CN107045587A - A kind of interaction output intent and robot for robot - Google Patents
A kind of interaction output intent and robot for robot Download PDFInfo
- Publication number
- CN107045587A CN107045587A CN201611262279.6A CN201611262279A CN107045587A CN 107045587 A CN107045587 A CN 107045587A CN 201611262279 A CN201611262279 A CN 201611262279A CN 107045587 A CN107045587 A CN 107045587A
- Authority
- CN
- China
- Prior art keywords
- health
- personal information
- user
- fitness tip
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Abstract
The invention discloses a kind of interaction output intent and robot for robot.Methods described includes:The multi-modal input information of collection is simultaneously parsed, and obtains the Health & Fitness Tip interaction demand of active user;Obtain the personal information of the active user associated with the Health & Fitness Tip interaction demand;Based on the Health & Fitness Tip interaction demand and personal information search knowledge base, generation is directed to the Health & Fitness Tip of the Health & Fitness Tip interaction demand, wherein, the Health & Fitness Tip is matched with the personal information;The multi-modal output Health & Fitness Tip.The method according to the invention, robot can export the Health & Fitness Tip of correspondence individual subscriber feature needed for user, not only extend the application of robot, and ensure that the validity of Health & Fitness Tip, substantially increase the Consumer's Experience of robot.
Description
Technical field
The present invention relates to robot field, and in particular to a kind of interaction output intent and robot for robot.
Background technology
(whether such as body weight is exceeded, taken exercise by what in the health problem frequently encountered in life by current people
The discomfort of mode energy rapid recovery body, eat what contribute to eliminate catch a cold etc.) when, generally will not directly go to hospital to see the doctor,
But voluntarily search the settling mode (consulting friends and family) for obtaining these health problems.
With the continuous popularization of internet, the settling mode that people obtain daily common health problem is increasing
It is partial to search for the Health & Fitness Tip for obtaining correspondence health problem on the internet using search engine.But, in prior art ring
Under border, the Health & Fitness Tip that acquisition is searched on the internet is usually the health problem inputted described in strict matching user.Due to
The health problem of user's input is generally only described comprising fundamental problem, and this allows for the Health & Fitness Tip that finally obtains in fact not
The actual conditions of user can be matched well, also just not can solve the actual health problem of user.Especially, by
In the professional person of user's not health field, usually occur when inputting health problem and state unclear situation, this just makes
Obtaining the validity of Health & Fitness Tip further reduces.
The content of the invention
The invention provides a kind of interaction output intent for robot, methods described includes:
The multi-modal input information of collection is simultaneously parsed, and obtains the Health & Fitness Tip interaction demand of active user;
Obtain the personal information of the active user associated with the Health & Fitness Tip interaction demand;
Based on the Health & Fitness Tip interaction demand and personal information search knowledge base, generation is built for the health
The Health & Fitness Tip of interaction demand is discussed, wherein, the Health & Fitness Tip is matched with the personal information;
The multi-modal output Health & Fitness Tip.
In one embodiment, gather multi-modal input information and parse, wherein, user speech and/or user behavior are entered
Row parsing.
In one embodiment, gather multi-modal input information and parse, wherein:
Determine the active user with the presence or absence of the intention for obtaining Health & Fitness Tip;
Determine whether the active user needs to receive Health & Fitness Tip according to the state of the active user.
In one embodiment, the personal information of the active user associated with the Health & Fitness Tip interaction demand is obtained,
Wherein:
The personal information is extracted from the personal information preserved;
And/or,
Initiate to inquire to the active user, obtain the personal information.
In one embodiment, methods described also includes:
Personal information and the preservation of user is gathered in interactive process, wherein:
Parsing it is related to user it is multi-modal interactively enter, extraction it is described it is multi-modal interactively enter in it is including with healthy phase
The personal information of pass;
And/or,
The inquiry for the personal information actively is initiated to user, with health according to being obtained the response of the user
Related personal information.
The invention also provides a kind of robot, the robot includes:
Requirement validation module, it is configured to gather multi-modal input information and parsed, and obtains the Health & Fitness Tip of active user
Interaction demand;
Personal information extraction module, it is configured to obtain the active user associated with the Health & Fitness Tip interaction demand
Personal information;
Health & Fitness Tip acquisition module, it is configured to the Health & Fitness Tip interaction demand and personal information search
Knowledge base, generation is directed to the Health & Fitness Tip of the Health & Fitness Tip interaction demand, wherein, the Health & Fitness Tip and the personal information
Matching;
Output module, it is configured to the multi-modal output Health & Fitness Tip.
In one embodiment, the requirement validation module is included:
Speech analysis unit, it is configured to parse user speech;
And/or,
Behavior resolution unit, it is configured to parse user behavior.
In one embodiment, the requirement validation module is included:
Interaction is intended to confirmation unit, and it is configured to determine the active user with the presence or absence of the intention for obtaining Health & Fitness Tip;
Ownness's confirmation unit, its be configured to according to the state of the active user determine the active user whether need
Receive Health & Fitness Tip.
In one embodiment, the personal information extraction module is configured to:
The personal information is extracted from the personal information preserved;
And/or,
Initiate to inquire to the active user, obtain the personal information.
In one embodiment, the robot also includes personal information acquisition module, and it is configured in interactive process
The personal information of middle collection user and preservation, wherein:
Parsing it is related to user it is multi-modal interactively enter, extraction it is described it is multi-modal interactively enter in it is including with healthy phase
The personal information of pass;
And/or,
The inquiry for the personal information actively is initiated to user, with health according to being obtained the response of the user
Related personal information.
The method according to the invention, robot can export the Health & Fitness Tip of correspondence individual subscriber feature needed for user,
The application of robot is not only extended, and relative to traditional network health consultation way, is good for by robot
Health is seeked advice from, and the suggestion provided meets the individual state of user closer to user's request, it is ensured that the validity of Health & Fitness Tip, greatly
The big Consumer's Experience for improving robot.
The further feature or advantage of the present invention will be illustrated in the following description.Also, the present invention Partial Feature 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, the reality with the present 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~Fig. 4 is the partial process view of method according to embodiments of the present invention;
Fig. 5 and Fig. 8 are robot system architecture's sketches according to embodiments of the present invention;
Fig. 6 and Fig. 7 are robot system part-structure sketches according to embodiments of the present invention.
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, whereby implementation personnel of the invention
Can fully understand how application technology means solve technical problem by 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 formed protection scope of the present invention it
It is interior.
(whether such as body weight is exceeded, taken exercise by what in the health problem frequently encountered in life by current people
The discomfort of mode energy rapid recovery body, eat what contribute to eliminate catch a cold etc.) when, generally will not directly go to hospital to see the doctor,
But voluntarily search the settling mode (consulting friends and family) for obtaining these health problems.
With the continuous popularization of internet, the settling mode that people obtain daily common health problem is increasing
It is partial to search for the Health & Fitness Tip for obtaining correspondence health problem on the internet using search engine.But, in prior art ring
Under border, the Health & Fitness Tip that acquisition is searched on the internet is usually the health problem inputted described in strict matching user.Due to
The health problem of user's input is generally only described comprising fundamental problem, and this allows for the Health & Fitness Tip that finally obtains in fact not
The actual conditions of user can be matched well, also just not can solve the actual health problem of user.Especially, by
In the professional person of user's not health field, usually occur when inputting health problem and state unclear situation, this just makes
Obtaining the validity of Health & Fitness Tip further reduces.
In view of the above-mentioned problems, the present invention proposes a kind of interaction output intent for robot.Implement in the present invention one
In example, when user's unsoundness advises interaction demand (needing robot to export Health & Fitness Tip to user), robot passes through search
Knowledge base obtains the Health & Fitness Tip of the Health & Fitness Tip interaction demand for user.During search, robot is not only
According only to user Health & Fitness Tip interaction demand carry out matching search, but also with reference to the individual subscriber user profile to health
It is recommended that being matched.So, just the final Health & Fitness Tip exported to user can be caused to be adapted to the user as far as possible, so as to ensure
The validity of Health & Fitness Tip.
Next it is described in detail based on accompanying drawing in the detailed process of method according to embodiments of the present invention, the flow chart of accompanying drawing
The step of showing can perform in the computer system comprising such as one group computer executable instructions.Although in flow charts
The logical order of each step is shown, but in some cases, can be to perform shown different from order herein or retouch
The step of stating.
As shown in figure 1, in one embodiment, the multi-modal input information (step S100) of robot collection simultaneously parses (step
S110), so as to obtain the Health & Fitness Tip interaction demand (step S120) of active user;Next the personal letter of active user is obtained
Cease (step S130);Health & Fitness Tip interaction demand and personal information search knowledge base are then based on, generation is directed to Health & Fitness Tip
The Health & Fitness Tip (step S140) of interaction demand;Last multi-modal output Health & Fitness Tip (step S150).
The method according to the invention, robot can export the Health & Fitness Tip of correspondence individual subscriber feature needed for user,
The application of robot is not only extended, and ensure that the validity of Health & Fitness Tip, the user of robot is substantially increased
Experience.
One of key point of above-mentioned steps is step S140.In this step, due to based on Health & Fitness Tip interaction demand
And personal information searches for knowledge base and generates Health & Fitness Tip, this allows for Health & Fitness Tip and matched with personal information, so as to ensure
Health & Fitness Tip matches the personal considerations of active user as far as possible, and then ensure that the validity of Health & Fitness Tip.
Further, in order to further improve the validity of Health & Fitness Tip, it is to avoid export unnecessary information to user,
It is not to obtain all personal information preserved for active user in step s 130, but extract in one embodiment
With the current related personal information of Health & Fitness Tip interaction demand in personal information.Step S140 can thus be effectively improved
The specific aim of middle search operation, improves search efficiency, it is ensured that the validity of search result.
Further, in common interaction scenarios, interaction demand is typically a larger directionality concept, in order to enter
One step improves the specific aim of search operation in step S140, improves search efficiency, in one embodiment, active user is being determined
Health & Fitness Tip interaction demand after, also make further parsing to the Health & Fitness Tip interaction demand, therefrom extracting directly to be carried out
The health problem request of knowledge base searching.The essence of this step be the Health & Fitness Tip interaction demand of user is embodied, hypostazation,
Object search scope in reduction process S140 as far as possible, so as to improve the formation efficiency of Health & Fitness Tip and ensure Health & Fitness Tip
Validity.
As shown in Fig. 2 in one embodiment, the multi-modal input information (step S200) of robot collection simultaneously parses (step
S210), judge that active user whether there is Health & Fitness Tip interaction demand (step S220) according to analysis result;If it does not,
Then interacted (step S240) with user using other interactive strategies;If there is Health & Fitness Tip interaction demand in user,
By further parsing the health problem (S230) corresponding to the health interacting demand for determining user, and next based on health
Problem carries out the acquisition of userspersonal information and the generation of Health & Fitness Tip afterwards.
In the interaction scenarios of person to person, A provides Health & Fitness Tip to B and is generally basede on two kinds of reasons, one is B is actively to A
Represent, oneself needs Health & Fitness Tip.Such as B is actively proposed " could you tell me how to lose weight " to A.Another reason is A it was observed that B
Be not in good state, it is necessary to receive Health & Fitness Tip, then actively provide Health & Fitness Tip to B.For example, A has found that the nearest body weight of B explodes,
Then actively proposed " you are too fat recently, and I tells you a ways of preventing obesity " to B.
In an embodiment of the present invention, in order to improve the Consumer's Experience of robot as far as possible, therefore the friendship of robot is made
Mutually strategy simulates the interaction habits of person to person as far as possible.Specifically, robot to be replaced with to the A of above-mentioned scene, based on two sides
The analysis in face come confirm active user whether there is Health & Fitness Tip interaction demand.
(1) determine active user with the presence or absence of the intention for obtaining Health & Fitness Tip.Specifically, by pair related to user defeated
Enter data (the multi-modal of user interactively enters data and user other associated property datas) to be analyzed, determine that user is current
Whether the intention of active obtaining Health & Fitness Tip is had.
