CN110442695A - A kind of intelligent interaction platform training method, apparatus, equipment - Google Patents
A kind of intelligent interaction platform training method, apparatus, equipment Download PDFInfo
- Publication number
- CN110442695A CN110442695A CN201910706857.8A CN201910706857A CN110442695A CN 110442695 A CN110442695 A CN 110442695A CN 201910706857 A CN201910706857 A CN 201910706857A CN 110442695 A CN110442695 A CN 110442695A
- Authority
- CN
- China
- Prior art keywords
- task
- slot position
- user
- learning data
- critical learning
- 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.)
- Granted
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 title claims abstract description 22
- 239000000284 extract Substances 0.000 claims abstract description 4
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012986 modification Methods 0.000 claims description 8
- 230000004048 modification Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 abstract description 17
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 210000004209 hair Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012913 prioritisation Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of intelligent interaction platform training methods, which is characterized in that the described method includes: step 1, receives one or more tasks of one or more user's creations, wherein task includes task identification and task definition；Step 2, the parsing one or more of user's creations of the task, extracts multiple all critical learning data relevant to task；Step 3, multiple slot positions associated with one or more of tasks are obtained, all critical learning data corresponding with the slot position is determined, all critical learning data is filled to the slot position.The implementation of the embodiment of the present invention effectively training smart interaction platform, raising user can be intended to understandability, establish more optimized interactive controlling and management, promote user experience, achieve beneficial effect.
Description
Technical field
The present embodiments relate to technical field of information processing, in particular to a kind of intelligent interaction platform training method, dress
It sets, equipment and computer readable storage medium.
Background technique
With the development and universal, the various aspects offer that the intellectual technologies such as human-computer interaction are lived in people of computer technology
Conveniently service.Human-computer interaction HCI (Human-Computer Interaction) technology refer to by computer input,
Output equipment realizes the technology of people and computer dialog in an efficient way.Human-computer interaction technology include machine by output or
Display equipment largely for information about and prompts to ask for instructions to people's offer, and people is inputted for information about by input equipment to machine, time
Question and answer topic and prompt are asked for instructions.The intelligentized man-machine interaction mode of rapid development for being currently based on artificial intelligence also constantly updates hair
Exhibition.
Current human-computer interaction service is usually to be trained by developer, and function is opposite to limit to.How intelligence is effectively trained
Energy interaction platform improves user and is intended to understandability, and establishing more optimized interactive controlling and management is current urgent need to resolve problem.
Summary of the invention
The embodiment of the invention provides a kind of input method based on scene, device, equipment and computer-readable storage mediums
Matter can be used for solving the problems in the relevant technologies.
On the one hand, the embodiment of the invention provides a kind of intelligent interaction platform training methods, which is characterized in that the method
Include:
Step 1, one or more tasks of one or more user's creations are received, wherein task includes task identification and appoints
Business content；
Step 2, the task is parsed, multiple all critical learning data relevant to task are extracted；
Step 3, multiple slot positions associated with the task are obtained, determine that the key corresponding with the slot position is known
Know data, all critical learning data are filled to the slot position.
Preferably, the task identification of user's creation includes task names, and/or task description information.
Preferably, the task definition of user's creation includes task basic demand；Or flow of task and task execution
Relevant knowledge data.
Preferably, the method further includes steps 4, generate the interaction sub- engine based on the task, the sub- engine packet
Sub- engine containing voice and/or text sub- engine.
Preferably, the general slot position preset for the task by inquiry intelligent interaction platform, and/or, pass through inquiry
Slot position in associated same generic task obtains one or more basic slot positions；And/or it is customized by the user and matches with task
The basic slot positions of one or more；
All critical learning data corresponding with basic slot position in task definition are extracted, corresponding basic slot position is filled.
Preferably, judge crucial to the one or more of basic slot position with the presence or absence of not being filled in the task definition of parsing
Knowledge data, and if it exists, generate corresponding one or more extension slot positions, and all critical learning data are filled to correspondence
Extension slot position.
Alternatively, lacking corresponding all critical learning data when judgement executes user task, generates corresponding one or more and expand
Slot position is opened up, and all critical learning data lacked are filled to corresponding extension slot position.
The acquisition of all critical learning data lacked can be automatically performed by retrieval local or cloud data bank, or
Lack all critical learning data to user feedback, requests user's supplementary data.
Alternatively, after all critical learning data have been filled to corresponding slot position, judge whether there is and lack key and know
Know the basic slot position of data, and if it exists, inquire to user feedback vacancy slot position information, or automatically and fill corresponding knowledge number
According to, or by the basic slot position set vacancy.
Preferably, increase, the modification, delete operation of the task definition that user creates it, the operation based on user are received
Update user task.
On the other hand, the embodiment of the invention provides a kind of intelligent interaction platform training devices, which is characterized in that the dress
It sets and includes:
Interface module receives one or more tasks of one or more user's creations, and wherein task includes task identification
And task definition；
Analysis module parses the task, extracts multiple all critical learning data relevant to task；
Configuration module obtains multiple slot positions associated with the task, determines the pass corresponding with the slot position
Key knowledge data fills all critical learning data to the slot position.
Preferably, the task identification of user's creation includes task names, and/or task description information.
Preferably, the task definition of user's creation includes task basic demand；Or flow of task and task execution
Relevant knowledge data.
Preferably, package module, for generating the interaction sub- engine based on the task, the sub- engine includes voice
Engine and/or text sub- engine.
Preferably, the configuration module is further used for, preset for the task by inquiry intelligent interaction platform
General slot position, and/or, by the slot position inquired in associated same generic task, obtain one or more basic slot positions；And/or by
The customized basic slot position of one or more to match with task of user；
All critical learning data corresponding with basic slot position in the task definition of extraction are filled to corresponding basic slot position.
Preferably, the configuration module is also used to, and judging, which whether there is in the task definition of parsing, is not filled to basic
One or more all critical learning data of slot position, and if it exists, feedback message to configuration module；
Generate corresponding one or more extension slot positions；
The all critical learning data not being filled are filled to corresponding extension slot position；
Or
When judgement executes user task, lack corresponding all critical learning data, and if it exists, feedback message to configuration module；
Generate corresponding one or more extension slot positions；
The all critical learning data lacked are filled to corresponding extension slot position.The acquisition of all critical learning data lacked
It can be automatically performed by retrieval local or cloud data bank, or lack all critical learning data to user feedback, request user
Supplementary data.
Or
After all critical learning data have been filled to corresponding slot position, judge whether there is and lack all critical learning data
Basic slot position, and if it exists, to user feedback vacancy slot position information, perhaps automatically inquire and fill corresponding knowledge data or
Vacancy is set by the basic slot position.
Preferably, the interface module is further used for, receive the increase of user's task definition that it is created, modification,
Delete operation,
Described device further comprises update module, and the update module updates user for the operation based on user and appoints
Business.
On the other hand, the embodiment of the invention provides a kind of terminal devices comprising intelligent interaction platform training device.
On the other hand, the embodiment of the invention provides a kind of computer equipment, the computer equipment include processor and
Memory is stored with the computer program that can be run on a processor in the memory, and the computer program is described
Processor realizes method above-mentioned when executing.
On the other hand, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storages
The computer program that can be run on a processor is stored in medium, the computer program realize when executed it is aforementioned
Method.
The implementation of the embodiment of the present invention effectively training smart interaction platform, raising user can be intended to understandability, build
More optimized interactive controlling and management are found, user experience is promoted, achieves beneficial effect.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it is clear that ground, the accompanying drawings in the following description are this hairs
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the schematic diagram for the intelligent interaction platform that this specification embodiment provides.
Fig. 2 is the flow diagram for the intelligent interaction platform training method that this specification embodiment provides.
Fig. 3 is the intelligent interaction platform training apparatus structure that this specification embodiment provides.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.The embodiment of the present invention and the specific features of embodiment are to technical side of the embodiment of the present invention
The detailed description of case, rather than the restriction to description of the invention technical solution, in the absence of conflict, the embodiment of the present invention
And the technical characteristic of embodiment can be combined with each other.
