JPWO2020023787A5 - - Google Patents
Download PDFInfo
- Publication number
- JPWO2020023787A5 JPWO2020023787A5 JP2021503796A JP2021503796A JPWO2020023787A5 JP WO2020023787 A5 JPWO2020023787 A5 JP WO2020023787A5 JP 2021503796 A JP2021503796 A JP 2021503796A JP 2021503796 A JP2021503796 A JP 2021503796A JP WO2020023787 A5 JPWO2020023787 A5 JP WO2020023787A5
- Authority
- JP
- Japan
- Prior art keywords
- database
- keyword
- field
- node
- tables
- 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
Links
- 238000000034 method Methods 0.000 claims 18
- 238000005352 clarification Methods 0.000 claims 2
- 239000000284 extract Substances 0.000 claims 1
Claims (11)
テーブルを有するデータベースにアクセスすることを含み、各テーブルは、前記各テーブルを識別するラベルと、フィールドとを含み、各フィールドは属性を含み、前記方法はさらに、
エンティティを含むカスタムデータベースインデックスにアクセスすることを含み、前記エンティティは、前記フィールドと、前記属性と、前記フィールドまたは前記属性の１つ以上の同義語とを含み、前記方法はさらに、
自然言語検索クエリにアクセスすることと、
前記自然言語検索クエリからパースツリーを構築することとを含み、前記パースツリーは、単語タイプを含む少なくとも１つの終端ノードと、前記自然言語検索クエリの単語またはフレーズを表す少なくとも１つの終端ノードとを含み、前記パースツリーは、前記自然言語クエリの構文情報を識別し、前記方法はさらに、
前記パースツリーから１つ以上の節を識別することを含み、節はキーワードを含み、各キーワードは名詞または動詞であり、前記方法はさらに、
以下の１つ以上、すなわち、
各キーワードを、（ｉ）前記テーブルのうちの１つのテーブルのラベルまたは（ｉｉ）前記テーブルのうちの１つのテーブルのフィールドまたは（ｉｉｉ）フィールドの属性のいずれかにマッチングさせること、および
前記キーワードと前記カスタムデータベースインデックスとの間のマッチの閾値レベルを判断すること、の１つ以上を実行することと、
前記マッチングされたキーワードからデータベースクエリを生成することと、
前記データベースクエリを前記データベースに提供することによって前記データベースから結果を得ることと、
前記結果をユーザデバイスに表示することとを含む、方法。 A way to process natural language queries through a database,
Each table comprises accessing a database having tables, each table comprises a label identifying each of the tables, a field, each field comprises an attribute, and the method further comprises.
Containing access to a custom database index containing an entity, said entity comprises said field, said attribute, and one or more synonyms for said field or attribute, the method further comprises.
Accessing natural language search queries and
Containing building a perspective tree from the natural language search query, the perspective tree comprises at least one termination node containing a word type and at least one termination node representing a word or phrase in the natural language search query. The perspective tree contains, and the method further identifies the syntax information of the natural language query.
The method comprises further identifying one or more clauses from the perspective tree, the clauses comprising keywords, each keyword being a noun or verb.
One or more of the following, ie
Matching each keyword to either (i) the label of one of the tables or (ii) the field of one of the tables or the attribute of the field (iii), and with the keyword. Performing one or more of determining the threshold level of a match with the custom database index,
Generating a database query from the matched keywords
Obtaining results from the database by providing the database query to the database
A method comprising displaying the result on a user device.
前記キーワードのうちのあるキーワードが前記データベース内でマッチしないと判断することに応答して、暗黙ノードを前記パースツリーに挿入することを含み、前記暗黙ノードは前記キーワードを識別し、前記方法はさらに、
前記キーワードを前記ユーザデバイスに提示することを含む、請求項１に記載の方法。 The method further
The implicit node identifies the keyword, the method further comprises inserting an implicit node into the perspective tree in response to determining that one of the keywords does not match in the database. ,
The method of claim 1, comprising presenting the keyword to the user device.
前記ユーザデバイスから明確化を受信することと、
前記明確化に基づいて前記パースツリーを更新することと、
前記パースツリーからの更新された節を前記データベースにマッチングすることとを含む、請求項２に記載の方法。 The method further
Receiving the clarification from the user device and
Updating the perspective tree based on the clarification,
The method of claim 2, comprising matching updated clauses from the perspective tree to the database.
