CN110516050A - A kind of construction method of the multipath Training scene of knowledge based map - Google Patents
A kind of construction method of the multipath Training scene of knowledge based map Download PDFInfo
- Publication number
- CN110516050A CN110516050A CN201910634606.3A CN201910634606A CN110516050A CN 110516050 A CN110516050 A CN 110516050A CN 201910634606 A CN201910634606 A CN 201910634606A CN 110516050 A CN110516050 A CN 110516050A
- Authority
- CN
- China
- Prior art keywords
- map
- scene
- training scene
- training
- art
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/046—Forward inferencing; Production systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a kind of construction methods of the multipath Training scene of knowledge based map to cover intention all in Training scene, and sorted out and be associated with link according to business model including establishing main knowledge mapping according to the intention motivation of words art problem；Each for being intended to map physically establish it is corresponding with this be intended to it is associated if art problem pair；The knowledge reasoning path of strong relationship and weak relationship, including semantic analysis and various knowledge reasoning models are established in each problem is to map；One or more Training scenes are generated according to selected condition, essential condition includes the link of Training scene, examination point keyword, problem to quantitative index.One of scene in Training scene that the present invention can allow user that ten million paths is selected to automatically generate is trained, and greatly improves the convenience of creation Training scene and the intelligence degree of scene.
Description
Technical field
The present invention relates to knowledge mapping technical fields, and in particular to a kind of multipath Training scene of knowledge based map
Construction method.
Background technique
Currently, also need manually to create Training scene by configuration flow for the man-machine Training scene set to white silk,
The single stiff, solidification of scene, intelligence degree is low, time-consuming and laborious, and is unable to satisfy the flexible and changeable creation Training scene of client
Real demand.
Summary of the invention
The object of the present invention is to provide a kind of construction method of the multipath Training scene of knowledge based map, the multipaths
It is man-machine to white silk, more convenient spirit that Training scene can allow user to be carried out according to some Training scene of mulitpath unrestricted choice
It is living.
To achieve the above object, the present invention provides following schemes:
A kind of construction method of the multipath Training scene of knowledge based map, comprising the following steps:
(1) the intention map for being intended to motivation based on words art is constructed；Main knowledge graph is established according to the intention motivation of words art problem
Spectrum, covers intention all in Training scene, and sorted out and be associated with link according to business model；
(2) building is intended to the problem of map upper layer to map；Be intended to map each physically establish it is corresponding with
This is intended to art problem pair if being associated；
(3) Construct question is to the strong relationship and weak relationship in map；Established in each problem is to map strong relationship and
The knowledge reasoning path of weak relationship, including semantic analysis and various knowledge reasoning models；
(4) judgment models of building multipath branch trend；One or more training places are generated according to selected condition
Scape, essential condition include the link of Training scene, examination point keyword, problem to quantitative index.
Further, further includes:
Construct the man-machine art library to experienced Training scene；By in sales process the problem of consumer, and it is quasi- for problem
Surely the standard words art replied, to form the man-machine art library to white silk；
Preferably, further includes:
Building words art process frame system；Art content classification will be talked about according to the business model of words art and link, and according to pin
The scene for being associated with building and forming man-machine training that logic is had in art will be talked about by selling process, form words art process frame system.Simultaneously
Also manager is facilitated integrally to manage words art content, art if art or modification and perfection have fallen behind if increasing and increasing newly.
The invention discloses a kind of construction methods of the multipath Training scene of knowledge based map, user can be allowed to select
One of scene in the Training scene that ten million paths automatically generate is trained, and greatly improves creation Training scene
Convenience and scene intelligence degree.
Compared with present technology, the present invention is had the effect that first, it can be achieved that automatically creating the training place of mulitpath
Scape, the Training scene of even 1,100 different training contents embody intelligence and flexibility that scene automatically creates.Second,
The Training scene that knowledge based map constructs automatically, the scene accuracy than manually creating is higher, especially complex relationship
Scene.Third, the Training scene of knowledge based map includes logic association relationship, problem and intention clear logic, well arranged,
Closer to actual services scene.
Detailed description of the invention
Fig. 1 is flow diagram of the present invention；
Fig. 2 is the structural schematic diagram of the intention map of the embodiment of the present invention；
Structural schematic diagram of the problem of Fig. 3 is the embodiment of the present invention to map；
Fig. 4 is the Training scene path profile of the embodiment of the present invention；
Specific embodiment
Below in conjunction with the attached drawing in case study on implementation of the present invention, the technical solution in case study on implementation of the present invention is carried out clear
Chu, complete description, it is clear that the embodiment described is only a part of the embodiment of the present invention, and is not whole embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment belongs to the range of protection of the invention.
The object of the present invention is to provide a kind of construction method of the multipath Training scene of knowledge based map, this method structures
The Training scene built, the one of scene in Training scene that can allow user that ten million paths is selected to automatically generate are instructed
Practice.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with attached drawing and specifically
Embodiment is described in further details the present invention.
Fig. 1 is the process signal of the embodiment of knowledge based map multipath Training scene construction method provided by the invention
Figure, as shown in Figure 1, the method includes:
Step 101: constructing the intention map for being intended to motivation based on words art；
Main knowledge mapping is established according to the intention motivation of words art problem, covers intention all in Training scene, then again
The pass between being intended to is established according to the method that intention is classified, and simulate effective sale promotion business by business model and link
Connection relationship eventually forms words art and is intended to map.
Step 102: building is intended to the problem of map upper layer to map；
Each for being intended to map physically establish it is corresponding with this be intended to it is associated if art problem pair, and by problem
To encoding, conveniently check that problem is intended to which is belonged to；
Step 103: Construct question is to the strong relationship and weak relationship in map；
Establish the knowledge reasoning path of strong relationship and weak relationship in each problem is to map, including semantic analysis and each
Kind knowledge reasoning model.
Wherein strong relationship refer to some problem be directed toward next problem path be it is determining, represented by arrow relationship
Strong reasoning from logic next node；The path that weak relationship refers to that some problem is directed toward next problem is uncertain
, need to further determine that by semantic analysis or other knowledge reasoning models direction next node where.
Step 104: the judgment models of building multipath branch trend；
One or more Training scenes are generated according to selected condition, essential condition includes the link of Training scene, examines
Epipole keyword, problem are to indexs such as quantity.
It should be noted that being intended to motivation refers to reason and power most direct when consumer's purchase and consumer lines, institute
To obtain and talk about what the problem of intention motivation of art is the consumer from sales process abstracted, then again according to sale process
The intention taken out is had to the associative combination of logic, finally formed intention map will be closer to actual sales process, together
When also achieve the purpose of the present invention.
Judgment models are moved towards in conjunction with multipath branch and infer one or more coordinates measurement Training scenes, are facilitated cleverer
Living establishes Training scene, by selecting the link of Training scene, the conditional filterings such as point keyword being examined to go out walking for different paths
To avoiding creation very simple or extremely complex various Training scenes for not meeting real demand, user can be allowed to select thousand
One of scene in Training scene that ten thousand paths generate, improves the intelligence of creation Training scene.
Fig. 2 is the structural schematic diagram of the intent of the present invention map, and the method includes the step 101- in above-described embodiment
102, it further comprises:
Semantic relation between building intention；Path trend between intention is determined by semantic relation, if grapheme
Some semantic relation in He Liao branch then enters the intention that semantic relation is directed toward, ultimately forms its in ten million paths
In a scenario path.
Fig. 3 is problem of the present invention to the structural schematic diagram of map, and the method includes the steps in above-mentioned first embodiment
103:
Construct question is to the strong relationship and weak relationship in map；The Construct question in map strong relationship and weak pass
System is the knowledge reasoning path that strong relationship and weak relationship are established in each problem is to map, including semantic analysis and various is known
Know inference pattern.
Fig. 4 is scenario path figure of the invention, and the method includes the steps 104 in above-mentioned first embodiment:
Construct the judgment models of multipath branch trend；The judgment models of the building multipath branch trend are bases
Selected condition generates one or more Training scenes, and essential condition includes the link of Training scene, examination point keyword, asks
Topic is to indexs such as quantity.Each paths have been built into a complete Training scene automatically.
Explanation is described to the principle of the present invention and embodiment herein, the statement of above embodiments is only intended to manage
Solve core of the invention thought；Meanwhile those of ordinary skill in the art are according to the thought of the present invention, in specific embodiment and answer
In place of it can be changed in range, but every other embodiment obtained without making creative work,
Belong to the range of protection of the invention.
Claims (3)
1. a kind of construction method of the multipath Training scene of knowledge based map, which comprises the following steps:
(1) the intention map for being intended to motivation based on words art is constructed；Main knowledge mapping is established according to the intention motivation of words art problem, is contained
All intentions in lid Training scene, and sorted out and be associated with link according to business model；
(2) building is intended to the problem of map upper layer to map；Be intended to map each physically establish it is corresponding with this meaning
Art problem pair if figure is associated；
(3) Construct question is to the strong relationship and weak relationship in map；Strong relationship and weak pass are established in each problem is to map
The knowledge reasoning path of system, including semantic analysis and various knowledge reasoning models；
(4) judgment models of building multipath branch trend；One or more Training scenes are generated according to selected condition, it is main
Wanting condition includes the link of Training scene, examination point keyword, problem to quantitative index.
2. a kind of construction method of the multipath Training scene of knowledge based map according to claim 1, feature exist
In, further includes:
Construct the man-machine art library to experienced Training scene；By in sales process the problem of consumer, and drafted back for problem
Art is talked about in multiple standard words art or outstanding recommendation, to form the man-machine art library to white silk.
3. a kind of construction method of the multipath Training scene of knowledge based map according to claim 1 or 2, feature
It is, further includes:
Building words art process frame system；Art intention motivation, which will be talked about, according to the business model of words art and link carries out abstract classification,
And the associative combination that logic is had in words art is formed to the scene of man-machine training according to sale process, form words art process frame body
System.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910634606.3A CN110516050A (en) | 2019-07-15 | 2019-07-15 | A kind of construction method of the multipath Training scene of knowledge based map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910634606.3A CN110516050A (en) | 2019-07-15 | 2019-07-15 | A kind of construction method of the multipath Training scene of knowledge based map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110516050A true CN110516050A (en) | 2019-11-29 |
Family
ID=68623207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910634606.3A Pending CN110516050A (en) | 2019-07-15 | 2019-07-15 | A kind of construction method of the multipath Training scene of knowledge based map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110516050A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309879A (en) * | 2020-01-20 | 2020-06-19 | 北京文思海辉金信软件有限公司 | Knowledge graph-based man-machine training scene construction method and device |
| CN111339278A (en) * | 2020-02-28 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for generating training speech generating model and method and device for generating answer speech |
| CN111552814A (en) * | 2020-03-26 | 2020-08-18 | 平安医疗健康管理股份有限公司 | Assessment scheme generation method and device based on assessment index map |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590216A (en) * | 2017-08-31 | 2018-01-16 | 北京百度网讯科技有限公司 | Answer preparation method, device and computer equipment |
| CN107589828A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN108415898A (en) * | 2018-01-19 | 2018-08-17 | 苏州思必驰信息科技有限公司 | The word figure of deep learning language model beats again a point method and system |
| CN108415932A (en) * | 2018-01-23 | 2018-08-17 | 苏州思必驰信息科技有限公司 | Interactive method and electronic equipment |
| CN108509519A (en) * | 2018-03-09 | 2018-09-07 | 北京邮电大学 | World knowledge collection of illustrative plates enhancing question and answer interactive system based on deep learning and method |
| CN109101624A (en) * | 2018-08-13 | 2018-12-28 | 腾讯科技（深圳）有限公司 | Dialog process method, apparatus, electronic equipment and storage medium |
| CN109635117A (en) * | 2018-12-26 | 2019-04-16 | 零犀(北京)科技有限公司 | A kind of knowledge based spectrum recognition user intention method and device |
-
2019
- 2019-07-15 CN CN201910634606.3A patent/CN110516050A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107589828A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN107590216A (en) * | 2017-08-31 | 2018-01-16 | 北京百度网讯科技有限公司 | Answer preparation method, device and computer equipment |
| CN108415898A (en) * | 2018-01-19 | 2018-08-17 | 苏州思必驰信息科技有限公司 | The word figure of deep learning language model beats again a point method and system |
| CN108415932A (en) * | 2018-01-23 | 2018-08-17 | 苏州思必驰信息科技有限公司 | Interactive method and electronic equipment |
| CN108509519A (en) * | 2018-03-09 | 2018-09-07 | 北京邮电大学 | World knowledge collection of illustrative plates enhancing question and answer interactive system based on deep learning and method |
| CN109101624A (en) * | 2018-08-13 | 2018-12-28 | 腾讯科技（深圳）有限公司 | Dialog process method, apparatus, electronic equipment and storage medium |
| CN109635117A (en) * | 2018-12-26 | 2019-04-16 | 零犀(北京)科技有限公司 | A kind of knowledge based spectrum recognition user intention method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309879A (en) * | 2020-01-20 | 2020-06-19 | 北京文思海辉金信软件有限公司 | Knowledge graph-based man-machine training scene construction method and device |
| CN111339278A (en) * | 2020-02-28 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for generating training speech generating model and method and device for generating answer speech |
| CN111552814A (en) * | 2020-03-26 | 2020-08-18 | 平安医疗健康管理股份有限公司 | Assessment scheme generation method and device based on assessment index map |
| CN111552814B (en) * | 2020-03-26 | 2023-02-03 | 深圳平安医疗健康科技服务有限公司 | Assessment scheme generation method and device based on assessment index map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112784092B (en) | Cross-modal image text retrieval method of hybrid fusion model | |
| CN110516050A (en) | A kind of construction method of the multipath Training scene of knowledge based map | |
| CN107067045A (en) | Data clustering method, device, computer-readable medium and electronic equipment | |
| CN110532996A (en) | The method of visual classification, the method for information processing and server | |
| CN111212303B (en) | Video recommendation method, server and computer-readable storage medium | |
| CN108427939A (en) | model generating method and device | |
| CN106951925A (en) | Data processing method, device, server and system | |
| CN106022568A (en) | Workflow processing method and apparatus | |
| CN106777971A (en) | A kind of intelligent hospital guide's method and its device | |
| CN107193962A (en) | A kind of intelligent figure method and device of internet promotion message | |
| CN109115237A (en) | A kind of position recommended method and server of riding | |
| CN110032623A (en) | The matching process and device of user's question sentence and knowledge dot leader | |
| CN108154198A (en) | Knowledge base entity normalizing method, system, terminal and computer readable storage medium | |
| CN106874296A (en) | A kind of style recognition methods of commodity and device | |
| CN109508420A (en) | A kind of cleaning method and device of knowledge mapping attribute | |
| CN114418035A (en) | Decision tree model generation method and data recommendation method based on decision tree model | |
| CN109086356A (en) | The incorrect link relationship diagnosis of extensive knowledge mapping and modification method | |
| CN106204297A (en) | A kind of recognition methods closing social propagation opinion leader and device | |
| CN108197203A (en) | A kind of shop front head figure selection method, device, server and storage medium | |
| CN110263332A (en) | A kind of natural language Relation extraction method neural network based | |
| CN110782448A (en) | Rendered image evaluation method and device | |
| CN111639169A (en) | Man-machine interaction method and device, computer readable storage medium and electronic equipment | |
| CN108038131A (en) | Data Quality Analysis preprocess method and device, storage medium, terminal | |
| CN111046213B (en) | Knowledge base construction method based on image recognition | |
| CN116089645A (en) | Hierarchical style-based conditional text-e-commerce picture retrieval method and system |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 608, building 4, No. 299, Longcao Road, Xuhui District, Shanghai 200030 Applicant after: CLP Jinxin software (Shanghai) Co.,Ltd. Address before: Room 608, building 4, No. 299, Longcao Road, Xuhui District, Shanghai 200030 Applicant before: Shanghai Wensi Haihui Jinxin Software Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191129 |