Summary of the invention
In view of this, the method, apparatus and robot for being designed to provide a kind of human-computer interaction of the embodiment of the present invention, with
It solves the above problems.
In a first aspect, the embodiment of the invention provides a kind of methods of human-computer interaction, comprising:
Acquire the multimedia messages of user, wherein the multimedia messages include: user images information and/or user's language
Message breath;
The use is determined according to the multimedia messages and the collected multimedia messages that store in preset database
The identity and interactive mode at family;Wherein, the interactive mode includes: interactive voice and/or movement interaction;
Interaction content corresponding with the identity of the user is transferred according to determining interactive mode and the user carries out mutually
It is dynamic.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein on
State acquisition user multimedia messages include:
When monitoring that user enters in image acquisition region, the multimedia messages of user described in automatic collection;
Alternatively, acquiring the multimedia messages of the user when monitoring user's triggering collection option.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein on
The multimedia messages for stating acquisition user include: the automatic call answering when having identified telephone bell, and acquire user in call
Voice messaging;
It is described to determine institute according to the multimedia messages stored in preset database and the collected multimedia messages
The identity and interactive mode for stating user include: crucial according to the voice messaging identification voice of user in the collected call
Word;The identity of the user is determined according to the voice recognition information stored in the voice keyword and preset database and is worked as
Preceding interactive mode is movement interaction, wherein the voice keyword includes that the name of the user and/or the user need to connect
Personnel's name of electricity;
It is described according to determining interactive mode transfer interaction content corresponding with the identity of the user and the user into
Row interaction includes: to transfer call forwarding number corresponding with the identity of the user, and the call is forwarded to the phone and is turned
Connect the corresponding terminal of number.
Any middle possibility, the embodiment of the present invention into second of possible embodiment of first aspect with reference to first aspect
Provide the third possible embodiment of first aspect, wherein above-mentioned to transfer and the use according to determining interactive mode
The corresponding interaction content of the identity at family interact with the user
According to language form corresponding to the voice messaging of user identification voice, according to determining interactive mode and identify
Language form transfer interaction content corresponding with the identity of the user and interacted with the user.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein on
The method for stating human-computer interaction further include: when having identified doorbell sound, starting automatically-controlled door is opened.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein on
It states to transfer interaction content corresponding with the identity of the user according to determining interactive mode and interact with the user and includes:
Interaction content corresponding with the identity of the user is looked up from the preset database according to determining interactive mode,
Wherein, it is previously stored in the database one of following or a variety of: in the information and corresponding interaction of visiting client
Hold, the pre- information for prompting employee and corresponding hint instructions, the identity of the stranger identified and corresponding image letter
Breath;
The interaction content found is transferred, and is interacted with the user.
With reference to first aspect, the embodiment of the invention provides the 6th kind of possible embodiments of first aspect, wherein on
The method for stating human-computer interaction further include:
When acquiring the multimedia messages during inspection, unusual condition is carried out to the collected multimedia messages and is sentenced
It is disconnected;
It when identifying the multimedia messages is burst or abnormal conditions, alarms, wherein the alarm is at least
Including following one: field speech or light warning send a telegraph client service center or related personnel's alarm.
Second aspect, the embodiment of the invention also provides a kind of square law device of human-computer interaction, which includes:
Information acquisition module, for acquiring the multimedia messages of user, wherein the multimedia messages include: user's figure
As information and/or user speech information;
Identity with interact determining module, for according to the multimedia messages and collected institute stored in preset database
State identity and interactive mode that multimedia messages determine the user;Wherein, the interactive mode include: interactive voice and/or
Movement interaction;
Interaction content transfers module, for transferring interaction corresponding with the identity of the user according to determining interactive mode
Content is interacted with the user.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein on
Stating information acquisition module includes:
First acquisition unit, for when monitoring that user enters in image acquisition region, user described in automatic collection
Multimedia messages;Alternatively,
Second acquisition unit, for acquiring the multimedia of the user when monitoring user's triggering collection option
Information.
In conjunction with second aspect, the embodiment of the invention provides second of possible embodiments of second aspect, wherein on
Stating information acquisition module includes:
Call voice acquisition unit, for when having identified telephone bell, automatic call answering, and acquire and used in call
The voice messaging at family;
The identity includes: with determining module is interacted
Keyword recognition unit, it is crucial for the voice messaging identification voice according to user in the collected call
Word;
The identity determination unit of user, for being known according to the voice stored in the voice keyword and preset database
Other information determines the identity of the user and current interactive mode is movement interaction, wherein the voice keyword includes described
The name of user and/or the user need personnel's name of even electricity;
The interaction content transfers module
Switching number transfers unit, will be described logical for transferring call forwarding number corresponding with the identity of the user
Words are forwarded to the corresponding terminal of the call forwarding number.
In conjunction with second aspect to second aspect second of possible embodiment in any middle possibility, the embodiment of the present invention
Provide the third possible embodiment of second aspect, wherein above-mentioned interaction content transfers module and includes:
Language form recognition unit, for the language form according to corresponding to the voice messaging of user identification voice;
First interaction content transfers unit, for transferring according to determining interactive mode and the language form identified and institute
The corresponding interaction content of identity for stating user is interacted with the user.
In conjunction with second aspect, the embodiment of the invention provides the 4th kind of possible embodiments of second aspect, wherein on
State the device of human-computer interaction further include:
Automatically-controlled door starting module, for when having identified doorbell sound, starting automatically-controlled door to be opened.
In conjunction with second aspect, the embodiment of the invention provides the 5th kind of possible embodiments of second aspect, wherein on
It states interaction content and transfers module and include:
Interaction content searching unit, for being looked up from the preset database and the user according to determining interactive mode
The corresponding interaction content of identity, wherein be previously stored in the database one of following or a variety of: visiting client's
Information and corresponding interaction content, the pre- information for prompting employee and corresponding hint instructions, the stranger's identified
Identity and corresponding image information;
Second interaction content transfers unit, carries out mutually for transferring the interaction content found, and with the user
It is dynamic.
In conjunction with second aspect, the embodiment of the invention provides the 6th kind of possible embodiments of second aspect, wherein on
State the device of human-computer interaction further include:
Unusual condition judgment module, when for acquiring the multimedia messages during inspection, to collected more matchmakers
Body information carries out unusual condition judgement;
Alarm module, for alarming when identifying the multimedia messages is burst or abnormal conditions,
In, the alarm includes at least following one: field speech or light warning, sends a telegraph client service center or related personnel's alarm.
The third aspect, the embodiment of the invention also provides a kind of robot, which includes: the dress of above-mentioned human-computer interaction
It sets.
In the method and device of human-computer interaction provided in an embodiment of the present invention, firstly, the multimedia messages of acquisition user,
Wherein, multimedia messages include: user images information and/or user speech information;Then, it is stored according in preset database
Multimedia messages and collected multimedia messages determine the identity and interactive mode of user;Wherein, interactive mode includes: language
Sound interaction and/or movement interaction;Finally, transferring interaction content corresponding with the identity of user according to determining interactive mode and using
Family is interacted, and by transferring matched interaction content according to the user identity identified, and then is carried out mutually with user
It is dynamic, the diversity of human-computer interaction is realized, and realize the mode for targetedly carrying out human-computer interaction.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
Middle attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the range of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on the embodiment of the present invention, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall within the protection scope of the present invention.
It says hello or guiding function in view of current most of robots mainly realize, function is relatively simple, and intelligently
Degree is not high, ineffective so as to cause human-computer interaction.Based on this, the embodiment of the invention provides a kind of method of human-computer interaction,
Device and robot, are described below by embodiment.
As shown in Figure 1, the embodiment of the invention provides a kind of method of human-computer interaction, the method comprising the steps of S102-
S106, specific as follows:
Step S102: the multimedia messages of user being acquired, wherein above-mentioned multimedia messages can be user images information,
It is also possible to user speech information, can also be user images information and user speech information while acquires;
Wherein it is possible to the multimedia messages of user are acquired in the following way, specifically:
A kind of mode is the multimedia messages for the user that real time monitoring active acquisition enters image acquisition areas, i.e., ought monitor
When user is entered in image acquisition region, the multimedia messages of the above-mentioned user of automatic collection;
Another way is the multimedia messages for the user that passive acquisition enters image acquisition areas, i.e., ought monitor that user touches
When hair acquisition option, the multimedia messages of above-mentioned user are acquired, have such as detected that user presses capture button either point
When hitting check box on touch screen, start to execute acquisition movement.
Step S104: true according to the multimedia messages and collected above-mentioned multimedia messages that are stored in preset database
The identity and interactive mode of fixed above-mentioned user;Wherein, above-mentioned interactive mode includes: interactive voice and/or movement interaction;
Specifically, the image information that will be stored in user images information collected in step S102 and preset database
It is compared, and then judges the identity of user;Meanwhile keyword is identified according to collected user speech information, according to identification
To keyword determine interactive mode, such as when identifying that user is visiting guest and needs to look for company XXX employee, interact at this time
Mode is movement interaction and interactive voice, then transfers corresponding interaction content by following step S106 and is interacted: first
It is first said hello in a manner of taking in guests, on then station which is guided to arrival company XXX employee.
Step S106: interaction content corresponding with the identity of above-mentioned user and above-mentioned use are transferred according to determining interactive mode
Family is interacted.
After the identity and interactive mode that determine user by step S104, step S106 is executed according to the identity and friendship of user
Mutual mode is transferred corresponding interaction content and is interacted, i.e., according to the identity of the user identified and the interactive mode determined,
It transfers interaction content corresponding with the user identity in preset database to be exchanged, such as: if judging user for public affairs
Take charge of employee, then said hello " good morning by XXX/and Good noon ";If it is unidentified go out identity, it is believed that its be visiting guest, then into
Row says hello " welcome XXX company, may I ask you has what what wanted help ";Then, it is identified according to the voice messaging of user
Keyword out, and relevant answer is retrieved from preset database, it exchanges, interact with user, in addition, ought not retrieve
In the case where matched answer, client service center will be gone to, the people in visiting guest's service or phone is continued as by manual service
Member's service, while aspectant exchange, interaction are realized by way of video calling.
In the method for human-computer interaction provided in an embodiment of the present invention, firstly, the multimedia messages of acquisition user, wherein
Multimedia messages include: user images information and/or user speech information;Then, more according to what is stored in preset database
Media information and collected multimedia messages determine the identity and interactive mode of user;Wherein, interactive mode includes: that voice is handed over
Mutually and/or movement interacts;Finally, according to determining interactive mode transfer interaction content corresponding with the identity of user and user into
Row interaction, in embodiments of the present invention by identifying the identity of user using face recognition technology, and according to the use identified
Family identity transfers matched interaction content, while by identifying keyword using voiced keyword identification technology, and
Interaction content is determined according to keyword and user identity, and then is interacted with user, is realized the diversity of human-computer interaction, is mentioned
The high flexibility of human-computer interaction, and different interaction contents is transferred for different users, realize targetedly into
The mode of row human-computer interaction.
Further, it is contemplated that work hours or quitting time may have guest to throw the phone of company at any time, be based on
This, another flow chart of man-machine interaction method as shown in Figure 2 is specific as follows:
Step S202: when having identified telephone bell, automatic call answering, and acquire the voice letter of user in call
Breath;
Step S204: voice keyword is identified according to the voice messaging of user in collected above-mentioned call;
Step S206: it is determined according to the voice recognition information stored in above-mentioned voice keyword and preset database above-mentioned
The identity of user and current interactive mode are movement interaction, wherein above-mentioned voice keyword include above-mentioned user name and/or
Above-mentioned user needs personnel's name of even electricity;
Step S208: transferring call forwarding number corresponding with the identity of above-mentioned user, above-mentioned call is forwarded to above-mentioned
The corresponding terminal of call forwarding number.
Wherein, above-mentioned call forwarding number corresponding with the identity of user may include called cell-phone number, also can wrap
Extension number is included, can also include client service center's number, it, will if the identity of above-mentioned user is that associated company employee is needed to open XX
XX phone is opened as call forwarding number, if not inquiring company personnel in presetting database opens XX phone, transfers customer service
Central number is as call forwarding number.
In addition, the process of receiving calls can also be interacted with user in call, asking questions for user is directly answered, is had
Body, can be with automatic call answering when having identified phone, and keyword is gone out according to the speech recognition of user in call, so
Relevant answer is retrieved from preset database afterwards, exchanges, interact with user in call, in addition, ought not retrieve
In the case where the answer matched, client service center will be gone to, personnel service in phone is continued as by manual service.
In embodiments of the present invention, by the way that the function of automatic call answering is arranged, and voiced keyword identification technology is combined,
Interaction content corresponding with user identity can be exported, and can be automatically by the call forwarding electricity that user needs into call
On words switching number, the diversity of human-computer interaction is furthermore achieved, improves the flexibility of human-computer interaction.
Further, due to consideration that being used in order to better improve there are many language form of collected user is possible
Family Experience Degree is based on this, transfers interaction content corresponding with the identity of above-mentioned user and above-mentioned use according to determining interactive mode
Family carries out interaction
According to language form corresponding to the voice messaging of user identification voice, according to determining interactive mode and identify
Language form transfer interaction content corresponding with the identity of above-mentioned user and interacted with above-mentioned user.
Wherein, it is also possible to identify the macroscopic features of user according to the image information of user, according to determining interactive mode
Interaction content corresponding with the identity of above-mentioned user and above-mentioned use are transferred with language form corresponding to the macroscopic features identified
Family is interacted, and both the above mode can determine language form, and if using both modes simultaneously, it can make really
The language form made is more accurate, either the language form according to corresponding to the voice messaging of user identification voice, still
The macroscopic features that user is identified according to the image information of user, determines language form, above two basis further according to macroscopic features
The multimedia messages of user determine language form, in protection scope of the present invention in a manner of realizing multi-language environment exchange
It is interior.
In embodiments of the present invention, according to the language message of collected user identify voice corresponding to language form
Or the macroscopic features of user is identified according to the image information of collected user, class of languages is determined further according to macroscopic features
Type is exchanged with visiting guest using corresponding language form, is interacted, by using the exchange way of multi-language environment, into
One step increases the flexibility of human-computer interaction, improves the Experience Degree of visiting guest.
Further, the above method further include: when having identified doorbell sound, starting automatically-controlled door is opened.
In embodiments of the present invention, it may be implemented to automatically open automatically-controlled door, specifically include: when having identified doorbell sound
When, it automatically opens automatically-controlled door and the image information of collected user is recorded and and uses targeted interaction side
Formula is convenient for real-time monitoring and subsequent tracking.
The flexibility of human-computer interaction in order to further increase, it is above-mentioned to transfer according to determining interactive mode with above-mentioned user's
The corresponding interaction content of identity interact with above-mentioned user
Interaction content corresponding with the identity of above-mentioned user is looked up from the preset database according to determining interactive mode,
Wherein, it is previously stored in above-mentioned database one of following or a variety of: in the information and corresponding interaction of visiting client
Hold, the pre- information for prompting employee and corresponding hint instructions, the identity of the stranger identified and corresponding image letter
Breath;
The above-mentioned interaction content found is transferred, and is interacted with above-mentioned user.
Specifically, can be stored in advance in preset database visiting client information and corresponding interaction content,
Such as: when might have certain leader's inspection in the recent period, then it can temporarily add the identification data (facial image of the leader
And/or acoustic information), and corresponding identification mode (recognition of face/or voice recognition) is added in robot, and add
Corresponding human-computer interaction mode (be such as directed to and be specially arranged welcome mode);If judging, user is pre-stored arrives
Expert/the professor for facing guidance is then said hello " warm welcome XXX expert/professor come XXX company instruct work ";As a result, may be used
Some special interaction modes are carried out to control robot, further increase flexibility and the practicability of human-computer interaction;
The pre- information for prompting employee and corresponding hint instructions, example can also be stored in advance in preset database
Such as, for interior employee, the interactive service needed for oneself can be set in robot, after identifying the identity of the employee,
The XX time can be needed to have a meeting for some corresponding interaction modes of employee's offer of the identity, such as interior employee second day, then
The setting meeting in robot can be shifted to an earlier date and remind service, after robot saves the setting, can identify this at second day
After employee, the human-computer interaction operation for prompting of setting is executed;For another example, remind operation can also be prompting whether band work board,
Or reminded according to current time it is whether late etc., can be with by the way that identification to be combined with human-computer interaction mode is set
Further enhance flexibility and the practicability of human-computer interaction;
Can also real-time storage has identified in preset database stranger identity and corresponding image letter
Breath, specifically includes: carrying out image recording to the personnel for the company that first enters and saves its identity, which is again introduced into company can
To automatically identify its identity, output exchange sentence is determined according to the identity of the stored personnel, and carry out and the personnel
The corresponding exchange of identity, interaction, such as: identify that personnel identity is courier, the courier second by first time exchange
Ci Lai company actively says hello by the mode of saying hello with courier.
In embodiments of the present invention, by being preset in preset database in user information and corresponding interaction
Hold, by the way of this flexible setting human-computer interaction, while increasing face identity memory function, further increases man-machine mutual
Dynamic flexibility improves the Experience Degree of user.
In addition, the above method further include: acquisition inspection during multimedia messages when, to collected above-mentioned multimedia
Information carries out unusual condition judgement;
When identifying above-mentioned multimedia messages is burst or abnormal conditions, alarm, wherein above-mentioned alarm is at least
Including following one: field speech or light warning send a telegraph client service center or related personnel's alarm.
Specifically, can be alarmed by alarm module, when identifying in the presence of burst or abnormal conditions wherein alarming
Mode can be field speech alarm, can also be alarmed with light flash, can also be and is transferred to client service center, or switching
Onto preset mobile phone, to be monitored in real time by the camera shooting acquisition device in robot, realizes 24 hours and supervise round the clock
Control can push on company's foreground system and APP if someone swarms into and can trigger alarm system in time outside the work hours, logical in time
Know that mansion property is ensured public security, suffers a loss from company's property;Meanwhile by supervising data storage to Cloud Server, the cloud service
Device is communicated by wireless communication mode and client, and the user in relative client can obtain from Cloud Server at any time
Required information.
In conclusion in the method for human-computer interaction provided in an embodiment of the present invention, firstly, the multimedia letter of acquisition user
Breath, wherein the multimedia messages include: user images information and/or user speech information;Then, according to preset database
The multimedia messages of middle storage and collected multimedia messages determine the identity and interactive mode of user;Wherein, the interaction side
Formula includes: interactive voice and/or movement interaction;Finally, being transferred according to determining interactive mode corresponding with the identity of user mutual
Dynamic content is interacted with user, the embodiment of the present invention by identifying the identity of user using face recognition technology, and according to
The user identity identified transfers matched interaction content, while by being identified using voiced keyword identification technology
Keyword, and interaction content is determined according to keyword and user identity, and then interact with user, realize human-computer interaction
Diversity improves the flexibility of human-computer interaction, and transfers different interaction contents for different users, has realized needle
To property carry out the mode of human-computer interaction;Further, by the way that the function of automatic call answering is arranged, and voiced keyword is combined
Identification technology, it can output interaction content corresponding with user identity, and can automatically use call forwarding into call
On the call forwarding number that family needs, the diversity of human-computer interaction is furthermore achieved, improves the flexibility of human-computer interaction;Again
Further, according to the language message of collected user identify voice corresponding to language form or according to collected
The image information of user identifies the macroscopic features of user, determines language form further according to macroscopic features, using corresponding language
Type is exchanged with visiting guest, is interacted, and by using the exchange way of multi-language environment, further increases human-computer interaction
Flexibility improves the Experience Degree of visiting guest;Further, by preset in preset database user information and
Corresponding interaction content by the way of this flexible setting human-computer interaction, while increasing face identity memory function, further
The flexibility for increasing human-computer interaction improves the Experience Degree of user.
As shown in figure 3, the embodiment of the invention provides a kind of device of human-computer interaction, which includes:
Information acquisition module 402, for acquiring the multimedia messages of user, wherein above-mentioned multimedia messages include: user
Image information and/or user speech information;
Identity with interact determining module 404, for according to the multimedia messages that are stored in preset database and collecting
Above-mentioned multimedia messages determine the identity and interactive mode of above-mentioned user;Wherein, above-mentioned interactive mode includes: interactive voice
And/or movement interaction;
Interaction content transfers module 406, corresponding with the identity of above-mentioned user for transferring according to determining interactive mode
Interaction content is interacted with above-mentioned user.
Further, above- mentioned information acquisition module 402 includes:
First acquisition unit, for when monitoring that user enters in image acquisition region, the above-mentioned user's of automatic collection
Multimedia messages;Alternatively,
Second acquisition unit, for acquiring the multimedia of above-mentioned user when monitoring user's triggering collection option
Information.
Further, as shown in figure 4, above- mentioned information acquisition module 402 includes:
Call voice acquisition unit 4021, for when having identified telephone bell, automatic call answering, and acquire call
The voice messaging of middle user;
Above-mentioned identity includes: with determining module 404 is interacted
Keyword recognition unit 4041, for being closed according to the voice messaging identification voice of user in collected above-mentioned call
Keyword;
The identity determination unit 4042 of user, for according to the language stored in above-mentioned voice keyword and preset database
Sound identification information determines the identity of above-mentioned user and current interactive mode is movement interaction, wherein above-mentioned voice keyword includes
The name of above-mentioned user and/or above-mentioned user need personnel's name of even electricity;
Above-mentioned interaction content transfers module 406
Switching number transfers unit 4061, will be upper for transferring call forwarding number corresponding with the identity of above-mentioned user
It states call and is forwarded to the corresponding terminal of above-mentioned call forwarding number.
Further, as shown in figure 5, above-mentioned interaction content transfers module 406 includes:
Language form recognition unit 4062, for the language form according to corresponding to the voice messaging of user identification voice;
First interaction content transfers unit 4063, for transferring according to determining interactive mode and the language form identified
Interaction content corresponding with the identity of above-mentioned user is interacted with above-mentioned user.
Further, above-mentioned human-computer interaction device further include:
Automatically-controlled door starting module, for when having identified doorbell sound, starting automatically-controlled door to be opened.
Further, above-mentioned interaction content transfers module 406 and includes:
Interaction content searching unit, for being looked up from the preset database and above-mentioned user according to determining interactive mode
The corresponding interaction content of identity, wherein be previously stored in above-mentioned database one of following or a variety of: visiting client's
Information and corresponding interaction content, the pre- information for prompting employee and corresponding hint instructions, the stranger's identified
Identity and corresponding image information;
Second interaction content transfers unit, carries out mutually for transferring the above-mentioned interaction content found, and with above-mentioned user
It is dynamic.
Further, above-mentioned human-computer interaction device further include:
Unusual condition judgment module, when for acquiring the multimedia messages during inspection, to collected above-mentioned more matchmakers
Body information carries out unusual condition judgement;
Alarm module, for alarming when identifying above-mentioned multimedia messages is burst or abnormal conditions,
In, above-mentioned alarm includes at least following one: field speech or light warning, sends a telegraph client service center or related personnel's alarm.
A kind of robot is also provided in the embodiment of the present invention, which includes: the device of above-mentioned human-computer interaction.
Due to consideration that most of robots mainly realize and say hello or guiding function that function is relatively simple at present, and
Degree of intelligence is not high, and function achieved by existing robot is insufficient for the demand of foreground supervision, can not substitute foreground
Personnel complete the related work on foreground, are embedded in face identification functions in robot provided in an embodiment of the present invention, pass through acquisition
It into the image information of the personnel of company, is then compared, and then judges with the image information for being stored in advance in the database
The identity of the personnel is exchanged using preset exchange way, while being embedded in voiced keyword identification function, by acquire into
The voice messaging for entering the personnel of company, then identifies keyword, transfers interaction content, this hair according to keyword and personnel identity
The robot that bright embodiment provides, which can be used to substitute foreground personnel, accurately to be exchanged with visiting guest, is interacted, Ke Yigeng
It is good to meet the actual demand for being applied to foreground robot;The field of human-computer interaction diversity, flexibility can also be required using other
Scape.
Further, it can also be embedded in punch card system in above-mentioned robot, and automatically generate attendance record, it is specific to wrap
It includes: by identifying disengaging personnel image, company being passed in and out to employee and is recorded the time, and generates attendance record list, the record
Project includes date, work hours, quitting time, and the work hours enter and leave company and can also be recorded.
Further, can also be embedded in predetermined module in above-mentioned robot: such as meeting room is predetermined.
Further, it can also be embedded in sound source positioning function in above-mentioned robot, can be adjusted in time according to sound source position
It turns to, always face face.
Based on above-mentioned analysis it is found that compared with robot in the related technology, provided in an embodiment of the present invention man-machine mutual
Dynamic device and robot is firstly, acquire the multimedia messages of user, wherein the multimedia messages include: user images information
And/or user speech information;Then, according to the multimedia messages and collected multimedia messages stored in preset database
Determine the identity and interactive mode of user;Wherein, which includes: interactive voice and/or movement interaction;Finally, according to
Determining interactive mode is transferred interaction content corresponding with the identity of user and is interacted with user, and the embodiment of the present invention passes through benefit
The identity of user is identified with face recognition technology, and is transferred in matched interaction according to the user identity identified
Hold, while by identifying keyword using voiced keyword identification technology, and interaction is determined according to keyword and user identity
Content, and then interacted with user, the diversity of human-computer interaction is realized, the flexibility of human-computer interaction, Yi Jizhen are improved
Different interaction contents is transferred to different users, realizes the mode for targetedly carrying out human-computer interaction;Further, lead to
The function of setting automatic call answering is crossed, and combines voiced keyword identification technology, it can output is corresponding with user identity
Interaction content, and can automatically will call forwarding to call in user need call forwarding number on, be furthermore achieved
The diversity of human-computer interaction improves the flexibility of human-computer interaction;Further, according to the language message of collected user
It identifies language form corresponding to voice or identifies the macroscopic features of user according to the image information of collected user,
Language form is determined further according to macroscopic features, is exchanged, is interacted with visiting guest using corresponding language form, by using
The exchange way of multi-language environment further increases the flexibility of human-computer interaction, improves the Experience Degree of visiting guest;Further
, it is man-machine using this flexible setting by presetting user information and corresponding interaction content in preset database
The mode of interaction, while increasing face identity memory function, the flexibility of human-computer interaction is further increased, improves user's
Experience Degree.
The device of human-computer interaction provided by the embodiment of the present invention can set for the specific hardware in equipment or be installed on
Standby upper software or firmware etc..The technical effect of device provided by the embodiment of the present invention, realization principle and generation and aforementioned
Embodiment of the method is identical, and to briefly describe, Installation practice part does not refer to place, can refer to corresponding in preceding method embodiment
Content.It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description, dress
The specific work process with unit is set, the corresponding process during reference can be made to the above method embodiment, details are not described herein.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.