined format including the person name of the person to be registered.

  In the text data that has been confirmed to be an introductory sentence by the introductory sentence extracting unit 13, the person name extracting unit 14 identifies the noun that the morpheme analyzing unit 12 has identified as “noun, proper noun, person name, surname”. Extracted as text data of person names. The extracted text data of the person name is output to the voice instruction generation unit 15 and the registration data management unit 18.

  The voice instruction generation unit 15 acquires the text of the person name (for example, “Suzuki”) extracted by the person name extraction unit 14 and places the person name at a predetermined position of the instruction template stored in the instruction template database 23. Is inserted to generate a voice instruction including the person name. Note that a specific example of processing in which the voice instruction generation unit 15 generates a voice instruction including the person name of the person to be registered introduced by the user U will be described later.

  The imaging device control unit 16 controls the imaging device 33 to take an image when a registration target person who has heard the voice instruction output from the voice output unit 32 performs a predetermined operation instructed by the voice instruction. Note that when the text data of the person name extracted by the person name extraction unit 14 is output from the person name extraction unit 14 to the voice instruction generation unit 15, the imaging device control unit 16 starts imaging by the imaging device 33. You may instruct. Alternatively, when the voice instruction generation unit 15 outputs the generated voice instruction to the voice output unit 32, the imaging device control unit 16 may be instructed to start imaging by the imaging device 33.

  In addition, the imaging device control unit 16 determines whether or not the captured image R captured by the imaging device 33 satisfies a condition that must be satisfied in order to extract feature data, and if this condition is not satisfied, The voice instruction generation unit 15 may be instructed to output the same voice instruction or a voice instruction (related voice instruction) that instructs a related operation. The conditions to be satisfied in order to extract the feature data include, for example, that the area of the face image F in the captured image R is a certain size or more, and each position of the eyes, nose, and mouth in the captured face image F ( For example, the position coordinates of the points P1 to P6 in FIG. 3C can be determined.

  The feature data extraction unit 17 includes the positions of the points P1 and P2 corresponding to the eyes of the face image F, the position of the point P3 corresponding to the nose, the point P4 (the center of the mouth), and the point P5 (the mouth of the mouth). (Right end), the position coordinates of each position of the point P6 (left end of the mouth), the distance between the points, and the like are extracted as feature data.

  The registration data management unit 18 generates registration data by associating the feature data extracted by the feature data extraction unit 17 with the person name, and stores the registration data in the registration database 24.

  As described above, when the information processing apparatus 1 receives the input of the voice of the user U who introduces the registration target person to be registered, the information processing apparatus 1 includes the person name of the registration target person so that the registration target person performs a predetermined operation. Give voice instructions. Accordingly, since the face of the registration target person can be imaged without being mistaken for another person, registration data relating to the registration target person can be managed accurately.

  In addition, the audio | voice which becomes the object which extracts the person name of a registration object person is the audio | voice which the user U introduces a registration object person to the third party or the information processing apparatus 1, or the registration object person introduces himself / herself to another person. It is not limited to the voice to be used, and may be a voice when the user U talks to or asks a registration target person. For example, in the case shown in FIG. 3, the user U asks Mr. Suzuki and Mr. Sato, for example, a voice for asking “Mr. Suzuki, how are you?” There may be. In such a case, the introductory sentence extracting unit 13 (target sentence extracting unit), based on the result of the morphological analysis, generates a predetermined format issued to a person other than itself from text data generated by speech recognition. The speech text data (target sentence) having the following sentence pattern is extracted. Next, the person name extraction unit 14 has the morpheme analysis unit 12 of “noun, proper noun, person name, surname” in the text data confirmed by the introduction sentence extraction unit 13 to have a sentence pattern of a predetermined format. Can be extracted as text data of a person name.

(Extraction of person name from text data)
Next, a process in which the person name extraction unit 14 extracts a person name included in the text data based on the morphological analysis of the text data by the morpheme analysis unit 12 will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of processing for extracting the text of the person name from the text data. (A) in FIG. 4 explains the morphological analysis of text data “This is Mr. Suzuki” and the extraction of person names, and (b) is the text “This is Mr. Suzuki and Mr. Sato.” This explains data morphological analysis and person name extraction.

  As shown in FIG. 4A, the text data “This is Mr. Suzuki” is decomposed into morphemes “This”, “Ha”, “Suzuki”, “Mr.”, and “Is”. . "Here" is attributed as "noun, pronoun, general (noun)", "ha" is attributed as "particle, co-particle", and "Suzuki" is "noun, proper noun, person" “First name, surname” is attributed, “san” is attributed as “noun, suffix, person name”, and “is” is attributed as “auxiliary verb”. The person name extraction unit 14 extracts text data “Suzuki” to which the morpheme analysis unit 12 belongs as “noun, proper noun, person name, surname” as a person name.

  As shown in FIG. 4B, the text data “This is Mr. Suzuki and Mr. Sato” are “here”, “ha”, “Suzuki”, “san”, “to”, “Sato”. , “San”, and “is” morphemes. “Suzuki” and “Sato” are attributed as “nouns, proper nouns, person names, surnames”. The person name extraction unit 14 extracts text data “Suzuki” to which the morpheme analysis unit 12 belongs as “noun, proper noun, person name, surname” as a person name.

  As described above, the person name extraction unit 14 may extract text data of one or more person names from each text data. Thereby, even when the voice which introduces a plurality of persons is inputted from user U, person name extraction part 14 can extract all the person names of the registration subject introduced by the voice.

(Generation of output audio)
Next, an example of a voice instruction that instructs the registration target person so that the registration target person performs a predetermined operation will be described with reference to FIG. FIG. 5 is a diagram illustrating an example of an audio template output by the information processing apparatus 1. The voice instruction generation unit 15 reads the instruction template from the instruction template database 23, inserts the person name acquired from the person name extraction unit 14 into each instruction template, and generates a voice instruction.

  The voice instruction “Mr. Suzuki, please bring your face closer” output from the information processing apparatus 1 shown in (a) of FIG. 3 is a voice instruction A1 instruction template “(person name). It can be generated by inserting “Suzuki”, which is the person name acquired from the person name extraction unit 14, in the place of “(person name)” of “Please move closer”.

  Note that the imaging device control unit 16 determines whether or not the captured image R captured by the imaging device 33 satisfies a condition that should be satisfied in order to extract feature data, and if this condition is not satisfied, The voice instruction generation unit 15 may be instructed to output the same voice instruction or a voice instruction (related voice instruction) for instructing a related operation, and the face image may be captured again.

  For example, when the imaging device control unit 16 determines that the condition for extracting the feature data is not satisfied because the area of the face image F in the captured image R is not a certain size or larger, the voice instruction A2 By inserting the person name of the person to be registered obtained from the person name extraction unit 14 into the “(person name)” portion of the instruction template “(person name), please bring your face closer”. You may generate | occur | produce the audio | voice instruction | indication which makes a registration subject further approach a face. Similarly, the person of the registration target acquired from the person name extraction unit 14 at the position of “(person name)” in the instruction template “(person name), please face your face here” of the voice instruction A3. By inserting a name, a voice instruction that makes the person to be registered closer to the face may be generated.

  Before generating the voice instruction, an auxiliary phrase voice as shown in FIG. 5B may be generated and output. For the auxiliary phrase sound, for example, the person name of the person to be registered acquired from the person name extraction unit 14 is inserted into the location of “(person name)” of the auxiliary phrase X1 template “(person name), nice to meet you”. Is generated by By outputting such a voice, it is possible to prompt the registration subject to prepare to listen to the voice instruction, and to increase interest in the voice instruction to be output later.

  Furthermore, when the face is captured successfully, an auxiliary phrase sound as shown in FIG. 5B may be generated and output. Auxiliary phrase audio is, for example, a person in the place of “(person name)” in the auxiliary phrase X2 template “(person name), thank you very much” and auxiliary phrase X3 template “(person name) thank you.” It is generated by inserting the person name of the person to be registered acquired from the name extraction unit 14. By outputting such sound, the user U who introduced the registration target person that the imaging of the face of the registration target person has been completed, that is, the process has proceeded to the process of extracting feature data and generating registration data. And can notify the registered person.

(Processing flow in which the information processing apparatus 1 registers the person name of the person to be registered and the feature data in association with each other)
Here, the flow of processing in which the information processing apparatus 1 registers the person name of the person to be registered and the feature data in association with each other will be described with reference to FIG. FIG. 6 is a flowchart for explaining an example of a flow of processing in which the information processing apparatus 1 registers the person name of the person to be registered and the feature data in association with each other.

