CN106096576B - A kind of intelligent Service method of robot - Google Patents
A kind of intelligent Service method of robot Download PDFInfo
- Publication number
- CN106096576B CN106096576B CN201610475562.0A CN201610475562A CN106096576B CN 106096576 B CN106096576 B CN 106096576B CN 201610475562 A CN201610475562 A CN 201610475562A CN 106096576 B CN106096576 B CN 106096576B
- Authority
- CN
- China
- Prior art keywords
- service
- service object
- robot
- scene
- intended
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
Abstract
The invention discloses a kind of intelligent Service methods of robot, the identity that this method passes through the service object of identification robot, it is intended to according to the behavioral data information of the identity-acquiring service object of service object and according to the scene of behavioral data information acquisition service object, so that robot services service object according to scene intention, personalized service cannot independently be provided by solving existing intelligent robot, intelligence degree is low, and the technical problem that user experience is bad, can not only automatic identification user and guess obtain user demand, personalized service can also be provided on demand or/and provide service based on human-computer interaction, intelligence degree is high, user experience is good.
Description
Technical field
The present invention relates to fields of communication technology, and in particular to a kind of intelligent Service method of robot.
Background technique
In the modern life, more and more scenes introduce intelligent robot and are serviced, such as household service robot,
Dining room service robot, shopping guide robot, supermarket, airport guided robot etc..The intelligent machine of the prior art under these scenes
Device people cannot accomplish automatic identification user and guess the demand for obtaining user when providing service for user, then mention automatically on demand
Service is provided for personalized service or/and based on human-computer interaction, intelligence degree is low, and user experience is bad.So needing to mention
Personalized and intelligent Service intelligent robot method of servicing can be independently provided for a kind of.
Summary of the invention
The present invention provides a kind of intelligent Service methods of robot, cannot independently be provided with solving existing intelligent robot
Personalized service, intelligence degree is low, and the technical problem that user experience is bad.
The intelligent Service method of robot provided by the invention, comprising:
Identify the identity of the service object of robot；
According to the behavioral data information of the identity-acquiring service object of service object；
It is intended to according to the scene of behavioral data information acquisition service object, so that robot is intended to according to scene to service pair
As being serviced.
Further, the identity for identifying the service object of robot includes:
Obtain the biological characteristic of the service object of robot；
Biological characteristic is matched with the sample biological characteristic for being stored in advance in the database, to identify robot
The identity of service object.
Further, it when biological characteristic is not matched that with the sample biological characteristic for being stored in advance in the database, also wraps
It includes:
The username information with the biometric matches of service object is searched on the internet；
The identity of service object is identified according to username information.
Further, the identity for identifying the service object of robot includes:
Preset range threshold value；
Choosing has same application program and service of the mobile terminal as robot in range threshold with robot
Object, wherein application program has the permission for obtaining geographical location information；
Further, the body of the service object of the username information identification robot according to service object in application program
Part.
Further, include: according to the behavioral data information of the identity-acquiring service object of service object
According to the corresponding username information of the identities match of service object；
The electronic register information of service object is obtained according to username information；
According to the essential attribute information and user behaviors log information of electronic register information acquisition services object, and by essential attribute
The behavioral data information of information and user behaviors log information as service object.
Further, include: according to the scene of behavioral data information acquisition service object intention
It presets input feature vector entry corresponding with scene type belonging to robot and scene is intended to output classification；
The sample behavioral data corresponding with input feature vector entry of training sample is acquired, and is extracted according to sample behavioral data
The input feature value of training sample；
It is intended to output classification training classifier according to the scene of input feature value and training sample, obtains scene and be intended to know
Other model；
According to scene intention assessment model, identify that the scene of service object is intended to.
Further, robot carries out service to service object and includes: according to scene intention
It obtains preset and scene and is intended to most matched robot service option；
Set Service Properties entry corresponding with service option；
According to the behavioral data information of service object, the Service Properties corresponding with Service Properties entry of service object are obtained
Content；
Service object is serviced according to Service Properties content.
Further, robot carries out service to service object and includes: according to scene intention
It obtains preset and scene and is intended to most matched robot service option；
Human-computer interaction is carried out according to preset service regulation corresponding with service option and service object, and is based on people
Machine interaction services service object.
Further, biological characteristic includes:
One of face, fingerprint, sound, smell, iris, hand shape, palmmprint, signature, gait or multiple combinations.
Further, scene type are as follows:
Household, dining room, hotel, airport, office, cinema, beauty parlor, tourist attraction, appointing in the scene type of market
It anticipates one kind.
The invention has the following advantages:
The intelligent Service method of robot provided by the invention, the body that this method passes through the service object of identification robot
Part, according to the behavioral data information of the identity-acquiring service object of service object and according to the service pair of behavioral data information acquisition
The scene of elephant is intended to, so that robot services service object according to scene intention, solves existing intelligent robot not
Personalized service can be independently provided, intelligence degree is low, and the technical problem that user experience is bad, can not only automatic identification use
The demand for obtaining user is simultaneously guessed in family, can also provide personalized service on demand or/and provide service, intelligence based on human-computer interaction
Degree height can be changed, user experience is good.
Other than objects, features and advantages described above, there are also other objects, features and advantages by the present invention.
Below with reference to figure, the present invention is described in further detail.