キーワードの１つ以上の同義語を判断することと、
前記１つ以上の同義語を前記テーブルのうちの１つのテーブルのフィールドにマッチングすることとを含む、請求項１～３のいずれか１項に記載の方法。 Matching each keyword is
Judging one or more synonyms for a keyword,
The method of any one of claims 1-3, comprising matching the one or more synonyms to a field in one of the tables.
前記カスタムデータベースインデックスを検索することによって複数の候補を得ることと、
各候補について、前記エンティティと対応する結果との間のマッチのレベルを判断することと、
すべての前記エンティティのうちで最も高いマッチのレベルを有するエンティティを判断することとを含む、請求項１～６のいずれか１項に記載の方法。 Determining the threshold level of the match is
To get multiple candidates by searching the custom database index,
For each candidate, determining the level of match between the entity and the corresponding result,
The method of any one of claims 1-6 , comprising determining which of all the said entities has the highest level of matching.
接続されたノードのセットを含むシソーラスにアクセスすることを含み、前記接続されたノードは、ルートノードおよび終端ノードを含み、前記終端ノードは、前記ルートノードの同義語であり、カスタムデータベースインデックスにアクセスすることはさらに、
反復的に、前記終端ノードの各々について、
前記ルートノードから対応の終端ノードへの経路を含む検索クエリを形成することと、
前記検索クエリを検索エンジンに提供することによって結果のセットを得ることと、
前記結果のセットの各ペアの結果のペア単位一般化を計算することとを含み、ペア単位一般化は、対応のペアの各結果に共通の１つ以上のキーワードを抽出し、カスタムデータベースインデックスにアクセスすることはさらに、反復的に、前記終端ノードの各々について、
前記ペア単位一般化から単語またはフレーズを抽出することと、
前記ペア単位一般化内で閾値頻度を超えて生ずるソートされた要素のサブセットを抽出することと、
前記抽出された要素のサブセットから新たなノードを作成することと、
前記新たなノードを対応の終端ノードに接続することとを含む、請求項１～８のいずれか１項に記載の方法。 Accessing a custom database index is
Including accessing a thesaurus containing a set of connected nodes, said connected node includes a root node and a terminal node, said terminal node is a synonym for said root node and accesses a custom database index. To do more
Iteratively, for each of the termination nodes
Forming a search query that includes a route from the root node to the corresponding terminating node,
To get a set of results by providing the search query to a search engine,
Including calculating the pair-based generalization of the results of each pair of the above set of results, the pair-based generalization extracts one or more keywords common to each result of the corresponding pair and puts them in a custom database index. Access is further iteratively for each of the termination nodes.
Extracting words or phrases from the pair-based generalization,
Extracting a subset of sorted elements that occur above the threshold frequency within the pair-based generalization.
Creating a new node from the subset of the extracted elements,
The method of any one of claims 1-8 , comprising connecting the new node to the corresponding termination node.
コンピュータ実行可能プログラム命令を記憶するコンピュータ可読媒体と、
前記コンピュータ可読媒体に通信可能に結合され、前記コンピュータ実行可能プログラム命令を実行するための処理装置とを備え、前記コンピュータ実行可能プログラム命令を実行することは、動作を実行するように前記処理装置を構成し、前記動作は、
テーブルを有するデータベースにアクセスすることを含み、各テーブルは、前記各テーブルを識別するラベルと、フィールドとを含み、各フィールドは属性を含み、前記動作はさらに、
エンティティを含むカスタムデータベースインデックスにアクセスすることを含み、前記エンティティは、前記フィールドと、前記属性と、前記フィールドまたは前記属性の１つ以上の同義語とを含み、前記動作はさらに、
自然言語検索クエリにアクセスすることと、
前記自然言語検索クエリからパースツリーを構築することとを含み、前記パースツリーは、単語タイプを含む少なくとも１つの終端ノードと、前記自然言語検索クエリの単語またはフレーズを表す少なくとも１つの終端ノードとを含み、前記パースツリーは、前記自然言語検索クエリの構文情報を識別し、前記動作はさらに、
前記パースツリーから１つ以上の節を識別することを含み、節はキーワードを含み、各キーワードは名詞または動詞であり、前記動作はさらに、
以下の１つ以上、すなわち、
各キーワードを、（ｉ）前記テーブルのうちの１つのテーブルのラベルまたは（ｉｉ）前記テーブルのうちの１つのテーブルのフィールドまたは（ｉｉｉ）フィールドの属性のいずれかにマッチングさせること、および
前記キーワードと前記カスタムデータベースインデックスとの間のマッチの閾値レベルを判断すること、の１つ以上を実行することと、
前記マッチングされたキーワードからデータベースクエリを生成することと、
前記データベースクエリを前記データベースに提供することによって前記データベースから結果を得ることと、
前記結果をユーザデバイスに表示することとを含む、システム。 It ’s a system,
A computer-readable medium that stores computer -executable program instructions,
Communicably coupled to the computer-readable medium, provided with a processing device for executing the computer -executable program instruction, executing the computer -executable program instruction is to perform an operation. The processing device is configured, and the operation is
Each table comprises accessing a database having tables, each table comprises a label identifying each of the tables, a field, each field comprises an attribute, and the behavior further comprises.
Containing access to a custom database index containing an entity, the entity comprises the field, the attribute, and one or more synonyms for the field or the attribute, the behavior further comprising.
Accessing natural language search queries and
Containing building a perspective tree from the natural language search query, the perspective tree comprises at least one termination node containing a word type and at least one termination node representing a word or phrase in the natural language search query. The perspective tree contains, and the behavior further identifies the syntax information of the natural language search query.
The action comprises further identifying one or more clauses from the perspective tree, the clauses containing keywords, each keyword being a noun or verb, and the action further.
One or more of the following, ie
Matching each keyword to either (i) the label of one of the tables or (ii) the field of one of the tables or the attribute of the field (iii), and with the keyword. Performing one or more of determining the threshold level of a match with the custom database index,
Generating a database query from the matched keywords
Obtaining results from the database by providing the database query to the database
A system comprising displaying the results on a user device.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US201862703389P | 2018-07-25 | 2018-07-25 | |
| US62/703,389 | 2018-07-25 | ||
| PCT/US2019/043505 WO2020023787A1 (en) | 2018-07-25 | 2019-07-25 | Natural language interfaces for databases using autonomous agents and thesauri |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| JP2021530818A JP2021530818A (en) | 2021-11-11 |
| JPWO2020023787A5 true JPWO2020023787A5 (en) | 2022-04-14 |
| JP7449919B2 JP7449919B2 (en) | 2024-03-14 |
Family
ID=67544463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2021503796A Active JP7449919B2 (en) | 2018-07-25 | 2019-07-25 | Natural language interface for autonomous agents and databases with thesaurus |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US10592505B2 (en) |
| EP (1) | EP3788503A1 (en) |
| JP (1) | JP7449919B2 (en) |
| CN (1) | CN112437917B (en) |
| WO (1) | WO2020023787A1 (en) |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299219B (en) * | 2018-08-31 | 2022-08-12 | 北京奥星贝斯科技有限公司 | Data query method and device, electronic equipment and computer readable storage medium |
| US11360969B2 (en) * | 2019-03-20 | 2022-06-14 | Promethium, Inc. | Natural language based processing of data stored across heterogeneous data sources |
| US11734325B2 (en) * | 2019-04-30 | 2023-08-22 | Salesforce, Inc. | Detecting and processing conceptual queries |
| US11789940B2 (en) * | 2019-08-16 | 2023-10-17 | American Express Travel Related Services Company, Inc. | Natural language interface to databases |
| US11222013B2 (en) * | 2019-11-19 | 2022-01-11 | Sap Se | Custom named entities and tags for natural language search query processing |
| CN111666372B (en) * | 2020-04-29 | 2023-08-18 | 百度在线网络技术（北京）有限公司 | Method, device, electronic equipment and readable storage medium for analyzing query word query |
| CN111625554B (en) * | 2020-07-30 | 2020-11-03 | 武大吉奥信息技术有限公司 | Data query method and device based on deep learning semantic understanding |
| CA3135717A1 (en) * | 2020-10-23 | 2022-04-23 | Royal Bank Of Canada | System and method for transferable natural language interface |
| US11403326B2 (en) | 2020-12-03 | 2022-08-02 | International Business Machines Corporation | Message-based event grouping for a computing operation |
| US11599404B2 (en) | 2020-12-03 | 2023-03-07 | International Business Machines Corporation | Correlation-based multi-source problem diagnosis |
| US11995562B2 (en) | 2020-12-03 | 2024-05-28 | International Business Machines Corporation | Integrating documentation knowledge with log mining for system diagnosis |
| US11513930B2 (en) | 2020-12-03 | 2022-11-29 | International Business Machines Corporation | Log-based status modeling and problem diagnosis for distributed applications |
| US11474892B2 (en) | 2020-12-03 | 2022-10-18 | International Business Machines Corporation | Graph-based log sequence anomaly detection and problem diagnosis |
| US11243835B1 (en) | 2020-12-03 | 2022-02-08 | International Business Machines Corporation | Message-based problem diagnosis and root cause analysis |
| US11797538B2 (en) | 2020-12-03 | 2023-10-24 | International Business Machines Corporation | Message correlation extraction for mainframe operation |
| US20220180056A1 (en) * | 2020-12-09 | 2022-06-09 | Here Global B.V. | Method and apparatus for translation of a natural language query to a service execution language |
| CN112819512B (en) * | 2021-01-22 | 2023-03-24 | 北京有竹居网络技术有限公司 | Text processing method, device, equipment and medium |
| WO2022164724A1 (en) | 2021-01-27 | 2022-08-04 | Verantos, Inc. | High validity real-world evidence study with deep phenotyping |
| US12008043B2 (en) * | 2021-03-29 | 2024-06-11 | Microsoft Technology Licensing, Llc | Natural language query processing and debugging |
| US11500865B1 (en) | 2021-03-31 | 2022-11-15 | Amazon Technologies, Inc. | Multiple stage filtering for natural language query processing pipelines |
| US11604794B1 (en) | 2021-03-31 | 2023-03-14 | Amazon Technologies, Inc. | Interactive assistance for executing natural language queries to data sets |
| US11726994B1 (en) | 2021-03-31 | 2023-08-15 | Amazon Technologies, Inc. | Providing query restatements for explaining natural language query results |
| US11494557B1 (en) * | 2021-05-17 | 2022-11-08 | Verantos, Inc. | System and method for term disambiguation |
| JP7472078B2 (en) * | 2021-05-20 | 2024-04-22 | 株式会社東芝 | Data virtualization apparatus and method |
| CN113553414B (en) * | 2021-06-30 | 2023-08-25 | 北京百度网讯科技有限公司 | Intelligent dialogue method, intelligent dialogue device, electronic equipment and storage medium |
| CN113449003B (en) * | 2021-07-07 | 2024-04-16 | 京东科技控股股份有限公司 | Information query method, device, electronic equipment and medium |
| US20230127907A1 (en) * | 2021-10-22 | 2023-04-27 | International Business Machines Corporation | Intention identification in dialogue system |
| CN114048312B (en) * | 2021-11-09 | 2024-06-21 | 中国人民银行清算总中心 | Model input information processing method and device for natural language query task |
| KR20230079729A (en) * | 2021-11-29 | 2023-06-07 | 주식회사 포티투마루 | Method for converting natural language query to sql and device thereof |
| US20230177277A1 (en) * | 2021-12-06 | 2023-06-08 | International Business Machines Corporation | Contextual dialogue framework over dynamic tables |
| CN115374765B (en) * | 2022-10-27 | 2023-06-02 | 浪潮通信信息系统有限公司 | Computing power network 5G data analysis system and method based on natural language processing |
| CN116628140B (en) * | 2023-07-20 | 2023-10-27 | 湖南华菱电子商务有限公司 | Information pushing method and device based on man-machine interaction and man-machine interaction system |
| CN117271767B (en) * | 2023-09-15 | 2024-02-13 | 上海海启科技有限公司 | Operation and maintenance knowledge base establishing method based on multiple intelligent agents |
| CN117708304B (en) * | 2024-02-01 | 2024-05-28 | 浙江大华技术股份有限公司 | Database question-answering method, equipment and storage medium |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0944508A (en) * | 1995-07-27 | 1997-02-14 | Toshiba Corp | Data base natural language interface device and its method |
| JP2002207761A (en) * | 2001-01-10 | 2002-07-26 | Just Syst Corp | Searching device, searching method, program and recording medium |
| JP2002288201A (en) * | 2001-03-23 | 2002-10-04 | Fujitsu Ltd | Question-answer processing method, question-answer processing program, recording medium for the question- answer processing program, and question-answer processor |
| JP2002342361A (en) * | 2001-05-15 | 2002-11-29 | Mitsubishi Electric Corp | Information retrieving device |
| JP2005208825A (en) * | 2004-01-21 | 2005-08-04 | Toshiba Corp | Data retrieval system, data retrieval method and program |
| US10417247B2 (en) * | 2014-09-25 | 2019-09-17 | Oracle International Corporation | Techniques for semantic searching |
| CN107016011B (en) * | 2015-09-11 | 2021-03-30 | 谷歌有限责任公司 | Disambiguation of join paths for natural language queries |
| US9959311B2 (en) * | 2015-09-18 | 2018-05-01 | International Business Machines Corporation | Natural language interface to databases |
| US10489393B1 (en) * | 2016-03-30 | 2019-11-26 | Amazon Technologies, Inc. | Quasi-semantic question answering |
| US10657124B2 (en) * | 2016-12-08 | 2020-05-19 | Sap Se | Automatic generation of structured queries from natural language input |
| US10691685B2 (en) * | 2017-06-03 | 2020-06-23 | Apple Inc. | Converting natural language input to structured queries |
| CN107885786B (en) * | 2017-10-17 | 2021-10-26 | 东华大学 | Natural language query interface implementation method facing big data |
| CN108052547B (en) * | 2017-11-27 | 2019-09-27 | 华中科技大学 | Natural language question-answering method and system based on question sentence and knowledge graph structural analysis |
| US11409737B2 (en) * | 2017-11-29 | 2022-08-09 | Resilient Cognitive Solutions, LLC | Interactive structured analytic systems |
-
2019
- 2019-07-25 US US16/522,549 patent/US10592505B2/en active Active
- 2019-07-25 WO PCT/US2019/043505 patent/WO2020023787A1/en unknown
- 2019-07-25 EP EP19750015.0A patent/EP3788503A1/en not_active Withdrawn
- 2019-07-25 CN CN201980046615.9A patent/CN112437917B/en active Active
- 2019-07-25 JP JP2021503796A patent/JP7449919B2/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JPWO2020023787A5 (en) | ||
| Baik et al. | Bridging the semantic gap with SQL query logs in natural language interfaces to databases | |
| CN107993724B (en) | Medical intelligent question and answer data processing method and device | |
| CN112069298B (en) | Man-machine interaction method, device and medium based on semantic web and intention recognition | |
| US8041697B2 (en) | Semi-automatic example-based induction of semantic translation rules to support natural language search | |
| US9715493B2 (en) | Method and system for monitoring social media and analyzing text to automate classification of user posts using a facet based relevance assessment model | |
| JP3719415B2 (en) | Information search method, information search system, and program | |
| US8463593B2 (en) | Natural language hypernym weighting for word sense disambiguation | |
| US20170308607A1 (en) | Method and System for a Semantic Search Engine | |
| US20160041986A1 (en) | Smart Search Engine | |
| KR100546743B1 (en) | Method for automatically creating a question and indexing the question-answer by language-analysis and the question-answering method and system | |
| US20070185831A1 (en) | Information retrieval | |
| JP2001511564A (en) | Apparatus and method for information retrieval system using natural language processing of search results to increase overall accuracy | |
| CN113268569B (en) | Semantic-based related word searching method and device, electronic equipment and storage medium | |
| JP2011118689A (en) | Retrieval method and system | |
| US20190266286A1 (en) | Method and system for a semantic search engine using an underlying knowledge base | |
| WO2019141801A1 (en) | Method for processing a question in natural language | |
| JP2008021270A (en) | Data conversion apparatus and its method, database management apparatus and its method, and database search system and its method | |
| Juan | An effective similarity measurement for FAQ question answering system | |
| US20190012388A1 (en) | Method and system for a semantic search engine using an underlying knowledge base | |
| Wang et al. | Semi-supervised chinese open entity relation extraction | |
| JP2022546228A (en) | Resolution of queries using structured and unstructured data | |
| KR102411778B1 (en) | Server, method and computer program for infering comparative advantage of multiple knowledge | |
| WO2012143839A1 (en) | A computerized system and a method for processing and building search strings | |
| KR20030006201A (en) | Integrated Natural Language Question-Answering System for Automatic Retrieving of Homepage |