WO2020001233A1 - 一种用于隐性关联知识发现的多关系融合方法及智能化*** - Google Patents

一种用于隐性关联知识发现的多关系融合方法及智能化*** Download PDF

Info

Publication number
WO2020001233A1
WO2020001233A1 PCT/CN2019/089509 CN2019089509W WO2020001233A1 WO 2020001233 A1 WO2020001233 A1 WO 2020001233A1 CN 2019089509 W CN2019089509 W CN 2019089509W WO 2020001233 A1 WO2020001233 A1 WO 2020001233A1
Authority
WO
WIPO (PCT)
Prior art keywords
term
word set
relationship
fusion
matrix
Prior art date
Application number
PCT/CN2019/089509
Other languages
English (en)
French (fr)
Inventor
刘晓勇
Original Assignee
广东技术师范大学
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 广东技术师范大学 filed Critical 广东技术师范大学
Priority to US16/627,796 priority Critical patent/US20210334465A1/en
Publication of WO2020001233A1 publication Critical patent/WO2020001233A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/93—Document management systems
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation

Definitions

  • the invention relates to the technical field of intelligent system and knowledge engineering research, in particular to a multi-relational fusion method and intelligent system for implicitly associated knowledge discovery.
  • the term is usually lacking its consideration of the topical compactness of the literature when selecting the term. For example, the selection of intermediate words usually ignores the tightness of the starting term to the subject of the original document.
  • the middle word set B is generally extracted (selected) from the document set a retrieved from the term A, and then the co-occurrence of A and B is used to sort and filter the middle word set. But there may be two situations when choosing B:
  • the B word extracted (selected) in a may have a greater relevance to A
  • the B word extracted (selected) in a may not have much relevance to A, and is probably not suitable as an intermediate word;
  • the purpose of the present invention is to solve the above-mentioned shortcomings in the prior art, and to provide a multi-relational fusion method and an intelligent system for implicitly associated knowledge discovery.
  • a first aspect of the present invention discloses a multi-relation fusion method for implicitly associated knowledge discovery.
  • the multi-relation fusion method includes the following steps:
  • the first term set MSR-Terms that is semantically related to the term A at the beginning is identified to form the MSR matrix of the middle term set B;
  • the middle word set B is obtained through the fusion of the common relationship and the semantic relationship;
  • a second term set MSR-Terms that is semantically related to the middle word set B is identified to form a terminal word set C MSR matrix;
  • the terminal word set C is obtained through the fusion of the common relationship and the semantic relationship;
  • a relationship fusion is performed by using a z-value fusion algorithm based on Stouffer.
  • a second aspect of the present invention discloses a multi-relation fusion intelligent system for tacit association knowledge discovery.
  • the multi-relation fusion intelligent system includes:
  • the starting term search unit is used to give a starting term A, and the initial document set a is found by searching;
  • a subject compactness related term recognition unit is configured to identify a first term set TC-Terms related to the starting term A subject compactness to form an intermediate word set B TC matrix;
  • a semantically related term recognition unit for identifying the first term set MSR-Terms semantically related to the start term A, to form an intermediate word set B MSR matrix;
  • the middle word set relationship fusion unit is used to obtain the middle word set B through the fusion of the common relationship and the semantic relationship;
  • An intermediate word set retrieval unit for searching through the intermediate word set B to find an intermediate document set b;
  • the B-topic compactness-related term recognition unit is used to identify a second term set TC-Terms related to the intermediate word set B-topic compactness to form a terminal word set C TC matrix;
  • B semantic related term recognition unit for identifying a second term set MSR-Terms semantically related to the intermediate word set B to form a terminal word set C MSR matrix
  • Terminal word set retrieval unit configured to obtain the terminal word set C through the fusion of the relationship between the common relationship and the semantic relationship
  • Co-occurrence judgment unit which checks the co-occurrence of the starting term A and the terminal word set C. If the two do not co-occur in the same document, they can be stored in the implicit relational knowledge base; if the two co-occur in the same document , The association between the start term A and the term set C is not saved.
  • a stouffer-based z-value fusion algorithm is used to perform relationship fusion between the common relationship and the semantic relationship.
  • the present invention has the following advantages and effects:
  • the tacit knowledge associations identified by the term pair co-occurrence method based on topic compactness and the semantic relationship between the term pairs are used to identify the tacit knowledge associations that actually exist and are semantically related between the term pairs.
  • Stouffer's z-value fusion algorithm for relationship fusion compared with the current domestic and foreign mainstream LBD knowledge discovery technology, it can find more reliable and valuable tacit knowledge associations.
  • FIG. 1 is a flowchart of a multi-relational fusion method for implicitly associated knowledge discovery disclosed in the present invention
  • FIG. 2 is a schematic structural diagram of a multi-relation fusion intelligent system for tacit knowledge discovery.
  • this embodiment discloses a multi-relation fusion method for tacit association knowledge discovery.
  • the multi-relation fusion method includes the following steps:
  • the initial document set a Given a starting term A (starting concept), the initial document set a is found by searching;
  • the first term set MSR-Terms that is semantically related to the term A at the beginning is identified to form the MSR matrix of the middle term set B;
  • the intermediate word set B (linking concept) is obtained through the fusion of the common relationship and the semantic relationship;
  • a second term set MSR-Terms that is semantically related to the middle word set B is identified to form a terminal word set C MSR matrix;
  • the terminal word set C (target concept) is obtained through the fusion of the common relationship and the semantic relationship;
  • the relationship fusion through the common relationship and the semantic relationship is performed by a Stouffer-based z-value fusion algorithm.
  • this embodiment discloses a multi-relation fusion intelligent system for tacit association knowledge discovery.
  • the multi-relation fusion intelligent system includes:
  • a starting term retrieval unit which is used to give a starting term A (starting concept, that is, an initial word), and find an initial document set a by searching;
  • a subject compactness related term recognition unit is configured to identify a first term set TC-Terms related to the starting term A subject compactness to form an intermediate word set B TC matrix;
  • a semantically related term recognition unit for identifying the first term set MSR-Terms semantically related to the start term A, to form an intermediate word set B MSR matrix;
  • the middle word set relationship fusion unit is used to obtain the middle word set B (linking concept) through the fusion of the common relationship and the semantic relationship;
  • An intermediate word set retrieval unit for searching through the intermediate word set B to find an intermediate document set b;
  • the B-topic compactness-related term recognition unit is used to identify a second term set TC-Terms related to the intermediate word set B-topic compactness to form a terminal word set C TC matrix;
  • B semantic related term recognition unit for identifying a second term set MSR-Terms semantically related to the intermediate word set B to form a terminal word set C MSR matrix
  • the terminal word set retrieval unit is used to obtain a terminal word set C (target concept) through the fusion of the common relationship and the semantic relationship;
  • Co-occurrence judgment unit which checks the co-occurrence of the starting term A and the terminal word set C. If the two do not co-occur in the same document, they can be stored in the implicit relational knowledge base; , The association between the start term A and the term set C is not saved.
  • a stouffer-based z-value fusion algorithm is used in the intermediate word set retrieval unit and the terminal word set retrieval unit to perform relationship fusion between a common relationship and a semantic relationship.
  • the present invention solves how to find valuable and reliable tacit knowledge associations from a large number of scientific literatures.
  • the solution of this problem can provide a new method for helping scientific researchers to cross scientific islands and promote interdisciplinary research.
  • the present invention uses the proposed improved co-occurrence relationship and semantic relationship fusion mining method to display and reveal meaningful potential knowledge associations hidden in a large amount of scientific literature that cannot be effectively identified by the current LBD method.
  • sequence numbers of the steps cannot be used to define the sequence of the steps.
  • sequence of the steps can be changed without paying creative labor. It is also within the protection scope of the present invention.
  • each module and unit included is only divided according to functional logic, but it is not limited to the above division, as long as it can achieve the corresponding function; in addition, each module
  • the specific names of the sum unit are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种用于隐性关联知识发现的多关系融合方法及智能化***，该方法步骤如下：首先给出一个始端术语A，通过检索找到初始文献集a，识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms和语义相关的第一术语集合MSR-Terms，分别形成中间词集BTC和BMSR矩阵，通过共同关系与语义关系的关系融合得到中间词集B，再通过中间词集B进行检索找到中间文献集b，识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms和语义相关的第二术语集合MSR-Terms，分别形成终端词集CTC和CMSR矩阵，通过共同关系与语义关系的关系融合得到终端词集C，将始端术语A与终端词集C进行共现判断。

Description

一种用于隐性关联知识发现的多关系融合方法及智能化*** 技术领域
本发明涉及智能***与知识工程研究技术领域，具体涉及一种用于隐性关联知识发现的多关系融合方法及智能化***。
背景技术
Don R.Swanson提出的Literature-Based Discovery(LBD)知识发现技术，经过多年的发展，很多学者投入到该方法的研究当中。该方法能够使得科研人员不再受限于自己所熟悉的狭小的研究领域，相反，可以依靠该方法避免科学孤岛现象，较为有效的支持学科间的交叉创新。但纵观当前国内外的相关研究，该技术及相关的智能化***存在如下不足：
(1)术语的选择方法有待改进
当前主流的基于术语共现的LBD方法研究中，术语在选择时通常缺少其对文献主题紧致度(Topic Compactness)的考虑。如：中间词集在选择时通常忽略了始端术语对初始文献主题的紧致度。中间词集B一般都是从由始端术语A检索得到的文献集a中进行抽取(选择)的，然后利用A和B的共现，对中间词集进行排序和过滤。但是在选择B的时候可能存在这样两种情况，：
①如果A与文献a的主题强相关，则在a中抽取(选择)的B词可能与A的关联性意义较大；
②如果A与文献a的主题弱相关，则在a中抽取(选择)的B词可能与A的关联性意义不大，很可能不适合作为中间词；
这种由始端术语A与文献a的主题紧致度的不同对于中间词集的选择 所造成的影响，尚未见到相关的研究报道。忽略了表征术语与文献主题关联程度的主题紧致度，是导致当前的LBD方法中最终产生的隐性关联数量繁多的主要因素之一。
(2)隐性关联术语对的识别忽略了术语对间客观存在的语义关系
当前LBD的研究主要是从术语共现的角度出发，寻找术语间的关联，缺少对术语对间真正存在的语义关系的考虑。虽然Hu和Hristovski等人也分别提出了基于语义的LBD技术，但是Kostoff指出其算法本质上仍然属于主流LBD的研究中基于简单共现的技术。因为A词和B词共现，并不一定表明A和B在语义上存在关联关系。因此单纯依赖术语共现的LBD技术，最终找到的隐性关联知识并不可靠。
发明内容
本发明的目的是为了解决现有技术中的上述缺陷，提供一种用于隐性关联知识发现的多关系融合方法及智能化***。
根据公开的实施例，本发明的第一方面公开了一种用于隐性关联知识发现的多关系融合方法，所述的多关系融合方法包括下列步骤：
给出一个始端术语A，通过检索找到初始文献集a；
识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms，形成中间词集B TC矩阵；
识别出与始端术语A语义相关的第一术语集合MSR-Terms，形成中间词集B MSR矩阵；
通过共同关系与语义关系的关系融合得到中间词集B；
通过中间词集B进行检索找到中间文献集b；
识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms，形成终端词集C TC矩阵；
识别出与中间词集B语义相关的第二术语集合MSR-Terms，形成终端 词集C MSR矩阵；
通过共同关系与语义关系的关系融合得到终端词集C；
将始端术语A与终端词集C进行共现检查，如果两者没有在同一篇文献中共现，即可存入隐性关联知识库中；如果两者在同一篇文献中共现，则不保存始端术语A与终端词集C关联。
进一步地，所述的通过共同关系与语义关系的关系融合中通过基于Stouffer的z值融合算法进行关系融合。
根据公开的实施例，本发明的第二方面公开了一种用于隐性关联知识发现的多关系融合智能化***，所述的多关系融合智能化***包括：
始端术语检索单元，用于给出一个始端术语A，通过检索找到初始文献集a；
A主题紧致度相关术语识别单元，用于识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms，形成中间词集B TC矩阵；
A语义相关术语识别单元，用于识别出与始端术语A语义相关的第一术语集合MSR-Terms，形成中间词集B MSR矩阵；
中间词集关系融合单元，用于通过共同关系与语义关系的关系融合得到中间词集B；
中间词集检索单元，用于通过中间词集B进行检索找到中间文献集b；
B主题紧致度相关术语识别单元，用于识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms，形成终端词集C TC矩阵；
B语义相关术语识别单元，用于识别出与中间词集B语义相关的第二术语集合MSR-Terms，形成终端词集C MSR矩阵；
终端词集检索单元，用于通过共同关系与语义关系的关系融合得到终端词集C；
共现判断单元，将始端术语A与终端词集C进行共现检查，如果两者没有在同一篇文献中共现，即可存入隐性关联知识库中；如果两者在同一 篇文献中共现，则不保存始端术语A与终端词集C关联。
进一步地，所述的中间词集检索单元和所述的终端词集检索单元中采用基于Stouffer的z值融合算法进行共同关系与语义关系的关系融合。
本发明相对于现有技术具有如下的优点及效果：
本发明将基于主题紧致度的术语对共现方法识别出的隐性知识关联和从术语对间蕴含的语义关系研究出发，识别术语对间实际存在的且语义上相关的隐性知识关联，通过基于Stouffer的z值融合算法进行关系融合，相比当前国内外主流的LBD知识发现技术，能够发现更加可靠的、有价值的隐性知识关联。
附图说明
图1是本发明公开的一种用于隐性关联知识发现的多关系融合方法的流程步骤图；
图2是一种用于隐性关联知识发现的多关系融合智能化***的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
实施例一
如附图1所示，本实施例公开了一种用于隐性关联知识发现的多关系融合方法，该多关系融合方法包括下列步骤：
给出一个始端术语A(starting concept，即初始词)，通过检索找到初始文献集a；
识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms，形成中间词集B TC矩阵；
识别出与始端术语A语义相关的第一术语集合MSR-Terms，形成中间词集B MSR矩阵；
通过共同关系与语义关系的关系融合得到中间词集B(linking concept)；
通过中间词集B进行检索找到中间文献集b；
识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms，形成终端词集C TC矩阵；
识别出与中间词集B语义相关的第二术语集合MSR-Terms，形成终端词集C MSR矩阵；
通过共同关系与语义关系的关系融合得到终端词集C(target concept)；
将始端术语A与终端词集C进行共现检查，如果两者没有在同一篇文献中共现，即可存入隐性关联知识库中；如果两者在同一篇文献中共现，则不保存始端术语A与终端词集C关联。
在本实施例中，所述的通过共同关系与语义关系的关系融合中通过基于Stouffer的z值融合算法进行关系融合。
实施例二
如附图2所示，本实施例公开了一种用于隐性关联知识发现的多关系融合智能化***，该多关系融合智能化***包括：
始端术语检索单元，用于给出一个始端术语A(starting concept，即初始词)，通过检索找到初始文献集a；
A主题紧致度相关术语识别单元，用于识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms，形成中间词集B TC矩阵；
A语义相关术语识别单元，用于识别出与始端术语A语义相关的第一 术语集合MSR-Terms，形成中间词集B MSR矩阵；
中间词集关系融合单元，用于通过共同关系与语义关系的关系融合得到中间词集B(linking concept)；
中间词集检索单元，用于通过中间词集B进行检索找到中间文献集b；
B主题紧致度相关术语识别单元，用于识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms，形成终端词集C TC矩阵；
B语义相关术语识别单元，用于识别出与中间词集B语义相关的第二术语集合MSR-Terms，形成终端词集C MSR矩阵；
终端词集检索单元，用于通过共同关系与语义关系的关系融合得到终端词集C(target concept)；
共现判断单元，将始端术语A与终端词集C进行共现检查，如果两者没有在同一篇文献中共现，即可存入隐性关联知识库中；如果两者在同一篇文献中共现，则不保存始端术语A与终端词集C关联。
在本实施例中，所述的中间词集检索单元和所述的终端词集检索单元中采用基于Stouffer的z值融合算法进行共同关系与语义关系的关系融合。
综上所述，本发明解决如何从大量科学文献中发现有价值的、可靠的隐性知识关联，该问题的解决能够为帮助科研人员跨越科学孤岛，促进学科交叉提供一种新的方法。本发明通过提出的改进的共现关系和语义关系融合挖掘的方法去显示揭示出依靠当前的LBD方法无法有效识别的、隐藏在大量科学文献中的有意义的潜在知识关联。
在本发明各方法实施例中，所述各步骤的序号并不能用于限定各步骤的先后顺序，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，对各步骤的先后变化也在本发明的保护范围之内。
值得注意的是，上述智能化***实施例中，所包括的各个模块和单元只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，各模块和单元的具体名称也只是为了便于相互区 分，并不用于限制本发明的保护范围。
上述实施例为本发明较佳的实施方式，但本发明的实施方式并不受上述实施例的限制，其他的任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化，均应为等效的置换方式，都包含在本发明的保护范围之内。

Claims (4)

  1. 一种用于隐性关联知识发现的多关系融合方法，其特征在于，所述的多关系融合方法包括下列步骤：
    给出一个始端术语A，通过检索找到初始文献集a；
    识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms，形成中间词集B TC矩阵；
    识别出与始端术语A语义相关的第一术语集合MSR-Terms，形成中间词集B MSR矩阵；
    通过共同关系与语义关系的关系融合得到中间词集B；
    通过中间词集B进行检索找到中间文献集b；
    识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms，形成终端词集C TC矩阵；
    识别出与中间词集B语义相关的第二术语集合MSR-Terms，形成终端词集C MSR矩阵；
    通过共同关系与语义关系的关系融合得到终端词集C；
    将始端术语A与终端词集C进行共现检查，如果两者没有在同一篇文献中共现，即可存入隐性关联知识库中；如果两者在同一篇文献中共现，则不保存始端术语A与终端词集C关联。
  2. 根据权利要求1所述的一种用于隐性关联知识发现的多关系融合方法，其特征在于，
    所述的通过共同关系与语义关系的关系融合中通过基于Stouffer的z值融合算法进行关系融合。
  3. 一种用于隐性关联知识发现的多关系融合智能化***，其特征在于，所述的多关系融合智能化***包括：
    始端术语检索单元，用于给出一个始端术语A，通过检索找到初始文 献集a；
    A主题紧致度相关术语识别单元，用于识别出与始端术语A主题紧致度相关的第一术语集合TC-Terms，形成中间词集B TC矩阵；
    A语义相关术语识别单元，用于识别出与始端术语A语义相关的第一术语集合MSR-Terms，形成中间词集B MSR矩阵；
    中间词集关系融合单元，用于通过共同关系与语义关系的关系融合得到中间词集B；
    中间词集检索单元，用于通过中间词集B进行检索找到中间文献集b；
    B主题紧致度相关术语识别单元，用于识别出与中间词集B主题紧致度相关的第二术语集合TC-Terms，形成终端词集C TC矩阵；
    B语义相关术语识别单元，用于识别出与中间词集B语义相关的第二术语集合MSR-Terms，形成终端词集C MSR矩阵；
    终端词集检索单元，用于通过共同关系与语义关系的关系融合得到终端词集C；
    共现判断单元，将始端术语A与终端词集C进行共现检查，如果两者没有在同一篇文献中共现，即可存入隐性关联知识库中；如果两者在同一篇文献中共现，则不保存始端术语A与终端词集C关联。
  4. 根据权利要求3所述的一种用于隐性关联知识发现的多关系融合智能化***，其特征在于，所述的中间词集检索单元和所述的终端词集检索单元中采用基于Stouffer的z值融合算法进行共同关系与语义关系的关系融合。
PCT/CN2019/089509 2018-06-30 2019-05-31 一种用于隐性关联知识发现的多关系融合方法及智能化*** WO2020001233A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/627,796 US20210334465A1 (en) 2018-06-30 2019-05-31 Multi-relation fusion method and intelligent system for latent-association lbd

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810702397.7A CN108959540A (zh) 2018-06-30 2018-06-30 一种用于隐性关联知识发现的多关系融合方法及智能化***
CN201810702397.7 2018-06-30

Publications (1)

Publication Number Publication Date
WO2020001233A1 true WO2020001233A1 (zh) 2020-01-02

Family

ID=64484285

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/089509 WO2020001233A1 (zh) 2018-06-30 2019-05-31 一种用于隐性关联知识发现的多关系融合方法及智能化***

Country Status (3)

Country Link
US (1) US20210334465A1 (zh)
CN (1) CN108959540A (zh)
WO (1) WO2020001233A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022270994A1 (ko) 2021-06-25 2022-12-29 한국화학연구원 유비퀴틴 프로테오좀 경로를 통해 비티케이 분해작용을 가지는 신규한 이작용성 헤테로사이클릭 화합물과 이의 용도

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108959540A (zh) * 2018-06-30 2018-12-07 广东技术师范学院 一种用于隐性关联知识发现的多关系融合方法及智能化***
CN110580339B (zh) * 2019-08-21 2023-04-07 华东理工大学 一种医疗术语知识库完善的方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060047441A1 (en) * 2004-08-31 2006-03-02 Ramin Homayouni Semantic gene organizer
US20100114890A1 (en) * 2008-10-31 2010-05-06 Purediscovery Corporation System and Method for Discovering Latent Relationships in Data
CN106547739A (zh) * 2016-11-03 2017-03-29 同济大学 一种文本语义相似度分析方法
CN106919689A (zh) * 2017-03-03 2017-07-04 中国科学技术信息研究所 基于术语释义知识单元的专业领域知识图谱动态构建方法
CN107301218A (zh) * 2017-06-15 2017-10-27 北京航天长征科技信息研究所 一种非相关文献隐性关联知识发现方法
CN108959540A (zh) * 2018-06-30 2018-12-07 广东技术师范学院 一种用于隐性关联知识发现的多关系融合方法及智能化***

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060047441A1 (en) * 2004-08-31 2006-03-02 Ramin Homayouni Semantic gene organizer
US20100114890A1 (en) * 2008-10-31 2010-05-06 Purediscovery Corporation System and Method for Discovering Latent Relationships in Data
CN106547739A (zh) * 2016-11-03 2017-03-29 同济大学 一种文本语义相似度分析方法
CN106919689A (zh) * 2017-03-03 2017-07-04 中国科学技术信息研究所 基于术语释义知识单元的专业领域知识图谱动态构建方法
CN107301218A (zh) * 2017-06-15 2017-10-27 北京航天长征科技信息研究所 一种非相关文献隐性关联知识发现方法
CN108959540A (zh) * 2018-06-30 2018-12-07 广东技术师范学院 一种用于隐性关联知识发现的多关系融合方法及智能化***

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022270994A1 (ko) 2021-06-25 2022-12-29 한국화학연구원 유비퀴틴 프로테오좀 경로를 통해 비티케이 분해작용을 가지는 신규한 이작용성 헤테로사이클릭 화합물과 이의 용도

Also Published As

Publication number Publication date
US20210334465A1 (en) 2021-10-28
CN108959540A (zh) 2018-12-07

Similar Documents

Publication Publication Date Title
WO2020001233A1 (zh) 一种用于隐性关联知识发现的多关系融合方法及智能化***
Garfield et al. Why do we need algorithmic historiography?
CN105573977A (zh) 一种中文事件时序关系识别方法及***
CN108733793B (zh) 一种面向关系数据库的本体模型构造方法及***
CN111914141B (zh) 一种舆情知识库构建方法及舆情知识库
CN110147420A (zh) 一种基于图谱模型的地名地址匹配查询方法及***
CN109947914A (zh) 一种基于模板的软件缺陷自动问答方法
CN102890723B (zh) 一种例句检索的方法及***
CN111538795A (zh) 一种关系型数据库与对象型数据库的智能交互***
Feng Family burden coefficient in China: exploratory research and application
CN106157651B (zh) 一种基于语音语义理解的交通电台路况信息播报***
LU103037B1 (en) String matching algorithm based on features of comprehensive energy system
Koudas et al. Spider: flexible matching in databases
Li et al. Research on the evolution path of China’s provincial innovation chain model based on complex network model
Cheng et al. Data fusion method for digital gazetteer
Shengchuan et al. Practice and Prospect of Oral History in Sports Study
Xiaojiang et al. Women and feminism in China and India: A conversation with Li Xiaojiang
US20090089284A1 (en) Method and apparatus for automatically differentiating between types of names stored in a data collection
Li et al. Bibliometric analysis of data mining in the Chinese Social Science Circle
Meng et al. Construction and Application of a Tree Knowledge Graph
Li et al. Research of intelligent word segmentation and information retrieval
Yue et al. A Review of Domestic Cultural Tourism Research in the Past Decade
Feng et al. Research on Hotspots of Mutual Assistance for the Elderly in China--Based on CiteSpace Software
Gutiérrez et al. Querying heterogeneous spatial databases: Combining an ontology with similarity functions
Qin et al. Some Thoughts on Constructing Domain Multi-Modal Knowledge Graph

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19826836

Country of ref document: EP

Kind code of ref document: A1