CN110364164A - Session control, conversational system, dialog control method and storage medium - Google Patents
Session control, conversational system, dialog control method and storage medium Download PDFInfo
- Publication number
- CN110364164A CN110364164A CN201910207297.1A CN201910207297A CN110364164A CN 110364164 A CN110364164 A CN 110364164A CN 201910207297 A CN201910207297 A CN 201910207297A CN 110364164 A CN110364164 A CN 110364164A
- Authority
- CN
- China
- Prior art keywords
- mentioned
- speech
- reaction
- robot
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000006243 chemical reaction Methods 0.000 claims abstract description 160
- 238000012545 processing Methods 0.000 claims description 119
- 230000009471 action Effects 0.000 claims description 69
- 238000004891 communication Methods 0.000 claims description 58
- 210000004209 hair Anatomy 0.000 claims description 15
- 238000006757 chemical reactions by type Methods 0.000 claims description 5
- 230000007935 neutral effect Effects 0.000 claims description 4
- 241001465754 Metazoa Species 0.000 claims description 2
- 235000013305 food Nutrition 0.000 claims description 2
- 230000004044 response Effects 0.000 description 18
- 230000006870 function Effects 0.000 description 16
- 238000012360 testing method Methods 0.000 description 14
- 230000001815 facial effect Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 239000000203 mixture Substances 0.000 description 6
- 210000003128 head Anatomy 0.000 description 5
- 238000009877 rendering Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 230000005428 wave function Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 229910044991 metal oxide Inorganic materials 0.000 description 2
- 150000004706 metal oxides Chemical class 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 229920003002 synthetic resin Polymers 0.000 description 1
- 239000000057 synthetic resin Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Manipulator (AREA)
- User Interface Of Digital Computer (AREA)
- Toys (AREA)
Abstract
The present invention relates to session control, conversational system, dialog control method and storage mediums.The present invention accurately grasps the hobby of user, and carries out the dialogue being consistent with the hobby of user.Robot (100A) includes: reaction acquisition unit (110A), multiple reactions are obtained to determine as a result, multiple reaction determines to react the result determined comprising the speech to regulation object for the result that is determined of reaction of the speech of robot (100A) and to regulation object for the robot (100B) being mutually provided independently from robot (100A) in result；And speech control unit (115A), determined based on multiple reactions for being obtained by reaction acquisition unit (110A) as a result, controlling comprising at least any one the speech in multiple speech devices including robot (100A) and robot (100B).
Description
The application is with the Japanese patent application 2018-058200 submitted on March 26th, 2018 and on December 28th, 2018
Based on the Japanese patent application 2018-247382 of submission, the priority of these applications is enjoyed, and will be in these basis applications
Hold and all quotes in the application.
Technical field
The present invention relates to session control, conversational system, dialog control method and storage mediums.
Background technique
The exploitation of the equipment such as the robot exchanged with people is developing, general in order to obtain the equipment such as this robot
And getting close to easness is more important aspect.For example, Japanese Unexamined Patent Publication 2006-071936 bulletin discloses following technology: passing through
Dialogue with user learns the hobby of user, and carries out the dialogue being consistent with the hobby of user.
Disclosed in the Japanese Unexamined Patent Publication 2006-071936 bulletin in technology, it is difficult to accurately grasp the hobby of user.
Summary of the invention
The present invention is carried out in view of situation as described above, and its purpose is to provide can accurately grasp use
The hobby of person and session control, conversational system, the dialog control method for carrying out the dialogue being consistent with the hobby of user
And storage medium.
To achieve the goals above, a mode of session control according to the present invention is characterized in that having:
Acquisition unit is reacted, multiple reactions is obtained and determines as a result, multiple reaction determines to include to regulation object in result for the 1st hair
Say the result and be directed to and above-mentioned 1st speech device phase to above-mentioned regulation object that the reaction of the speech of device is determined
The result that the reaction of the speech for the 2nd speech device being provided independently from is determined；And speech control unit, based on by upper
State reaction acquisition unit obtain multiple reactions determine as a result, to comprising it is above-mentioned 1st and the 2nd speech device the above-mentioned 1st and
At least any one the above-mentioned speech in multiple speech devices including 2nd speech device is controlled.
In addition, to achieve the goals above, a mode of conversational system according to the present invention is to have and be configured to
The 1st speech device and the 2nd speech device and session control, the conversational system enough made a speech are characterized in that, above-mentioned right
Words control device has: reaction acquisition unit, obtains multiple reactions and determines as a result, multiple reaction determines in result comprising to rule
Determine speech of the object for the 1st speech device the result that is determined of reaction and to above-mentioned regulation object for it is upper
State the result that the reaction of the speech for the above-mentioned 2nd speech device that the 1st speech device is mutually provided independently from is determined；And hair
It says control unit, is determined based on the multiple reactions obtained by above-mentioned reaction acquisition unit as a result, to including the above-mentioned 1st and the 2nd
At least any one the above-mentioned speech in multiple speech devices including speech device is controlled.
In addition, to achieve the goals above, a mode of dialog control method of the present invention is characterized in that, packet
It includes: obtaining the processing that multiple reactions determine result, multiple reaction determines in result comprising filling to regulation object for the 1st speech
The result and above-mentioned regulation object is directed to mutually independent with above-mentioned 1st speech device that the reaction for the speech set is determined
The result that the reaction of the speech of 2nd speech device of ground setting is determined；And based on acquired above-mentioned multiple reactions
Determine as a result, to comprising at least any one the above-mentioned hair in multiple speech devices including above-mentioned 1st and the 2nd speech device
Say the processing controlled.
In addition, to achieve the goals above, a mode of storage medium according to the present invention is characterized in that, storage
The program for functioning computer as such as lower unit: reaction acquisition unit obtains multiple reactions and determines as a result, multiple anti-
Should determine in result comprising to regulation object for the result that is determined of reaction of the speech of the 1st speech device and right
The reacting for speech that above-mentioned regulation object is directed to the 2nd speech device being mutually provided independently from above-mentioned 1st speech device carries out
The result of judgement；And speech control unit, determined based on the multiple reactions obtained by above-mentioned reaction acquisition unit as a result, to packet
It is controlled containing at least any one the above-mentioned speech in multiple speech devices including above-mentioned 1st and the 2nd speech device.
The effect of invention
In accordance with the invention it is possible to provide the hobby that can accurately grasp user and carry out the hobby with user
Session control, conversational system, dialog control method and the storage medium for the dialogue being consistent.
Detailed description of the invention
Fig. 1 is the figure for indicating the composition of conversational system involved in the 1st embodiment of the invention.
Fig. 2 is the main view of robot involved in the 1st embodiment.
Fig. 3 is the block diagram for indicating the composition of robot involved in the 1st embodiment.
Fig. 4 is the figure for indicating an example of audio response polarity judging table involved in the 1st embodiment.
Fig. 5 is the flow chart for indicating the process of dialogue control processing involved in the 1st embodiment.
Fig. 6 is to indicate that user involved in the 1st embodiment determines the flow chart of the process of processing.
Fig. 7 is the flow chart for indicating the process of sound determination processing involved in the 1st embodiment.
Fig. 8 is the flow chart for indicating the process of expression determination processing involved in the 1st embodiment.
Fig. 9 is the flow chart for indicating the process of action determination processing involved in the 1st embodiment.
Figure 10 is the flow chart for indicating the process of hobby determination processing involved in the 1st embodiment.
Figure 11 is the composition block diagram for indicating the conversational system of the 2nd embodiment.
Specific embodiment
Hereinafter, embodiment of the present invention is described in detail referring to attached drawing.
(the 1st embodiment)
Conversational system 1 involved in the 1st embodiment of the invention is configured to comprising multiple robots 100.Multiple machines
People 100 is configured in the living spaces such as the office of regulation object, house, and multiple robots 100 and regulation object carry out pair
Words.In the following description, the example to engage in the dialogue to 2 robots 100 with regulation object is illustrated, but conversational system
1 is also configured to the robot 100 comprising 3 or more.
It is all of conversational system typically herein, it is specified that object refers to the user (user) using conversational system
Person, the kinsfolk of the owner or friend etc..In addition, in addition to human, it is specified that object is also including, for example, as raising pets
Animal, the other robot different from robot 100.
As shown in Figure 1, conversational system 1 has 2 robots 100 that can be in communication with each other, engage in the dialogue with user USR.
Herein, for ease of description, the robot in left side 100 is set as robot 100A towards the paper of Fig. 1, towards the paper of Fig. 1
Face and the robot on right side 100 is set as robot 100B.In addition, being carried out with not distinguishing robot 100A and robot 100B
In the case where explanation, " robot 100 " is recorded as with being referred to as by any one robot or by these robots sometimes.Robot
100A and robot 100B are configured in mutually different place, and are respectively arranged at identical regulation object and can not identify machine
Place as the both sides of the speech of people 100A and robot 100B.For example, robot 100A is configured in regulation object
Office, robot 100B are configured in the house of the regulation object far from the office.Alternatively, robot 100A configuration is being advised
Determine the facility that object is often gone, robot 100B is disposed substantially away from other facilities that the regulation object of the facility is often gone.
As shown in Fig. 2, robot 100 is the robot in appearance with the three-dimensional shape for having imitated people.In addition, machine
The exterior trim of people 100 is formed by the material based on synthetic resin.Robot 100 has body part 101, upper with body part 101
It the head 102 of portion's connection, the hand 103 being separately connected with the left and right of body part 101 and is connect to the lower part from body part 101
Liang Zhi foot 104.In addition, head 102 has pair of right and left eye 105, mouth 106 and pair of right and left ear 107.This
Outside, the upside of Fig. 2, downside, left side, right side are set to upside, downside, right side, the left side of robot 100.
Then, it is illustrated referring to composition of the Fig. 3 to robot 100.Fig. 3 is shown to robot 100A and robot 100B
Respectively constitute the block diagram being indicated, robot 100A is identical as the composition of robot 100B.Firstly, by taking robot 100A as an example
It is constituted and is illustrated.
As shown in figure 3, robot 100A has control unit 110A, storage unit 120A, image pickup part 130A, voice input portion
140A, audio output unit 150A, moving portion 160A and communication unit 170A.These each portions are electrically connected to each other via bus B L.
Control unit 110A is by with CPU (Central Processing Unit: central processing unit), ROM (Read
Only Memory: read-only memory), the computer of RAM (Random Access Memory: random access memory) constitute,
The movement of robot 100A entirety is controlled.Control unit 110A by by CPU read the control program that is stored of ROM and
It executes on RAM, thus the movement in each portion of robot 100A is controlled.
Thus control unit 110A is used as user's test section 111A, user's determining section 112A, user by executing control program
Information acquiring section 113A, voice recognition portion 114A, speech control unit 115A, speech synthesiser 116A, reaction determination unit 117A with
And hobby determination unit 118A is functioned.
User's test section 111A detects around robot 100A (for example, in the range of being radius 2m from robot 100A)
Existing user USR.User's test section 111A for example aftermentioned image pickup part 130A is controlled and to robot 100A around
It is imaged, is detected by activity, head, the face etc. to object, thus to user existing around robot 100A
USR is detected.
User's determining section 112A determines the user USR that user's test section 111A is detected.User's determining section 112A for example from
The comparable face-image of facial parts with user USR is extracted in the photographed images of image pickup part 130A.Then, user's determining section
112A detects characteristic quantity from the face-image, with it is being registered in the User Information Database of aftermentioned storage unit 120A,
It indicates that the facial information of the characteristic quantity of face is compareed, similarity is calculated based on the result of control, and according to calculated
Whether similarity meets defined benchmark to determine user USR.Rule are stored in the User Information Database of storage unit 120A
The facial information of the characteristic quantity of the respective face of expression of fixed multiple user USR.Use is determined by user's determining section 112A
The user USR that family test section 111A is detected is which user USR in these user USR.Characteristic quantity is can to identify user
The information of USR, the external appearance characteristics such as shape, size, configuration of each section for e.g. being included by the face such as eye, nose, mouth
The information indicated with numerical value.In the following description, it will be detected by user's test section 111A and by user's determining section
The user USR that 112A is determined is known as object user.In this way, user's determining section 112A is sent out as object determination unit of the invention
Wave function.
