CN109015666A - A kind of intelligent robot - Google Patents
A kind of intelligent robot Download PDFInfo
- Publication number
- CN109015666A CN109015666A CN201810640828.1A CN201810640828A CN109015666A CN 109015666 A CN109015666 A CN 109015666A CN 201810640828 A CN201810640828 A CN 201810640828A CN 109015666 A CN109015666 A CN 109015666A
- Authority
- CN
- China
- Prior art keywords
- emotion
- sentence
- text
- word
- emotional intensity
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0005—Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a kind of intelligent robots, including personnel's detection device, telecontrol equipment and affective interaction device, personnel's detection device obtains ambient condition information for robot, detect whether that there are personnel, the telecontrol equipment controls robot to personnel's movement according to the personal information detected for robot, the affective interaction device carries out affective interaction for robot and personnel, the affective interaction device includes voice acquisition module, text conversion module, emotion recognition module and affective interaction module, the voice acquisition module is used to acquire the voice messaging of user, the text conversion module is used to convert text for voice messaging, the emotion recognition module is used to determine the affective state of text, the affective interaction module is interacted according to the affective state of text with user for robot.The invention has the benefit that providing a kind of intelligent robot, identified by the affective state to user, realizes man-machine emotion and accurately interact.
Description
Technical field
The present invention relates to robotic technology fields, and in particular to a kind of intelligent robot.
Background technique
With the continuous renewal of science and technology, the future of artificial intelligence is put forward new requirements.Meanwhile along with society
Civilization degree be continuously improved, scientific and technological level also improves constantly, and the level of the spiritual civilization of people also constantly improves,
Everything all brings economic fast development, and living standard and quality of life increase substantially.Exactly under this opportunity,
Intelligent robot comes into being.
In Research on Intelligent Robots, researcher only considers the hardware of robot, and the considerations of lack to software environment,
It is easy to ignore the individualized experience of user and affection need, ignores the domestic demand of user.
Summary of the invention
In view of the above-mentioned problems, the present invention is intended to provide a kind of intelligent robot.
The purpose of the present invention is realized using following technical scheme:
Provide a kind of intelligent robot, including personnel's detection device, telecontrol equipment and affective interaction device, the personnel
Detection device obtains ambient condition information for robot, detects whether there are personnel, and the telecontrol equipment is used for robot root
Robot is controlled to personnel's movement according to the personal information detected, and the affective interaction device carries out feelings for robot and personnel
Sense interaction, the affective interaction device includes voice acquisition module, text conversion module, emotion recognition module and affective interaction mould
Block, the voice acquisition module are used to acquire the voice messaging of user, and the text conversion module is for converting voice messaging
For text, the emotion recognition module is used to determine the affective state of text, the affective interaction module for robot according to
The affective state of text is interacted with user.
The invention has the benefit that providing a kind of intelligent robot, identified by the affective state to user,
Man-machine emotion is realized accurately to interact.
Optionally, the emotion recognition module includes word segmentation module, emotion word determining module, emotion word modeling module, language
Sentence affective state determining module, text emotion state determining module, the word segmentation module is for sentence in text to be partitioned into
Word, the emotion word determining module are used to filter out the word of characterization affective characteristics from word as emotion word, the feelings
Sense word modeling module is used to establish the mathematical model of emotion word, and the sentence affective state determining module is used for according to emotion word
Mathematical model determines that the affective state of sentence, the text emotion state determining module are used to determine according to the affective state of sentence
The affective state of text.
Optionally, the emotion word modeling module is used to establish the mathematical model of emotion word, specifically:
By emotion word qnIt indicates, emotion word affective state Z (qn)=[b (qn), c (qn)] indicate, wherein n=1,
2 ..., N, N indicate the quantity of emotion word in sentence, b (qn) indicate emotion word feeling polarities, c (qn) indicate emotion word emotion
Intensity;
The feeling polarities of emotion word specifically: if b (qn)=1, then the emotion word is positive emotion word, if b (qn)=- 1,
Then emotion word is negative sense emotion word;
The emotional intensity of emotion word specifically:c(qn) indicate
Emotion word qnEmotional intensity, c (qn) bigger, indicate that the emotional intensity of emotion word is bigger.