Referring to Fig. 1, Fig. 1 is the schematic diagram of intelligent interaction platform, human-computer interaction interface 101, processing module are specifically included that
102, database 103 etc..Wherein processing module includes interactive engine 112, and interactive engine 112 may include semantic understanding module
201, dialogue management and control module 202 talk with generation module 203, command execution module 204.Wherein, processing module 102 with
Human-computer interaction interface 101 is connected with each other, and the data of user's input can be received by human-computer interaction interface 101, and pass through people
Machine interactive interface exports interaction data to user, i.e. 101 one side of human-computer interaction interface can be received instead by processing module 102
It feeds the dialogue data of user, on the one hand can receive the order implementation procedure and result data of the feedback of processing module 102.For
Intelligent sound interaction platform, processing module 102 can also include: speech recognition module 210, voice output module 211.Institute's predicate
Sound identification module 210, voice output module 211 can also be configured in interactive engine 112.In addition, interactive engine 112 can be by
Leading engine and/or multiple sub- engines are constituted.
The one of them main points of intelligent interaction platform training are to improve the processing capacity of interactive engine, enhance interactive engine pair
In semantic understanding, the efficiency of dialogue interaction is improved, and promotes task execution accuracy；These require to user be intended into
Row accurate understanding improves interactive engine for interactive control by enriching slot position and slot position parsing in user's expression sentence
And management.
Embodiment one
Referring to Fig. 2, Fig. 2 is a kind of process signal for intelligent interaction platform training method that the embodiment of the present invention one provides
Figure, this method includes but is not limited to:
Step 1, one or more tasks of one or more user's creations are received, wherein task includes task identification and appoints
Business content；
Specifically, task of oneself is created by the open interface can be allowed users to user's open interface.
Wherein, the task identification of user's creation includes task names, and/or task description information.The task definition of user's creation can be with
Include task basic demand；It can also include the relevant knowledge data of flow of task and task execution that user uploads.
For example, user A creation library borrows task, task names are book borrowing and reading, and task definition is from self-service book
Borrow " empire, Qun Dynasty third portion military hardware " in shop；
User B can by creating oneself task to user's open interface, such as: task names are Tokyo travel notes, are appointed
Business content is the tourism strategy that user B writes；
Step 2, the task is parsed, multiple all critical learning data relevant to task are extracted；
Specifically, for the task of user A creation, it is assumed that it is former intelligent interaction platform that its library created, which borrows task,
Being not present for task then analyzes the task of user's creation first, determines being intended to " checking out " for user, all critical learning number of task
According to are as follows: Self-service Library, " empire, Qun Dynasty third portion military hardware "；
For the task of user B creation, by the analysis to its task, confirm that user's is intended to " tourism strategy ",
Position, business hours and the evaluation at the sight spot for including in the task definition of upload, name location, the price in the hotel restaurant of recommendation
And evaluation, the route of navigation, the price of the vehicles, time, each stroke used time, the contents such as recommendation of shopping site can be used as
All critical learning data.Such as task definition suggestion is played from Tai Chang to shallow careless temple, can be sat Yurikamome in platform field and be arrived
Then new bridge changes the shallow careless line of all battalion and gets off to shallow careless temple station, 35 minutes whole.The all critical learning data of then extracting for task are as follows:
Platform field, shallow careless temple, Yurikamome, new bridge, transfer, all battalion's shallow careless line, 35 minutes.
Step 3, multiple slot positions associated with the task are obtained, determine that the key corresponding with the slot position is known
Know data, all critical learning data are filled to the slot position.
Slot position usually requires to describe comprising slot position, slot position content and other elements explained to slot position, such as slot
Position type: whether the slot position has to fill out；Such as slot position attribute: the meaning of the slot position such as represents time, place, period, area
Domain or currencies；For simple example, the embodiment of the present invention is mainly described with slot position, the signal of slot position content.
Specifically, obtaining multiple slot positions associated with the task further comprises, by inquiring intelligent interaction platform
For the preset general slot position of the task, and/or, by the slot position inquired in associated same generic task, obtain one or more
A basic slot position；And/or it is customized by the user the basic slot position of one or more to match with task.
Such as user A, since platform does not provide the task, user A can self-setting establish the base for completing the task
This slot position, since user A task definition initially set is to borrow " empire, Qun Dynasty third portion Jin Getie from Self-service Library
Horse "；Then it selects to borrow source, title as basic slot position.
For user B, the basic slot position of the possible initial setting up of the tourism task of platform are as follows: departure place, destination, traffic work
Have 1-n, transfer stop 1-n, time, expense.
It is then determined that all critical learning data corresponding with the slot position, all critical learning data are filled to described
Slot position.
Specifically, judge crucial to the one or more of basic slot position with the presence or absence of not being filled in the task definition of parsing
Knowledge data, and if it exists, generate corresponding one or more extension slot positions, and all critical learning data are filled to correspondence
Extension slot position.
Alternatively, lacking corresponding all critical learning data when judgement executes user task, generates corresponding one or more and expand
Slot position is opened up, and all critical learning data lacked are filled to corresponding extension slot position.
The acquisition of all critical learning data lacked can be automatically performed by retrieval local or cloud data bank, or
Lack all critical learning data to user feedback, requests user's supplementary data.
Alternatively, after all critical learning data have been filled to corresponding slot position, judge whether there is and lack key and know
Know the basic slot position of data, and if it exists, inquire to user feedback vacancy slot position information, or automatically and fill corresponding knowledge number
According to, or by the basic slot position set vacancy.
It is described in detail below for user A, basic slot position filling is as follows: in the task of user A creation
Table 1: the basic slot position design of user's A book borrowing and reading
| Slot position description | Slot position content |
| Borrow source | Self-service Library |
| Title | " empire, Qun Dynasty third portion military hardware " |
After having handled the playback of all critical learning data, it is input to the module with dialogue ability, this has dialogue energy
The module of power can be the existing dialogue management of intelligent interaction platform and control module, dialogue generation module.It is expressed for user
It returns and is replied defined in dialogue dialogue management and control, finally meet user's particular demands.
When executing the task of user's creation, discovery Self-service Library website needs to submit reader's card number of user, then
New extension slot position can be configured, for example, borrowing voucher by identifying the condition.When task can after the completion of, to user A create
Task into encapsulation, generate the interaction sub- engine based on the task.
It is described in detail below for user B, basic slot position filling is as follows: in task
Table 2: the basic slot position design of user's B tour schedule
| Slot position description | Slot position content |
| Departure place | Platform field |
| Destination | Shallow grass temple |
| The vehicles 1 | Yurikamome |
| Transfer stop | New bridge |
| The vehicles 2 | All shallow careless lines of battalion |
| Time | 35 minutes |
| Expense | Null |
Since user B does not record this Key Points of expense, internet data can be retrieved for the slot position, it is automatic complete
At, can also transmit the message to user B, request user B supplemental information or this do not add temporarily, by the slot position content
It empties.
The interaction sub- engine based on the task is generated for the task of user B creation.
In addition, to reinforce the ability of platform interactive engine, the subsequent task or existing task that can be completed to creation
It is counted, establishes the linked database of task attribute, slot position, as shown in table 3:
Table 3: the linked database of task attribute, slot position
The embodiment of the present invention is only to illustrate to the citing of slot position, for completing specific task, the quantity for the slot position being related to
It is richer, it does not enumerate one by one herein.
It is subsequent that the slot position of completion is configured in the task of B and other users creation for user A, can selectively,
According to the association of task attribute, slot position, the slot position description and/or the introducing of slot position content for the slot position being arranged have same task
Interactive engine/sub- engine of attribute, to supplement and improve the slot position design of corresponding interactive engine/sub- engine.
Further it is provided that download path and the zone of discussion of user task, count the task download of user's creation；
It scores to the evaluation of user task.
According to download/evaluation of user task, the priority level of user is set.
According to the priority level of user, all critical learning high priority data of multiple users of dynamic adjustment filling to same slot position
Grade.
For example, there is user D simultaneously, user E creates the tourism task similar with user B, passes through statistics download hair
The download of current family B is maximum, then being described based on same slot position, the slot position content prioritization of user B is filled in other users
Slot position content on.
In the same slot position description that multiple users provide, stored in the slot position content of user H and the slot position of other users
When clearly contradicted, can not insert user H offer corresponding slot position content is described with slot position.
In addition, receiving increase, the modification, delete operation for the task definition that user creates it, the operation based on user is more
New user task.
Embodiment two
Based on similarly conceiving with information push method in previous embodiment, the embodiment of the invention also provides a kind of intelligence
Interaction platform training device, the intelligent interaction platform training device can also be embedded in independently of intelligent interaction platform
Intelligent interaction platform is realized.Referring to Fig. 3, described device includes:
Interface module 301 receives one or more tasks of one or more user's creations, and wherein task includes task mark
Knowledge and task definition；
Analysis module 302 parses the task of one or more of user's creations, extracts multiple keys relevant to task
Knowledge data；
Configuration module 303 obtains multiple slot positions associated with the task, determines corresponding with the slot position described
All critical learning data fill all critical learning data to the slot position.
Specifically, the task identification of user's creation includes task names, and/or task description information.The user
The task definition of creation includes task basic demand；Or the relevant knowledge data of flow of task and task execution.
Specifically, the interface module of intelligent interaction platform training device can be connected with intelligent interaction platform, thus side
Just data self-teaching training is obtained from intelligent interaction platform.
Specifically intelligent interaction platform training device further includes package module 304, for generating the friendship based on the task
Mutual sub- engine, the sub- engine include voice sub- engine and/or text sub- engine.
Specifically, the configuration module is further used for, preset for the task by inquiry intelligent interaction platform
General slot position, and/or, by the slot position inquired in associated same generic task, obtain one or more basic slot positions；And/or by
The customized basic slot position of one or more to match with task of user；
All critical learning data corresponding with basic slot position in the task definition of extraction are filled to corresponding basic slot position.
Preferably, the configuration module is further used for, judge parsing task definition in the presence or absence of be not filled to
One or more all critical learning data of basic slot position, and if it exists, feedback message to configuration module；
Generate corresponding one or more extension slot positions；
The all critical learning data not being filled are filled to corresponding extension slot position；
Or
The configuration module is further used for, and when judging to execute user task, lacks corresponding all critical learning data, if depositing
In feedback message to configuration module；
Generate corresponding one or more extension slot positions；
The all critical learning data lacked are filled to corresponding extension slot position.The acquisition of all critical learning data lacked
It can be automatically performed by retrieval local or cloud data bank, or lack all critical learning data to user feedback, request user
Supplementary data.
Or
The configuration module is further used for, after all critical learning data have been filled to corresponding slot position, judgement
With the presence or absence of the basic slot position for lacking all critical learning data, and if it exists, to user feedback vacancy slot position information, or automatic inquiry
And corresponding knowledge data is filled, or set vacancy for the basic slot position.
Establish the linked database of task attribute, slot position；
The slot position that completion is configured in the subsequent task for user's creation is set according to the association of task attribute, slot position
The slot position of the slot position set describes and/or slot position content introduces the interactive engine/sub- engine for having same task attribute, with supplement and
Improve the slot position design of corresponding interactive engine/sub- engine.
Further it is provided that download path and the zone of discussion of user task, the intelligent interaction platform further includes statistical module,
Task download for creating to user counts；It scores to the evaluation of user task.
According to download/evaluation of user task, the priority level of user is set.
According to the priority level of user, all critical learning high priority data of multiple users of dynamic adjustment filling to same slot position
Grade.
For example, there is user D simultaneously, user E creates the tourism task similar with user B, passes through statistics download hair
The download of current family B is maximum, then being described based on same slot position, the slot position content prioritization of user B is filled in other users
Slot position content on.
In the same slot position description that multiple users provide, stored in the slot position content of user H and the slot position of other users
When clearly contradicted, can not insert user H offer corresponding slot position content is described with slot position.
Preferably, the interface module is further used for, receive the increase of user's task definition that it is created, modification,
Delete operation,
Described device further comprises update module, and the update module updates user for the operation based on user and appoints
Business.
Based on similarly conceiving with information push method in previous embodiment, the embodiment of the invention also provides a kind of terminals
Equipment, the terminal include the intelligent interaction platform training device in above-described embodiment two.
Specifically, terminal device can be computer, tablet computer, mobile phone, intelligent assistant, car-mounted terminal etc..
Based on similarly conceiving with information push method in previous embodiment, the embodiment of the invention also provides a kind of calculating
Machine equipment, the computer equipment include processor and memory, and be stored in the memory to run on a processor
Computer program, the computer program realize corresponding information push method when being executed by the processor.
Based on similarly conceiving with information push method in previous embodiment, the embodiment of the invention also provides a kind of calculating
Machine readable storage medium storing program for executing is stored with the computer program that can be run on a processor, institute in the computer readable storage medium
State the method that the computer program realizes information push when executed.
The above is only a preferred embodiment of the present invention, it is not intended to restrict the invention, it is noted that for this skill
For the those of ordinary skill in art field, without departing from the technical principles of the invention, can also make it is several improvement and
Modification, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (17)
1. a kind of intelligent interaction platform training method, which is characterized in that the described method includes:
Step 1, one or more tasks of one or more user's creations are received, wherein task includes in task identification and task
Hold；
Step 2, the task is parsed, multiple all critical learning data relevant to task are extracted；
Step 3, multiple slot positions associated with the task are obtained, determine all critical learning number corresponding with the slot position
According to filling all critical learning data to the slot position.
2. the method according to claim 1, wherein
The task identification of user's creation includes task names, and/or task description information.
3. the method according to claim 1, wherein
The task definition of user's creation includes task basic demand；Or the relevant knowledge number of flow of task and task execution
According to.
4. the method according to claim 1, wherein
Step 4, the interaction sub- engine based on the task is generated, the sub- engine includes that voice sub- engine and/or text draw
It holds up.
5. the method according to claim 1, wherein
By the inquiry intelligent interaction platform general slot position preset for the task, and/or, by inquiring associated similar
Slot position in business obtains one or more basic slot positions；And/or it is customized by the user the one or more to match with task
Basic slot position；
All critical learning data corresponding with basic slot position in task definition are extracted, corresponding basic slot position is filled.
6. according to the method described in claim 5, it is characterized in that,
Judging, which whether there is in the task definition of parsing, is not filled to one or more all critical learning data of basic slot position, if
In the presence of, the corresponding one or more extension slot positions of generation, and all critical learning data are filled to corresponding extension slot position.
Alternatively, lacking corresponding all critical learning data when judgement executes user task, corresponding one or more expansion slot are generated
Position, and all critical learning data lacked are filled to corresponding extension slot position.
The acquisition of all critical learning data lacked can by retrieval local or cloud data bank be automatically performed, or to
Family feedback lacks all critical learning data, requests user's supplementary data.
Alternatively, judging whether there is after all critical learning data have been filled to corresponding slot position and lacking all critical learning number
According to basic slot position, and if it exists, inquire and fill corresponding knowledge data to user feedback vacancy slot position information, or automatically, or
The basic slot position is set vacancy by person.
7. the method according to claim 1, wherein
Increase, the modification, delete operation for receiving the task definition that user creates it, the operation based on user update user and appoint
Business.
8. a kind of intelligent interaction platform training device, which is characterized in that described device includes:
Interface module receives one or more tasks of one or more user's creations, and wherein task includes task identification and appoints
Business content；
Analysis module parses the task, extracts multiple all critical learning data relevant to task；
Configuration module obtains multiple slot positions associated with the task, determines that the key corresponding with the slot position is known
Know data, all critical learning data are filled to the slot position.
9. device according to claim 8, which is characterized in that
The task identification of user's creation includes task names, and/or task description information.
10. device according to claim 8, which is characterized in that
The task definition of user's creation includes task basic demand；Or the relevant knowledge number of flow of task and task execution
According to.
11. device according to claim 8, which is characterized in that
Package module, for generating the interaction sub- engine based on the task, the sub- engine includes voice sub- engine and/or text
This sub- engine.
12. device according to claim 8, which is characterized in that the configuration module is further used for,
By the inquiry intelligent interaction platform general slot position preset for the task, and/or, by inquiring associated similar
Slot position in business obtains one or more basic slot positions；And/or it is customized by the user the one or more to match with task
Basic slot position；
All critical learning data corresponding with basic slot position in the task definition of extraction are filled to corresponding basic slot position.
13. device according to claim 12, which is characterized in that the configuration module is also used to,
Judging, which whether there is in the task definition of parsing, is not filled to one or more all critical learning data of basic slot position, if
In the presence of feedback message to configuration module；
Generate corresponding one or more extension slot positions；
The all critical learning data not being filled are filled to corresponding extension slot position；
Or
When judgement executes user task, lack corresponding all critical learning data, and if it exists, feedback message to configuration module；
Generate corresponding one or more extension slot positions；
The all critical learning data lacked are filled to corresponding extension slot position.The acquisition of all critical learning data lacked can
It is automatically performed by retrieval local or cloud data bank, or lacks all critical learning data, request user's supplement to user feedback
Data.
Or
After all critical learning data have been filled to corresponding slot position, the base for lacking all critical learning data is judged whether there is
This slot position, and if it exists, to user feedback vacancy slot position information, perhaps inquire and fill corresponding knowledge data or should automatically
Basic slot position is set as vacancy.
14. device according to claim 8, which is characterized in that
The interface module is further used for, and receives increase, the modification, delete operation of the task definition that user creates it,
Described device further comprises update module, and the update module updates user task for the operation based on user.
15. a kind of terminal device, it is characterised in that: include intelligent interaction platform training device described in claim 8-14.
16. a kind of computer equipment, which is characterized in that the computer equipment includes processor and memory, the memory
In be stored with the computer program that can be run on a processor, the computer program is realized such as when being executed by the processor
The described in any item methods of claim 1 to 7.
17. a kind of computer readable storage medium, which is characterized in that being stored in the computer readable storage medium can locate
Computer program, the computer program run on reason device is realized as described in any one of claim 1 to 7 when executed
Method.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141639 | 2019-02-26 | ||
| CN2019101416394 | 2019-02-26 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110442695A true CN110442695A (en) | 2019-11-12 |
| CN110442695B CN110442695B (en) | 2022-03-01 |
Family
ID=68432840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910706857.8A Active CN110442695B (en) | 2019-02-26 | 2019-08-01 | Intelligent interaction platform training method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110442695B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124866A (en) * | 2019-12-26 | 2020-05-08 | 北京蓦然认知科技有限公司 | Voice interaction method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010140160A2 (en) * | 2009-06-05 | 2010-12-09 | Hewlett-Packard Development Company, L. P. | System and method for representing user interaction with a web service |
| US20170098180A1 (en) * | 2015-10-05 | 2017-04-06 | Yahoo! Inc. | Method and system for automatically generating and completing a task |
| CN107315737A (en) * | 2017-07-04 | 2017-11-03 | 北京奇艺世纪科技有限公司 | A kind of semantic logic processing method and system |
| CN107463601A (en) * | 2017-06-13 | 2017-12-12 | 北京百度网讯科技有限公司 | Dialogue based on artificial intelligence understands system constituting method, device, equipment and computer-readable recording medium |
| CN108897867A (en) * | 2018-06-29 | 2018-11-27 | 北京百度网讯科技有限公司 | For the data processing method of knowledge question, device, server and medium |
-
2019
- 2019-08-01 CN CN201910706857.8A patent/CN110442695B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010140160A2 (en) * | 2009-06-05 | 2010-12-09 | Hewlett-Packard Development Company, L. P. | System and method for representing user interaction with a web service |
| US20170098180A1 (en) * | 2015-10-05 | 2017-04-06 | Yahoo! Inc. | Method and system for automatically generating and completing a task |
| CN107463601A (en) * | 2017-06-13 | 2017-12-12 | 北京百度网讯科技有限公司 | Dialogue based on artificial intelligence understands system constituting method, device, equipment and computer-readable recording medium |
| CN107315737A (en) * | 2017-07-04 | 2017-11-03 | 北京奇艺世纪科技有限公司 | A kind of semantic logic processing method and system |
| CN108897867A (en) * | 2018-06-29 | 2018-11-27 | 北京百度网讯科技有限公司 | For the data processing method of knowledge question, device, server and medium |
Non-Patent Citations (1)
| Title |
|---|
| 匿名: "《5步创建自定义技能》", 《HTTPS://DOC-BOT.TMALL.COM/DOCS/DOC.HTM?SPM=0.7629140.0.0.4A3A1780D0H0TF&TREEID=393&ARTICLEID=106714&DOCTYPE=1》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124866A (en) * | 2019-12-26 | 2020-05-08 | 北京蓦然认知科技有限公司 | Voice interaction method and device |
| CN111124866B (en) * | 2019-12-26 | 2023-12-08 | 光禹莱特数字科技(上海)有限公司 | Voice interaction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110442695B (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9971766B2 (en) | Conversational agent | |
| RU2745632C1 (en) | Automated response server device, terminal device, response system, response method and program | |
| US20210173834A1 (en) | Method and system for capturing and exploiting user intent in a conversational interaction based information retrieval system | |
| CN105448292B (en) | A kind of time Speech Recognition System and method based on scene | |
| CN106776936A (en) | intelligent interactive method and system | |
| TW201832104A (en) | Natural language question answering method and apparatus, and server | |
| CN110110321A (en) | Products Show method, apparatus, equipment and storage medium based on voice data | |
| CN102099803A (en) | Method and computer system for automatically answering natural language questions | |
| US20170343365A1 (en) | Method for dynamic creation of customized tour guides | |
| CN103377652A (en) | Method, device and equipment for carrying out voice recognition | |
| CN107180029A (en) | A kind of information processing method and device based on consultation service | |
| US20220136840A1 (en) | Method for dynamic creation of customized tour guides | |
| CN110879837B (en) | Information processing method and device | |
| CN109684455A (en) | The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing | |
| CN109977216A (en) | Dialogue recommended method and system based on scene | |
| CN107705131A (en) | Public transport method of payment, device and public transport payment system | |
| CN113468300B (en) | Intelligent message processing system and method based on WeChat interaction | |
| CN110460654A (en) | The method for down loading and device of interactive engine in a kind of intelligent interaction platform | |
| CN113868252A (en) | Database mode matching method and device and SQL query statement generation method | |
| CN110275948A (en) | Free jump method, device and the medium of Self-Service | |
| CN108021556A (en) | For obtaining the method and device of information | |
| CN110442695A (en) | A kind of intelligent interaction platform training method, apparatus, equipment | |
| CN113132214B (en) | Dialogue method, dialogue device, dialogue server and dialogue storage medium | |
| CN110442694A (en) | A kind of intelligent interaction platform training method, apparatus, equipment | |
| CN105389309A (en) | Music regulation system driven by emotional semantic recognition based on cloud fusion |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211231 Address after: 310024 floor 5, zone 2, building 3, Hangzhou cloud computing Industrial Park, Zhuantang street, Xihu District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou suddenly Cognitive Technology Co.,Ltd. Address before: Room 401, gate 2, block a, Zhongguancun 768 Creative Industry Park, 5 Xueyuan Road, Haidian District, Beijing 100083 Applicant before: BEIJING MORAN COGNITIVE TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231016 Address after: Room 820, 8th floor, No. 390-408 Beijing East Road, Huangpu District, Shanghai, 200001 Patentee after: Guangyulaite Digital Technology (Shanghai) Co.,Ltd. Address before: 310024 floor 5, zone 2, building 3, Hangzhou cloud computing Industrial Park, Zhuantang street, Xihu District, Hangzhou City, Zhejiang Province Patentee before: Hangzhou suddenly Cognitive Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |