CN108804698A - Man-machine interaction method, system, medium based on personage IP and equipment - Google Patents
Man-machine interaction method, system, medium based on personage IP and equipment Download PDFInfo
- Publication number
- CN108804698A CN108804698A CN201810623329.1A CN201810623329A CN108804698A CN 108804698 A CN108804698 A CN 108804698A CN 201810623329 A CN201810623329 A CN 201810623329A CN 108804698 A CN108804698 A CN 108804698A
- Authority
- CN
- China
- Prior art keywords
- personage
- user
- information
- knowledge mapping
- input
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of man-machine interaction method, system, medium and equipment based on personage IP.The method of the present invention, including：Obtain the input information of user；Extract the input entity for including in the input information；User view is identified according to the input information；According to the input entity and user view, based on the knowledge mapping pre-established, the return information for image with preset acquiescence personage IP is generated；It is image with the acquiescence personage IP, the return information is exported to user.The personality that robot humanoid can be assigned is made the specific personage IP of robot simulation, is interacted with user with the identity of specific personage IP, more targetedly respond user；And the personage's custom for considering personage IP, makes that robot is more intelligent, personalizes, is preferably interacted with user, can improve user experience.
Description
Technical field
The present invention relates to field of artificial intelligence, and in particular to a kind of man-machine interaction method based on personage IP, system,
Medium and equipment.
Background technology
In the prior art, robot is by being retrieved in existing dialogue library when replying user's input
Similar question sentence is inputted with user, then using the corresponding answer of the question sentence as to reply input by user；Or by using
The intelligent algorithms such as machine learning, deep learning, RNN, by the way that existing dialogue data to be labeled, as artificial intelligence
The input of algorithm is trained intelligent algorithm to obtain training pattern, which can be after obtaining user's newly input, certainly
The dynamic reply generated to user, there is no the individual characteies for considering robot, and user, user experience cannot be replied in a manner of personalizing
It is poor.
Invention content
For the defects in the prior art, the present invention provides a kind of man-machine interaction method, system, medium based on personage IP
And equipment, the personality of robot humanoid can be assigned, makes the specific personage IP of robot simulation, with the identity and use of specific personage IP
Family interacts, and more targetedly responds user；And the personage's custom for considering personage IP, keeps robot more intelligent
Change, personalize, preferably interacted with user, user experience can be improved.
In a first aspect, the present invention provides a kind of man-machine interaction methods based on personage IP, including：
Obtain the input information of user；
Extract the input entity for including in the input information；
User view is identified according to the input information；
According to the input entity and user view, based on the knowledge mapping pre-established, generate with preset silent
The object IP that recognizes people is the return information of image；
It is image with the acquiescence personage IP, the return information is exported to user.
Preferably, the knowledge mapping, including：Using knowledge mapping of the person names as core node for giving tacit consent to personage IP
And/or world knowledge collection of illustrative plates.
Preferably, it is generated based on the knowledge mapping pre-established to set in advance according to the input entity and user view
Fixed acquiescence personage IP is the return information of image, including：
The input entity is associated with the entity in the knowledge mapping；
From the knowledge mapping, extraction and the input entity and the relevant knowledge mapping subgraph of user view；
According to the knowledge mapping subgraph and syntax rule, the reply for image with preset acquiescence personage IP is generated
Information.
Preferably, it according to the knowledge mapping subgraph and syntax rule, generates using preset acquiescence personage IP as shape
The return information of elephant, including：
According to the knowledge mapping subgraph and syntax rule, original return information corresponding with the input information is generated；
According to the weight of the historical data of storage and the user view, acquiescence personage IP is calculated in current scene, often
Kind personage is accustomed to the confidence level occurred；
According to the confidence level, the reasonable personage custom of current scene is determined；
According to reasonable personage's custom and syntax rule, the original return information is processed, is generated with advance
The acquiescence personage IP set is the return information of image.
Preferably, further include：
Obtain personage IP change directives input by user；
According to the change directive, it sets personage IP to new persona IP from acquiescence personage IP；
The corresponding new knowledge collection of illustrative plates of the new persona IP is transferred from database；
Human-computer interaction is carried out according to the new knowledge collection of illustrative plates and user.
Preferably, the knowledge mapping of at least one personage IP is stored in the database.
Preferably, the return information, including：Voice-response information and/or action response information.
Second aspect, a kind of man-machine interactive system based on personage IP provided by the invention, including：
Data obtaining module, the input information for obtaining user；
Entity extraction module, for extracting the input entity for including in the input information；
Intention assessment module, for identifying user view according to the input information；
Generation module is replied, is used for according to the input entity and user view, it is raw based on the knowledge mapping pre-established
At the return information with preset acquiescence personage IP for image；
Message output module exports the return information for being image with the acquiescence personage IP to user.
Preferably, the knowledge mapping, including：Using knowledge mapping of the person names as core node for giving tacit consent to personage IP
And/or world knowledge collection of illustrative plates.
Preferably, generation module is replied, including：Associative cell, for will be in the input entity and the knowledge mapping
Entity be associated；Extraction unit, for from the knowledge mapping, extraction to be related to the input entity and user view
Knowledge mapping subgraph；Information generating unit, for according to the knowledge mapping subgraph and syntax rule, generating to preset
Acquiescence personage IP be image return information.
Preferably, information generating unit, including：Raw information generates subelement, for according to the knowledge mapping subgraph
And syntax rule, generate original return information corresponding with the input information；Confidence calculations subelement, for according to storage
Historical data weight and the user view, calculate acquiescence personage IP in current scene, each personage be accustomed to occur
Confidence level；It is accustomed to determination subelement, for according to the confidence level, determining the reasonable personage custom of current scene；Information generates
Subelement, for according to reasonable personage's custom and syntax rule, being processed, being generated with pre- to the original return information
The acquiescence personage IP first set is the return information of image.