Detailed description of the invention
The attached drawing for constructing a part of the application is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not construct inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the method flow diagram of the intelligent Service of preferred embodiment of the present invention robot；
Fig. 2 is the process of the intelligent Service method for the robot that the preferred embodiment of the present invention simplifies embodiment for first
Figure；
Fig. 3 is the process of the intelligent Service method for the robot that the preferred embodiment of the present invention simplifies embodiment for second
Figure；
Fig. 4 is the process of the intelligent Service method for the robot that the preferred embodiment of the present invention simplifies embodiment for third
Figure.
Specific embodiment
The embodiment of the present invention is described in detail below in conjunction with attached drawing, but the present invention can be defined by the claims
Implement with the multitude of different ways of covering.
Referring to Fig.1, the preferred embodiment of the present invention provides a kind of intelligent Service method of robot, comprising:
Step S101 identifies the identity of the service object of robot；
Step S102, according to the behavioral data information of the identity-acquiring service object of service object；
Step S103 is intended to, so that robot anticipates according to scene according to the scene of behavioral data information acquisition service object
Figure services service object.
The intelligent Service method of robot provided by the invention, the body that this method passes through the service object of identification robot
Part, according to the behavioral data information of the identity-acquiring service object of service object and according to the service pair of behavioral data information acquisition
The scene of elephant is intended to, so that robot services service object according to scene intention, solves existing intelligent robot not
Personalized service can be independently provided, intelligence degree is low, and the technical problem that user experience is bad, can not only automatic identification use
The demand for obtaining user is simultaneously guessed in family, can also provide personalized service on demand or/and provide service, intelligence based on human-computer interaction
Degree height can be changed, user experience is good.
In the prior art, intelligent robot generally requires service object first to intelligence when providing service for service object
Robot carries out active operation, and operating process complexity is cumbersome, and user experience is bad.The present embodiment for this problem, first automatically
Identify service object identity, and according to the behavioral data information of the service object of acquisition to the scene of service object be intended into
Service object is greatly saved to the master of intelligent robot to provide service object actively personalized service in row conjecture
Dynamic operating process, and be intended to provide personalized service to service object, significantly by the scene of intelligent recognition service object
The user experience is improved.
Scene in the present embodiment is intended to specifically refer to service object's scene locating for the robot for providing intelligent Service
Under intention.Such as when intelligent robot is placed in office, the scene intention of user may be to have tea, drink coffee, beating
Printed text part, cleaning etc., and when intelligent robot is placed in cinema, the scene intention of user may be buy tickets,
Convert ticket, select seat etc., that is to say, that the scene intention of user is unlikely to be mimeograph documents substantially at this time.
Optionally, the identity for identifying the service object of robot includes:
Obtain the biological characteristic of the service object of robot；
Biological characteristic is matched with the sample biological characteristic for being stored in advance in the database, to identify robot
The identity of service object.
It is existing user identify generally first the identity of user is identified, and identifying to the identity of user can
To take various ways.Specifically, the present embodiment obtains robot when identifying the identity of service object of robot first
The biological characteristic of service object, then by the biological characteristic of service object with sample biological characteristic in the database is stored in advance
It is matched, to identify the identity of the service object of robot.Wherein, the biological characteristic of service object includes: face, refers to
One of line, sound, smell, iris, hand shape, palmmprint, signature, gait or multiple combinations.
It often stores the sample biological characteristic of some users in the database of existing intelligent robot, such as face, refers to
Line, sound, smell, iris, hand shape, palmmprint, signature, gait etc., therefore when robot collects the biological characteristic of service object
Afterwards, often first match in its database whether include the service object sample biological characteristic, if successful match, basis
The sample biological characteristic that the service object stores in the database carries out identification to it.For example, when collecting service object
Face characteristic information when, then face sample characteristics in its database with intelligent robot are carried out using face recognition technology
Matching identifies the identity of service object to realize.
The present embodiment first carries out the identity of service object before realizing that robot carries out intelligent Service to service object
Identification is conducive to robot and carries out automation services to service object, while being also beneficial to subsequent be obtained according to the identity of service object
Other information relevant to service object, such as the behavioral data information of service object etc. are taken, to be subsequent intelligence machine
People carries out personalized service to service object and lays the foundation.
Optionally, when biological characteristic is not matched that with the sample biological characteristic for being stored in advance in the database, further includes:
The username information with the biometric matches of service object is searched on the internet；
The identity of service object is identified according to username information.
Due to when the biological characteristic of service object is matched with the sample biological characteristic in database, in fact it could happen that
Not the case where biological characteristic is not matched that with the sample biological characteristic for being stored in advance in the database, namely cannot be from being stored in advance in
Biological characteristic identical with service object is matched in sample biological characteristic in database.In response to this, the present embodiment
By searching for the username information with the biometric matches of service object on the internet, then identified according to username information
The identity of service object.
For example, when system cannot match and service pair from the face sample biological characteristic being stored in advance in the database
When as identical face biological characteristic, then it is right therewith to be searched on the internet according to the face biological characteristic of the service object of acquisition
The username information answered.When this is mainly based upon existing user and carries out identity registration on the internet, often it is required to provide
Corresponding biological characteristic, such as face, signature etc..The present embodiment is based on the correlation of the two, passes through service pair first
The biological characteristic of elephant is searched on the internet obtains matching username information, is then identified and is serviced according to username information
The identity of object.
It is corresponding to it should be noted that the present embodiment is obtained according to the search of the biological characteristic of service object on the internet
Username information when, more than one username information may be obtained.At this point, the present embodiment can choose wherein any one use
Name in an account book information identifies the identity of service object, can also choose and believe with the highest user name of the biometric matches degree of service object
Cease the identity of service object for identification.