Further, in common interaction scenarios, two kinds of situations be generally there are:
One is that user directly demands Health & Fitness Tip to robot.For example, when user's direct access inquiry " what if having caught a cold ".
Two be that user does not have and directly seeks Health & Fitness Tip to robot, but pass through other approach and obtain Health & Fitness Tip.
For example, user does not inquire robot, but voluntarily " what if having caught a cold " is searched on network.
For above-mentioned two situations, in an embodiment of the present invention, robot determines that active user is by two kinds of approach
It is no to there is the intention for obtaining Health & Fitness Tip.First, robot is entered data to by parsing user for the multi-modal of robot
Determine active user with the presence or absence of the intention for obtaining Health & Fitness Tip.Secondly, robot gathers and analyzes user behavior, confirms user
It is current to whether there is the behavior for soliciting Health & Fitness Tip.
(2) determine whether the active user needs to receive Health & Fitness Tip according to the state of active user.Specifically, passing through
Pair input data related to user (the multi-modal of user interactively enters data and user other associated property datas) is carried out
Analysis, determines the current state of user, and then further whether analysis is necessary actively to provide strong for the current state of user
Kang Jianyi.
For example, robot collect user cough, have a running nose, by parsing confirm user it is sick and be likely to be sense
Emit.So that it is determined that needing to user's Health & Fitness Tip that actively output is caught a cold about treatment.
To sum up, in one embodiment, robot confirms that active user whether there is the process of Health & Fitness Tip interaction demand such as
Shown in Fig. 3.The multi-modal input information (step S300) of robot collection simultaneously parses (step S310), obtains the intention of user currently
(step S320).Specifically, the intention of user includes, user is intended to for the interaction of current robot and user is not pin
Behavior to other behavioral activities of robot is intended to.
Then judge user be intended to whether comprising obtain Health & Fitness Tip intention (user whether be intended to obtain health builds
View) (step S330).When user view obtains Health & Fitness Tip, determine that user wants the corresponding health of Health & Fitness Tip obtained
Next problem (obtaining Health & Fitness Tip interaction demand) (step S370) simultaneously carries out obtaining for userspersonal information based on health problem
Take and Health & Fitness Tip afterwards generation.
When user does not obtain the intention of Health & Fitness Tip, state (such as health status) (step of user is confirmed
S340);Whether needed to receive whether Health & Fitness Tip (currently needs robot actively to user according to the condition adjudgement user of user
Initiate Health & Fitness Tip) (step S350);If user needs to receive Health & Fitness Tip, determine that user wants the Health & Fitness Tip obtained
Next corresponding health problem (obtaining Health & Fitness Tip interaction demand) (step S370) simultaneously carries out user based on health problem
The acquisition of people's information and the generation of Health & Fitness Tip afterwards.If user does not need Health & Fitness Tip, other interactions are taken
Strategy is interacted with user.
Further, in an embodiment of the present invention, robot collection is multi-modal inputs information and parses, so as to obtain strong
Kang Jianyi interaction demands.Specifically, robot is parsed to user speech and/or user behavior, confirmed based on analysis result
The Health & Fitness Tip interaction demand of user.
Further, in the step S130 shown in Fig. 1, it is current that robot acquisition is associated with Health & Fitness Tip interaction demand
The personal information of user.Specifically, in an embodiment of the present invention, robot extracts matching from the personal information preserved
Personal information.
But, sometimes, robot may not preserve the Health & Fitness Tip interaction of correspondence association active user
Demand personal information.For such case, in an alternative embodiment of the invention, personal information is obtained using the method for inquiry.
The inquiry for personal information is initiated to active user, according to the answer personal information of user.
Specifically, as shown in figure 4, in one embodiment, being needed when the Health & Fitness Tip that robot gets active user is interacted
After asking, first determine whether currently whether preserve the personal information (step of the above-mentioned Health & Fitness Tip interaction demand of association of active user
S400), if so, then extracting the personal information (step S410).If it is not, inquiry (step S430) is initiated to user,
Answer based on user obtains personal information (step S430).
Further, in one embodiment, in order to reduce the data processing amount of matching search personal information, shown in Fig. 4
S400 points of several stages of step are carried out, and are to determine whether to preserve the personal information of correspondence active user first, if it is not,
It is directly entered step S420.If there is the personal information of correspondence active user, it is determined that whether there is in personal information with working as
The associated personal information of the Health & Fitness Tip interaction demand of preceding user, if it is not, into step S420, if so, then entering
Enter step S410.
Further, in one embodiment, when in the presence of the individual associated with the Health & Fitness Tip interaction demand of active user
During information, robot also judges whether enough whether generation Health & Fitness Tip (can be by obtaining further letter for the personal information
Cease further to reduce matching hunting zone during generation Health & Fitness Tip).If robot judges to need to obtain more personal
Information, then initiate to inquire to user while the personal information preserved is extracted, obtain more detailed personal information.
In the above-described embodiments, the premise that robot directly extracts personal information (being obtained not by inquiry user) is machine
Device people has preserved at end the personal information of the user.To realize this function, in an embodiment of the present invention, it is also proposed that collection
Record the step flow of userspersonal information.Specifically, being carried out in robot and user during other interacts in man-machine friendship
The personal information of collection user and preservation during mutually, so that can extract individual during generation Health & Fitness Tip after
People's information.
Further, in one embodiment, the mode of timely intersection record is taken to obtain personal information.Specifically, in machine
During the daily use of device people, parse it is related to user it is multi-modal interactively enter, extract and accumulate multi-modal interactively enter
In include to the related personal information of health.I.e.:
(1) robot is based on other topics and carries out man-machine interaction with user, when the interaction content that user exports includes user
Healthy class personal information when, robot is recorded preservation.For example, user tells robot that " I makes to dessert feels emerging very much
Interest, because I has a sweet tooth very much, almost sweet food is not from mouth ".Then while current interaction content be for user preferences this
Topic, but the health problem of user can be but associated with this diet hobby by often eating sweet food, therefore robot will
User often eats sweet food record in the personal information of user.
(2) data such as behavioural information, appearance information of robot collection user, the healthy class for therefrom parsing user is personal
Information.For example, robot gathers the daily bedtime of user, got up the time, the sleep habit and record of user is therefrom parsed.
Because the personal information collection behavior of robot is incidentally implemented during other interbehaviors are performed, because
The personal information collection behavior of this robot does not interfere with other activities of user.But the shortcoming of this acquisition mode is desirable
Long period carries out data accumulation analysis, also, is easy to record mistake in data deficiencies or data acquisition error
Personal information.
In view of the above-mentioned problems, in one embodiment, personal information is obtained by the way of inquiry record.Specifically, actively
The inquiry for personal information is initiated to user, the personal information related to health is obtained according to the response of user.
Based on method proposed by the present invention, the invention also provides a kind of robot.As shown in figure 5, in one embodiment,
Robot includes:
Requirement validation module 500, it is configured to gather multi-modal input information and parsed, and the health for obtaining active user is built
Discuss interaction demand;
Personal information extraction module 510, it is configured to for obtaining the active user associated with Health & Fitness Tip interaction demand
People's information;
Health & Fitness Tip acquisition module 520, it is configured to Health & Fitness Tip interaction demand and personal information search knowledge
Storehouse, generation is directed to the Health & Fitness Tip of Health & Fitness Tip interaction demand, wherein, Health & Fitness Tip is matched with personal information;
Output module 530, it is configured to multi-modal output Health & Fitness Tip.
Further, in one embodiment, as shown in fig. 6, the requirement validation module 600 of robot includes speech analysis list
Member 611 and behavior resolution unit 612, wherein:
Speech analysis unit 611 is configured to parse user speech;
Behavior resolution unit 612 is configured to parse user behavior.
Multi-modal input information is input to speech analysis unit 611 or behavior resolution unit according to different data categories
612 are parsed.The input voice data of such as user is sent to speech analysis unit 611, behavioral data (user's row of user
For image acquisition data) it is sent to behavior resolution unit 612.
Further, in other embodiments, speech analysis unit and behavior solution can be only constructed in requirement validation module
Analyse one in unit.
Further, in one embodiment, as shown in fig. 7, requirement validation module 700 is included:
Interaction is intended to confirmation unit 711, and it is configured to determine active user with the presence or absence of the intention for obtaining Health & Fitness Tip;
Ownness's confirmation unit 712, it is configured to determine whether active user needs to connect according to the state of active user
By Health & Fitness Tip.
Further, in one embodiment, speech analysis unit and/or behavior resolution unit are intended to confirmation unit with interacting
And ownness's confirmation unit be combined with each other.That is, speech analysis unit and/or behavior resolution unit is provided with interacting meaning
The function of figure confirmation unit and ownness's confirmation unit, in other words, interaction is intended to confirmation unit and ownness confirms
Unit employs the data dissection process mode of speech analysis unit and/or behavior resolution unit.
Further, in one embodiment, personal information extraction module is configured to:
Personal information is extracted from the personal information preserved;
And/or,
Initiate to inquire to active user, obtain personal information.
Specifically, as shown in figure 8, in one embodiment, requirement validation module 500 gathers multi-modal input information and solved
Analysis, obtains the Health & Fitness Tip interaction demand of active user;The search extraction unit 811 of personal information extraction module 510, which is obtained, to be come
From the Health & Fitness Tip interaction demand of requirement validation module 500, extract and interacted with Health & Fitness Tip from personal information storage unit 812
The personal information of the active user of demand association is simultaneously output to Health & Fitness Tip acquisition module 520.
When the personal information of the active user associated with Health & Fitness Tip interaction demand is not present in personal information storage unit 812
When, search extraction unit 811 indicates that inquiry unit 813 initiates associated interrogation to user;Personal information acquiring unit 814 is received simultaneously
Parse user to answer, obtain corresponding personal information, and personal information is output to Health & Fitness Tip acquisition module 520.Further
, personal information acquiring unit 814 is defeated also by personal information while personal information is exported to Health & Fitness Tip acquisition module 520
Go out into personal information storage unit 812 preservation.
Health & Fitness Tip acquisition module 520 is based on the individual from search extraction unit 811 or personal information acquiring unit 814
Information and the Health & Fitness Tip interaction demand search knowledge base from requirement validation module 500, generation is for Health & Fitness Tip interaction
The Health & Fitness Tip of demand;The multi-modal output Health & Fitness Tip of last output module 530.
Further, in one embodiment, robot also includes personal information acquisition module, and it is configured in man-machine interaction
During collection user personal information and preservation, wherein people's information acquisition module obtains personal information in the following ways:
Parsing it is related to user it is multi-modal interactively enter, extraction is multi-modal interactively enter in include to it is healthy related
Personal information;
And/or,
Actively to inquiry of user's initiation for personal information, the personal letter related to health is obtained according to the response of user
Breath.
While it is disclosed that embodiment as above, but described content is only to facilitate understanding the present invention and adopting
Embodiment, 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 skilled 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 the scope of the claims of the present invention.
Claims (10)
1. a kind of interaction output intent for robot, it is characterised in that methods described includes:
The multi-modal input information of collection is simultaneously parsed, and obtains the Health & Fitness Tip interaction demand of active user;
Obtain the personal information of the active user associated with the Health & Fitness Tip interaction demand;
Based on the Health & Fitness Tip interaction demand and personal information search knowledge base, generation is handed over for the Health & Fitness Tip
The Health & Fitness Tip of mutual demand, wherein, the Health & Fitness Tip is matched with the personal information;
The multi-modal output Health & Fitness Tip.
2. according to the method described in claim 1, it is characterised in that the multi-modal input information of collection is simultaneously parsed, wherein, to user
Voice and/or user behavior are parsed.
3. according to the method described in claim 1, it is characterised in that the multi-modal input information of collection is simultaneously parsed, wherein:
Determine the active user with the presence or absence of the intention for obtaining Health & Fitness Tip;
Determine whether the active user needs to receive Health & Fitness Tip according to the state of the active user.
4. according to the method described in claim 1, it is characterised in that it is described that acquisition is associated with the Health & Fitness Tip interaction demand
The personal information of active user, wherein:
The personal information is extracted from the personal information preserved;
And/or,
Initiate to inquire to the active user, obtain the personal information.
5. method according to claim 4, it is characterised in that methods described also includes:
Personal information and the preservation of user is gathered in interactive process, wherein:
Parsing it is related to user it is multi-modal interactively enter, extraction it is described it is multi-modal interactively enter in include to it is healthy related
Personal information;
And/or,
The inquiry for the personal information actively is initiated to user, it is related to health according to being obtained the response of the user
Personal information.
6. a kind of robot, it is characterised in that the robot includes:
Requirement validation module, it is configured to gather multi-modal input information and parsed, and obtains the Health & Fitness Tip interaction of active user
Demand;
Personal information extraction module, it is configured to for obtaining the active user associated with the Health & Fitness Tip interaction demand
People's information;
Health & Fitness Tip acquisition module, it is configured to the Health & Fitness Tip interaction demand and personal information search knowledge
Storehouse, generation is directed to the Health & Fitness Tip of the Health & Fitness Tip interaction demand, wherein, the Health & Fitness Tip and the personal information
Match somebody with somebody;
Output module, it is configured to the multi-modal output Health & Fitness Tip.
7. robot according to claim 6, it is characterised in that the requirement validation module is included:
Speech analysis unit, it is configured to parse user speech;
And/or,
Behavior resolution unit, it is configured to parse user behavior.
8. robot according to claim 6, it is characterised in that the requirement validation module is included:
Interaction is intended to confirmation unit, and it is configured to determine the active user with the presence or absence of the intention for obtaining Health & Fitness Tip;
Ownness's confirmation unit, it is configured to determine whether the active user needs to connect according to the state of the active user
By Health & Fitness Tip.
9. robot according to claim 6, it is characterised in that the personal information extraction module is configured to:
The personal information is extracted from the personal information preserved;
And/or,
Initiate to inquire to the active user, obtain the personal information.
10. robot according to claim 9, it is characterised in that the robot also includes personal information acquisition module,
It is configured to personal information and preservation that user is gathered in interactive process, wherein:
Parsing it is related to user it is multi-modal interactively enter, extraction it is described it is multi-modal interactively enter in include to it is healthy related
Personal information;
And/or,
The inquiry for the personal information actively is initiated to user, it is related to health according to being obtained the response of the user
Personal information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611262279.6A CN107045587A (en) | 2016-12-30 | 2016-12-30 | A kind of interaction output intent and robot for robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611262279.6A CN107045587A (en) | 2016-12-30 | 2016-12-30 | A kind of interaction output intent and robot for robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107045587A true CN107045587A (en) | 2017-08-15 |
Family
ID=59543416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611262279.6A Pending CN107045587A (en) | 2016-12-30 | 2016-12-30 | A kind of interaction output intent and robot for robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107045587A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019051847A1 (en) * | 2017-09-18 | 2019-03-21 | Microsoft Technology Licensing, Llc | Providing diet assistance in a session |
CN110136798A (en) * | 2019-04-18 | 2019-08-16 | 广州城市职业学院 | A kind of nutrition and health consultation robot and its working method |
WO2019169854A1 (en) * | 2018-03-09 | 2019-09-12 | 南京阿凡达机器人科技有限公司 | Human-computer interaction method, and interactive robot |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070122783A1 (en) * | 2005-10-07 | 2007-05-31 | Habashi Nader M | On-line healthcare consultation services system and method of using same |
CN102054118A (en) * | 2009-11-02 | 2011-05-11 | 俞青 | Remote medical system |
CN103400054A (en) * | 2013-08-27 | 2013-11-20 | 哈尔滨工业大学 | Computer-assisted psychological consulting automatic question-answering robot system |
CN103996155A (en) * | 2014-04-16 | 2014-08-20 | 深圳市易特科信息技术有限公司 | Intelligent interaction and psychological comfort robot service system |
CN105303060A (en) * | 2015-11-24 | 2016-02-03 | 上海应用技术学院 | Gastropathy expert system based on mobile terminal |
CN105681318A (en) * | 2016-02-03 | 2016-06-15 | 百度在线网络技术(北京)有限公司 | Information push method and device based on voice recognition of artificial intelligence |
-
2016
- 2016-12-30 CN CN201611262279.6A patent/CN107045587A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070122783A1 (en) * | 2005-10-07 | 2007-05-31 | Habashi Nader M | On-line healthcare consultation services system and method of using same |
CN102054118A (en) * | 2009-11-02 | 2011-05-11 | 俞青 | Remote medical system |
CN103400054A (en) * | 2013-08-27 | 2013-11-20 | 哈尔滨工业大学 | Computer-assisted psychological consulting automatic question-answering robot system |
CN103996155A (en) * | 2014-04-16 | 2014-08-20 | 深圳市易特科信息技术有限公司 | Intelligent interaction and psychological comfort robot service system |
CN105303060A (en) * | 2015-11-24 | 2016-02-03 | 上海应用技术学院 | Gastropathy expert system based on mobile terminal |
CN105681318A (en) * | 2016-02-03 | 2016-06-15 | 百度在线网络技术(北京)有限公司 | Information push method and device based on voice recognition of artificial intelligence |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019051847A1 (en) * | 2017-09-18 | 2019-03-21 | Microsoft Technology Licensing, Llc | Providing diet assistance in a session |
US11430347B2 (en) | 2017-09-18 | 2022-08-30 | Microsoft Technology Licensing, Llc | Providing diet assistance in a session |
WO2019169854A1 (en) * | 2018-03-09 | 2019-09-12 | 南京阿凡达机器人科技有限公司 | Human-computer interaction method, and interactive robot |
CN110136798A (en) * | 2019-04-18 | 2019-08-16 | 广州城市职业学院 | A kind of nutrition and health consultation robot and its working method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pal et al. | Computer‐based diabetes self‐management interventions for adults with type 2 diabetes mellitus | |
Keskin et al. | The evaluation of depression, suicidal ideation and coping strategies in haemodialysis patients with renal failure | |
Robertson et al. | Embodied masculinities in the context of cardiac rehabilitation | |
KR20180098840A (en) | Real-time system of psychotherapy, and method thereof | |
Snell et al. | Maintaining a therapeutic connection: nursing in an inpatient eating disorder unit | |
CN108009198A (en) | Medicine method, system, electronic equipment and storage medium are recommended based on user behavior | |
CN107045587A (en) | A kind of interaction output intent and robot for robot | |
Liu et al. | Toward automated consumer question answering: Automatically separating consumer questions from professional questions in the healthcare domain | |
Scotto | The lived experience of adherence for patients with heart failure | |
Moran et al. | On his terms: representations of sexuality in women's magazines and the implications for negotiating safe sex | |
CN109036588A (en) | The method, apparatus, equipment and computer-readable medium of interrogation on line | |
CN106503043A (en) | A kind of interaction data processing method for intelligent robot | |
Sprott et al. | Health disparities among kinky sex practitioners | |
Bellamy et al. | Women's understandings of sexual problems: findings from an in‐depth interview study | |
Kalra et al. | Sexuality and mental health: Issues and what next? | |
Piqueras-Fiszman | Open-ended questions in sensory testing practice | |
Kaczmarek et al. | Give and take: The role of reciprocity in capitalization | |
O’Byrne | Population health and social governance: Analyzing the mainstream incorporation of ethnography | |
Liang et al. | Online health information use by disabled people: The moderating role of disability | |
Chiang et al. | On the qi deficiency in traditional Chinese medicine | |
Johnson | Hegans: An examination of the emerging male vegan | |
Chalaguine et al. | Domain modelling in computational persuasion for behaviour change in healthcare | |
KR102262278B1 (en) | Method for providing healthcare questionnaire service based on chatter robot ana user device for supporting the same | |
Koval et al. | Potential benefits and risks of high-nicotine e-cigarettes | |
Dyson | Experiences of alcohol dependence: a qualitative study: in this study Dr Jane Dyson analyses the experiences of individuals who are alcohol dependent and suggests that nurses and other health workers could do more to help |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170815 |
|
RJ01 | Rejection of invention patent application after publication |