+

WO2002073531A1 - Exploration en profondeur de donnees en une etape avec specifications en langage naturel et resultats - Google Patents

Exploration en profondeur de donnees en une etape avec specifications en langage naturel et resultats Download PDF

Info

Publication number
WO2002073531A1
WO2002073531A1 PCT/US2002/006247 US0206247W WO02073531A1 WO 2002073531 A1 WO2002073531 A1 WO 2002073531A1 US 0206247 W US0206247 W US 0206247W WO 02073531 A1 WO02073531 A1 WO 02073531A1
Authority
WO
WIPO (PCT)
Prior art keywords
data mining
data
goal
natural language
text
Prior art date
Application number
PCT/US2002/006247
Other languages
English (en)
Inventor
David Kil
Williams K. Fertig
Original Assignee
Rockwell Scientific Company, Llc
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
Priority claimed from US09/945,530 external-priority patent/US20020169735A1/en
Priority claimed from US09/992,435 external-priority patent/US20020138492A1/en
Application filed by Rockwell Scientific Company, Llc filed Critical Rockwell Scientific Company, Llc
Publication of WO2002073531A1 publication Critical patent/WO2002073531A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/285—Clustering or classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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

Definitions

  • Information processing is generally the systematic performance of operations upon information. It includes data processing and can include operations such as data communication and office automation.
  • Data processing is generally the systematic performance of operations upon data. Examples of data processing include arithmetic or logic operations upon data, merging or sorting of data, assembling or compiling of programs, or operations on text, such as editing, sorting, merging, storing, retrieving, displaying, or printing .
  • a natural language is a language whose rules are based on current usage without being specifically prescribed. Examples of natural language include, for example, English, Russian, or Chinese. In contrast, an artificial language is a language whose rules are explicitly established prior to its use. Examples of artificial languages include computer- programming languages such as C, Java, BASIC, FORTRAN, or COBOL.
  • the method can also include providing (as part of the user interface) a plurality text templates for communicating the key performance results and selecting one text template from among the plurality of text templates for communicating the key performance results, whereby the user interface does not display the same text template for every data mining operation.
  • the user interface can be provided on a client system and the data model on a server, or the user interface and the client system can both be contained on a general- purpose computer.
  • a third embodiment is a method in a computer system for controlling a data mining operation.
  • This method includes a step of the computer system receiving problem specification input determining a data mining operation goal.
  • the input data determining a data mining operation goal is the only input required by the data mining application.
  • the problem specification input can be a formal definition based on a data model or can be natural language data.
  • the method can also include identifying key performance results; providing a user interface having a control for communicating information; and communicating a natural language description of the key performance results using the control on the user interface.
  • a fourth embodiment is a data mining application user interface.
  • the user interface includes, but is not limited to a control that receives natural language input describing the goal of a data mining operation and an interface that sends the natural language input to a text parser.
  • FIG. 7 is a system resources chart illustrating an example of a configuration of data units and process units suitable for solving the problem of mapping a goal of data mining in text to data fields for automated problem specification.
  • FIG. 8 illustrates screens and windows that can be presented to the user in an embodiment for mapping a goal of data mining in text to data fields for automated problem specification .
  • FIG. 11 is a data flow chart that illustrates an example of a path of data in solving the problem of text display of key data mining performance results.
  • the algorithm of this embodiment then recommends a set of fields, fewer than all the fields in the database, that have relatively higher probabilities to be candidates for or components of the dependent variable than other fields not recommended. The user can then narrow down the selection even further by selecting some of the suggested fields. If the dependent variable is actually some combination of the selected fields, the user can also define the true dependent variable by entering a mathematical expression .
  • the boilerplate text template can be particularly adapted to each specialized market sector using the terminology ordinarily used by persons in that field.
  • the performance summary text descriptions are made to seem more human and less automatic by randomizing the templates that have been customized for each market sector. While different templates each provide essentially the same message, the body of the text can contain differently worded details text.
  • One embodiment provides one-step data mining. It asks the user to enter the goal of data mining, which can be specified in natural language such as plain English. This embodiment then employs techniques disclosed. in provisional application 60/274,008, filed March 7, 2001, which is incorporated herein by reference, in order to transport the user directly to analyzing output results. This embodiment selects all the algorithm parameters and runs the entire data mining operation automatically.
  • the data-exploration window (255) can further include a basic information text box (265) containing fundamental information in the data set that is the subject of data mining.
  • the data exploration window (255) can further include additional text boxes (267, 270) containing further information about the data set to be analyzed.
  • the data exploration window (255) can further include an inputs text box (272) listing domain-space source variates relevant to the problem to be analyzed.
  • the data exploration window (255) can further include a related field index textbox (275) .
  • the data exploration window (255) can further include an outputs textbox (276) listing the fields that are the range-space of potential candidate variables relevant to the problem to be analyzed.
  • the identify-keywords process (414) matches words parsed from the text by the parse-text process (412) with known keywords. This matching can be performed by any algorithm suitable for this purpose. Those of ordinary skill in the art will recognize in general the equivalence of such algorithms for keyword identification as are now known or may later be developed.
