CN106202238A - Real person's analogy method - Google Patents
Real person's analogy method Download PDFInfo
- Publication number
- CN106202238A CN106202238A CN201610496193.3A CN201610496193A CN106202238A CN 106202238 A CN106202238 A CN 106202238A CN 201610496193 A CN201610496193 A CN 201610496193A CN 106202238 A CN106202238 A CN 106202238A
- Authority
- CN
- China
- Prior art keywords
- module
- tone color
- object model
- answer
- model
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
Abstract
The present invention provides a kind of real person's analogy method, comprises the steps: according to portrait photographs by Software Create 3D character data model, and is printed stereo man object model by 3D printer;Implanting electronic module inside described stereo man object model, it includes wireless network module, question and answer robot module, tone color matching module;The external voice that the microphone module being built in stereo man object model is collected by question and answer robot, is uploaded to the webserver by wireless network module, and the language of answering fed back by the webserver is broadcasted by loudspeaker module;The voice color of answering of question and answer robot can be set to the tone color same or like with the real personage corresponding to this stereo man object model by tone color matching module.The method can retain the current stereoscopic pattern of personage and tone color, and descendant can be made to exchange therewith, as exchanged with previous true man, makes the sense of reality of person model be greatly improved.
Description
Technical field
The present invention relates to personage and regard as memory technical field, especially, relate to personage's stereomodel manufacture technology field.
Background technology
In actual life, it is generally desirable that keep each fine moment here, or the apperance of all age group;To this end,
In early days, commonly used photographic means, the fragment retained desired by this kind of people is retained by photo.Along with the development of technology,
At present in addition to photo, the mode of the most commonly used video shoot retains slice of life;Relative to photo, video segment more has concurrently
The sound of personage and action, more can give deep impression.But, this kind of photo and video are Flat-picture, it is difficult to
Presenting figure image in real space outside screen, its reality sense has been short of;On the other hand, this kind of picture is only to life
The direct record of fragment, and entirely without interaction between beholder, the sense of reality of personage is the most not enough.
Also having a kind of 3D camera technique at present, computed in software is drawn by main employing 3D printer, or 3D scanner
Personage's stereomodel that scanning obtains prints;Thus form the stereo man object model that can be placed in three-dimensional realistic space,
The reality sense of this kind of person model is slightly stronger according to sheet, but still does not has any interaction, and sense of reality is the most not enough.
Summary of the invention
For the problems referred to above, it is an object of the invention to provide a kind of real person's analogy method, the method can retain
Stereoscopic pattern that personage is current and tone color, and descendant can be made to exchange therewith, as exchanged with previous true man, make personage's mould
The sense of reality of type is greatly improved.
The technical solution adopted for the present invention to solve the technical problems is: this real person's analogy method includes walking as follows
Rapid:
One, according to portrait photographs by Software Create 3D character data model, or directly scanned by 3D scanner and obtain 3D personage's number
According to model;And printed stereo man object model by 3D printer;Or used potter's clay to pinch into solid according to portrait photographs by technician
Person model;
Two, implanting electronic module inside described stereo man object model, described electronic module includes wireless network module, interrogator
Device people's module, tone color matching module;The microphone module being built in stereo man object model is gathered by described question and answer robot
The external voice arrived, is uploaded to the webserver by described wireless network module, and the webserver is fed back answer language
Broadcasted by the loudspeaker module being built in stereo man object model;Described tone color matching module can be by described question and answer robot
Answer voice color and be set to the tone color same or like with the real personage corresponding to this stereo man object model.
As preferably, described tone color matching module is that tone color selects module, and it includes bank, by user directly at this sound
Color storehouse is selected a tone color close with the real personage corresponding to this stereo man object model;The program is convenient to operate and makes
With.Further, in described bank, each tone color shows with the form reading aloud one section of fixed text.
As preferably, described tone color matching module is tone color training module;Described tone color training module can include following two
Kind of training program: one, allow user read aloud more than one section fixing text, the vocal print feature of crawl declaimer, and set up tone color
Model;Two, allowing user read aloud pinyin table, record user is for the pronunciation of each phonetic;And described question and answer robot is answered in broadcast
During language, for answering each word in language, the pronunciation of user is used to combine into syllables.
As preferably, in the webserver corresponding to described question and answer robot, it is additionally provided with a character and module is set, institute
State personality to arrange module and can arrange N kind personality, and the described webserver process not there is the problem determining answer time, generate
The N kind corresponding with described N kind personality answers language, and the personality phase only set with user to described question and answer robot module feedback
That of coupling answers language.
The beneficial effects of the present invention is: the stereo man object model that this real person's analogy method is provided, not only retain
The stereo man figure image that can be arbitrarily placed in realistic space, and remain the tone color of this personage, can directly enter with it
Row interactive voice, as exchanged with true man, its verity is extremely strong, is respectively provided with significantly in souvenir mode and technological means
Breakthrough development.
Detailed description of the invention
Below the present invention is described in further detail:
Real person's analogy method that the present invention provides comprises the steps:
One, according to portrait photographs by Software Create 3D character data model;This kind of software is more, usually, by one just at present
Face, according to generating the 3D person model more alike with true man, if being shone and one or two side photographs by a front, then generates
3D person model and true man similarity further.The method is suitable for remote service, and e.g., service provider can directly be carried by client
The photo of confession is that it generates 3D person model, thus forms huge market.
Or can also directly be scanned by 3D scanner and obtain 3D character data model;Personage's mould obtained by this kind of mode
Type similarity is high, but is often suitable only for Site Service, i.e. solid shop/brick and mortar store service, and its market is limited by bigger space.
After obtaining 3D character data model by above method, 3D printer print stereo man object model.For non-
Full-color 3D printer, after printing stereo man object model, also should paint to model;And full-color 3D is printed
Machine, can directly print the appearance color of stereo man object model.
Two, implanting electronic module inside described stereo man object model, described electronic module includes wireless network module, asks
Answer robot module, tone color matching module;The microphone module institute that described question and answer robot will be built in stereo man object model
The external voice collected, is uploaded to the webserver by described wireless network module, and the webserver is fed back
Answer language to be broadcasted by the loudspeaker module being built in stereo man object model.The current kind of this kind of question and answer robot is more, as
Siri, worm hole etc., process voice response business the most in the above described manner.
The voice color of answering of described question and answer robot can be set to and this stereo man object model institute by described tone color matching module
The tone color that corresponding real personage is same or like.
Specifically, described tone color matching module can use the following two kinds module:
1, tone color selects module, and it includes bank, user directly select one and this solid personage's mould in this bank
The tone color that real personage corresponding to type is close;In described bank, each tone color shows with the form reading aloud one section of fixed text
Come.The program is easy to operate and use, for the most commonly used mode.
2, tone color training module;Described tone color training module can include the following two kinds training program:
One, allow user read aloud more than one section fixing text, capture the vocal print feature of declaimer, and set up tone color model.Should
Mode is the most universal tone color training method, and its shortcoming is that the tone color set up is the highest with actual tone color similarity.
Two, allowing user read aloud pinyin table, record user is for the pronunciation of each phonetic;And described question and answer robot is broadcasting
When answering language, for answering each word in language, the pronunciation of user is used to combine into syllables.Which is first in the design process of the present invention
Secondary proposition, advantage is the most obvious: firstly, since the phonetic quantity in pinyin table is extremely limited so that training process is the most brief;
Secondly, the pronunciation of user's typing covers the pronunciation of all words, and all words can be made to read with the real speech of user all completely
Going out, the tone color that question and answer robot module is broadcasted is the most completely the same with actual tone color similarity.
It addition, in the webserver corresponding to described question and answer robot module, be additionally provided with a character and arrange module, institute
State personality to arrange module and can arrange N kind personality, and the described webserver process not there is the problem determining answer time, e.g.,
For emotion class problem, or sex chromosome mosaicism of talking in professional jargon, generate the N kind corresponding with described N kind personality and answer language, and only ask to described
That answers that the personality that robot module's feedback and user set matches that answers language.So that the appearance of this stereo man object model,
Tone color, personality are all consistent with corresponding real personage, talk with it, and the most close with true man's dialogue.
The stereo man object model that above-mentioned real person's analogy method is provided, not only remains and can arbitrarily be placed in reality sky
Stereo man figure image between, and remain the tone color of this personage, directly can carry out interactive voice with it, as with true man
Exchange is general, and its verity is extremely strong, is respectively provided with obvious breakthrough development in souvenir mode and technological means;Just think, we
Can in realistic space with oneself exchanging Face to face when childhood or time juvenile, or face-to-face with late ancestor
Exchange, this kind of experience is the most extraordinary, has thoroughly overturned traditional mode cherishing the memory of the past.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all spirit in the present invention and
Within principle, any amendment of being made, equivalent, should be included within the scope of the present invention.
Claims (6)
1. real person's analogy method, it is characterised in that: comprise the steps:
One, according to portrait photographs by Software Create 3D character data model, or directly scanned by 3D scanner and obtain 3D personage's number
According to model;And printed stereo man object model by 3D printer;Or used potter's clay to pinch into solid according to portrait photographs by technician
Person model;
Two, implanting electronic module inside described stereo man object model, described electronic module includes wireless network module, interrogator
Device people's module, tone color matching module;The microphone module being built in stereo man object model is gathered by described question and answer robot
The external voice arrived, is uploaded to the webserver by described wireless network module, and the webserver is fed back answer language
Broadcasted by the loudspeaker module being built in stereo man object model;Described tone color matching module can be by described question and answer robot
Answer voice color and be set to the tone color same or like with the real personage corresponding to this stereo man object model.
Real person's analogy method the most according to claim 1, it is characterised in that: described tone color matching module is tone color choosing
Selecting module, it includes bank, by user directly select in this bank one with this stereo man object model corresponding to show
The tone color that real personage is close.
Real person's analogy method the most according to claim 2, it is characterised in that: in described bank, each tone color is to read aloud
The form of one section of fixed text shows.
Real person's analogy method the most according to claim 1, it is characterised in that: described tone color matching module is tone color instruction
Practice module;Described tone color training module includes following training method: allowing user read aloud more than one section fixing text, crawl is read aloud
The vocal print feature of person, and set up tone color model.
Real person's analogy method the most according to claim 1, it is characterised in that: described tone color matching module is tone color instruction
Practice module;Described tone color training module includes following training method: allowing user read aloud pinyin table, record user is for each phonetic
Pronunciation;And described question and answer robot is when language is answered in broadcast, for answering each word in language, the pronunciation of user is used to combine into syllables.
Real person's analogy method the most as claimed in any of claims 1 to 5, it is characterised in that: described interrogator
In the webserver corresponding to device people, being additionally provided with a character and arrange module, described personality arranges module can arrange N kind
Lattice, and the described webserver is not when process has the problem determining answer, generates the N kind corresponding with described N kind personality
Answer language, and the personality only set to described question and answer robot module feedback and user match that answer language.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610496193.3A CN106202238A (en) | 2016-06-30 | 2016-06-30 | Real person's analogy method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610496193.3A CN106202238A (en) | 2016-06-30 | 2016-06-30 | Real person's analogy method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106202238A true CN106202238A (en) | 2016-12-07 |
Family
ID=57462614
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610496193.3A Pending CN106202238A (en) | 2016-06-30 | 2016-06-30 | Real person's analogy method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106202238A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106649746A (en) * | 2016-12-26 | 2017-05-10 | 北京云知声信息技术有限公司 | Answer acquisition method and device |
CN106649752A (en) * | 2016-12-26 | 2017-05-10 | 北京云知声信息技术有限公司 | Answer acquisition method and device |
CN108073112A (en) * | 2018-01-19 | 2018-05-25 | 福建捷联电子有限公司 | A kind of intelligent Service humanoid robot with role playing |
CN110265021A (en) * | 2019-07-22 | 2019-09-20 | 深圳前海微众银行股份有限公司 | Personalized speech exchange method, robot terminal, device and readable storage medium storing program for executing |
WO2022227188A1 (en) * | 2021-04-27 | 2022-11-03 | 平安科技(深圳)有限公司 | Intelligent customer service staff answering method and apparatus for speech, and computer device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101000765A (en) * | 2007-01-09 | 2007-07-18 | 黑龙江大学 | Speech synthetic method based on rhythm character |
CN204337737U (en) * | 2014-12-02 | 2015-05-20 | 湖南化身科技有限公司 | The three-dimensional portrait product of personalized head portrait |
CN105427855A (en) * | 2015-11-09 | 2016-03-23 | 上海语知义信息技术有限公司 | Voice broadcast system and voice broadcast method of intelligent software |
CN105551493A (en) * | 2015-11-30 | 2016-05-04 | 北京光年无限科技有限公司 | Method and device of data processing of children voice robot and children voice robot |
-
2016
- 2016-06-30 CN CN201610496193.3A patent/CN106202238A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101000765A (en) * | 2007-01-09 | 2007-07-18 | 黑龙江大学 | Speech synthetic method based on rhythm character |
CN204337737U (en) * | 2014-12-02 | 2015-05-20 | 湖南化身科技有限公司 | The three-dimensional portrait product of personalized head portrait |
CN105427855A (en) * | 2015-11-09 | 2016-03-23 | 上海语知义信息技术有限公司 | Voice broadcast system and voice broadcast method of intelligent software |
CN105551493A (en) * | 2015-11-30 | 2016-05-04 | 北京光年无限科技有限公司 | Method and device of data processing of children voice robot and children voice robot |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106649746A (en) * | 2016-12-26 | 2017-05-10 | 北京云知声信息技术有限公司 | Answer acquisition method and device |
CN106649752A (en) * | 2016-12-26 | 2017-05-10 | 北京云知声信息技术有限公司 | Answer acquisition method and device |
CN108073112A (en) * | 2018-01-19 | 2018-05-25 | 福建捷联电子有限公司 | A kind of intelligent Service humanoid robot with role playing |
CN108073112B (en) * | 2018-01-19 | 2024-02-20 | 冠捷电子科技(福建)有限公司 | Intelligent service type robot with role playing function |
CN110265021A (en) * | 2019-07-22 | 2019-09-20 | 深圳前海微众银行股份有限公司 | Personalized speech exchange method, robot terminal, device and readable storage medium storing program for executing |
WO2022227188A1 (en) * | 2021-04-27 | 2022-11-03 | 平安科技(深圳)有限公司 | Intelligent customer service staff answering method and apparatus for speech, and computer device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106202238A (en) | Real person's analogy method | |
Dockett et al. | Children's drawings: Experiences and expectations of school | |
US20100141662A1 (en) | Communication network and devices for text to speech and text to facial animation conversion | |
CN107798931A (en) | A kind of intelligent children education learning system and method | |
JP5802911B2 (en) | Photo game machine | |
WO2021012491A1 (en) | Multimedia information display method, device, computer apparatus, and storage medium | |
Galer | Photography Foundations for Art and Design: The creative photography handbook | |
CN110505405A (en) | Video capture system and method based on body-sensing technology | |
CN117156199A (en) | Digital short-man video production platform and production method thereof | |
CN212847226U (en) | Immersive scene practical training system | |
TW580652B (en) | Multimedia language learning system and method with assistance of graphic profile using touch panel | |
JP2013041273A (en) | Photography game device | |
JP2006339951A (en) | Device, method and program for automatic photography | |
Karlholm | Developing the picture: Wölfflin's performance art | |
D’armenio | The mediatic dimension of images: visual semiotics faced with Gerhard Richter’s artwork | |
Baron | Lessons from Venice: Authenticity, emotions, and ICTs | |
Haas | Writer's groups for MA ESOL students: Collaboratively constructing a model of the writing process | |
KR102318683B1 (en) | Creative education system that generates video from picture | |
Morrison-Low | Brewster, Talbot and the Adamsons: The arrival of photography in St Andrews | |
KR20180037873A (en) | Assembly type block with picture and manufacturing method thereof | |
Ochi et al. | The report on developing a prototype system of interactive multi-language stories for children and their preference of its interface | |
JP5904474B2 (en) | Image editing system | |
Gilmore | Large Direct Heads: Robert Crawshay’s Dream of Life-Size Photography | |
Yang | Comeback and Development of Large Format Photography in the Era of Digital Photography | |
JP5440992B2 (en) | Photo shooting device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |