CN105279145B - A kind of machine word justice engineering system - Google Patents
A kind of machine word justice engineering system Download PDFInfo
- Publication number
- CN105279145B CN105279145B CN201410227079.1A CN201410227079A CN105279145B CN 105279145 B CN105279145 B CN 105279145B CN 201410227079 A CN201410227079 A CN 201410227079A CN 105279145 B CN105279145 B CN 105279145B
- Authority
- CN
- China
- Prior art keywords
- semantic
- computer
- engine
- model
- word
- 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.)
- Active
Links
Abstract
The invention discloses a kind of machine word justice engineering system, it is characterised in that：It includes a computer according to external input information, the system that application project method is created, accumulated, management and self-perfection computer are semantic.Here " semanteme " is the concept of a broad sense, refers to any semanteme of computer itself definition.In order to solve the problems, such as CNLU, semantic engineering system simulation human cognitive structure and process, use class language model to establish semantic model for computer, realize that computer " semanteme " approaches to human language is semantic.Semantic engineering system includes dynamic semantics voluminous dictionary, Semantic mapping engine, digital brain（Cyber Brain）, semantic model storehouse and its modeling tool, the subsystem such as semantic study engine, semantic applications engine development environment and regular maintenance tool.Semantic mapping engine, digital brain, semantic study engine, semantic model storehouse, the complete closed loop of dynamic semantics voluminous dictionary one semantic engineering self study process of formation.
Description
Technical field
The invention belongs to computer natural language understanding field, and in particular to a kind of innovation and the base of new theory and method
Created in the application system of the new theory and method.
Background technology
In a computer in literary natural language understanding field, the research for semanteme is often referred to as " semantics recognition " or " language
Reason and good sense solution ", without crying " semantic engineering ".Because it must be semanteme in human language that " semanteme " here, which refers to, it is by the mankind in life
Created in work, computer only " identifies " and the part of " understanding "." semanteme " in the semantic engineering system of the present patent application protection
Refer to must be computer oneself definition semanteme." engineering " in semantic engineering system refer to must be computer application engineering method from
Oneself creates, accumulates, manages, safeguards and improved its semantic system.In short, Study on Semantic in the industry is to allow computer passively to go
Understand the semanteme of the mankind, and the semantic engineering of the present invention is to allow computer to create and safeguard on one's own initiative the semanteme of itself.
The content of the invention
In fact, all computer programs that the mankind write can be regarded as a kind of simple semantic system of computer
System.Its semantic model is embodied in the rule that computer program code implies, and semantic instance is stored in various program variables
Or in database data, its semantic applications engine is exactly the function of program in itself and the power function that can be called.Require emphasis
It is that for computer program, either semantic model, semantic instance, or semantic applications engine is all that programmer inputs calculating
Machine is simultaneously solidificated among computer, and computer simply mechanically, is passively made a response by formula.Artificial intelligence system and meter
The maximum difference of calculation machine program is the semanteme of computer and semantic applications engine may all be created by computer oneself and perfect.
But the method that most of traditional artificial intelligence studies have still continued to use programmer's programming, do not distinguish semantic establishment and language
Adopted application engine creates, but close coupling they are write in a program.So conventional artificial intelligence system is extremely multiple
It is miscellaneous, and poor universality.
The primary innovation of the present patent application protection is exactly that the semantic system in artificial intelligence study is decomposed into semantic establishment
System and semantic applications engine create system.Just as the mankind can be learning knowledge and learning skill separately.The two can be with
Make a breakthrough respectively.The semantic engineering system of the present invention mainly completes computer oneself and creates semantic part, and establishment
Open development environment is made in the part of semantic applications engine, is created for third party programmer.As to how allow computer certainly
Oneself, which creates semantic applications engine, will apply for that other patent of invention gives disclosure.
When building the semantic model of machine word justice engineering system, I had once attempted many mathematics existing in the industry and built
Mould method, including based on ontological OWL modeling methods, but it is all undesirable.Reason is that neither one mathematical modeling can be with
Meet the completeness of Turing machine, i.e.,：It can allow computer simulation arbitrarily complicated phenomenon in the world.Knowledge based on mathematical algorithm
Model can only be applicable in a small range in specific field, once the complicated social phenomenon in face of big data will fail.Anti-
I found that, only the natural language of the mankind can describe arbitrarily complicated social phenomenon in multiple trial.Nationality, a portion in the world
Fall, no matter how fall behind, or even understand mathematics not at all, still, their langue is all perfect, and people never feel
It can not be linked up because of the defects of language.Importantly, the rule of language --- grammer, to be easily mastered than mathematical algorithm
It is more.
The Section 2 important innovations of the present patent application protection are to replace mathematical algorithm model with natural language descriptive model
To build the semantic model of semantic engineering system, strengthen the universality of semantic engineering system with this.Filled when building semantic structure
Divide and absorb the ancient philosophy of China《The book of Changes》Thought, including：Dynamic and quiet, cloudy and positive, digital symbol, time sequence, space sequence, cycle
Rule and holographic law etc..Meanwhile using natural language sentence as semantic formula, using grammar for natural language as semantic mould
The description rule of type（The SQL of the similar database of effect）.
" semanteme " of computer is the concept of a broad sense, is not necessarily the semanteme of human language.We can allow semanteme
Engineering system develops special semantic applications engine for any specific ken construction computer special " semanteme ".
This is also the method that many artificial intelligence systems use at present.The defects of this method is no versatility.The present invention is in order to increase
The versatility of strong system and the ability for handling complicated big data, the descriptive model for employing natural language are semantic as computer
Model.So machine word justice engineering system of the invention is particularly suitable for the research of CNLU.For up to this mesh
Mark, the Section 3 innovation of the present patent application protection are to allow the cognitive process of the computer simulation mankind, are created with computer itself
" semanteme " goes to approach the semanteme that the mankind create in life, so as to realize " semantic understanding " of Chinese natural language.
The research of many computer Chinese natural language understandings of current industry abandons original research for imitating human thinking
Method, then the statistical method expected on a large scale is used, thus " Chinese information processing " can only study at last, i.e.,：From real
Some useful information are refined in Chinese text information, do not reach the degree of semantic understanding much.And the semantic engineering of the present invention
System is expected to approach the original target of Chinese natural language semantic understanding research.
The content of the invention
The invention provides a kind of machine word justice engineering system, it is mainly used in grinding for Chinese natural language semantic understanding
Study carefully, can simultaneously serve as the basic technology solution of all kinds of Computerized intelligent applications.
The machine word justice engineering system of the present invention, it is characterised in that：It includes a computer and believed according to outside input
Breath, the system that application project method is created, accumulated, management and self-perfection computer are semantic.Here the concept of " semanteme " does not refer to
It has often been said that human language semanteme, and refer to computer itself definition, semanteme that machine is appreciated that.Computer understanding
Scope include its perception scope add its all semantic applications engine function set.
This semantic engineering system, is further characterized in that：In order to allow " semanteme " and Human Natural Language caused by computer
" semanteme " method for adopting computer recognition structural simulation human cognitive structure close proximity to the realization of, the system, i.e.,：With
Natural language model is computer constructing semantic model instead of mathematical modeling, and the description language of computer semantic model is exactly people
Natural language, the rule of computer semanteme Model description language is exactly the grammer of Human Natural Language.Wherein,
It is the semantic process of computer and one according to this mapping that " cognitive structure ", which includes one to input information MAP,
Relation and a series of processes for understanding rule and making behavior response.
The overall framework of the principle of the semantic engineering system and each subsystem is referring to accompanying drawing one.It includes the big diction of dynamic semantics
Allusion quotation, Semantic mapping engine, digital brain（Cyber Brain）, semantic model storehouse and its modeling tool, semantic study engine, language
Adopted application engine development environment and regular maintenance tool.Wherein,
Preferably, including：Dynamic semantics voluminous dictionary, semantic model, digital brain（Cyber Brain）, Semantic mapping draws
Hold up, semanteme learns engine and semantic applications engine development environment.
Dynamic semantics voluminous dictionary is the basis of semantics recognition, is with the main distinction of conditional electronic dictionary：Traditional dictionary
In the comment section of each word be often one section of word manually entered by language specialist, be changeless；And dynamic semantics
The comment section of each word is by enriching constantly and improving and dynamic change according to semantic model storehouse and digital brain in voluminous dictionary.
Semantic model simulates human knowledge structure, and it absorbs the ancient philosophy of China《The book of Changes》Structuring, digitlization, it is dynamic with
The idea about modeling of quiet combination, construct the computer semantic structure of uniqueness.The main distinction of it and other semantic models in the industry is：
Traditional semantic model is all certain mathematical algorithm model, including ontology model most fiery now；And the language of semantic engineering system
For adopted model using speech like sound descriptive model, mathematics is the reasoning tool of this model.
Digital brain（Cyber Brain）Storage and management semantic instance, the difference with all kinds of knowledge bases or database exist
In：The storage organization of traditional knowledge storehouse or database is fixed, and its storing process is that data in storehouse or knowledge quantity are increasing
Subtract；And the storage organization of digital brain is dynamically excellent by the needs stored according to semantic instance and the semantic feedback for learning engine
Change.So it is not " storehouse ", but " brain ".
Semantic mapping engine completes semantics recognition and mapping process, is the basic module of semantic engineering system, it is determined
Can Chinese natural language text message successfully be converted into the semantic instance in semantic engineering system number brain.
Semanteme study engine performs semantic engineering, and complete semantic instance is refined from the fragmentation semantic instance of magnanimity,
New semantic model is created, constantly substantial semantic model storehouse and the storage organization for improving digital brain.It is semantic engineering system
Move towards practical key modules.
Semantic applications engine development environment will cash all semantic values of computer establishment.It is with other artificial intelligence
The main distinction of the similar module of system is：Other artificial intelligence systems often only provide a tool for a set of knowledge model
The semantic applications engine of body, complete certain particular kind of behavior；Semantic engineering system can be in a set of semantic model by difference
The set of semantics of granularity designs different semantic applications engines, and minimum granularity can be a semantic member.Therefore, it is semantic
The establishment of semantic applications engine is designed as an open system by engineering system, i.e.,：Semantic applications engine development environment, for the 3rd
Fang Liyong numbers brain develops a variety of semantic applications engines, realizes the maximization of the semantic value of semantic engineering system.
Fig. 1 is the principle framework figure of machine word justice engineering system.(reference explanation book accompanying drawing)
" semanteme " of computer is the concept of a broad sense, is not necessarily the semanteme of human language.But it is possible to allow calculating
Machine approaches the highest goal that the semantic understanding of human language is the present invention.So next with Chinese natural language semantic understanding
Exemplified by, illustrate machine word justice engineering system of the present invention realizes logic.
1）The big data operation object that the semantic engineering system of the present invention is directed to is the true Chinese text of internet mass.
System is inputted using article as set of semantics, and in article is a complete semantic member per a word, represents some semantic model
In a fragment.One article refers at least to a semantic model, is usually directed to many semantic models.System input is once located
Reason a word, i.e.,：Continual character string between sentence punctuation mark.What uninterrupted character string initially entered is that Semantic mapping is drawn
Hold up.The engine calling dynamic semantics voluminous dictionary carries out cutting word to the character string of input, and according to dynamic semantics voluminous dictionary to each
The annotation of individual word（I.e.：Usage of the word in various known semantic models）Disambiguation, semantic feature are carried out to the word being syncopated as
Mark, and identify all semantic formulas in every a word.
2）Each semantic formula correspond to one or more semantic models behind.Semantic mapping engine is according to identification
The semantic formula gone out derives the example of the semantic model that call or semantic model.If these semantic models or semanteme
The example of model was defined in semantic model storehouse or was instantiated in digital brain, then Semantic mapping engine will be it
Directly recall；If some of which semantic model is not present in systems, Semantic mapping engine will be from semantic formula
Obtain semantic model information（Because natural language is the description language of semantic model）, and created according to based on semantic formula
The new semantic model of the rule creation of semantic model.
For example, in short mention an enterprise for being referred to as " Huawei ".According to dynamic semantics voluminous dictionary, Semantic mapping engine is known
Road Huawei is an enterprise, and it can look at the semantic instance either with or without ready-made enterprise of Huawei into digital brain first, if
Have and just recall；If not provided, remove the general semantics model of enterprise in semantic model storehouse of arriving；If even common enterprise is semantic
Model does not all have, and will create an enterprise semantic model according to the semantic formula of the words（Fragment）.
3）The semantic model being transferred out is mere skeleton, and the sentence that Semantic mapping engine is being handled includes real world
Specifying information.Real information in the words can be filled into semantic model by Semantic mapping engine, and semantic model is become
One semantic instance based on the model, i.e.,：Complete a Semantic mapping.If what is be transferred out is language existing in digital brain
Adopted example, Semantic mapping engine will add to the fresh information that the sentence handled includes in the semantic instance being transferred out.
The output of Semantic mapping engine is that semantic instance is stored in digital brain.
For example, a general corporate model includes organizational structure, business model, product composition, management state etc..This
Individual model is applied to many enterprises.After the filling of the information of Huawei is entered, the model has reformed into an enterprise of description Huawei
The specific semantic instance of industry.In short often it is only referred to Huawei in a certain respect（So referred to as fragment）, Semantic mapping engine
Incomplete Huawei's enterprise semantic model will be instantiated by once encountering the sentence of Huawei, and be stored in digital brain.After
Every sentence for encountering Huawei, Semantic mapping engine all can again recall the semantic instance of Huawei from digital brain, new
Information supplement enter, formed a bigger semantic instance on Huawei（Fragment）, then it is restored again into digital brain.
4）Digital brain is the module of special access and management semantic instance.Its input is the output of Semantic mapping engine
Semantic instance fragment；Its output and output of the semantic engineering system to semantic applications engine, it is mainly more completely semantic
Example.The characteristics of its is maximum is enriching constantly with semantic instance, particularly describes the increase of dimension, the storage of digital brain
Structure can make corresponding adjustment, to keep optimal storage performance.This is the ability that conventional database systems do not possess.
5）Semanteme study engine is the functional module for performing semantic engineering.Its input is the semantic instance in digital brain
Fragment, output are more complete semantic instance and the neology model extracted.The learning rules storehouse of the engine simulates the mankind
Most of learning methods, such as：Parse, conclude, be comprehensive, abstract, inherit, associate, comparing, judging etc..It is regular according to these,
Semanteme study engine is arranged the semantic instance fragment in digital brain repeatedly, progressively restores complete semantic instance,
It is stored back into digital brain.At the same time, the part of general character and regular part are extracted, as the improved suggestion of semantic model
It is output to semantic model storehouse.
6）Semantic model storehouse is establishment and the module for safeguarding semantic engineering system Knowledge framework, is the soul institute of whole system
.It is absorbed《The book of Changes》Structuring, the design concept for digitizing, being association of activity and inertia, mathematical modeling is replaced using class language model
Semantic model is established, using description instrument of the natural language as semantic model.Initial " seed " language in the semantic model storehouse
What adopted model was manually entered, constantly enrich, grow up under the cooperation of semantic study engine later.
7）Dynamic semantics voluminous dictionary is actually another form of expression in semantic model storehouse.Its each word exists
Mistake defined in semantic model storehouse, the comment section of each word is usage of the word in relevant semantic model.With semanteme
Model library is enriched constantly, is perfect, and dynamic semantics voluminous dictionary will dynamically update therewith, enrich and perfect.The big diction of dynamic semantics
The effect of allusion quotation is to provide word and the basis of word contrast for Semantic mapping engine, provides foundation for the disambiguation of semantic formula, be
That group semantic model of the Semantic mapping engine calling or semantic instance are given a clue.
This is arrived, the semantic study engine à semantic models storehouse à dynamic semantics voluminous dictionaries of Semantic mapping engine à number brains à are formed
The complete closed loop of one semantic engineering self study process.
It is noted that in order to improve the scalability of system, each engine is equipped with can be with the rule of manual intervention
Then storehouse.That is, people is to control the function of each engine and performance by controlling the change of rule.
8）The complete semantic instance being stored in digital brain gives semantic applications engine using as exporting for semantic engineering system.
In order to adapt to different application fields, different application engines, semantic engineering of the invention are developed using different semantic instances
System design semantic applications engine development environments, smoothly carried for semantic applications engine using the semantic instance resource of digital brain
For support.
Will be disclosed in other patents of invention as the specifically semantic applications engine based on digital brain.
Embodiment
The mode of the specific implementation to the present invention and order are further described below.
1）The exploitation in semantic model storehouse is completed, and " seed " semantic model is manually entered into semantic model storehouse；
2）The exploitation of dynamic semantics voluminous dictionary is completed, and " seed " semantic model dynamic in semantic model storehouse is raw
Into " seed " semantic voluminous dictionary；
3）In order to increase versatility, it is referred to《Modern Chinese dictionary》To plan the content of above-mentioned two step, i.e.,：According to
《Modern Chinese dictionary》In the word included plan which " seed " semantic model be required for, the big diction of dynamic semantics of dynamic generation
Which semantic member is allusion quotation should possess, and cover how much vocabulary.
4）Complete the exploitation of digital brain.
5）The exploitation of Semantic mapping engine is completed, and selected real Chinese text debugs Semantic mapping as Sample Storehouse
Engine.Debugging process is mainly abundant and improves Semantic mapping rule base.
6）Complete the exploitation and debugging of semantic study engine.Debugging process is then abundant and perfect semantic study rule base.
7）The semantic engineering system of the present invention is run in real internet environment, makes to possess in digital brain enough
More complete semantic instance, meanwhile, make semantic model storehouse and dynamic semantics voluminous dictionary " growth " to practical scale.
8）Building for semantic applications engine development environment is completed, and digital brain can be utilized to develop several semantic applications and drawn
Hold up, such as：Internet information automatic classification system, intelligent public sentiment monitoring system, intelligent supply-demand relationship matching system and
Theme of news deduction system etc..
Claims (6)
1. a kind of machine word justice engineering system, it includes a computer according to external input information, itself create, accumulation,
Management and the semantic system of self-perfection computer oneself, it is characterised in that：The machine word justice engineering system includes as follows
Subsystem：
1) dynamic semantics voluminous dictionary, basis is provided for semantics recognition；
2) Semantic mapping engine, semantics recognition and mapping process are completed；
3) digital brain (Cyber Brain), storage and management semantic instance；
4) semantic model storehouse and its modeling tool, human knowledge structure is simulated；
5) semantic study engine, performs semantic engineering, it is semantic to produce computer；
6) semantic applications engine development environment and regular maintenance tool, various differences are developed using digital brain for third party
Semantic applications engine.
A kind of 2. machine word justice engineering system according to claim 1, it is characterised in that：Above-mentioned each subsystem collaboration fortune
Capable flow will form " Semantic mapping an engine → digital brain → semanteme study engine → things semantic model storehouse → dynamic
The complete closed loop of the semantic engineering self study process of semantic voluminous dictionary → Semantic mapping engine ", specifically,
1) under the support of dynamic semantics voluminous dictionary, the text message of input is converted into computer to manage Semantic mapping engine
The knowledge fragment of solution, is stored in digital brain；
2) semantic study engine obtains mass knowledge fragment from digital brain, is analyzed, learnt, and they are organized into more
Big fragment, until complete semantic knowledge model, is stored in semantic knowledge-base；
3) comment section of each word is exactly usage of the word in semantic model, therefore, semantic mould in dynamic semantics voluminous dictionary
Improving for type is more abundant by the comment section for making each word of dynamic semantics voluminous dictionary, so as to preferably instruct Semantic mapping engine
The plain text of input is converted into computer semantic knowledge.
A kind of 3. machine word justice engineering system according to claim 1, it is characterised in that：In order to allow caused by computer
" semanteme " of " semanteme " and Human Natural Language is close proximity to the realization of the system adopts the computer recognition structural simulation mankind
The cognitive approach of cognitive structure, i.e.,：It is computer constructing semantic model to replace mathematical modeling with natural language model, wherein,
It is the semantic process of computer and one according to this mapping relations and one that " cognitive structure ", which includes one to input information MAP,
Series understands that rule makes the process of behavior response, and the understanding rule of the semantic model has fully absorbed grammar for natural language
Rule, have and natural language identical knowledge description ability.
A kind of 4. machine word justice engineering system according to claim 1, it is characterised in that：The semantic model of the system is adopted
With the ancient philosophy of China《The book of Changes》The framework be association of activity and inertia replaces current the most frequently used ontology framework in the industry to carry out constructing semantic mould
Type, the semantic model is not only described static things, and be good at describing dynamic process, and ontology be only suitable for describing it is quiet
State things.
A kind of 5. machine word justice engineering system according to claim 1, it is characterised in that：The dynamic semantics of the system is big
The comment section of each word of dictionary by enriching constantly and improving and dynamic change according to things semantic model storehouse and digital brain,
It is changeless and the comment section of each word is one section of word manually entered by language specialist in traditional dictionary.
A kind of 6. machine word justice engineering system according to claim 1, it is characterised in that：The digital brain of the system
Storage organization dynamically optimizes the needs stored according to semantic instance and the semantic feedback for learning engine, i.e.,：Its storage
Process is also an optimization process in itself, and the storage organization of traditional knowledge storehouse or database is changeless, and it was stored
Journey is that data in storehouse or knowledge quantity are increasing and decreasing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410227079.1A CN105279145B (en) | 2014-05-27 | 2014-05-27 | A kind of machine word justice engineering system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410227079.1A CN105279145B (en) | 2014-05-27 | 2014-05-27 | A kind of machine word justice engineering system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105279145A CN105279145A (en) | 2016-01-27 |
| CN105279145B true CN105279145B (en) | 2018-01-09 |
Family
ID=55148175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410227079.1A Active CN105279145B (en) | 2014-05-27 | 2014-05-27 | A kind of machine word justice engineering system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105279145B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10606952B2 (en) * | 2016-06-24 | 2020-03-31 | Elemental Cognition Llc | Architecture and processes for computer learning and understanding |
| EP3475887B1 (en) | 2016-08-22 | 2023-07-19 | Oracle International Corporation | System and method for dynamic lineage tracking, reconstruction, and lifecycle management |
| CN109447251B (en) * | 2018-09-28 | 2021-09-24 | 电子科技大学 | Neural turing machine model with novel memory module and setting method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271448A (en) * | 2007-03-19 | 2008-09-24 | 株式会社东芝 | Chinese language fundamental noun phrase recognition, its regulation generating method and apparatus |
| CN102236645A (en) * | 2010-05-06 | 2011-11-09 | 上海五和际软件信息有限公司 | Semantic logic-based pseudo-natural language human-computer dialogue device |
| CN102681982A (en) * | 2012-03-15 | 2012-09-19 | 上海云叟网络科技有限公司 | Method for automatically recognizing semanteme of natural language sentences understood by computer |
| CN102789450A (en) * | 2012-07-12 | 2012-11-21 | 卢玉敏 | Definable semantic analysis system and method on basis of rules |
| CN103294770A (en) * | 2013-05-06 | 2013-09-11 | 清华大学 | Human-object interaction method based on tag recognition and natural language semantic analysis |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120101803A1 (en) * | 2007-11-14 | 2012-04-26 | Ivaylo Popov | Formalization of a natural language |
| US8615551B2 (en) * | 2009-09-08 | 2013-12-24 | Nokia Corporation | Method and apparatus for selective sharing of semantic information sets |
-
2014
- 2014-05-27 CN CN201410227079.1A patent/CN105279145B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271448A (en) * | 2007-03-19 | 2008-09-24 | 株式会社东芝 | Chinese language fundamental noun phrase recognition, its regulation generating method and apparatus |
| CN102236645A (en) * | 2010-05-06 | 2011-11-09 | 上海五和际软件信息有限公司 | Semantic logic-based pseudo-natural language human-computer dialogue device |
| CN102681982A (en) * | 2012-03-15 | 2012-09-19 | 上海云叟网络科技有限公司 | Method for automatically recognizing semanteme of natural language sentences understood by computer |
| CN102789450A (en) * | 2012-07-12 | 2012-11-21 | 卢玉敏 | Definable semantic analysis system and method on basis of rules |
| CN103294770A (en) * | 2013-05-06 | 2013-09-11 | 清华大学 | Human-object interaction method based on tag recognition and natural language semantic analysis |
Non-Patent Citations (3)
| Title |
|---|
| 一种基于知网的文档语义模型构建方法;许琦;《中国科技资源导刊》;20100728;第42卷(第4期);55-60 * |
| 基于类自然语言的管理问题立即方法研究;卢涛 等;《管理科学学报》;20030228;第6卷(第1期);摘要，第1，3节 * |
| 神经网络模拟实验与语言认知研究的互动;徐以中;《南京航空航天大学学报（社会科学版）》;20100315;第12卷(第1期);摘要，第一部分第1，2节，第三部分第1，3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105279145A (en) | 2016-01-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kendall et al. | Ontology engineering | |
| Casellas | Legal ontology engineering: Methodologies, modelling trends, and the ontology of professional judicial knowledge | |
| Malhotra et al. | Evolution of knowledge representation and retrieval techniques | |
| Johannessen | Artificial intelligence, automation and the future of competence at work | |
| CN105279145B (en) | A kind of machine word justice engineering system | |
| Saini et al. | Automated traceability for domain modelling decisions empowered by artificial intelligence | |
| Liddament | The computationalist paradigm in design research | |
| Rabin et al. | Methods and formal models of intelligent analysis of weakly structured data | |
| Chuprina et al. | Ontology based data access methods to teach students to transform traditional information systems and simplify decision making process | |
| Radinsky et al. | Learning causality from textual data | |
| Yin | Standard model of knowledge representation | |
| Veldhoen et al. | Can neural networks learn logical reasoning? | |
| Ningning | Proposing data warehouse and data mining in teaching management research | |
| CN115033705A (en) | Power grid regulation and control risk early warning information knowledge graph design method and system | |
| Settas et al. | Using ontologies to represent software project management antipatterns. | |
| Bruzzone et al. | Mind, machines and manufacturing: a philosophical essay on machining | |
| Lupea et al. | Formal concept analysis of a Romanian emotion lexicon | |
| Rocchi | Technology+ Culture | |
| Tanwar et al. | An Effective Knowledge base system Architecture and issues in representation techniques | |
| Zavuschak | The context analysis and the process of its formation | |
| Hakkarainen et al. | Choosing appropriate method guidelines for web-ontology building | |
| Li et al. | An Empirical Study on the Gender Differences for Self-Organized Entrepreneurial Behavior Based on Grounded Theory: A Case from Jiangsu, China | |
| Yiming et al. | Research on the Construction of Maritime Legal Knowledge Graph | |
| Koskensalo | The Influence of Medialization to Legal Discourse Concerning Context, Media and Social Power | |
| Jiang et al. | Representation and reasoning of empirical engineering knowledge |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180820 Address after: 210001 room 1202, Tong Fu Building, 501 Zhongshan South Road, Nanjing, Jiangsu. Patentee after: Jiangsu United Industrial Limited by Share Ltd Address before: 210006 Zhongshan South Road, Qinhuai District, Nanjing, Jiangsu Patentee before: Wang Nan |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180831 Address after: 210006 Room 1202 of Nanjings Qinhuai District 501 Patentee after: Jiangsu United Industrial Limited by Share Ltd Address before: 210006 Zhongshan South Road, Qinhuai District, Nanjing, Jiangsu Patentee before: Wang Nan |
|
| TR01 | Transfer of patent right |