Optionally, the sentence affective state determining module is used to determine the emotion of sentence according to the mathematical model of emotion word
State, specifically:
By sentence pmIt indicates, sentence affective state Z (pm)=[d (pm), e (pm)] indicate, wherein m=1,2 ...,
M, M indicate the quantity of sentence in text, d (pm) indicate sentence feeling polarities, c (qn) indicate sentence emotional intensity;
The feeling polarities of sentence specifically: if the sum of the emotional intensity of positive emotion word is greater than negative sense feelings in sentence in sentence
Feel the sum of the emotional intensity of word, then d (pm)=1, which is positive emotion sentence, if the emotion of positive emotion word is strong in sentence
The sum of degree is less than the sum of the emotional intensity of negative sense emotion word in sentence, then d (pm)=- 1, sentence is negative sense emotion sentence, if language
The sum of the emotional intensity of positive emotion word is equal to the sum of the emotional intensity of negative sense emotion word in sentence in sentence, then d (pm)=0, should
Sentence is neutral emotion sentence;
The emotional intensity of sentence specifically:
In formula, e (pm) indicate sentence pmEmotional intensity, ∑ [c (qn)Just] indicate that the emotion of positive emotion word in sentence is strong
The sum of degree, ∑ [c (qn)It is negative] indicate sentence in negative sense emotion word the sum of emotional intensity;e(pm) bigger, indicate that the emotion of sentence is strong
It spends bigger.
Optionally, the text emotion state determining module is used to determine the emotion shape of text according to the affective state of sentence
State, specifically:
Text is indicated with w, text emotion state is indicated with Z (w)=[f (w), h (w)], wherein f (w) indicates text
Feeling polarities, h (w) indicate the emotional intensity of text;
The feeling polarities of text specifically: if the sum of the emotional intensity of positive emotion sentence is greater than negative sense in text in text
The sum of the emotional intensity of emotion sentence, then f (w)=1, the text are positive emotion text, if positive emotion sentence in text
The sum of emotional intensity is less than the sum of the emotional intensity of negative sense emotion sentence in text, then f (w)=- 1, and text is negative sense emotion text
This, if the sum of the emotional intensity of positive emotion sentence is equal to the sum of the emotional intensity of negative sense emotion sentence in text, f in text
(w)=0, the text is neutral emotion text;
The emotional intensity of text specifically:
In formula, h (w) indicates the emotional intensity of text w, ∑ [e (pm)Just] indicate that the emotion of positive emotion sentence in text is strong
The sum of degree, ∑ [e (pm)It is negative] indicate text in negative sense emotion sentence the sum of emotional intensity;H (w) is bigger, indicates the emotion of text
Intensity is bigger.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is structural schematic diagram of the invention;
Appended drawing reference:
Personnel's detection device 1, telecontrol equipment 2, affective interaction device 3.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of intelligent robot of the present embodiment, including personnel's detection device 1, telecontrol equipment 2 and emotion are handed over
Mutual device 3, personnel's detection device 1 obtain ambient condition information for robot, detect whether there are personnel, the movement
Device 2 controls robot to personnel's movement according to the personal information detected for robot, and the affective interaction device 3 is used for
Robot and personnel carry out affective interaction, and the affective interaction device 3 includes voice acquisition module, text conversion module, emotion
Identification module and affective interaction module, the voice acquisition module are used to acquire the voice messaging of user, and the text converts mould
Block is used to convert voice messaging to text, and the emotion recognition module is used to determine the affective state of text, and the emotion is handed over
Mutual module is interacted according to the affective state of text with user for robot.
A kind of intelligent robot is present embodiments provided, is identified by the affective state to user, is realized man-machine
Emotion accurately interacts.
Preferably, the emotion recognition module includes word segmentation module, emotion word determining module, emotion word modeling module, language
Sentence affective state determining module, text emotion state determining module, the word segmentation module is for sentence in text to be partitioned into
Word, the emotion word determining module are used to filter out the word of characterization affective characteristics from word as emotion word, the feelings
Sense word modeling module is used to establish the mathematical model of emotion word, and the sentence affective state determining module is used for according to emotion word
Mathematical model determines that the affective state of sentence, the text emotion state determining module are used to determine according to the affective state of sentence
The affective state of text;
This preferred embodiment has established base by carrying out screening and founding mathematical models to emotion word, for text emotion identification
Plinth realizes accurately identifying for text emotion.