  First, the information processing apparatus 1 starts receiving voice input from the voice input unit 31 and receives voice input from the user U that introduces the person to be registered (voice input step). The text unit 11 calculates the acoustic feature amount of the voice data of the input voice (S1). Next, the text converting unit 11 converts the voice data of the input voice into text data based on the correspondence relationship between the acoustic feature quantity and the text defined in the recognition dictionary 21 (S2). Subsequently, the morpheme analysis unit 12 decomposes the text data into grammatical components and refers to the morpheme analysis dictionary 22 to identify the grammatical relationship between the components (S3). When it is confirmed from the result of the morphological analysis of the text data that the introduction sentence extraction unit 13 introduces the person to be registered (S4), the person name extraction unit 14 is confirmed to be the introduction sentence. In the text data, the morphological analysis unit 12 extracts a word (noun) belonging as, for example, “noun, proper noun, person name, surname” from the text data as a person name (S5: identification information extraction step). The person name extraction unit 14 sends the extracted person name to the voice instruction generation unit 15 and the registration data management unit 18.

  The voice instruction generation unit 15 that has acquired the text of the person name reads out the instruction template from the instruction template database 23, inserts the person name acquired from the person name extraction unit 14 into each instruction template, and the person to be registered becomes a predetermined person. A voice instruction for instructing the operation is generated (S6: instruction generation step). Here, the voice instruction generation unit 15 sends an instruction to the imaging device control unit 16 to start imaging with the imaging device 33 before generating the voice instruction or immediately after generating the voice instruction. Imaging with the device 33 starts (S7). Thereafter, a voice instruction is output from the voice output unit 32 (S8: instruction presentation step). In addition, the order of the processing of S6 to S8 is an example, and is not limited to this. For example, imaging with the imaging device 33 may be started immediately after outputting a voice instruction from the voice output unit 32.

  Since the voice instruction output from the information processing apparatus 1 includes the person name of the person to be registered, only the person to be registered is called and instructed so that the person to be registered performs a predetermined operation. For example, as shown in FIG. 3A, Suzuki who is a registration target who has heard the voice instruction “Mr. Suzuki, please bring your face closer” brings his face closer to the information processing apparatus 1, but the user Since U and Mr. Sato have not received instructions, their faces are not brought close to the information processing apparatus 1. The information processing apparatus 1 acquires a captured image R obtained by capturing a close face as a face image F of Mr. Suzuki who is a registration target person.

  The imaging device control unit 16 detects the face image F from the captured image R (S9), and determines whether or not a condition to be satisfied in order to extract feature data is satisfied (S10). FIG. 6 illustrates an example in which the condition to be satisfied for extracting the feature data is that the area of the face image F in the captured image R is a size equal to or larger than the threshold value. If this condition is not satisfied (NO in S10), the process returns to S8 and instructs the voice instruction generation unit 15 to output the same voice instruction or a voice instruction (related voice instruction) instructing a related action. To do. On the other hand, when the feature data can be extracted (YES in S10), the captured image R is sent from the imaging device control unit 16 to the feature data extraction unit 17, and the feature data extraction unit 17 extracts the feature data of the face image F. (S11).

  Finally, the registration data management unit 18 stores in the registration database 24 the registration data of the person to be registered in which the feature data acquired from the feature data extraction unit 17 is associated with the person name acquired from the person name extraction unit 14. (S12: Registration data management step).

  As described above, when the information processing apparatus 1 receives an input of a voice introducing a registration target person to be registered, the information processing apparatus 1 gives a voice instruction including the person name of the registration target person so that the registration target person performs a predetermined operation. To emit. Accordingly, since the face of the registration target person can be imaged without being mistaken for another person, registration data relating to the registration target person can be managed accurately.

[Embodiment 2]
In the above-described example, the information processing apparatus 1 includes the voice input unit 31, the voice output unit 32, and the imaging device 33, and the example in which the registration data regarding the registration target person introduced by the user U is generated and managed has been described. However, the present invention is not limited to this. For example, if data transmission / reception between the information processing apparatus 1 and the audio input unit 31, the audio output unit 32, and the imaging device 33 is possible, the information processing apparatus 1, the audio input unit 31, the audio output unit 32, The imaging device 33 may be configured as a separate body.

  In this case, the audio data of the audio input to the audio input unit 31 is transmitted to the information processing apparatus 1. The information processing apparatus 1 converts the received voice data into text data, performs morphological analysis of the text data, and extracts a person name of a registration target person included in the text data. The information processing apparatus 1 transmits the voice data of the voice instruction generated using the person name to the voice output unit 32 and transmits an imaging start instruction to the imaging apparatus 33.

  The captured image R captured by the imaging device 33 is transmitted to the information processing device 1, and the information processing device 1 extracts the feature data of the registration target person from the face image F of the captured image R, and the person of the registration target person Registration data is generated in association with the name and stored in the storage unit 20.

  As described above, the voice input unit 31, the voice output unit 32, and the imaging device 33 can be installed at positions away from the position where the control unit 10 of the information processing apparatus 1 is installed.

[Embodiment 3]
Control blocks of the information processing device 1 (particularly, the text conversion unit 11, the morpheme analysis unit 12, the introduction sentence extraction unit 13, the person name extraction unit 14, the voice instruction generation unit 15, the imaging device control unit 16, the feature data extraction unit 17, The registered data management unit 18) may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be realized by software using a CPU (Central Processing Unit). .

  In the latter case, the information processing apparatus 1 includes a CPU that executes instructions of a program that is software that implements each function, and a ROM (Read Only Memory) in which the program and various data are recorded so as to be readable by a computer (or CPU). Alternatively, a storage device (these are referred to as “recording media”), a RAM (Random Access Memory) that expands the program, and the like are provided. And the objective of this invention is achieved when a computer (or CPU) reads the said program from the said recording medium and runs it. As the recording medium, a “non-temporary tangible medium” such as a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. The program may be supplied to the computer via an arbitrary transmission medium (such as a communication network or a broadcast wave) that can transmit the program. The present invention can also be realized in the form of a data signal embedded in a carrier wave in which the program is embodied by electronic transmission.

[Summary]
An information processing apparatus 1 according to an aspect 1 of the present invention is an information processing apparatus including a voice input unit 31 that accepts voice input, and includes voice information including identification information of a target person input from the voice input unit. The identification information extracting unit extracts the identification information extracting unit (person name extracting unit 14) that extracts the identification information of the subject from the data, and the operation instruction that instructs the subject to perform a predetermined operation. An instruction generation unit (speech instruction generation unit 15) that generates including the identification information, and an instruction presentation unit (speech output unit 32) that presents the operation instruction to the target person.

  According to said structure, the operation instruction containing the said subject's identification information is extracted so that the said subject's identification information is extracted from the audio | voice containing the subject's identification information, and the said subject performs predetermined | prescribed operation | movement. Present to the above target person. Thereby, it is possible to cause a correct target person to perform a predetermined operation without being mistaken for another person.

  In the information processing apparatus according to aspect 2 of the present invention, in the aspect 1, the sound including the identification information of the target person may be a sound uttered by a person different from the target person.

  Thereby, the identification information of the target person can be extracted from the voice uttered by the person different from the target person including the identification information of the target person. Therefore, the identification information of the target person can be extracted from the voice that the person different from the target person talks to or asks the target person, the voice that introduces the target person, and the like.

  The information processing apparatus according to aspect 3 of the present invention is the information processing apparatus according to aspect 2, wherein a person different from the target person introduces the target person from the text generated by voice recognition of the voice data input from the voice input unit. An introduction sentence extraction unit 13 that extracts an introduction sentence to be extracted and outputs the extracted introduction sentence to the identification information extraction unit may be further provided.

  According to said structure, the person different from the said target person extracts the said person's identification information from the introduction sentence which introduces the said target person. Thereby, for example, an introduction sentence can be extracted from a voice when a person different from the target person introduces the target person to a third party or an information processing apparatus. In addition, since the introduction sentence in which the person different from the target person introduces the target person is a sentence having a predetermined form of sentence including the identification information of the target person, by selectively extracting the introduction sentence from the voice, The identification information of the target person can be extracted efficiently.

  The information processing apparatus according to aspect 4 of the present invention is the information processing apparatus according to any one of the aspects 1 to 3, wherein the identification information is a person name indicating the target person, and the instruction generation unit includes the identification information extraction unit described above. The operation instruction including the person name extracted as identification information may be generated.

  According to said structure, the instruction | indication including the subject person's person name is produced | generated. Thereby, it is possible to clarify and output to whom the operation instruction is directed.

