CN109685550A - Smart machine control method, device, electronic equipment and storage medium - Google Patents
Smart machine control method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109685550A CN109685550A CN201811472043.4A CN201811472043A CN109685550A CN 109685550 A CN109685550 A CN 109685550A CN 201811472043 A CN201811472043 A CN 201811472043A CN 109685550 A CN109685550 A CN 109685550A
- Authority
- CN
- China
- Prior art keywords
- trigger condition
- smart machine
- artificial customer
- user
- customer side
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention relates to robotic technology field, a kind of smart machine control method, device, electronic equipment and storage medium are disclosed, which comprises determination meets preset artificial customer service trigger condition;If the trigger condition met belongs to first kind trigger condition, control smart machine exports prompt information, whether connects artificial customer side with prompt, and after receiving confirmation feedback, control smart machine connects artificial customer side;If the trigger condition met belongs to the second class trigger condition, control smart machine connects artificial customer side.Technical solution provided in an embodiment of the present invention, the help whether user needs artificial customer service can be judged automatically, and artificial customer side is connected when user wants help, remote assistance is provided for user, therefore, one remote handle customer service just can assist in more smart machines and complete routine work, save human cost.
Description
Technical field
The present invention relates to robotic technology field more particularly to a kind of smart machine control method, device, electronic equipment and
Storage medium.
Background technique
With flourishing for robot industry, more and more robots are applied in actual application scenarios, example
Such as, Self-Service machine people can help or guide user's transacting business, additionally it is possible to answer user's business relevant issues of proposition.
Although robot technology, in high speed development, there are still certain limitations for robot itself, such as machine under some scenes
Device people can not provide help or user does not know how using robot, for this purpose, often requiring to be equipped with a fortune for robot
On the one hand battalion personnel solve user and do not know how the puzzlement using robot, on the one hand when robot can not solve currently to ask
Help is provided for user when topic, to assist the proper use of robot of user.
The purpose of applied robot is in order to substitute manpower, still, if also need specially to be equipped with an operation personnel
Carve it is on duty beside robot, just cannot achieve reduce human cost original idea.
Summary of the invention
The embodiment of the present invention provides a kind of smart machine control method, device, electronic equipment and storage medium, existing to solve
Have that also to need specially to be equipped with operation personnel's moment in technology on duty beside robot, asking for human cost can not be reduced
Topic.
In a first aspect, one embodiment of the invention provides a kind of smart machine control method, comprising:
Determination meets preset artificial customer service trigger condition;
If the trigger condition met belongs to first kind trigger condition, control smart machine exports prompt information, with prompt
Whether artificial customer side is connected, and after receiving confirmation feedback, control smart machine connects artificial customer side;
If the trigger condition met belongs to the second class trigger condition, control smart machine connects artificial customer side.
Second aspect, one embodiment of the invention provide a kind of smart machine control device, comprising:
Trigger module meets preset artificial customer service trigger condition for determination;
Control module, if the trigger condition for being met belongs to first kind trigger condition, control smart machine output is mentioned
Show information, whether artificial customer side is connected with prompt, after receiving confirmation feedback, control smart machine connects artificial customer service
End;If the trigger condition met belongs to the second class trigger condition, control smart machine connects artificial customer side.
The third aspect, one embodiment of the invention provide a kind of electronic equipment, including transceiver, memory, processor and
Store the computer program that can be run on a memory and on a processor, wherein transceiver is under the control of a processor
Send and receive data, the step of processor realizes any of the above-described kind of method when executing program.
Fourth aspect, one embodiment of the invention provide a kind of computer readable storage medium, are stored thereon with computer
The step of program instruction, which realizes any of the above-described kind of method when being executed by processor.
