CN106843461A - A kind of interactive output intent and robot for robot - Google Patents
A kind of interactive output intent and robot for robot Download PDFInfo
- Publication number
- CN106843461A CN106843461A CN201611146822.6A CN201611146822A CN106843461A CN 106843461 A CN106843461 A CN 106843461A CN 201611146822 A CN201611146822 A CN 201611146822A CN 106843461 A CN106843461 A CN 106843461A
- Authority
- CN
- China
- Prior art keywords
- user
- competitive sports
- topic
- data
- robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a kind of interactive output intent and robot for robot.Method includes：Receive multi-modal input data and parse, judge that current whether there is can be as the competitive sports of topic；When exist can as the competitive sports of topic when judge whether the competitive sports not yet carry out or carrying out but not yet terminating；When the competitive sports are not yet carried out or are being carried out but not yet at the end of obtain the sample data of the various dimensions related to the competitive sports；The sample data is analyzed, competitive sports predicts the outcome described in the multi dimensional analysis prediction of result of the comprehensive sample data；Interacted with user as topic using the competitive sports, wherein, by multi-modal the output to the user that predict the outcome.Compared to prior art, the method according to the invention can greatly improve the interactive wish of user, improve the Consumer's Experience of man-machine interaction.
Description
Technical field
The present invention relates to robot field, and in particular to a kind of interactive output intent and robot for robot.
Background technology
With continuing to develop for robot technology, the increasing of intelligent robot is applied to the daily production of the mankind
In life.
In the prior art, one of most common man-machine interaction scene is robot and user's chat.But, existing
In man-machine interaction scene, the chat of robot and user is typically initiated and by user-driven by user, and robot can only be stayed
The passive enquirement to user of plate is done and is targetedly replied.It is very dull uninteresting that this allows for whole chat process, when user obtains
Getting can immediately stop chat process when oneself wanting the answer known, or even user carries twice in trial one under many circumstances
Just abandon puing question to after asking, it is one-sided to terminate interaction.
Therefore, in order to improve the interest that robot chats with user, the chat wish of user is improved, enhancing robot
Consumer's Experience is, it is necessary to a kind of more excellent interactive output intent.
The content of the invention
The invention provides a kind of interactive output intent for robot, methods described includes：
Receive multi-modal input data and parse, judge that current whether there is can be as the competitive sports of topic；
When exist can as the competitive sports of topic when judge whether the competitive sports not yet carry out or carrying out
But not yet terminate；
When the competitive sports are not yet carried out or are being carried out but not yet at the end of obtain related to the competitive sports
The sample data of various dimensions；
The sample data is analyzed, competitive sports is pre- described in the multi dimensional analysis prediction of result of the comprehensive sample data
Survey result；
Interacted with user as topic using the competitive sports, wherein, by it is described predict the outcome it is multi-modal export to
The user.
In one embodiment, judge it is current with the presence or absence of can as the competitive sports of topic, wherein, in man-machine interaction
In journey when the output content of the user includes the first competitive sports, judge that first competitive sports can be as topic.
In one embodiment, judge it is current with the presence or absence of can as the competitive sports of topic, wherein, detect and analyze institute
State the user behavior of user, when the user behavior is represented the user pays close attention to the second competitive sports when, judge described
Two competitive sports can be as topic.
In one embodiment, the sample data of the various dimensions related to the competitive sports is obtained, wherein, the sample number
According to comprising search data, social data, related race historical statistical data and user data, the user data is included and is directed to
User feedback data, the user behavior data for Above-the-line and the user's history intersection record actively putd question to.
In one embodiment, the sample data of the various dimensions related to the competitive sports is obtained, wherein, the sample number
According to comprising user preference, methods described also includes：
Gather multi-modal behavior of the user for the competitive sports；
Analyze the user preference that the multi-modal behavior is obtained and preserves the correspondence competitive sports；
The corresponding user preference is extracted according to the competitive sports as topic；
Predicting the outcome for the competitive sports is predicted with reference to the user preference；
Interacted with user as topic using the competitive sports with reference to the user preference.
In one embodiment：
Predicting the outcome for the competitive sports is predicted, wherein, obtain the multiple different of competitive sports and predict the outcome,
The corresponding probability of happening of the correspondence that predicted the outcome described in each；
By the output that predicts the outcome to the user, wherein, by the competitive sports it is multiple different predict the outcome,
Each corresponding probability of happening that predicts the outcome, prediction according to and information source is multi-modal exports to user.
The invention allows for a kind of intelligent robot, the robot includes：
Actualite parsing module, it is configured to receive multi-modal input data and parse, and judges that current whether there is can
As the competitive sports of topic；
Competitive sports process analysis module, its be configured to when exist can as the competitive sports of topic when judge the body
Educate whether race not yet carries out or carrying out but not yet terminating；
Competitive sports data acquisition module, it is configured to when the competitive sports are not yet carried out or carried out but not yet tied
The sample data of the various dimensions related to the competitive sports is obtained during beam；
Race prediction of result module, it is configured to analyze the sample data, the various dimensions point of the comprehensive sample data
Competitive sports predicts the outcome described in analysis prediction of result；
Interaction output module, it is configured to be interacted with user as topic using the competitive sports, wherein, will be described
Predict the outcome multi-modal output to the user.
In one embodiment, the actualite parsing module includes interaction content resolution unit, the interaction content solution
Analysis unit is configured in interactive process to judge when the output content of the user is comprising the first competitive sports described the
One competitive sports can be as topic.
In one embodiment, the actualite parsing module includes user behavior analysis unit, the user behavior point
Analysis unit is configured to detect and analyze the user behavior of the user, when the user behavior represents that the user is paying close attention to the
During two competitive sports, judge that second competitive sports can be as topic.
In one embodiment, the robot also also includes user preference acquisition module, the user comprising user data
Preference acquisition module is configured to：
Multi-modal behavior of the user for the competitive sports is gathered, the multi-modal behavior is analyzed and is obtained and preserve
The user preference of the correspondence competitive sports；
The corresponding user preference is extracted according to the competitive sports as topic.
The method of the present invention selects competitive sports as topic point of penetration by the prediction of result to competitive sports and user
Launch interaction.Compared to prior art, the method according to the invention can greatly improve the interactive wish of user, improve man-machine friendship
Mutual Consumer's Experience.
Further feature of the invention or advantage will be illustrated in the following description.Also, Partial Feature of the invention or
Advantage will be become apparent by specification, or be appreciated that by implementing the present invention.The purpose of the present invention and part
Advantage can be realized or obtained by specifically noted step in specification, claims and accompanying drawing.
Brief description of the drawings
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for specification, with reality of the invention
Apply example to be provided commonly for explaining the present invention, be not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is method flow diagram according to an embodiment of the invention；
Fig. 2 and Fig. 3 are the partial process views of method according to embodiments of the present invention；
Fig. 4 is competitive sports prediction of result information flow diagram according to an embodiment of the invention；
Fig. 5 and Fig. 6 are robot architecture's block diagrams according to embodiments of the present invention.
Specific embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, implementation personnel of the invention whereby
Can fully understand how application technology means solve technical problem for the present invention, and reach technique effect implementation process and according to
The present invention is embodied according to above-mentioned implementation process.If it should be noted that do not constitute conflict, each embodiment in the present invention
And each feature in each embodiment can be combined with each other, the technical scheme for being formed protection scope of the present invention it
It is interior.
In the prior art, one of most common man-machine interaction scene is robot and user's chat.But, existing
In man-machine interaction scene, the chat of robot and user is typically initiated and by user-driven by user, and robot can only be stayed
The passive enquirement to user of plate is done and is targetedly replied.It is very dull uninteresting that this allows for whole chat process, when user obtains
Getting can immediately stop chat process when oneself wanting the answer known, or even user carries twice in trial one under many circumstances
Just abandon puing question to after asking, it is one-sided to terminate interaction.
Therefore, in order to improve the interest that robot chats with user, the chat wish of user is improved, enhancing robot
Consumer's Experience, the present invention proposes a kind of interactive output intent for robot.
In the daily interaction scene of person to person, determine that one of strong and weak key of the talk wish of talk both sides is current
Chat script whether meet talk both sides interest.If talk both sides are interested in current chat script, then when
Preceding talk just can easily continue.Above-mentioned analysis is amplified in man-machine interaction scene, due to without the concern for machine
The talk interest of device people, it is only necessary to improve the talk interest of user as far as possible.So, the key of the chat wish of user is improved
One of point is just to maintain current topic content around user's content interested.
Further, in interactive process, robot carries out simple information if only specific topics are directed to
Push can cause the dry as dust of whole communication program (to go completely into a kind of information inquiry process, it is impossible to embody the sense of interaction
Feel).Therefore, in order to improve interactive interest, robot needs pair information related to topic to process, generates and export
Meet the interaction content (also, as far as possible, the interaction content will also meet the custom of active user) of mankind's talk custom.This
Require robot for the Treatment Analysis ability of information.But, the Treatment Analysis pattern of different types of information is not
With, therefore robot can not possibly possess the Treatment Analysis ability of all types of information.Therefore, in order to ensure current topic
It is topic that robot can be analyzed and processed, it is necessary to robot guides user to making certain control guiding in the selection of topic
Robot is familiar with and user's topic also interested is talked.
Further, during person to person is talked, competitive sports are passed through frequently as talk topic (most of users
Will be to some specific competitive sports interest interested), it is user that the associated topic of competitive sports has possibility higher
Interested.Therefore, in an embodiment of the present invention, cause in advance at the analysis of robot competitive sports associated topic
Reason ability, and as far as possible guide to competitive sports actualite in interactive process.
Further, for competitive sports, the focus of user has focused largely on the knot of competitive sports in the normal state
On fruit.Therefore, if for competitive sports result discuss have very big probability cause user concern (matching user
Point of interest).Especially, carry out prediction of result for still unclosed competitive sports and be even more very big probability attraction user.Cause
This, in an embodiment of the present invention, using the competitive sports interested to user as topic, around the prediction knot of the competitive sports
Fruit and user launch man-machine interaction, so as to ensure interest-degree of the user to man-machine interaction.
Next the detailed process of method according to embodiments of the present invention is described in detail based on accompanying drawing, in the flow chart of accompanying drawing
The step of showing can perform in comprising the such as one group computer system of computer executable instructions.Although in flow charts
The logical order of each step is shown, but in some cases, can be performing shown different from order herein or retouch
The step of stating.
As shown in figure 1, in one embodiment, robot receives multi-modal input data and parses in interactive process
(step S100), judges that current whether there is can be as competitive sports (user's competitive sports interested) (step of topic
S110)；But in the absence of can as the competitive sports of topic when carry out man-machine interaction (step S101) based on other interactive strategies,
And continue the new multi-modal input data (return to step S100) of mobile phone.
When exist can as the competitive sports of topic when to judge whether the competitive sports terminate (be not yet to start, opened
Beginning is carrying out but is not yet terminating or be over) (step S120).If the competitive sports are over, then directly
The result (step S141) of the competitive sports is obtained, the result based on the competitive sports is generated and exports multi-modal interaction data.
That is, with the competitive sports as topic, result and user around competitive sports launch man-machine interaction.
Obtained when the competitive sports are not over (carry out or not yet start) related to the competitive sports many
The sample data (step S131) of dimension；Analysis sample data, the multi dimensional analysis prediction of result physical culture match of comprehensive sample data
Thing predicts the outcome (step S132)；It is last to interact (step S133) as topic and user using the competitive sports, wherein,
The multi-modal output to user that predict the outcome that step S132 is obtained.That is, with the competitive sports as topic, around robot predicting
The race result for going out launches man-machine interaction with user.
The method according to the invention, interaction topic launches around the competitive sports interested to user, and by race
Predict the outcome and further attract the attention of user, so as to greatly improve the interest of man-machine interaction, strengthen the man-machine friendship of user
Mutual wish.
In the step shown in Fig. 1, one of key point is to judge that current whether there is can match as the physical culture of topic
Thing (step S110).In order to ensure the identified competitive sports as topic can be certain in step S110 increase user's
Man-machine interaction wish, needs to meet two conditions as the competitive sports of topic：
(1) active user has certain interest to the competitive sports, if user loses interest in, then should be around competitive sports
It is the interactive wish that cannot improve user exchange.
(2) current interactive occasion is adapted to talk about the competitive sports, if current interaction scenarios are not suitable for talking about the physical culture
Race (for example, user is absorbed in discusses other information), then carrying out exchange around the competitive sports will break normally
Exchange process, so as to reduce man-machine interaction experience, even if user has certain interest to the competitive sports, but cannot also carry
The interactive wish of user high.
Based on above-mentioned analysis, in an embodiment of the present invention, in step s 110, carried out by current interaction content
Analysis come determine whether exist can be as the competitive sports of topic.Specifically, when user's in interactive process
When output content includes certain competitive sports, then can illustrate that user is interested in the competitive sports first (otherwise will not be
The competitive sports are referred in interaction content), secondly, the competitive sports open to discussion of current interactive environment are (if interactive environment
Be not suitable for that the competitive sports are discussed, then user would not refer to the competitive sports in interaction content).Therefore, the now body
Educate race and can serve as topic.
As shown in Fig. 2 in one embodiment, obtain user's output (step S200), judge user export in content whether
Comprising competitive sports (step S210).If do not included, judgement there is currently no can be as the competitive sports (step of topic
S212).If comprising judgement there is currently can be as competitive sports (step S211) (user's output content institute of topic
Comprising competitive sports as topic).
Further, in some actual interaction scenarios, user may not have and be included in competitive sports interested
In the output of itself, but oneself concern to the competitive sports is embodied by user behavior.Therefore, in one embodiment, examine
Survey and analyze the user behavior of the user, when user behavior is represented user pays close attention to competitive sports when, then first can be with
Illustrate that user is (otherwise will not pay close attention to the competitive sports) interested in the competitive sports, secondly, current interactive environment can be with
Discuss that (behavior for paying close attention to the competitive sports does not produce interference to other behaviors of user, because if having for the competitive sports
Interference, user would not perform the behavior of concern competitive sports).Therefore, now the competitive sports can serve as topic.
As shown in figure 3, in one embodiment, detecting and analyzing user behavior (step S300), judge whether user pays close attention to
Competitive sports (step S310).If be not concerned with, judgement there is currently no can be as the competitive sports (step of topic
S312).If concern, judgement there is currently can be as competitive sports (step the S211) (physical culture of user's concern of topic
Race is used as topic).
Embodiment shown in Fig. 2 and Fig. 3 judges that current whether there is can be as the body of topic from two angles respectively
Educate race.Further, in an embodiment of the present invention, sentenced by the way of two angles shown in Fig. 2 and Fig. 3 are combined
Disconnected current whether there is can be as the competitive sports of topic.I.e. in interactive process, it is in detection user's output content
It is no comprising competitive sports while detection user behavior whether pay close attention to competitive sports.If either one detects body in two angles
Educate race, then be judged as exist can be as the competitive sports of topic.
Further, judge whether user's output content is carried out comprising competitive sports under man-machine interaction scene.
In some application scenarios, user does not produce with robot currently and interacts (user is performing other behaviors).In this kind of application
Under occasion, robot mainly judges whether user pays close attention to competitive sports by being analyzed to user behavior.That is, in non-man-machine friendship
Under mutual state, robot collection (looking on) user behavior judges whether user pays close attention to competitive sports.
Also, it is further, under non-man-machine interaction mode, if robot judges that user pays close attention to certain competitive sports,
Actively man-machine interaction can be initiated by topic of the competitive sports to user.
In the embodiment shown in fig. 1, in order to further improve the interactive interest of user, robot is not completed for current
Competitive sports carry out prediction of result, and launch to interact with user based on predicting the outcome.In this course, one of key point is
Predicting the outcome for more reliable (convincing) must be provided a user with, if it is filled with flaws to predict the outcome, then can drop on the contrary
The interactive wish of low user.In an embodiment of the present invention, in order to ensure the reliability for predicting the outcome, analyzed using big data
Mode carries out prediction of result.
In one embodiment, robot obtains the sample data of the various dimensions related to competitive sports and by sample number
According to analysis carry out prediction of result.Specifically, the sample data bag acquired in robot expands search data, and (such as Google becomes
Gesture, Baidu's index etc.), social data (such as microblogging, push away top grade), related race historical statistical data (such as newest integration row
Name, history is won the championship information etc.) and user data (human-computer dialogue data etc.).
Further, in one embodiment, search data, historical statistical information and social data are system background statistics,
User data is then gone through comprising the user feedback data, the user behavior data for Above-the-line putd question to for active and user
History intersection record.
Specifically, in one embodiment, being obtained by three kinds of forms " actively puing question to, customer problem is collected and online game "
User data.Actively put question to mainly with one kind similar to forms such as surveys, inquire the delicate fragrance preference of user.Customer problem is received
Collection generally refers to intelligent robot by the analysis to user's chat log, obtains some features.And online game is referred mainly to
Be by play form Mining Interesting information.
Further, after sample data has been collected, robot can extract special using heuritic approach from these data
Levy, while these data are divided into training set, checking collection and test set, by continuous training pattern and iterative model, obtain
To a relatively good forecast model, the Various types of data for being then based on newest collection is predicted the outcome.
Information flow direction schematic diagram as shown in Figure 4.Big data forecasting system collects user (A, B, C) by man-machine interaction layer
User data, from backstage collect historical statistical information, search data and social data.Then big data forecasting system passes through
Predicting the outcome for generating is fed back to user by man-machine interaction layer.
Further, generally, for a certain competitive sports, user is not merely the competitive sports of simple concern.
User also has the preference profiles in some details for competitive sports.For example for the competitive sports of confrontation class, user can be inclined
To in one party/a certain troop/certain player's (such as football match, user may significantly pay close attention to a certain branch team).Therefore,
In order to further improve the interactive wish of user, in one embodiment, robot enters around user's competitive sports of interest
Referring also to user preference during row interaction output.For example, user pays close attention to certain football match, and user's deflection and team A, then,
When using football match as topic, topic emphasis is just around team A for robot.
In order to obtain user preference, in one embodiment, multi-modal behavior of the robot collection user for competitive sports；
Analyze the user preference that the multi-modal behavior is obtained and preserves the correspondence competitive sports.Herein, user preference is to shift to an earlier date
Obtain and preserve (it is further, robot can obtain multiple users for the competitive sports of multiple differences user preference simultaneously
Preserve).When needing to carry out man-machine interaction around competitive sports, robot is (and current according to the competitive sports as topic
User) extract corresponding user preference.And it is further, with reference to predicting the outcome for user preference prediction competitive sports；And, knot
User preference is closed to be interacted with user as topic using competitive sports.
Further, so-called to predict the outcome, it is that it can happen that what is carried out estimates, will not be necessarily to following
One completely specified result.In order to avoid user understands deviation, and professional, the reliability for predicting the outcome are embodied, in this hair
In a bright embodiment, during acquisition predicts the outcome, obtain the multiple different of competitive sports and predict the outcome, each prediction
The corresponding probability of happening of result correspondence；It is corresponding, when the output that will predict the outcome is to user, by the multiple different of competitive sports
Predict the outcome, each corresponding probability of happening that predicts the outcome, prediction according to and information source is multi-modal exports to user.So
Can just allow user to understand that the prediction for predicting the outcome is originated, professional, the reliability of prediction of result be embodied, so as to improve user's
Interaction wish.In addition, the output of a large amount of related datas can also increase the auxiliary topic around the competitive sports, user is greatly improved
Further interaction wish.
To sum up, the method for the present invention selection competitive sports as topic point of penetration by the prediction of result to competitive sports with
User launches interaction.Compared to prior art, the method according to the invention can greatly improve the interactive wish of user, improve people
The Consumer's Experience of machine interaction.
Based on the method for the present invention, the invention allows for a kind of intelligent robot.As shown in figure 5, in one embodiment,
Robot includes：
Actualite parsing module 510, it is configured to receive multi-modal input data and parse, and judgement currently whether there is
Can be as the competitive sports of topic；
Competitive sports process analysis module 520, its be configured to when exist can as the competitive sports of topic when judge should
Whether competitive sports not yet carry out or are carrying out but not yet terminating；
Competitive sports data acquisition module 530, it is configured to when competitive sports are not yet carried out or carried out but not yet tied
The sample data of the various dimensions related to the competitive sports is obtained during beam；
Race prediction of result module 540, it is configured to analyze sample data, the multi dimensional analysis result of comprehensive sample data
Predict predicting the outcome for competitive sports；
Race result acquisition module 560, its actual knot for being configured to be obtained at the end of competitive sports the competitive sports
Really；
Interaction output module 550, it is configured to be interacted with user as topic using competitive sports, wherein, will predict
Result or actual result is multi-modal exports to user.
Further, in one embodiment, actualite parsing module includes interaction content resolution unit, interaction content solution
Analysis unit is configured in interactive process to judge when the output content of user is comprising competitive sports that the competitive sports can be with
As topic.
Further, in one embodiment, actualite parsing module includes user behavior analysis unit, user behavior point
Analysis unit is configured to detect and analyze the user behavior of user, when user behavior is represented user pays close attention to competitive sports when, sentence
Breaking the competitive sports can be as topic.
Further, in one embodiment, robot also includes user preference acquisition module, and user preference collecting unit is matched somebody with somebody
Multi-modal behavior of the collection user for the competitive sports is set to, multi-modal behavior is analyzed and is obtained and preserve correspondence competitive sports
User preference；When needing to carry out man-machine interaction around competitive sports, extract corresponding according to as the competitive sports of topic
User preference.
As shown in fig. 6, actualite parsing module 610 is configured to receive multi-modal input data and parse, judge current
With the presence or absence of can be as the competitive sports of topic；
Competitive sports process analysis module 620 be configured to when exist can as the competitive sports of topic when judge the physical culture
Whether race not yet carries out or is carrying out but not yet terminating；
Competitive sports data acquisition module 630 be configured to when competitive sports are not yet carried out or are being carried out but not yet at the end of
Obtain the sample data of the various dimensions related to the competitive sports；
User preference acquisition module 670 is configured to obtain and preserve the user preference of correspondence competitive sports, according to as words
Corresponding user preference is extracted in the competitive sports of topic
Race prediction of result module 640 is configured to analyze sample data, with reference to the multidimensional of user preference synthesis sample data
Degree analysis result predicts predicting the outcome for competitive sports；
Race result acquisition module 660 is configured to be obtained at the end of competitive sports the actual result of the competitive sports；
Interaction output module 650 is configured to be interacted with user as topic using competitive sports with reference to user preference, its
In, will predict the outcome or actual result is multi-modal exports to user.
While it is disclosed that implementation method as above, but described content is only to facilitate understanding the present invention and adopting
Implementation method, is not limited to the present invention.Method of the present invention can also have other various embodiments.Without departing substantially from
In the case of essence of the present invention, those of ordinary skill in the art work as can make various corresponding changes or change according to the present invention
Shape, but these corresponding changes or deformation should all belong to scope of the claims of the invention.
Claims (10)
1. a kind of interactive output intent for robot, it is characterised in that methods described includes：
Receive multi-modal input data and parse, judge that current whether there is can be as the competitive sports of topic；
When exist can as the competitive sports of topic when judge whether the competitive sports not yet carry out or carrying out but still
Do not terminate；
When the competitive sports are not yet carried out or are being carried out but not yet at the end of obtain the multidimensional related to the competitive sports
The sample data of degree；
The sample data is analyzed, the prediction knot of competitive sports described in the multi dimensional analysis prediction of result of the comprehensive sample data
Really；
Interacted with user as topic using the competitive sports, wherein, by multi-modal the output to described that predict the outcome
User.
2. method according to claim 1, it is characterised in that judge current with the presence or absence of can be matched as the physical culture of topic
Thing, wherein, in interactive process when the output content of the user includes the first competitive sports, judge first body
Educating race can be as topic.
3. method according to claim 1, it is characterised in that judge current with the presence or absence of can be matched as the physical culture of topic
Thing, wherein, the user behavior of the user is detected and analyzes, when the user behavior represents that the user is paying close attention to the second body
When educating race, judge that second competitive sports can be as topic.
4. method according to claim 1, it is characterised in that obtain the sample of the various dimensions related to the competitive sports
Data, wherein, the sample data includes search data, social data, related race historical statistical data and user data,
The user data is comprising for the user feedback data, the user behavior data for Above-the-line actively putd question to and user
History intersection record.
5. method according to claim 1, it is characterised in that obtain the sample of the various dimensions related to the competitive sports
Data, wherein, the sample data includes user preference, and methods described also includes：
Gather multi-modal behavior of the user for the competitive sports；
Analyze the user preference that the multi-modal behavior is obtained and preserves the correspondence competitive sports；
The corresponding user preference is extracted according to the competitive sports as topic；
Predicting the outcome for the competitive sports is predicted with reference to the user preference；
Interacted with user as topic using the competitive sports with reference to the user preference.
6. method according to claim 1, it is characterised in that：
Predicting the outcome for the competitive sports is predicted, wherein, obtain the multiple different of competitive sports and predict the outcome, each
The corresponding probability of happening of correspondence that predicts the outcome；
By the output that predicts the outcome to the user, wherein, by the competitive sports it is multiple different predict the outcome, each
Predict the outcome corresponding probability of happening, prediction according to and information source is multi-modal exports to user.
7. a kind of intelligent robot, it is characterised in that the robot includes：
Actualite parsing module, it is configured to receive multi-modal input data and parse, and judges that current whether there is can make
It is the competitive sports of topic；
Competitive sports process analysis module, its be configured to when exist can as the competitive sports of topic when judge physical culture match
Whether thing not yet carries out or is carrying out but not yet terminating；
Competitive sports data acquisition module, its be configured to when the competitive sports are not yet carried out or are being carried out but not yet at the end of
Obtain the sample data of the various dimensions related to the competitive sports；
Race prediction of result module, it is configured to analyze the sample data, the multi dimensional analysis knot of the comprehensive sample data
Fruit predicts predicting the outcome for the competitive sports；
Interaction output module, it is configured to be interacted with user as topic using the competitive sports, wherein, by the prediction
Result is multi-modal to be exported to the user.
8. robot according to claim 7, it is characterised in that the actualite parsing module includes interaction content solution
Analysis unit, the interaction content resolution unit is configured in interactive process include first when the output content of the user
Judge that first competitive sports can be as topic during competitive sports.
9. robot according to claim 7, it is characterised in that the actualite parsing module includes user behavior point
Analysis unit, the user behavior analysis unit is configured to detect and analyze the user behavior of the user, when the user behavior
When representing that the user pays close attention to the second competitive sports, judge that second competitive sports can be as topic.
10. robot according to claim 7, it is characterised in that the robot is also comprising user data also comprising using
Family preference acquisition module, the user preference acquisition module is configured to：
Multi-modal behavior of the user for the competitive sports is gathered, the multi-modal behavior is analyzed and is obtained and preserve correspondence
The user preference of the competitive sports；
The corresponding user preference is extracted according to the competitive sports as topic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611146822.6A CN106843461B (en) | 2016-12-13 | 2016-12-13 | Interactive output method for robot and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611146822.6A CN106843461B (en) | 2016-12-13 | 2016-12-13 | Interactive output method for robot and robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106843461A true CN106843461A (en) | 2017-06-13 |
| CN106843461B CN106843461B (en) | 2020-06-26 |
Family
ID=59139817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611146822.6A Active CN106843461B (en) | 2016-12-13 | 2016-12-13 | Interactive output method for robot and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106843461B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562863A (en) * | 2017-08-30 | 2018-01-09 | 深圳狗尾草智能科技有限公司 | Chat robots reply automatic generation method and system |
| CN108595420A (en) * | 2018-04-13 | 2018-09-28 | 畅敬佩 | A kind of method and system of optimization human-computer interaction |
| CN112272581A (en) * | 2018-01-21 | 2021-01-26 | 斯塔特斯公司 | Method and system for interactive, exposable and improved game and player performance prediction in team sports |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001188782A (en) * | 1999-12-28 | 2001-07-10 | Sony Corp | Device and method for processing information and recording medium |
| CN104200090A (en) * | 2014-08-27 | 2014-12-10 | 百度在线网络技术（北京）有限公司 | Prediction method and method based on multi-source heterogeneous data |
| CN105138671A (en) * | 2015-09-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Human-computer interaction guiding method and device based on artificial intelligence |
| CN105798918A (en) * | 2016-04-29 | 2016-07-27 | 北京光年无限科技有限公司 | Interactive method and device for intelligent robot |
| CN106200962A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Exchange method and system towards intelligent robot |
-
2016
- 2016-12-13 CN CN201611146822.6A patent/CN106843461B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001188782A (en) * | 1999-12-28 | 2001-07-10 | Sony Corp | Device and method for processing information and recording medium |
| CN104200090A (en) * | 2014-08-27 | 2014-12-10 | 百度在线网络技术（北京）有限公司 | Prediction method and method based on multi-source heterogeneous data |
| CN105138671A (en) * | 2015-09-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Human-computer interaction guiding method and device based on artificial intelligence |
| CN105798918A (en) * | 2016-04-29 | 2016-07-27 | 北京光年无限科技有限公司 | Interactive method and device for intelligent robot |
| CN106200962A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Exchange method and system towards intelligent robot |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562863A (en) * | 2017-08-30 | 2018-01-09 | 深圳狗尾草智能科技有限公司 | Chat robots reply automatic generation method and system |
| CN112272581A (en) * | 2018-01-21 | 2021-01-26 | 斯塔特斯公司 | Method and system for interactive, exposable and improved game and player performance prediction in team sports |
| CN108595420A (en) * | 2018-04-13 | 2018-09-28 | 畅敬佩 | A kind of method and system of optimization human-computer interaction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106843461B (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bigham et al. | Human-computer interaction and collective intelligence | |
| CN108536681A (en) | Intelligent answer method, apparatus, equipment and storage medium based on sentiment analysis | |
| CN106845624A (en) | The multi-modal exchange method relevant with the application program of intelligent robot and system | |
| O’Connor | Using grounded theory coding mechanisms to analyze case study and focus group data in the context of software process research | |
| CN110232573A (en) | Based on interactive intelligent response system | |
| CN109712618A (en) | A kind of control method of voice service, device, storage medium and air-conditioning | |
| US20210240927A1 (en) | Asynchronous role-playing system for dialog data collection | |
| CN106843461A (en) | A kind of interactive output intent and robot for robot | |
| Okon et al. | Detecting distracted driving with deep learning | |
| Carlson et al. | What goes without saying | |
| Bakhtiyari et al. | Fuzzy model of dominance emotions in affective computing | |
| Bakhtiyari et al. | Fuzzy model on human emotions recognition | |
| CN111612178A (en) | Model diagnosis method and related equipment | |
| Zhang et al. | Event organization 101: Understanding latent factors of event popularity | |
| Zeng et al. | What changed your mind: The roles of dynamic topics and discourse in argumentation process | |
| Daggett et al. | Predicting team performance through human behavioral sensing and quantitative workflow instrumentation | |
| CN105894017B (en) | Online activity recognition methods and system based on Markov Logic Network | |
| CN112927692A (en) | Automatic language interaction method, device, equipment and medium | |
| Langer et al. | Explainability of artificial intelligence in human resources | |
| Boussemart et al. | Behavioral recognition and prediction of an operator supervising multiple heterogeneous unmanned vehicles | |
| US10762339B2 (en) | Automatic emotion response detection | |
| CN109165327B (en) | Man-machine conversation method, device and computer readable storage medium | |
| CN115206328A (en) | Data processing method and device and customer service robot | |
| Araki et al. | Collection of multimodal dialog data and analysis of the result of annotation of users’ interest level | |
| CN107832342A (en) | Robot chat method and system |
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 |