  An information processing apparatus according to aspect 5 of the present invention is the information processing apparatus according to any one of aspects 1 to 4, wherein a unique information extraction unit that extracts unique information specific to the subject from a face image obtained by imaging the face of the subject. The target person further comprising a feature data extraction unit 17), which associates the identification information of the target person who has performed the predetermined operation with the specific information of the target person extracted by the specific information extraction part The registration data regarding may be stored in a storage unit (storage unit 20, registration database 24).

  According to said structure, the specific information specific to a subject is extracted from the face image which imaged the said subject's face, and identification information and specific information of a subject are matched and memorize | stored. In general, since a face differs for each target person, unique information unique to each target person can be extracted from the captured face image. Thereby, since the face of the subject can be imaged without being mistaken for another person, the registration data regarding the subject can be managed accurately.

  The control method of the information processing device 1 according to the aspect 6 of the present invention is a control method of the information processing device including the voice input unit 31 that receives voice input, and includes identification information of the subject from the voice input unit. A voice input step (S1) for receiving voice input; an identification information extraction step (S5) for extracting the target person's identification information from the voice data of the voice received in the voice input step; An instruction generation step (S6) for generating an operation instruction for instructing to perform a predetermined operation including the identification information extracted in the identification information extraction step, and the operation instruction generated in the instruction generation step. An instruction presentation step (S8) to be presented to the subject. According to said structure, there exists an effect similar to the said aspect 1. FIG.

  The information processing apparatus according to each aspect of the present invention may be realized by a computer. In this case, the information processing apparatus is operated on each computer by causing the computer to operate as each unit (software element) included in the information processing apparatus. The control program for the information processing apparatus to be realized in this way and a computer-readable recording medium on which the control program is recorded also fall within the scope of the present invention.

  The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims, and embodiments obtained by appropriately combining technical means disclosed in different embodiments. Is also included in the technical scope of the present invention. Furthermore, a new technical feature can be formed by combining the technical means disclosed in each embodiment.

  The present invention can be used for an electronic device or a robot having a communication function with a human.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 13 Introduction sentence extraction part 14 Person name extraction part (identification information extraction part)
15 Voice instruction generation unit (instruction generation unit)
17 Feature data extraction unit (unique information extraction unit)
18 Registration Data Management Unit 20 Storage Unit 24 Registration Database (Storage Unit)
31 Voice input part 32 Voice output part (instruction presentation part)
33 Imaging device

Claims (8)

An information processing apparatus including a voice input unit that receives voice input,
An identification information extracting unit that extracts the identification information of the subject from voice data including the identification information of the subject input from the voice input unit;
An instruction generating unit that generates an operation instruction for instructing the subject to perform a predetermined operation, including the identification information extracted by the identification information extracting unit;
An information presenting apparatus comprising: an instruction presenting unit that presents the operation instruction to the target person.   The information processing apparatus according to claim 1, wherein the voice including the identification information of the target person is a voice uttered by a person different from the target person.   An introductory sentence that extracts an introductory text that introduces the target person from a person different from the target person from text generated by speech recognition of the speech data input from the speech input section, and outputs the introductory text to the identification information extracting section The information processing apparatus according to claim 2, further comprising an extraction unit. The identification information is a person name indicating the target person,
The information processing apparatus according to any one of claims 1 to 3, wherein the instruction generation unit generates the operation instruction including the person name extracted as the identification information by the identification information extraction unit. . A unique information extraction unit that extracts unique information unique to the subject from a face image obtained by capturing the face of the subject,
Storing registration data relating to the target person in association with the identification information of the target person who has performed the predetermined operation and the specific information of the target person extracted by the specific information extracting unit. The information processing apparatus according to claim 1, wherein: A method for controlling an information processing apparatus including a voice input unit that receives voice input,
A voice input step for receiving voice input including identification information of the subject from the voice input unit;
An identification information extraction step of extracting the identification information of the subject from the voice data of the voice received in the voice input step;
An instruction generation step for generating an operation instruction for instructing the subject to perform a predetermined operation including the identification information extracted in the identification information extraction step;
An instruction presenting step of presenting the operation instruction generated in the instruction generating step to the target person.   A control program for causing a computer to function as the information processing apparatus according to claim 1, wherein the control program causes the computer to function as the identification information extraction unit and the instruction generation unit.   A computer-readable recording medium on which the control program according to claim 7 is recorded.

Images