WO2022163067A1 - 文書処理プログラム、情報処理装置及び文書処理方法 - Google Patents

文書処理プログラム、情報処理装置及び文書処理方法 Download PDF

Info

Publication number
WO2022163067A1
WO2022163067A1 PCT/JP2021/041487 JP2021041487W WO2022163067A1 WO 2022163067 A1 WO2022163067 A1 WO 2022163067A1 JP 2021041487 W JP2021041487 W JP 2021041487W WO 2022163067 A1 WO2022163067 A1 WO 2022163067A1
Authority
WO
WIPO (PCT)
Prior art keywords
document
search
search keyword
information
document information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/041487
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
隆裕 村田
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.)
LegalOn Technologies Inc
Original Assignee
LegalForce Inc
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 LegalForce Inc filed Critical LegalForce Inc
Publication of WO2022163067A1 publication Critical patent/WO2022163067A1/ja
Priority to US18/359,100 priority Critical patent/US12468744B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3325—Reformulation based on results of preceding query
    • G06F16/3326—Reformulation based on results of preceding query using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
    • G06F16/3328—Reformulation based on results of preceding query using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages using graphical result space presentation or visualisation
    • 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
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/3332—Query translation
    • G06F16/3334—Selection or weighting of terms from queries, including natural language queries
    • 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

Definitions

  • the present disclosure relates to a document processing program, an information processing device, and a document processing method.
  • Patent Document 1 As a conventional technology, an information processing device has been proposed that efficiently narrows down documents by presenting the categories of search results in document search processing (see Patent Document 1, for example).
  • Patent Document 1 performs clustering on a set of documents extracted as a search result based on a search condition input by a user, and provides the user with a category name representing the largest cluster with the largest number of classified documents.
  • the category is presented to let the user select whether the category is the category for which the search condition is to be searched, and according to the selection result, the document set within the maximum cluster or the document set within the other clusters is presented as the search result.
  • the search result is narrowed down by allowing the user to select a category from the set of documents extracted as the search result based on the search condition entered by the user, but the category is selected.
  • An object of the present disclosure is to provide a more user-friendly document processing program, information processing apparatus, and document processing method based on the above conventional technology.
  • One aspect of the invention according to the present disclosure provides the following document processing program, information processing apparatus, and document processing method in order to achieve the above object.
  • a computer A search keyword input field for searching document information stored in a storage unit based on an input search keyword, a type display area for selectively displaying a type determined based on the content of the document information, and the past document information.
  • a search keyword display area for displaying a search keyword based on the search history of (1) together with the number of search results of the document information searched by the search keyword; and output control means for outputting information for displaying the document information.
  • a memory configured to store document information in addition to predetermined instructions; Based on instructions stored in the memory, A search keyword input field for searching document information stored in a storage unit based on an input search keyword, a type display area for selectively displaying a type determined based on the content of the document information, and the past document information.
  • FIG. 1 is a schematic diagram showing an example configuration of a document processing system according to an embodiment.
  • FIG. 2 is a block diagram showing a configuration example of the document processing server device according to the embodiment.
  • FIG. 3 is a schematic diagram showing a configuration example of document information.
  • FIG. 4 is a schematic diagram showing a configuration example of specific contents of document information.
  • FIG. 5 is a schematic diagram showing a configuration example of contract type information.
  • FIG. 6 is a schematic diagram showing a configuration example of search keyword information.
  • FIG. 7 is a schematic diagram showing an example of the configuration of a search screen.
  • FIG. 8 is a schematic diagram showing an example of the configuration of a screen showing search results.
  • FIG. 9 is a flow chart showing an operation example of the document processing server device.
  • FIG. 1 is a schematic diagram showing an example configuration of a document processing system according to an embodiment.
  • This document processing system 5 is configured by connecting a document processing server device 1, a terminal 2, and a terminal 3 through a network 4 so that they can communicate with each other.
  • the terminal 2 is operated by a user who desires document management, document creation, document content confirmation, and/or document review
  • the terminal 3 is operated by another user, but is not limited to this.
  • the user of the terminal 2 and the user of the terminal 3 handle, for example, a contract and/or a standard document that defines standards for reviewing the contract as document information, and confirm the contents of the contract.
  • the document processing system 5 is mainly used to manage document information created by one or both of the users, and to search and narrow down the document information to be managed.
  • the document processing server device 1 is a server-type information processing device that operates in response to requests from the terminals 2 and 3.
  • the document processing server device 1 has a CPU (Central Processing Unit) having a function for processing information within its main body. ), HDD (Hard Disk Drive), and electronic components such as flash memory. Note that the document processing server device 1 does not necessarily have to consist of a single information processing device. can be anything. Also, the function of the document processing server device 1 may be realized within the terminal 2 and/or the terminal 3.
  • the terminals 2 and 3 are information processing devices such as PCs (Personal Computers) and tablet terminals, and are equipped with electronic components such as CPUs and flash memories that have functions for processing information.
  • PCs Personal Computers
  • CPUs Central Computers
  • flash memories that have functions for processing information.
  • the network 4 is a communication network capable of high-speed communication, such as a wired or wireless communication network such as the Internet, an intranet, or a LAN (Local Area Network).
  • a wired or wireless communication network such as the Internet, an intranet, or a LAN (Local Area Network).
  • the document processed by the document processing server device 1 is a document in the legal field such as a contract, and one or both of the users are not legal experts, but may read the contract and/or the contract.
  • one or both of the users are employees of the company's sales department or employees of the company's legal department.
  • contract when it is described as "contract” below, it shall include the contract and/or the standard document.
  • the document processing server device 1 receives the document information 111 under contract in order to reduce the user's workload for searching and narrowing down. Classify into types, display a list of contract types included in the document information to be searched and a list of search keywords with the top search history, display the number of hits for the search keywords, and Recalculate the number of hits and dynamically output changes in search results due to changes in search target types or search keywords.
  • the contract types included in the document information of the search results are displayed in a selectable manner, and changes in the contract types included in the search results are dynamically output.
  • a specific example of the display method will be described later.
  • a clause may be referred to as a "clause”. Embodiments are described below.
  • terminals 2 and terminal 3 may be connected to the network 4, and similarly, a plurality of users may operate these terminals.
  • FIG. 2 is a block diagram showing a configuration example of the document processing server device 1 according to the embodiment.
  • the document processing server device 1 comprises a CPU and the like, controls each part and executes various programs, a storage unit 11 comprising a storage medium such as a flash memory for storing information, and a network 4. and a communication unit 12 functioning as a communication interface for communicating with the outside via the.
  • the control unit 10 is composed of a processor such as a CPU, and is electrically connected to a storage unit 11 composed of a memory and a communication unit 12 functioning as a communication interface.
  • the control unit 10 functions as a document reception unit 100, a document classification unit 101, a document search unit 102, an output control unit 103, and the like by executing a document processing program 110, which will be described later.
  • the document accepting means 100 accepts, for example, a contract as document information 111 from the terminal 2 or terminal 3 and stores it in the storage unit 11 .
  • the document information 111 may be image information such as PDF in which sentences are laid out, or information such as a text file containing text data, a word file, or the like. If the document information 111 is information other than text, the document reception unit 100 converts it into text by performing OCR (Optical Character Recognition) or the like.
  • the document classification means 101 analyzes the constituent elements of the contract such as the title, preface, and clause unit of the document information 111 , classifies them into predetermined categories, and stores them in the storage unit 11 as contract type information 112 . . A specific classification method will be described later.
  • the document search means 102 searches the document information 111 using at least one of the contract type, search keyword, and search keyword with the highest past search history as a search condition.
  • the document search unit 102 calculates the number of hits in the document information 111 when the search keyword with the highest search history in the past is used as the search condition.
  • the document search means 102 calculates the number of hits when either or both of the contract type and the search keyword are used as search conditions, and when these and the search keywords with the highest search history in the past are used as search conditions. do.
  • the output control means 103 displays the document information 111, the contract type information 112, the search keyword information 113 in the storage unit 11, and the output results of the respective means 100 to 103 on the display units of the terminals 2 and 3 in a predetermined manner. information output control. Details of the display method will be described later.
  • the storage unit 11 is composed of a memory such as a flash memory, and is electrically connected to the control unit 10 composed of a processor or the like and the communication unit 12 functioning as a communication interface.
  • the storage unit 11 stores a document processing program 110, document information 111, contract type information 112, search keyword information 113, and the like, which causes the control unit 10 to operate as each means 100 to 103 described above.
  • FIG. 3 is a schematic diagram showing a configuration example of the document information 111.
  • FIG. 3 is a schematic diagram showing a configuration example of the document information 111.
  • the document information 111 includes a document ID for identifying a document in the document information 111, a document content indicating a file that is the content of the document, a user ID identifying the user who uploaded the document, and a document contract. It has a type and other information.
  • the document information 111 may have attribute information of each piece of document information.
  • Attribute information is a library indicating that each document information was created or reviewed by some user in the past, There is a template that can be used as a template, a reference document that is referred to or referred to when reviewing document information, etc., and any attribute information is associated with each piece of document information and stored.
  • FIG. 4 is a schematic diagram showing a configuration example of specific contents of the document information 111. As shown in FIG. 4
  • the document information 111a indicates the specific contents of the text of the document information 111, and has a title 111a1 , a preface 111a2 , articles 111a4 , articles 111a5 , articles 111a6 , and so on.
  • FIG. 5 is a schematic diagram showing a configuration example of the contract type information 112. As shown in FIG.
  • the contract type information 112 has a contract type ID for identifying the contract type and a contract type that is the name of the contract type.
  • FIG. 6 is a schematic diagram showing a configuration example of the search keyword information 113.
  • the search keyword information 113 has a search keyword ID for identifying the search keyword, a search keyword indicating the contents of the search keyword, and a search count indicating the number of times the search has been performed.
  • the user operates the terminal 2 to log in to the service provided by the document processing server device 1 .
  • the terminal 2 receives the input of information such as a user ID and a password from the user, the terminal 2 transmits an authentication request to the document processing server device 1 together with the information.
  • the document processing server device 1 When the document processing server device 1 receives an authentication request together with information such as a user ID and password from the terminal 2, the document processing server device 1 refers to user information (not shown) including a pre-registered user ID and password, etc. Authenticate.
  • the user when the user has logged in to the service, the user operates the terminal 2 to upload the contract document information and the change document information to the document processing server device 1 .
  • the terminal 2 uploads the document information to the document processing server device 1 .
  • FIG. 9 is a flow chart showing an operation example of the document processing server device 1 .
  • the document receiving means 100 of the document processing server device 1 receives the document information 111 corresponding to the contract from the terminal 2 operated by the user and stores it in the storage unit 11 (S1).
  • the document classification means 101 of the document processing server device 1 classifies the document information 111 into predetermined categories by analyzing contract components such as the title, preface, and clause units in the document information 111. is stored in the storage unit 11 as the contract type information 112 (S2).
  • the document classification means 101 performs classification based on the results of machine learning performed in advance.
  • contract data is prepared with a contract type label as training data, and words and phrases used in the contract title and text of the same type are used.
  • a classifier as a learning result receives a contract as an input, outputs an estimated probability for each contract type in a contract type list prepared in advance, and classifies which type the contract is based on the estimated probability.
  • the learning method and classifier specifications are examples, and other means may be used.
  • the output of the classifier may be weighted so that judgment from the contract title is prioritized.
  • the document classification means 101 first sets the contract type as the contract type when the contract title is the same as the name of the contract type in the contract type list prepared in advance. Next, the document classification means 101 classifies the contract type system (rough contract type, "outsourcing contract type", "license contract type”, etc.) from the contract title and the contract text, and scores them. adopt the one with the highest Further, the document classification means 101 scores finer classifications from the contract title and the contract text, and sets those with a high score as the contract type (for example, the contract type classified as "outsourcing contract type").
  • the contract type system rough contract type, "outsourcing contract type", "license contract type”, etc.
  • the estimated probability of the type classification is calculated from the number of appearances of the wording in the contract title and the text of the contract, and this estimated probability is used as the score.
  • the user operates the terminal 2 to search for the desired document.
  • the terminal 2 requests the document processing server device 1 to display the search screen.
  • the output control means 103 of the document processing server device 1 controls to output information for displaying the search screen shown in FIG.
  • the search keyword information 113 S3
  • the number of hits in the document information 111 when the search keyword with the highest search history is used as the search condition is calculated (S4), and the output control means 103 displays the number of hits together with the number of hits. (S5).
  • FIG. 7 is a schematic diagram showing an example of the configuration of the search screen.
  • Screen 103A includes a contract type display area 103a in which contract types are displayed together with check boxes based on contract type information 112, and a search keyword in which search keywords with high search histories are displayed together with the number of hits based on search keyword information 113. It has a display area 103b, a search keyword input field 103c for inputting a keyword for searching the document information 111, and other function icons 103d for transitioning to another screen.
  • the number of hits displayed in the search keyword display area 103b is the number of hits when the contract type is not limited. is.
  • the document search means 102 When the check box of the contract type is checked by the user (S6; Yes), the document search means 102 recalculates the number of hits for the search keyword for the document information 111 of the checked contract type (S7). , the output control means 103 displays it together with the number of hits (S5).
  • the display order of the search keywords displayed in the search keyword display area 103b is, for example, the number of search histories.
  • the display order of the contract types in the contract type display area 103a is, for example, the order of the number of hits.
  • the number of hits in FIG. 7 indicates the number of hits calculated regardless of the attribute information of the document information.
  • the number of hits is not limited to this, and the number of hits may be displayed separately for each piece of attribute information.
  • the user operates the terminal 2 to select a search keyword displayed in the search keyword display area 103b or enter a search keyword in the search keyword input field 103c while referring to the screen 103A to obtain the document.
  • Information 111 is searched (S8; Yes).
  • the document search means 102 selects the selected contract type, the search keyword selected from the search keyword display area 103b, and the search keyword entered in the search keyword input field 103c according to the user's operation content.
  • the document information 111 is searched using the designated information as a search condition (S9), and the output control means 103 outputs information for displaying the search result on the display section of the terminal 2 (S10).
  • S9 search condition
  • S10 output control means 103
  • the document search means 102 of the document processing server device 1 searches the document information 111 using the search keyword “search keyword” as a search condition, and the output control means 103 outputs the search result to the display section of the terminal 2. Outputs information for display in .
  • FIG. 8 is a schematic diagram showing an example of the configuration of a screen showing search results.
  • screen 103B Similar to screen 103A, screen 103B has contract type display area 103a, search keyword input field 103c, and other function icons 103d. and a search result display area 103e in which is displayed.
  • the output control means 103 displays the file name, creator, attached tag, etc. of the document information 111 hit by the search.
  • the range including "nonconforming" is displayed.
  • the contract type display area 103a is displayed by the output control means 103 so that only contract types included in the document information 111 hit by the search keyword "contract incompatibility" can be selected. Types are displayed in a non-selectable manner (in a different display form than those that are selectable). Contract types not included in the hit document information 111 may be hidden.
  • the document information 111 is classified into contract types, and a list of contract types included in the document information 111 to be searched (contract type display area 103a) and a list of search keywords with high search history are displayed. (Search keyword display area 103b) is displayed, the number of hits for the search keyword is displayed, and the number of hits is recalculated based on the contract type selected in the search keyword display area 103b. Changes in search results due to changes in search keywords can be dynamically output.
  • the contract type included in the document information 111 of the search result is displayed in the contract type display area 103a in a selectable manner. It is possible to dynamically output changes in the type of contract that is used.
  • the document information 111 is not limited to a contract, and may be a document of a law itself or a document in a field other than the law such as an instruction manual as long as it can be classified. be.
  • the language of the document information 111 is not limited to Japanese and English, and other languages can be applied as long as they can construct sentences from which information can be extracted.
  • the document processing server device 1 functions as an information processing device.
  • the present invention is not limited to this, and the processing executed by the document processing server device 1 and the information stored therein may be distributed to other server devices so that they function as an information processing device as a whole.
  • the terminal 2 or 3 may function as an information processing device and execute each process.
  • the search result is mainly output to the terminal 2 or terminal 3 via the communication unit of the document processing server device 1 and displayed on the display unit of the terminal 2 or 3 will be described.
  • search results may be notified to the user by any method, and any method may be used.
  • the terminal 2 or terminal 3 when the terminal 2 or terminal 3 functions as a document processing device, it may be output to an external display, or may be directly output to its own display unit.
  • each means 100-103 of the control unit 10 are realized by programs, but all or part of each means may be realized by hardware such as ASIC.
  • the program used in the above embodiment can be stored in a recording medium such as a CD-ROM and provided.
  • replacement, deletion, addition, etc., of the steps described in the above embodiment are possible without changing the gist of the present invention.
  • document processing server device 2 terminal 3: terminal 4: network 5: document processing system 10: control unit 11: storage unit 12: communication unit 100: document reception means 101: document classification means 102: document search means 103: output Control means 110: document processing program 111: document information 112: contract type information 113: search keyword information

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
PCT/JP2021/041487 2021-01-27 2021-11-11 文書処理プログラム、情報処理装置及び文書処理方法 Ceased WO2022163067A1 (ja)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/359,100 US12468744B2 (en) 2021-01-27 2023-07-26 Document processing method, document processing system, information processing device, and graphic user interface

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-011366 2021-01-27
JP2021011366A JP7548569B2 (ja) 2021-01-27 2021-01-27 文書処理プログラム、情報処理装置及び文書処理方法

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/359,100 Continuation US12468744B2 (en) 2021-01-27 2023-07-26 Document processing method, document processing system, information processing device, and graphic user interface

Publications (1)

Publication Number Publication Date
WO2022163067A1 true WO2022163067A1 (ja) 2022-08-04

Family

ID=82653144

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/041487 Ceased WO2022163067A1 (ja) 2021-01-27 2021-11-11 文書処理プログラム、情報処理装置及び文書処理方法

Country Status (3)

Country Link
US (1) US12468744B2 (enExample)
JP (2) JP7548569B2 (enExample)
WO (1) WO2022163067A1 (enExample)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2025169625A (ja) * 2024-05-01 2025-11-14 株式会社ウィ・キャン サーバ装置、制御方法、およびプログラム。

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09231234A (ja) * 1996-02-26 1997-09-05 Fuji Xerox Co Ltd 文書検索装置
JP2004240887A (ja) * 2003-02-07 2004-08-26 Nippon Telegr & Teleph Corp <Ntt> 検索情報表示システム及び検索キーワード情報表示方法及び検索キーワード情報表示プログラム
JP2005122683A (ja) * 2003-09-22 2005-05-12 Nippon Telegr & Teleph Corp <Ntt> 情報提供方法及びシステム及び情報提供プログラム
US20060047649A1 (en) * 2003-12-29 2006-03-02 Ping Liang Internet and computer information retrieval and mining with intelligent conceptual filtering, visualization and automation

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004111876A1 (ja) 2003-06-11 2004-12-23 Fujitsu Limited 検索条件を再利用する検索システムおよび方法
JP2005128872A (ja) 2003-10-24 2005-05-19 Toshiba Solutions Corp 文書検索システム及び文書検索プログラム
JP4774081B2 (ja) 2008-06-11 2011-09-14 ヤフー株式会社 文書検索システム、文書検索方法、及びプログラム
US20110125653A1 (en) * 2009-11-20 2011-05-26 David Ciccarelli System for managing online transactions involving voice talent
JP5581857B2 (ja) 2010-07-07 2014-09-03 日本電気株式会社 情報検索装置、情報検索方法および情報検索プログラム
JP5185402B2 (ja) 2011-01-11 2013-04-17 株式会社東芝 文書検索装置、文書検索方法、及び文書検索プログラム
US20140229205A1 (en) * 2013-02-11 2014-08-14 G Wizicon Technologies, Inc. Global insurance compliance management system
US20140229311A1 (en) * 2013-02-14 2014-08-14 Xtream Service, Inc. A Delaware Corporation Identifying potential customers for an identified vehicle in inventory based on information that is specific to the potential customer

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09231234A (ja) * 1996-02-26 1997-09-05 Fuji Xerox Co Ltd 文書検索装置
JP2004240887A (ja) * 2003-02-07 2004-08-26 Nippon Telegr & Teleph Corp <Ntt> 検索情報表示システム及び検索キーワード情報表示方法及び検索キーワード情報表示プログラム
JP2005122683A (ja) * 2003-09-22 2005-05-12 Nippon Telegr & Teleph Corp <Ntt> 情報提供方法及びシステム及び情報提供プログラム
US20060047649A1 (en) * 2003-12-29 2006-03-02 Ping Liang Internet and computer information retrieval and mining with intelligent conceptual filtering, visualization and automation

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2025169625A (ja) * 2024-05-01 2025-11-14 株式会社ウィ・キャン サーバ装置、制御方法、およびプログラム。
JP7781457B2 (ja) 2024-05-01 2025-12-08 株式会社ウィ・キャン サーバ装置、制御方法、およびプログラム。

Also Published As

Publication number Publication date
US12468744B2 (en) 2025-11-11
US20230367797A1 (en) 2023-11-16
JP2024152921A (ja) 2024-10-25
JP2022114897A (ja) 2022-08-08
JP7548569B2 (ja) 2024-09-10

Similar Documents

Publication Publication Date Title
US12197873B2 (en) Creation of component templates based on semantically similar content
US11100124B2 (en) Systems and methods for similarity and context measures for trademark and service mark analysis and repository searches
US8200695B2 (en) Database for uploading, storing, and retrieving similar documents
US20060122997A1 (en) System and method for text searching using weighted keywords
US11023503B2 (en) Suggesting text in an electronic document
US12339875B1 (en) Machine learning architecture for contextual data retrieval
US20250328935A1 (en) Systems and methods for automated response to online reviews
CN104750776A (zh) 使用元数据访问数据库平台中的信息内容
WO2024263741A2 (en) Context llm response system
US20120179702A1 (en) Method for setting metadata, system for setting metadata, and program
US20240070188A1 (en) System and method for searching media or data based on contextual weighted keywords
JP2024152921A (ja) 文書処理プログラム、情報処理装置及び文書処理方法
CN120543265A (zh) 一种基于xml结构化数据的电子招标系统及方法
JP2002251412A (ja) 文書検索装置および方法ならびに記憶媒体
US20220301330A1 (en) Information extraction system and non-transitory computer readable recording medium storing information extraction program
KR102388307B1 (ko) 대화방 제공 방법 및 단말
CN119557127A (zh) 一种异常业务分析方法、装置及电子设备
CN116975413A (zh) 用于搜索的方法、装置、设备和介质
JP2002251401A (ja) 文書検索装置および方法ならびに記憶媒体
JP2019061522A (ja) 文書推薦システム、文書推薦方法および文書推薦プログラム
US20250252124A1 (en) System and method for integrating artificial intelligence assistants with website building systems
KR102848028B1 (ko) Llm을 활용한 질문 카테고리 설정 기반 질의응답 시스템
US20230281229A1 (en) Query formatting system, query formatting method, and information storage medium
CN120950528A (zh) 一种数据资产管理方法、系统及相关设备
JP2024110307A (ja) 情報処理システム、サービス提供システム、情報抽出方法、プログラム、端末装置

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: 21923072

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21923072

Country of ref document: EP

Kind code of ref document: A1