Optionally, the identity for identifying the service object of robot includes:
Preset range threshold value；
Choosing has same application program and service of the mobile terminal as robot in range threshold with robot
Object, wherein application program has the permission for obtaining geographical location information；
According to the identity of the service object of username information identification robot of the service object in application program.
In the specific implementation process, the present embodiment is in addition to identifying its identity according to the biological characteristic of service object
Outside, the username information for the application program that can also be registered by service object identifies its identity.Specifically, it selects first
Taking has same application program and service object of the mobile terminal as robot in preset range threshold value with robot,
In, application program has the permission for obtaining geographical location information, then the user name letter according to service object in application program
The identity of the service object of breath identification robot.
Such as present embodiment assumes that robot have a kind of application program that can obtain geographical location information function privilege, and
The mobile terminal of service object similarly installs the application program, then the present embodiment obtains the preset range threshold value of robot first
Service object, then according to service object in application program username information identification robot service object body
Part.It should be noted that can choose in the present embodiment has same application program and appointing in range threshold with robot
Anticipate service object of the mobile terminal as robot, and can also choose with robot has same application program and in range
Service object of the nearest mobile terminal as robot in threshold value.
Optionally, include: according to the behavioral data information of the identity-acquiring service object of service object
According to the corresponding username information of the identities match of service object；
The electronic register information of service object is obtained according to username information；
According to the essential attribute information and user behaviors log information of electronic register information acquisition services object, and by essential attribute
The behavioral data information of information and user behaviors log information as service object.
Since service object is when carrying out identity registration, user name setting often will do it, and can also be arranged and user name
Other corresponding electronic register information of information, such as one of gender, age, occupation, hobby, family status or more
Kind.Meanwhile when getting the username information of service object, the present embodiment can also be in system corresponding with username information
Search obtains associated other information, such as log information, history information etc. in database.Specifically, this reality
It applies example obtaining with after the username information of the identities match of service object, corresponding electronics is obtained according to username information
Registration information, then further according to the essential attribute information and user behaviors log information of electronic register information acquisition services object, and will
The behavioral data information of essential attribute information and user behaviors log information as service object.
In actual implementation process, the behavioral data information of the service object in the present embodiment can specifically include service
One of the personal essential information of object, log information, communication information, online footprint information are a variety of, wherein personal basic
Information includes one of gender, age, occupation, hobby, family status or a variety of, and communication information includes instant messaging letter
One of breath, mobile communication information, email correspondence information, microblogging communication information are a variety of, and online footprint information includes
One of online shopping information, net page browse information are a variety of.
Optionally, include: according to the scene of behavioral data information acquisition service object intention
It presets input feature vector entry corresponding with scene type belonging to robot and scene is intended to output classification；
The sample behavioral data corresponding with input feature vector entry of training sample is acquired, and is extracted according to sample behavioral data
The input feature value of training sample；
It is intended to output classification training classifier according to the scene of input feature value and training sample, obtains scene and be intended to know
Other model；
According to scene intention assessment model, identify that the scene of service object is intended to.
In general, service object may have different intentions, such as the scene in cinema under different scenes
Under, the intention of service object may be to buy tickets, convert ticket, select seat etc., and under the scene of office, the intention of service object may
It is to sweep, have tea, print etc..In response to this, the present embodiment trains and scene type pair belonging to robot first
The scene intention assessment model answered, then according to trained with robot belonging to the corresponding scene intention assessment of scene type
Model identifies that the scene under scene type of the service object belonging to robot is intended to.
Specifically, when the present embodiment training scene intention assessment model corresponding with scene type, first against different
Different input feature vector entry is arranged in scene type and scene is intended to output classification, then acquire training sample and input feature vector
The corresponding sample behavioral data of entry, and according to the input feature value of sample behavioral data extraction training sample, last basis
The scene of input feature value and training sample is intended to output classification training classifier, obtains scene intention assessment model.Wherein,
Classifier can be support vector machine classifier, Bayes classifier etc..
In addition, the present embodiment is presetting input feature vector entry corresponding with scene type and scene intention output classification
When one or more can be set according to demand.Such as when scene type is household classification, pre-set input feature vector item
Mesh can be one of hobby, historical behavior habit, home care situation, household electric appliances state or a variety of, set in advance
It can be one of to put the music on, cook, sweeping, turning on the aircondition, opening TV, laundry clothes or more that the scene set, which is intended to output classification,
Kind, it specifically can refer to table 1.
Table 1
| Scene type | Input feature vector entry corresponding with scene type | Scene is intended to output classification |
| Household | Hobby, historical behavior habit, home care situation, household electric appliances state | It puts the music on, cook, sweeping, turning on the aircondition, opening TV, laundry clothes |
| Dining room | Group behavior feature under interest in diet hobby, historical behavior habit, same scene | It orders dishes, serve, settle accounts, serve the tea |
| Hotel | Historical behavior habit, chat record | Room is opened, cleaning, settles accounts, open TV |
| Office | Hobby, historical behavior habit, office's sanitary conditions | It sweeps, have tea, drink coffee, print |
| Cinema | Hobby, historical behavior habit, the group behavior feature under same scene, chat record | It buys tickets, converts ticket, selects seat |
| Beauty parlor | Hobby, history consumer record, age, gender | Facial-care, hair nursing, wash my hair, has one's hair cut at body care |
It should be noted that the present embodiment is for different scene type point in order to improve scene intention assessment accuracy rate
Different scene intention assessment models is not set.In actual implementation process, the present embodiment can be directed to different scene classes
One scene intention assessment model of other setting, namely can be intended to know using the scene type belonging to robot as scene at this time
One input feature vector of other model.
The present embodiment, can not only be according to service object's by training scene intention assessment model corresponding with scene type
Behavioral data intelligent recognition goes out matched scene and is intended to, and uses the trained scene intention assessment model of the present embodiment
High to the accuracy rate of the scene intention assessment of service object, being conducive to subsequent robot can be intended to according to the scene identified to clothes
Business object provides personalized service, embodies higher intelligent level.
Optionally, robot carries out service to service object and includes: according to scene intention
It obtains preset and scene and is intended to most matched robot service option；
Set Service Properties entry corresponding with service option；
According to the behavioral data information of service object, the Service Properties corresponding with Service Properties entry of service object are obtained
Content；
Service object is serviced according to Service Properties content.
After the scene for getting service object is intended to, robot can anticipate the present embodiment according to the scene of service object
Figure services it, but may need more personalized intimate service with the different service objects that same scene is intended to.Example
When such as gender, two different service objects remove market shopping, intelligent shopping guide robot is in the scene for judging two service objects
It is intended in the case where being all shopping, more personalized Intellectual garment can also be carried out to it according to the behavioral data information of service object
Business.
Specifically, obtain first it is preset be intended to most matched robot service option with scene, then setting with
The corresponding Service Properties entry of service option, and belonging to service according to the behavioral data information acquisition services object of service object
The property corresponding Service Properties content of entry, finally services service object according to Service Properties content.Namely for having
Same scene is intended to two service objects of (shopping), and the present embodiment obtains preset and scene first and is intended to (shopping) most
Matched robot service option (shopping guide), then set corresponding with service option Service Properties entry (such as hobby,
Age, gender etc.), be specifically shown in Table 2, finally according to the behavioral data information of service object, obtain service object with service
The corresponding Service Properties content of attributes entries services service object according to Service Properties content to realize.
Table 2
| Robot service option | Service Properties entry |
| Reservation | Floor hobby, towards preference, consuming capacity |
| Mall shopping | Age, gender, hobby, style of wearing the clothes |
| It orders dishes in dining room | Current health state, number of having dinner range, consuming capacity, abstains from taste at preferred diet |
The present embodiment, by the behavioral data information of service object, obtains pre- after the scene for obtaining service object is intended to
The corresponding Service Properties content of Service Properties entry corresponding with service option first set, and according to Service Properties content to clothes
Business object is serviced, and is realized and is provided personalized intelligent Service to it according to the behavioral data information of service object, significantly
The user experience is improved.
Optionally, robot carries out service to service object and includes: according to scene intention
It obtains preset and scene and is intended to most matched robot service option；
Human-computer interaction is carried out according to preset service regulation corresponding with service option and service object, and is based on people
Machine interaction services service object.
According to real life experience, intelligent robot both can directly be serviced service object, can also be led to
It crosses and it is serviced with service object's progress human-computer interaction realization.Since the present embodiment can automatic identification compared with existing intelligent robot
The scene of service object is intended to, and therefore, the present embodiment both can be intended to directly service it according to the scene of service object,
Human-computer interaction realization can also be carried out with it according to the scene of service object intention to service it.
Specifically, the present embodiment obtains the most matched robot service option of preset and scene intention first, so
Human-computer interaction is carried out according to preset service regulation corresponding with service option and service object afterwards, and is based on human-computer interaction
Service object is serviced.For example, obtaining anticipate with scene first when the scene for getting service object is intended to drink coffee
Scheme most matched robot service option, it is assumed that then right with service option (coffee) according to preset for coffee
Answer service regulation (such as first inquiry service object whether need to make coffee for it, inquire clothes again after obtaining positive reply
Business object the problems such as whether needing sugaring, inquires whether service object the rules such as needs to make tea for it after obtaining negative reply)
Human-computer interaction is carried out with service object, to service based on human-computer interaction service object.
It can be seen that robot, not only can be directly according to service when servicing service object in the present embodiment
The scene intention of object services it, moreover it is possible to according to preset service regulation corresponding with service option and service pair
As carrying out human-computer interaction, so as to provide more intelligent and personalized service for service object.
Optionally, biological characteristic includes:
One of face, fingerprint, sound, smell, iris, hand shape, palmmprint, signature, gait or multiple combinations.
Biological characteristic in the present embodiment is not limited to include face, fingerprint, sound, smell, iris, hand shape, palmmprint, label
One of name, gait or multiple combinations, are specifically customized by the user.
Optionally, scene type are as follows:
Household, dining room, hotel, airport, office, cinema, beauty parlor, tourist attraction, appointing in the scene type of market
It anticipates one kind.
Scene type in the present embodiment is not limited to include household, dining room, hotel, airport, office, cinema, beauty
Institute, tourist attraction, any one in the scene type of market, are specifically customized by the user.
Embodiment is simplified below for two to carry out more into one the process and principle of intelligent robot service of the invention
Walk explanation.
Simplify embodiment one
Referring to Fig. 2, the method for the intelligent robot service of the present embodiment includes:
Step S201 obtains the biological characteristic of the service object of robot.
Specifically, the present embodiment can obtain any one or more of biological characteristic of the service object of robot
It takes, such as one of the face of service object, fingerprint, sound, smell, iris, hand shape, palmmprint, signature, gait or a variety of groups
It closes feature to be obtained, present embodiment assumes that the biological characteristic obtained is the face characteristic of service object.
Step S202 matches biological characteristic with the sample biological characteristic for being stored in advance in the database, to know
The identity of the service object of other robot.
Specifically, the present embodiment will collect face sample in the database of the face characteristic and intelligent robot of service object
Eigen is matched, and is identified to realize to the identity of service object.Present embodiment assumes that can be matched from database
Out with the matched face sample characteristics of the face characteristic of service object.
Step S203, according to the corresponding username information of the identities match of service object.
Since service object is when carrying out identity registration, user name setting often will do it, and can also be arranged and user name
Other corresponding electronic register information of information, such as one of gender, age, occupation, hobby, family status or more
Kind.Specifically, it is assumed that the present embodiment is matched to and the face of service object spy in the face sample database in step S202
Levying the corresponding username information of identical face sample characteristics is the identities match of Zhang San namely the present embodiment according to service object
To the corresponding entitled Zhang San of user.
Step S204 obtains the electronic register information of service object according to username information.
Specifically, the present embodiment is according to the available electricity corresponding with the username information of username information of service object
Sub- registration information, such as the registration of phone number information corresponding with user name (Zhang San), instant messaging account information, E-mail address
Information etc..
Step S205, according to the essential attribute information and user behaviors log information of electronic register information acquisition services object, and
Using essential attribute information and user behaviors log information as the behavioral data information of service object.
Specifically, after the present embodiment is according to the electronic register information corresponding with username information obtained in step S204,
Can also be according to the essential attribute information and user behaviors log information of electronic register information acquisition services object, and essential attribute is believed
Breath and behavioral data information of the user behaviors log information as service object.Wherein, essential attribute information can specifically include service
The personal essential information of object, such as one of gender, age, occupation, hobby, family status or a variety of, behavior day
Will information can specifically include one of log information, communication information, online footprint information or a variety of, wherein communication information
Including one of instant communication information, mobile communication information, email correspondence information, microblogging communication information or a variety of, on
Net footprint information includes one of online shopping information, net page browse information or a variety of.
Step S206, presets input feature vector entry corresponding with scene type belonging to robot and scene intention is defeated
Classification out.
Specifically, it is intended to accurately obtain the scene under scene type of the service object belonging to robot, this implementation
Example identifies the intention of service object using trained scene intention assessment model, therefore by presetting and robot
The corresponding scene of affiliated scene type is intended to output classification, and scene intention assessment problem is converted into simple classification problem,
I.e. by having the machine learning method of supervision, support vector machines learning method, bayes classification method to its scene intention assessment
Model is trained, until training the higher scene intention assessment model of discrimination.
Assuming that scene type belonging to robot is office scenarios classification in the present embodiment, and setting and office first
The corresponding input feature vector entry of scene type is hobby, historical behavior habit, office's sanitary conditions, with office scenarios
It is to sweep, have tea, drinking coffee, printing that the corresponding scene of classification, which is intended to output classification, referring in particular to table 1.
Step S207 acquires the sample behavioral data corresponding with input feature vector entry of training sample, and according to sample row
The input feature value of training sample is extracted for data.
Specifically, the present embodiment acquires the sample behavioral data corresponding with input feature vector entry of training sample first, and
The input feature value of training sample is extracted according to sample behavioral data.Wherein, the quantity of training sample is answered as big as possible, thus
Guarantee the discrimination of scene intention assessment model.Assuming that the quantity of the training sample of the present embodiment is 100, then this is acquired respectively
The sample behavioral data corresponding with input feature vector entry of 100 training samples, and extracted according to the sample behavioral data of acquisition
The input feature value of training sample.
Step S208 is intended to output classification training classifier according to the scene of input feature value and training sample, obtains
Scene intention assessment model.
Step S209 identifies that the scene of service object is intended to, so that robot is according to field according to scene intention assessment model
Scape intention services service object.
Specifically, it is assumed that the present embodiment identifies that the scene of service object is anticipated according to trained scene intention assessment model
Figure is to drink coffee, then the scene intention that robot drinks coffee according to service object carries out respective service to it.
The intelligent Service method of robot provided by the invention, the body that this method passes through the service object of identification robot
Part, according to the behavioral data information of the identity-acquiring service object of service object and according to the service pair of behavioral data information acquisition
The scene of elephant is intended to, so that robot services service object according to scene intention, solves existing intelligent robot not
Personalized service can be independently provided, intelligence degree is low, and the technical problem that user experience is bad, can not only automatic identification use
The demand for obtaining user is simultaneously guessed in family, can also provide personalized service on demand or/and provide service, intelligence based on human-computer interaction
Degree height can be changed, user experience is good.
Simplify embodiment two
Referring to Fig. 3, the method for the intelligent robot service of the present embodiment includes:
Step S301, preset range threshold value.
Specifically, targetedly service object can be serviced in order to facilitate robot, the model of the present embodiment setting
It encloses threshold value and specifically refers to range threshold from robot.Assuming that the range threshold of the present embodiment setting is 200 meters.
Step S302, chooses and robot has same application program and the mobile terminal in range threshold is as machine
The service object of people, wherein application program has the permission for obtaining geographical location information.
Existing many application programs all have function and permission, such as wechat, QQ for obtaining geographical location information etc. immediately
Chat tool, Baidu map, drop drop such as are called a taxi at the application programs, and the present embodiment is by judging in the preset range threshold value of robot
Whether the mobile terminal that with robot there is same application program is had, to realize the acquisition and identification to service object.Specifically
Ground has the geographical location for obtaining the application program of geographical location information permission to robot by what is installed in robot first
It is read out, then obtains the service object for installing same application program mobile terminal in range threshold as robot.It is false
If the present embodiment, which is chosen with robot, has same application program and nearest mobile terminal in range threshold is as machine
The service object of device people.
Step S303, according to the body of the service object of username information identification robot of the service object in application program
Part.
Specifically, after the present embodiment gets service object according to step S302, according to service object in application program
Username information can identify robot service object identity.
Step S304, according to the behavioral data information of the identity-acquiring service object of service object.
Specifically, the present embodiment specifically can refer to according to the behavioral data information of the identity-acquiring service object of service object
It simplifies according to the behavioral data information of the identity-acquiring service object of service object in embodiment one, it is not described in detail herein.
Step S305 is intended to, so that robot anticipates according to scene according to the scene of behavioral data information acquisition service object
Figure services service object.
Specifically, it is assumed that scene type belonging to robot is cinema's scene type in the present embodiment, and is directed to this
Corresponding input feature vector entry is arranged in scape classification first and scene is intended to output classification, referring in particular to table 1.Wherein, film
Under institute's scene type, it is under hobby, historical behavior habit, same scene that corresponding input feature vector entry, which can be set,
Group behavior feature, chat record etc..Wherein, the group behavior feature under same scene is specifically referred in same scene class
Under other, the behavioural characteristic of other groups, such as under cinema's scene type, system monitoring to group behavior is to exchange film ticket
Behavior, then can will exchange the behavior of film ticket as group behavior feature；In addition, chat record can be current chat note
Record is also possible to history chat record, such as can be by the chat record of current service object (I prepares to exchange film ticket)
Or input feature vector of the history chat record (plan will be gone to the cinema tomorrow) etc. as scene intention assessment model.
Assuming that the present embodiment identifies that the scene of service object is intended to convert according to trained scene intention assessment model
Film ticket is changed, then robot carries out respective service to it according to the scene intention that service object exchanges film ticket.Specific real
During applying, the mode of human-computer interaction can be taken to provide service to it when robot services service object in the present embodiment,
Such as after the scene for judging service object is intended to, robot can inquire whether service object needs to exchange film for it
Ticket, so as to provide more intimate and intelligent service for service object.
The present embodiment passes through the identity of the service object of identification robot, according to the identity-acquiring service object of service object
Behavioral data information and according to the scene of behavioral data information acquisition service object be intended to, so that robot anticipates according to scene
Figure services service object, and personalized service, intelligence degree cannot independently be provided by solving existing intelligent robot
It is low, and the technical problem that user experience is bad, automatic identification user and it can not only guess the demand for obtaining user, it can also be on demand
Personalized service is provided or/and provides service based on human-computer interaction, intelligence degree is high, and user experience is good.
Simplify embodiment three
Referring to Fig. 4, the method for the intelligent robot service of the present embodiment includes:
Step S401 identifies the identity of the service object of robot.
Specifically, the present embodiment can both identify its identity according to the biological characteristic of service object, can also lead to
The username information for crossing the application program of service object's registration identifies its identity.
Step S402, according to the behavioral data information of the identity-acquiring service object of service object.
Specifically, the present embodiment specifically can refer to according to the behavioral data information of the identity-acquiring service object of service object
It simplifies according to the behavioral data information of the identity-acquiring service object of service object in embodiment one, it is not described in detail herein.
Step S403 is intended to according to the scene of behavioral data information acquisition service object.
Specifically, it is assumed that scene type belonging to robot is hotel in the present embodiment, and system according to training in advance
Scene intention assessment model obtain the scene of service object and be intended to hotel and open room.
Step S404 obtains preset and scene and is intended to most matched robot service option.
Specifically, the present embodiment is intended to after hotel opens room according to the scene that step S403 obtains service object, Ke Yigen
It is intended to according to preset scene and robot service option corresponding relationship, acquisition is intended to most matched robot service with scene
Option, it is assumed that getting and opening the most matched robot service option in room with hotel is reservation.
Step S405 sets Service Properties entry corresponding with service option.
In order to provide more intimate and intelligent service to service object, the present embodiment is being obtained and the scene of service object meaning
After scheming most matched robot service option, personality analysis further is carried out to service object.Specifically, setting and clothes first
The corresponding Service Properties entry of business option, present embodiment assumes that preset service corresponding with reservation service option belongs to
Property entry be floor hobby, towards preference, consuming capacity, be specifically shown in Table 2.
Step S406 obtains the corresponding with Service Properties entry of service object according to the behavioral data information of service object
Service Properties content.
Specifically, it is assumed that the present embodiment obtains corresponding with Service Properties entry according to the behavioral data information of service object
Service Properties content be respectively, floor hobby: between the building 10-20；Towards preference: south-north direction；Consuming capacity: 200-300
Member.
Step S407 services service object according to Service Properties content.
Specifically, the Service Properties content that the present embodiment is obtained according to step S406 can directly take for service object
Business, such as suitable room is directly made a reservation for for it according to the behavioral data information of service object, in addition, the present embodiment can also root
It interacts to complete service according to the Service Properties content and service object of acquisition, such as when robot is got in Service Properties
Rong Hou, can inquire service object (such as the floor of reservation be 15 layers, what do you think? the price of/reservation exists
Do 200 or so, you see properly? etc.), so that being embodied as user provides more intimate and personalized service.