Technical solution provided in an embodiment of the present invention is provided with two class people when judging whether user needs artificial customer service
Whether work customer service trigger condition is strong to distinguish the intention that user needs artificial customer service to help.When triggering first kind trigger condition
When, illustrate that user may need the help of artificial customer service, but intention is not obvious enough, controls smart machine output prompt letter at this time
Breath prompts whether connect artificial customer side, when user confirms that the artificial customer service of needs helps, reconnects artificial customer side, in this way,
Help can either be provided for user, and can reduce the workload of the artificial customer service in rear end.When triggering the second class trigger condition, say
Bright user is badly in need of the help of artificial customer service, is directly connected to artificial customer side at this time, does not need user and makes any operation, simplifies
User's operation improves user experience, and on duty beside smart machine without operation personnel's moment, saves human cost.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will make below to required in the embodiment of the present invention
Attached drawing is briefly described, it should be apparent that, attached drawing described below is only some embodiments of the present invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the application scenarios schematic diagram of smart machine control method provided in an embodiment of the present invention;
Fig. 2 is the another application schematic diagram of a scenario of smart machine control method provided in an embodiment of the present invention;
Fig. 3 is the flow diagram for the smart machine control method that one embodiment of the invention provides;
Fig. 4 is the structural schematic diagram for the smart machine control device that one embodiment of the invention provides;
Fig. 5 is the structural schematic diagram for the electronic equipment that one embodiment of the invention provides.
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
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
Any number of elements in attached drawing is used to example rather than limitation and any name are only used for distinguishing, without
With any restrictions meaning.
During concrete practice, in user's transacting business self-service using robot client, can usually encounter will not
Therefore the case where corresponding help can not be provided using robot or robot, usually sees robot client in real life
An other operation personnel on duty, provides help when user shows signs of reluctance for user, it is seen then that existing robot intelligence not enough
Energyization cannot achieve the original idea for reducing human cost.
For this purpose, the present inventor is it is considered that judge that user is using by the interaction scenario of user and smart machine
Whether meet difficulty during smart machine, interactive mode can be the various ways such as interactive voice, touch-control interaction.Sentencing
When whether disconnected user needs artificial customer service, it is provided with the artificial customer service trigger condition of two classes, needs artificial customer service side to distinguish user
Whether the intention helped is strong, and when user may need the help of artificial customer service but be intended to not obvious enough, control smart machine is defeated
Prompt information out prompts user that artificial customer service may be selected and helps, and when user confirms that the artificial customer service of needs helps, reconnects artificial
Customer side in this way, the user really to want help that can either be positive provides help, and can reduce the work of the artificial customer service in rear end
Amount;And when recognizing user and being badly in need of the help of artificial customer service, it is directly connected to artificial customer side, user is not needed and makes any behaviour
Make, simplifies user's operation, improve user experience.Since smart machine can independently judge whether user needs artificial customer service
It helps, and connection and the artificial customer side automatically when user wants help, provides remote assistance for user, therefore, one long-range
Artificial customer service just can assist in more smart machines and complete routine work, on duty by smart machine without operation personnel's moment
Side saves human cost.
After introduced the basic principles of the present invention, lower mask body introduces various non-limiting embodiment party of the invention
Formula.
It is the application scenarios schematic diagram of smart machine control method provided in an embodiment of the present invention referring initially to Fig. 1.With
In family 10 and 11 interactive process of smart machine, instruction, the data etc. that smart machine 11 inputs user are sent to server 12, by
Whether the information automatic identifications such as instruction, the data that server 12 is inputted according to user need artificial customer service to intervene, when server 12
When judgement needs artificial customer service intervention, control smart machine 11 connects artificial customer side 13, the artificial customer service of artificial customer side 13
14 provide help by way of video calling or voice communication for user 10.
Smart machine 11 under this application scenarios, server 12 by network carry out communication link between artificial customer side 13
It connects, which can be local area network, wide area network etc..
It is the another application schematic diagram of a scenario of smart machine control method provided in an embodiment of the present invention with reference to Fig. 2.With
In family 20 and 21 interactive process of smart machine, the autonomous classifications such as instruction, data that smart machine 21 is inputted according to user whether need
Artificial customer service is wanted to intervene, when smart machine 21 judges to need artificial customer service intervention, smart machine 21 connects artificial customer side 22,
The artificial customer service 23 of artificial customer side 22 provides help by way of video calling or voice communication for user 20.
It is communicatively coupled between smart machine 21 and artificial customer side 22 by network under this application scenarios, the network
It can be local area network, wide area network etc..
Below with reference to application scenarios shown in Fig. 1,2, technical solution provided in an embodiment of the present invention is illustrated.
With reference to Fig. 3, the embodiment of the present invention provides a kind of smart machine control method, comprising the following steps:
S301, determination meet preset artificial customer service trigger condition.