Preferably, the emotion word modeling module is used to establish the mathematical model of emotion word, specifically:
By emotion word qnIt indicates, emotion word affective state Z (qn)=[b (qn), c (qn)] indicate, wherein n=1,
2 ..., N, N indicate the quantity of emotion word in sentence, b (qn) indicate emotion word feeling polarities, c (qn) indicate emotion word emotion
Intensity;
The feeling polarities of emotion word specifically: if b (qn)=1, then the emotion word is positive emotion word, if b (qn)=- 1,
Then emotion word is negative sense emotion word;
The emotional intensity of emotion word specifically:c(qn) indicate
Emotion word qnEmotional intensity, c (qn) bigger, indicate that the emotional intensity of emotion word is bigger;
This preferred embodiment establishes the mathematical modulo of emotion word by the feeling polarities and emotional intensity of definition emotion word
Type is laid a good foundation for the determination of the affective state of subsequent sentence and text;
The sentence affective state determining module is used to determine the affective state of sentence, tool according to the mathematical model of emotion word
Body are as follows:
By sentence pmIt indicates, sentence affective state Z (pm)=[d (pm), e (pm)] indicate, wherein m=1,2 ...,
M, M indicate the quantity of sentence in text, d (pm) indicate sentence feeling polarities, c (qn) indicate sentence emotional intensity;
The feeling polarities of sentence specifically: if the sum of the emotional intensity of positive emotion word is greater than negative sense feelings in sentence in sentence
Feel the sum of the emotional intensity of word, then d (pm)=1, which is positive emotion sentence, if the emotion of positive emotion word is strong in sentence
The sum of degree is less than the sum of the emotional intensity of negative sense emotion word in sentence, then d (pm)=- 1, sentence is negative sense emotion sentence, if language
The sum of the emotional intensity of positive emotion word is equal to the sum of the emotional intensity of negative sense emotion word in sentence in sentence, then d (pm)=0, should
Sentence is neutral emotion sentence;
The emotional intensity of sentence specifically:
In formula, e (pm) indicate sentence pmEmotional intensity, ∑ [c (qn)Just] indicate that the emotion of positive emotion word in sentence is strong
The sum of degree, ∑ [c (qn)It is negative] indicate sentence in negative sense emotion word the sum of emotional intensity;e(pm) bigger, indicate that the emotion of sentence is strong
It spends bigger;
The text emotion state determining module is used to determine the affective state of text according to the affective state of sentence, specifically
Are as follows:
Text is indicated with w, text emotion state is indicated with Z (w)=[f (w), h (w)], wherein f (w) indicates text
Feeling polarities, h (w) indicate the emotional intensity of text;
The feeling polarities of text specifically: if the sum of the emotional intensity of positive emotion sentence is greater than negative sense in text in text
The sum of the emotional intensity of emotion sentence, then f (w)=1, the text are positive emotion text, if positive emotion sentence in text
The sum of emotional intensity is less than the sum of the emotional intensity of negative sense emotion sentence in text, then f (w)=- 1, and text is negative sense emotion text
This, if the sum of the emotional intensity of positive emotion sentence is equal to the sum of the emotional intensity of negative sense emotion sentence in text, f in text
(w)=0, the text is neutral emotion text;
The emotional intensity of text specifically:
In formula, h (w) indicates the emotional intensity of text w, ∑ [e (pm)Just] indicate that the emotion of positive emotion sentence in text is strong
The sum of degree, ∑ [e (pm)It is negative] indicate text in negative sense emotion sentence the sum of emotional intensity;H (w) is bigger, indicates the emotion of text
Intensity is bigger;
This preferred embodiment is by analyzing the emotion word for constituting sentence, it is determined that the affective state of sentence passes through
The sentence for constituting text is analyzed, it is determined that the affective state of text is laid a good foundation, specifically for accurately identifying for emotion
, text emotion is realized by the feeling polarities and emotional intensity of definition statement and text according to the affective state of emotion word
The accurate acquisition of state.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation for protecting range, although being explained in detail referring to preferred embodiment to the present invention, the ordinary skill destination of this field
It should be appreciated that can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from technical solution of the present invention
Spirit and scope.
Claims (5)
1. a kind of intelligent robot, which is characterized in that described including personnel's detection device, telecontrol equipment and affective interaction device
Personnel's detection device obtains ambient condition information for robot, detects whether there are personnel, and the telecontrol equipment is used for machine
It is mobile to personnel that people according to the personal information that detects controls robot, the affective interaction device for robot and personnel into
Row affective interaction, the affective interaction device include that voice acquisition module, text conversion module, emotion recognition module and emotion are handed over
Mutual module, the voice acquisition module are used to acquire the voice messaging of user, and the text conversion module is used for voice messaging
It is converted into text, the emotion recognition module is used to determine the affective state of text, and the affective interaction module is used for robot
It is interacted according to the affective state of text with user.
2. intelligent robot according to claim 1, which is characterized in that the emotion recognition module include word segmentation module,
Emotion word determining module, emotion word modeling module, sentence affective state determining module, text emotion state determining module, it is described
Word segmentation module is used to for sentence in text being partitioned into word, and the emotion word determining module from word for filtering out characterization
The word of affective characteristics is used to establish the mathematical model of emotion word, the sentence as emotion word, the emotion word modeling module
Affective state determining module is used to determine the affective state of sentence according to the mathematical model of emotion word, and the text emotion state is true
Cover half block is used to determine the affective state of text according to the affective state of sentence.
3. intelligent robot according to claim 2, which is characterized in that the emotion word modeling module is for establishing emotion
The mathematical model of word, specifically:
By emotion word qnIt indicates, emotion word affective state Z (qn)=[b (qn), c (qn)] indicate, wherein n=1,2 ..., N,
N indicates the quantity of emotion word in sentence, b (qn) indicate emotion word feeling polarities, c (qn) indicate emotion word emotional intensity;
The feeling polarities of emotion word specifically: if b (qn)=1, then the emotion word is positive emotion word, if b (qn)=- 1, then feelings
Sense word is negative sense emotion word;
The emotional intensity of emotion word specifically:c(qn) indicate emotion
Word qnEmotional intensity, c (qn) bigger, indicate that the emotional intensity of emotion word is bigger.
4. intelligent robot according to claim 3, which is characterized in that the sentence affective state determining module is used for root
The affective state of sentence is determined according to the mathematical model of emotion word, specifically:
By sentence pmIt indicates, sentence affective state Z (pm)=[d (pm), e (pm)] indicate, wherein m=1,2 ..., M, M table
Show the quantity of sentence in text, d (pm) indicate sentence feeling polarities, c (qn) indicate sentence emotional intensity;
The feeling polarities of sentence specifically: if the sum of the emotional intensity of positive emotion word is greater than negative sense emotion word in sentence in sentence
The sum of emotional intensity, then d (pm)=1, the sentence are positive emotion sentence, if in sentence positive emotion word emotional intensity it
With the sum of the emotional intensity for being less than negative sense emotion word in sentence, then d (pm)=- 1, sentence is negative sense emotion sentence, if in sentence
The sum of emotional intensity of positive emotion word is equal to the sum of the emotional intensity of negative sense emotion word in sentence, then d (pm)=0, the sentence
For neutral emotion sentence;
The emotional intensity of sentence specifically:
In formula, e (pm) indicate sentence pmEmotional intensity, ∑ [c (qn)Just] indicate positive emotion word in sentence emotional intensity it
With ∑ [c (qn)It is negative] indicate sentence in negative sense emotion word the sum of emotional intensity;e(pm) bigger, indicate that the emotional intensity of sentence is got over
Greatly.
5. intelligent robot according to claim 4, which is characterized in that the text emotion state determining module is used for root
The affective state of text is determined according to the affective state of sentence, specifically:
Text is indicated with w, text emotion state is indicated with Z (w)=[f (w), h (w)], wherein the emotion of f (w) expression text
Polarity, h (w) indicate the emotional intensity of text;
The feeling polarities of text specifically: if the sum of the emotional intensity of positive emotion sentence is greater than negative sense emotion in text in text
The sum of emotional intensity of sentence, then f (w)=1, the text are positive emotion text, if in text positive emotion sentence emotion
The sum of intensity is less than the sum of the emotional intensity of negative sense emotion sentence in text, then f (w)=- 1, and text is negative sense emotion text, if
The sum of emotional intensity of positive emotion sentence is equal to the sum of the emotional intensity of negative sense emotion sentence in text in text, then f (w)=
0, the text is neutral emotion text;
The emotional intensity of text specifically:
In formula, h (w) indicates the emotional intensity of text w, ∑ [e (pm)Just] indicate positive emotion sentence in text emotional intensity it
With ∑ [e (pm)It is negative] indicate text in negative sense emotion sentence the sum of emotional intensity;H (w) is bigger, indicates the emotional intensity of text
It is bigger.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810640828.1A CN109015666A (en) | 2018-06-21 | 2018-06-21 | A kind of intelligent robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810640828.1A CN109015666A (en) | 2018-06-21 | 2018-06-21 | A kind of intelligent robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109015666A true CN109015666A (en) | 2018-12-18 |
Family
ID=64609972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810640828.1A Withdrawn CN109015666A (en) | 2018-06-21 | 2018-06-21 | A kind of intelligent robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109015666A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060293874A1 (en) * | 2005-06-27 | 2006-12-28 | Microsoft Corporation | Translation and capture architecture for output of conversational utterances |
CN102178540A (en) * | 2011-03-18 | 2011-09-14 | 北京科技大学 | Three-wheeled omnidirectional mobile control device and auxiliary system for autistic children custody |
CN103456314A (en) * | 2013-09-03 | 2013-12-18 | 广州创维平面显示科技有限公司 | Emotion recognition method and device |
CN105244042A (en) * | 2015-08-26 | 2016-01-13 | 安徽建筑大学 | FSA (Finite State Automaton) based voice emotion interaction device and method |
CN107944008A (en) * | 2017-12-08 | 2018-04-20 | 神思电子技术股份有限公司 | A kind of method that Emotion identification is carried out for natural language |
-
2018
- 2018-06-21 CN CN201810640828.1A patent/CN109015666A/en not_active Withdrawn
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060293874A1 (en) * | 2005-06-27 | 2006-12-28 | Microsoft Corporation | Translation and capture architecture for output of conversational utterances |
CN102178540A (en) * | 2011-03-18 | 2011-09-14 | 北京科技大学 | Three-wheeled omnidirectional mobile control device and auxiliary system for autistic children custody |
CN103456314A (en) * | 2013-09-03 | 2013-12-18 | 广州创维平面显示科技有限公司 | Emotion recognition method and device |
CN105244042A (en) * | 2015-08-26 | 2016-01-13 | 安徽建筑大学 | FSA (Finite State Automaton) based voice emotion interaction device and method |
CN107944008A (en) * | 2017-12-08 | 2018-04-20 | 神思电子技术股份有限公司 | A kind of method that Emotion identification is carried out for natural language |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109117952B (en) | Robot emotion cognition method based on deep learning | |
CN104134060B (en) | Sign language interpreter and display sonification system based on electromyographic signal and motion sensor | |
Hato et al. | Pointing to space: modeling of deictic interaction referring to regions | |
Haasch et al. | A multi-modal object attention system for a mobile robot | |
CN105184058B (en) | A kind of secret words robot | |
CN101527092A (en) | Computer assisted hand language communication method under special session context | |
CN102622085A (en) | Multidimensional sense man-machine interaction system and method | |
CN109767769A (en) | A kind of audio recognition method, device, storage medium and air-conditioning | |
CN112908355B (en) | System and method for quantitatively evaluating teaching skills of teacher and teacher | |
CN105739702A (en) | Multi-posture fingertip tracking method for natural man-machine interaction | |
CN1969781A (en) | Guide for blind person | |
Kania et al. | Translation: Chinese government outlines AI ambitions through 2020 | |
Salvine et al. | Benefits of human-robot interaction [TC Spotlight] | |
CN107578015A (en) | A kind of first impression identification and feedback system and method based on deep learning | |
CN116661603A (en) | Multi-mode fusion user intention recognition method under complex man-machine interaction scene | |
CN115270807A (en) | Method, device and equipment for judging emotional tendency of network user and storage medium | |
CN109015666A (en) | A kind of intelligent robot | |
Flutura et al. | MobileSSI: Asynchronous fusion for social signal interpretation in the wild | |
CN108875025A (en) | A kind of smart home emotion interactive system | |
CN115147248B (en) | Travel information consultation system and method based on big data | |
CN115527404A (en) | Artificial intelligence self-adaptation interactive teaching system | |
Jokinen et al. | Embodied communicative activity in cooperative conversational interactions-studies in visual interaction management | |
CN114758676A (en) | Multi-modal emotion recognition method based on deep residual shrinkage network | |
CN115167674A (en) | Intelligent interaction method based on digital human multi-modal interaction information standard | |
Wu et al. | Energy efficient graph-based hybrid learning for speech emotion recognition on humanoid robot |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181218 |
|
WW01 | Invention patent application withdrawn after publication |