The present embodiment passes through the identity of the service object of identification robot, according to the identity-acquiring service object of service object
Behavioral data information and be intended to according to the scene of behavioral data information acquisition service object, and obtaining service object
After scene is intended to, by the behavioral data information of service object, preset Service Properties corresponding with service option are obtained
The corresponding Service Properties content of entry, and service object is serviced according to Service Properties content, solve existing intelligent machine
Device people cannot independently provide personalized service, and intelligence degree is low, and the technical problem that user experience is bad, realizes basis
The behavioral data information of service object provides personalized intelligent Service to it, greatly improves user experience.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (4)
1. a kind of intelligent Service method of robot, comprising:
Step S401 identifies the identity of the service object of robot；
Specifically, its identity is identified according to the biological characteristic of service object, or the application journey registered by service object
The username information of sequence identifies its identity；
Step S402, according to the behavioral data information of the identity-acquiring service object of service object；
Step S403 is intended to according to the scene of behavioral data information acquisition service object；
Step S404 obtains preset and scene and is intended to most matched robot service option；
Step S405 sets Service Properties entry corresponding with service option；
According to the scene of service object described in the behavioral data information acquisition intention include: preset with belonging to robot
The corresponding input feature vector entry of scene type and scene are intended to output classification；Acquire training sample with the input feature vector entry
Corresponding sample behavioral data, and extract according to the sample behavioral data input feature value of the training sample；According to
The scene of the input feature value and the training sample is intended to output classification training classifier, obtains scene intention assessment mould
Type；According to the scene intention assessment model, identify that the scene of the service object is intended to；The robot is according to the scene
It is intended to carry out the service object service to include: to obtain the preset and scene to be intended to most matched robot service
Option；
Set Service Properties entry corresponding with the service option；According to the behavioral data information of the service object, obtain
The Service Properties content corresponding with the Service Properties entry of the service object；According to the Service Properties content to described
Service object services.
2. a kind of intelligent Service method of robot as described in claim 1, comprising: anticipate obtaining with the scene of service object
After scheming most matched robot service option, personality analysis further is carried out to service object, first setting and service option
Corresponding Service Properties entry, preset Service Properties entry corresponding with reservation service option be floor hobby,
Towards preference, consuming capacity.
3. a kind of intelligent Service method of robot as claimed in claim 2, comprising: specifically, according to the row of service object
For data information, obtaining Service Properties content corresponding with Service Properties entry is respectively, floor hobby: between the building 10-20；Court
To preference: south-north direction；Consuming capacity: 200-300 member.
4. a kind of intelligent Service method of robot as described in claim 1, comprising: according to Service Properties content to service pair
As being serviced；
It specifically, is directly that service object services according to the Service Properties content of acquisition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610475562.0A CN106096576B (en) | 2016-06-27 | 2016-06-27 | A kind of intelligent Service method of robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610475562.0A CN106096576B (en) | 2016-06-27 | 2016-06-27 | A kind of intelligent Service method of robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106096576A CN106096576A (en) | 2016-11-09 |
| CN106096576B true CN106096576B (en) | 2019-05-07 |
Family
ID=57252736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610475562.0A Active CN106096576B (en) | 2016-06-27 | 2016-06-27 | A kind of intelligent Service method of robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106096576B (en) |
Families Citing this family (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774845B (en) * | 2016-11-24 | 2020-01-31 | 北京儒博科技有限公司 | intelligent interaction method, device and terminal equipment |
| CN106844429B (en) * | 2016-12-12 | 2020-01-14 | 北京光年无限科技有限公司 | Internet auxiliary application method for robot |
| CN108460503A (en) * | 2017-02-17 | 2018-08-28 | 张月妹 | A kind of supermarket's automatic translation QR algorithm |
| CN108537564A (en) * | 2017-03-02 | 2018-09-14 | 九阳股份有限公司 | A kind of dining information method for pushing and home-services robot |
| CN106926252A (en) * | 2017-04-19 | 2017-07-07 | 旗瀚科技有限公司 | A kind of hotel's intelligent robot method of servicing |
| CN107273944A (en) * | 2017-05-16 | 2017-10-20 | 北京元视觉科技有限公司 | Autonomous social smart machine, autonomous exchange method and storage medium |
| CN106956266A (en) * | 2017-05-16 | 2017-07-18 | 北京京东尚科信息技术有限公司 | robot control method, device and robot |
| CN107424085A (en) * | 2017-08-01 | 2017-12-01 | 深圳市益廷科技有限公司 | A kind of hotel service system |
| CN107544248B (en) | 2017-09-13 | 2019-12-13 | 上海思岚科技有限公司 | Task optimization method and device in mobile robot |
| JP6812325B2 (en) * | 2017-10-26 | 2021-01-13 | 株式会社日立ビルシステム | Robot management system |
| CN107885837A (en) * | 2017-11-09 | 2018-04-06 | 北京光年无限科技有限公司 | A kind of interaction output intent and intelligent robot for intelligent robot |
| KR20190057687A (en) | 2017-11-20 | 2019-05-29 | 삼성전자주식회사 | Electronic device and Method for changing Chatbot |
| CN108037699B (en) * | 2017-12-12 | 2020-04-07 | 深圳市天颐健康科技有限公司 | Robot, control method of robot, and computer-readable storage medium |
| CN108724203A (en) * | 2018-03-21 | 2018-11-02 | 北京猎户星空科技有限公司 | A kind of exchange method and device |
| CN108765921A (en) * | 2018-04-04 | 2018-11-06 | 昆山市工研院智能制造技术有限公司 | View-based access control model lexical analysis is applied to the intelligent patrol method of patrol robot |
| CN108564036A (en) * | 2018-04-13 | 2018-09-21 | 上海思依暄机器人科技股份有限公司 | A kind of method for judging identity, device and Cloud Server based on recognition of face |
| CN110533553B (en) * | 2018-05-25 | 2023-04-07 | 阿里巴巴集团控股有限公司 | Service providing method and device |
| US11631118B2 (en) * | 2018-12-21 | 2023-04-18 | Soham Inc | Distributed demand generation platform |
| CN111382629B (en) * | 2018-12-28 | 2021-03-05 | 中国科学院半导体研究所 | Footprint identification and information mining method and system based on convolutional neural network |
| CN110675201A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Service information processing method and device |
| CN111210264B (en) * | 2019-12-27 | 2023-11-28 | 福建凯米网络科技有限公司 | Management method and system based on interaction of self-mobile equipment and self-mobile equipment |
| CN113139117A (en) * | 2020-01-20 | 2021-07-20 | 北京智慧图科技有限责任公司 | Intelligent service system based on scene and intention recognition |
| CN112163078A (en) * | 2020-09-29 | 2021-01-01 | 彩讯科技股份有限公司 | Intelligent response method, device, server and storage medium |
| CN112684711B (en) * | 2020-12-24 | 2022-10-11 | 青岛理工大学 | Interactive recognition method for human behavior and intention |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101618542A (en) * | 2009-07-24 | 2010-01-06 | 塔米智能科技（北京）有限公司 | System and method for welcoming guest by intelligent robot |
| CN103390194A (en) * | 2012-05-07 | 2013-11-13 | 北京三星通信技术研究有限公司 | Method, device and system for predicating user intention and recommending suggestion |
| CN104951428A (en) * | 2014-03-26 | 2015-09-30 | 阿里巴巴集团控股有限公司 | User intention recognition method and device |
| CN105100269A (en) * | 2015-08-27 | 2015-11-25 | 努比亚技术有限公司 | Mobile terminal and content recommending method based on different users |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1741044B1 (en) * | 2004-03-27 | 2011-09-14 | Harvey Koselka | Autonomous personal service robot |
| CN204462847U (en) * | 2014-12-28 | 2015-07-08 | 青岛通产软件科技有限公司 | A kind of multi-functional hotel service robot |
-
2016
- 2016-06-27 CN CN201610475562.0A patent/CN106096576B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101618542A (en) * | 2009-07-24 | 2010-01-06 | 塔米智能科技（北京）有限公司 | System and method for welcoming guest by intelligent robot |
| CN103390194A (en) * | 2012-05-07 | 2013-11-13 | 北京三星通信技术研究有限公司 | Method, device and system for predicating user intention and recommending suggestion |
| CN104951428A (en) * | 2014-03-26 | 2015-09-30 | 阿里巴巴集团控股有限公司 | User intention recognition method and device |
| CN105100269A (en) * | 2015-08-27 | 2015-11-25 | 努比亚技术有限公司 | Mobile terminal and content recommending method based on different users |
Non-Patent Citations (1)
| Title |
|---|
| 家居服务机器人的人脸检测与识别问题的研究;曲莹;《中国优秀硕士学位论文全文数据库-信息科技辑》;20150815(第08期);第I138-1401页：摘要，正文第1章 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106096576A (en) | 2016-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106096576B (en) | A kind of intelligent Service method of robot | |
| US10762299B1 (en) | Conversational understanding | |
| CN103838834B (en) | Mention recommendation method, information processing method and system | |
| CN108121211A (en) | Control method, server and the computer readable storage medium of home appliance | |
| CN105046601A (en) | User data processing method and system | |
| CN105046600A (en) | Personalized information recommendation method and system of televisions for hotels | |
| CN106407930A (en) | Service method of massage robot | |
| CN105227971A (en) | The information recommendation method of a kind of hotel TV and system | |
| CN103629781B (en) | The system of air-treatment is carried out based on weather data | |
| CN103425649A (en) | Method and device for adding friend information | |
| CN106303599A (en) | A kind of information processing method, system and server | |
| WO2016101881A1 (en) | Method and apparatus for information recommendation realized by computer, and computer device | |
| CN102567534B (en) | Interactive product user generated content intercepting system and intercepting method for the same | |
| CN109471382A (en) | Water dispenser response method, device, equipment and storage medium | |
| KR102237319B1 (en) | An artificial intelligence system providing customized goods | |
| CN108107743A (en) | Distribution method, device, storage medium and the processor of control authority | |
| CN111413877A (en) | Method and device for controlling household appliance | |
| CN108711082A (en) | Recommend method, apparatus, Server for catering and storage medium in dining room | |
| CN110233764B (en) | Service providing method, device and system based on intelligent storage cabinet | |
| CN104102328B (en) | Information processing method and message processing device | |
| CN105989005A (en) | Information pushing method and device | |
| CN106548358A (en) | Conversation processing method and device | |
| CN109658173A (en) | A kind of food and beverage sevice customization method and system | |
| CN102306240A (en) | Touch type intelligent dynamic menu ordering system with independent food collision inspection function | |
| CN110705733A (en) | Number obtaining method and device, electronic equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200410 Address after: 410000 room a1380, headquarters building, Changsha Zhongdian Software Park Co., Ltd., No.39, Jianshan Road, high tech Development Zone, Changsha City, Hunan Province Patentee after: Changsha ge'ermen Intelligent Technology Co., Ltd Address before: 410000 Hunan province Changsha High-tech Development Zone Lugu industrial base Lu Tin Road No. 8 Building 1036 unit 4 Oaks Patentee before: Chen Baorong |