When it is implemented, trigger condition can be divided into two classes: when triggering first kind trigger condition, illustrating that user may need people
The help of work customer service, but be intended to not obvious enough;When triggering the second class trigger condition, illustrate that the artificial visitor of needs is explicitly indicated in user
Take help.
In the embodiment of the present invention, first kind trigger condition includes but is not limited at least one following condition:
(1) it under wake-up states, is continuously detected the facial image of target object but does not receive target in preset duration
The input of object is requested.
Above-mentioned condition (1) is for following scene setting: before user rests on smart machine and for a long time not into
When row operation smart machine, show that the user is in state of hesitating, user may not know how operation smart machine, at this time really
The help of artificial customer service may be needed by determining user.
Target object refers to the user using smart machine, if be continuously detected by the camera of smart machine same
The facial image of user, before showing that the user persistently rests on smart machine.Whether there is user to stop before detection smart machine
Mode is not limited to the mode of above-mentioned detection facial image, can also be by equipment detections such as infrared sensors built in smart machine
It is no to there is user to stop before smart machine.
Preset duration in above-mentioned trigger condition (1) can be adjusted according to concrete application scene.
In the present embodiment, input request is the instruction or number that user is inputted during using smart machine to smart machine
According to etc. information.When it is implemented, input request includes but is not limited to following at least one mode: touch control operation, voice messaging and
Limb action etc..For example, user presses " confirmation " key on smart machine, to trigger " confirmation " input request;User makes
With the fingerprint capturer of smart machine, card reader etc., to get the finger print data or card data of user's input;User's input
Voice messaging " checks lower one page ";User makes the movement nodded, and smart machine utilizes the image recognition user of camera acquisition
The movement nodded, to get " nodding " movement of user's input.
(2) continuously receiving target object indicates that the quantity of the input request of same or similar intention is more than preset quantity.
For example, the phonetic order same semantic when the input of user's continuous several times, and when number has been more than preset quantity, show
User from smart machine there is no satisfied feedback is obtained, so inquiry smart machine can be just repeated continuously, at this point, user
It may need the help of artificial customer service.
Preset quantity in above-mentioned trigger condition (2) can be adjusted according to concrete application scene, such as preset quantity is set
It is set to 3 times.
Certainly, when it is implemented, prefixed time interval can also be arranged in above-mentioned trigger condition (2), when in preset time
In interval, continuously receiving indicates that the quantity of the input request of same or similar intention is more than preset quantity, just triggers the condition
(2).Wherein, prefixed time interval can be adjusted according to concrete application scene.
(3) response of the input request of same or similar intention, which is that wrong number is more than, continuously to be indicated to target object
First preset times.
For example, smart machine or server provide when the input of user's continuous several times indicates the voice of same or similar semanteme
Response be mistake when, show that smart machine or server can not correctly be run, the intervention of artificial customer service may be needed at this time.
Wherein, the first preset times can be adjusted according to concrete application scene.
(4) number that can not continuously parse the intention of the input request of target object is more than the second preset times.
For example, continuous several times receive the unclear voice of user semantic, cause server that can not parse semanteme, at this point,
Show that user may not know how operation smart machine, needs the intervention of artificial customer service.
Wherein, the second preset times can be adjusted according to concrete application scene, such as the second preset times are set as 5
It is secondary.
(5) it cannot respond to the input request of target object.
In the present embodiment, the input request that cannot respond to target object be can be, for the instruction that user assigns, due to certainly
Body Equipment (such as smart machine breaks down, or the server fail connecting with smart machine), leads to not complete
Instruct corresponding task.For example, smart machine is lost map when smart machine provides navigation Service for user, lead to nothing
Method completes the navigation task that user assigns, and may need the intervention of artificial customer service at this time.
(6) number for being consecutively detected the input information errors of target object is more than third preset times.
Trigger condition (6) is for following scene setting: smart machine needs user to input some specified information, example
Such as password, identifying code information, alternatively, user is needed to make blink, the first-class some required movements of point, still, user does not know
How to operate, user is caused to mishandle and the information of input error.At this point, can by user input input information and correctly
Information is compared, make user input input information be mistake judging result, when detect user's continuous several times input
When error message, show that user may need the help of artificial customer service.
Wherein, third preset times can be adjusted according to concrete application scene, such as third preset times are set as 3
It is secondary.
It should be noted that the first kind trigger condition in the embodiment of the present invention is not limited to above-mentioned 6 conditions, it can be according to reality
Border application scenarios and user demand configure first kind trigger condition.For example, when not needing certain on user's operation smart machine
When a little equipment (for example, card reader, fingerprint capturer etc.) and user continue to operate these equipment, identify that the input request of user is
Mistake indicates that user may not know how proper use of smart machine, it may be necessary to the intervention of artificial customer service at this time.
In the embodiment of the present invention, the second class trigger condition includes but is not limited to: receiving target object indicates to need manually
The input request that customer service is intended to.
When input request is voice messaging, the semanteme of capable of speech information includes the language to want help when recognizing
When adopted, the second class trigger condition is triggered.For example, when user input " I wants help ", " someone exists ", " why this machine is used " or
When " artificial customer service " etc. includes the voice for needing artificial customer service to be intended to, illustrate that the intention for needing artificial customer service to help is very strong, this
When can directly control smart machine and connect artificial customer side, without prompting user.
When input request is touch control operation, detect user click the artificial customer service of calling on smart machine by
Button triggers the second class trigger condition.
The above-mentioned trigger condition enumerated is merely illustrative, and in specific implementation process, is not limited to above-mentioned embodiment.
When it is implemented, server can store multiple inputs request that same user inputs within the same period and this
The response condition of multiple input requests, so as to according to the intention of a series of operation identification user of user.
If S302, the trigger condition met belong to first kind trigger condition, control smart machine exports prompt information, with
Whether prompt connects artificial customer side, and after receiving confirmation feedback, control smart machine connects artificial customer side.
When triggering first kind trigger condition, illustrate that user may need the help of artificial customer service, but be intended to not obvious enough.This
When, it can remind user that artificial customer service can be used by way of exporting prompt information, be decided in its sole discretion by user and whether need to obtain
The help of artificial customer service, in this way, can reduce the workload of the artificial customer service in rear end.
When it is implemented, controllable smart machine is by way of floating tag and/or the mode of voice broadcast is exported and mentioned
Show information.
When exporting prompt information by way of floating tag, the content of prompt information may include asking the user whether
The text information for needing artificial customer service to help, such as " help for whether needing artificial customer service ".Can also include in prompt information
The method for connecting artificial customer side, to assist user to use smart machine.Alternatively, insertion connection is artificial directly in prompt information
The virtual touch controlled key of customer side clicks directly on the virtual touching in prompt information when user confirms that the artificial customer service of needs helps
Control button can connect artificial customer side, save user and find the process that triggering connects the button of artificial customer side.If handed over
There is the virtual touch controlled key for calling artificial customer service that can also highlight while display reminding information in mutual interface
The virtual touch controlled key allows the user to be quickly found out the entrance for connecting artificial customer side.
It is exportable similar " help for whether needing artificial customer service " when exporting prompt information by way of voice broadcast
Inquiry language, operation prompt informations such as " if you need to help, the call button of screen lower left please be click " can also be exported.
When it is implemented, voice broadcast can be carried out while exporting prompt information by way of floating tag.
The information that user can be voice or input validation needs artificial customer service to help by way of clicking button, smart machine
After the confirmation message for receiving user's input, it is directly connected to artificial customer side.Alternatively, the confirmation for being inputted user by smart machine
Information is sent to server, connects artificial customer side by server control smart machine.
If S303, the trigger condition met belong to the second class trigger condition, control smart machine connects artificial customer side.
When triggering the second class trigger condition, the intention for illustrating that user needs artificial customer service to help is very strong, at this point, can be straight
It connects control smart machine and connects artificial customer side, without exporting prompt information, to simplify the behaviour that user calls artificial customer service
Make.
When it is implemented, it includes: that control smart machine is connected by video that control smart machine, which connects artificial customer side method,
It connects or the mode of voice connection connects artificial customer side.After establishing connection, the artificial customer service of artificial customer side can be logical by video
Words or the mode of voice communication are assisted user to handle related service or user's exclusion are helped to be encountered in the process using smart machine
It is difficult.
The smart machine control method of the present embodiment is provided with two class people when judging whether user needs artificial customer service
Whether work customer service trigger condition is strong to distinguish the intention that user needs artificial customer service to help.When triggering first kind trigger condition
When, illustrate that user may need the help of artificial customer service, but intention is not obvious enough, controls smart machine output prompt letter at this time
Breath prompts whether connect artificial customer side, when user confirms that the artificial customer service of needs helps, reconnects artificial customer side, in this way,
Help can either be provided for user, and can reduce the workload of the artificial customer service in rear end.When triggering the second class trigger condition, say
Bright user is badly in need of the help of artificial customer service, is directly connected to artificial customer side at this time, does not need user and makes any operation, simplifies
User's operation improves user experience.
In addition, the smart machine control method of the present embodiment, is asked according to user and the input in smart machine interactive process
It asks and smart machine is to the response condition of input request, independently judge whether user needs artificial customer service, recognizing user
When artificial customer service being needed to assist, connection smart machine and artificial customer side, artificial customer service passes through video calling or voice communication
It is difficult that mode helps user to solve, and therefore, a remote handle customer service just can assist in more smart machines and complete routine work,
It is on duty beside smart machine without operation personnel's moment, save human cost.In addition, in the touch-control behaviour inputted based on user
On the basis of work judge whether user needs artificial help, a variety of means of identification such as speech recognition, human body sensing are combined, from more
A dimension judges whether user needs manually to help, and improves the accuracy rate of judgement, reduces smart machine erroneous trigger called person
The frequency of work customer service function.
Further, after control smart machine connects artificial customer side, the smart machine control method of the present embodiment
It is further comprising the steps of: the face information of control smart machine acquisition target object;According to face information carry out recognition of face with
It determines the corresponding user information of target object, and is sent to artificial customer side.
If user used such smart machine or carried out registration before, server can store user's letter of the user
Breath, face information, identity information or operation information including user etc..Server is searched according to current collected face information
It is sent to corresponding artificial customer side to the user information of the user, and by user information, so that customer service can be got in time
User information preferably provides help for user.It can be strange use by the user if identify that the user is strange user
The information at family is sent to artificial customer side, and therefore, customer service would know that the user may be to use smart machine for the first time.
Further, trigger condition can be updated according to the difference or variation of application scenarios, such as can modifies, increases or deletes
Trigger condition, trigger condition include first kind trigger condition and the second class trigger condition.Wherein, modification trigger condition includes modification
Parameter value in trigger condition, such as preset duration, preset quantity, preset times (including the first preset times, second default time
Number, third preset times), prefixed time interval etc..
For example, during smart machine is assisted in artificial customer service, can touch under a large amount of representative, real scenes,
The high customer problem of real-time, on backstage by record these problems, summarizing relevant data can be refined for artificial customer service
Smart machine needs the function of optimizing out, plays greatly positive feedback effect to the function of improving smart machine itself.It is based on
The customer problem that artificial customer service encounters in practical applications can extract new trigger condition, or the certain trigger conditions of discovery
It is easy to cause false triggering, deletes the trigger condition, or modify to trigger condition.
When it is implemented, server counts the case where can also being triggered to each trigger condition, according to statistical
Analysis result automatically updates trigger condition.
The situation that is triggered is counted there are two types of mode for first kind trigger condition, it is automatic to be carried out to first kind trigger condition
It updates:
First way is directed to each first kind trigger condition, counts the triggering time that the first kind trigger condition is triggered
The several and first kind trigger condition connects the connection number of artificial customer side after being triggered, calculate triggering times and connection number it
Between conversion ratio the first kind trigger condition is updated according to the corresponding conversion ratio of first kind trigger condition.
For example, first kind trigger condition A is triggered 100 times, after user sees the prompt information of smart machine output, only
5 selections call artificial customer service, then conversion ratio is 5%, illustrate under the corresponding scene of first kind trigger condition A, user is simultaneously
The help of artificial customer service is not needed, the probability of first kind trigger condition A false triggering is larger, first kind trigger condition A can be deleted, or
Person modifies the parameter value in first kind trigger condition A, reduces the probability of false triggering.
The second way is directed to each first kind trigger condition, counts the triggering frequency that the first kind trigger condition is triggered
Rate updates the first kind trigger condition according to the corresponding triggering frequency of the first kind trigger condition.
For example, the frequency that first kind trigger condition B is triggered is 1 time/month, illustrate first kind trigger condition B be not easy by
Triggering, shows the setting irrationality of first kind trigger condition B, can delete first kind trigger condition B, or modification first kind touching
Parameter value in clockwork spring part B improves its probability being triggered, and the first kind trigger condition waste for avoiding bulk redundancy useless calculates
Resource.
The automatic update method of second class trigger condition includes: to count second class for each second class trigger condition
The triggering frequency that trigger condition is triggered updates second class triggering according to the corresponding triggering frequency of the second class trigger condition
Condition.
For example, the frequency that the second class trigger condition C is triggered is 1 time/month, illustrate the second class trigger condition C be not easy by
Triggering, shows the setting irrationality of the second class trigger condition C, can delete the second class trigger condition C, or modification the second class touching
The parameter value in condition C is sent out, its probability being triggered is improved, the second class trigger condition waste for avoiding bulk redundancy useless calculates
Resource.
It should be noted that the smart machine control method of the present embodiment can be executed by server, alternatively, by smart machine
It executes.
As shown in figure 4, being based on inventive concept identical with above-mentioned smart machine control method, the embodiment of the present invention is also provided
A kind of smart machine control device 40, including trigger module 401 and control module 402.
Trigger module 401 meets preset artificial customer service trigger condition for determination;
If the trigger condition that control module 402 is used to be met belongs to first kind trigger condition, control smart machine output
Whether prompt information connects artificial customer side with prompt, and after receiving confirmation feedback, control smart machine connects artificial customer service
End;If the trigger condition met belongs to the second class trigger condition, control smart machine connects artificial customer side.
Optionally, first kind trigger condition includes at least one following condition:
Under wake-up states, it is continuously detected the facial image of target object but does not receive target object in preset duration
Input request;
Continuously receiving target object indicates that the quantity of the input request of same or similar intention is more than preset quantity;
It is more than that the response for continuously indicating target object the input request of same or similar intention, which is the number of mistake,
One preset times;
The number that the intention of the input request of target object can not continuously be parsed is more than the second preset times;
It cannot respond to the input request of target object;
The number for being consecutively detected the input information errors of target object is more than third preset times.
Optionally, the second class trigger condition includes: and receives target object to indicate that the input for needing artificial customer service to be intended to is asked
It asks.
Further, control module 402 is specifically used for: control smart machine is by way of floating tag and/or voice
The mode of casting exports prompt information.
Further, the smart machine control device 40 of the present embodiment further includes face recognition module, for controlling intelligence
Equipment acquires the face information of target object, carries out recognition of face according to face information to determine the corresponding user's letter of target object
Breath, and it is sent to artificial customer side.
Further, the smart machine control device 40 of the present embodiment further includes condition update module, for updating first
Class trigger condition and/or the second class trigger condition.
Further, condition update module be specifically used for counting triggering times that each first kind trigger condition is triggered and
First kind trigger condition connects the connection number of artificial customer side after being triggered, calculate triggering times and connect turn between number
Ratio is changed, according to the corresponding conversion ratio of first kind trigger condition, updates first kind trigger condition;And/or statistics each first
The triggering frequency that class trigger condition is triggered updates the first kind and triggers item according to the corresponding triggering frequency of first kind trigger condition
Part.
Further, condition update module is specifically used for counting the triggering frequency that each second class trigger condition is triggered,
According to the corresponding triggering frequency of the second class trigger condition, the second class trigger condition is updated.
Further, input request includes but is not limited to following at least one mode: touch control operation, voice messaging and limbs
Movement etc..
Further, control module 402 is specifically used for: control smart machine is in such a way that video connects or voice connects
Connect artificial customer side.
The smart machine control device 40 that the embodiment of the present invention mentions uses identical with above-mentioned smart machine control method
Inventive concept can obtain identical beneficial effect, and details are not described herein.
Based on inventive concept identical with above-mentioned smart machine control method, the embodiment of the invention also provides a kind of electronics
Equipment, as shown in figure 5, the electronic equipment 50 may include processor 501, memory 502 and transceiver 503.Transceiver 503 is used
Data are sended and received under the control in processor 501.
Memory 502 may include read-only memory (ROM) and random access memory (RAM), and provide to processor
The program instruction and data stored in memory.In embodiments of the present invention, memory can be used for storing smart machine control
The program of method.
Processor 501 can be CPU (centre buries device), ASIC (Application Specific Integrated
Circuit, specific integrated circuit), FPGA (Field-Programmable Gate Array, field programmable gate array) or
CPLD (Complex Programmable Logic Device, Complex Programmable Logic Devices) processor is by calling storage
The program instruction of device storage, the smart machine control method in any of the above-described embodiment is realized according to the program instruction of acquisition.
The embodiment of the invention provides a kind of computer readable storage mediums, for being stored as above-mentioned electronic equipments
Computer program instructions, it includes the programs for executing above-mentioned smart machine control method.
Above-mentioned computer storage medium can be any usable medium or data storage device that computer can access, packet
Include but be not limited to magnetic storage (such as floppy disk, hard disk, tape, magneto-optic disk (MO) etc.), optical memory (such as CD, DVD,
BD, HVD etc.) and semiconductor memory (such as it is ROM, EPROM, EEPROM, nonvolatile memory (NAND FLASH), solid
State hard disk (SSD)) etc..
The above, above embodiments are only described in detail to the technical solution to the application, but the above implementation
The method that the explanation of example is merely used to help understand the embodiment of the present invention, should not be construed as the limitation to the embodiment of the present invention.This
Any changes or substitutions that can be easily thought of by those skilled in the art, should all cover the embodiment of the present invention protection scope it
It is interior.
Claims (10)
1. a kind of smart machine control method characterized by comprising
Determination meets preset artificial customer service trigger condition;
If the trigger condition met belongs to first kind trigger condition, the smart machine output prompt information is controlled, with prompt
Artificial customer side whether is connected, after receiving confirmation feedback, the smart machine is controlled and connects artificial customer side;
If the trigger condition met belongs to the second class trigger condition, controls the smart machine and connect artificial customer side.
2. the method according to claim 1, wherein the first kind trigger condition include it is following at least one
Part:
Under wake-up states, it is continuously detected the facial image of target object but does not receive the target object in preset duration
Input request;
Continuously receiving target object indicates that the quantity of the input request of same or similar intention is more than preset quantity;
It is more than first pre- that the response for continuously indicating target object the input request of same or similar intention, which is wrong number,
If number;
The number that the intention of the input request of target object can not continuously be parsed is more than the second preset times;
It cannot respond to the input request of target object;
The number for being consecutively detected the input information errors of target object is more than third preset times.
3. the method according to claim 1, wherein the second class trigger condition includes: to receive target pair
As the input request for indicating that artificial customer service is needed to be intended to.
4. the method according to claim 1, wherein the control smart machine exports prompt information, packet
It includes:
The smart machine is controlled by way of floating tag and/or the mode of voice broadcast exports prompt information.
5. the method according to claim 1, wherein control after the smart machine connects artificial customer side,
Further include:
Control the face information of the smart machine acquisition target object;
Recognition of face is carried out with the corresponding user information of the determination target object according to the face information, and is sent to artificial
Customer side.
6. method according to any one of claims 1 to 5, which is characterized in that further include: update the first kind trigger condition
And/or the second class trigger condition.
7. according to the method described in claim 6, it is characterized in that, described update the first kind trigger condition, comprising:
Count triggering times that each first kind trigger condition is triggered and the first kind trigger condition be triggered after connect people
The connection number of work customer side calculates the conversion ratio between the triggering times and the connection number, is touched according to the first kind
The corresponding conversion ratio of clockwork spring part updates the first kind trigger condition;And/or it counts each first kind trigger condition and is touched
The triggering frequency of hair updates the first kind trigger condition according to the corresponding triggering frequency of the first kind trigger condition.
8. according to the method described in claim 6, it is characterized in that, described update the second class trigger condition, comprising:
The triggering frequency that each second class trigger condition is triggered is counted, according to the corresponding triggering frequency of the second class trigger condition
Rate updates the second class trigger condition.
9. according to the method in claim 2 or 3, which is characterized in that the input request comprises at least one of the following mode:
Touch control operation, voice messaging and limb action.