Preferably, further include：Instruction acquisition module, for obtaining personage IP change directives input by user；Module is changed,
For according to the change directive, setting personage IP to new persona IP from acquiescence personage IP；Knowledge mapping transfers module, is used for
The corresponding new knowledge collection of illustrative plates of the new persona IP is transferred from database；Interactive module, for according to the new knowledge collection of illustrative plates with
User carries out human-computer interaction.
Preferably, the knowledge mapping of at least one personage IP is stored in the database.
Preferably, the return information, including：Voice-response information and/or action response information.
A kind of third aspect, computer readable storage medium provided by the invention, is stored thereon with computer program, the journey
A kind of man-machine interaction method based on personage IP in first aspect is realized when sequence is executed by processor.
Fourth aspect, a kind of human-computer interaction device based on personage IP provided by the invention, including：Memory, processor
And storage is on a memory and the computer program that can run on a processor, when processor execution described program, realizes the
A kind of man-machine interaction method based on personage IP in one side.
Man-machine interaction method provided in an embodiment of the present invention based on personage IP is carried by obtaining the input information of user
The input entity for including in input information is taken, user view is identified according to input information, further according to input entity and user view,
Based on the knowledge mapping pre-established, generate with the return information that preset acquiescence personage IP is image, finally with acquiescence
Personage IP is image, and return information is exported to user.The personality that robot humanoid can be assigned makes the specific personage of robot simulation
IP is interacted with user with the identity of specific personage IP, more targetedly responds user；And consider the people of personage IP
Object is accustomed to, and makes that robot is more intelligent, personalizes, and is preferably interacted with user, can improve user experience.
A kind of man-machine interactive system, a kind of computer readable storage medium and one kind based on personage IP provided by the invention
Based on the human-computer interaction device of personage IP, with a kind of above-mentioned man-machine interaction method based on personage IP for identical invention structure
Think, advantageous effect having the same.
Description of the drawings
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described.In all the appended drawings, similar element
Or part is generally identified by similar reference numeral.In attached drawing, each element or part might not be drawn according to actual ratio.
Fig. 1 is a kind of flow chart of the man-machine interaction method based on personage IP provided by the invention；
Fig. 2 is a kind of schematic diagram of the man-machine interactive system based on personage IP provided by the invention.
Specific implementation mode
The embodiment of technical solution of the present invention is described in detail below in conjunction with attached drawing.Following embodiment is only used for
Clearly illustrate technical scheme of the present invention, therefore be intended only as example, and the protection of the present invention cannot be limited with this
Range.
It should be noted that unless otherwise indicated, technical term or scientific terminology used in this application should be this hair
The ordinary meaning that bright one of ordinary skill in the art are understood.
The present invention provides a kind of man-machine interaction method, system, medium and equipment based on personage IP.Below in conjunction with the accompanying drawings
The embodiment of the present invention is illustrated.
The present invention executive agent be chat robots, robot manufacture when can be provided with acquiescence personage IP, when with
When using robot, robot can be interacted as image with user using giving tacit consent to personage IP at family.The present invention can be adapted to
Bean vermicelli group, meets user demand.
Referring to FIG. 1, Fig. 1 is a kind of stream for man-machine interaction method based on personage IP that the specific embodiment of the invention provides
Cheng Tu, a kind of man-machine interaction method based on personage IP provided in this embodiment, including：
Step S101：Obtain the input information of user.
Wherein, the input information of user can be voice input information, word input information, button operation input information etc.
In it is one or more, this is all within the scope of the present invention.
Step S102：Extract the input entity for including in the input information.
After getting input information, need input information being converted to word input information；If the input got
Information is word input information, then need not be converted.
In the input entity for including in extracting input information, including following steps：
Input information is converted to word input information by the first step；
Second step carries out participle operation using natural language understanding method to word input information；
Third walks, and using entity alignment thereof, each word after participle is aligned with entity；
4th step identifies the entity in word, and extract the entity using disambiguation, extensive technology, as input entity.
Input entity can be accurately extracted by this method, and then more rational return information can be generated, more preferably
Ground is interacted with user.
Step S103：User view is identified according to the input information.
Identify that the process of user view is according to input information：
The input entity in input information is extracted, it is identical as the method for step S102；
Identify the sentence pattern of input information；When identifying sentence pattern, can be identified using conventional rules；
According to the sentence pattern of the input entity and input information of extraction, user view is identified.
When identifying user view according to input entity and sentence pattern, machine learning method, rule and slot filling may be used
The methods of, to identify that user view, any applicable conventional technical means may serve to identification user view.Here and it is unlimited
Fixed specific user view recognition methods.
Step S104：It is generated with advance based on the knowledge mapping pre-established according to the input entity and user view
The acquiescence personage IP set is the return information of image.
Wherein, the knowledge mapping, including：Using give tacit consent to the person names of personage IP as the knowledge mapping of core node and/
Or world knowledge collection of illustrative plates.
According to input entity and user view, may be used also before generating return information based on the knowledge mapping pre-established
To include：
Knowledge mapping is established, including：It establishes using the person names of personage IP as the knowledge mapping of core node and general
Knowledge mapping.Wherein, the knowledge mapping of the personage IP of foundation may include the knowledge mapping of multiple personage IP.For each personage
IP can establish multiple knowledge mappings, can also establish a knowledge mapping.World knowledge collection of illustrative plates can also there are one or it is more
A, this is all within the scope of the present invention.In the present invention, the executive agent for establishing knowledge mapping can be server-side.
When establishing using the person names of personage IP as the knowledge mapping of core node, including：Acquire the personage of personage IP
Information；According to people information, establish using corresponding person names as the knowledge mapping of core node.
Specifically the process of establishing of the knowledge mapping of personage IP is：
Personage's knowledge mapping framework is set；Determine personage IP；The people information for acquiring personage IP, according to people information and people
Object knowledge mapping framework is established using corresponding person names as the knowledge mapping of core node.
Wherein, personage IP refers to particular persons image, can be star personage.For example, the personages IP such as user A, user B.
Personage's knowledge mapping framework refers to the knowledge mapping framework using person names as core node.
Wherein, people information may include：The objective information of personage, habits information, event information, subjective attitude information
Deng.
Wherein, objective information, including：Alias/the pet name, gender, date of birth, occupation, speciality, faith, hobby, appearance are special
Point, microblogging account, number of fans, works (and the broadcasting time of works, number, Time To Market, specific role, other participants
Member), social relationships (friend, love and marriage relationship, love and marriage relationship before) etc..
Habits information, including：Human dialog habits information and figure action habits information.
Event information refer to personage did whithin a period of time some have record meaning thing.
Attitude and viewpoint that subjective attitude information, which refers to personage, holds something etc..
Human dialog habits information, including：Word custom, clause custom, pronunciation custom, tone custom etc..
Figure action habits information refers to the habitual movement of personage usually, for example, sealing mouth, getting to know, rub hands.
Above-mentioned people information includes all information for the personage being collected into from each channel, for example, can be by direct
There is provided existing knowledge mapping, web search extracts, the modes such as extraction obtain information from interview.
After obtaining people information, it can be built using person names as core according to people information and personage's knowledge mapping framework
The knowledge mapping of heart node.In structure, people information is classified and stored according to personage's knowledge mapping framework.For example,
Human dialog library, maneuver library etc. can be established.In this way, the convenient input information for subsequently responding user according to knowledge mapping.
Wherein, in human dialog library include the existing conversation content of personage, such as on the way from webpage, films and television programs, interview
The audio and video of human dialog, question and answer that diameter obtains, so extract from audio and video dialogue content and group of text at dialogue library.
The maneuver library of personage is used to help the action that cyberchat robot imitates personage.Maneuver library includes：Whole section of personage's dancing
Video, personage are taken part in a performance the action segment of movie and television play, the daily typical habits sexual act segment of personage etc..
Dialogue library and maneuver library can also be stored in the form of triple in knowledge mapping.For example, personage IP is personage
A, the triplet format in the corresponding dialogue libraries mark personage IP is in knowledge mapping<Personage A talks with library,
"DialogDatabase123055601">, wherein DialogDatabase123055601 indicates the corresponding dialogue libraries personage A
ID can talk with the index in library as personage A, the dialogue library of personage A can be found by the index.
After the knowledge mapping of structure perfect person's object IP, the figural fresh information can be acquired in real time；According to institute
Fresh information is stated, the knowledge mapping for the corresponding personage IP that timely updates.In such manner, it is possible to generate more accurate return information, in turn
Improve user experience.
Wherein, fresh information refers to the information of people information change.It can be pushed away according to information, news, the system on network
The knowledge mapping for the personage IP that timely updates such as send.
Server-side can establish the knowledge mapping using person names as core node, be provided and personage IP for chat robots
Corresponding knowledge mapping, and then chat robots can be made to be interacted with particular persons IP and user, it can be carried for user
For more targeted, accurate return information, the case where giving an irrelevant answer can be reduced, and then user experience can be improved.
In the present invention, world knowledge collection of illustrative plates is for storing some well known knowledge.It is first when establishing world knowledge collection of illustrative plates
First, it needs to obtain common knowledge；Then, according to common knowledge, world knowledge collection of illustrative plates is established.
In the present invention, the structure of different knowledge mappings is with uniformity, meets general definition and the knot of knowledge mapping
Structure.
In knowledge mapping, this ternary relation is generally formally indicated with RDF.RDF(Resource
Description Framework), i.e. resource description framework is the normal data for describing entities/resources that W3C is formulated
Model.The entity and their attribute that knowledge mapping is connected with each other by some are constituted, and simple to understand, knowledge mapping is by a rule
Knowledge forms, and every representation of knowledge is a SPO triple (Subject-Predicate-Object).
After having established knowledge mapping, knowledge mapping can be stored in the storage device carried to robot, it can also
By in knowledge mapping storage to the database of remote server or Cloud Server, knowledge mapping if necessary is not stored in
In included storage device, then corresponding knowledge mapping can be transferred from database temporarily with user interaction process.
After having established knowledge mapping, according to the input entity and user view, based on the knowledge mapping pre-established,
It generates with the return information that preset acquiescence personage IP is image, including：By the input entity and the knowledge mapping
In entity be associated；From the knowledge mapping, extraction and the input entity and the relevant knowledge mapping of user view
Subgraph；According to the knowledge mapping subgraph and syntax rule, generates and believed with the reply that preset acquiescence personage IP is image
Breath.
The generating process of return information：
Inputting the process that entity is associated with the entity in knowledge mapping is：Entity and the reality in knowledge mapping will be inputted
Body is compared, and identical entity or similar entities are associated.
After association, corresponding multiple triples can be directly extracted, can also be regenerated newly according to associated triple
Triple, and store, and then obtain and the input relevant multiple triples of entity.
Again from knowledge mapping with input the relevant triple of entity in, extraction with the relevant triple of user view, group
At knowledge mapping subgraph.
Finally, according to knowledge mapping subgraph and syntax rule, by the triple in knowledge mapping subgraph according to syntax rule
It split, combined, generate the return information for image with preset acquiescence personage IP.
According to the return information that the process generates, the input information of user can be met well, targetedly carried out
It replies.
In a specific embodiment provided by the invention, according to the knowledge mapping subgraph and syntax rule, generate with
Preset acquiescence personage IP is the return information of image, including：According to the knowledge mapping subgraph and syntax rule, generate
Original return information corresponding with the input information；According to the weight of the historical data of storage and the user view, calculate
Personage IP is given tacit consent in current scene, each personage is accustomed to the confidence level occurred；According to the confidence level, current scene is determined
Reasonable personage's custom；According to the reasonable personage custom and syntax rule, the original return information is processed, generate with
Preset acquiescence personage IP is the return information of image.
According to knowledge mapping subgraph and syntax rule, when generating return information, personage's custom can also be added, make reply
Information is more targeted, more life-like, and then improves user experience.
The specific steps are：
The first step generates original return information corresponding with input information according to knowledge mapping subgraph and syntax rule；Tool
Body process with above-mentioned according to knowledge mapping subgraph and syntax rule to generate the process of return information identical.
Second step calculates acquiescence personage IP in current scene according to the weight and user view of the historical data of storage,
Each personage is accustomed to the confidence level occurred；
Before calculating each personage and being accustomed to the confidence level occurred, personage's custom is required to look up, personage's custom can store
In knowledge mapping, it can also be stored in the custom subgraph taken out in advance, this is all within the scope of the present invention.Pass through
It is spare to extract custom subgraph, the efficiency of return information generation can be improved.
Wherein, historical data refers to the data of speaking of the personage IP of storage, and may include：Speech content and scene of speaking
Data.
Preferably, the weight of historical data is related with the generation time for data of speaking, and time point closer data more can be anti-
Answer the custom that figure image is nearest, therefore, can be arranged time point it is close data weights it is high.
It further according to the weight and user view of historical data, calculates in current scene, what each personage was accustomed to occurring sets
Reliability.
When calculating confidence level, all people's object is practised in the current scene being consistent with user view in statistical history data
It is used, including speech habits and motor habit, further according to the power of the weight of each personage custom, that is, corresponding historical data
Weight calculates the confidence level of each personage custom.
Third walks, and according to the confidence level being calculated, determines the reasonable personage custom of current scene.
If finding personage's custom that user uses in current scene has multiple, and the confidence level of each personage custom is not
Together, then the highest personage's custom of confidence level is selected to be accustomed to as reasonable personage.
When the confidence level of two kinds of personages custom is identical, two kinds of personage's customs can be all accustomed to as reasonable personage,
One of which personage can be randomly choosed to be accustomed to being accustomed to as reasonable personage.
4th step is processed the original return information according to reasonable personage custom and syntax rule, generates with pre-
The acquiescence personage IP first set is the return information of image.
After choosing reasonable personage's custom, reasonable personage custom is added in original return information, original reply is believed
Breath is processed, and in process, needs, according to syntax rule, to generate the return information of grammaticality.
For example, robot personage's IP images are personage A, input information is：" your age is how many？" original return information
For：" I is born in nineteen eighty-two, 35 years old this year ", reasonable personage's custom are：" Ow, it is good ", after processing is with personage IP
Image return information be：" Ow, I is born in nineteen eighty-two, 35 years old this year, good ".
In the present invention, it if without storage personage's custom in knowledge mapping, need not be generated back in conjunction with personage's custom
Complex information generates return information directly according to knowledge mapping subgraph and syntax rule.
The personage custom different by considering different scenes, can targetedly combine according to different input informations
Different personage's customs, more life-like return information is exported to user, and then improve user experience.
In a specific embodiment provided by the invention, the method can also include：Obtain personage input by user
IP change directives；According to the change directive, it sets personage IP to new persona IP from acquiescence personage IP；It is transferred from database
The corresponding new knowledge collection of illustrative plates of the new persona IP；Human-computer interaction is carried out according to the new knowledge collection of illustrative plates and user.
If user, dissatisfied to current figure image, can also change personage IP during using robot,
Current personage IP can be acquiescence personage IP, can also be the personage IP that user had replaced, can repeatedly be replaced.
After robot receives personage IP change directives input by user, according to change directive, by personage IP from acquiescence
Personage IP is set as new persona IP, and the corresponding new knowledge collection of illustrative plates of new persona IP is transferred from database, further according to new knowledge figure
Spectrum carries out human-computer interaction with user, and interactive process is identical as the acquiescence interactive process of personage IP.
User to robot send personage's IP change directives when, can by voice send instruct, can also by button,
The other manners such as action send instruction.This is all within the scope of the present invention.
The personage IP for switching chat robots in this way need not change the code of bottom, and personage IP switchings are more
Add conveniently, is conducive to the popularization and maintenance of chat robots product.
Step S105：It is image with the acquiescence personage IP, the return information is exported to user.
Finally, it is image to give tacit consent to personage IP, return information is exported to user.
Wherein, return information may include：Speech answering information and/or action return information.
User chats with chat robots, in dialogue, asks the age of chat robots, chat robots can answer currently
The age of the personage IP of setting, chat robots can in the form of speech, the form etc. of action (sign language, the shape of the mouth as one speaks) answer oneself
Age.When user requires chat robots to show that a certain action, chat robots can be based on according to the input information of user
The habitual movement of the personage IP stored in knowledge mapping carries out multi-modal reply, by corresponding action demonstration to user to user.
For example, user requires robot to show a certain actions of personage A, such as perform MV, then robot is examined from knowledge mapping
The maneuver library of rope personage A, and the action of corresponding MV is found from maneuver library, then by the action demonstration to user.
For example, if user is requiring robot to meet demand for accompanying, such as read, then robot needs imitation personage A to say
The readings such as tone, tone color, the tone of words.Robot can find personage A in the books of selection reading with retrieval knowledge collection of illustrative plates
The books that the books and/or user often read are liked, and show the books using speech pattern.
For example, if user requires robot to show technical ability, such as write the poem, retrieves personage's A knowledge mappings first, determine people
Whether object A has corresponding technical ability, if so, then selecting the works that personage A has write out to show user's (reading aloud), if do not had
Have, then robot responds user's " do not did/will not/do not do " etc. according to the personage A response patterns being accustomed to and character personality.
Example 1：Robot current people IP is personage A, and user's input information of acquisition is that " age in your this year is more
It is few？"
The user view of robot identification is " chat ", and main body is " machine ", and object is " age ", wherein object and master
Body belongs to input entity.Wherein, when identifying main body, extensive technology is used, based on " you " identification " machine ", also
It is " personage A ".
Robot is according to input entity and user view, from the knowledge mapping and world knowledge collection of illustrative plates of the personage A of foundation,
Triple related with the age is searched, the result of lookup may be：(" personage A ", " age ", " 35 "), (" personage A ", " birth
Time ", " 1982 "), the two triples can form knowledge mapping subgraph, according to the knowledge mapping subgraph and syntax rule,
Original return information can be generated：" I is born in nineteen eighty-two, 35 years old this year ".
The term custom for searching personage A from the knowledge mapping of personage A again is accustomed to the reply to related enquirement, and calculates
The confidence level of each personage custom selects the higher personage's custom of confidence level to be accustomed to as reasonable personage, for example, only finding people
The term custom of object A is " Ow, good ", but does not find other relevant personages' customs, then term custom is closes
Manage personage's custom.Finally, according to reasonable personage custom and syntax rule, original return information is processed, is ultimately generated
Return information is：" Ow, I is born in nineteen eighty-two, 35 years old this year, good ".
Robot with the identity of personage A image, is replied again to user：" Ow, I is born in nineteen eighty-two, 35 years old this year, no
It is wrong ".
Example 2：Robot current people IP is personage B, and user's input information of acquisition is：" age in personage A this year is
How much？"
The user view of robot identification is " chat ", and main body is " personage A ", and object is " age ", wherein object and master
Body belongs to input entity.
Robot is according to input entity and user view, from the knowledge mapping and world knowledge collection of illustrative plates of the personage B of foundation,
Triple related with personage A and age is searched, still, personage A and personage B does not have social relationships, finally in world knowledge figure
The age information of personage A has been found in spectrum.
The custom user that robot finds personage B is sky, then is directly advised in conjunction with grammer according to the age information of lookup
Then, return information is generated, final return information can be：" personage B just helps you to ask, personage A is born in nineteen eighty-two, this year
35 years old ".
Robot with the identity of personage B image, is replied again to user：" personage B just helps you to ask, personage A is born in 1982
Year, 35 years old this year ".
Example 3：Robot current people IP is personage A, and user's input information of acquisition is " putting first song to hear ".
The input entity of extraction is：" song ", user view are " loosen and listen song ", then according to inputting entity and user view,
From lookup in the knowledge mapping and world knowledge collection of illustrative plates of personage A and song and the relevant knowledge mapping subgraphs of personage A, personage A is found
New song is issued, then robot is exported to user：" well hearing my new song XXX ".
By means of the invention it is possible to assign the personality of robot humanoid, make the specific personage IP of robot simulation, with specific personage
The identity of IP is interacted with user, more targetedly responds user；And the personage's custom for considering personage IP, makes machine
People is more intelligent, personalizes, and is preferably interacted with user, can improve user experience.
Based on inventive concept identical with a kind of above-mentioned man-machine interaction method based on personage IP, the embodiment of the present invention provides
A kind of man-machine interactive system based on personage IP, as shown in Fig. 2, including：Data obtaining module 101, for obtaining user's
Input information；Entity extraction module 102, for extracting the input entity for including in the input information；Intention assessment module
103, for identifying user view according to the input information；Generation module 104 is replied, for according to the input entity and use
Family is intended to, and based on the knowledge mapping pre-established, generates the return information for image with preset acquiescence personage IP；Information
Output module 105 exports the return information for being image with the acquiescence personage IP to user.
Wherein, the knowledge mapping, including：Using give tacit consent to the person names of personage IP as the knowledge mapping of core node and/
Or world knowledge collection of illustrative plates.
Wherein, generation module 104 is replied, including：Associative cell, for will be in the input entity and the knowledge mapping
Entity be associated；Extraction unit, for from the knowledge mapping, extraction to be related to the input entity and user view
Knowledge mapping subgraph；Information generating unit, for according to the knowledge mapping subgraph and syntax rule, generating to preset
Acquiescence personage IP be image return information.
Wherein, information generating unit, including：Raw information generates subelement, for according to the knowledge mapping subgraph and
Syntax rule generates original return information corresponding with the input information；Confidence calculations subelement, for according to storage
The weight of historical data and the user view calculate acquiescence personage IP in current scene, and what each personage was accustomed to occurring sets
Reliability；It is accustomed to determination subelement, for according to the confidence level, determining the reasonable personage custom of current scene；Information generates son
Unit, for according to reasonable personage's custom and syntax rule, being processed, being generated with advance to the original return information
The acquiescence personage IP set is the return information of image.
In a specific embodiment provided by the invention, can also include：Instruction acquisition module, it is defeated for obtaining user
The personage's IP change directives entered；Module is changed, for according to the change directive, personage IP to be set as new from acquiescence personage IP
Personage IP；Knowledge mapping transfers module, for transferring the corresponding new knowledge collection of illustrative plates of the new persona IP from database；Interaction mould
Block, for carrying out human-computer interaction according to the new knowledge collection of illustrative plates and user.
Wherein, the knowledge mapping of at least one personage IP is stored in the database.
Wherein, the return information, including：Voice-response information and/or action response information.
Man-machine interactive system provided in an embodiment of the present invention based on personage IP, adds knowledge mapping in robot,
The knowledge mapping includes：Using the person names of personage IP as the knowledge mapping of core node and world knowledge collection of illustrative plates, Neng Goufu
The personality for giving robot humanoid is made the specific personage IP of robot simulation, is interacted with user with the identity of specific personage IP, more
Targetedly respond user；And the personage's custom for considering personage IP, makes that robot is more intelligent, personalizes, more preferably
Ground is interacted with user, can improve user experience.
Based on inventive concept identical with a kind of above-mentioned man-machine interaction method based on personage IP, the embodiment of the present invention provides
A kind of computer readable storage medium, is stored thereon with computer program, which realizes above-mentioned one when being executed by processor
Man-machine interaction method of the kind based on personage IP.
Computer readable storage medium provided in an embodiment of the present invention can realize above-mentioned base under the control of a processor
In the man-machine interaction method of personage IP, the personality of robot humanoid can be assigned, makes the specific personage IP of robot simulation, with specific
The identity of personage IP is interacted with user, more targetedly responds user；And the personage's custom for considering personage IP, makes
Robot is more intelligent, personalizes, and is preferably interacted with user, can improve user experience.
Based on inventive concept identical with a kind of above-mentioned man-machine interaction method based on personage IP, the embodiment of the present invention also carries
A kind of human-computer interaction device based on personage IP has been supplied, including：Memory, processor and storage on a memory and can handled
The computer program run on device, the processor realize a kind of above-mentioned human-computer interaction based on personage IP when executing described program
Method.
Human-computer interaction device provided in an embodiment of the present invention based on personage IP, can be when processor works, in realization
The man-machine interaction method based on personage IP is stated, the personality of robot humanoid can be assigned, makes the specific personage IP of robot simulation, with
The identity of specific personage IP is interacted with user, more targetedly responds user；And the personage for considering personage IP practises
It is used, make that robot is more intelligent, personalizes, is preferably interacted with user, user experience can be improved.
In the specification of the present invention, numerous specific details are set forth.It is to be appreciated, however, that the embodiment of the present invention can be with
It puts into practice without these specific details.In some instances, well known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that：Its according to
So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into
Row equivalent replacement；And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover in the claim of the present invention and the range of specification.
Claims (10)
1. a kind of man-machine interaction method based on personage IP, which is characterized in that including：
Obtain the input information of user；
Extract the input entity for including in the input information；
User view is identified according to the input information；
It is generated with preset acquiescence people based on the knowledge mapping pre-established according to the input entity and user view
Object IP is the return information of image；
It is image with the acquiescence personage IP, the return information is exported to user.
2. according to the method described in claim 1, it is characterized in that, the knowledge mapping, including：To give tacit consent to the personage of personage IP
The knowledge mapping and/or world knowledge collection of illustrative plates of entitled core node.
3. according to the method described in claim 2, it is characterized in that, according to the input entity and user view, based on advance
The knowledge mapping of foundation is generated with the return information that preset acquiescence personage IP is image, including：
The input entity is associated with the entity in the knowledge mapping；
From the knowledge mapping, extraction and the input entity and the relevant knowledge mapping subgraph of user view；
According to the knowledge mapping subgraph and syntax rule, generates and believed with the reply that preset acquiescence personage IP is image
Breath.
4. according to the method described in claim 3, it is characterized in that, according to the knowledge mapping subgraph and syntax rule, generate
With the return information that preset acquiescence personage IP is image, including：
According to the knowledge mapping subgraph and syntax rule, original return information corresponding with the input information is generated；
According to the weight of the historical data of storage and the user view, acquiescence personage IP is calculated in current scene, each people
The confidence level that object custom occurs；
According to the confidence level, the reasonable personage custom of current scene is determined；
According to reasonable personage's custom and syntax rule, the original return information is processed, is generated to preset
Acquiescence personage IP be image return information.
5. according to the method described in claim 1, it is characterized in that, further including：
Obtain personage IP change directives input by user；
According to the change directive, it sets personage IP to new persona IP from acquiescence personage IP；
The corresponding new knowledge collection of illustrative plates of the new persona IP is transferred from database；
Human-computer interaction is carried out according to the new knowledge collection of illustrative plates and user.
6. according to the method described in claim 5, it is characterized in that, being stored with knowing at least one personage IP in the database
Know collection of illustrative plates.
7. according to the method described in claim 1, it is characterized in that, the return information, including：Voice-response information and/or
Action response information.
8. a kind of man-machine interactive system based on personage IP, which is characterized in that including：
Data obtaining module, the input information for obtaining user；
Entity extraction module, for extracting the input entity for including in the input information；
Intention assessment module, for identifying user view according to the input information；
Reply generation module, for according to the input entity and user view, based on the knowledge mapping pre-established, generation with
Preset acquiescence personage IP is the return information of image；
Message output module exports the return information for being image with the acquiescence personage IP to user.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The method described in one of claim 1-7 is realized when row.
10. a kind of human-computer interaction device based on personage IP, including：Memory, processor and storage are on a memory and can be
The computer program run on processor, which is characterized in that the processor realized when executing described program claim 1-7 it
Method described in one.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810286505 | 2018-03-30 | ||
| CN2018102865057 | 2018-03-30 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108804698A true CN108804698A (en) | 2018-11-13 |
Family
ID=64086586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810623329.1A Pending CN108804698A (en) | 2018-03-30 | 2018-06-15 | Man-machine interaction method, system, medium based on personage IP and equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108804698A (en) |
| WO (1) | WO2019184103A1 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522399A (en) * | 2018-11-20 | 2019-03-26 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110070370A (en) * | 2019-04-29 | 2019-07-30 | 上海智臻智能网络科技股份有限公司 | Pay a return visit providing method, device, computer equipment and the storage medium of service |
| CN110111795A (en) * | 2019-04-23 | 2019-08-09 | 维沃移动通信有限公司 | A kind of method of speech processing and terminal device |
| CN110532399A (en) * | 2019-08-07 | 2019-12-03 | 广州多益网络股份有限公司 | Knowledge mapping update method, system and the device of object game question answering system |
| CN110674398A (en) * | 2019-09-05 | 2020-01-10 | 深圳追一科技有限公司 | Virtual character interaction method and device, terminal equipment and storage medium |
| CN111159546A (en) * | 2019-12-24 | 2020-05-15 | 腾讯科技（深圳）有限公司 | Event pushing method and device, computer readable storage medium and computer equipment |
| CN111897864A (en) * | 2020-08-13 | 2020-11-06 | 创智和宇信息技术股份有限公司 | Expert database data extraction method and system based on Internet AI outbound |
| CN112102840A (en) * | 2020-09-09 | 2020-12-18 | 中移（杭州）信息技术有限公司 | Semantic recognition method, device, terminal and storage medium |
| CN112395399A (en) * | 2020-11-13 | 2021-02-23 | 四川大学 | Specific personality dialogue robot training method based on artificial intelligence |
| CN114363277A (en) * | 2020-12-31 | 2022-04-15 | 万翼科技有限公司 | Intelligent chatting method and device based on social relationship and related products |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737481B (en) * | 2019-10-10 | 2024-03-01 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and storage medium for noise reduction of knowledge graph |
| CN111177335B (en) * | 2019-11-29 | 2023-11-21 | 广东轩辕网络科技股份有限公司 | Knowledge graph-based intelligent assistant information processing method and device |
| CN111737492B (en) * | 2020-06-23 | 2023-11-03 | 安徽大学 | Autonomous robot task planning method based on knowledge graph technology |
| US11875362B1 (en) | 2020-07-14 | 2024-01-16 | Cisco Technology, Inc. | Humanoid system for automated customer support |
| US11907670B1 (en) | 2020-07-14 | 2024-02-20 | Cisco Technology, Inc. | Modeling communication data streams for multi-party conversations involving a humanoid |
| CN112466307B (en) * | 2020-11-19 | 2023-09-26 | 珠海格力电器股份有限公司 | Voice replying method and device, storage medium and electronic device |
| CN116049425B (en) * | 2022-11-04 | 2023-09-22 | 合肥中科前沿科技有限公司 | Robot interaction method based on RCS architecture |
| CN115840841A (en) * | 2023-02-01 | 2023-03-24 | 阿里巴巴达摩院(杭州)科技有限公司 | Multi-modal dialog method, device, equipment and storage medium |
| CN116627261A (en) * | 2023-07-25 | 2023-08-22 | 安徽淘云科技股份有限公司 | Interaction method, device, storage medium and electronic equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140316764A1 (en) * | 2013-04-19 | 2014-10-23 | Sri International | Clarifying natural language input using targeted questions |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN106202476A (en) * | 2016-07-14 | 2016-12-07 | 广州安望信息科技有限公司 | A kind of interactive method and device of knowledge based collection of illustrative plates |
| CN106297789A (en) * | 2016-08-19 | 2017-01-04 | 北京光年无限科技有限公司 | The personalized interaction method of intelligent robot and interactive system |
| CN107273477A (en) * | 2017-06-09 | 2017-10-20 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device for robot |
| CN107294837A (en) * | 2017-05-22 | 2017-10-24 | 北京光年无限科技有限公司 | Engaged in the dialogue interactive method and system using virtual robot |
| CN107340865A (en) * | 2017-06-29 | 2017-11-10 | 北京光年无限科技有限公司 | Multi-modal virtual robot exchange method and system |
| CN107368572A (en) * | 2017-07-13 | 2017-11-21 | 张勇 | Multifunctional intellectual man-machine interaction method and system |
| CN107589826A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN107589828A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN107797663A (en) * | 2017-10-26 | 2018-03-13 | 北京光年无限科技有限公司 | Multi-modal interaction processing method and system based on visual human |
| WO2018045553A1 (en) * | 2016-09-09 | 2018-03-15 | 上海海知智能科技有限公司 | Man-machine interaction system and method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004295766A (en) * | 2003-03-28 | 2004-10-21 | Sony Corp | Robot apparatus and user authentication method through robot |
| CN103489210A (en) * | 2013-09-06 | 2014-01-01 | 雷路德 | Virtual character proactive contacting system and method thereof |
| CN106503156B (en) * | 2016-10-24 | 2019-09-03 | 北京百度网讯科技有限公司 | Man-machine interaction method and device based on artificial intelligence |
| CN107563517A (en) * | 2017-08-25 | 2018-01-09 | 深圳狗尾草智能科技有限公司 | Robot autognosis real time updating method and system |
-
2018
- 2018-06-15 WO PCT/CN2018/091636 patent/WO2019184103A1/en active Application Filing
- 2018-06-15 CN CN201810623329.1A patent/CN108804698A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140316764A1 (en) * | 2013-04-19 | 2014-10-23 | Sri International | Clarifying natural language input using targeted questions |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN107589826A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN107589828A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN106202476A (en) * | 2016-07-14 | 2016-12-07 | 广州安望信息科技有限公司 | A kind of interactive method and device of knowledge based collection of illustrative plates |
| CN106297789A (en) * | 2016-08-19 | 2017-01-04 | 北京光年无限科技有限公司 | The personalized interaction method of intelligent robot and interactive system |
| WO2018045553A1 (en) * | 2016-09-09 | 2018-03-15 | 上海海知智能科技有限公司 | Man-machine interaction system and method |
| CN107294837A (en) * | 2017-05-22 | 2017-10-24 | 北京光年无限科技有限公司 | Engaged in the dialogue interactive method and system using virtual robot |
| CN107273477A (en) * | 2017-06-09 | 2017-10-20 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device for robot |
| CN107340865A (en) * | 2017-06-29 | 2017-11-10 | 北京光年无限科技有限公司 | Multi-modal virtual robot exchange method and system |
| CN107368572A (en) * | 2017-07-13 | 2017-11-21 | 张勇 | Multifunctional intellectual man-machine interaction method and system |
| CN107797663A (en) * | 2017-10-26 | 2018-03-13 | 北京光年无限科技有限公司 | Multi-modal interaction processing method and system based on visual human |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522399A (en) * | 2018-11-20 | 2019-03-26 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN109522399B (en) * | 2018-11-20 | 2022-08-12 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110111795B (en) * | 2019-04-23 | 2021-08-27 | 维沃移动通信有限公司 | Voice processing method and terminal equipment |
| CN110111795A (en) * | 2019-04-23 | 2019-08-09 | 维沃移动通信有限公司 | A kind of method of speech processing and terminal device |
| CN110070370A (en) * | 2019-04-29 | 2019-07-30 | 上海智臻智能网络科技股份有限公司 | Pay a return visit providing method, device, computer equipment and the storage medium of service |
| CN110532399A (en) * | 2019-08-07 | 2019-12-03 | 广州多益网络股份有限公司 | Knowledge mapping update method, system and the device of object game question answering system |
| CN110674398A (en) * | 2019-09-05 | 2020-01-10 | 深圳追一科技有限公司 | Virtual character interaction method and device, terminal equipment and storage medium |
| CN111159546A (en) * | 2019-12-24 | 2020-05-15 | 腾讯科技（深圳）有限公司 | Event pushing method and device, computer readable storage medium and computer equipment |
| CN111159546B (en) * | 2019-12-24 | 2023-10-24 | 深圳市雅阅科技有限公司 | Event pushing method, event pushing device, computer readable storage medium and computer equipment |
| CN111897864A (en) * | 2020-08-13 | 2020-11-06 | 创智和宇信息技术股份有限公司 | Expert database data extraction method and system based on Internet AI outbound |
| CN112102840A (en) * | 2020-09-09 | 2020-12-18 | 中移（杭州）信息技术有限公司 | Semantic recognition method, device, terminal and storage medium |
| CN112102840B (en) * | 2020-09-09 | 2024-05-03 | 中移（杭州）信息技术有限公司 | Semantic recognition method, semantic recognition device, terminal and storage medium |
| CN112395399A (en) * | 2020-11-13 | 2021-02-23 | 四川大学 | Specific personality dialogue robot training method based on artificial intelligence |
| CN114363277A (en) * | 2020-12-31 | 2022-04-15 | 万翼科技有限公司 | Intelligent chatting method and device based on social relationship and related products |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019184103A1 (en) | 2019-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804698A (en) | Man-machine interaction method, system, medium based on personage IP and equipment | |
| CN105512228B (en) | A kind of two-way question and answer data processing method and system based on intelligent robot | |
| CN106503156B (en) | Man-machine interaction method and device based on artificial intelligence | |
| US11645547B2 (en) | Human-machine interactive method and device based on artificial intelligence | |
| CN109829039B (en) | Intelligent chat method, intelligent chat device, computer equipment and storage medium | |
| CN110427472A (en) | The matched method, apparatus of intelligent customer service, terminal device and storage medium | |
| CN109918650B (en) | Interview intelligent robot device capable of automatically generating interview draft and intelligent interview method | |
| CN106295792B (en) | Dialogue data interaction processing method and device based on multi-model output | |
| WO2018036555A1 (en) | Session processing method and apparatus | |
| CN106448670A (en) | Dialogue automatic reply system based on deep learning and reinforcement learning | |
| CN111831798A (en) | Information processing method, information processing device, electronic equipment and computer readable storage medium | |
| CN110364146A (en) | Audio recognition method, device, speech recognition apparatus and storage medium | |
| CN111145721A (en) | Personalized prompt language generation method, device and equipment | |
| CN110795913A (en) | Text encoding method and device, storage medium and terminal | |
| WO2017191696A1 (en) | Information processing system and information processing method | |
| CN106815321A (en) | Chat method and device based on intelligent chat robots | |
| CN106952648A (en) | A kind of output intent and robot for robot | |
| CN108595609A (en) | Generation method, system, medium and equipment are replied by robot based on personage IP | |
| CN114495927A (en) | Multi-modal interactive virtual digital person generation method and device, storage medium and terminal | |
| CN117251552B (en) | Dialogue processing method and device based on large language model and electronic equipment | |
| CN116401354A (en) | Text processing method, device, storage medium and equipment | |
| CN116561265A (en) | Personalized dialogue generation method, model training method and device | |
| CN113761156A (en) | Data processing method, device and medium for man-machine interaction conversation and electronic equipment | |
| Huang et al. | Applied to mobile multimedia intelligent speech system interactive topic guiding model | |
| CN110781327B (en) | Image searching method and device, terminal equipment and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 301, Building 39, 239 Renmin Road, Gusu District, Suzhou City, Jiangsu Province, 215000 Applicant after: SHENZHEN GOWILD ROBOTICS Co.,Ltd. Address before: 518000 Dongfang Science and Technology Building 1307-09, 16 Keyuan Road, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN GOWILD ROBOTICS Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |
|
| RJ01 | Rejection of invention patent application after publication |