User information acquisition unit 113A obtains the user information of speech, appearance, action for indicating object user etc..In this reality
It applies in mode, user information acquisition unit 113A for example controls image pickup part 130A, voice input portion 140A, and obtains and include
Take the image information of the image data of the photographed images of object user and the sound of the sound issued comprising object user
In the acoustic information of data at least any one, as user information.In this way, user information acquisition unit 113A and image pickup part
130A, voice input portion 140A cooperate as acquisition unit of the invention and function.
Voice data included in the acoustic information that voice recognition portion 114A obtains user information acquisition unit 113A is real
Voice recognition processing is applied, and is converted to the text data for indicating the speech content of object user.Voice recognition processing for example using
Sound equipment model, language model, the word word that acoustic information DB (Data Base: database) 122A of storage unit 120A is stored
Allusion quotation.Voice recognition portion 114A for example eliminates ambient noise from acquired voice data, to being eliminated after ambient noise
Voice data included in phoneme identified, referring to word lexicon generate will identify that phoneme column is converted to word
Multiple conversion candidates.Then, voice recognition portion 114A is selected from multiple conversion candidates generated appropriate referring to language model
The highest candidate of property, is exported as text data corresponding with voice data.
Speech control unit 115A controls the speech of robot 100A.Control unit 115A make a speech referring for example to storage unit
The speech information that the speech information DB123A of 120A is stored, extracted from the speech information that is stored of speech information DB123A with
The corresponding multiple speeches of situation are candidate.Then, speech control unit 115A is referring to user information DB121A the stored user information
Included in taste information, the speech time that selection is matched with the hobby of object user from extracted multiple speech candidates
Choosing, and it is determined as the speech content of robot 100A.In this way, speech control unit 115A is sent out as speech control unit of the invention
Wave function.
In addition, speech control unit 115A communicated via communication unit 170A with robot 100B, and with robot 100B
Speech control unit 115B cooperation and adjust and determine the speech content of robot 100A as described below.
That is, speech control unit 115A cooperates with the speech control unit 115B of robot 100B, such as obtain robot 100B
Pass through the time after speech, when in acquired robot when passing through within time (such as 72 hours) by the time for regulation
100A make a speech in the case where, adjust and determine the topic of the speech of robot 100A so that robot 100A speech topic at
If the topic made a speech for the regulation before starting from the speech in robot 100A by robot 100B within the time is different
Topic.The decision of such topic similarly carries out in the speech control unit 115B of robot 100B.By the above, machine
The topic of people 100A and robot 100B speech is decided to be mutually different topic, and controls according to the topic determined
The speech of Liang Ge robot 100A, 100B.
As described later, robot 100A and robot 100B difference determine object user is directed to the anti-of the speech of itself
It answers, and result is determined to collect the taste information of (storage) object user based on it, but in this case, as robot 100A
It is repeated with the topic of robot 100B speech or when being always associated with, the new taste information, wider of object user can not be collected
The taste information in field.In addition, object user is also due to hearing the speech of duplicate topic and being fed up with.By by machine
The topic of the speech of people 100A and robot 100B is determined as mutually different topic, more various thus, it is possible to collect
Taste information.
In contrast, in the case where have passed through regulation by more than the time after robot 100B speech, speech control
Portion 115A determines speech content by oneself, without by the speech content limitation of robot 100B.That is, robot 100A and 100B
The topic (speech content) of speech is mutually not coordinated with and determines with being independent of each other (mutually indepedent).
Speech control unit 115A generates and export expression cooperate with robot 100B decision the speech content of itself text
Notebook data.
Speech synthesiser 116A is generated and the speech content of the expression robot 100A inputted from speech control unit 115A
The corresponding voice data of text data.Speech synthesiser 116A in the acoustic information DB122A of storage unit 120A for example using saving
Sound equipment model etc., generate the voice data for reading text strings shown in text data.In addition, speech synthesiser 116A is controlled
Audio output unit 150A, so that voice data generated is carried out sound output.
React the reaction of speech of the determination unit 117A determine object user for robot 100A.Accordingly, for above-mentioned rule
The each object user determined by user's determining section 112A in fixed multiple user USR determines for robot 100A's
The reaction of speech.Reacting determination unit 117A has sound determination unit 117AA, expression determination unit 117BA and action determination unit
117CA.Sound determination unit 117AA, expression determination unit 117BA and action determination unit 117CA are based respectively on the sound of object user
Sound, expression and action will be three polarity for the reaction classification of the speech of subject machine people 100A, thus determined.
Three polarity are that the reaction of affirmative is " actively (Positive) ", the reaction of negative is " passive (Negative) " and both be unwilling to
The fixed neutral reaction for also not negating i.e. " neutral (Neutral) ".
Sound determination unit 117AA is used based on the sound that object user is issued after robot 100A speech, determine object
Reaction of the family for the speech of robot 100A.Sound determination unit 117AA is based on text data by the speech content of object user
Audio response polar " positive ", " passiveness " and " neutrality " these three polarity are classified as, thus determine object user is directed to machine
The reaction of the speech of device people 100A, above-mentioned text data are voice recognition portion 114A for the user after the speech of robot 100A
Information acquiring section 113A obtain sound implement voice recognition processing and generate.In this way, sound determination unit 117AA is as this hair
Bright sound judging unit functions.
Expression of the expression determination unit 117BA based on the object user after robot 100A speech, determine object user are directed to
The reaction of the speech of robot 100A.Expression determination unit 117BA calculates the smiling face's degree for indicating the degree of smiling face, as evaluating
The index of the expression of object user.Expression determination unit 117BA is from user information acquisition unit 113A after the speech in robot 100A
The face-image of object user, and the characteristic quantity of the face of test object user are extracted in the photographed images of acquirement.Expression determines
Portion 117BA determines the smiling face's degree information stored in information DB124A referring to the reaction of storage unit 120A, and based on detected
Characteristic quantity carrys out smiling face's degree of computing object user.Expression determination unit 117BA is according to calculated smiling face's degree, by the table of object user
Feelings are classified as " positive ", " passiveness " and " neutrality " of expression antipolarity these three polarity, and thus determine object user is directed to
The reaction of the speech of robot 100A.In this way, expression determination unit 117BA is functioned as expression judging unit of the invention.
Action of the action determination unit 117CA based on the object user after robot 100A speech, determine object user are directed to
The reaction of the speech of robot 100A.Determination unit 117CA take action from user information acquisition unit after the speech in robot 100A
The action of test object user in the photographed images that 113A is obtained, and the action of object user is classified as action antipolarity
" positive ", " passiveness " and " neutrality " these three polarity, thus reaction of the determine object user for the speech of robot 100A.
In this way, action determination unit 117CA is functioned as action judging unit of the invention.
Hobby determination unit 118A determines the topic of the dialogue between object user and robot 100A, and is determined based on reaction
Each judgement result of portion 117A determines hobby degree, which indicates the height of hobby of the object user for identified topic
Degree.Accordingly, for each object user determined by user's determining section 112A in above-mentioned defined multiple user USR, sentence
Its fixed hobby degree.Herein, so-called hobby refer to no matter tangible or interest invisible and related with various things, hobby, such as
Other than comprising interest related with food, sport, weather etc., hobby, also comprising the correspondence (speech for robot 100
Content) hobby.Have a liking for the sequence had a liking for from high to low of the determination unit 118A according to object user for topic, by hobby degree point
Class is " hobby degree A ", " hobby degree B ", " hobby degree C " and " hobby degree D " this four grades.In this way, hobby determination unit 118A
It is functioned as determination unit of the invention and hobby judging unit.
In addition, user's test section 111A, user's determining section 112A, user information acquisition unit 113A, voice recognition portion 114A,
Make a speech control unit 115A, speech synthesiser 116A, reaction determination unit 117A and hobby determination unit 118A, can be by individually counting
Calculation machine realizes each function, can also realize each function by independent computer respectively.
Storage unit 120A has the non-volatile semiconductor memory that can rewrite storage content, hard disk drive etc.,
And memory control unit 110A each portion of robot 100A is controlled required for various data.
Storage unit 120A has the multiple databases for saving various data respectively.Storage unit 120A is for example with user information
DB121A, acoustic information DB122A, speech information DB123A and reaction determine information DB124A.In addition, in storage unit 120A
In, the speech of topic of speech date-time and speech according to each user USR storage comprising robot 100A speech etc.
Resume information.
User information DB121A using with each related various information of the multiple user USR registered as user information
It is accumulated and is stored.User information is for example comprising each and pre-assigned user identification in order to identify multiple user USR
Information (for example, ID of user USR), indicate user USR face characteristic quantity facial information and indicate USR pairs of user
In the taste information of the hobby degree of each topic.In this way, multiple respective taste informations of user USR are stored as, known using user
Other information can recognize that be which user USR taste information.
Acoustic information DB122A is as the data for voice recognition processing or sound rendering processing, such as to save
There are sound equipment model, word lexicon and language model, above-mentioned sound equipment model indicates the sound for distinguishing meaning and other words
The respective feature of minimum unit, that is, phoneme (frequency characteristic) of sound, above-mentioned word lexicon establish the feature of phoneme and word pair
It answers, above-mentioned language model indicates arrangement and its connection probability of word.
Information DB123A storage of making a speech indicates the candidate speech information of the speech of robot 100A.Make a speech information for example comprising
Speech in the case where starting with object user's talk is candidate, for the speech of object user response in the case where speech wait
Choosing and with robot 100B session in the case where speech candidate etc., corresponding to the various of the dialogue situation with object user
Speech is candidate.
Reaction determines that information DB124A storage reaction determines information, is directed to machine in reaction determination unit 117A determine object user
Information is determined using the reaction when reaction of the speech of device people 100A.Reaction determines that information DB124A is, determines letter as reaction
Breath, such as it is stored in speech of the sound determination unit 117AA determine object user for robot 100A of reaction determination unit 117A
Reaction when the sound that uses determine information.Sound determines information for example with the shape of audio response polarity judging table shown in Fig. 4
Formula storage.In audio response polarity judging table, aftermentioned audio response polarity is corresponding with the foundation of feature critical word.In addition, anti-
It should determine that information DB124A is, determine information as reaction, such as be stored in the expression determination unit 117BA of reaction determination unit 117A
Smiling face's degree information that the smiling face of computing object user uses when spending.Smiling face's degree information be, for example, according to canthus, the corners of the mouth position,
The variation degree of the size of eye, mouth etc., information obtained from smiling face's degree is quantized in the range of 0~100%.
Image pickup part 130A is made of video camera, which has camera lens and CCD (Charge Coupled
Device: Image coupler part) imaging sensor, CMOS (Complementary Metal Oxide Semiconductor:
Complementary metal oxide semiconductor) photographing elements such as imaging sensor, image pickup part 130A around robot 100A to taking the photograph
Picture.Image pickup part 130A is for example set to the front upper on head 102, images to the front on head 102, generates and exports number
Word image data.Video camera is installed on the pallet of the motor driving acted in a manner of the direction that can change camera lens institute direction
(gimbal etc.), and be configured to be tracked the face etc. of user USR.
Voice input portion 140A is made of microphone, A/D (Analog to Digital: simulation numeral) converter etc., example
Such as by by microphone pickup that ear 107 is set to sound amplify, and the signals such as A/D conversion, coding will be implemented
The digital audio data (acoustic information) of processing is output to control unit 110A.
Audio output unit 150A is made of loudspeaker, D/A (Digital to Analog: digital simulation) converter etc., right
The voice data supplied from the speech synthesiser 116A of control unit 110A implements the signal processings such as decoding, D/A conversion, amplification, and
Analoging sound signal is exported from the loudspeaker that mouth 106 is for example arranged in.
Robot 100A carries out pickup to the sound of object user by the microphone of voice input portion 140A, and is controlling
Under the control of portion 110A, the corresponding sound of speech content with object user is exported from the loudspeaker of audio output unit 150A,
It generates and exchanges thus, it is possible to engage in the dialogue with object user.In this way, robot 100A is as the 1st speech device hair of the invention
Wave function.
Moving portion 160A is the position for keeping robot 100A mobile.Moving portion 160A, which has, is respectively arranged at robot
The wheel of the bottom of the foot 104 of the left and right of 100A, rotation drive the motor of the wheel of left and right and carry out driving control to motor
The driving circuit of system.According to the control signal received from control unit 110A, pulse of the driving circuit to motor supply driving
Signal.Motor makes the wheel rotation driving of left and right according to the pulse signal of driving, and keeps robot 100A mobile.In this way, moving
Dynamic portion 160A is functioned as mobile unit of the invention.In addition, the wheel for being configured to left and right separately rotates driving,
But as long as robot 100A is able to carry out the traveling such as advance, retrogressing, turning, acceleration and deceleration, and the quantity of motor is arbitrary.Example
Such as, link mechanism, steering mechanism etc. can be set and drive the wheel controlled by a motor.In addition, also can be with horse
The quantity reached matchingly suitably changes the quantity of driving circuit.
Communication unit 170A is made of the wireless communication module and antenna communicated for using communication,
Wireless data communication is carried out with robot 100B.As communication, such as it can suitably use Bluetooth (note
Volume trade mark), BLE (Bluetooth Low Energy: low-power consumption bluetooth), ZigBee (registered trademark), infrared communication etc. it is close
The wireless LAN traffics modes such as distance wireless communication mode, WiFi (Wireless Fidelity).In the present embodiment, machine
People 100A carries out wireless data communication via communication unit 170A and robot 100B, thus robot 100A and robot 100B
It engages in the dialogue with object user.
Robot 100B is identical as robot 100A, therefore constitutes and be briefly described to it.It is same as robot 100A,
Robot 100B have control unit 110B, storage unit 120B, image pickup part 130B, voice input portion 140B, audio output unit 150B,
Moving portion 160B and communication unit 170B.Control unit 110B controls the movement of robot 100B entirety, by executing control
Processing procedure sequence and as user's test section 111B, user's determining section 112B, user information acquisition unit 113B, voice recognition portion 114B,
Speech control unit 115B, speech synthesiser 116B, reaction determination unit 117B and hobby determination unit 118B are functioned.Speech control
Portion 115B processed is referring to the taste information for including in user information DB121B the stored user information, from extracted multiple speeches
The speech for selecting the hobby with object user to match in candidate is candidate, and is determined as the speech content of robot 100B.Via
Communication unit 170B is communicated with robot 100A, and is cooperated with the speech control unit 115A of robot 100A, such as obtains machine
Pass through the time after device people 100A speech.Acquired when passing through within the time by the time for above-mentioned regulation, speech control
Portion 115B adjusts and determines the speech content of robot 100B so that robot 100B speech topic in robot 100B
Speech start before the topic made a speech by robot 100A within the time of regulation it is different.React determination unit 117B judgement pair
As user is for the reaction of the speech of robot 100B.Reacting determination unit 117B has sound determination unit 117AB, expression determination unit
117BB and action determination unit 117CB.Sound determination unit 117AB will be directed to subject machine by the sound based on object user
The reaction classification of the speech of people 100B is " positive ", " passiveness ", " neutrality " these three polarity determine.Expression determination unit
117BB will be " positive ", " disappeared by the expression based on object user for the reaction classification of the speech of subject machine people 100B
Pole ", " neutrality " these three polarity are determined.Take action determination unit 117CB by the action based on object user will for pair
As the reaction classification of the speech of robot 100B is " positive ", " passiveness ", " neutrality " these three polarity are determined.Storage unit
120B has the multiple databases for saving various data respectively.Storage unit 120B for example believes with user information DB121B, sound
It ceases DB122B, speech information DB123B and reaction and determines information DB124B.In addition, in storage unit 120B, according to each use
Family USR stores the speech resume information of topic etc. of the speech date-time comprising robot 100B speech and speech.Machine
Device people 100B carries out pickup to the sound of object user by the microphone of voice input portion 140B, and in the control of control unit 110B
Under system, export corresponding with the speech content of object user sound from the loudspeaker of audio output unit 150B, thus, it is possible to it is right
Exchange is generated as user engages in the dialogue.In this way, robot 100B is functioned as the 2nd speech device of the invention.
Then, flow chart referring to Figure 5 is illustrated the dialogue control processing that robot 100 executes.Dialogue control
System processing is that the processing of dialogue is controlled according to the hobby of object user.Herein, it is executed with the control unit 110A of robot 100A
In case where come illustrate talk with control processing.Control unit 110A is detected around robot 100A with user's test section 111A
It is opportunity to the case where user USR, starts to talk with control processing.
Control unit 110A is, when starting dialogue control processing, user to be first carried out and determines processing (step S101).This
Place determines that processing is illustrated to user referring to flow chart shown in fig. 6.User determines that processing is determining user's test section
What 111A was detected is present in the processing of the user around robot 100A.
Control unit 110A is, when beginning user determines processing, first from the photographed images obtained by image pickup part 130A
Extract the face-image (step S201) of object user.Control unit 110A (user determining section 112A) is for example in photographed images
Area of skin color is detected, and determine in area of skin color with the presence or absence of with the comparable part of facial parts such as eye, nose, mouth, when
When being judged as in the presence of part comparable with facial parts, area of skin color is considered as face-image and is extracted.
Then, 110A couples of control unit registration user corresponding with extracted face-image is retrieved (step S202).
Control unit 110A (user determining section 112A) for example detects characteristic quantity from extracted face-image, and with storage unit 120A's
The facial information stored in user information DB121A is compareed, and is carried out to the registration user that similarity is defined benchmark or more
Retrieval.
Control unit 110A determines the user USR being present in around robot 100 according to the search result in step S202
(step S203).Control unit 110A (user determining section 112A) for example by user USR corresponding with following characteristic quantity, is determined as
The object user being present in around robot 100A, features described above amount are the above-mentioned multiple use stored in user information DB121A
In the characteristic quantity of the respective face of family USR and from the highest feature of similarity between the characteristic quantity detected in face-image
Amount.
Control unit 110A after the processing for performing step S203, terminate user determine processing, make processing returns to pair
Talk about control processing.
Back to Fig. 5, after performing user and determining processing (step S101), control unit 110A is established and robot
Communication connection (step S102) between 100B (other robot).Herein, the foundation of so-called communication connection refers to, specifies communication
Object and carry out defined process and establish mutually to be capable of the state of sending and receiving data.Control unit 110A control communication unit 170A and
The defined process based on communication mode is carried out, the communication connection between robot 100B is thus established.In addition, in robot
In the case that 100A and robot 100B carries out data communication using infrared communication mode, do not need to establish communication link in advance
It connects.
Then, control unit 110A determine than above-mentioned regulation by (for example, within 20 seconds) short stipulated time time,
Whether the object user determined in step s101 makes a speech (step S103).Control unit 110A is for example using being attached to CPU's
RTC (Real Time Clock: real-time clock) measurement current time information come measure since present treatment execute
By the time, and based on user information acquisition unit 113A obtain acoustic information come determine at the appointed time object user whether there is or not
Speech.
In the case where being determined as that object user has made a speech at the appointed time (step S103: yes), control unit 110A (hair
Speech control unit 115A) it is judged as the dialogue being carrying out between object user, and conduct is collaboratively determined with robot 100B
For the speech content (step S104) of the response of the speech of object user.Control unit 110A (speech control unit 115A) reference is deposited
The speech information DB123A and user information DB121A of storage portion 120A, determine it is corresponding with the speech content of object user and
The candidate for the topic that hobby with the object user stored in user information DB121A matches.In this case, as with it is right
As the candidate for the topic that the hobby of user matches, topic corresponding with aftermentioned hobby degree A and B is determined.
In step S104, when the candidate of the topic determined is one, it is determined as final topic.It is another
Aspect is carried out in the case where determining the candidate of multiple topics when being stored with speech in the storage unit 120B in robot 100B
When going through information, control unit 110A (speech control unit 115A) reads the speech stored in storage unit 120B via communication unit 170A
Resume information, and determine in read-out speech resume information with the presence or absence of identical as some in the candidate of multiple topics
Or associated topic and be until its speech date-time plays current (that is, when speech of robot 100A)
Be regulation by the topic (hereinafter referred to as " the 1st comparison other topic ") within the time by the time.
Then, control unit 110A (speech control unit 115A) is, when being determined as that in speech resume information, there are the above-mentioned 1st
When comparison other topic, if removing is consistent or associated with above-mentioned 1st comparison other topic from the candidate of multiple topics
Topic, and finally determine topic.The candidate by the remaining topic of the removing there are it is multiple in the case where, will from wherein with
The topic selected to machine is determined as final topic.
On the other hand, in the case where determining the candidate of multiple topics, when in the storage unit 120B in robot 100B
When not stored any speech resume information or when being judged to that the 1st comparison other topic is not present in resume information of making a speech,
Be randomly chosen out from the candidate of the multiple topics determined topic is determined as final topic.Speech control unit
115A output indicates the text data of the speech content according to the topic determined as described above.
On the other hand, in the case where being determined as that object user does not make a speech at the appointed time (step S103: no), control
Portion 110A (speech control unit 115A) determines the topic (step S105) with the speech of object user's talk.At this point, control unit
110A (speech control unit 115A) is determined and is used referring to the speech information DB123A and user information DB121A of storage unit 120A
The candidate for multiple topics that the hobby of the object user stored in the information DB121A of family matches.In this case, as with
The candidate for the topic that the hobby of object user matches determines topic corresponding with aftermentioned hobby degree A and B.
In step S105, when the candidate of the topic determined is one, it is determined as final topic.It is another
Aspect, when determining the candidate of multiple topics, with step S104 the case where is identical, selects most from the candidate of this multiple topic
Whole topic.Specifically, control unit 110A (speech control unit 115A) is, in the candidate situation for determining multiple topics
Under, when being stored with speech resume information in the storage unit 120B in robot 100B, control unit 110A (speech control unit
The speech resume information stored in storage unit 120B 115A) is read via communication unit 170A, and is determined in read-out speech
It whether there is above-mentioned 1st comparison other topic in resume information.
Then, control unit 110A (speech control unit 115A) is to compare when being determined as that in speech resume information, there are the 1st
When object topic, topic consistent or associated with the 1st comparison other topic is removed from the candidate of multiple topics, and final
Ground determines topic.The candidate by the remaining topic of the removing there are it is multiple in the case where, will be from being wherein randomly chosen
A topic out is determined as final topic.
On the other hand, in the case where determining the candidate of multiple topics, when in the storage unit 120B in robot 100B
When not stored any speech resume information or when being judged to that the 1st comparison other topic is not present in resume information of making a speech,
Be randomly chosen out from the candidate of the multiple topics determined topic is determined as final topic.
In the case where object user does not make a speech at the appointed time with the movement of object user's talk, become object user
The triggering of dialogue between robot 100A and robot 100B, in order to promote object user real using conversational system 1
It applies.
After performing step S104 or step S105, control unit 110A is based on the speech according to the topic determined
Content is come made a speech (step S106).Control unit 110A (speech synthesiser 116A) is generated to be inputted with from speech control unit 115A
Expression robot 100A speech content the corresponding voice data of text data, and control audio output unit 150A and export
Sound based on voice data.
Step S107~step S109 is the speech for determine object user for the robot 100A in step S106
Reaction processing.
Sound determination processing (step is first carried out in control unit 110A (the sound determination unit 117AA of reaction determination unit 117A)
S107).Herein, sound determination processing is illustrated referring to flow chart shown in Fig. 7.Sound determination processing is based in machine
Carry out the reaction of speech of the determine object user for robot 100A after the speech of people 100A from the sound that object user issues
Processing.
Sound determination unit 117AA is, when starting sound determination processing, to determine robot in step s 106 first
It whether there is the speech (step S301) of object user after the speech of 100A.Control unit 110A is based on user information acquisition unit 113A
The acoustic information obtained after the speech of robot 100A determines whether the hair of the object user of the speech for robot 100A
Speech.
Being determined as after the speech of robot 100A there are (step S301: yes) in the case where the speech of object user,
Sound determination unit 117AA extracts feature critical word (step from the speech of the object user of the speech for robot 100A
S302).The textual data of speech content of the sound determination unit 117AA based on the expression object user generated by voice recognition portion 114
According to, such as keyword relevant to emotion is extracted, the feature critical word of feature is assigned as the speech content to object user.
Then, sound determination unit 117AA determines audio response polarity (step S303) based on feature critical word.Sound is sentenced
Determine portion 117AA and determines the figure stored in information DB124A as reaction judgement information referring for example to the reaction in storage unit 120A
Audio response polarity judging table shown in 4, according to extracted feature critical word establish corresponding audio response polarity come
Determined.Sound determination unit 117AA for example feature critical word be " liking ", " happy " etc. in the case wheres, by audio response
Polarity judging is " positive ".
On the other hand, (step in the case where not having the speech of object user after being determined as in the speech of robot 100A
S301: no), since object user is indefinite for the reaction of the speech of robot 100A, sound determination unit 117AA is by sound
Sound antipolarity is determined as " neutrality " (step S304).
Control unit 110 after performing step S303 or S304, terminate sound determination processing, make processing returns to pair
Talk about control processing.
Back to Fig. 5, after performing sound determination processing (step S107), control unit 110A (reaction determination unit 117
Expression determination unit 117BA) execute expression determination processing (step S108).Herein, expression is sentenced referring to flow chart shown in Fig. 8
Fixed processing is illustrated.Expression determination processing is the expression based on object user come determine object user for robot 100A
The processing of the reaction of speech.
Control unit 110A (the expression determination unit 117BA of reaction determination unit 117A) is, first when starting expression determination processing
First, it is extracted from the photographed images obtained after the speech of robot 100A in step s 106 by user information acquisition unit 113A
The face-image (step S401) of object user.
Then, expression determination unit 117BA is based on the face-image extracted in step S401, the smiling face of computing object user
It spends (step S402).Control unit 110 determines the smiling face's degree information stored in information DB124A referring for example to reaction, based on face
Variation, variation of mouth size of canthus position in image etc., calculate the smiling face of object user in the range of 0~100%
Degree.
Then, expression determination unit 117BA determine in step S402 calculated object user smiling face's degree whether be
70% or more (step S403).In the case where smiling face's degree of object user is 70% or more (step S403: yes), control unit
Expression antipolarity is determined as " positive " (step S405) by 110.
In the case where smiling face's degree of object user is not 70% or more (step S403: no), control unit 110A judgement pair
As whether smiling face's degree of user is 40% more than and less than 70% (step S404).It is 40% or more in smiling face's degree of object user
And less than 70% in the case where (step S404: yes), expression antipolarity is determined as " neutrality " (step by control unit 110
S406)。
Smiling face's degree of object user be not 40% more than and less than 70% in the case where (step S404: no), that is, right
As user smiling face's degree less than 40% in the case where, expression antipolarity is determined as " passiveness " (step S407) by control unit 110.
After control unit 110A determined the expression antipolarity of object user in either one or two of step S405~S407,
Terminate expression determination processing, make processing returns to dialogue control processing.
Back to Fig. 5, after performing expression determination processing (step S108), control unit 110A is executed at action judgement
It manages (step S109).Herein, action determination processing is illustrated referring to flow chart shown in Fig. 9.Determination processing of taking action is base
Carry out the processing of the reaction of speech of the determine object user for robot 100A in the action of object user.
The control unit 110A action determination unit 117CA of determination unit 117A (reaction) is, when go into action determination processing when, it is first
Whether first determine object user moves (step S501) breezily.Determination unit 117CA take action based on machine in step s 106
Determined after the speech of people 100A by the movement of the object user in the photographed images of user information acquisition unit 113A acquirement.
In the case where being determined as that object user moves breezily (step S501: yes), action determination unit 117CA determine object user's
Whether sight is towards robot 100A (step S502).Action determination unit 117CA for example takes according to user information acquisition unit 113A
Photographed images in eye areas in pupil position and face direction etc. come determine object user sight direction,
Thus determined.
In the case where being determined as the sight of object user towards robot 100A (step S502: yes), determination unit of taking action
Action antipolarity is determined as " positive " (step S508) by 117CA.On the other hand, in the non-court of sight for being determined as object user
In the case where robot 100A (step S502: no), action antipolarity is determined as " passiveness " by action determination unit 117CA
(step S509).
In step S501, in the case where being determined as that object user does not move breezily (step S501: no), action is sentenced
Determine whether portion 117CA determine object user has approached robot 100A (step S503).Take action determination unit 117CA for example according to
The size variation for the face-image in photographed images that family information acquiring section 113A is obtained is determined.
In the case where being determined as that object user has approached robot 100A (step S503: yes), take action determination unit 117CA
Whether the sight of determine object user is towards robot 100A (step S504).In the sight for being determined as object user towards machine
In the case where people 100A (step S504: yes), action antipolarity is determined as " positive " (step by action determination unit 117CA
S508).On the other hand, in the case where being determined as the sight of object user not towards robot 100A (step S504: no), row
Action antipolarity is determined as " passiveness " (step S509) by dynamic determination unit 117CA.
In step S503, in the case where being determined as object user not close to robot 100A (step S503: no), row
Dynamic determination unit 117CA determine object user whether from robot 100A far from (step S505).Be determined as object user from
Far from the case where (step S505: yes), the action determination unit 117CA antipolarity that will take action is judged to " disappearing robot 100A
Pole " (step S509).
On the other hand, in the case where being determined as that object user is not separate from robot 100A (step S505: no), action
Determination unit 117C determines whether not observing the face (step S506) of object user.Make the direction reversion of face in object user
Deng and in the case where becoming can not to extract the face-image of object user from photographed images, action determination unit 117CA is determined as
The facial parts of object user are not observed.(the step in the case where being judged to not observing the facial parts of object user
S506: yes), action antipolarity is determined as " neutrality " (step S510) by action determination unit 117CA.
In the case where being determined as is not the facial parts for not observing object user (step S506: no), action determines
Whether the sight of portion 117CA determine object user is towards robot 100A (step S507).In the sight for being determined as object user
In the case where robot 100A (step S507: yes), action antipolarity is determined as " positive " by action determination unit 117CA
(step S508).On the other hand, in the case where being determined as the sight of object user not towards robot 100A (step S507:
It is no), action antipolarity is determined as " passiveness " (step S509) by action determination unit 117CA.
Control unit 110 is, when the action that determined object user in either one or two of step S508~step S510 is reacted
After polarity, closing action determination processing, make processing returns to dialogue control processing.
Back to Fig. 5, after performing action determination processing (step S109), control unit 110A (hobby determination unit
118A) execute hobby determination processing (step S110).Herein, flow chart shown in 0 says hobby determination processing referring to Fig.1
It is bright.Hobby determination processing is following processing: respectively being sentenced using sound determination processing, expression determination processing, action determination processing
Determine as a result, synthetically determine object user is directed to the hobby degree of the topic of the dialogue between object user and robot 100A.
Hobby determination unit 118A is, when starting to have a liking for determination processing, firstly, determine object user and robot 100A it
Between dialogue topic (step S601).Hobby determination unit 118A is, in the step S105 of dialogue control processing, when in object
When user talks in the case where not making a speech the stipulated time with object user, in the case where being preset with topic, referring to RAM
The topic keyword stored in, determines the topic of the dialogue between object user and robot 100A.On the other hand, not
In the case where presetting topic, the textual data of the speech content based on the expression object user generated by voice recognition portion 114A
According to keyword is inscribed in extraction from the speech of object user, if thereby determining that the dialogue between object user and robot 100A
Topic.For example, determining topic as " baseball " according to the speech of object user as " liking baseball ".
Then, whether hobby determination unit 118A determines the audio response polarity determined by the sound determination processing of Fig. 7
Hobby degree is determined as in the case where audio response polarity is " positive " (step S602: yes) for " positive " (step S602)
" hobby degree A " (step S609).
In the case where audio response polarity is not " positive " (step S602: no), hobby determination unit 118A determines sound
Whether antipolarity is " passiveness " (step S603).It is thermophilic in the case where audio response polarity is " passiveness " (step S603: yes)
Good determination unit 118A determines whether the expression antipolarity determined by the expression determination processing of Fig. 8 is " positive " (step
S604).In the case where expression antipolarity is " positive " (step S604: yes), hobby determination unit 118A determines hobby degree
For " hobby degree B " (step S610).On the other hand, in the case where expression antipolarity is not " positive " (step S604: no),
Have a liking for determination unit 118A and hobby degree is determined as " hobby degree D " (step S612).
In step S603, in the case where audio response polarity is not " passiveness " (step S603: no), have a liking for determination unit
118A determines whether the action antipolarity determined by the action determination processing of Fig. 9 is " positive " (step S605).It is expert at
Dynamic antipolarity is in the case where " positive " (step S605: yes), hobby determination unit 118A judgement expression antipolarity whether be
Some (step S606) in " positive " or " neutrality ".It is a certain in " positive " or " neutrality " in expression antipolarity
In the case where a (step S606: yes), have a liking for determination unit 118A for hobby degree and be determined as " hobby degree A " (step S609).It is another
Aspect, in the case where expression antipolarity is not any one of " positive " and " neutrality " (step S606: no), that is, in expression
In the case that antipolarity is " passiveness ", has a liking for determination unit 118A for hobby degree and be determined as " hobby degree C " (step S611).
In step s 605, in the case where antipolarity of taking action is not " positive " (step S605: no), have a liking for determination unit
118A determines whether action antipolarity is " neutrality " (step S607), in the case where antipolarity of taking action is not " neutrality "
(step S607: no) has a liking for determination unit 118A for hobby degree and is determined as " hobby degree C " (step S611).
On the other hand, the case where antipolarity of taking action is " neutrality " (step S607: yes), hobby determination unit 118A determines
Whether expression antipolarity is " positive " (step S608).Hobby determination unit 118A is, is " positive " in expression antipolarity
In the case of (step S608: yes), hobby degree is determined as " hobby degree B " (step S610), is not " product in expression antipolarity
In the case where pole " (step S608: no), hobby degree is determined as " hobby degree D " (step S612).
In either one or two of step S609~step S612, after it determined the hobby degree of object user, hobby determines
Portion 118A terminate have a liking for determination processing, make processing returns to dialogue control processing.
Back to Fig. 5, after performing hobby determination processing (step S110), hobby is determined result by control unit 110A
Reflect in hobby degree information (step S111).Control unit 110A is that the hobby as hobby determination processing determines as a result, will make
The topic and hobby degree of dialogue between object user and robot 100A establish corresponding information, are appended to user information
In DB121A in the hobby degree information of the stored user information, and hobby degree information is updated.Hobby degree information as a result,
It is updated according to each user USR.The topic of dialogue between object user and robot 100A is if storing in RAM etc.
Inscribe topic represented by keyword.In addition, control unit 110A controls communication unit 170A, object user and robot will be made
The topic and hobby degree of dialogue between 100A establish corresponding information, are sent to robot 100B.Receive the information
Robot 100B is similarly appended in the hobby degree information of the stored user information in user information DB121B, and right
Hobby degree information is updated.Robot 100A and robot 100B can share respective hobby judgement result as a result,.This
Outside, the initial value for the hobby degree that the hobby degree information accordingly stored with each foundation of multiple topics is included is set to thermophilic
Spend A well.In this way, comprising react determination unit 117A (117B), have a liking for determination unit 118A (118B) control unit 110A (110B) with
And communication unit 170A (170B) is functioned as reaction acquisition unit of the invention.
After the processing for performing step S111, control unit 110A determines to whether there is object around robot 100A
User (step S112).Being determined as around robot 100A there are (step S112: yes) in the case where object user, control
Portion 110A, which is judged as, can continue to engage in the dialogue with object user, and make that processing returns to step S103.It is in step S112
In step S103 in the case where being, determine from being completed the speech of step S106 by the time whether be the stipulated time with
It is interior.
On the other hand, in the case where being judged to that object user is not present around robot 100A (step S112: no),
Control unit 110A, which is judged as, can not continue to engage in the dialogue with object user, and release and robot 100B (other robot)
It communicates to connect (step S113).Control unit 110A controls communication unit 170A and carries out the defined mistake based on communication mode
Thus journey releases the communication connection with robot 100B.Later, control unit 110A terminates to talk with control processing.
It is the dialogue control processing that the control unit 110A of robot 100A is executed, the control unit 110B of robot 100B above
The dialogue control processing of execution is also identical.As shown in figure 5, control unit 110B starts to talk with control processing.It holds as shown in Figure 6
Row user determines processing.
In the step S103 of Fig. 5, (the step in the case where being determined as that object user has made a speech at the appointed time
S103: yes), control unit 110B (speech control unit 115B) is judged as the dialogue being carrying out with object user, and determines conduct
For the speech content (step S104) of the response of the speech of object user.Control unit 110B (speech control unit 115B) reference is deposited
The speech information DB123B and user information DB121B of storage portion 120B, determine it is corresponding with the speech content of object user and with
The candidate for the topic that the hobby of object user matches.
In step S104, when the candidate of the topic determined is one, it is determined as final topic.It is another
Aspect is carried out in the case where determining the candidate of multiple topics when being stored with speech in the storage unit 120A in robot 100A
When going through information, control unit 110B (speech control unit 115B) reads the speech stored in storage unit 120A via communication unit 170B
Resume information.Then, control unit 110B (speech control unit 115B) determines in read-out speech resume information, if exists
With some candidate identical or associated topic of multiple topics and be played from its speech date-time it is current (i.e.
When the speech of robot 100B starts) until be regulation by topic (hereinafter referred to as " the 2nd ratio within the time by the time
Compared with object topic ").
Control unit 110B (speech control unit 115B) is, when being determined to have the 2nd comparison other topic, from multiple topics
Candidate in remove consistent or associated with above-mentioned 2nd comparison other topic topic, and finally determine topic.
On the other hand, in the case where determining the candidate of multiple topics, when in the storage unit 120A in robot 100A
When not stored any speech resume information or when being judged to that the 2nd comparison other topic is not present in resume information of making a speech,
Be randomly chosen from the candidate of the multiple topics determined topic is determined as final topic.Speech control unit
115B output indicates the text data of the speech content according to the topic determined as described above.
On the other hand, in the case where being determined as that object user does not make a speech at the appointed time (step S103: no), control
Portion 110B (speech control unit 115B) determines the speech content (step S105) with object user's talk.At this point, control unit 110B
(speech control unit 115B) determines to believe with user referring to the speech information DB123B and user information DB121B of storage unit 120B
The candidate for multiple topics that the hobby of the object user stored in breath DB121B matches.In this case, as with object
Topic corresponding with hobby degree A and B, is determined as the candidate of topic by the topic that the hobby of user matches.
In step S105, when the candidate of the topic determined is one, it is determined as final topic.It is another
Aspect, when determining the candidate of multiple topics, with step S104 the case where is same, selects most from the candidate of this multiple topic
Whole topic.Specifically, control unit 110B (speech control unit 115B) is, in the case where determining the candidate of multiple topics,
When being stored with speech resume information in the storage unit 120A in robot 100A, control unit 110B (speech control unit 115B) warp
The speech resume information stored in storage unit 120A is read by communication unit 170B.Then, control unit 110B (speech control unit
115B) determine to whether there is above-mentioned 2nd comparison other topic in read-out speech resume information.
Control unit 110B (speech control unit 115B) is, when being determined to have the 2nd comparison other topic, from multiple topics
Candidate in remove consistent or associated with the 2nd comparison other topic topic, and finally determine topic.
On the other hand, in the case where determining the candidate of multiple topics, but in the storage unit 120A of robot 100A
When not stored any speech resume information or when being judged to that the 2nd comparison other topic is not present in resume information of making a speech,
Be randomly chosen out from the candidate of the multiple topics determined topic is determined as final topic.
Control unit 110B is, when being made a speech (step S106) and exported based on the speech content according to the topic determined
When sound, execute the sound determination processing shown in Fig. 7 of reaction of determine object user, expression determination processing shown in Fig. 8, with
And action determination processing shown in Fig. 9.At the end of determination processing of taking action, hobby determination processing shown in Fig. 10 is executed.Control
The hobby having a liking in determination processing is determined that result is appended to the stored user information in user information DB121B by portion 110B
In hobby degree information, and hobby degree information is updated.In addition, control unit 110B controls communication unit 170B, will make
The topic and hobby degree of dialogue between object user and robot 100B establish corresponding information and are sent to robot 100A.
The robot 100A for receiving the information is similarly appended to the thermophilic of the stored user information in user information DB121A
It spends in information well, and hobby degree information is updated.Robot 100A and robot 100B shares respective hobby and sentences as a result,
Determine result.
In addition, in the above-described first embodiment, when the robot speech in robot 100A and 100B
Afterwards, in the case where another robot makes a speech within above-mentioned regulation is by the time, the topic that another robot makes a speech is determined
It is set to the topic different from the topic that a robot has made a speech within the regulation before the speech of another robot is by the time.
In the case where in addition to this, mutually it is not coordinated with and determines robot 100A and 100B with being independent of each other (mutually indepedent) make a speech
Topic.Also it can replace the determining method, the hobby of the object user stored in user information DB121A (DB121B)
In the case that the quantity of information is less than defined threshold value, robot 100A and the 100B topic made a speech are determined as mutually different
Topic, in the case where more than for defined threshold value, determine with being independent of each other robot 100A and 100B speech topic.
I.e., or, when defined condition is set up, robot 100A and the 100B topic made a speech are determined as mutually different
Topic determines the topic of robot 100A and 100B speech when defined condition is invalid with being independent of each other.Alternatively,
Can be unrelated with defined condition, if being always mutually not coordinated with and determine robot 100A and 100B speech with being independent of each other
Topic (speech content).
(the 2nd embodiment)
In the above-described embodiment, robot 100A and robot 100B is respectively provided with the function that reaction determines, speech controls
Can, but these functions can also have an independent existence with robot 100A and robot 100B phase.In the present embodiment, it is arranged
The external server that can be communicated with robot 100A and robot 100B, server carry out robot 100A and machine
The processing of reaction judgement, the speech control of people 100B.
As shown in figure 11, the conversational system 1 in present embodiment includes robot 100A, robot 100B and server
200。
In a same manner as in the first embodiment, robot 100A has control unit 110A, storage unit 120A, image pickup part 130A, sound
Input unit 140A, audio output unit 150A, moving portion 160A and communication unit 170A.But with the case where 1 embodiment not
Together, control unit 110A does not have speech control unit 115A, reaction determination unit 117A and hobby determination unit 118A.In addition, with the 1st
The case where embodiment, is different, and storage unit 120A does not have user information DB121A, acoustic information DB122A, speech information
DB123A and reaction determine information DB124A.The composition of robot 100B is also same as robot 100A, has control unit
110B, storage unit 120B, image pickup part 130B, voice input portion 140B, audio output unit 150B, moving portion 160B and communication unit
170B.Control unit 110B does not have speech control unit 115B, reaction determination unit 117B and hobby determination unit 118B.In addition, depositing
Storage portion 120B does not have user information DB121B, acoustic information DB122B, speech information DB123B and reaction and determines information
DB124B。
Server 200 has control unit 210, storage unit 220 and communication unit 270.Control unit 210 has speech control unit
215, determination unit 217 and hobby determination unit 218 are reacted.That is, instead of robot 100A and robot 100B, server 200
Carry out control for carrying out robot 100A and the respective speech of robot 100B, the judgement of the reaction of user, user
The various processing such as the judgement of hobby.Storage unit 220 have user information DB221, acoustic information DB222, speech information DB223 with
And reaction determines information DB224.That is, robot 100A and robot the 100B above-mentioned database having are pooled to server
In 200.In addition, storage unit 220 stores speech resume information according to each user USR, which includes machine
The speech date-time and the topic made a speech etc. that people 100A and robot 100B is made a speech.Server 200 is via logical
Letter portion 270, the communication unit 170A of robot 100A and robot 100B communication unit 170B and robot 100A and machine
People 100B carries out wireless data communication.Server 200 controls robot 100A and robot 100B as a result, and object user carries out
The case where dialogue.In this way, communication unit 170A, 170B are functioned as the 1st communication unit of the invention.In addition, communication unit 270
It is functioned as the 2nd communication unit of the invention.
Then, the dialogue control processing in present embodiment is illustrated.Herein, it is controlled with the dialogue of robot 100A
It is illustrated for processing.The control unit 110A of robot 100A is detected around robot 100A with user's test section 111A
The case where user USR is opportunity, starts to talk with control processing.
Control unit 110A is, when starting to talk with control processing (referring to Fig. 5), firstly, executing user determines processing.Control
Portion 110A retrieves registration user corresponding with the face-image extracted from photographed images, which is from image pickup part
What 130A was obtained.Control unit 110A (user determining section 112A) accesses the user information DB221 of the storage unit 220 of server 200,
The respective face-image of multiple users that will be stored from the face-image and user information DB221 extracted in photographed images
It is compareed, user USR is determined as object user.Herein, control unit 110A is played as object determination unit of the invention
Function.
The control unit 210 for receiving the server 200 of the information of user USR is to be determined as object at the appointed time
In the case that user is made a speech, control unit 210 (speech control unit 215) is judged as pair being carrying out with object user
Words, and determine the speech content of the response as the speech for object user.Control unit 210 (speech control unit 215) reference
The speech information DB223 and user information DB221 of storage unit 220, determine it is corresponding with the speech content of object user and with it is right
As the candidate for the topic that the hobby of user matches.
When the candidate of the topic determined is one, it is determined as final topic.On the other hand, determine it is more
In the case where the candidate of a topic, when being stored with the speech resume information of robot 100B in storage unit 220, control unit
210 (speech control units 215) read the speech resume information stored in storage unit 220, and determine to carry out in read-out speech
It goes through in information with the presence or absence of the 1st comparison other topic.
Control unit 210 (speech control unit 215) is, when being determined to have the 1st comparison other topic, from multiple topics
Topic consistent or associated with above-mentioned 1st comparison other topic is removed in candidate, and finally determines topic.
On the other hand, in the case where determining the candidate of multiple topics, in the hair of not stored any robot 100B
It says when resume information or when being determined as in resume information of making a speech there is no the 1st comparison other topic, it will be from determining
A topic being randomly chosen out in the candidate of multiple topics is determined as final topic.The output of control unit 215 of making a speech indicates
According to the text data of the speech content of the topic determined as described above.
On the other hand, in the case where being determined as that object user does not make a speech at the appointed time, (the speech control of control unit 210
Portion 215 processed) determine the speech content talked with object user.At this point, speech control unit 215 is believed referring to the speech of storage unit 220
What the hobby of the object user stored in breath DB223 and user information DB221, decision and user information DB221 matched
The candidate of multiple topics.
When the candidate of the topic determined is one, it is determined as final topic.On the other hand, determine it is more
When the candidate of a topic, final topic is selected from the candidate of this multiple topic.In the candidate feelings for determining multiple topics
Under condition, when being stored with the speech resume information of robot 100B, control unit 210 (speech control unit 215) reads speech resume
Information, and determine whether that there are the 1st comparison other topics.
Control unit 210 (speech control unit 215) is, when being determined to have the 1st comparison other topic, from multiple topics
Topic consistent or associated with the 1st comparison other topic is removed in candidate, and finally determines topic.
On the other hand, in the case where determining the candidate of multiple topics, in the hair of not stored any robot 100B
It says when resume information or when being determined as in resume information of making a speech there is no the 1st comparison other topic, it will be from determining
A topic being randomly chosen out in the candidate of multiple topics is determined as final topic.
Robot 100A receives text data via communication unit 170A, and is sent to speech synthesiser 116A.Sound rendering
Portion 116A accesses the acoustic information DB222 of the storage unit 220 of server 200, uses the sound equipment saved in acoustic information DB222
Model etc., text data generates voice data based on the received.Speech synthesiser 116A to audio output unit 150A into
Row control carries out sound output to voice data generated.
Then, reaction determination processing (referring to Fig. 7 to Fig. 9) is executed, reaction determination processing determine object user is directed to machine
The reaction of the speech of device people 100A.
Control unit 210 (the sound determination unit 217A of reaction determination unit 217) executes sound determination processing (referring to Fig. 7).Sound
Sound determination unit 217A carrys out determine object user for robot based on the sound that object user issues after robot 100A speech
The reaction of the speech of 100A.When object user's speech, the voice recognition portion 114A access server 200 of robot 100A is deposited
The acoustic information DB222 in storage portion 220, using the sound equipment model etc. saved in acoustic information DB222, according to voice data next life
At text data.Text data is sent to server 200.Sound determination unit 217A by communication unit 270 based on being received
Text data, reaction of the determine object user for the speech of robot 100A and robot 100B.
After performing sound determination processing, control unit 210 (the expression determination unit 217B of reaction determination unit 217) is executed
Expression determination processing (referring to Fig. 8).Expression of the expression determination unit 217B based on the object user after robot 100A speech, determines
Reaction of the object user for the speech of robot 100A.When the user information acquisition unit 113A of robot 100A obtains user's
When photographed images, user information acquisition unit 113A sends server 200 for photographed images via communication unit 170A.Expression determines
The characteristic quantity of portion 217B face of test object user from the photographed images obtained via communication unit 270, referring to storage unit 220
Reaction determine smiling face's degree information for being stored in information DB224, based on detected characteristic quantity come computing object user's
Smiling face's degree.Expression determination unit 217B according to calculated smiling face's degree come determine object user for robot 100A speech it is anti-
It answers.
After performing expression determination processing, control unit 210 executes action determination processing (referring to Fig. 9).Action determines
Action of the portion 217C based on the object user after robot 100A speech, carrys out the hair that determine object user is directed to robot 100A
The reaction of speech.Determination unit 217C take action based on the object user's detected from the photographed images obtained via communication unit 270
Action carrys out the reaction of speech of the determine object user for robot 100A.
After performing action determination processing, control unit 210 (hobby determination unit 218A) executes hobby determination processing (ginseng
According to Figure 10).Have a liking for the topic for the dialogue that determination unit 218 determines between object user and robot 100A, and is determined based on reaction
The each of portion 217 determines the hobby degree as a result, the height to determine to indicate hobby of the object user for topic.
After performing hobby determination processing, hobby is determined result reflection into hobby degree information by control unit 210.Control
Portion 210 processed is that the hobby as hobby determination processing determines as a result, will make the dialogue between object user and robot 100A
Topic and hobby degree establish corresponding information, are appended to the hobby degree letter of the stored user information in user information DB221
In breath, and hobby degree information is updated.Taste information is updated according to each user USR as a result,.
Same control processing is also carried out for robot 100B.In the 1st embodiment, robot 100A uses object
The hobby degree information of dialogue between family and robot 100A is updated, and is sent to robot 100B, receives the letter
The hobby degree information stored in user information DB121B is similarly updated by the robot 100B of breath.Robot as a result,
100A and robot 100B can share respective hobby and determine result.In contrast, in the present embodiment, in server
Believe in 200 user information DB221 according to the hobby degree that each user USR is stored with robot 100A and robot 100B
Breath, therefore do not need to be updated mutual hobby degree information.
In the above-described embodiment, server 200 performs robot 100A and the respective speech of robot 100B
The various processing such as control, the judgement of the reaction of user and the judgement of hobby of user.But, however it is not limited to this, server
200 can selectively execute any processing of robot 100A and robot 100B.For example, it is also possible to be, server 200
Control unit 210 only has speech control unit 215, and only executes the place of the speech control of robot 100A and robot 100B
Reason, other processing are executed by robot 100A and robot 100B.Alternatively, it is also possible to being robot 100A and robot
User's detection, user's determination, user information acquirement, voice recognition, sound rendering, speech control, the reaction of 100B determines, has a liking for
The processing of judgement is all executed by server.In addition, in the present embodiment, the storage unit 220 of server 200 has user's letter
It ceases DB221, acoustic information DB222, speech information DB223 and reaction and determines information DB224.But, however it is not limited to this, clothes
Business device 200 can have arbitrary database.For example, or, not being in the present embodiment that server 200 has sound
Information DB222, but robot 100A and robot 100B have acoustic information DB222 respectively.In addition, about user information
The facial information of the determination user of DB221 is also possible to not only server 200 and has, but also robot 100A and robot
100B also has respectively.As a result, when voice recognition, sound rendering, user determine, robot 100A and robot 100B are not
Need to access server 200.
As described above, according to the 1st embodiment, conversational system 1 has robot 100A and robot
100B, and based on result (the i.e. object user determined for the reaction of the speech of robot 100A object user
Taste information) and to object user for result (the i.e. object user that is determined of reaction of the speech of robot 100B
Taste information), control robot 100A and the respective speech of robot 100B.
According to the 2nd embodiment, conversational system 1 has robot 100A, robot 100B and server 200, service
Device 200 is based on to object user, for the result that the reaction of the speech of robot 100A is determined, (i.e. object user's is thermophilic
Good information) and result (i.e. object user that object user is determined for the reaction of the speech of robot 100B
Taste information), control robot 100A and the respective speech of robot 100B.By the above, implementing according to the 1st and the 2nd
Mode, being capable of high-precision and the effectively hobby of grasp object user, and the dialogue that progress is consistent with the hobby of object user.
In addition, being able to carry out various modifications and application the present invention is not limited to above embodiment.Above embodiment
It can deform as described below.
In the above-described embodiment, robot 100A and robot 100B are arranged on mutual speech not by object user
The place of identification.In contrast, mutual speech is arranged on to robot 100A and robot 100B to be identified by object user
Place in the case where variation be illustrated.In this case, robot 100A and robot 100B can simultaneously with it is right
As user engages in the dialogue.But when the repetition of the speech moment of robot 100A and robot 100B or consecutive hours, it is possible to nothing
Method suitably judges that object user is reacted which speech.Then, the hobby of object user can not suitably be obtained
Information, in addition, can not suitably reply.Therefore, speech control unit 115A (115B) is robot 100A and machine in order to prevent
The speech moment of device people 100B is mutually repeatedly or mutually continuous, and the speech control unit 115B (robot with robot 100B
The speech control unit 115A of 100A) collaboratively determine that the speech of robot 100A (100B) starts period.Make a speech control unit 115A
The speech of robot 100A (100B) is started period and is determined as by (115B), robot 100A and the mutual hair of robot 100B
Speech interval is such as the time for the reaction for judging object user enough more than the stipulated time.In addition, the hair of robot 100B
The speech of robot 100B (100A) is started period decision by speech control unit 115B (the speech control unit 115A of robot 100A)
It will not be in the speech of robot 100A (100B) for, robot 100B (100A) and speech terminates next continuously to make a speech.
The speech of robot 100A and robot 100B start period, other than being determined respectively by speech control unit 115A, 115B,
It can be determined by one party.In the case where server 200 controls the speech of robot 100A and robot 100B,
Speech control unit 215 determines that the speech of the two starts period.The speech of robot 100A and robot 100B will not phases as a result,
It mutually continuously carries out, but is carried out in the timing more than stipulated time of mutual difference.Thereby, it is possible to accurately grasp object to use
The hobby at family, and carry out the dialogue being consistent with the hobby of object user.
It also, may be the speech control unit of speech control unit 115A and robot 100B in above-mentioned variation
The robot 100A and robot 100B topic made a speech is determined as mutually different topic by 115B cooperation.In this case,
Can also be with 1 embodiment the case where, is same, after a robot in robot 100A and 100B makes a speech, upper
In the case where regulation is stated by another robot speech within the time, by the topic that another robot makes a speech be determined as with
The different topic of the topic that regulation before the speech of another robot is made a speech by a robot within the time,
In the case where in addition to this, mutually it is not coordinated with and determines robot 100A and 100B speech with is independent of each other (mutually indepedent)
Topic.Alternatively, in this case, or, the object user's stored in user information DB121A (DB121B) is thermophilic
In the case that the quantity of good information is less than defined threshold value, robot 100A and the 100B topic made a speech are determined as mutually not
Same topic, in the case where more than for defined threshold value, determine robot 100A and 100B speech with being independent of each other if
Topic.Alternatively, can also be unrelated with rated condition as described above, determine robot with being always mutually not coordinated with and be independent of each other
The topic (speech content) of 100A and 100B speech.
In addition, being carried out to the control of speech to moving portion 160A for example, it is also possible to have according to speech control unit 115A
The mobile control unit of control.It is the speech with robot 100A that mobile control unit, which can for example control moving portion 160A,
Start cooperatively to make robot 100A close to object user.
For example, it is also possible to be, multiple robots 100 of conversational system 1 are constituted using main equipment/from DeviceMode, for example,
As the robot 100 that main equipment functions, the speech content as the robot 100 functioned from equipment is included in
It is interior and determine together, and indicate to send out based on the speech content determined to as the robot 100 functioned from equipment
Speech.In this case, the robot 100 that functions as main equipment and as the robot 100 functioned from equipment
Determining method is arbitrary, for example, the robot for detecting and having determined at first the user USR of surrounding can be made as main equipment
It functions, is used as other robot 100 and is functioned from equipment.In addition, for example, can make to be connected by user USR at first
The robot 100 of power supply is functioned as main equipment, and the robot 100 for being then switched on power supply is made to play function as from equipment
Can, it is also configured to, user USR is able to use the robot 100 that the settings such as the switch of physics are functioned as main equipment
With as the robot 100 functioned from equipment.
Furthermore it is possible to the pre-determined robot 100 functioned as main equipment and as being functioned from equipment
Robot 100.In this case, it also can be omitted what a part was able to carry out as the robot 100 functioned from equipment
Function.For example, according to the instruction of the robot 100 functioned as main equipment to be made a speech, as from
The robot 100 that equipment functions may not possess and the comparable functions such as speech control unit 115A.
In addition, in the above-described embodiment, the example to engage in the dialogue to robot 100A and robot 100B and object user
Son is illustrated, but is also configured to, and implements the dialogue with object user by 1 robot 100.In the situation
Under, for example, 1 robot 100 is, with it is above-mentioned the case where being functioned as main equipment it is same, determine the hair of itself together
Say the speech content of content and other robot, and it is defeated that the speech content determined is successively carried out sound with changing sensual pleasure
Out, 1 robot 100 such as is thus shown as to represent the speech of other robot.
In the above-described embodiment, in case where conversational system 1 is that have the robot system of multiple robots 100
It is illustrated, but conversational system 1 can also be by having the more of all or part constituted that robot 100 has
A Interface is constituted.
In the above-described embodiment, the control program that the CPU of control unit 110A, 110B is executed is stored in advance in ROM etc..
But the present invention is not limited to this, and the control program for being used to execute above-mentioned various processing can also be installed to existing lead to
With electronic equipments such as computer, framework, work stations, thus make its as with robot 100A involved in above embodiment,
The comparable device of 100B functions.For example, as with the comparable speech device of robot 100A, 100B, comprising have sound
Portable terminal, digital signage of miscellaneous function etc..So-called digital signage, which refers to, shows shadow on the electronic display units such as display
The system of picture, information.In addition, speech is not limited to carry out sound output by loudspeaker, it is also contained in conduct in display equipment
Text is shown.Therefore, the portable terminal of speech text importing, digital signage etc. are also included as and robot
The comparable speech device of 100A, 100B.
The providing method of such program is arbitrarily, for example, it is (soft to be stored in the recording medium that computer can be read
Disk, CD (Compact Disc: compact disk)-ROM, DVD (Digital Versatile Disc: digital versatile disc)-
) etc. ROM distribute, program can also be stored in the memory on the networks such as internet in advance, by being downloaded to it
To provide.
In addition, by OS (Operating System: operating system) and application program share or OS and application
Application program only can also be saved in recording medium, in memory come in the case where executing above-mentioned processing by the cooperation of program.Separately
Outside, also can on carrier wave overlay programme and via Web Publishing.For example, can be in the bulletin board (Bulletin on network
Board System (BBS): bulletin board system) in announce above procedure, and via Web Publishing program.Moreover, can also
To be configured to, starts issued program and executed in the same manner as other applications under the control of the os, thus, it is possible to execute
Above-mentioned processing.
The present invention without departing from the broad spirit and scope of the present invention, can become various embodiments and change
Shape.In addition, above embodiment be it is of the invention for illustrating, not delimit the scope of the invention.That is, the scope of the present invention is not
By embodiment by the Range Representation of Patent request.Also, range in the range of Patent request and with Patent request
The various modifications implemented in the range of the meaning of same invention are considered as within the scope of the invention.
Claims (20)
1. a kind of session control, which is characterized in that have:
Acquisition unit is reacted, multiple reactions is obtained and determines as a result, multiple reaction determines in result comprising being directed to regulation object
The result and above-mentioned regulation object is directed to and above-mentioned 1st speech dress that the reaction of the speech of 1st speech device is determined
Set the result that the reaction of the speech for the 2nd speech device being mutually provided independently from is determined；And
Make a speech control unit, based on is obtained by above-mentioned reaction acquisition unit multiple reactions judgement as a result, to comprising the above-mentioned 1st with
And at least any one the above-mentioned speech of the 2nd multiple speech devices including speech device is controlled.
2. session control as described in claim 1, which is characterized in that
Above-mentioned reaction acquisition unit obtain it is in following situation, comprising to above-mentioned regulation object for it is above-mentioned 1st and the 2nd speech
The above-mentioned multiple reactions for the result that the reaction of each speech of device is determined determine as a result, above situation are as follows: by upper
It states the 1st speech device and the place of above-mentioned speech is carried out and by above-mentioned 2nd speech device to above-mentioned rule to above-mentioned regulation object
Determine the place that object carries out above-mentioned speech, is that above-mentioned regulation object can not identify the above-mentioned of above-mentioned 1st and the 2nd speech device
The place of the both sides of speech.
3. session control as described in claim 1, which is characterized in that
Above-mentioned speech control unit is controlled, so that the above-mentioned speech of above-mentioned 1st and the 2nd speech device is not mutual continuously
It carries out and is carried out in the timing more than stipulated time of mutual difference.
4. session control as described in claim 1, which is characterized in that
The topic of the above-mentioned speech of above-mentioned 1st and the 2nd speech device is determined as mutually different by above-mentioned speech control unit
Topic.
5. session control as described in claim 1, which is characterized in that
Above-mentioned speech control unit determines the content of the above-mentioned speech of above-mentioned 1st and the 2nd speech device with being independent of each other.
6. session control as described in claim 1, which is characterized in that
Above-mentioned multiple reactions determine the result is that based in the photographed images of sound and above-mentioned regulation object for providing object sending
At least any one, the reaction of speech to above-mentioned regulation object for above-mentioned 1st and the 2nd speech device carried out judgement
As a result.
7. session control as described in claim 1, which is characterized in that
It is also equipped with acquisition unit, which obtains the camera shooting of sound and above-mentioned regulation object that above-mentioned regulation object issues
In image at least any one,
Above-mentioned reaction acquisition unit is, by based in the above sound and above-mentioned photographed images obtained by above-mentioned acquisition unit
It is above-mentioned at least any one, to above-mentioned regulation object for it is above-mentioned 1st and the 2nd speech the respective above-mentioned speech of device reaction
Determined, thus obtains above-mentioned multiple reactions and determine result.
8. session control as claimed in claim 7, which is characterized in that
Above-mentioned reaction acquisition unit has at least any in sound judging unit, expression judging unit and action judging unit
It is a,
Above sound judging unit determines above-mentioned regulation object for above-mentioned based on the above sound obtained by above-mentioned acquisition unit
The content of the above sound of 1st and the 2nd speech respective above-mentioned speech of device,
Above-mentioned expression judging unit determines that above-mentioned regulation object is directed to based on the above-mentioned photographed images obtained by above-mentioned acquisition unit
The expression of above-mentioned 1st and the 2nd speech respective above-mentioned speech of device,
Above-mentioned action judging unit determines that above-mentioned regulation object is directed to based on the above-mentioned photographed images obtained by above-mentioned acquisition unit
The action of above-mentioned 1st and the 2nd speech respective above-mentioned speech of device,
Above-mentioned reaction acquisition unit is based on above sound judging unit, above-mentioned expression judging unit and above-mentioned action judging unit
In it is above-mentioned at least any one judgement as a result, determine above-mentioned regulation object for it is above-mentioned 1st and the 2nd speech device it is respective
Thus the reaction of above-mentioned speech obtains above-mentioned multiple reactions and determines result.
9. session control as claimed in claim 8, which is characterized in that
At least appointing in above sound, above-mentioned expression and above-mentioned action of the above-mentioned reaction acquisition unit based on above-mentioned regulation object
One, the above-mentioned reaction classification by above-mentioned regulation object is the reaction of affirmative, the reaction of negative and neither affirms nor negate
Neutral reaction, thus determine the above-mentioned reaction of above-mentioned regulation object.
10. session control as claimed in claim 7, which is characterized in that be also equipped with:
Determination unit, the above sound issued based on above-mentioned regulation object, the above-mentioned speech of above-mentioned 1st speech device, Yi Jishang
State in the above-mentioned speech of the 2nd speech device at least any one, the topic of the determining dialogue with above-mentioned regulation object；And
Have a liking for judging unit, determines result based on acquired above-mentioned multiple reactions to determine hobby degree, in hobby degree expression
The degree that regulation object is directed to the hobby for the above-mentioned topic determined by above-mentioned determination unit is stated,
Above-mentioned speech control unit is based on the hobby degree determined by above-mentioned hobby judging unit, to the upper of above-mentioned multiple speech devices
At least any one above-mentioned speech is stated to be controlled.
11. session control as claimed in claim 10, which is characterized in that
Above-mentioned hobby be with interest tangible and invisible unrelated and related with things, hobby, in addition to having with food, sport, weather
Except the interest of pass, hobby, also comprising at least any one the hair for above-mentioned 1st speech device and above-mentioned 2nd speech device
Say the hobby of content.
12. session control as claimed in claim 10, which is characterized in that
Above-mentioned hobby judging unit is directed to the sequence of the above-mentioned hobby of above-mentioned topic from high to low according to above-mentioned regulation object will be upper
It states hobby degree and is determined as multiple grades,
Above-mentioned multiple grades of the above-mentioned speech control unit based on the above-mentioned hobby degree of expression determined by above-mentioned hobby judging unit
Information, above-mentioned at least any one the above-mentioned speech of above-mentioned multiple speech devices is controlled.
13. session control as described in claim 1, which is characterized in that
Above-mentioned regulation object includes people, animal or robot.
14. the session control as described in any one of claims 1 to 13, which is characterized in that
It is also equipped with object determination unit, which determines above-mentioned regulation object from mutually different multiple objects,
Above-mentioned reaction acquisition unit obtains multiple reactions and determines as a result, multiple reaction determines in result comprising determining to above-mentioned
Above-mentioned regulation object for above-mentioned 1st speech device speech the result that is determined of reaction and to above-mentioned determination
Above-mentioned regulation object out be directed to it is above-mentioned 1st speech device be mutually provided independently from the 2nd speech device speech react into
Gone determine result.
15. session control as described in claim 1, which is characterized in that
Above-mentioned session control be set to it is above-mentioned 1st and the 2nd speech device at least any one.
16. session control as described in claim 1, which is characterized in that
Above-mentioned session control is mutually provided independently from above-mentioned 1st and the 2nd speech device.
17. a kind of conversational system has the 1st speech device for being configured to speech and the 2nd speech device and dialogue control
Device, which is characterized in that
Above-mentioned session control has:
Acquisition unit is reacted, multiple reactions is obtained and determines as a result, multiple reaction determines in result comprising being directed to regulation object
The result and above-mentioned regulation object is directed to and above-mentioned 1st speech dress that the reaction of the speech of 1st speech device is determined
Set the result that the reaction of the speech for the above-mentioned 2nd speech device being mutually provided independently from is determined；And
Make a speech control unit, based on is obtained by above-mentioned reaction acquisition unit multiple reactions judgement as a result, to comprising the above-mentioned 1st with
And at least any one the above-mentioned speech in the 2nd multiple speech devices including speech device is controlled.
18. conversational system as claimed in claim 17, which is characterized in that
Above-mentioned 1st and the 2nd speech device has respectively:
Acquisition unit obtains at least any of the photographed images of sound and above-mentioned regulation object that above-mentioned regulation object issues
It is a；And
1st communication unit,
Above-mentioned session control is also equipped with for carrying out via above-mentioned 1st communication unit and above-mentioned 1st and the 2nd speech device
2nd communication unit of communication,
The above-mentioned reaction acquisition unit of above-mentioned session control is,
It obtains via above-mentioned 1st communication unit and the 2nd communication unit and is obtained by the above-mentioned acquisition unit of above-mentioned 1st speech device
Above sound and above-mentioned photographed images in above-mentioned at least any one i.e. the 1st data, and the based on above-mentioned acquirement the above-mentioned 1st
Data come determine above-mentioned regulation object for it is above-mentioned 1st speech device above-mentioned speech reaction, thus obtain above-mentioned regulation pair
As for it is above-mentioned 1st speech device above-mentioned speech reaction judgement result the i.e. the 1st reaction determine as a result,
It obtains via above-mentioned 1st communication unit and the 2nd communication unit and is obtained by the above-mentioned acquisition unit of above-mentioned 2nd speech device
Above sound and above-mentioned photographed images in above-mentioned at least any one i.e. the 2nd data, and based on above-mentioned acquirement it is above-mentioned 2nd number
According to come determine above-mentioned regulation object for it is above-mentioned 2nd speech device above-mentioned speech reaction, thus obtain above-mentioned regulation object
For it is above-mentioned 2nd speech device above-mentioned speech reaction judgement result the i.e. the 2nd reaction determine as a result,
The above-mentioned speech control unit of above-mentioned session control based on by above-mentioned reaction acquisition unit obtain comprising the above-mentioned 1st
And the 2nd reaction determine the above-mentioned multiple reactions judgements of result as a result, via above-mentioned 2nd communication unit and the 1st communication unit,
The above-mentioned speech of above-mentioned 1st and the 2nd speech device is controlled.
19. a kind of dialog control method characterized by comprising
The processing that multiple reactions determine result is obtained, multiple reaction determines to include to regulation object in result for the 1st speech
The result and above-mentioned regulation object is directed to mutually only with above-mentioned 1st speech device that the reaction of the speech of device is determined
The result that the reaction of the speech for the 2nd speech device being on the spot arranged is determined；And
Determined based on acquired above-mentioned multiple reactions as a result, to comprising multiple hairs including above-mentioned 1st and the 2nd speech device
The processing that at least any one above-mentioned speech in speech device is controlled.
20. a kind of storage medium, which is characterized in that
Store the program for functioning computer as such as lower unit:
Acquisition unit is reacted, multiple reactions is obtained and determines as a result, multiple reaction determines in result comprising being directed to regulation object
The result and above-mentioned regulation object is directed to and above-mentioned 1st speech dress that the reaction of the speech of 1st speech device is determined
Set the result that the reaction of the speech for the 2nd speech device being mutually provided independently from is determined；And
Make a speech control unit, based on is obtained by above-mentioned reaction acquisition unit multiple reactions judgement as a result, to comprising the above-mentioned 1st with
And at least any one the above-mentioned speech in the 2nd multiple speech devices including speech device is controlled.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2018058200 | 2018-03-26 | ||
| JP2018-058200 | 2018-03-26 | ||
| JP2018-247382 | 2018-12-28 | ||
| JP2018247382A JP2019175432A (en) | 2018-03-26 | 2018-12-28 | Dialogue control device, dialogue system, dialogue control method, and program |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110364164A true CN110364164A (en) | 2019-10-22 |
| CN110364164B CN110364164B (en) | 2023-12-05 |
Family
ID=68167044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910207297.1A Active CN110364164B (en) | 2018-03-26 | 2019-03-19 | Dialogue control device, dialogue system, dialogue control method, and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| JP (3) | JP2019175432A (en) |
| CN (1) | CN110364164B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7407560B2 (en) | 2019-10-30 | 2024-01-04 | 日本放送協会 | Keyword evaluation device, keyword evaluation method, and keyword evaluation program |
| WO2021131737A1 (en) * | 2019-12-27 | 2021-07-01 | ソニーグループ株式会社 | Information processing device, information processing method, and information processing program |
| JP2021144086A (en) * | 2020-03-10 | 2021-09-24 | 株式会社東海理化電機製作所 | Agent system and computer program |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1561514A (en) * | 2001-09-27 | 2005-01-05 | 松下电器产业株式会社 | Dialogue apparatus, dialogue parent apparatus, dialogue child apparatus, dialogue control method, and dialogue control program |
| JP2006178063A (en) * | 2004-12-21 | 2006-07-06 | Toyota Central Res & Dev Lab Inc | Interactive processing device |
| JP2008158697A (en) * | 2006-12-21 | 2008-07-10 | Nec Corp | Robot control device |
| JP2016020963A (en) * | 2014-07-14 | 2016-02-04 | シャープ株式会社 | Interaction evaluation device, interaction evaluation system, interaction evaluation method, and interaction evaluation program |
| JP2016109897A (en) * | 2014-12-08 | 2016-06-20 | シャープ株式会社 | Electronic equipment, speech production control method and program |
| CN106233378A (en) * | 2014-05-13 | 2016-12-14 | 夏普株式会社 | Control device and message output control system |
| CN106484093A (en) * | 2015-09-01 | 2017-03-08 | 卡西欧计算机株式会社 | Session control, dialog control method |
| CN106503030A (en) * | 2015-09-03 | 2017-03-15 | 卡西欧计算机株式会社 | Session control, dialog control method |
| CN106663219A (en) * | 2014-04-17 | 2017-05-10 | 软银机器人欧洲公司 | Methods and systems of handling a dialog with a robot |
| WO2017094212A1 (en) * | 2015-11-30 | 2017-06-08 | ソニー株式会社 | Information processing device, information processing method, and program |
| CN107053186A (en) * | 2015-12-14 | 2017-08-18 | 卡西欧计算机株式会社 | Interface, robot, dialogue method and storage medium |
| JP2017194910A (en) * | 2016-04-22 | 2017-10-26 | Ｃｏｃｏｒｏ Ｓｂ株式会社 | Response data collection system, customer response system, and program |
| WO2017200072A1 (en) * | 2016-05-20 | 2017-11-23 | 日本電信電話株式会社 | Dialog method, dialog system, dialog device, and program |
| WO2017200077A1 (en) * | 2016-05-20 | 2017-11-23 | 日本電信電話株式会社 | Dialog method, dialog system, dialog device, and program |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004021509A (en) | 2002-06-14 | 2004-01-22 | Mitsubishi Heavy Ind Ltd | Information sharing robot |
| JP2004062063A (en) * | 2002-07-31 | 2004-02-26 | Matsushita Electric Ind Co Ltd | Interactive apparatus |
| JP2005099934A (en) * | 2003-09-22 | 2005-04-14 | Konica Minolta Photo Imaging Inc | Robot service system |
| JP2007011674A (en) | 2005-06-30 | 2007-01-18 | National Institute Of Information & Communication Technology | Method for executing service for explaining reason by using interactive robot, device and program thereof |
| JP2015184563A (en) * | 2014-03-25 | 2015-10-22 | シャープ株式会社 | Interactive household electrical system, server device, interactive household electrical appliance, method for household electrical system to interact, and program for realizing the same by computer |
| JP2015219583A (en) | 2014-05-14 | 2015-12-07 | 日本電信電話株式会社 | Topic determination device, utterance device, method, and program |
| JP6555113B2 (en) | 2015-12-14 | 2019-08-07 | 株式会社デンソー | Dialogue device |
| JP2017151517A (en) * | 2016-02-22 | 2017-08-31 | 富士ゼロックス株式会社 | Robot control system |
| JP6380469B2 (en) * | 2016-06-23 | 2018-08-29 | カシオ計算機株式会社 | Robot, robot control method and program |
| JP6767206B2 (en) * | 2016-08-30 | 2020-10-14 | シャープ株式会社 | Response system |
| JP6731598B2 (en) * | 2016-08-31 | 2020-07-29 | Ｊｓｗ株式会社 | Communication device for ornamental fish, communication system for ornamental fish, and communication method with ornamental fish |
-
2018
- 2018-12-28 JP JP2018247382A patent/JP2019175432A/en active Pending
-
2019
- 2019-03-19 CN CN201910207297.1A patent/CN110364164B/en active Active
-
2023
- 2023-02-07 JP JP2023016582A patent/JP7416295B2/en active Active
- 2023-07-21 JP JP2023119290A patent/JP2023133410A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1561514A (en) * | 2001-09-27 | 2005-01-05 | 松下电器产业株式会社 | Dialogue apparatus, dialogue parent apparatus, dialogue child apparatus, dialogue control method, and dialogue control program |
| JP2006178063A (en) * | 2004-12-21 | 2006-07-06 | Toyota Central Res & Dev Lab Inc | Interactive processing device |
| JP2008158697A (en) * | 2006-12-21 | 2008-07-10 | Nec Corp | Robot control device |
| CN106663219A (en) * | 2014-04-17 | 2017-05-10 | 软银机器人欧洲公司 | Methods and systems of handling a dialog with a robot |
| CN106233378A (en) * | 2014-05-13 | 2016-12-14 | 夏普株式会社 | Control device and message output control system |
| JP2016020963A (en) * | 2014-07-14 | 2016-02-04 | シャープ株式会社 | Interaction evaluation device, interaction evaluation system, interaction evaluation method, and interaction evaluation program |
| JP2016109897A (en) * | 2014-12-08 | 2016-06-20 | シャープ株式会社 | Electronic equipment, speech production control method and program |
| CN106484093A (en) * | 2015-09-01 | 2017-03-08 | 卡西欧计算机株式会社 | Session control, dialog control method |
| CN106503030A (en) * | 2015-09-03 | 2017-03-15 | 卡西欧计算机株式会社 | Session control, dialog control method |
| WO2017094212A1 (en) * | 2015-11-30 | 2017-06-08 | ソニー株式会社 | Information processing device, information processing method, and program |
| CN107053186A (en) * | 2015-12-14 | 2017-08-18 | 卡西欧计算机株式会社 | Interface, robot, dialogue method and storage medium |
| JP2017194910A (en) * | 2016-04-22 | 2017-10-26 | Ｃｏｃｏｒｏ Ｓｂ株式会社 | Response data collection system, customer response system, and program |
| WO2017200072A1 (en) * | 2016-05-20 | 2017-11-23 | 日本電信電話株式会社 | Dialog method, dialog system, dialog device, and program |
| WO2017200077A1 (en) * | 2016-05-20 | 2017-11-23 | 日本電信電話株式会社 | Dialog method, dialog system, dialog device, and program |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2023133410A (en) | 2023-09-22 |
| CN110364164B (en) | 2023-12-05 |
| JP2019175432A (en) | 2019-10-10 |
| JP2023055910A (en) | 2023-04-18 |
| JP7416295B2 (en) | 2024-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yon et al. | Precision and the Bayesian brain | |
| US11670324B2 (en) | Method for predicting emotion status and robot | |
| CN110364164A (en) | Session control, conversational system, dialog control method and storage medium | |
| US8538750B2 (en) | Speech communication system and method, and robot apparatus | |
| WO2017145466A1 (en) | Information processing system, client terminal, information processing method, and recording medium | |
| CN100445046C (en) | Robot device and behavior control method for robot device | |
| US7987091B2 (en) | Dialog control device and method, and robot device | |
| CN110119815A (en) | Model training method, device, storage medium and equipment | |
| US8340816B2 (en) | User preference inferring apparatus, user profile inferring apparatus, and robot | |
| EP3623118A1 (en) | Emotion recognizer, robot including the same, and server including the same | |
| JP7400923B2 (en) | Information processing device and information processing method | |
| WO2016080553A1 (en) | Learning robot, learning robot system, and learning robot program | |
| CN107825429A (en) | Interface and method | |
| JP7476941B2 (en) | ROBOT, ROBOT CONTROL METHOD AND PROGRAM | |
| CN109313935B (en) | Information processing system, storage medium, and information processing method | |
| JP2021108142A (en) | Information processing system, information processing method, and information processing program | |
| JP7205148B2 (en) | ROBOT, CONTROL METHOD AND PROGRAM | |
| CN109108962A (en) | Robot, the control method of robot and storage medium | |
| CN110263131A (en) | Return information generation method, device and storage medium | |
| JP6887035B1 (en) | Control systems, control devices, control methods and computer programs | |
| EP3502940A1 (en) | Information processing device, robot, information processing method, and program | |
| CN111931897A (en) | Interaction method, interaction device, electronic equipment and storage medium | |
| CN113952583B (en) | Cognitive training method and system based on VR technology | |
| JP7156300B2 (en) | Information processing device, information processing method, and program | |
| KR20190114931A (en) | Robot and method for controlling the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |