CN108363492B - Man-machine interaction method and interaction robot - Google Patents
Man-machine interaction method and interaction robot Download PDFInfo
- Publication number
- CN108363492B CN108363492B CN201810193098.5A CN201810193098A CN108363492B CN 108363492 B CN108363492 B CN 108363492B CN 201810193098 A CN201810193098 A CN 201810193098A CN 108363492 B CN108363492 B CN 108363492B
- Authority
- CN
- China
- Prior art keywords
- interaction
- user
- information
- robot
- content
- 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.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 198
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000002452 interceptive effect Effects 0.000 claims abstract description 72
- 230000007613 environmental effect Effects 0.000 claims abstract description 30
- 230000009471 action Effects 0.000 claims description 30
- 230000014509 gene expression Effects 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 6
- 230000000875 corresponding effect Effects 0.000 description 55
- 238000001514 detection method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000008921 facial expression Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 206010011469 Crying Diseases 0.000 description 1
- 239000004480 active ingredient Substances 0.000 description 1
- 230000002730 additional effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000011089 mechanical engineering Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/0304—Detection arrangements using opto-electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
Abstract
The invention provides a man-machine interaction method and an interactive robot, wherein the method comprises the following steps: s1, when the robot detects the user needing active interaction, acquiring user integrated information, wherein the user integrated information comprises the personal information of the current user and the environmental information of the current robot system; s2, generating active interactive content matched with the user comprehensive information; and S3, actively interacting with the user according to the active interaction content. According to the invention, during the human-computer interaction process of the robot, the personalized active human-computer interaction can be realized according to the information of different users and the information of the current environment.
Description
Technical Field
The invention relates to the field of human-computer interaction, in particular to a human-computer interaction method and an interactive robot.
Background
The robot is an emerging comprehensive subject developed in recent decades, concentrates latest research results of various subjects such as mechanical engineering, electronic engineering, information science, automatic control, artificial intelligence and the like, and is one of the most active research fields of scientific and technological development at present. With the development of scientific technology, service robots have been widely used.
For the service robot, the good human-computer interaction experience is the key of the service performance of the service robot and is the most basic requirement of the user on the robot. Currently, a mainstream service robot generally has a certain degree of human-computer interaction function. Common human-computer interactions include mouse-and-keyboard human-computer interactions such as those of PCs, touch-and-slide human-computer interactions such as those of tablet phones, and voice human-computer interactions. The voice interaction type human-computer interaction mode is one of the most important human-computer interaction modes of the service robot due to the advantages of convenience and naturalness of an interaction mode, low interaction learning cost and the like.
The robot continuously monitors a voice command of a user, starts voice recognition after receiving a specific voice command, and makes corresponding answer and feedback for the user according to specific recognized contents. However, the man-machine interaction mode is passive, the robot cannot actively communicate with the user, and the attraction to the user is not strong enough; moreover, the interactive answer content is rigid and not flexible enough, and the answer content is the same for different people and not personalized enough. The user experience may be reduced.
Therefore, in order to solve the above drawbacks, the present invention provides an active personalized human-machine interaction.
Disclosure of Invention
The invention aims to provide a human-computer interaction method and an interactive robot, which can realize personalized active interaction according to different user information of different users and by combining information of the current environment in the process of human-computer interaction of the robot.
The technical scheme provided by the invention is as follows:
the invention provides a man-machine interaction method, which comprises the following steps: s1, when the robot detects a user needing active interaction, acquiring user integrated information, wherein the user integrated information comprises personal information of the user and environmental information of the current robot system; s2, generating active interactive content matched with the user comprehensive information; and S3, actively interacting with the user according to the active interaction content.
Preferably, the method includes, before the step S1, the steps of: s0, according to the environment information of the current robot, setting the application scene of the robot matched with the environment information, wherein the application scene comprises the interaction rule of robot interaction and the interaction resources used in the interaction.
Preferably, step S2 specifically includes: s20, according to the interaction rule, obtaining the interaction resource matched with the user comprehensive information, thereby generating the active interaction content.
Preferably, the interaction resources include: voice content, action content, or multimedia content; the interaction rule comprises a plurality of rule nodes, and each rule node represents the mapping relation between different user comprehensive information and different interaction resources.
Preferably, the personal information of the current user includes: gender, age, expression, face angle, face spatial position, face occurrence frequency, user name, number of faces currently detected, and voice information; the environmental information of the current robot system includes: time, place, temperature, weather, network connection status, system language.
Preferably, the step S1 specifically includes the steps of: s10, when the robot detects the user needing active interaction, acquiring the user comprehensive information, and endowing each user characteristic in the personal information of the current user with a corresponding user characteristic keyword and a corresponding user characteristic parameter value, and endowing each environmental characteristic in the environmental information of the current robot system with a corresponding environmental characteristic keyword and a corresponding environmental characteristic parameter value.
Preferably, step S21 specifically includes the steps of: s211, screening a plurality of candidate rule nodes matched with the user comprehensive information from the interaction rules; s212, generating interactive contents according to the interactive resources corresponding to the candidate rule nodes; the interactive content comprises voice interactive content, action interactive content and multimedia interactive content.
Preferably, step S211 specifically includes the steps of: s2111, judging whether all preset feature keywords and corresponding preset feature parameter values in each rule node are the same as part of feature keywords and corresponding feature parameter values in the user comprehensive information one by one; the characteristic keywords comprise user characteristic keywords and environment characteristic keywords, and the characteristic parameter values comprise user characteristic parameter values and environment characteristic parameter values; and if S2112 is yes, the rule nodes meeting the conditions are taken as candidate rule nodes.
Preferably, step S212 specifically includes the steps of: s2121, analyzing respective priority values of the candidate rule nodes, and sequencing the candidate rule nodes according to the priority values; for a plurality of candidate rule nodes with the same priority value, randomly or weighted randomly selecting one candidate rule node to participate in sequencing; s2122, sequentially combining the interaction resources corresponding to the sorted candidate rule nodes to generate the interaction content.
The invention also provides an interactive robot, which is characterized by comprising: the information acquisition module is used for acquiring user comprehensive information when the robot detects a user needing active interaction, wherein the user comprehensive information comprises personal information of the user and environmental information of a current robot system; the processing module is electrically connected with the information acquisition module and is used for generating active interactive content matched with the user comprehensive information; and the interaction module is used for actively interacting with the user according to the active interaction content.
Preferably, the scene setting module is further configured to set an application scene of the robot matched with the environmental information according to the environmental information where the current robot is located, where the application scene includes interaction rules of robot interaction and interaction resources used in the interaction.
The processing module is preferably further configured to obtain, according to the interaction rule, an interaction resource matched with the user comprehensive information, so as to generate active interaction content.
Preferably, the interaction resources include: voice content, action content, or multimedia content; the interaction rule comprises a plurality of rule nodes, and each rule node represents the mapping relation between different user comprehensive information and different interaction resources.
Preferably, the personal information of the current user includes: gender, age, expression, face angle, face spatial position, face occurrence frequency, user name, number of faces currently detected, and voice information; the environmental information of the current robot system includes: time, place, temperature, weather, network connection status, system language.
Preferably, the information obtaining module is further configured to, when the robot detects a user who needs to actively interact, obtain user comprehensive information, assign a corresponding user characteristic keyword and a user characteristic parameter value to each user characteristic in the personal information of the current user, and assign a corresponding environment characteristic keyword and an environment characteristic parameter value to each environment characteristic in the environment information of the current robot system.
Preferably, the matching sub-module is configured to screen out a plurality of candidate rule nodes matching the user comprehensive information from the interaction rules; each rule node comprises a plurality of preset characteristic keywords and corresponding preset characteristic parameter values; the interactive content generation sub-module generates interactive content according to the interactive resources corresponding to the candidate rule nodes; the interactive content comprises voice interactive content, action interactive content and multimedia interactive content.
Preferably, the matching sub-module is further configured to determine, one by one, whether all preset feature keywords and corresponding preset feature parameter values in each rule node are the same as part of the feature keywords and corresponding feature parameter values in the user integrated information; the characteristic keywords comprise user characteristic keywords and environment characteristic keywords, and the characteristic parameter values comprise user characteristic parameter values and environment characteristic parameter values; and if so, taking the rule node meeting the condition as a candidate rule node.
Preferably, the interactive content generation sub-module is further configured to analyze respective priority values of the plurality of candidate rule nodes, and sort the candidate rule nodes according to the priority values; for a plurality of candidate rule nodes with the same priority value, randomly selecting one of the candidate rule nodes to participate in the sorting, or weighted randomly selecting one of the candidate rule nodes to participate in the sorting; and the interactive content generation sub-module is further used for sequentially combining the interactive resources corresponding to the ordered candidate rule nodes to generate the interactive content. The man-machine interaction method and the interactive robot provided by the invention can bring at least one of the following beneficial effects:
1. according to the invention, the interaction mode of the robot is different from the current passive interaction, and the robot can actively interact with the user after recognizing the user, so that the user is attracted to participate in the interaction, and the interaction experience is improved. Meanwhile, the robot can acquire the personal information of the current user and the environmental information of the current robot system during interaction, and active interactive content is comprehensively formed, so that the interactive content can be more suitable for the current environment and the personal characteristics of the user, the user can be more integrated into human-computer interaction, and the experience of the human-computer interaction is improved.
2. After the robot identifies the current user, personal information of the user, such as age, gender, expression and the like, is acquired through face identification, the current facial expression of the user is acquired, if the user speaks, voice information is acquired, and the information is integrated to form personalized current user information. The robot can acquire the current date, time, the place where the robot is located, weather and other environmental information through a network system or the current system of the robot. The robot can generate corresponding interactive contents according to the user comprehensive information with the user personality, so that the interaction is closer to the user, and the interaction intelligence is improved.
Drawings
The above features, technical features, advantages and implementations of a human-computer interaction method and an interactive robot will be further described in the following detailed description of preferred embodiments in a clearly understandable manner, in conjunction with the accompanying drawings.
FIG. 1 is a flow diagram of one embodiment of a method of human-computer interaction of the present invention;
FIG. 2 is a flow diagram of another embodiment of a method of human-computer interaction of the present invention;
FIG. 3 is a flow diagram of yet another embodiment of a method of human-computer interaction of the present invention;
FIG. 4 is a schematic structural diagram of an interactive robot according to an embodiment of the present invention;
the reference numbers illustrate:
the system comprises a scene setting module, a 2-information acquisition module, a 3-user comprehensive information module, a 4-processing module, a 41-matching sub-module, a 42-interactive content generation sub-module and a 5-interactive module.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "one" means not only "only one" but also a case of "more than one".
The invention provides an embodiment of a human-computer interaction method, as shown in fig. 1, comprising:
s1, when the robot detects the user needing active interaction, acquiring user integrated information, wherein the user integrated information comprises the personal information of the current user and the environmental information of the current robot system;
s2, generating active interactive content matched with the user comprehensive information;
and S3, actively interacting with the user according to the active interaction content.
Preferably, the step S1 is preceded by the steps of: s0, according to the environment information of the current robot, setting the application scene of the robot matched with the environment information, wherein the application scene comprises the interaction rule of robot interaction and the interaction resources used in the interaction.
In this embodiment, the application scenario includes interaction rules followed by the robot during interaction in the scenario and interaction resources required during interaction. A user customizes a user scene through selecting or based on platforms such as a webpage and an application, and deploys the user scene on the robot in real time, so that the robot can meet the requirement of rapid application in different environments while avoiding the change of a system hierarchy.
Specifically, before the robot is used, a user can set an application scene which better accords with the current use environment according to the application scene of the robot in advance, the current environment can be more matched in the human-computer interaction process, the user is enabled to be more integrated into the human-computer interaction, and the experience feeling of the human-computer interaction is improved. The application scenario includes interaction rules and interaction resources. If the robot is used in a shopping mall, interaction rules and interaction resources related to shopping are increased. For example, when the interaction rule identifies the user for the robot, the user is asked to purchase which goods, or the user is asked to find out which services are not in place in the market, and the like; a cheerful song or clapping and bowing actions can be set in the interaction resources, and when the user responds to the purchased commodities, the clapping action can be made to encourage the user to continue consuming.
If the robot is applied to a hospital, interaction rules and interaction resources related to medical treatment, medicines, epidemic prevention and the like are increased. For example, when the interaction rule identifies that the robot is distracted by the user, the robot asks the user why the robot is distracted, consolidates the user, and simultaneously takes the action of clapping the shoulders of the user and plays some cheerful music; some actions such as music, shoulder beating, oiling and the like can be set in the interactive resources.
When the robot identifies the user, the current user information is acquired through face identification, the environment information of the robot is acquired through an internal system of the robot, and finally the user comprehensive information with user individuation is formed. Then the robot can obtain what the interaction should be completed currently according to the interaction rule in the application scene, call the corresponding interaction resource in the interaction resource to form active interaction content, and actively interact with the user. Different from the current interaction mode, many current interaction modes are passive interaction, the robot starts to perform voice recognition after receiving a specific voice command by continuously monitoring the voice command of a user, and corresponding answers and feedbacks are made for the user according to specific recognized contents. The human-computer interaction mode is passive, the robot cannot actively communicate with the user, and the attraction to the user is not strong enough. In the invention, after the robot detects the user, the robot can form the active interactive content with user individuation through the acquired user comprehensive information, actively interact with the user, and attract the user to participate in human-computer interaction.
For example, if the robot is used in a mall, the user may add interaction rules and interaction resources related to shopping. The interaction rule is: after the robot identifies the user, the user is identified firstly, current user information and environment information are obtained, if the user is identified to be an adult, the user is inquired about which commodities the user purchases, and a response is made; secondly, inquiring which services are not in place in the user market, and responding; finally, the user says the bye-bye. If the child is a child, the child will be called first and then a dance will be made for the child.
The user can set a happy song or an action of clapping, bowing, waving, squatting, etc. in the interactive resource, and the user can make the clapping action when responding to the purchased goods, so that the user is encouraged to continue consuming.
When the user identified by the robot is a woman and the current time is 10 am and a half, the robot may say: "good morning for women! Asking you which goods you buy today? And simultaneously making hand waving motions to call the lady. The female responds: "buy a garment. "the robot will respond: "thank you for our mall! "make a bow simultaneously. Then continue to say: "what services are not in place in the mall" and then the content spoken by the user is recorded. Finally saying "bye" with the user.
When the user recognized by the robot is a girl, the current time is 5 pm, the expression of the current girl is a smiling face, and the robot can speak: "good afternoon friend! How do so like o? The user can simultaneously make a squatting action and keep the same height with the girl. Girl responses: "today mom bought me a new garment. "the robot will respond: "i am jumping a dance bar for you" while playing dance music.
It can be seen that, because the user comprehensive information embodied by the user is different, the interaction mode of the robot is also greatly different, and in the prior art, the interaction content of the robot for each user is the same, and after the user is identified, only: "you are you asking what can help you? Unlike the present invention, personalized interactive contents can be output according to different characteristics carried by different users.
The interaction rules and the interaction resources can be set by self, and the robot finds corresponding responses in the interaction rules according to the comprehensive information of the user, generates interaction contents by combining the interaction resources and carries out man-machine interaction. It can be seen that the comprehensive information of the users of different users is different, and the robot can generate different interactive contents according to different genders, different expressions and different ages of different users, so that the interactive contents have individuation.
As shown in fig. 2, the present invention further provides an embodiment of a human-computer interaction method, including:
s0, according to the environment information of the current robot, setting the application scene of the robot matched with the environment information, wherein the application scene comprises the interaction rule of robot interaction and the interaction resources used in the interaction.
S1, when the robot detects the user needing active interaction, acquiring user integrated information, wherein the user integrated information comprises the personal information of the current user and the environmental information of the current robot system;
s201, screening a plurality of candidate rule nodes matched with the user comprehensive information from the interaction rules;
s202, generating interactive contents according to the interactive resources corresponding to the candidate rule nodes; the interactive content comprises voice interactive content, action interactive content and multimedia interactive content.
And S3, actively interacting with the user according to the active interaction content.
The interaction resources include: voice content, action content, or multimedia content; the interaction rule comprises a plurality of rule nodes, and each rule node represents the mapping relation between different user comprehensive information and different interaction resources.
The interaction rule comprises: when the robot interacts, whether certain detection results are responded, such as whether the name of a user is inquired, whether the system time is detected, and the like; and selecting specific contents of corresponding feedback upon detection of the response, for example, different names for different genders, different actions of different users, and the like.
The interaction resources include: resources required under the corresponding interaction rules, such as all speech text content, all optional action content, all music and video content, and so on.
The personal information of the current user includes: gender, age, expression, face angle, face spatial position, face occurrence frequency, user name, number of faces currently detected, and voice information; the environmental information of the current robot system includes: time, place, temperature, weather, network connection status, system language.
Specifically, in this embodiment, the system comprehensively outputs a group of user information descriptions for the user through various kinds of recognition and detection, such as human body recognition, face recognition, environmental system detection, and the like, so as to describe the specific information of the current interactive user. The user integrated information form is expressed as follows:
head；key1：value1；key2：value2；key3：value3；...；
where the head is fixed, the string identifier of the string identifies the specific content of the string so as to distinguish it from other types of strings. The keys are various features in the user comprehensive information, namely a user feature keyword and an environment feature keyword, each key represents a feature for describing the current user, and the features can comprise: face number, face name, gender, age, time, expression, face angle, face location, face size, weather, location, temperature, type of movement, network connection status, etc. The value is a specific parameter value corresponding to the current key value, namely, the user characteristic parameter value and the environment characteristic parameter value in the invention. Value pairs can modify the number and content of user description features according to output changes of various detection and identification tools such as different human body identification, human face identification, system detection, motion detection and the like.
The simple user summary information is as follows:
example 1:
rvn；ultrasound；event；payload；type:passby；
rvn, among others; ultrasound; an event; payload; as a string header, it is indicated that the string contains the user information description of the ultrasonic sensor. The bar is relatively simple in description and merely shows that the robot perceives, via the ultrasonic sensor, that someone has walked in front of it.
Example 2:
rvf；vison；event；face；payload；type:face；stop:yes；name:avatar；gender:masculine；age:53；time:13.04；emotion:none；roll:-13.61209；pitch:23.196611；yaw:23.330135；fac eID:1；number:1；sequence:1；px:646；py:189；pw:352；ph:352；
rvf, among others; vison; an event; face; payload; as a string header, it is indicated that the string is a user integrated information description including visual sensor information. The key, value of each pair represents an information characteristic of the user. In particular, it can be interpreted as: the face information of the user is continuous; the user name: an avatar; sex: male; and (4) age: age 53; this record generation time: 13 point 04 points; the facial expression of the user: none; face angle roll value: -13.61209 degrees; face angle pitch value: 23.196611 degrees; face angle yaw value: 23.330135 degrees; face record number: number 1; the number of faces in the current picture; 1, the number of the active ingredients is 1; the face of the user is the first in the total face; face position X value: 646 px; face position Y value: 189 px; face width: 352 px; face length: 352 px;
different users, different environments, different interactive familiarity degrees, and different detection and recognition tools can generate different user description results. The comprehensive description of the users is personalized user description, and through the analysis of the different descriptions, the system generates interactive contents corresponding to the different descriptions through the rules and resources of the current scene.
The method generates a group of interactive contents corresponding to the input user comprehensive information. The interactive content of the feedback comprises the following three types: voice content, action content, and multimedia content. The voice content is an active voice prompt played by the robot; the action content is a group of motion contents of the head, the limbs and other moving parts; the multimedia content comprises pictures, music, videos, applications and the like, and is played through the display platform in front of the chest of the robot. The multimedia content can be played simultaneously along with the voice prompt, and can also be played after the voice prompt is finished, so as to meet the requirements of different scenes.
The rule nodes comprise Node nodes, and the interaction rules store voice, action and multimedia contents corresponding to each recognition result in a tree-shaped data structure. The interaction rule tree comprises a plurality of Node nodes, each Node comprises a plurality of preset characteristic keywords and corresponding preset characteristic parameter values, and also comprises a plurality of interaction resources such as voice, actions, multimedia and the like.
Key values in Node nodes describe the necessary conditions that the group of sentences, actions and multimedia needs to be selected. Firstly, when there is a piece of user's integrated information, each Node group Node will match with the currently input user integrated information, if the current user integrated information meets the necessary conditions of the Node, the Node will become a candidate Node, and it will be selected later. If the current user integrated information and the necessary conditions of the Node are not completely satisfied, the Node will not become a candidate rule Node.
As shown in fig. 3, the present invention further provides an embodiment of a human-computer interaction method, including:
s0, according to the environment information of the current robot, setting the application scene of the robot matched with the environment information, wherein the application scene comprises the interaction rule of robot interaction and the interaction resources used in the interaction.
S10, when the robot detects the user needing active interaction, acquiring the user comprehensive information, and endowing each user characteristic in the personal information of the current user with a corresponding user characteristic keyword and a corresponding user characteristic parameter value, and endowing each environmental characteristic in the environmental information of the current robot system with a corresponding environmental characteristic keyword and a corresponding environmental characteristic parameter value.
S2000, judging whether all preset feature keywords and corresponding preset feature parameter values in each rule node are the same as part of feature keywords and corresponding feature parameter values in the user comprehensive information one by one; the characteristic keywords comprise user characteristic keywords and environment characteristic keywords, and the characteristic parameter values comprise user characteristic parameter values and environment characteristic parameter values;
if S2001 is true, the rule node satisfying the condition is taken as a candidate rule node.
S2010 analyzing the respective priority values of the candidate rule nodes and sequencing the candidate rule nodes according to the priority values; for a plurality of candidate rule nodes with the same priority value, randomly or weighted randomly selecting one candidate rule node to participate in sequencing;
and S2011 sequentially combines the interaction resources corresponding to the sorted candidate rule nodes to generate the interaction content.
And S3, actively interacting with the user according to the active interaction content.
Specifically, in this embodiment, the feature keyword is a key Value, the feature parameter Value is a Value corresponding to the key Value, and the rule Node is a Node.
The specific steps of screening out a plurality of candidate rule nodes matching the user comprehensive information are shown in step S411 and step S412, and if the Value values in all the characteristics of the Node and the Value values of the same characteristics in the user comprehensive information are all satisfied, the Node is taken as a candidate rule Node. If the Value of the feature in the Node is All, that is, indicating, the Value result of the corresponding feature in All the user information is considered to be satisfied by the feature. The characteristics in the user's integrated information are usually more than the characteristic values needed by the Node nodes, and the system will not judge and filter the excessive characteristic values according to the results.
When the candidate Node nodes are matched, for the Node nodes which become the candidate nodes, a complete voice prompt is combined according to the Priority value of the Node nodes. The method decomposes a complete speech interactive content into different sentence segments, each sentence segment being a segment of a complete speech prompt. The Priority value Priority in each Node indicates the position of the sentence fragment in the complete sentence.
Simply, we can divide a complete sentence into multiple sentence segments, such as a title segment, a time segment, a content segment, and a question segment. The invention does not limit the segmentation number of the sentences, and the user can segment the sentences by himself according to the completeness of the sentences. Each section is freely combined with the next section. Therefore, the complete sentence finally combined becomes very flexible. For a plurality of candidate nodes at the same position, the method selects a Node meeting the condition through random selection.
For example, the voice interaction content to be generated comprises a call segment, a greeting segment and a content segment, wherein the call segment comprises two Node nodes with the same priority value, namely ' old man's home ' and ' old man's Node; the greeting end has three Node nodes with the same priority value, which are respectively' hello! "good morning! "good morning! "the content segment has a Node, and is" you are really good. "for the call segment and the greeting segment, one of the contents can be randomly selected to participate in the ordering of the voice information. As can be seen, the content of the voice information has 6 combination modes, and under the same condition, the content of the robot for voice interaction can be changed continuously, so that the robot cannot be rigid and the user experience is not influenced.
In some Node nodes, multiple Item options (i.e. the content executed by the robot) can be preset, and for multiple Item options existing in the Node nodes, the final result meeting the condition is selected according to the difference of Key values of the multiple Item options. If multiple Item options corresponding to the same Key value result exist, the method selects one result as a final result through a sequential selection method or a random selection method and outputs the final result.
Because the interactive content depends on the combination mode of the candidate rule nodes and the selection of Item options in each candidate rule node, under the same scene, only one candidate rule node with the same priority value is randomly selected to participate in the sequencing, and for each candidate rule node, a plurality of Item options corresponding to the key value can be randomly weighted randomly or selected in a certain sequence, so that the combination mode is very many. In the interaction process, the content of interaction is different for the same scene, and the interaction in the fixed mode is not performed very hard.
For example, in calling, the action corresponding to the key value may be three Item options of handshake, waving and salutation, in which case, one Item may be selected for output. When calling, the robot does not have too much rigid interaction due to too single action. Likewise, the calling language can be set to be multiple, and assigned to different Item options. When an Item is randomly selected, the output languages are different, and the content is diversified during interaction.
The action content and the multimedia content exist by being attached after each specific speech sentence. By defining additional actions and multimedia content after each concrete statement, when the active feedback content combination is completed, the corresponding actions and multimedia content are generated accordingly. The action and multimedia content are determined by the additional content of the last sentence component. Therefore, different actions and prompts on multimedia contents can be made by different contents and different long and short sentences. The voice script and the resource script are flexibly used, and the feedback information generated by the method can be correspondingly changed along with the difference of the comprehensive information input of the user.
By the face recognition method and in combination with personal information in the internet, certain personal information of the user, such as basic information of name, age, gender and the like, can be acquired. The present embodiment will explain the interactive system of the present invention by taking an example.
For example, when the robot identifies a crying boy in front, the collected user summary information may include: the male is 8 years old, the name and the facial expression cry, the current time is 10 am, the current weather is 2 ℃, the current location is a hospital, the air quality is good, and a word string is formed after the value is assigned for the system to call. And the robot searches out candidate rule nodes meeting the matching conditions from the rule nodes according to the comprehensive information of the user, sorts the rule nodes according to the priority values, and sequentially combines the interactive resources corresponding to the candidate rule nodes. After the robot recognizes the boy, the robot can actively make a call with the boy, and when making a call, the robot may have a plurality of Item values corresponding to the key value in the Node (the language contents of the items are respectively 'child hello!', 'hello, little commander!', 'hi, and child', and the action contents of the items are respectively waving, shaking, bowing and ritual) and only needs to select one of the language contents or the action contents as the interactive content, so that the interactive content output each time is continuously changed and cannot be too rigid.
As shown in FIG. 4, the present invention provides one embodiment of an interactive robot comprising:
the information acquisition module 2 is used for acquiring current user information and environment information;
the user comprehensive information module 3 is electrically connected with the information acquisition module 2 and is used for generating user comprehensive information according to the current user information and the environment information;
the processing module 4 is electrically connected with the user comprehensive information module 3 and is used for generating interactive contents according to the user comprehensive information and the application scene;
and the interaction module 5 is used for performing active human-computer interaction according to the interaction content.
Preferably, the interactive robot further comprises: the scene setting module 1 is further configured to set an application scene of the robot matched with the environmental information according to the environmental information where the current robot is located, where the application scene includes interaction rules of robot interaction and interaction resources used in the interaction.
Preferably, the scene setting module 1 is further configured to store a preset interaction rule of the robot and an interaction resource required by the robot when interacting under the interaction rule, and use the interaction rule and the application resource as an application scene; the interaction rule comprises a plurality of rule nodes, and each rule node comprises a plurality of preset feature keywords and corresponding preset feature parameter values.
Preferably, the user comprehensive information module 3 is further configured to assign a corresponding user characteristic keyword and a corresponding user characteristic parameter value to each user characteristic in the current user information, and assign a corresponding environment characteristic keyword and a corresponding environment characteristic parameter value to each environment characteristic in the environment information; the user comprehensive information module 3 is further configured to combine the user characteristic keywords and the corresponding user characteristic parameter values, the environment characteristic keywords and the corresponding environment characteristic parameter values into word strings, and assign corresponding word string identifiers to the word strings; and taking the string with the string identifier as the current user comprehensive information.
Preferably, the processing module 4 specifically includes: a matching sub-module 41, configured to screen out, in the application scenario, a plurality of candidate rule nodes that match the user comprehensive information; the interactive content generating submodule 42 is used for generating interactive content according to the interactive resources corresponding to the candidate rule nodes; the interactive content comprises voice interactive content, action interactive content and multimedia interactive content.
Preferably, the matching sub-module 41 is further configured to determine, one by one, whether all preset feature keywords and corresponding preset feature parameter values in each rule node are the same as part of the feature keywords and corresponding feature parameter values in the user integrated information; the characteristic keywords comprise user characteristic keywords and environment characteristic keywords, and the characteristic parameter values comprise user characteristic parameter values and environment characteristic parameter values; and if so, taking the rule node meeting the condition as a candidate rule node.
Preferably, the interactive content generating sub-module 42 is further configured to analyze respective priority values of the plurality of candidate rule nodes, and sort the candidate rule nodes according to the priority values; selecting one candidate rule node from a plurality of candidate rule nodes with the same priority value to participate in sequencing; and sequentially combining the interaction resources corresponding to the sorted candidate rule nodes to generate the interaction content.
Specifically, the information acquisition module 2 has two functions, one of which is to identify the current user and acquire user resources; for example, when a user is detected within a preset range, the user starts to be identified, which mainly identifies the facial features of the user. The expression of the current user can be recognized through a face recognition technology, and some basic data information of the user is obtained by combining with internet big data. And secondly, acquiring environmental information such as the current robot location, time, weather and the like according to the current robot system.
The processing module 4 may be composed of a processor of the robot, and the interaction module 5 includes a voice control system, a display system, a driving system, and the like used in the robot interaction process. The process of robot interaction may refer to the above method embodiments, and is not described herein again.
It should be noted that the above embodiments can be freely combined as necessary. The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (6)
1. A human-computer interaction method is characterized by comprising the following steps:
s0, according to the environment information of the current robot, setting an application scene of the robot matched with the environment information, wherein the application scene comprises an interaction rule of robot interaction and interaction resources used in the interaction;
s1, when the robot detects a user needing active interaction, acquiring user integrated information, wherein the user integrated information comprises personal information of the user and environmental information of the current robot system;
s2, generating active interactive content matched with the user comprehensive information;
s3, actively interacting with the user according to the active interaction content;
s20, according to the interaction rule, acquiring interaction resources matched with the user comprehensive information, thereby generating active interaction content; the interaction rule comprises a plurality of rule nodes, and each rule node represents the mapping relation between different user comprehensive information and different interaction resources;
s20 specifically includes:
s2000, judging whether all preset feature keywords and corresponding preset feature parameter values in each rule node are the same as part of feature keywords and corresponding feature parameter values in the user comprehensive information one by one; the characteristic keywords comprise user characteristic keywords and environment characteristic keywords, and the characteristic parameter values comprise user characteristic parameter values and environment characteristic parameter values;
if S2001 is true, the rule nodes meeting the conditions are used as candidate rule nodes;
s2010 analyzing respective priority values of a plurality of candidate rule nodes and sequencing the candidate rule nodes according to the priority values; for a plurality of candidate rule nodes with the same priority value, randomly or weighted randomly selecting one candidate rule node to participate in sequencing;
and S2011 sequentially combines the interaction resources corresponding to the sorted candidate rule nodes to generate the interaction content.
2. A method of human-computer interaction according to claim 1, wherein:
the interaction resources include: voice content, action content, or multimedia content.
3. A method of human-computer interaction according to any one of claims 1-2, characterised in that:
the personal information of the user includes: gender, age, expression, face angle, face spatial position, face occurrence frequency, user name, number of faces currently detected, and voice information;
the environmental information of the current robot system includes: time, place, temperature, weather, network connection status, system language.
4. An interactive robot, comprising:
the scene setting module is used for setting an application scene of the robot matched with the environmental information according to the environmental information of the current robot, wherein the application scene comprises an interaction rule of robot interaction and interaction resources used during interaction;
the information acquisition module is used for acquiring user comprehensive information when the robot detects a user needing active interaction, wherein the user comprehensive information comprises personal information of the user and environmental information of a current robot system;
the processing module is electrically connected with the information acquisition module and is used for generating active interactive content matched with the user comprehensive information;
the interaction module is used for actively interacting with the user according to the active interaction content;
the processing module is further used for acquiring interaction resources matched with the user comprehensive information according to the interaction rules so as to generate active interaction content;
the interaction rule comprises a plurality of rule nodes, and each rule node represents the mapping relation between different user comprehensive information and different interaction resources;
the matching sub-module is used for judging whether all preset feature keywords and corresponding preset feature parameter values in each rule node are the same as part of feature keywords and corresponding feature parameter values in the user comprehensive information one by one; the characteristic keywords comprise user characteristic keywords and environment characteristic keywords, and the characteristic parameter values comprise user characteristic parameter values and environment characteristic parameter values; if so, taking the rule nodes meeting the conditions as candidate rule nodes;
the interactive content generation submodule is used for analyzing the respective priority values of a plurality of candidate rule nodes and sequencing the candidate rule nodes according to the priority values; selecting one candidate rule node from a plurality of candidate rule nodes with the same priority value to participate in sequencing; and sequentially combining the interaction resources corresponding to the sorted candidate rule nodes to generate the interaction content.
5. An interactive robot as claimed in claim 4, wherein:
the interaction resources include: voice content, action content, or multimedia content.
6. An interactive robot as claimed in any one of claims 4 to 5, wherein:
the personal information of the user includes: gender, age, expression, face angle, face spatial position, face occurrence frequency, user name, number of faces currently detected, and voice information;
the environmental information of the current robot system includes: time, place, temperature, weather, network connection status, system language.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810193098.5A CN108363492B (en) | 2018-03-09 | 2018-03-09 | Man-machine interaction method and interaction robot |
| PCT/CN2018/106780 WO2019169854A1 (en) | 2018-03-09 | 2018-09-20 | Human-computer interaction method, and interactive robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810193098.5A CN108363492B (en) | 2018-03-09 | 2018-03-09 | Man-machine interaction method and interaction robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108363492A CN108363492A (en) | 2018-08-03 |
| CN108363492B true CN108363492B (en) | 2021-06-25 |
Family
ID=63003702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810193098.5A Active CN108363492B (en) | 2018-03-09 | 2018-03-09 | Man-machine interaction method and interaction robot |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108363492B (en) |
| WO (1) | WO2019169854A1 (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363492B (en) * | 2018-03-09 | 2021-06-25 | 南京阿凡达机器人科技有限公司 | Man-machine interaction method and interaction robot |
| CN109409063A (en) * | 2018-10-10 | 2019-03-01 | 北京小鱼在家科技有限公司 | A kind of information interacting method, device, computer equipment and storage medium |
| CN109492074A (en) * | 2018-11-22 | 2019-03-19 | 广州小鹏汽车科技有限公司 | Intelligent greeting method, system, storage medium and automobile based on Weather information |
| CN110154048B (en) * | 2019-02-21 | 2020-12-18 | 北京格元智博科技有限公司 | Robot control method and device and robot |
| CN110097400A (en) * | 2019-04-29 | 2019-08-06 | 贵州小爱机器人科技有限公司 | Information recommendation method, apparatus and system, storage medium, intelligent interaction device |
| CN111949773A (en) * | 2019-05-17 | 2020-11-17 | 华为技术有限公司 | Reading equipment, server and data processing method |
| CN110716634A (en) * | 2019-08-28 | 2020-01-21 | 北京市商汤科技开发有限公司 | Interaction method, device, equipment and display equipment |
| CN112527095A (en) * | 2019-09-18 | 2021-03-19 | 奇酷互联网络科技（深圳）有限公司 | Man-machine interaction method, electronic device and computer storage medium |
| CN111176503A (en) * | 2019-12-16 | 2020-05-19 | 珠海格力电器股份有限公司 | Interactive system setting method and device and storage medium |
| CN111327772B (en) * | 2020-02-25 | 2021-09-17 | 广州腾讯科技有限公司 | Method, device, equipment and storage medium for automatic voice response processing |
| CN111428637A (en) * | 2020-03-24 | 2020-07-17 | 新石器慧通（北京）科技有限公司 | Method for actively initiating human-computer interaction by unmanned vehicle and unmanned vehicle |
| CN111993438A (en) * | 2020-08-26 | 2020-11-27 | 陕西工业职业技术学院 | an intelligent robot |
| CN113147771A (en) * | 2021-05-10 | 2021-07-23 | 前海七剑科技(深圳)有限公司 | Active interaction method and device based on vehicle-mounted virtual robot |
| CN114385000A (en) * | 2021-11-30 | 2022-04-22 | 达闼机器人有限公司 | Intelligent equipment control method, device, server and storage medium |
| CN115016636A (en) * | 2022-05-13 | 2022-09-06 | 北京百度网讯科技有限公司 | A distribution robot interaction method, device and electronic device |
| CN115009189A (en) * | 2022-06-23 | 2022-09-06 | 星河智联汽车科技有限公司 | A kind of vehicle weather broadcasting method, device and vehicle |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105598972A (en) * | 2016-02-04 | 2016-05-25 | 北京光年无限科技有限公司 | Robot system and interactive method |
| 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 |
| CN106462255A (en) * | 2016-06-29 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | A method, system and robot for generating interactive content of robot |
| CN106462254A (en) * | 2016-06-29 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | Robot interaction content generation method, system and robot |
| CN106489114A (en) * | 2016-06-29 | 2017-03-08 | 深圳狗尾草智能科技有限公司 | A kind of generation method of robot interactive content, system and robot |
| CN106537294A (en) * | 2016-06-29 | 2017-03-22 | 深圳狗尾草智能科技有限公司 | Method, system and robot for generating interactive content of robot |
| CN106537293A (en) * | 2016-06-29 | 2017-03-22 | 深圳狗尾草智能科技有限公司 | Method and system for generating robot interactive content, and robot |
| CN106625711A (en) * | 2016-12-30 | 2017-05-10 | 华南智能机器人创新研究院 | Method for positioning intelligent interaction of robot |
| CN106843463A (en) * | 2016-12-16 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of interactive output intent for robot |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701211A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Question-answering system-oriented active interaction data processing method and system |
| CN106774845B (en) * | 2016-11-24 | 2020-01-31 | 北京儒博科技有限公司 | An intelligent interaction method, device and terminal device |
| CN107045587A (en) * | 2016-12-30 | 2017-08-15 | 北京光年无限科技有限公司 | A kind of interaction output intent and robot for robot |
| CN108363492B (en) * | 2018-03-09 | 2021-06-25 | 南京阿凡达机器人科技有限公司 | Man-machine interaction method and interaction robot |
-
2018
- 2018-03-09 CN CN201810193098.5A patent/CN108363492B/en active Active
- 2018-09-20 WO PCT/CN2018/106780 patent/WO2019169854A1/en active Application Filing
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105598972A (en) * | 2016-02-04 | 2016-05-25 | 北京光年无限科技有限公司 | Robot system and interactive method |
| CN106462255A (en) * | 2016-06-29 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | A method, system and robot for generating interactive content of robot |
| CN106462254A (en) * | 2016-06-29 | 2017-02-22 | 深圳狗尾草智能科技有限公司 | Robot interaction content generation method, system and robot |
| CN106489114A (en) * | 2016-06-29 | 2017-03-08 | 深圳狗尾草智能科技有限公司 | A kind of generation method of robot interactive content, system and robot |
| CN106537294A (en) * | 2016-06-29 | 2017-03-22 | 深圳狗尾草智能科技有限公司 | Method, system and robot for generating interactive content of robot |
| CN106537293A (en) * | 2016-06-29 | 2017-03-22 | 深圳狗尾草智能科技有限公司 | Method and system for generating robot interactive content, and robot |
| 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 |
| CN106843463A (en) * | 2016-12-16 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of interactive output intent for robot |
| CN106625711A (en) * | 2016-12-30 | 2017-05-10 | 华南智能机器人创新研究院 | Method for positioning intelligent interaction of robot |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019169854A1 (en) | 2019-09-12 |
| CN108363492A (en) | 2018-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363492B (en) | Man-machine interaction method and interaction robot | |
| Eskimez et al. | Speech driven talking face generation from a single image and an emotion condition | |
| Alexanderson et al. | Listen, denoise, action! audio-driven motion synthesis with diffusion models | |
| Bhattacharya et al. | Text2gestures: A transformer-based network for generating emotive body gestures for virtual agents | |
| CN110647636B (en) | Interaction method, interaction device, terminal equipment and storage medium | |
| US11335062B2 (en) | Automated apparel design using machine learning | |
| Sonlu et al. | A conversational agent framework with multi-modal personality expression | |
| CN106297789B (en) | Personalized interaction method and system for intelligent robot | |
| Ahuja et al. | To react or not to react: End-to-end visual pose forecasting for personalized avatar during dyadic conversations | |
| CN110121706B (en) | Providing responses in a conversation | |
| US20200395008A1 (en) | Personality-Based Conversational Agents and Pragmatic Model, and Related Interfaces and Commercial Models | |
| KR102448382B1 (en) | Electronic device for providing an image associated with text and method for operating the same | |
| TWI430189B (en) | System, apparatus and method for message simulation | |
| JP2018014094A (en) | Virtual robot interaction method, system, and robot | |
| KR20020071917A (en) | User interface/entertainment device that simulates personal interaction and charges external database with relevant data | |
| KR20020067591A (en) | Self-updating user interface/entertainment device that simulates personal interaction | |
| KR20020067592A (en) | User interface/entertainment device that simulates personal interaction and responds to user's mental state and/or personality | |
| KR20020067590A (en) | Environment-responsive user interface/entertainment device that simulates personal interaction | |
| WO2018169001A1 (en) | Interactive system, interactive device and computer program therefor | |
| CN116541498A (en) | Providing emotion care in a conversation | |
| JP7044244B2 (en) | Reinforcement learning system | |
| CN113301352A (en) | Automatic chat during video playback | |
| WO2025044647A1 (en) | Emotion recognition method, pre-training method for emotion recognition model, and electronic device | |
| Rach et al. | Emotion recognition based preference modelling in argumentative dialogue systems | |
| CN113806620A (en) | Content recommendation method, device, system 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |