CN112232082A - Multimode DIKW content multi-semantic analysis method for essential computing - Google Patents

Multimode DIKW content multi-semantic analysis method for essential computing Download PDF

Info

Publication number
CN112232082A
CN112232082A CN202011099503.0A CN202011099503A CN112232082A CN 112232082 A CN112232082 A CN 112232082A CN 202011099503 A CN202011099503 A CN 202011099503A CN 112232082 A CN112232082 A CN 112232082A
Authority
CN
China
Prior art keywords
dikw
resource
semantic
new
information
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
Application number
CN202011099503.0A
Other languages
Chinese (zh)
Other versions
CN112232082B (en
Inventor
段玉聪
胡时京
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hainan University
Original Assignee
Hainan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hainan University filed Critical Hainan University
Priority to CN202011099503.0A priority Critical patent/CN112232082B/en
Publication of CN112232082A publication Critical patent/CN112232082A/en
Application granted granted Critical
Publication of CN112232082B publication Critical patent/CN112232082B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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

Abstract

The invention provides a multimode DIKW content multi-semantic analysis method for essential computing, which comprises the following steps of: s1, obtaining type resources to carry out semantic recognition, and judging whether multiple semantics exist according to the recognition result, wherein the type resources comprise data resources DDIKWInformation resource IDIKWAnd knowledge resources KDIKW(ii) a S2, when multiple meanings exist, analyzing the reason for forming the multiple meanings; and S3, based on the reason of multi-semantic formation, converting the original type resource into a new type resource by adopting a corresponding strategy, and acquiring a final semantic recognition result. The invention can help the artificial intelligence system to improve the language text recognition efficiency and improve the accuracy of the recognition result.

Description

Multimode DIKW content multi-semantic analysis method for essential computing
Technical Field
The invention relates to the technical field of semantic analysis, in particular to an essential computing-oriented multi-modal DIKW content multi-semantic analysis method.
Background
At present, semantic recognition of natural language based on a DIKW atlas technology is a new technical development direction in related fields, semantic content is modeled based on a DIKW atlas, type Resources (type Resources) can be extracted from a language text for semantic recognition, and the type Resources can be divided into Data Resources (Data Resources), Information Resources (Information Resources) and Knowledge Resources (Knowledge Resources). While a multi-semantic problem may occur when semantic recognition is performed based on a DIKW atlas technique, the multi-semantic refers to understanding that semantic content has a plurality of different purposes, that is, type resources in the semantic content can be derived from various types of resources to obtain information resources with different purposes. The multi-semantic problem can cause the efficiency of recognizing the language text of the artificial intelligence system to be reduced and the accuracy of the recognition result to be reduced.
Disclosure of Invention
The present invention aims to provide a multimodal DIKW content multi-semantic analysis method oriented to essential computing, so as to overcome or at least partially solve the above problems in the prior art.
An essential computing-oriented multi-modal DIKW content multi-semantic analysis method comprises the following steps:
s1, obtaining type resources to carry out semantic recognition, and judging whether multiple semantics exist according to the recognition result, wherein the type resources comprise data resources DDIKWInformation resource IDIKWAnd knowledge resources KDIKW；
S2, when multiple meanings exist, analyzing the reason for forming the multiple meanings;
and S3, based on the reason of multi-semantic formation, converting the original type resource into a new type resource by adopting a corresponding strategy, and acquiring a final semantic recognition result.
Further, the multiple semantic formation reasons include type resource missing and type resource redundancy.
Further, in step S2, when the reason for forming multiple meanings is analyzed as the type resource missing, it is determined that the type resource missing attribute is data resource missing or information resource missing.
Further, in step S3, when the reason for forming multiple meanings is a type resource loss, the adopted strategy specifically includes:
known data resource D0And information resources I0With respect to KDIKWCombined to obtain new information resource I with different purposesnew1And Inew2；
Searching data resource D related to data chart in data chartrelated；
Will DrelatedTo related IDIKWAnd KDIKWCarrying out the combination to further obtainObtain new information resource Inew3；
Determination of Inew3And Inew1And Inew2By keeping the relationship of (I)new3Supported IDIKWDelete other IDIKW；
Will remain IDIKWAnd setting as a final semantic recognition result.
Further, in step S3, when the reason for forming multiple meanings is a type resource loss, the adopted strategy specifically includes:
known data resource D0And information resources I0With respect to KDIKWCombined to obtain new information resource I with different purposesnew1And Inew2；
Searching related information resources I related to information in information chartrelated；
Will IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew3；
Determination of Inew3And Inew1And Inew2By keeping the relationship of (I)new3Supported IDIKWDelete other IDIKW；
Will remain IDIKWAnd setting as a final semantic recognition result.
Further, in step S2, when the reason for forming multiple meanings is analyzed as the type resource redundancy, it is determined that the type resource redundancy attribute is data resource redundancy or information resource redundancy.
Further, in step S3, when the reason for forming multiple meanings is redundancy of information resources, the adopted policy specifically includes:
finding conflicting information resources I01And I02；
Searching data resource D related to data chart in data chartrelated；
Will DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
Determination of InewAnd I01And I02The association relationship between them is preserved InewThe supported semantic recognition result deletes other semantic recognition results;
will InewAnd setting the supported semantic recognition result as a final semantic recognition result.
Further, in step S3, when the reason for forming multiple meanings is redundancy of information resources, the adopted policy specifically includes:
finding conflicting information resources I01And I02；
Searching information source I related to information chartrelated；
Will IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
Determination of InewAnd I01And I02The association relationship between them is preserved InewThe supported semantic recognition result deletes other semantic recognition results;
will InewAnd setting the supported semantic recognition result as a final semantic recognition result.
Further, in step S3, when the reason for forming multiple meanings is data resource redundancy, the adopted policy specifically includes:
finding conflicting data resources D01And D02；
Searching data resource D related to data chart in data chartrelated；
Will DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Dnew；
Determination of DnewAnd D01And D02The association relationship between them, reserve DnewThe supported semantic recognition result deletes other semantic recognition results;
will DnewAnd setting the supported semantic recognition result as a final semantic recognition result.
Further, in step S3, when the reason for forming multiple meanings is data resource redundancy, the adopted policy specifically includes:
finding conflicting data resources D01And D02；
Searching related information resources I related to information in information chartrelated；
Will IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
Determination of InewAnd D01And D02The relation between, retention InewThe supported semantic recognition result deletes other semantic recognition results;
will InewAnd setting the supported result as a final semantic recognition result.
Compared with the prior art, the invention has the beneficial effects that:
according to the multimode DIKW content multi-semantic analysis method for essential computation, when a multi-semantic result appears in a semantic recognition process based on type resources, original type resources are converted into new type resources by analyzing multi-semantic forming reasons and adopting corresponding strategies according to different forming reasons to be applied to semantic recognition, redundant recognition results are eliminated, and a final semantic recognition result is obtained, so that an artificial intelligent system is helped to improve the language text recognition efficiency, and the recognition result accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive efforts.
Fig. 1 is a schematic overall flow chart of a multi-modal DIKW content multi-semantic analysis method according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, the illustrated embodiments are provided to illustrate the invention and not to limit the scope of the invention.
Referring to fig. 1, the present invention provides a multimodal DIKW contents multi-semantic analysis method oriented to essential computing, the method comprising the steps of:
s1, obtaining type resources to carry out semantic recognition, and judging whether multiple semantics exist according to the recognition result, wherein the type resources comprise data resources DDIKWInformation resource IDIKWAnd knowledge resources KDIKW。
Where a data resource is a discrete element resulting from direct observation, without context, having no meaning, and not being associated with some particular purpose of a human being. The data resource expresses the attribute content of a single entity, and the simplest expression is 'is _ a', and (X | a) expresses the attribute (a) of the entity X.
The information resource records human behaviors and is used for mining, analyzing and expressing the interaction relation between two entities, wherein the entities can be another person or things which exist objectively. The information resource is related to a specific purpose of a human being and is used for deducing the relationship between two entities through the purpose, and the simplest expression of the information resource is 'has _ a' and is used for representing the relationship between the entities E1 and E2.
The knowledge resources are obtained by deduction of data resources and information resources in a structured form, the entity relationship is further improved on the basis of the information resources, and the knowledge resources perform abstract induction summary on the entity relationship on the basis of the information resources.
S2, when multiple meanings exist, the reason for forming multiple meanings is analyzed.
And S3, based on the reason of multi-semantic formation, converting the original type resource into a new type resource by adopting a corresponding strategy, and acquiring a final semantic recognition result.
Wherein the multiple semantic formation reasons comprise type resource missing and type resource redundancy. Missing type resource TR in semantic contentDIKWResulting in a reduction in the limitation of the content understanding range. By adding contentUnderstanding restrictions, the scope of content understanding can be narrowed so that only one derivative I is reserved for different purposesDIKWAnd further solve the multi-semantic problem. The type resource missing includes data resource missing or information resource missing, so in step S2, when the analysis result indicates that the type resource missing is caused by multiple semantic formation, it needs to further determine that the type resource missing attribute is data resource missing or information resource missing.
In an embodiment of the present invention, when the reason for forming multiple meanings in step S3 is a type resource loss, the adopted strategy specifically includes:
a1, data resource D to be known0And information resources I0With respect to KDIKWCombined to obtain new information resource I with different purposesnew1And Inew2。
A2, searching the data chart for the data resource D related to the data chartrelated。
A3, DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew3。
A4, determination of Inew3And Inew1And Inew2By keeping the relationship of (I)new3Supported IDIKWDelete other IDIKW。
A5, and I remainingDIKWAnd setting as a final semantic recognition result.
As an example, assuming that the semantic content is "at night in summer, user a stays in the study room", the system may be ambiguous in understanding the content because the semantic content lacks the information resource of "what user a does in the study room". For example, data resource D01"user A stays in the study room" and knowledge resources K1In combination with "study room is the place of study", it can be inferred that the purpose of user a staying in the study room is to study. In conjunction with data resources D02Night and knowledge resources K2"people are sleeping often night," it can be inferred that user A may be sleeping in the study room. Both of these derivation methods are true in the absence of other related types of resourcesBut the purpose of the information resources they generate is different, leading to multiple meanings.
Obtaining related data resources D on the basis of the data resources D1'air conditioner in bedroom is broken' and D2"the air condition of study room is good", combine data resource D03Summer and knowledge resources K3"summer hot" can be inferred as the temperature in the bedroom is higher and the temperature in the study room is lower. These data resources increase the constraints on the study room environment, narrowing the scope of content understanding to the temperature-related domain. Combining knowledge resources K4"people like to sleep in a cool place", it can be concluded that the temperature of the study room is low, suitable for sleeping, and supports IDIKW"the user A stays asleep in the study room", thereby solving the multi-semantic problem.
In another embodiment of the present invention, when the reason for forming multiple meanings in step S3 is a type resource loss, the adopted strategy specifically includes:
b1, data resource D to be known0And information resources I0With respect to KDIKWCombined to obtain new information resource I with different purposesnew1And Inew2。
B2, searching related information resources I related to information in information chartrelated。
B3, mixing IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew3。
B4, determination of Inew3And Inew1And Inew2By keeping the relationship of (I)new3Supported IDIKWDelete other IDIKW。
B5, I remainingDIKWAnd setting as a final semantic recognition result.
The embodiment is used for solving the multi-semantic problem that the semantic content is 'at night in summer and user A stays in study room', and the related information resource I is obtained1"user A dislikes learning", in combination with D02Night and knowledge resources K5"people who like learning may be at nightInter-learning ", it can be inferred that user a is unlikely to learn in the study room at this time. This IDIKWExclude I fromDIKW"user A stays in the learning room for learning", and the only I leftDIKW"user a stays in the study room for sleep" is the final result, thus solving the multi-meaning problem.
Redundancy of type resources refers to D in semantic contentDIKWOr IDIKWAn understanding of the many different purposes arises on the same issue. The type resource redundancy includes data resource redundancy or information resource redundancy, and therefore, in step S2, when the reason for the multi-meaning formation is analyzed as the type resource redundancy, it is necessary to further determine that the type resource redundancy attribute is the data resource redundancy or the information resource redundancy.
In an embodiment of the present invention, when the reason for forming multiple meanings in step S3 is redundancy of information resources, the adopted policy specifically includes:
c1 finding conflicting information resources I01And I02。
C2, searching the data chart for the data resource D related to the data chartrelated。
C3, mixing DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew。
C4, determination of InewAnd I01And I02The association relationship between them is preserved InewAnd (4) deleting other semantic recognition results according to the supported semantic recognition results.
C5, mixing InewAnd setting the supported semantic recognition result as a final semantic recognition result.
As an example, when the semantic content is "user A likes playing basketball and user A does not like sports", resource I can be extracted01"user A likes playing basketball" and I02"the user A hates the sport", obtain knowledge resource K1"playing basketball is a sport", K2"relationship 'dislike' and relationship 'like' contradict", from I02"user A disagrees with sports" and K1"playing basketball belongs to a sportTo infer new information resources Inew1"user A hates playing basketball". Due to K2Knowing I01And Inew1Contradictory, therefore, for the question "attitude of user A to play basketball", I01And I02With different understanding, represent IDIKWRedundancy in semantic content.
When the embodiment is applied to solve the multi-meaning problem, the spatial data resource D related to the basketball court of the user A is obtained1. Having related knowledge resources K3"the main activities of the basketball court are playing basketball" and "people who play basketball regularly like playing basketball". Binding of D1And K3It can be deduced that user a is often present on a basketball court and thus user a is often playing basketball. Binding K4"user A plays basketball frequently, and people who play basketball frequently are likely to like basketball", which indicates that user A is likely to like basketball and supports I01. When information resource I01With support of DDIKWBut information resource I02Unsupported DDIKWWhen it is, it tends to judge I01Correct, I02And errors, thereby solving the multi-semantic problem.
In another embodiment of the present invention, when the reason for forming multiple meanings is redundancy of information resources in step S3, the adopted policy specifically includes:
d1 finding conflicting information resources I01And I02；
D2, searching the information chart for the information resource I related to the information chartrelated；
D3, mixing IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
D4, determination of InewAnd I01And I02The association relationship between them is preserved InewThe supported semantic recognition result deletes other semantic recognition results;
d5, mixing InewAnd setting the supported semantic recognition result as a final semantic recognition result.
This embodiment is used to address the aforementioned intra-semanticWhen the multi-meaning problem that the user A likes playing basketball and the user A does not like sports is solved, the related information resource I is obtained1"user A is a member of school basketball team", has related knowledge resources K5"members of the basketball team play basketball regularly". Binding of I1And K5It can be deduced that user a is a member of the school basketball team, so user a plays basketball often. Binding K4"user A plays basketball often, people who play basketball often probably like playing basketball", which means that user A probably likes playing basketball, supports information resource I01. When information resource I01With supported IDIKWBut information resource I02Unsupported IDIKWThe system tends to determine I01Is correct, I02Is erroneous.
In an embodiment of the present invention, when the reason for forming multiple meanings in step S3 is data resource redundancy, the adopted policy specifically includes:
e1 finding conflicting data resources D01And D02；
E2, search data D related to it in data chartrelated；
E3, mixing DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Dnew；
E4, determination of DnewAnd D01And D02The association relationship between them, reserve DnewThe supported semantic recognition result deletes other semantic recognition results;
e5, mixing DnewAnd setting the supported semantic recognition result as a final semantic recognition result.
As an example, when the semantic content contains a data resource D01"today's temperature is 30 degrees" and D02When the temperature of today is 20 degrees, aiming at the problem of the temperature of today, the data resource D01And D02Is contradictory, which indicates that in redundant data resource D01And D02There must be an error in between.
Application of the embodimentTo solve the multi-semantic problem of "today's temperature", data resource D is obtained1Summer and D2"Hainan", and knowledge resource K1"Hainan summer temperature is higher". Binding of D1、D2And K1It can be deduced that today's temperature should be high, supporting data resource D01. When data resource D01With support of DDIKWBut data resource D02Unsupported DDIKWThe system tends to judge D01Correct but D02And errors, thereby solving the multi-semantic problem.
In another embodiment of the present invention, in step S3, when the reason for forming multiple meanings is data resource redundancy, the adopted policy specifically includes:
f1 finding conflicting data resources D01And D02；
F2, searching related information resource I related to information in information chartrelated；
F3, mixing IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
F4, determination of InewAnd D01And D02The relation between, retention InewThe supported semantic recognition result deletes other semantic recognition results;
f5, mixing InewAnd setting the supported result as a final semantic recognition result.
When this embodiment is used to solve the aforementioned multi-semantic problem of "temperature today", information resource I is obtained1"data resource D01From the weather bureau' and information resources I2"data resource D02From the internet ", and knowledge resources K2"data from professional organizations is more reliable than data from the internet". In connection with information resources I1、I2And knowledge resources K2Data resources D can be derived01Ratio data resource D02And is more reliable. Thus, the system tends to determine D01Is true, D02Is wrong, thereby solvingA multi-lingual problem.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. An essential computing-oriented multi-modal DIKW content multi-semantic analysis method, characterized by comprising the following steps:
s1, obtaining type resources to carry out semantic recognition, and judging whether multiple semantics exist according to the recognition result, wherein the type resources comprise data resources DDIKWInformation resource IDIKWAnd knowledge resources KDIKW；
S2, when multiple meanings exist, analyzing the reason for forming the multiple meanings;
and S3, based on the reason of multi-semantic formation, converting the original type resource into a new type resource by adopting a corresponding strategy, and acquiring a final semantic recognition result.
2. The intrinsically computer-oriented multi-modal DIKW content multi-semantic analysis method of claim 1, wherein the multi-semantic formation reasons comprise type resource loss and type resource redundancy.
3. The method of claim 2, wherein in step S2, when the analysis result is type resource missing, the type resource missing attribute is determined to be data resource missing or information resource missing.
4. The intrinsically computer-oriented multi-modal DIKW content multi-semantic analysis method of claim 2 or 3, wherein in the step S3, when the multi-semantic forming reason is the type resource loss, the adopted strategy specifically comprises:
known data resource D0And information resources I0With respect to KDIKWCombined to obtain new information resource I with different purposesnew1And Inew2；
Searching data resource D related to data chart in data chartrelated；
Will DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew3；
Determination of Inew3And Inew1And Inew2By keeping the relationship of (I)new3Supported IDIKWDelete other IDIKW；
Will remain IDIKWAnd setting as a final semantic recognition result.
5. The intrinsically computer-oriented multi-modal DIKW content multi-semantic analysis method of claim 2 or 3, wherein in the step S3, when the multi-semantic forming reason is the type resource loss, the adopted strategy specifically comprises:
known data resource D0And information resources I0With respect to KDIKWCombined to obtain new information resource I with different purposesnew1And Inew2；
Searching related information resources I related to information in information chartrelated；
Will IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew3；
Determination of Inew3And Inew1And Inew2By keeping the relationship of (I)new3Supported IDIKWDelete other IDIKW；
Will remain IDIKWAnd setting as a final semantic recognition result.
6. The method of claim 2, wherein in step S2, when the reason for forming multiple semantics is type resource redundancy, the type resource redundancy attribute is determined as data resource redundancy or information resource redundancy.
7. The method of claim 6, wherein in step S3, when the reason for multi-semantic formation is redundancy of information resources, the adopted strategy specifically includes:
finding conflicting information resources I01And I02；
Searching data resource D related to data chart in data chartrelated；
Will DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
Determination of InewAnd I01And I02The association relationship between them is preserved InewThe supported semantic recognition result deletes other semantic recognition results;
will InewAnd setting the supported semantic recognition result as a final semantic recognition result.
8. The method of claim 6, wherein in step S3, when the reason for multi-semantic formation is redundancy of information resources, the adopted strategy specifically includes:
finding conflicting information resources I01And I02；
Searching information source I related to information chartrelated；
Will IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
Determination of InewAnd I01And I02The association relationship between them is preserved InewThe supported semantic recognition result deletes other semantic recognition results;
will InewAnd setting the supported semantic recognition result as a final semantic recognition result.
9. The method of claim 6, wherein in step S3, when the reason for multi-semantic formation is data resource redundancy, the strategy adopted in the method specifically includes:
finding conflicting data resources D01And D02；
Searching data resource D related to data chart in data chartrelated；
Will DrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Dnew；
Determination of DnewAnd D01And D02The association relationship between them, reserve DnewThe supported semantic recognition result deletes other semantic recognition results;
will DnewAnd setting the supported semantic recognition result as a final semantic recognition result.
10. The method of claim 6, wherein in step S3, when the reason for multi-semantic formation is data resource redundancy, the strategy adopted in the method specifically includes:
finding conflicting data resources D01And D02；
Searching related information resources I related to information in information chartrelated；
Will IrelatedTo related IDIKWAnd KDIKWCombining to further obtain new information resource Inew；
Determination of InewAnd D01And D02The relation between, retention InewThe supported semantic recognition result deletes other semantic recognition results;
will InewAnd setting the supported result as a final semantic recognition result.
CN202011099503.0A 2020-10-14 2020-10-14 Multimode DIKW content multi-semantic analysis method for essential computing Active CN112232082B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011099503.0A CN112232082B (en) 2020-10-14 2020-10-14 Multimode DIKW content multi-semantic analysis method for essential computing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011099503.0A CN112232082B (en) 2020-10-14 2020-10-14 Multimode DIKW content multi-semantic analysis method for essential computing

Publications (2)

Publication Number Publication Date
CN112232082A true CN112232082A (en) 2021-01-15
CN112232082B CN112232082B (en) 2022-02-18

Family

ID=74113023

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011099503.0A Active CN112232082B (en) 2020-10-14 2020-10-14 Multimode DIKW content multi-semantic analysis method for essential computing

Country Status (1)

Country Link
CN (1) CN112232082B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112949321A (en) * 2021-04-21 2021-06-11 海南大学 DIKW model construction method and device oriented to intention calculation and reasoning
CN113032832A (en) * 2021-04-09 2021-06-25 海南大学 Group difference privacy protection method and device of intention-driven DIKW system
CN113538179A (en) * 2021-06-11 2021-10-22 海南大学 DIKW-based intelligent patent application method and system
CN113609307A (en) * 2021-08-09 2021-11-05 海南大学 Method, device, storage medium and electronic equipment for updating DIKW map
WO2023029178A1 (en) * 2021-08-30 2023-03-09 海南大学 Dikw resource-oriented emotional expression mapping, measurement and optimized transmission system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7249117B2 (en) * 2002-05-22 2007-07-24 Estes Timothy W Knowledge discovery agent system and method
CN102289430A (en) * 2011-06-29 2011-12-21 北京交通大学 Method for analyzing latent semantics of fusion probability of multi-modality data
CN103177075A (en) * 2011-12-30 2013-06-26 微软公司 Knowledge-based entity detection and disambiguation
CN105631032A (en) * 2015-12-31 2016-06-01 上海智臻智能网络科技股份有限公司 Method, device and system for establishing question and answer knowledge base based on abstract semantic recommendation
CN106970909A (en) * 2016-01-14 2017-07-21 芋头科技（杭州）有限公司 A kind of semantic semantic analysis of Secondary Match
CN107038261A (en) * 2017-05-28 2017-08-11 海南大学 A kind of processing framework resource based on data collection of illustrative plates, Information Atlas and knowledge mapping can Dynamic and Abstract Semantic Modeling Method
WO2018055646A1 (en) * 2016-09-22 2018-03-29 Dogma Srl. Method and system for searching, publishing and managing the life cycle of multimedia contents related to public events and the user experience
CN111046190A (en) * 2019-11-28 2020-04-21 佰聆数据股份有限公司 Semantic graph-based big data label conflict detection method and system, storage medium and computer equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7249117B2 (en) * 2002-05-22 2007-07-24 Estes Timothy W Knowledge discovery agent system and method
CN102289430A (en) * 2011-06-29 2011-12-21 北京交通大学 Method for analyzing latent semantics of fusion probability of multi-modality data
CN103177075A (en) * 2011-12-30 2013-06-26 微软公司 Knowledge-based entity detection and disambiguation
CN105631032A (en) * 2015-12-31 2016-06-01 上海智臻智能网络科技股份有限公司 Method, device and system for establishing question and answer knowledge base based on abstract semantic recommendation
CN106970909A (en) * 2016-01-14 2017-07-21 芋头科技（杭州）有限公司 A kind of semantic semantic analysis of Secondary Match
WO2018055646A1 (en) * 2016-09-22 2018-03-29 Dogma Srl. Method and system for searching, publishing and managing the life cycle of multimedia contents related to public events and the user experience
CN107038261A (en) * 2017-05-28 2017-08-11 海南大学 A kind of processing framework resource based on data collection of illustrative plates, Information Atlas and knowledge mapping can Dynamic and Abstract Semantic Modeling Method
CN111046190A (en) * 2019-11-28 2020-04-21 佰聆数据股份有限公司 Semantic graph-based big data label conflict detection method and system, storage medium and computer equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
雷羽潇；段玉聪: "基于DIKW图谱的虚拟社区用户性格分类与转换方法", 《应用科学学报》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113032832A (en) * 2021-04-09 2021-06-25 海南大学 Group difference privacy protection method and device of intention-driven DIKW system
CN113032832B (en) * 2021-04-09 2022-02-08 海南大学 Group difference privacy protection method and device of intention-driven DIKW system
CN112949321A (en) * 2021-04-21 2021-06-11 海南大学 DIKW model construction method and device oriented to intention calculation and reasoning
CN112949321B (en) * 2021-04-21 2022-04-01 海南大学 DIKW model construction method and device oriented to intention calculation and reasoning
CN113538179A (en) * 2021-06-11 2021-10-22 海南大学 DIKW-based intelligent patent application method and system
CN113609307A (en) * 2021-08-09 2021-11-05 海南大学 Method, device, storage medium and electronic equipment for updating DIKW map
CN113609307B (en) * 2021-08-09 2023-10-20 海南大学 Method and device for updating DIKW map, storage medium and electronic equipment
WO2023029178A1 (en) * 2021-08-30 2023-03-09 海南大学 Dikw resource-oriented emotional expression mapping, measurement and optimized transmission system

Also Published As

Publication number Publication date
CN112232082B (en) 2022-02-18

Similar Documents

Publication Publication Date Title
CN112232082B (en) Multimode DIKW content multi-semantic analysis method for essential computing
Garfield et al. Why do we need algorithmic historiography?
CN103631852B (en) Method and system of context-based graph-relational intersect derived database
Belfin et al. A graph based chatbot for cancer patients
US8676857B1 (en) Context-based search for a data store related to a graph node
Pilehvar et al. A large-scale pseudoword-based evaluation framework for state-of-the-art word sense disambiguation
US9418138B2 (en) Method and system for determining sets of variant items
US20090182723A1 (en) Ranking search results using author extraction
WO2022078145A1 (en) Cross-dikw modal text ambiguity processing method for essential calculation and reasoning
CN107301227A (en) Search information analysis method and device based on artificial intelligence
Wisselgren et al. Testing methods of record linkage on Swedish censuses
US9262506B2 (en) Generating mappings between a plurality of taxonomies
Mahr et al. Classification and classification criteria for vasculitis: achievements, limitations and prospects
JP2009520284A (en) Access method of XML file data
Hannell Fan studies and/as feminist methodology
WO2021114836A1 (en) Text coherence determining method, apparatus, and device, and medium
Weng et al. Construction and application of teaching system based on crowdsourcing knowledge graph
Hu et al. Essence Computation Oriented Multi-semantic Analysis Crossing Multi-modal DIKW Graphs
US20120324346A1 (en) Method for relational analysis of parsed input for visual mapping of knowledge information
CN111177309A (en) Medical record data processing method and device
De Nies et al. Modeling uncertain provenance and provenance of uncertainty in w3c prov
Martínez-González et al. On the evaluation of thesaurus tools compatible with the Semantic Web
CN117577254A (en) Method and system for constructing language model in medical field and structuring text of electronic medical record
CN104508656B (en) Document automation in distributed computing system replicates
Tong et al. Religious Geography and County‐Level Sex Ratios in China

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
GR01 Patent grant
GR01 Patent grant