10. method according to any one of claims 1 to 5, which is characterized in that the control smart machine connection is artificial
Customer side specifically includes:
It controls the smart machine and connects artificial customer side by way of video connection or voice connection.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811472043.4A CN109685550A (en) | 2018-12-04 | 2018-12-04 | Smart machine control method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811472043.4A CN109685550A (en) | 2018-12-04 | 2018-12-04 | Smart machine control method, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109685550A true CN109685550A (en) | 2019-04-26 |
Family
ID=66186606
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811472043.4A Pending CN109685550A (en) | 2018-12-04 | 2018-12-04 | Smart machine control method, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109685550A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113726964A (en) * | 2021-09-03 | 2021-11-30 | 中国银行股份有限公司 | Outbound processing method and device, storage medium and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105306281A (en) * | 2015-12-03 | 2016-02-03 | 腾讯科技(深圳)有限公司 | Information processing method and client |
CN107122824A (en) * | 2017-05-04 | 2017-09-01 | 中兴耀维科技江苏有限公司 | A kind of method that enterprise's exhibition room is explained online |
CN107590159A (en) * | 2016-07-08 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
CN105592237B (en) * | 2014-10-24 | 2019-02-05 | ***通信集团公司 | A kind of method, apparatus and intelligent customer service robot of session switching |
-
2018
- 2018-12-04 CN CN201811472043.4A patent/CN109685550A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105592237B (en) * | 2014-10-24 | 2019-02-05 | ***通信集团公司 | A kind of method, apparatus and intelligent customer service robot of session switching |
CN105306281A (en) * | 2015-12-03 | 2016-02-03 | 腾讯科技(深圳)有限公司 | Information processing method and client |
CN107590159A (en) * | 2016-07-08 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
CN107122824A (en) * | 2017-05-04 | 2017-09-01 | 中兴耀维科技江苏有限公司 | A kind of method that enterprise's exhibition room is explained online |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113726964A (en) * | 2021-09-03 | 2021-11-30 | 中国银行股份有限公司 | Outbound processing method and device, storage medium and electronic equipment |
CN113726964B (en) * | 2021-09-03 | 2023-06-30 | 中国银行股份有限公司 | Outbound processing method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3617946B1 (en) | Context acquisition method and device based on voice interaction | |
CN112380981B (en) | Face key point detection method and device, storage medium and electronic equipment | |
CN109086276B (en) | Data translation method, device, terminal and storage medium | |
CN103686274A (en) | Android smart television remote controller with fingerprint identification function and remote control processing method of remote controller | |
CN108074571A (en) | Sound control method, system and the storage medium of augmented reality equipment | |
CN115438214B (en) | Method and device for processing text image and training method of neural network | |
CN108897517B (en) | Information processing method and electronic equipment | |
CN108805035A (en) | Interactive teaching and learning method based on gesture identification and device | |
CN115422389A (en) | Method for processing text image, neural network and training method thereof | |
CN110673723A (en) | Speech interaction method, system, medium, and apparatus based on biometric features | |
CN114648796A (en) | User identification method, device, storage medium and electronic equipment | |
CN110428816B (en) | Method and device for training and sharing voice cell bank | |
WO2024140978A1 (en) | Cursor display method and related device | |
CN114495103B (en) | Text recognition method and device, electronic equipment and medium | |
CN111368721A (en) | Identity recognition processing method and device, electronic equipment and storage medium | |
CN111611365A (en) | Flow control method, device, equipment and storage medium of dialog system | |
CN109685550A (en) | Smart machine control method, device, electronic equipment and storage medium | |
CN114360554A (en) | Vehicle remote control method, device, equipment and storage medium | |
CN113835570A (en) | Method, device, apparatus, storage medium, and program for controlling display screen in vehicle | |
CN113553568B (en) | Man-machine identification method, slide block verification device, medium and equipment | |
CN113342170A (en) | Gesture control method, device, terminal and storage medium | |
CN112581664A (en) | Control method and device based on intelligent identification, electronic equipment and storage medium | |
CN115909505A (en) | Control method and device of sign language recognition equipment, storage medium and electronic equipment | |
CN113596011B (en) | Flow identification method and device, computing device and medium | |
CN115421590A (en) | Gesture control method, storage medium and camera device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |
|
RJ01 | Rejection of invention patent application after publication |