WO2020037217A1 - Techniques for building a knowledge graph in limited knowledge domains - Google Patents

Techniques for building a knowledge graph in limited knowledge domains Download PDF

Info

Publication number
WO2020037217A1
WO2020037217A1 PCT/US2019/046841 US2019046841W WO2020037217A1 WO 2020037217 A1 WO2020037217 A1 WO 2020037217A1 US 2019046841 W US2019046841 W US 2019046841W WO 2020037217 A1 WO2020037217 A1 WO 2020037217A1
Authority
WO
WIPO (PCT)
Prior art keywords
entities
knowledge graph
graph
entries
computer
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.)
Ceased
Application number
PCT/US2019/046841
Other languages
English (en)
French (fr)
Inventor
Gautam Singaraju
Prithviraj Venkata AMMANABROLU
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.)
Oracle International Corp
Original Assignee
Oracle International Corp
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 Oracle International Corp filed Critical Oracle International Corp
Priority to EP19762050.3A priority Critical patent/EP3837642A1/en
Priority to CN202510377080.0A priority patent/CN120297390A/zh
Priority to CN201980053458.4A priority patent/CN112567394B/zh
Priority to JP2021507744A priority patent/JP7387714B2/ja
Publication of WO2020037217A1 publication Critical patent/WO2020037217A1/en
Anticipated expiration legal-status Critical
Priority to JP2023194404A priority patent/JP2024023311A/ja
Priority to JP2025179680A priority patent/JP2026027289A/ja
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F16/35—Clustering; Classification
    • G06F16/353—Clustering; Classification into predefined classes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/268—Morphological analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/096—Transfer learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/041—Abduction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • FIG. 1 depicts a distributed system that implements a bot system for communicating with end users using a messaging application according to certain embodiments.
  • entities can be extracted from the small user dataset (including, e.g., user utterances, intents, entities, and QnAs) for a custom application (e.g., a chatbot) based on certain rules.
  • a seed graph can be generated based on the extracted entities and connections or relations between the entities.
  • Large-scale reference knowledge graphs such as WikiData, can then be traversed using a finite state machine to identify candidate entities and/or relations to be added to the seed graph to expand the seed graph into a customized knowdedge graph for the custom application. The traversal may also help to identify possible additional relations between entities in the user dataset and relevant facts from the reference knowledge graph.
  • the term“intents” may refer to categories of actions or tasks users expect a skill to perform for them.
  • the term“entities” may refer to variables that identify key information from user input that enable the skill to fulfill a task.
  • the term“components” may refer to various functions a skill can use to respond to users.
  • the term“components” may refer to generic functions, such as outputting text, or returning information from a backend and performing custom logic.
  • the term“dialog flow” may refer to the definition of the skill-user interaction and may describe how a skill responds and behaves according to user inputs.
  • the term“channels” may refer to platform-specific configurations to allow the skills to access messaging platforms or client messaging apps. A single skill may have several channels configured for it so that it can run on different services or platforms simultaneously.
  • FIG. 1 depicts a distributed system 100 that may be used to implement a bot system for communicating with an end user using a messaging application according to certain embodiments.
  • System 100 may include a bot system 120, one or more messaging application systems 1 15, and one or more end user devices, such as one or more mobile devices 110.
  • the messaging application may be installed on an electronic device (e.g., a desktop computer, a laptop, mobile device 110, or the like).
  • connector 130 may route the content to a message-in queue 140.
  • Message-in queue 140 may include a buffer (e.g., a first-in first-out (FIFO) buffer) that stores content in the order received.
  • FIFO first-in first-out
  • each connector 130 may be associated with one or more message-in queues.
  • a purpose of the message may be to order a pizza, order a computer, transfer money, ask a question regarding delivery', etc.
  • parameters associated with the intent that more specifically define or clarify the action to take which may be referred to as entities, may also be extracted from the message by natural language processor 152 and/or intent determination subsystem 154
  • Bot system 120 may communicate with one or more enterprise services (e.g., enterprise service 125), one or more storage systems for storing and/or analyzing messages received by bot system 120, or a content system for providing content to bot system 120.
  • Enterprise service 125 may communicate with one or more of connector 130, action engine 160, or any combination thereof.
  • Enterprise service 125 may communicate with connector 130 in a manner similar to messaging application system 115.
  • Enterprise service 125 may send content to connector 130 to be associated with one or more end users.
  • Enterprise service 125 may also send content to connector 130 to cause bot system 120 to perform an action associated with an end user.
  • Action engine 160 may communicate with enterprise service 125 to obtain information from enterprise service 125 and/or to instruct enterprise sendee 125 to take an action identified by action engine 160.
  • the response may include a greeting with the name of the end user, such as“Hi Tom, What can I do for you?”.
  • the bot system may progress to accomplish a goal of the enterpri se. For example, if the bot system is associated with a pizza delivery enterprise, the bot system may send a message to the end user asking if the end user would like to order pizza. The conversation between the bot system and the end user may continue from there, going back and forth, until the bot system has completed the conversation or the end user stops responding to the bot system.
  • the bot system may maintain information between conversations. The information may be used later so that the bot system does not need to ask some questions every time a new conversation is started between the end user and the bot system. For example, the bot system may store information regarding a previous order of pizza by the end user. In a new conversation, the bot system may send a message to the end user that asks if the end user wants the same order as last time.
  • conversation events may be generated by dialog engine 212.
  • a conversation event may include a message received by a bot system from an end user device (referred to as msg_received).
  • Msg_received may include one or more of the following parameters or variables: the content of the message, the time when the message is received by the bot system, the language of the message received, a device property (e.g., version or name), an operating system property (e.g., version or name), a geolocation property (e.g, an Internet Protocol address, a latitude, a longitude, or the like), identification information (e.g, a user ID, a session ID, a bot system ID, a tenant ID, or the like), a time stamp (e.g., device created, device sent, collector derived time stamp), the channel, or the like.
  • a device property e.g., version or name
  • an operating system property e.g., version or name
  • geolocation property e.g, an Internet Protocol
  • An entity resolver event may be captured at an entity- resolution
  • attributes associated with an entity resolver event may include an entity name, a rule applied, a search term, a state resolved, a query statement, an entity type, a time of execution, a communication language, a device property, an operating system property, a browser property, an app property, a geoiocation property, identification information, a time stamp, a channel, or the like.
  • the entity name may be a name of an entity currently being resolved.
  • the rule applied may be, for example, preceding, following, or aggregate.
  • the search term may be from, to, destination, origin, or the like.
  • the state resolved may be a dialog state resolved for the entity.
  • the query statement may be a message containing entity value.
  • the high-level intent of “purchase shoes” may be fed into the user intent classification engine, and training phrases, such as“I want to buy some shoes”,“I am looking for a pair of shoes”,“I want shoes,” and the like, may also be provided to train the user intent classification engine.
  • the user intent classification engine may attempt to expand on the example phrases and use the example phrases to match user utterance.
  • the entities may be detected from the user dataset using entity linking techniques, such as the Dexter 2 technique (see, e.g, Ceccare!li et ak,“Dexter: an open source framework for entity linking,” Proceedings of the sixth international workshop on Exploiting semantic annotations in information retrieval, ACM 2013, pp. 17-20).
  • entity linking techniques such as the Dexter 2 technique (see, e.g, Ceccare!li et ak,“Dexter: an open source framework for entity linking,” Proceedings of the sixth international workshop on Exploiting semantic annotations in information retrieval, ACM 2013, pp. 17-20).
  • a simulated annealing optimization method (see, e.g., Nourani & Andresen,“A comparison of simulated annealing cooling strategies,” J. Phys. A: Math. Gen. 51. 1998, 8373-8385) may be used to iteratively expand the seed graph by gradually adding entities and relations to the seed graph.
  • a temperature value may be set or adjusted at 508. The temperature may be used for determining priority scores of candidate entities to add to the knowledge graph as described in detail below.
  • WCCfG is a weakly connected component function used to identify weakly- connected components in a graph
  • t is the current time step
  • T(t) is the temperature at time t k h
  • Z are real constants
  • G’ is a ne ' graph formed by the union of a graph G with the set of edges between (w, e).
  • New' graph G’ can be represented by:
  • Portable handheld devices may include cellular phones, smartphones, (e.g., an iPhone ® ), tablets (e.g, iPad ® ), personal digital assistants (PDAs), and the like.
  • Wearable devices may include Google Glass ® head mounted display, and other devices.
  • Gaming systems may include various handheld gaming devices, Internet-enabled gaming devices (e.g., a Microsoft Xbox ® gaming console with or without a Kinect ® gesture input device,
  • FIG. 11 is a simplified block diagram of a cloud-based system environment in which various sendees may be offered as cloud services, in accordance with certain embodiments.
  • cloud infrastructure system 1102 may provide one or more cloud se dees that may be requested by users using one or more client devices 1104, 1106, and 1108.
  • Cloud infrastructure system 1102 may comprise one or more computers and/or servers that may include those described above for server 812.
  • the computers in cloud infrastructure system 1102 may be organized as general purpose computers, specialized server computers, server farms, server clusters, or any other appropriate arrangement and/or combination.
  • cloud service is generally used to refer to a service that is made available to users on demand and via a communication network such as the Internet by systems (e.g., cloud infrastructure system 1102) of a service provider.
  • systems e.g., cloud infrastructure system 1102
  • cloud service provider e.g., a public cloud environment
  • servers and systems that make up the cloud sendee provider’s system are different from the customer’s own on-premise servers and systems.
  • the cloud service provider’s systems are managed by the cloud service provider. Customers can thus avail themselves of cloud services provided by a cloud service provider without having to purchase separate licenses, support, or hardware and software resources for the sendees.
  • a cloud service provider’s system may host an application, and a user may, via the Internet, on demand, order and use the application without the user having to buy infrastructure resources for executing the application.
  • Cloud services are designed to provide easy, scalable access to applications, resources and sendees.
  • Several providers offer cloud services. For example, several cloud services are offered by Oracle Corporation® of Redwood Shores, California, such as middleware services, database services, Java cloud sendees, and others.
  • Cloud infrastructure system 1102 may comprise multiple subsystems. These subsystems may be implemented in software, or hardware, or combinations thereof. As depicted in FIG. 11, the subsystems may include a user interface subsystem 1112 that enables users or customers of cloud infrastructure system 1 102 to interact with cloud infrastructure system 1102. User interface subsystem 1 1 12 may include various different interfaces such as a web interface 1114, an online store interface 1116 where cloud sendees provided by cloud infrastructure system 1 102 are advertised and are purchasable by a consumer, and other interfaces 1118. For example, a customer may, using a client device, request (sendee request 1134) one or more services provided by cloud infrastructure system 1102 by placing subscription orders using one or more of interfaces 1114, 11 16, and 1118.
  • Storage subsystem 1218 provides a repository' or data store for storing information and data that is used by computer system 1200.
  • Storage subsystem 1218 provides an example of a tangible n on-transitory computer-readable storage medium for storing the basic programming and data constructs that provide the functionality of some embodiments.
  • system memory 1210 may load application programs 1212 that are being executed, which may include various applications such as Web browsers, mid-tier applications, relational database management systems (RDBMS), and the like, program data 1214, and an operating system 1216.
  • application programs 1212 may include various applications such as Web browsers, mid-tier applications, relational database management systems (RDBMS), and the like, program data 1214, and an operating system 1216.
  • RDBMS relational database management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Animal Behavior & Ethology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/US2019/046841 2018-08-16 2019-08-16 Techniques for building a knowledge graph in limited knowledge domains Ceased WO2020037217A1 (en)

Priority Applications (6)

Application Number Priority Date Filing Date Title
EP19762050.3A EP3837642A1 (en) 2018-08-16 2019-08-16 Techniques for building a knowledge graph in limited knowledge domains
CN202510377080.0A CN120297390A (zh) 2018-08-16 2019-08-16 用于在有限的知识领域中构建知识图的技术
CN201980053458.4A CN112567394B (zh) 2018-08-16 2019-08-16 用于在有限的知识领域中构建知识图的技术
JP2021507744A JP7387714B2 (ja) 2018-08-16 2019-08-16 限られた知識ドメイン内でナレッジグラフを構築するための技術
JP2023194404A JP2024023311A (ja) 2018-08-16 2023-11-15 限られた知識ドメイン内でナレッジグラフを構築するための技術
JP2025179680A JP2026027289A (ja) 2018-08-16 2025-10-24 限られた知識ドメイン内でナレッジグラフを構築するための技術

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201862765005P 2018-08-16 2018-08-16
US62/765,005 2018-08-16
US16/542,017 US11625620B2 (en) 2018-08-16 2019-08-15 Techniques for building a knowledge graph in limited knowledge domains
US16/542,017 2019-08-15

Publications (1)

Publication Number Publication Date
WO2020037217A1 true WO2020037217A1 (en) 2020-02-20

Family

ID=69523284

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2019/046841 Ceased WO2020037217A1 (en) 2018-08-16 2019-08-16 Techniques for building a knowledge graph in limited knowledge domains

Country Status (5)

Country Link
US (2) US11625620B2 (https=)
EP (1) EP3837642A1 (https=)
JP (3) JP7387714B2 (https=)
CN (2) CN120297390A (https=)
WO (1) WO2020037217A1 (https=)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112799928A (zh) * 2021-01-29 2021-05-14 北京索为系统技术股份有限公司 基于知识图谱的工业app关联性分析方法、装置及介质
JPWO2021210148A1 (https=) * 2020-04-16 2021-10-21
CN113892865A (zh) * 2021-10-29 2022-01-07 珠海格力电器股份有限公司 清洁机器人清洁策略生成方法与装置
JP2022031625A (ja) * 2020-09-15 2022-02-22 ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド 情報をプッシュするための方法および装置、電子機器、記憶媒体並びにコンピュータプログラム
CN114493516A (zh) * 2022-01-18 2022-05-13 安徽大学 一种基于异质图对比学习的云erp下知识补全方法及系统
CN114745286A (zh) * 2022-04-13 2022-07-12 电信科学技术第五研究所有限公司 基于知识图谱技术面向动态网络智能网络态势感知系统
JP2023070000A (ja) * 2021-11-08 2023-05-18 エヌビディア コーポレーション 対話環境におけるニューラル・ネットワークを使用したユーザの意図及び関連するエンティティの認識
JP2024503519A (ja) * 2021-01-20 2024-01-25 オラクル・インターナショナル・コーポレイション 自然言語プロセッサのための複数特徴均衡化
JP2024513293A (ja) * 2021-04-12 2024-03-25 インターナショナル・ビジネス・マシーンズ・コーポレーション トランスフォーマベースのモデルナレッジグラフリンク予測
WO2024065778A1 (en) * 2022-09-30 2024-04-04 Siemens Aktiengesellschaft Method, apparatus, device, and medium for building knowledge graph and executing workflow
US20240354320A1 (en) * 2013-09-20 2024-10-24 Fulcrum Management Solutions Ltd. System and method for diverse thought object selection using llm and embedding models

Families Citing this family (124)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220004366A1 (en) 2016-10-17 2022-01-06 Engineer.ai Naya Limited Advanced software development application methods, systems, and computer readable medium
US12314689B2 (en) 2016-10-17 2025-05-27 Engineer.ai Corp Application development involving instant prototyping
US10902323B2 (en) * 2017-08-11 2021-01-26 Sap Se Bot framework
GB2568233A (en) * 2017-10-27 2019-05-15 Babylon Partners Ltd A computer implemented determination method and system
US11625620B2 (en) 2018-08-16 2023-04-11 Oracle International Corporation Techniques for building a knowledge graph in limited knowledge domains
US11429834B1 (en) * 2018-09-07 2022-08-30 Intuit, Inc. Neural-based agent assistance interface for providing answers based on a query vector
US11693896B2 (en) * 2018-09-25 2023-07-04 International Business Machines Corporation Noise detection in knowledge graphs
US10922493B1 (en) * 2018-09-28 2021-02-16 Splunk Inc. Determining a relationship recommendation for a natural language request
US11269870B2 (en) * 2018-10-02 2022-03-08 Adobe Inc. Performing automatic segment expansion of user embeddings using multiple user embedding representation types
US11636123B2 (en) * 2018-10-05 2023-04-25 Accenture Global Solutions Limited Density-based computation for information discovery in knowledge graphs
KR102669026B1 (ko) * 2018-10-26 2024-05-27 삼성전자주식회사 전자 장치 및 이의 제어 방법
US11663501B2 (en) * 2018-11-01 2023-05-30 American Express Travel Related Services Company, Inc. Information support system using artificial intelligence
US10977442B2 (en) * 2018-12-13 2021-04-13 Sap Se Contextualized chat bot framework
US11087091B2 (en) * 2018-12-27 2021-08-10 Wipro Limited Method and system for providing contextual responses to user interaction
US10834026B2 (en) * 2019-01-24 2020-11-10 Jiseki Health, Inc. Artificial intelligence assisted service provisioning and modification for delivering message-based services
US11080490B2 (en) * 2019-03-28 2021-08-03 Servicenow, Inc. Pre-training of virtual chat interfaces
US11301224B1 (en) 2019-04-30 2022-04-12 Automation Anywhere, Inc. Robotic process automation system with a command action logic independent execution environment
US11243803B2 (en) 2019-04-30 2022-02-08 Automation Anywhere, Inc. Platform agnostic robotic process automation
US11614731B2 (en) 2019-04-30 2023-03-28 Automation Anywhere, Inc. Zero footprint robotic process automation system
US11113095B2 (en) 2019-04-30 2021-09-07 Automation Anywhere, Inc. Robotic process automation system with separate platform, bot and command class loaders
US11227018B2 (en) * 2019-06-27 2022-01-18 International Business Machines Corporation Auto generating reasoning query on a knowledge graph
US11573961B2 (en) * 2019-07-10 2023-02-07 Microsoft Technology Licensing, Llc Delta graph traversing system
US11258741B2 (en) * 2019-08-15 2022-02-22 Rovi Guides, Inc. Systems and methods for automatically identifying spam in social media comments
US11677703B2 (en) 2019-08-15 2023-06-13 Rovi Guides, Inc. Systems and methods for automatically identifying spam in social media comments based on context
US11184298B2 (en) * 2019-08-28 2021-11-23 International Business Machines Corporation Methods and systems for improving chatbot intent training by correlating user feedback provided subsequent to a failed response to an initial user intent
US11924373B2 (en) 2019-09-09 2024-03-05 First Orion Corp. Dynamic enhanced call data assignment based on called numbers
US11115522B2 (en) 2019-09-09 2021-09-07 First Orion Corp. Customization of CNAM information for calls placed to mobile devices
US11108907B2 (en) * 2019-09-09 2021-08-31 First Orion Corp. Customization of CNAM information for calls placed to mobile devices
US11397897B2 (en) * 2019-09-10 2022-07-26 Abbas Ameri Knowledge currency
WO2021064879A1 (ja) * 2019-10-01 2021-04-08 富士通株式会社 学習方法、学習装置、学習プログラム、予測方法、予測装置および予測プログラム
WO2021072013A1 (en) * 2019-10-08 2021-04-15 Pricewaterhousecoopers Llp Intent-based conversational knowledge graph for spoken language understanding system
US11836159B2 (en) * 2019-10-11 2023-12-05 Visa International Service Association System, method, and computer program product for analyzing a relational database using embedding learning
US10891440B1 (en) * 2019-10-30 2021-01-12 Globant España, S.A. Natural language driven transaction system
WO2021108679A1 (en) 2019-11-27 2021-06-03 ConverSight.ai, Inc. Contextual and intent based natural language processing system and method
US11283839B2 (en) * 2019-12-06 2022-03-22 International Business Machines Corporation Enforcement knowledge graph-based data security rule change analysis
KR20210085775A (ko) * 2019-12-31 2021-07-08 삼성전자주식회사 전자 노트 기능을 지원하는 모바일 단말기 및 그의 제어 방법
US11443264B2 (en) 2020-01-29 2022-09-13 Accenture Global Solutions Limited Agnostic augmentation of a customer relationship management application
US11550786B1 (en) * 2020-02-04 2023-01-10 Apttus Corporation System, method, and computer program for converting a natural language query to a structured database update statement
US11615089B1 (en) 2020-02-04 2023-03-28 Apttus Corporation System, method, and computer program for converting a natural language query to a structured database query
US11574123B2 (en) * 2020-03-25 2023-02-07 Adobe Inc. Content analysis utilizing general knowledge base
US11227323B2 (en) * 2020-03-30 2022-01-18 EMC IP Holding Company LLC Smart software recommendation using an application network
US11580112B2 (en) * 2020-03-31 2023-02-14 Pricewaterhousecoopers Llp Systems and methods for automatically determining utterances, entities, and intents based on natural language inputs
US11482223B2 (en) 2020-03-31 2022-10-25 Pricewaterhousecoopers Llp Systems and methods for automatically determining utterances, entities, and intents based on natural language inputs
WO2021202282A1 (en) * 2020-03-31 2021-10-07 Pricewaterhousecoopers Llp Systems and methods for automatically determining utterances, entities, and intents based on natural language inputs
US12079584B2 (en) 2020-03-31 2024-09-03 PwC Product Sales LLC Systems and methods for conversation modeling
US11615080B1 (en) * 2020-04-03 2023-03-28 Apttus Corporation System, method, and computer program for converting a natural language query to a nested database query
US11151320B1 (en) * 2020-04-21 2021-10-19 Microsoft Technology Licensing, Llc Labeled knowledge graph based priming of a natural language model providing user access to programmatic functionality through natural language input
US11392960B2 (en) * 2020-04-24 2022-07-19 Accenture Global Solutions Limited Agnostic customer relationship management with agent hub and browser overlay
US11481785B2 (en) 2020-04-24 2022-10-25 Accenture Global Solutions Limited Agnostic customer relationship management with browser overlay and campaign management portal
EP3905097A1 (de) * 2020-04-30 2021-11-03 Robert Bosch GmbH Vorrichtung und verfahren zum bestimmen eines knowledge graph
CN111488467B (zh) * 2020-04-30 2022-04-05 北京建筑大学 地理知识图谱的构建方法、装置、存储介质及计算机设备
US11741308B2 (en) 2020-05-14 2023-08-29 Oracle International Corporation Method and system for constructing data queries from conversational input
US11037549B1 (en) * 2020-06-05 2021-06-15 Inference Communications Pty Ltd System and method for automating the training of enterprise customer response systems using a range of dynamic or generic data sets
US11574128B2 (en) 2020-06-09 2023-02-07 Optum Services (Ireland) Limited Method, apparatus and computer program product for generating multi-paradigm feature representations
US12242821B2 (en) 2020-06-16 2025-03-04 Engineer.ai Corp Systems and methods for creating software
CN111813828B (zh) * 2020-06-30 2024-02-27 北京百度网讯科技有限公司 一种实体关系挖掘方法、装置、电子设备及存储介质
US12260344B2 (en) * 2020-07-20 2025-03-25 International Business Machines Corporation Dynamic in-memory construction of a knowledge graph
KR20220014713A (ko) * 2020-07-29 2022-02-07 삼성전자주식회사 서비스의 제공을 위한 지식 그래프를 수정하는 시스템 및 방법
EP4176370B1 (en) * 2020-08-05 2026-03-11 DRIMCO GmbH Enhancement of bootstrapping for information extraction
US20220067590A1 (en) * 2020-08-28 2022-03-03 International Business Machines Corporation Automatic knowledge graph construction
KR102526501B1 (ko) * 2020-09-02 2023-04-27 고려대학교 산학협력단 질의에 대한 응답 결정 장치, 방법 및 시스템
US20240211470A1 (en) * 2020-09-11 2024-06-27 Ping Identity International, Inc. Smart signaling for never stale caching
CA3194708A1 (en) 2020-10-01 2022-04-07 Thomas KEHLER Diagnosing sources of noise in an evaluation
WO2022075897A1 (en) * 2020-10-08 2022-04-14 Telefonaktiebolaget Lm Ericsson (Publ) Root cause analysis
CN112417082B (zh) * 2020-10-14 2022-06-07 西南科技大学 一种科研成果数据消歧归档存储方法
US12106230B2 (en) * 2020-10-23 2024-10-01 International Business Machines Corporation Implementing relation linking for knowledge bases
CN112256888A (zh) * 2020-10-30 2021-01-22 南京师范大学 地理知识获取方法
US11693874B2 (en) * 2020-11-25 2023-07-04 Sap Se Framework to facilitate data access
JP7843760B2 (ja) 2020-11-30 2026-04-14 オラクル・インターナショナル・コーポレイション 自然言語処理のための距離ベースのロジット値
US11972220B2 (en) * 2020-11-30 2024-04-30 Oracle International Corporation Enhanced logits for natural language processing
CN112507040B (zh) * 2020-12-21 2023-08-08 北京百度网讯科技有限公司 多元关系生成模型的训练方法、装置、电子设备及介质
CA3146673A1 (en) * 2021-01-25 2022-07-25 Royal Bank Of Canada System and method for natural languages processing with pretained languauage models
US11636086B1 (en) * 2021-03-29 2023-04-25 Tonic AI, Inc. Multi-database subsetting
US12347418B2 (en) * 2021-03-30 2025-07-01 Five9, Inc. Systems and methods for training natural language processing models in a contact center
US12353964B2 (en) * 2021-05-04 2025-07-08 Optum, Inc. Cross-entity similarity determinations using machine learning frameworks
CN113242236B (zh) * 2021-05-08 2022-09-16 国家计算机网络与信息安全管理中心 一种网络实体威胁图谱构建方法
US11907209B2 (en) * 2021-05-26 2024-02-20 Microsoft Technology Licensing, Llc. Enforcing both syntactic and semantic correctness of domain-specific data queries
US11902308B2 (en) * 2021-06-03 2024-02-13 At&T Intellectual Property I, L.P. Detecting threat pathways using sequence graphs
CN115510196B (zh) * 2021-06-07 2024-07-23 马上消费金融股份有限公司 知识图谱的构建方法、问答方法、装置和存储介质
CN113297262B (zh) * 2021-06-18 2024-11-26 中国农业银行股份有限公司 数据流图的布局方法和装置
CN113360675B (zh) * 2021-06-25 2024-02-13 中关村智慧城市产业技术创新战略联盟 一种基于互联网开放世界的知识图谱特定关系补全方法
US11886470B2 (en) * 2021-06-29 2024-01-30 Graft, Inc. Apparatus and method for aggregating and evaluating multimodal, time-varying entities
US11809417B2 (en) 2021-06-29 2023-11-07 Graft, Inc. Apparatus and method for transforming unstructured data sources into both relational entities and machine learning models that support structured query language queries
US12019627B2 (en) 2021-07-05 2024-06-25 International Business Machines Corporation Automatically and incrementally specifying queries through dialog understanding in real time
CN113434610A (zh) * 2021-07-06 2021-09-24 中电科大数据研究院有限公司 一种基于命名规则和缓存机制的知识图谱构的操作方法
US12007868B2 (en) * 2021-07-06 2024-06-11 Google Llc Generating action elements suggesting content for ongoing tasks
US12014387B1 (en) 2021-07-23 2024-06-18 Apttus Corporation System, method, and computer program for providing a pricing platform for performing different types of pricing calculations for different customers
US11954436B2 (en) * 2021-07-26 2024-04-09 Freshworks Inc. Automatic extraction of situations
US20230033737A1 (en) * 2021-07-30 2023-02-02 Intuit Inc. Method and system of compliance scenario prediction
US11698934B2 (en) 2021-09-03 2023-07-11 Optum, Inc. Graph-embedding-based paragraph vector machine learning models
US11321538B1 (en) * 2021-10-15 2022-05-03 Dovel Technologies, Llc Ensemble natural language processing model with compliance verification
KR102678591B1 (ko) * 2021-11-02 2024-06-26 (주)미소정보기술 메시지의 의도를 추론하는 방법
KR102780200B1 (ko) * 2021-11-26 2025-03-12 주식회사 케이티 지식 그래프를 증강하는 서버, 방법 및 컴퓨터 프로그램
CN114003791B (zh) * 2021-12-30 2022-04-08 之江实验室 基于深度图匹配的医疗数据元自动化分类方法及系统
US12412571B2 (en) * 2022-01-27 2025-09-09 Accenture Global Solutions Limited Dialog flow inference based on weighted finite state automata
US20230335256A1 (en) * 2022-02-04 2023-10-19 Chanda L. Spates Support on-demand services (s.o.s) collaboration hub mobile application and collaborative (community-wide) behavior interventions delivery model
US12242801B2 (en) * 2022-02-08 2025-03-04 International Business Machines Corporation Blending graph predictions
CN114510580B (zh) * 2022-02-15 2025-07-25 广东三维家信息科技有限公司 家装设计知识图谱构建方法、装置、电子设备及存储介质
US20230274214A1 (en) * 2022-02-25 2023-08-31 Microsoft Technology Licensing, Llc Multi-level graph embedding
US12086565B2 (en) * 2022-02-28 2024-09-10 International Business Machines Corporation Meaning and sense preserving textual encoding and embedding
US12067037B1 (en) 2022-02-28 2024-08-20 Apttus Corporation System, method, and computer program for performing natural language searches for documents in a database using alternate search suggestions
US11722358B1 (en) * 2022-03-03 2023-08-08 Arista Networks, Inc. Root cause analysis for operational issues using a rules mining algorithm
WO2023211093A1 (ko) * 2022-04-24 2023-11-02 박종배 지식교차와 지식연결을 통한 연결지식 생성 방법 및 시스템
CN115048529B (zh) * 2022-05-20 2025-03-25 支付宝(杭州)信息技术有限公司 一种路径处理方法、装置、存储介质及电子设备
US12517772B2 (en) * 2022-06-30 2026-01-06 Atlassian Pty Ltd. Event processing systems and methods
US12481497B2 (en) * 2022-07-20 2025-11-25 Lti Mindtree Ltd Method and system for building and leveraging a knowledge fabric to improve software delivery lifecycle (SDLC) productivity
CN115036034B (zh) * 2022-08-11 2022-11-08 之江实验室 一种基于患者表征图的相似患者识别方法及系统
CN115359890B (zh) * 2022-10-17 2023-02-03 中科厚立信息技术(成都)有限公司 基于迁移学习的单病种资源消耗分析方法、系统及终端
JP7745528B2 (ja) * 2022-10-19 2025-09-29 Kddi株式会社 文の知識誤りを検出する知識判定装置、プログラム及び方法
US12367662B2 (en) * 2022-11-11 2025-07-22 Salesforce, Inc. Systems and methods for video models with procedure understanding
US11907673B1 (en) * 2023-02-28 2024-02-20 Fmr, Llc Enhancing chatbot recognition of user intent through graph analysis
US12457519B2 (en) * 2023-04-07 2025-10-28 Adobe Inc. Message generation based on communication loss correlation
CN116501889A (zh) * 2023-04-26 2023-07-28 日本电气株式会社 用于信息处理的方法和设备
US12511282B1 (en) 2023-05-02 2025-12-30 Microstrategy Incorporated Generating structured query language using machine learning
US12562917B2 (en) 2023-06-29 2026-02-24 International Business Machines Corporation Implementing personal knowledge graphs
US12346356B2 (en) 2023-11-02 2025-07-01 International Business Machines Corporation Graph and vector usage for automated QA system
WO2025106768A1 (en) * 2023-11-16 2025-05-22 The Trustees Of Princeton University Graph language models: distilling reliable knowledge graphs from high-quality text
US20250190575A1 (en) * 2023-12-06 2025-06-12 International Business Machines Corporation Assessing sbom accuracy and completeness
US12242503B1 (en) 2024-01-12 2025-03-04 THIA ST Co. Copilot architecture: network of microservices including specialized machine learning tools
US12367425B1 (en) 2024-01-12 2025-07-22 THIA ST Co. Copilot customization with data producer(s)
US12367426B1 (en) 2024-01-12 2025-07-22 THIA ST Co. Customization of machine learning tools with occupation training
US12536045B2 (en) * 2024-01-12 2026-01-27 THIA ST Co. Distribution of tasks among microservices in a copilot
US12481548B2 (en) 2024-01-30 2025-11-25 Dell Products L.P. Correlation enhanced causation identification for data processing system management
US12294492B1 (en) 2024-01-30 2025-05-06 Dell Products L.P. Configuration management using knowledge graphs

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180075359A1 (en) * 2016-09-15 2018-03-15 International Business Machines Corporation Expanding Knowledge Graphs Based on Candidate Missing Edges to Optimize Hypothesis Set Adjudication

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140297644A1 (en) * 2013-04-01 2014-10-02 Tencent Technology (Shenzhen) Company Limited Knowledge graph mining method and system
US9997157B2 (en) * 2014-05-16 2018-06-12 Microsoft Technology Licensing, Llc Knowledge source personalization to improve language models
US9569733B2 (en) * 2015-02-20 2017-02-14 International Business Machines Corporation Extracting complex entities and relationships from unstructured data
US10628490B2 (en) * 2015-11-05 2020-04-21 Microsoft Technology Licensing, Llc Techniques for digital entity correlation
US10423652B2 (en) * 2016-08-08 2019-09-24 Baidu Usa Llc Knowledge graph entity reconciler
EP3306501A1 (en) * 2016-10-06 2018-04-11 Fujitsu Limited A computer apparatus and method to identify healthcare resources used by a patient of a medical institution
US10366168B2 (en) * 2017-01-12 2019-07-30 Microsoft Technology Licensing, Llc Systems and methods for a multiple topic chat bot
EP3577572A4 (en) * 2017-02-06 2020-11-25 Thomson Reuters Enterprise Centre GmbH AUTOMATIC SEMANTIC TOKEN MARKING SYSTEMS AND METHODS
CN108052547B (zh) * 2017-11-27 2019-09-27 华中科技大学 基于问句和知识图结构分析的自然语言问答方法及系统
US11625620B2 (en) 2018-08-16 2023-04-11 Oracle International Corporation Techniques for building a knowledge graph in limited knowledge domains

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180075359A1 (en) * 2016-09-15 2018-03-15 International Business Machines Corporation Expanding Knowledge Graphs Based on Candidate Missing Edges to Optimize Hypothesis Set Adjudication

Non-Patent Citations (16)

* Cited by examiner, † Cited by third party
Title
ANTOINE BORDES ET AL: "Question Answering with Subgraph Embeddings", PROCEEDINGS OF THE 2014 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 1 January 2014 (2014-01-01), Stroudsburg, PA, USA, pages 615 - 620, XP055638522, DOI: 10.3115/v1/D14-1067 *
BEN HIXON ET AL: "Learning Knowledge Graphs for Question Answering through Conversational Dialog", PROCEEDINGS OF THE 2015 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, DENVER, COLORADO, USA, MAY 31-JUNE 5, 2015, 1 June 2015 (2015-06-01), Stroudsburg, PA, USA, pages 851 - 861, XP055458499, DOI: 10.3115/v1/N15-1086 *
BORDES ET AL.: "Advances in Neural Information Processing Systems 26", 2013, CURRAN ASSOCIATES, INC., article "Translating Embeddings for Modeling Multi-relational Data", pages: 2787 - 2795
CECCARELLI ET AL.: "Proceedings of the sixth international workshop on Exploiting semantic annotations in information retrieval", 2013, ACM, article "Dexter: an open source framework for entity linking", pages: 17 - 20
FAN YAN ET AL: "DKGBuilder: An Architecture for Building a Domain Knowledge Graph from Scratch", 22 March 2017, INTELLIGENT VIRTUAL AGENT. IVA 2015. LNCS; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER, BERLIN, HEIDELBERG, PAGE(S) 663 - 667, ISBN: 978-3-642-17318-9, XP047407425 *
GOIKOETXEA: "Single or multiple? combining word representations independently learned from text and wordnet", PROCEEDINGS OF AAAI, 2016
J. VITTER: "Random sampling with a reservoir", ACM TRANS. ON MATHEMATICAL SOFTWARE, vol. 1 1, no. 1, March 1985 (1985-03-01), pages 37 - 57, XP058202892, doi:10.1145/3147.3165
JENNY ROSE FINKEL ET AL.: "Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling", PROCEEDINGS OF THE 43RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2005, pages 563 - 370
KRISTINA TOUTANOVA ET AL.: "Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network", PROCEEDINGS OF HLT-NAACL, 2003, pages 252 - 259
M. FAN ET AL.: "Transition-based knowledge graph embedding with relational mapping proper- ties", PROC. 28TH PACIFIC ASIA CONF. LANGUAGE INF. CONIPUT., 2014, pages 328 - 337
MANNING ET AL.: "The Stanford CoreNLP Natural Language Processing Toolkit", PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: SYSTEM DEMONSTRATIONS, 2014, pages 55 - 60
NOURANIANDRESEN: "A comparison of simulated annealing cooling strategies", J. PHYS. A: MATH. GEN., vol. 51, 1998, pages 8373 - 8385
PENNINGTON ET AL.: "Glove: Global vectors for word representation", PROCEEDINGS OF THE EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP, 2014
See also references of EP3837642A1
VRANDECICKROTZSCH: "Wikidata: A Free Collaborative Knowledgebase", COMMUNICATIONS OF THE ACM, vol. 57, no. 10, 2014, pages 78 - 85
ZHAO XUEJIAO ET AL: "HDSKG: Harvesting domain specific knowledge graph from content of webpages", 2017 IEEE 24TH INTERNATIONAL CONFERENCE ON SOFTWARE ANALYSIS, EVOLUTION AND REENGINEERING (SANER), IEEE, 20 February 2017 (2017-02-20), pages 56 - 67, XP033080227, DOI: 10.1109/SANER.2017.7884609 *

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240354320A1 (en) * 2013-09-20 2024-10-24 Fulcrum Management Solutions Ltd. System and method for diverse thought object selection using llm and embedding models
JPWO2021210148A1 (https=) * 2020-04-16 2021-10-21
JP7375919B2 (ja) 2020-04-16 2023-11-08 富士通株式会社 オントロジー生成プログラム、オントロジー生成装置およびオントロジー生成方法
JP2022031625A (ja) * 2020-09-15 2022-02-22 ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド 情報をプッシュするための方法および装置、電子機器、記憶媒体並びにコンピュータプログラム
JP7771196B2 (ja) 2021-01-20 2025-11-17 オラクル・インターナショナル・コーポレイション 自然言語プロセッサのための複数特徴均衡化
JP2024503519A (ja) * 2021-01-20 2024-01-25 オラクル・インターナショナル・コーポレイション 自然言語プロセッサのための複数特徴均衡化
CN112799928B (zh) * 2021-01-29 2023-08-18 索为技术股份有限公司 基于知识图谱的工业app关联性分析方法、装置及介质
CN112799928A (zh) * 2021-01-29 2021-05-14 北京索为系统技术股份有限公司 基于知识图谱的工业app关联性分析方法、装置及介质
JP2024513293A (ja) * 2021-04-12 2024-03-25 インターナショナル・ビジネス・マシーンズ・コーポレーション トランスフォーマベースのモデルナレッジグラフリンク予測
JP7811072B2 (ja) 2021-04-12 2026-02-04 インターナショナル・ビジネス・マシーンズ・コーポレーション トランスフォーマベースのモデルナレッジグラフリンク予測
CN113892865A (zh) * 2021-10-29 2022-01-07 珠海格力电器股份有限公司 清洁机器人清洁策略生成方法与装置
JP2023070000A (ja) * 2021-11-08 2023-05-18 エヌビディア コーポレーション 対話環境におけるニューラル・ネットワークを使用したユーザの意図及び関連するエンティティの認識
CN114493516B (zh) * 2022-01-18 2022-12-23 安徽大学 一种基于异质图对比学习的云erp下知识补全方法及系统
CN114493516A (zh) * 2022-01-18 2022-05-13 安徽大学 一种基于异质图对比学习的云erp下知识补全方法及系统
CN114745286B (zh) * 2022-04-13 2023-11-21 电信科学技术第五研究所有限公司 基于知识图谱技术面向动态网络智能网络态势感知系统
CN114745286A (zh) * 2022-04-13 2022-07-12 电信科学技术第五研究所有限公司 基于知识图谱技术面向动态网络智能网络态势感知系统
WO2024065778A1 (en) * 2022-09-30 2024-04-04 Siemens Aktiengesellschaft Method, apparatus, device, and medium for building knowledge graph and executing workflow

Also Published As

Publication number Publication date
JP2026027289A (ja) 2026-02-18
EP3837642A1 (en) 2021-06-23
CN112567394B (zh) 2025-04-15
US20230206087A1 (en) 2023-06-29
US20200057946A1 (en) 2020-02-20
CN120297390A (zh) 2025-07-11
CN112567394A (zh) 2021-03-26
JP7387714B2 (ja) 2023-11-28
JP2021534493A (ja) 2021-12-09
US11625620B2 (en) 2023-04-11
JP2024023311A (ja) 2024-02-21
US12340316B2 (en) 2025-06-24

Similar Documents

Publication Publication Date Title
US12340316B2 (en) Techniques for building a knowledge graph in limited knowledge domains
US12182518B2 (en) Relying on discourse analysis to answer complex questions by neural machine reading comprehension
US11775572B2 (en) Directed acyclic graph based framework for training models
US12106055B2 (en) Techniques for providing explanations for text classification
US12430329B2 (en) Transforming natural language to structured query language based on multi- task learning and joint training
US12002456B2 (en) Using semantic frames for intent classification
JP2025530712A (ja) 自然言語インターフェースとして訓練されている機械学習モデルの信頼スコアの較正
US20250094725A1 (en) Digital assistant using generative artificial intelligence
JP2022547631A (ja) 自然言語処理のためのストップワードデータ拡張
JP2023530423A (ja) 堅牢な固有表現認識のためのチャットボットにおけるエンティティレベルデータ拡張
US12093253B2 (en) Summarized logical forms based on abstract meaning representation and discourse trees
CN114616560A (zh) 用于机器学习（ml）的自适应和上下文感知自动化服务组成的技术
US20240062108A1 (en) Techniques for training and deploying a named entity recognition model
US20210081799A1 (en) Compressing neural networks for natural language understanding
US12340172B2 (en) Semantic parser including a coarse semantic parser and a fine semantic parser
US12573380B2 (en) Transforming natural language to a logical form
JP7851913B2 (ja) テキスト分類についての説明を与えるための技術
JP2025528391A (ja) 名前付きエンティティ認識モデルの訓練を容易にするための適応的訓練データ拡大

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: 19762050

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021507744

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019762050

Country of ref document: EP

Effective date: 20210316

WWG Wipo information: grant in national office

Ref document number: 201980053458.4

Country of ref document: CN

WWG Wipo information: grant in national office

Ref document number: 202147005729

Country of ref document: IN