CN109783625A - Exchange method and calculating equipment - Google Patents
Exchange method and calculating equipment Download PDFInfo
- Publication number
- CN109783625A CN109783625A CN201811641649.6A CN201811641649A CN109783625A CN 109783625 A CN109783625 A CN 109783625A CN 201811641649 A CN201811641649 A CN 201811641649A CN 109783625 A CN109783625 A CN 109783625A
- Authority
- CN
- China
- Prior art keywords
- information
- intention
- intent
- user
- intended
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
Present disclose provides a kind of exchange methods, are applied in intelligent conversational system, and the intelligence conversational system can input information to the user received and respond and provide feedback information, this method comprises: obtaining user inputs information;N number of intent information that the user inputs information representation is extracted and exports, the N is the positive integer greater than 1;It responds the user and inputs information, generate and export M feedback information, the M is the positive integer greater than 1 and less than or equal to N, and the M feedback information corresponds to preceding M intent information in N number of intent information.The disclosure additionally provides a kind of calculating equipment.
Description
Technical field
This disclosure relates to a kind of exchange method and calculating equipment.
Background technique
In intelligent customer service, after natural language understanding system carries out semantic understanding to user's input content, it can generate
The semantic understanding of one various dimensions is as a result, the prior art can be interacted based on the semantic understanding result with user's expansion.
It is interacted however, the prior art usually only chooses a semantic understanding result, that is, exports one and be directed to the semanteme
Understand the answer of result, this is unable to satisfy in different application scene and inputs the need that information needs to provide different answers for user
It asks.
Summary of the invention
An aspect of this disclosure provide one kind be able to satisfy in different application scene for user input information need to
The exchange method of different answers out, the exchange method are applied in intelligent conversational system, and the intelligence conversational system can dock
The user received inputs information and responds and provide feedback information, and the method may include following operations, uses firstly, obtaining
Family inputs information, then, extracts and export N number of intent information that the user inputs information representation, the N is just greater than 1
Integer then responds the user and inputs information, generates and export M feedback information, and the M is greater than 1 and to be less than or equal to N
Positive integer, the M feedback information correspond to N number of intent information in preceding M intent information.It can be parsed out so more
A intention is simultaneously shown to user, and provides the corresponding answer of intention of sequence top M, is directed to meeting in different application scene
User inputs the demand that information needs to provide different answers.
Optionally, described to generate and export M feedback information, the M is the positive integer greater than 1 and less than or equal to N, described
It may include operating as follows that M feedback information, which corresponds to preceding M intent information in N number of intent information: if N number of meaning
Figure information is not excluded from, then responds the user and input information, generate and export M feedback information, the M feedback information pair
The preceding M intent informations being not excluded from N number of intent information described in Ying Yu, alternatively, if there is phase in N number of intent information
The intent information of repulsion, then the X intent informations being not excluded from, respond the user before choosing from N number of intent information
Information is inputted, M feedback information is generated and export, the M feedback information corresponds in the preceding X intent information preceding M
The intent information being not excluded from, wherein the M≤X≤N, and be positive integer, mutual lance can be provided to avoid intelligent customer service in this way
The answer of shield.
Optionally, the N number of intent information extracted and export user's input information representation may include grasping as follows
Make: firstly, inputting information to the user carries out semantic understanding, first intention information is obtained, then, according to the first intention
Information determines that associated second intention information, the second intention information include the meaning modifying the first intention information and obtaining
Figure information.The answer provided due to intelligent customer service is usually generally applicable in application scenarios, be such as suitable for vast majority of people and
The answer of situation, still, in actual use, the service object of intelligent customer service usually has some self attributes or by emergency event
Influence etc., cause this to be generally applicable in the answer being applicable in application scenarios and be not suitable in above-mentioned special screne, such as by region, event
Or emergency event influence etc., it needs to adjust the answer that intelligent customer service provides, but trains the mould of a semantic understanding thus again
The time cost and resources costs of type are all very high, and the present embodiment passes through after obtaining the intention being generally applicable in application scenarios
Analysis determines that at least one associated second intention, the second intention can be adapted at least one above-mentioned special screne,
Therefore, can meet well in different application scene and need the needs of providing different answers for user's input information, and not
The answer of incoherent intention can be provided.
Optionally, described to determine that associated second intention information may include grasping as follows according to the first intention information
Make: firstly, according to being intended to be intended to variable with the corresponding relationship and the first intention acquisition of information for being intended to variable, wherein one
It is intended to the trigger condition that variable corresponds at least one modification intent information, then, if the triggering item that at least one modification is intended to
Part is triggered, then modifies intent information, obtains second intention information, wherein the first intention information and the second intention
Information is mutually repelled or is not excluded from.It in this way can be based on the trigger condition for being intended to the corresponding relationship for being intended to variable and being intended to variable
Modification is determined the need for be intended to.
Optionally, the intention variable includes any of the following or a variety of: position, time, space, user property, use
Family device attribute or event.Such as when the service object of intelligent customer service is in the region that Mobile phone is not publicly sold, and receive
When the purchase consulting of the service object, then purchase link will not be sent to the service object.
Optionally, at least partly intent information may include and the first intention information phase in the second intention information
Anti- intent information, alternatively, in the second intention information at least partly intent information include with the first intention information not
The intent information of same type.
Optionally, the intention can construct in the following manner with the corresponding relationship for being intended to variable: firstly, obtaining alternative
Intent information, the alternative intent information are there is a possibility that the intent information of modification, then, obtain the alternative intent information
The corresponding trigger condition for being intended to variable and modifying intent information, then, according to the alternative intent information, the alternative intention
The trigger condition of the corresponding intention variable of information and the modification intent information determines the intention and the corresponding pass for being intended to variable
System.
Optionally, the intention can also construct in the following manner with the corresponding relationship for being intended to variable: firstly, defining one
Then a situation, the corresponding at least one intent information of the situation from the information obtained under the situation in history log, connect
, the variable for influencing the corresponding intent information of the situation is obtained from the information under the situation.
Optionally, the intention can be described with the corresponding relationship for being intended to variable by the main external key mode in database.
Another aspect of the disclosure provides a kind of interactive device, comprising: data obtaining module, be intended to obtain module and
Output module, wherein the data obtaining module inputs information for obtaining user, and the intention obtains module for extracting simultaneously
N number of intent information that the user inputs information representation is exported, the N is the positive integer greater than 1, and the output module is for ringing
It answers the user to input information, generates and export M feedback information, the M is the positive integer greater than 1 and less than or equal to N, described
M feedback information corresponds to preceding M intent information in N number of intent information.
Optionally, if the intention obtains module and is not excluded from specifically for N number of intent information, described in response
User inputs information, generates and export M feedback information, and the M feedback information corresponds to preceding M in N number of intent information
A intent information being not excluded from, alternatively, if there is the intent information mutually repelled, from the N in N number of intent information
It is a anti-that the preceding X intent informations being not excluded from are chosen in a intent information, the user is responded and inputs information, generate and export M
Feedforward information, the M feedback information correspond to the preceding M intent informations being not excluded from the preceding X intent information, wherein
M≤the X≤N, and be positive integer.
Optionally, it may include acquiring unit and modification unit that the intention, which obtains module, wherein the acquiring unit is used
Semantic understanding is carried out in inputting information to the user, obtains first intention information, the modification unit is for according to described the
One intent information determines that associated second intention information, the second intention information include modifying the first intention information to obtain
The intent information arrived.
Optionally, the modification unit includes Relation acquisition subelement and modification subelement, wherein Relation acquisition
Unit is used to be intended to variable according to the corresponding relationship and the first intention acquisition of information that are intended to and are intended to variable, wherein one
It is intended to the trigger condition that variable corresponds at least one modification intent information, if the modification subelement is at least one modification
The trigger condition of intention is triggered, then modifies intent information, obtains second intention information, wherein the first intention information and
The second intention information is mutually repelled or is not excluded from.
Another aspect of the disclosure provides a kind of calculating equipment, including one or more processors and computer
Readable storage medium storing program for executing, wherein the computer readable storage medium is for storing one or more computer programs, the calculating
Machine program realizes method as described above when being executed by the processor.
Another aspect of the present disclosure provides a kind of computer readable storage medium, is stored with computer executable instructions,
Described instruction is when executed for realizing method as described above.
Another aspect of the present disclosure provides a kind of computer program, and the computer program, which includes that computer is executable, to be referred to
It enables, described instruction is when executed for realizing method as described above.
Detailed description of the invention
In order to which the disclosure and its advantage is more fully understood, referring now to being described below in conjunction with attached drawing, in which:
Figure 1A diagrammatically illustrates the exchange method according to the embodiment of the present disclosure and calculates the application scenarios of equipment;
Figure 1B diagrammatically illustrates the computer system architecture suitable for exchange method according to the embodiment of the present disclosure;
Fig. 2 diagrammatically illustrates the flow chart of the exchange method according to the embodiment of the present disclosure;
Fig. 3 A diagrammatically illustrates the schematic diagram of the interactive interface according to the embodiment of the present disclosure;
Fig. 3 B diagrammatically illustrates the schematic diagram being intended to according to the modification of the embodiment of the present disclosure;
Fig. 3 C diagrammatically illustrates the flow chart of the method for the determination second intention information according to the embodiment of the present disclosure;
Fig. 3 D diagrammatically illustrates the intention and the schematic diagram for the corresponding relationship for being intended to variable according to the embodiment of the present disclosure;
Fig. 4 diagrammatically illustrates the block diagram of the interactive device according to the embodiment of the present disclosure;And
Fig. 5 diagrammatically illustrates the block diagram of the calculating equipment according to the embodiment of the present disclosure.
Specific embodiment
Hereinafter, will be described with reference to the accompanying drawings embodiment of the disclosure.However, it should be understood that these descriptions are only exemplary
, and it is not intended to limit the scope of the present disclosure.In the following detailed description, to elaborate many specific thin convenient for explaining
Section is to provide the comprehensive understanding to the embodiment of the present disclosure.It may be evident, however, that one or more embodiments are not having these specific thin
It can also be carried out in the case where section.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid
Unnecessarily obscure the concept of the disclosure.
Term as used herein is not intended to limit the disclosure just for the sake of description specific embodiment.It uses herein
The terms "include", "comprise" etc. show the presence of the feature, step, operation and/or component, but it is not excluded that in the presence of
Or add other one or more features, step, operation or component.
There are all terms (including technical and scientific term) as used herein those skilled in the art to be generally understood
Meaning, unless otherwise defined.It should be noted that term used herein should be interpreted that with consistent with the context of this specification
Meaning, without that should be explained with idealization or excessively mechanical mode.
It, in general should be according to this using statement as " at least one in A, B and C etc. " is similar to
Field technical staff is generally understood the meaning of the statement to make an explanation (for example, " system at least one in A, B and C "
Should include but is not limited to individually with A, individually with B, individually with C, with A and B, with A and C, have B and C, and/or
System etc. with A, B, C).Using statement as " at least one in A, B or C etc. " is similar to, generally come
Saying be generally understood the meaning of the statement according to those skilled in the art to make an explanation (for example, " having in A, B or C at least
One system " should include but is not limited to individually with A, individually with B, individually with C, with A and B, have A and C, have
B and C, and/or the system with A, B, C etc.).
Shown in the drawings of some block diagrams and/or flow chart.It should be understood that some sides in block diagram and/or flow chart
Frame or combinations thereof can be realized by computer program instructions.These computer program instructions can be supplied to general purpose computer,
The processor of special purpose computer or other programmable data processing units, so that these instructions are when executed by this processor can be with
Creation is for realizing function/operation device illustrated in these block diagrams and/or flow chart.The technology of the disclosure can be hard
The form of part and/or software (including firmware, microcode etc.) is realized.In addition, the technology of the disclosure, which can be taken, is stored with finger
The form of computer program product on the computer readable storage medium of order, the computer program product is for instruction execution system
System uses or instruction execution system is combined to use.
Figure 1A diagrammatically illustrates the exchange method according to the embodiment of the present disclosure and calculates the application scenarios of equipment.It needs to infuse
Meaning, being only shown in Figure 1A can be using the example of the scene of the embodiment of the present disclosure, to help skilled in the art to understand
The technology contents of the disclosure, but it is not meant to that the embodiment of the present disclosure may not be usable for other equipment, system, environment or scene.
Existing intelligent customer service is all based on the result of natural language understanding to interact, still, if session management
It is gone if inquiring related content only according to the result of natural language understanding, the result checked out in this way can be led to the problem of.For example,
For buying mobile phone, it is that can not push purchase if inquiry purchase that Mobile phone, which is to need to hold in close confidence before public offering,
Buyer's formula and link, but after public offering, just not maintain secrecy.In another example Mobile phone is undisclosed in some region
Before sales, and cannot be to the pushes customer buying pattern and connection in the region, and the region of public offering can be it
Push buying pattern and connection.It is current to realize if the work of this part is all allowed natural language understanding system come if completing
Mode is constructed based on current application scene with training pattern to determine whether push associated answer, but the instruction of model
Practice and mark training data can all take much time, i.e., time cost is very high, is not able to satisfy requirement online at any time.
As shown in the upper figure of Figure 1A, the user positioned at certain region inquires whether intelligent customer service can buy Motorola
(MOTO) mobile phone Z3, and the model mobile phone is not publicly sold in the region, it is thus impossible to buying pattern and link are pushed for it,
But intelligent customer service to user input information carry out natural language understanding after obtain be intended that purchase mobile phone, at this point, existing
The intelligent customer service of technology can push buying pattern and link to the user, and this does not allow.Further, since selling state etc.
In addition to other than by regional effect, there is also various factors, therefore, it is impossible to timely provide a variety of natural languages for intelligent customer service
Model is understood to adapt to various application scenarios, and higher cost.
As shown in the following figure of Figure 1A, embodiment of the disclosure can be pushed more according to different application scenarios etc. to user
Accurate answer.Whether the customer inquiries intelligent customer service as being located at certain region can buy Motolora mobilephone Z3, and the model
Mobile phone is not publicly sold in the region, it is thus impossible to buying pattern and link be pushed for it, although at this point, intelligent customer service is based on
What is obtained after natural language understanding is intended that purchase mobile phone, and still, intelligent customer service is determining that region locating for the user is undisclosed
When selling, modification can be intended to automatically, and provide answer according to modified intention: Motorola Z3 mobile phone is not also in XXXX at present
Sale, and indirect push buying pattern and link.
Embodiment of the disclosure provides a kind of exchange method and calculates equipment.This method includes intention assessment process and answers
Multiple process.In being intended to identification process, parses multiple intentions and export multiple intentions.After completing intention assessment process,
Into the process of answer, targetedly answer is provided based on the multiple intentions of one in multiple intentions.
Figure 1B diagrammatically illustrates the computer system architecture suitable for exchange method according to the embodiment of the present disclosure.It needs
Illustrate, being only shown in Figure 1B can be using the example of the system architecture of the embodiment of the present disclosure, to help those skilled in the art
Member understands the technology contents of the disclosure, should not be understood as the restriction to the disclosure.
As shown in Figure 1B, system architecture 100 may include terminal device 101,102,103, network according to this embodiment
104 and server 105.Network 104 between terminal device 101,102,103 and server 105 to provide communication link
Medium.Network 104 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
It delivers letters breath etc..Various telecommunication customer end applications can be installed, such as web browser is answered on terminal device 101,102,103
With (merely illustrative) such as, searching class application, instant messaging tools, mailbox client, social platform softwares.
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee, desktop computer, virtual reality device or Google's eye
Mirror etc..
Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user
The consulting of progress provides the background server (merely illustrative) intelligently replied.Background server can seek advice from the user received
Etc. information analyze etc. processing, and by processing result (such as answer, information or data generated according to user's consultation information
Deng) feed back to terminal device.
It should be noted that exchange method provided by the embodiment of the present disclosure can generally be executed by server 105.Accordingly
Ground, interactive device provided by the embodiment of the present disclosure generally can be set in server 105.Provided by the embodiment of the present disclosure
Exchange method can also be by being different from server 105 and can communicate with terminal device 101,102,103 and/or server 105
Server or server cluster execute.Correspondingly, interactive device provided by the embodiment of the present disclosure also can be set in difference
In server 105 and the server or server cluster that can be communicated with terminal device 101,102,103 and/or server 105
In.
It should be understood that the number of terminal device, network and server in Figure 1B is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Fig. 2 diagrammatically illustrates the flow chart of exchange method according to an embodiment of the present disclosure.
As shown in Fig. 2, this method may include operation S201~S203.
In operation S201, obtains user and input information.
Specifically, it can be in intelligent conversational system, such as the information inputted in intelligent customer service, Ke Yiwei that user, which inputs information,
Various types of information.
In operation S202, N number of intent information that the user inputs information representation is extracted and exports, the N is greater than 1
Positive integer, such as 2,3,4,8.Wherein, N number of intent information, which can be, inputs multiple original meanings that information extracts based on user
Figure can also include the one or more intentions obtained after being modified based on original intent.For example, original intent is purchase hand
Machine, but the mobile phone is offered for sale in user region not yet, therefore, purchase mobile phone can be revised as not buy mobile phone
Or mobile phone upgrading etc. is intended to.It should be noted that the N number of intent information for exporting user's input information representation can be output
To user, intelligent customer service support team or another judge whether to need to change the system etc. being intended to.
Fig. 3 A diagrammatically illustrates the schematic diagram of the interactive interface according to the embodiment of the present disclosure.
As shown in Figure 3A, in one embodiment, it is parsed to obtain multiple intent informations when to user's input information,
And when the true intention of uncertain user, multiple intent informations can be sent to user and be determined.For example, user inputs letter
Breath are as follows: I wants to buy Z3, accordingly extract a variety of possible intentions: buying mobile phone, purchase laptop ... etc..At this point, can
To send and show user for the multiple intentions extracted, so that user provides accurate intention, further, it is also possible to give user
The corresponding answer of intention of sequence top M is provided.
In another embodiment, multiple intentions of output can be directly output to for generating feedback letter based on intention
The system of breath can thus respectively obtain the corresponding feedback information of multiple intentions.It should be noted that is obtained in this way is multiple
There may be mutually exclusive feedback informations in feedback information, this is because one or more of multiple intentions may be modification
Therefore intention afterwards can further screen feedback information.
In a specific embodiment, the N number of intent information extracted and export user's input information representation can
To include operating as follows.
Firstly, inputting information to the user carries out semantic understanding, first intention information is obtained.The operation can be compared with
Technology.
Then, associated second intention information, the second intention packet are determined according to the first intention information
It includes and modifies the intent information that the first intention information obtains.
Specifically, at least partly intent information includes opposite with the first intention information in the second intention information
Intent information, alternatively, at least partly intent information includes and the first intention information inhomogeneity in the second intention information
The intent information of type.
Fig. 3 B diagrammatically illustrates the schematic diagram being intended to according to the modification of the embodiment of the present disclosure.
As shown in Figure 3B, intent information can be revised as opposite intent information or not according to current application scenarios
The intent information of same type.
For example, the associated second intention can be the intention opposite with first intention, it will such as buy mobile phone and be revised as
Mobile phone is not bought, there is presently no public offerings for the mobile phone of user's consulting, although there is sale to connect in system, cannot push
To user, the intention for buying mobile phone can be revised as not buy mobile phone at this time.
In addition, the second intention information is also likely to be the intent information different classes of with first intention, for example, first intention
Information includes purchase mobile phone, and second intention information includes upgrading mobile phone, repairing mobile phone etc..
It is broken for example, user inputs the mobile phone that information includes: for I, wants to buy newest Motolora mobilephone Z3, at this point, by
It is offered for sale not yet in Z3, therefore sale link cannot be pushed to user, but user inputs in information and further comprises mobile phone
Therefore the information being broken can will repair mobile phone and reply as intention.
To want to buy ViVo Z3 mobile phone for me in another example user inputs information, active user region, which has disclosed, sells,
Therefore, it is intended to be purchase mobile phone, but is influenced by emergency event, the natural calamity that such as happens suddenly recalls, limits and purchase thing
Part occurs, and the current slot of emergency event cannot sell the mobile phone, then can be revised as not buying by the intention for buying mobile phone
Mobile phone.
In operation S203, respond the user and input information, generate and export M feedback information, the M for greater than 1 and
Positive integer less than or equal to N, the M feedback information correspond to preceding M intent information in N number of intent information.
It wherein, can be compared with technology based on the process for being intended to determining feedback information.Multiple feedback informations of output can be with
User all is fed back to, can also only feed back partial feedback information therein, for example, when there is mutually punching in multiple feedback informations
It, can only feedback wherein not conflicting information when prominent information.It should be noted that the user inputs information in addition to including
The text information etc. of user's input can also include the personal attribute information etc. of user, as current time, current geographic position,
Current device model, languages etc., these information aid in determining whether feedback information.
For example, described generate and export M feedback information, the M is the positive integer greater than 1 and less than or equal to N, the M
It may include the following two kinds situation that a feedback information, which corresponds to preceding M intent information in N number of intent information,.
If N number of intent information is not excluded from, responds the user and input information, generate and export M feedback
Information, the M feedback information correspond to the preceding M intent informations being not excluded from N number of intent information.
If having the intent information mutually repelled in N number of intent information, before being chosen in N number of intent information
The X intent informations being not excluded from respond the user and input information, generate and export M feedback information, the M feedback
Information corresponds to the preceding M intent informations being not excluded from the preceding X intent information, wherein the M≤X≤N, and be positive
Integer.It should be noted that M information of output might not will be sent to user, one only can be sent to user terminal
Feedback information is as answer, such as a feedback information of highest scoring.
The model of the same natural language analysis can be used in embodiment of the disclosure, for use in different application scene
Family input information needs to provide different intentions, and then provides correct feedback information according to different intentions.
A kind of embodiment that modification is intended to is given in detail below.
Fig. 3 C diagrammatically illustrates the flow chart of the method for the determination second intention information according to the embodiment of the present disclosure.
As shown in Figure 3 C, described to determine that associated second intention information may include behaviour according to the first intention information
Make S301~operation S302.
In operation S301, it is intended to become according to the corresponding relationship and the first intention acquisition of information that are intended to and are intended to variable
Amount, wherein one is intended to the trigger condition that variable corresponds at least one modification intent information.
In operation S302, if the trigger condition that at least one modification is intended to is triggered, intent information is modified, is obtained
Second intention information, wherein the first intention information is mutually repelled or is not excluded from the second intention information.
In the present embodiment, the intention variable may include it is following any one or more: position, time, space, use
Family attribute, user equipment attribute or event.For example, when current location region is unsatisfactory for first intention information corresponding condition
Triggering modification is intended to, and triggering modification is intended to when current time is unsatisfactory for first intention information corresponding condition, and current spatial is (as high
Degree, environment influence etc.) when being unsatisfactory for first intention information corresponding condition triggering modification be intended to, active user's attribute (such as age,
Gender, VIP grade, grade ... etc.) when being unsatisfactory for first intention information corresponding condition triggering modification be intended to, emergency event is (such as
Irresistible natural calamity, political event, short-term recall event etc.) it is unsatisfactory for triggering when first intention information corresponding condition
Modification is intended to.
Fig. 3 D diagrammatically illustrates the intention and the schematic diagram for the corresponding relationship for being intended to variable according to the embodiment of the present disclosure.
As shown in Figure 3D, corresponding relationship includes but is not limited to: sequential relationship: the relationship between time and intention.It closes position
System: the relationship between place and intention.Spatial relationship: the relationship between space and intention.Temporary undefined relationship: its dependent variable and
There are no the relationships excavated between intention.
In one embodiment, the intention can carry out structure with the corresponding relationship for being intended to variable in the following manner
It builds.
Firstly, obtaining alternative intent information, the alternative intent information is there is a possibility that the intent information of modification.Example
Such as, the multiple intent informations being collected into can be analyzed, judges which intent information may be in different application scenarios
It is lower to need to provide different feedback informations.
Then, the corresponding trigger condition for being intended to variable and modifying intent information of the alternative intent information is obtained.For example,
It can be analyzed according to the experience of business expert or according to operation flow etc. and be intended to variable and its trigger condition.
Then, it is anticipated according to the alternative intent information, the alternative corresponding intention variable of intent information and the modification
The trigger condition of figure information determines the corresponding relationship of the intention with intention variable.
In another embodiment, the intention can carry out structure with the corresponding relationship for being intended to variable in the following manner
It builds.
Firstly, a situation is defined, the corresponding at least one intent information of the situation.For example, different geographical, different time
The situation that the lower intention for needing to obtain natural language analysis is modified, the intention as described above for needing to modify purchase mobile phone
The situation of information.
Then, it from the information obtained in history log under the situation, can be obtained from the dialog history of multiple users
Relevant information in the case of definition.
Then, the variable for influencing the corresponding intent information of the situation is obtained from the information under the situation.It can pass through
Analysis expert can also obtain influencing the variable of the corresponding intent information of the situation by modes such as big data excavations.
Wherein, the intention is described with the corresponding relationship for being intended to variable by the main external key mode in database.For example, making
Stored with relevant database, specifically, by be intended to intention variable corresponding relationship in intention and variable regard as
A table in database will be intended to variable relation and be stored by relevant database, so correlativity calculating is logical
Inquiry database mode is crossed to obtain.For example, the time is the variable of buying intention, determine whether intention is purchase by query time
It buys.
In a specific embodiment, it is illustrated for being intended to the relationship with the time." Wish i knew rubs user's input
Toro draws whether Z3 sells " after this problem, natural language understanding system is after understanding and coming out result " purchase mobile phone ".Meeting
Session management can inquire " purchase mobile phone ", and this is intended to relationship between one group of variable, these variables include the time, place,
Space etc. (including but not limited to these, may be there are also other variables, it is only for examples) variable.System can inquire " purchase
It is related between this intention of mobile phone " and which variable.In the variable checked out, successively " purchase mobile phone " can be anticipated
Figure and variable are matched in figure and the corresponding relationship for being intended to variable.
If it find that " purchase mobile phone " is intended to and has relationship with the time, relationship is that sequential relationship (is such as determined by business expert
What justice came out).It so needs to judge whether this mobile phone meets in time this when and has disclosed sale.If without public affairs
If expense is sold, then it is intended to " purchase mobile phone " to change into " mobile phone cannot be bought " intention, then releases related feedback information, such as
Talk about art etc..
In another specific embodiment, it is illustrated for being intended to the relationship with position.
User inputs after " Wish i knew, and whether Motorola Z3 sells " this problem, and natural language understanding system understands
It is intended to " purchase mobile phone " out.Conversation management system can inquire " purchase mobile phone ", and this is intended to the relationship between one group of variable.
Be intended to and there is relationship in place when inquiring " purchase mobile phone ", relationship is positional relationship, need to judge at this time this mobile phone with
Family is currently located whether region has disclosed sale.If without public offering, " purchase mobile phone " being intended to change into
" cannot buy mobile phone " is intended to, and then releases related words art.
The disclosure provide method in intelligent customer service, consider variable cause usually decide whether modification natural language understanding
Intention out, it is thereby achieved that dynamic modification natural language understanding is as a result, keep its fast and easy online, meet demand.
Fig. 4 diagrammatically illustrates the block diagram of the interactive device according to the embodiment of the present disclosure.
As shown in figure 4, the device 400 may include data obtaining module 410, be intended to obtain module 420 and output module
430。
Wherein, the data obtaining module 410 inputs information for obtaining user, and the intention obtains module 420 and is used for
N number of intent information that the user inputs information representation is extracted and exports, the N is the positive integer greater than 1, the output module
430 input information for responding the user, generate and export M feedback information, and the M is greater than 1 and to be less than or equal to N just
Integer, the M feedback information correspond to preceding M intent information in N number of intent information.
In one embodiment, if the intention obtains module 420 and can be specifically used for N number of intent information not
Mutually repel, then respond the user and input information, generate and export M feedback information, the M feedback information corresponds to described
The preceding M intent informations being not excluded from N number of intent information, alternatively, if there is the meaning mutually repelled in N number of intent information
Figure information, then the X intent informations being not excluded from before choosing from N number of intent information respond the user and input information,
M feedback information is generated and exports, what the M feedback information was not excluded from corresponding to preceding M in the preceding X intent information
Intent information, wherein the M≤X≤N, and be positive integer.
Specifically, it may include acquiring unit and modification unit that the intention, which obtains module 420,.
Wherein, the acquiring unit, which is used to input information to the user, carries out semantic understanding, obtains first intention information.
The modification unit is used to determine associated second intention information, the second intention information according to the first intention information
The intent information obtained including modifying the first intention information.
Optionally, the modification unit may include Relation acquisition subelement and modification subelement, wherein the relationship obtains
Take subelement for being intended to variable according to the corresponding relationship and the first intention acquisition of information that are intended to and are intended to variable, wherein
One is intended to the trigger condition that variable corresponds at least one modification intent information, if the modification subelement is used at least one
The trigger condition that modification is intended to is triggered, then modifies intent information, obtain second intention information, wherein the first intention letter
Breath mutually repels or is not excluded from the second intention information.
In accordance with an embodiment of the present disclosure, the operating process of device 400 may refer to above description, be not repeated herein.
It is module according to an embodiment of the present disclosure, submodule, unit, any number of or in which any more in subelement
A at least partly function can be realized in a module.It is single according to the module of the embodiment of the present disclosure, submodule, unit, son
Any one or more in member can be split into multiple modules to realize.According to the module of the embodiment of the present disclosure, submodule,
Any one or more in unit, subelement can at least be implemented partly as hardware circuit, such as field programmable gate
Array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, the system in encapsulation, dedicated integrated electricity
Road (ASIC), or can be by the hardware or firmware for any other rational method for integrate or encapsulate to circuit come real
Show, or with any one in three kinds of software, hardware and firmware implementations or with wherein any several appropriately combined next reality
It is existing.Alternatively, can be at least by part according to one or more of the module of the embodiment of the present disclosure, submodule, unit, subelement
Ground is embodied as computer program module, when the computer program module is run, can execute corresponding function.
For example, data obtaining module 410, any number of can merging of being intended to obtain in module 420 and output module 430
It is realized in a module or any one module therein can be split into multiple modules.Alternatively, in these modules
At least partly function of one or more modules can be combined at least partly function of other modules, and in a module
It realizes.In accordance with an embodiment of the present disclosure, data obtaining module 410, intention obtain in module 420 and output module 430 at least
One can at least be implemented partly as hardware circuit, such as field programmable gate array (FPGA), programmable logic array
(PLA), system on chip, the system on substrate, the system in encapsulation, specific integrated circuit (ASIC), or can be by circuit
The hardware such as any other rational method that is integrated or encapsulating or firmware are carried out to realize, or with software, hardware and firmware three
Any one in kind of implementation several appropriately combined is realized with wherein any.Alternatively, data obtaining module 410, meaning
Figure, which obtains at least one of module 420 and output module 430, can at least be implemented partly as computer program module, when
When the computer program module is run, corresponding function can be executed.
Fig. 5 diagrammatically illustrates the block diagram of the calculating equipment according to the embodiment of the present disclosure.Computer system shown in Fig. 5 is only
Only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 5, the calculating equipment 500 may include: one or more processors 510 and computer-readable storage
Medium 520.The server cluster can execute the method according to the embodiment of the present disclosure.
Specifically, processor 510 for example may include general purpose microprocessor, instruction set processor and/or related chip group
And/or special microprocessor (for example, specific integrated circuit (ASIC)), etc..Processor 510 can also include using for caching
The onboard storage device on way.Processor 510 can be the different movements for executing the method flow according to the embodiment of the present disclosure
Single treatment unit either multiple processing units.
Computer readable storage medium 520, such as can be non-volatile computer readable storage medium, specific example
Including but not limited to: magnetic memory apparatus, such as tape or hard disk (HDD);Light storage device, such as CD (CD-ROM);Memory, such as
Random access memory (RAM) or flash memory etc..
Computer readable storage medium 520 may include program 521, which may include that code/computer can be held
Row instruction, executes processor 510 according to the method for the embodiment of the present disclosure or its any change
Shape.
Program 521 can be configured to have the computer program code for example including computer program module.For example, showing
In example embodiment, the code in program 521 may include one or more program modules, for example including program module 521A, journey
Sequence module 521B ....It should be noted that the division mode and number of program module are not fixed, those skilled in the art
It can be combined according to the actual situation using suitable program module or program module, when these program modules are combined by processor
When 510 execution, processor 510 is executed according to the method for the embodiment of the present disclosure or its any deformation.
In accordance with an embodiment of the present disclosure, processor 510 can be interacted with computer readable storage medium 520, to hold
Row is according to the method for the embodiment of the present disclosure or its any deformation.
In accordance with an embodiment of the present disclosure, data obtaining module 410, intention obtain in module 420 and output module 430 extremely
Few one can be implemented as the program module with reference to Fig. 5 description and may be implemented to be described above when being executed by processor 510
Corresponding operating.
The disclosure additionally provides a kind of computer readable storage medium, which can be above-mentioned reality
It applies included in equipment/device/system described in example;Be also possible to individualism, and without be incorporated the equipment/device/
In system.Above-mentioned computer readable storage medium carries one or more program, when said one or multiple program quilts
When execution, the method according to the embodiment of the present disclosure is realized.
In accordance with an embodiment of the present disclosure, computer readable storage medium can be non-volatile computer-readable storage medium
Matter, such as can include but is not limited to: portable computer diskette, hard disk, random access storage device (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
It will be understood by those skilled in the art that the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination, even if such combination or combination are not expressly recited in the disclosure.Particularly, exist
In the case where not departing from disclosure spirit or teaching, the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination.All these combinations and/or combination each fall within the scope of the present disclosure.
Although the disclosure, art technology has shown and described referring to the certain exemplary embodiments of the disclosure
Personnel it should be understood that in the case where the spirit and scope of the present disclosure limited without departing substantially from the following claims and their equivalents,
A variety of changes in form and details can be carried out to the disclosure.Therefore, the scope of the present disclosure should not necessarily be limited by above-described embodiment,
But should be not only determined by appended claims, also it is defined by the equivalent of appended claims.
Claims (10)
1. a kind of exchange method is applied in intelligent conversational system, the intelligence conversational system can be defeated to the user received
Enter information and is responded and provided feedback information, this method comprises:
It obtains user and inputs information;
N number of intent information that the user inputs information representation is extracted and exports, the N is the positive integer greater than 1;
It responds the user and inputs information, generate and export M feedback information, the M is greater than 1 and just whole less than or equal to N
Number, the M feedback information correspond to preceding M intent information in N number of intent information.
2. according to the method described in claim 1, wherein, the generation simultaneously exports M feedback information, and the M is greater than 1 and small
In the positive integer for being equal to N, the M feedback information corresponds to preceding M intent information in N number of intent information and includes:
If N number of intent information is not excluded from, responds the user and inputs information, generate and export M feedback information,
The M feedback information corresponds to the preceding M intent informations being not excluded from N number of intent information;
If having the intent information mutually repelled in N number of intent information, X before being chosen from N number of intent information
The intent information being not excluded from responds the user and inputs information, generates and export M feedback information, the M feedback information
The intent information being not excluded from corresponding to preceding M in the preceding X intent information, wherein the M≤X≤N, and be positive integer.
3. according to the method described in claim 1, wherein, the extraction simultaneously exports N number of meaning that the user inputs information representation
Figure information includes:
Information is inputted to the user and carries out semantic understanding, obtains first intention information;And
Determine that associated second intention information, the second intention information include described in modification according to the first intention information
The intent information that first intention information obtains.
4. described to determine associated second meaning according to the first intention information according to the method described in claim 3, wherein
Figure information includes:
It is intended to variable according to the corresponding relationship and the first intention acquisition of information that are intended to and are intended to variable, wherein an intention
Variable corresponds to the trigger condition of at least one modification intent information;And
If the trigger condition that at least one modification is intended to is triggered, intent information is modified, second intention information is obtained,
In, the first intention information is mutually repelled or is not excluded from the second intention information.
5. according to the method described in claim 4, wherein, the intention variable is included any of the following or a variety of: position, when
Between, space, user property, user equipment attribute or event.
6. according to the method described in claim 4, wherein:
At least partly intent information includes the intent information opposite with the first intention information in the second intention information;Or
Person
At least partly intent information includes believing with the different types of intention of the first intention information in the second intention information
Breath.
7. according to the method described in claim 5, wherein, the intention be intended to the corresponding relationship of variable structure in the following manner
It builds:
Alternative intent information is obtained, the alternative intent information is there is a possibility that the intent information of modification;
Obtain the corresponding trigger condition for being intended to variable and modifying intent information of the alternative intent information;
According to the alternative intent information, the corresponding touching for being intended to variable and the modification intent information of the alternative intent information
Clockwork spring part determines the corresponding relationship of the intention with intention variable.
8. according to the method described in claim 5, wherein, the intention be intended to the corresponding relationship of variable structure in the following manner
It builds:
Define a situation, the corresponding at least one intent information of the situation;
From the information obtained in history log under the situation;
The variable for influencing the corresponding intent information of the situation is obtained from the information under the situation.
9. according to the method described in claim 3, wherein, the intention passes through in database with the corresponding relationship for being intended to variable
Main external key mode describes.
10. a kind of calculating equipment, comprising:
One or more processors;
Computer readable storage medium, for storing one or more computer programs, the computer program is by the place
When managing device execution, method according to claim 1 to 9 is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811641649.6A CN109783625A (en) | 2018-12-29 | 2018-12-29 | Exchange method and calculating equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811641649.6A CN109783625A (en) | 2018-12-29 | 2018-12-29 | Exchange method and calculating equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109783625A true CN109783625A (en) | 2019-05-21 |
Family
ID=66499535
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811641649.6A Pending CN109783625A (en) | 2018-12-29 | 2018-12-29 | Exchange method and calculating equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109783625A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111127040A (en) * | 2019-12-19 | 2020-05-08 | 联想(北京)有限公司 | Data processing method, intelligent customer service system, electronic equipment and medium |
CN111161068A (en) * | 2019-12-23 | 2020-05-15 | 支付宝(杭州)信息技术有限公司 | Transaction element checking method and device |
CN111210232A (en) * | 2019-12-31 | 2020-05-29 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
CN111241257A (en) * | 2020-01-03 | 2020-06-05 | 联想(北京)有限公司 | Information processing method and electronic device |
CN112163078A (en) * | 2020-09-29 | 2021-01-01 | 彩讯科技股份有限公司 | Intelligent response method, device, server and storage medium |
CN112527979A (en) * | 2020-11-10 | 2021-03-19 | 联想(北京)有限公司 | Information interaction method and device and readable storage medium |
CN112784024A (en) * | 2021-01-11 | 2021-05-11 | 软通动力信息技术(集团)股份有限公司 | Man-machine conversation method, device, equipment and storage medium |
CN113065362A (en) * | 2021-03-19 | 2021-07-02 | 联想(北京)有限公司 | Intelligent reply method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102722558A (en) * | 2012-05-29 | 2012-10-10 | 百度在线网络技术(北京)有限公司 | User question recommending method and device |
CN105488164A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Question and answer (QA) data processing method and device, intelligent robot |
CN108197115A (en) * | 2018-01-26 | 2018-06-22 | 上海智臻智能网络科技股份有限公司 | Intelligent interactive method, device, computer equipment and computer readable storage medium |
US20180232376A1 (en) * | 2017-02-16 | 2018-08-16 | Microsoft Technology Licensing, Llc | Conversational virtual assistant |
-
2018
- 2018-12-29 CN CN201811641649.6A patent/CN109783625A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102722558A (en) * | 2012-05-29 | 2012-10-10 | 百度在线网络技术(北京)有限公司 | User question recommending method and device |
CN105488164A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Question and answer (QA) data processing method and device, intelligent robot |
US20180232376A1 (en) * | 2017-02-16 | 2018-08-16 | Microsoft Technology Licensing, Llc | Conversational virtual assistant |
CN108197115A (en) * | 2018-01-26 | 2018-06-22 | 上海智臻智能网络科技股份有限公司 | Intelligent interactive method, device, computer equipment and computer readable storage medium |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111127040A (en) * | 2019-12-19 | 2020-05-08 | 联想(北京)有限公司 | Data processing method, intelligent customer service system, electronic equipment and medium |
CN111161068A (en) * | 2019-12-23 | 2020-05-15 | 支付宝(杭州)信息技术有限公司 | Transaction element checking method and device |
CN111161068B (en) * | 2019-12-23 | 2022-06-14 | 支付宝(杭州)信息技术有限公司 | Transaction element checking method and device |
CN111210232A (en) * | 2019-12-31 | 2020-05-29 | 联想(北京)有限公司 | Data processing method and device and electronic equipment |
CN111241257A (en) * | 2020-01-03 | 2020-06-05 | 联想(北京)有限公司 | Information processing method and electronic device |
CN111241257B (en) * | 2020-01-03 | 2023-07-21 | 联想(北京)有限公司 | Information processing method and electronic device |
CN112163078A (en) * | 2020-09-29 | 2021-01-01 | 彩讯科技股份有限公司 | Intelligent response method, device, server and storage medium |
CN112527979A (en) * | 2020-11-10 | 2021-03-19 | 联想(北京)有限公司 | Information interaction method and device and readable storage medium |
CN112784024A (en) * | 2021-01-11 | 2021-05-11 | 软通动力信息技术(集团)股份有限公司 | Man-machine conversation method, device, equipment and storage medium |
CN112784024B (en) * | 2021-01-11 | 2023-10-31 | 软通动力信息技术(集团)股份有限公司 | Man-machine conversation method, device, equipment and storage medium |
CN113065362A (en) * | 2021-03-19 | 2021-07-02 | 联想(北京)有限公司 | Intelligent reply method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109783625A (en) | Exchange method and calculating equipment | |
AU2019204285B2 (en) | Artificial intelligence (ai) based chatbot creation and communication system | |
WO2022160707A1 (en) | Human-machine interaction method and apparatus combined with rpa and ai, and storage medium and electronic device | |
US10430250B2 (en) | Decomposing monolithic application into microservices | |
US10713664B1 (en) | Automated evaluation and reporting of microservice regulatory compliance | |
US11106683B2 (en) | System architecture for interactive query processing | |
JP2021534493A (en) | Techniques for building knowledge graphs within a limited knowledge domain | |
CN113377850A (en) | Big data technology platform of cognitive Internet of things | |
US11151321B2 (en) | Anaphora resolution | |
CN111046237B (en) | User behavior data processing method and device, electronic equipment and readable medium | |
US10671752B1 (en) | Computer-based methods and systems for managing private data of users | |
US11019019B2 (en) | Dynamic hashtag ordering based on projected interest | |
US20200285636A1 (en) | Context-sensitive cross-lingual searches | |
CN108702377A (en) | For for the suggestion of intelligent mobile object, start and the system of automatically or semi-automatically downloading application | |
CN112286601A (en) | User interface display method and device | |
CN105786941A (en) | Information mining method and device | |
CN109145092A (en) | A kind of database update, intelligent answer management method, device and its equipment | |
US20200412671A1 (en) | Chat bot operation and management architecture | |
US10547734B2 (en) | Augmenting messages based on sender location | |
US20220027788A1 (en) | Cognitive platform for autonomous data orchestration and the method thereof | |
US20210097413A1 (en) | Predictive Readiness and Accountability Management | |
US11388260B2 (en) | Protocol for exchanging user model data objects among ubiquitous devices | |
Nasir et al. | Software engineering based fault tolerance model for information system in plants shopping center | |
US10963796B1 (en) | System and method for implementing an assessment tool | |
US20190347117A1 (en) | Virtual action-based troubleshooter |
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: 20190521 |
|
RJ01 | Rejection of invention patent application after publication |