WO2017104657A1 - Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement - Google Patents

Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement Download PDF

Info

Publication number
WO2017104657A1
WO2017104657A1 PCT/JP2016/087049 JP2016087049W WO2017104657A1 WO 2017104657 A1 WO2017104657 A1 WO 2017104657A1 JP 2016087049 W JP2016087049 W JP 2016087049W WO 2017104657 A1 WO2017104657 A1 WO 2017104657A1
Authority
WO
WIPO (PCT)
Prior art keywords
occurrence
causal
chain
information processing
elements
Prior art date
Application number
PCT/JP2016/087049
Other languages
English (en)
Japanese (ja)
Inventor
大地 木村
英司 平尾
俊輔 河野
Original Assignee
日本電気株式会社
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 日本電気株式会社 filed Critical 日本電気株式会社
Priority to JP2017556067A priority Critical patent/JPWO2017104657A1/ja
Publication of WO2017104657A1 publication Critical patent/WO2017104657A1/fr

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor

Definitions

  • Patent Document 2 describes a technique for describing a causal relationship structure between nodes by connecting nodes (elements) constituting the system by an arc and generating a simulation program using a simulation model inheriting the structure. Is disclosed.
  • an information processing apparatus includes at least two combinations of information representing an element that causes a causal relationship regarding an event and information representing an element that results.
  • a chain extraction unit that extracts a chain of causal relationships composed of two causal relationships; a document storage unit that can hold one or more documents; and the end points of the chain of causal relationships extracted by the chain extraction unit in the document.
  • the co-occurrence detection unit for detecting the co-occurrence of the elements
  • the co-occurrence rate calculation unit for calculating the ratio of co-occurrence related to the co-occurrence detected by the co-occurrence detection unit, and the result of the calculation by the co-occurrence rate calculation unit
  • a result output unit that outputs output information including the output information.
  • Document storage unit 103 holds (stores) documents.
  • the document stored in the document storage unit 103 is not particularly limited as long as the document is expected to describe the elements constituting the event and the causal relationship between the elements.
  • a document may be, for example, a document published on the WEB (World Wide Web), a newspaper article, or a white paper.
  • Such a document is not limited to the above example, and other appropriate documents can be selected.
  • the document storage unit 103 is not limited to a document composed of text data, and includes information that can be documented using appropriate analysis techniques (speech recognition, image analysis, etc.) such as voice, image, and moving image data.
  • the document storage unit 103 can store the document using, for example, a well-known file system or a database.
  • the co-occurrence rate calculation unit 105 calculates the co-occurrence rate based on the detection result by the co-occurrence detection unit 104.
  • the co-occurrence ratio is information used to determine whether or not the elements (causal relation element pairs) at both ends of the causal relation chain are consistent when a plurality of causal relations are linked.
  • the information processing apparatus 100 or the user can determine whether a causal relationship element pair is consistent based on the co-occurrence ratio calculated by the co-occurrence ratio calculation unit 105.
  • the co-occurrence ratio calculated by the co-occurrence ratio calculation unit 105 can be an index for determining whether or not a certain causal relationship element pair is consistent.
  • step S302 the chain extraction unit 102 extracts a chain of causal relationships including two causal relationships from the received causal relationship information.
  • a method for extracting the causal chain will be described with reference to a specific example shown in FIG.
  • the co-occurrence detection unit 104 analyzes the document stored in the document storage unit 103 using a natural language analysis method (for example, morphological analysis, syntax analysis, etc.), and causal elements in the document. Detect pair co-occurrence.
  • a natural language analysis method for example, morphological analysis, syntax analysis, etc.
  • the co-occurrence ratio calculation unit 105 can calculate the Dice coefficient using the following equation.
  • the chain extraction unit 801 (chain extraction unit) includes a chain of causal relationships including at least two causal relationships from a plurality of combinations of information indicating elements that cause causal relationships related to events and information indicating the resulting elements. To extract. For example, as in the first embodiment, the chain extraction unit 801 generates a chain of causal relationships from causal relationship information including a plurality of combinations of information representing the cause elements and information representing the resulting elements. It may be extracted. In this case, the causal relationship information and the causal relationship chain may be the same as those in the first embodiment.
  • the chain extraction unit 801 may be provided with the causal relationship information from a user (not shown) of the information processing device 800 or another information processing device, and is held in a storage device (not shown) in the information processing device 800. The causal relationship information may be acquired.
  • Document storage unit 803 (document storage means) holds one or more documents. Such a document is not particularly limited, for example, as in the first embodiment, and may be any document that is expected to describe the elements constituting the event and the causal relationship between the elements.
  • the document storage unit 803 can store the document using, for example, a known file system or a database.
  • the document storage unit 803 may be configured, for example, in the same manner as the document storage unit 103 in the first embodiment, and may hold a document by the same processing as the document storage unit 103.
  • the co-occurrence ratio calculation unit 804 may be configured, for example, in the same manner as the co-occurrence ratio calculation unit 105 in the first embodiment, and the co-occurrence ratio calculation unit 105 calculates the co-occurrence ratio by the same processing as the co-occurrence ratio calculation unit 105. It may be calculated.

Abstract

La présente invention a pour but de proposer des informations au moyen desquelles il est possible d'évaluer la cohérence d'une relation formée par concaténation d'une pluralité de relations de cause à effet. Le dispositif de traitement d'informations, selon la présente invention, comporte : une unité d'extraction de chaîne qui extrait une chaîne d'au moins deux relations de cause à effet, sur la base d'une pluralité de combinaisons d'informations représentant un paramètre de cause et d'informations représentant un paramètre d'effet qui sont trouvées dans des évènements de relation de cause à effet ; une unité d'accumulation de documents qui peut conserver un ou plusieurs documents ; une unité de détection de cooccurrence qui détecte, dans le ou les documents, la cooccurrence d'éléments représentant les paramètres aux deux extrémités de la chaîne d'au moins deux relations de cause à effet extraite par l'unité d'extraction de chaîne ; une unité de calcul de mesure de cooccurrence qui calcule une mesure de la cooccurrence détectée par l'unité de détection de cooccurrence, dans le ou les documents ; et une unité de délivrance de résultat qui délivre des informations de sortie comprenant les résultats du calcul réalisé par l'unité de calcul de mesure de cooccurrence.
PCT/JP2016/087049 2015-12-14 2016-12-13 Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement WO2017104657A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2017556067A JPWO2017104657A1 (ja) 2015-12-14 2016-12-13 情報処理装置、情報処理方法、及び、コンピュータ・プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2015243101 2015-12-14
JP2015-243101 2015-12-14

Publications (1)

Publication Number Publication Date
WO2017104657A1 true WO2017104657A1 (fr) 2017-06-22

Family

ID=59056751

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/087049 WO2017104657A1 (fr) 2015-12-14 2016-12-13 Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement

Country Status (2)

Country Link
JP (1) JPWO2017104657A1 (fr)
WO (1) WO2017104657A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2022122029A (ja) * 2021-02-09 2022-08-22 株式会社東芝 データ処理装置、データ処理方法及びデータ処理プログラム

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015121897A (ja) * 2013-12-20 2015-07-02 国立研究開発法人情報通信研究機構 シナリオ生成装置、及びそのためのコンピュータプログラム

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015121897A (ja) * 2013-12-20 2015-07-02 国立研究開発法人情報通信研究機構 シナリオ生成装置、及びそのためのコンピュータプログラム

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HITOMI SAWAMURA ET AL.: "Fukusu bunshonai no jishokan no inga kankei chushutsu eno torikumi", ARCHITECTURE SOFTWARE KAGAKU DATABASE TOMEDIA, 2012, pages 1-595 - 1-596 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2022122029A (ja) * 2021-02-09 2022-08-22 株式会社東芝 データ処理装置、データ処理方法及びデータ処理プログラム

Also Published As

Publication number Publication date
JPWO2017104657A1 (ja) 2018-11-01

Similar Documents

Publication Publication Date Title
US8762132B2 (en) Textual entailment recognition apparatus, textual entailment recognition method, and computer-readable recording medium
US9009024B2 (en) Performing sentiment analysis
US10891322B2 (en) Automatic conversation creator for news
US10089296B2 (en) System and method for sentiment lexicon expansion
US9606978B2 (en) Discovering relationships in tabular data
US8769470B2 (en) Timing closure in chip design
CN113110988A (zh) 利用定义的输入格式来测试应用
CN101751333A (zh) 用于支援程序解析的方法、及其计算机程序以及计算机系统
CN110795572B (zh) 一种实体对齐方法、装置、设备及介质
WO2016151618A1 (fr) Système de mise à jour de modèle prédictif, procédé de mise à jour de modèle prédictif, et programme de mise à jour de modèle prédictif
WO2014134990A1 (fr) Procédé, dispositif et support de stockage lisible par ordinateur de test de fermeture
WO2017104657A1 (fr) Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement
US11030362B2 (en) Modeling and cooperative simulation of systems with interdependent discrete and continuous elements
WO2015166508A1 (fr) Découverte d'instruments par corrélations
US20190166142A1 (en) Method for analysing cyber threat intelligence data and apparatus thereof
WO2017104571A1 (fr) Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement
JP6154072B2 (ja) 情報分析システム、情報分析方法及び情報分析プログラム
US11636022B2 (en) Server and control method thereof
WO2017104656A1 (fr) Dispositif de traitement d'informations, procédé de traitement d'informations et support d'enregistrement
US11188696B1 (en) Method, system, and product for deferred merge based method for graph based analysis pessimism reduction
JP6907703B2 (ja) 解析装置、解析方法、および解析プログラム
JP2017151594A (ja) 支援装置、支援方法及びプログラム
US20150277858A1 (en) Performance evaluation device, method, and medium for information system
CN114556238A (zh) 用于在云计算环境中生成资产信息的数字表示的方法和系统
CN105868113B (zh) 字符串查找方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16875634

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017556067

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16875634

Country of ref document: EP

Kind code of ref document: A1