  • the next step concerns calculation of maximum a posteriori ("MAP") probabilities.
  • MAP maximum a posteriori
  • control passes next to a calculate-MAP- probability process (420).
  • the calculate-MAP-probability process (420) is a processing function to compare the results of the lexical analysis process (416) with names and descriptions of fields in the database to be analyzed by data mining software package.
  • control passes next to an identify-target- field-candidates process (425).
  • the identify-target-field- candidates process (425) is a processing function to identify likely dependent variable fields in the database to be analyzed by the data mining software package. Based on the results of the comparison performed in the calculate-MAP- probability process (420) , the identify-target-field- candidates process (425) can select those fields most likely to represent dependent variables for the end user's problem definition.
  • the communicate-best- fields process (440) is a processing function to communicate to the end user the identification and ranking of fields likely to be relevant to the dependent variable that the application ' software identifies based on the enter-goal-in- natural-language process (410). This communicate-best-fields process (440) thus enables the end user to complete the selection and definition of the dependent variable for the data mining problem.
  • control passes next to an incorporate-user-refinements process (445).
  • the rank-input-fields process (447) is a processing function to rank input features based on their level of contribution to the projected data mining performance. One way to assess this contribution is to measure the input field's accurate prediction of the selected output variable. Many actual feature-ranking algorithms can be used. The interchangeability and general equivalence of these algorithms will be appreciated by those of ordinary skill in the art. The selection of a particular feature-ranking algorithm for a particular embodiment of the data mining application software package might depend on various factors and is within the abilities of those of ordinary skill in the art. In one embodiment of the data mining application software package, the end user can be given the option to select input features. In a second embodiment of the data mining application software package, the selection of input features can be performed entirely by the data mining application software package. Any algorithm suitable for sorting can be employed for this rank- input-fields process (435).
  • FIG. 5 there is depicted a system resources chart illustrating a configuration of data units and process units suitable for use in a software application to solve the problem.
  • the control passes first to an enter-goal-in-natural- language process (410), which is a processing function to receive as input natural language description data (310) describing the goal of the data mining operation in natural language.
  • input natural language description data (310) can be input manually at run time, but this is a detail of the implementation that can vary in other embodiments. Other forms of natural language description data in other media can be used without altering the basic characteristics of the invention.
  • the lexical analysis process (416) can use other link-analysis techniques.
  • the lexical analysis process (416) produces analyzed text data (340), here depicted as being stored in interned storage although the media for such analyzed text data (340) is a detail of implementation that can be varied in different embodiments of the invention.
  • This analyzed text data (340) and a field description database (355) are next used in a calculate-MAP-probability process (420).
  • control passes to an identify-target-field-candidates process (425).
  • the identity-target-field-candidates-process (425) is a processing function that uses the field descriptions database (355) and the results of the calculate-MAP-probability process (420) to select target fields data.
  • the software application next evaluates the condition "Is MAP probability high enough" in a decision operation (430). If that conditional evaluates False, then in one embodiment control is passed to an alternative-problem-specification-process (455) .
  • FIG. 6 there is depicted a program network chart illustrating the path of program activations and the interactions to related data for translating a goal of data mining expressed in natural language text into the specification of input and output variables automatically prior to the commencement of data mining.
  • Natural language description data (610) describing the data mining problem to be solved passes to a parse-text process (412) .
  • the parse text-process (412) upon completion activates a identify- keywords-process (414), which interacts with keywords data (620).
  • the identify-keywords process (414) upon completion activates a lexical analysis process (416).
  • Problem description data (710) is a natural language description of the goal to be analyzed by the data mining software application.
  • the medium of problem description data (710) can be manual input.
  • Manual input is data, the medium being of any type where the information is entered manually at the time of processing, for example, on-line keyboard, switch settings, push buttons, light pen, bar-code wand.
  • the natural language description of 'the problem description data (710) could have been provided previously and stored in some other medium.
  • Problem description data (710) communicates with the problem definition processor (750) .
  • Temporary workspace data (730) is storage used for working results, such as text that has been parsed and lists of fields likely to be part of the problem definition data (720). Temporary workspace data is here depicted as internal storage. Internal storage is data stored in, for example, RAM or a cache. Temporary workspace data (730) interacts with the problem definition processor (750) .
  • Field descriptions data (740) is a database or other suitable data structure containing field names and descriptive information regarding the database that can be analyzed by the data mining software application. Field descriptions data (740) is here depicted as direct access storage. Other media and storage forms are possible and equivalent for purposes of this invention to direct access storage, including but not limited to sequential storage and internal storage.
  • the data set comprises three depicted tables: basic patient information, thrombosis-test results, and medical history.
  • the field named "thrombosis" is the actual target variable.
  • the goal of the data mining operation is to identify other input fields relevant in diagnosing thrombosis.
  • the "birthday” field in particular shows an example of a field having no predictive power.
  • the example is illustrated by a display window (800) containing elements used in one embodiment implementing the process.
  • the display window (800) in this example includes conventional elements such as title bar (805), a drop-down task menu (810) and control elements (815).
  • the title bar (805) can contain any appropriate title such as, for example, "Figure No. 3: Help with selecting input be a ranking according to field importance.”
  • the drop-down task menu (810) can contain conventional elements such as a file menu, an edit menu, and window menu, and a help menu.
  • the control elements (815) can include conventional controls such as a button to minimize the window (800), a button to maximize the window (800), a button to restore the window (800), and a button to close the window (800) .
  • the window (800) in this example depicts data from three tables: a basic information table (820), a thrombosis test table (825), and a ranking for historical data table (830) .
  • additional display control elements such as, for example, a slider control bar (835) , can be included to permit subsections of the window (800) to be scrolled to display all data.
  • fields from each table are explained in text boxes below that table.
  • the fields from the basic information table (820) are enumerated in the basic information text box (840), which identifies the fields as sex, birthday, description, first date, admission, and diagnosis respectively.
  • the fields charted in the thrombosis test table (825) are enumerated in the thrombosis test list box (845) .
  • the fields charted in the ranking for historical data table (830) are enumerated in the ranking for historical data list box (850) .
  • List boxes (840, 845, 850) can typically include a slider control bar to scroll through the items listed.
  • Fig. 9 there is depicted a data flow chart illustrating a path of data and the processing steps in an embodiment of a method for displaying key performance results of data mining operation in natural language such as plain English to that a novice user can understand the results without having to consult an expert for interpretation.
  • the operation takes as input performance results of data (910) and type of operation data (920).
  • Presentation templates data (990) is used by a template- selection process (980).
  • the template selection-process (980) and the hierarchical-prioritization-process (930) both also can take as input information from vertical market area data (970).
  • the hierarchical-prioritization-process (930) generates as its output a set of vital results data (940) .
  • the set of vital results data (940) passes as input to a performance-summary-generation process (950).
  • the template selection process (980) using vertical market area data (970) as input, generates output template data (990).
  • the template data (990) is also provided as input to the performance summary generation process (950).
  • the performance summary generation process (950) generates as output performance summary data (960), which can then communicated to the user by any convenient means such as, for example, display on a cathode ray tube, output to a printer, or other output methods.
  • control passes first to a select-vital-information process (1010).
  • the select-vital-information process (1010) identifies key performance data about which information can be communicated to the user.
  • Control passes next to a select-template process (1020).
  • the select-template process (1020) identifies a predefined template appropriate for displaying the key information identified in the select-vital-information process (1010).
  • control passes next to a generate-summary process (1030).
  • a performance window (1280) displays first.
  • the performance window (1280) can include conventional elements (1295) such as a title bar, control elements, and drop-down task menus.
  • the title bar in the conventional control elements (1295) of the performance summary window (1280) contains the title "performance summary figure.”
  • the performance summary window (1280) can also include a text box (1285), which displays key data mining performance results using a text template in a natural language such as, for example, English.
  • the performance summary window (1280) can also include a detailed analysis button (1290).
  • the performance detail window (1205) can include detailed charts (1210, 1220, 1230, 1240, 1250, 1260), which show in more detail and in graphic form the information summarized in the summary window (1280). Additional controls (1270) can be included in the detail window (1205), the additional controls (1270) providing access to additional information.
  • Computer readable media includes any recording medium in which computer code may be fixed, including but not limited to CD's, DVD's, semiconductor ram, rom, or flash memory, paper tape, punch cards, and any optical, magnetic, or semiconductor recording medium or the like.
  • Examples of computer readable media include recordable-type media such as floppy disc a hard disk drive, a RAM, and CD-ROMs, DVD-ROMs, an online internet web site, tape storage, and compact flash storage, and transmission-type media such as digital and analog communications links, and any other volatile or non-volatile mass storage system readable by the computer.
  • the computer readable medium includes cooperating or interconnected computer readable media, which exist exclusively on single computer system or are distributed among multiple interconnected computer systems that may be local or remote. Those skilled in the art will also recognize many other configurations of these and similar components which can also comprise computer system, which are considered equivalent and are intended to be encompassed within the scope of the claims herein.
  • the data mining application software is easy to use with most functionality behind the scenes. Such embodiments can include preprocessing, intelligent performance optimization, information visualization, or an intuitive graphical interface (GUI) that provides guidance for novice users. Such embodiments can provide a near turnkey solution to expand the use of data mining technologies.
  • the data mining application software provides technically powerful data mining capabilities. Such embodiments can include a robust algorithm set or scalability for large data sets. Some embodiments can provide digital signal processing and image processing algorithms for temporally and spatially sampled data, such as macroeconomic data or images. Some embodiments can provide fusion of several complementary algorithms. Some embodiments can provide advanced or simple visualization tools to enhance the interpretation of data mining results in order to derive actionable insights.
  • the data mining application software is flexible and customizable. Some embodiments can provide seamless insertion of user's algorithms through file- based I/O and dynamic script generation that maps user's requests into actions. Some embodiments can provide web-based data mining through intranet and or Internet.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

On décrit diverses formes de réalisation d'un procédé et d'un système qui permettent de contrôler une opération d'exploration en profondeur de données en précisant le but de l'opération en langage naturel; d'effectuer l'opération d'exploration en profondeur sans aucune entrée supplémentaire autre que la spécification du problème; et à présenter des résultats de performance clés d'une opération d'exploration en profondeur de données en langage naturel. Dans une forme de réalisation, le système présente une interface utilisateur comprenant un contrôle pour recevoir une entrée en langage naturel décrivant le but de l'opération d'exploration en profondeur de données à partir du contrôle de l'interface utilisateur (130). Une deuxième forme de réalisation identifie des résultats de performance clés, et présente une interface utilisateur comprenant un contrôle pour transmettre des informations et communiquer une description en langage naturel des résultats de performance clés en utilisant le contrôle de l'interface utilisateur (910). Dans une troisième forme de réalisation, des données d'entrée déterminant le but d'une opération d'exploration en profondeur de données constitue la seule entrée requise par l'application d'exploration en profondeur de données (410).
PCT/US2002/006247 2001-03-07 2002-03-01 Exploration en profondeur de donnees en une etape avec specifications en langage naturel et resultats WO2002073531A1 (fr)

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US27400801P 2001-03-07 2001-03-07
US60/274,008 2001-03-07
US09/945,530 2001-08-03
US09/945,530 US20020169735A1 (en) 2001-03-07 2001-08-03 Automatic mapping from data to preprocessing algorithms
US09/942,435 2001-11-16
US09/992,435 US20020138492A1 (en) 2001-03-07 2001-11-16 Data mining application with improved data mining algorithm selection

Publications (1)

Publication Number Publication Date
WO2002073531A1 true WO2002073531A1 (fr) 2002-09-19

Family

ID=27402619

Family Applications (3)

Application Number Title Priority Date Filing Date
PCT/US2002/006247 WO2002073531A1 (fr) 2001-03-07 2002-03-01 Exploration en profondeur de donnees en une etape avec specifications en langage naturel et resultats
PCT/US2002/006248 WO2002073530A1 (fr) 2001-03-07 2002-03-01 Dispositif et procede d'exploration de donnees utilisant un outil de terrain a interface utilisateur et des algorithmes d'utilisateur
PCT/US2002/006519 WO2002073532A1 (fr) 2001-03-07 2002-03-04 Caracterisation hierarchique de champs de tables multiples selon des rapports un a plusieurs pour l'exploration de donnees globale

Family Applications After (2)

Application Number Title Priority Date Filing Date
PCT/US2002/006248 WO2002073530A1 (fr) 2001-03-07 2002-03-01 Dispositif et procede d'exploration de donnees utilisant un outil de terrain a interface utilisateur et des algorithmes d'utilisateur
PCT/US2002/006519 WO2002073532A1 (fr) 2001-03-07 2002-03-04 Caracterisation hierarchique de champs de tables multiples selon des rapports un a plusieurs pour l'exploration de donnees globale

Country Status (1)

Country Link
WO (3) WO2002073531A1 (fr)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9244894B1 (en) 2013-09-16 2016-01-26 Arria Data2Text Limited Method and apparatus for interactive reports
US9323743B2 (en) 2012-08-30 2016-04-26 Arria Data2Text Limited Method and apparatus for situational analysis text generation
US9336193B2 (en) 2012-08-30 2016-05-10 Arria Data2Text Limited Method and apparatus for updating a previously generated text
US9355093B2 (en) 2012-08-30 2016-05-31 Arria Data2Text Limited Method and apparatus for referring expression generation
US9396181B1 (en) 2013-09-16 2016-07-19 Arria Data2Text Limited Method, apparatus, and computer program product for user-directed reporting
US9405448B2 (en) 2012-08-30 2016-08-02 Arria Data2Text Limited Method and apparatus for annotating a graphical output
US9600471B2 (en) 2012-11-02 2017-03-21 Arria Data2Text Limited Method and apparatus for aggregating with information generalization
US9640045B2 (en) 2012-08-30 2017-05-02 Arria Data2Text Limited Method and apparatus for alert validation
US9904676B2 (en) 2012-11-16 2018-02-27 Arria Data2Text Limited Method and apparatus for expressing time in an output text
US9946711B2 (en) 2013-08-29 2018-04-17 Arria Data2Text Limited Text generation from correlated alerts
US9990360B2 (en) 2012-12-27 2018-06-05 Arria Data2Text Limited Method and apparatus for motion description
US10115202B2 (en) 2012-12-27 2018-10-30 Arria Data2Text Limited Method and apparatus for motion detection
US10445432B1 (en) 2016-08-31 2019-10-15 Arria Data2Text Limited Method and apparatus for lightweight multilingual natural language realizer
US10467347B1 (en) 2016-10-31 2019-11-05 Arria Data2Text Limited Method and apparatus for natural language document orchestrator
US10565308B2 (en) 2012-08-30 2020-02-18 Arria Data2Text Limited Method and apparatus for configurable microplanning
US10664558B2 (en) 2014-04-18 2020-05-26 Arria Data2Text Limited Method and apparatus for document planning
US10776561B2 (en) 2013-01-15 2020-09-15 Arria Data2Text Limited Method and apparatus for generating a linguistic representation of raw input data
US11176214B2 (en) 2012-11-16 2021-11-16 Arria Data2Text Limited Method and apparatus for spatial descriptions in an output text

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103150354A (zh) * 2013-01-30 2013-06-12 王少夫 一种基于粗糙集的数据挖掘算法
CN105117430B (zh) * 2015-08-06 2018-07-31 中山大学 一种基于等价类的重复任务过程发现方法
US10692601B2 (en) * 2016-08-25 2020-06-23 Hitachi, Ltd. Controlling devices based on hierarchical data
US10776408B2 (en) 2017-01-11 2020-09-15 International Business Machines Corporation Natural language search using facets
US10572826B2 (en) 2017-04-18 2020-02-25 International Business Machines Corporation Scalable ground truth disambiguation
US12197846B2 (en) 2019-11-19 2025-01-14 International Business Machines Corporation Mathematical function defined natural language annotation
CN113342800A (zh) * 2020-02-18 2021-09-03 中国电信股份有限公司 数据关系处理方法和装置、计算机可读存储介质
CN111640031B (zh) * 2020-05-29 2023-07-14 泰康保险集团股份有限公司 跨系统的理赔数据处理方法、装置及相关设备
CN113821552B (zh) * 2020-06-18 2023-11-17 南京南瑞继保电气有限公司 电力实时数据库模型数据导出至关系数据库的映射方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5933818A (en) * 1997-06-02 1999-08-03 Electronic Data Systems Corporation Autonomous knowledge discovery system and method
US5966126A (en) * 1996-12-23 1999-10-12 Szabo; Andrew J. Graphic user interface for database system
US5991751A (en) * 1997-06-02 1999-11-23 Smartpatents, Inc. System, method, and computer program product for patent-centric and group-oriented data processing

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5257365A (en) * 1990-03-16 1993-10-26 Powers Frederick A Database system with multi-dimensional summary search tree nodes for reducing the necessity to access records
US5544355A (en) * 1993-06-14 1996-08-06 Hewlett-Packard Company Method and apparatus for query optimization in a relational database system having foreign functions
US6034697A (en) * 1997-01-13 2000-03-07 Silicon Graphics, Inc. Interpolation between relational tables for purposes of animating a data visualization
US5861891A (en) * 1997-01-13 1999-01-19 Silicon Graphics, Inc. Method, system, and computer program for visually approximating scattered data
US5960435A (en) * 1997-03-11 1999-09-28 Silicon Graphics, Inc. Method, system, and computer program product for computing histogram aggregations
US5930803A (en) * 1997-04-30 1999-07-27 Silicon Graphics, Inc. Method, system, and computer program product for visualizing an evidence classifier

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5966126A (en) * 1996-12-23 1999-10-12 Szabo; Andrew J. Graphic user interface for database system
US5933818A (en) * 1997-06-02 1999-08-03 Electronic Data Systems Corporation Autonomous knowledge discovery system and method
US5991751A (en) * 1997-06-02 1999-11-23 Smartpatents, Inc. System, method, and computer program product for patent-centric and group-oriented data processing

Cited By (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10839580B2 (en) 2012-08-30 2020-11-17 Arria Data2Text Limited Method and apparatus for annotating a graphical output
US10467333B2 (en) 2012-08-30 2019-11-05 Arria Data2Text Limited Method and apparatus for updating a previously generated text
US9336193B2 (en) 2012-08-30 2016-05-10 Arria Data2Text Limited Method and apparatus for updating a previously generated text
US9355093B2 (en) 2012-08-30 2016-05-31 Arria Data2Text Limited Method and apparatus for referring expression generation
US10565308B2 (en) 2012-08-30 2020-02-18 Arria Data2Text Limited Method and apparatus for configurable microplanning
US9405448B2 (en) 2012-08-30 2016-08-02 Arria Data2Text Limited Method and apparatus for annotating a graphical output
US9323743B2 (en) 2012-08-30 2016-04-26 Arria Data2Text Limited Method and apparatus for situational analysis text generation
US10504338B2 (en) 2012-08-30 2019-12-10 Arria Data2Text Limited Method and apparatus for alert validation
US10963628B2 (en) 2012-08-30 2021-03-30 Arria Data2Text Limited Method and apparatus for updating a previously generated text
US10282878B2 (en) 2012-08-30 2019-05-07 Arria Data2Text Limited Method and apparatus for annotating a graphical output
US9640045B2 (en) 2012-08-30 2017-05-02 Arria Data2Text Limited Method and apparatus for alert validation
US10026274B2 (en) 2012-08-30 2018-07-17 Arria Data2Text Limited Method and apparatus for alert validation
US10769380B2 (en) 2012-08-30 2020-09-08 Arria Data2Text Limited Method and apparatus for situational analysis text generation
US10216728B2 (en) 2012-11-02 2019-02-26 Arria Data2Text Limited Method and apparatus for aggregating with information generalization
US9600471B2 (en) 2012-11-02 2017-03-21 Arria Data2Text Limited Method and apparatus for aggregating with information generalization
US10853584B2 (en) 2012-11-16 2020-12-01 Arria Data2Text Limited Method and apparatus for expressing time in an output text
US10311145B2 (en) 2012-11-16 2019-06-04 Arria Data2Text Limited Method and apparatus for expressing time in an output text
US11176214B2 (en) 2012-11-16 2021-11-16 Arria Data2Text Limited Method and apparatus for spatial descriptions in an output text
US9904676B2 (en) 2012-11-16 2018-02-27 Arria Data2Text Limited Method and apparatus for expressing time in an output text
US11580308B2 (en) 2012-11-16 2023-02-14 Arria Data2Text Limited Method and apparatus for expressing time in an output text
US10860810B2 (en) 2012-12-27 2020-12-08 Arria Data2Text Limited Method and apparatus for motion description
US10115202B2 (en) 2012-12-27 2018-10-30 Arria Data2Text Limited Method and apparatus for motion detection
US9990360B2 (en) 2012-12-27 2018-06-05 Arria Data2Text Limited Method and apparatus for motion description
US10803599B2 (en) 2012-12-27 2020-10-13 Arria Data2Text Limited Method and apparatus for motion detection
US10776561B2 (en) 2013-01-15 2020-09-15 Arria Data2Text Limited Method and apparatus for generating a linguistic representation of raw input data
US9946711B2 (en) 2013-08-29 2018-04-17 Arria Data2Text Limited Text generation from correlated alerts
US10671815B2 (en) 2013-08-29 2020-06-02 Arria Data2Text Limited Text generation from correlated alerts
US11144709B2 (en) 2013-09-16 2021-10-12 Arria Data2Text Limited Method and apparatus for interactive reports
US10860812B2 (en) 2013-09-16 2020-12-08 Arria Data2Text Limited Method, apparatus, and computer program product for user-directed reporting
US10282422B2 (en) 2013-09-16 2019-05-07 Arria Data2Text Limited Method, apparatus, and computer program product for user-directed reporting
US10255252B2 (en) 2013-09-16 2019-04-09 Arria Data2Text Limited Method and apparatus for interactive reports
US9244894B1 (en) 2013-09-16 2016-01-26 Arria Data2Text Limited Method and apparatus for interactive reports
US9396181B1 (en) 2013-09-16 2016-07-19 Arria Data2Text Limited Method, apparatus, and computer program product for user-directed reporting
US10664558B2 (en) 2014-04-18 2020-05-26 Arria Data2Text Limited Method and apparatus for document planning
US10445432B1 (en) 2016-08-31 2019-10-15 Arria Data2Text Limited Method and apparatus for lightweight multilingual natural language realizer
US10853586B2 (en) 2016-08-31 2020-12-01 Arria Data2Text Limited Method and apparatus for lightweight multilingual natural language realizer
US10467347B1 (en) 2016-10-31 2019-11-05 Arria Data2Text Limited Method and apparatus for natural language document orchestrator
US10963650B2 (en) 2016-10-31 2021-03-30 Arria Data2Text Limited Method and apparatus for natural language document orchestrator
US11727222B2 (en) 2016-10-31 2023-08-15 Arria Data2Text Limited Method and apparatus for natural language document orchestrator

Also Published As

Publication number Publication date
WO2002073532A1 (fr) 2002-09-19
WO2002073530A1 (fr) 2002-09-19

Similar Documents

Publication Publication Date Title
US20030115192A1 (en) One-step data mining with natural language specification and results
WO2002073531A1 (fr) Exploration en profondeur de donnees en une etape avec specifications en langage naturel et resultats
Korinek Generative AI for economic research: Use cases and implications for economists
US11531673B2 (en) Ambiguity resolution in digital paper-based interaction
Kohler et al. Data analysis using Stata
Liu et al. An adaptive user interface based on personalized learning
EP2124173A2 (fr) Système et procédé de création semi-automatique et maintenance des règles d'expansion de requête
US20230376857A1 (en) Artificial inelligence system with intuitive interactive interfaces for guided labeling of training data for machine learning models
AU2020380139A1 (en) Data preparation using semantic roles
JP2011501258A (ja) 情報抽出装置および方法
US8442992B2 (en) Mixed mode (mechanical process and english text) query building support for improving the process of building queries correctly
KR20040102071A (ko) 자연어 인식 애플리케이션 구축을 위한 통합 개발 툴
US10977155B1 (en) System for providing autonomous discovery of field or navigation constraints
US12210839B1 (en) Multilevel data analysis
WO2020161505A1 (fr) Procédé et système améliorés de recherche à base de texte
JP2021523509A (ja) エキスパートレポートエディタ
US20230244218A1 (en) Data Extraction in Industrial Automation Systems
US20240111944A1 (en) System and Method for Annotation-Based Document Management
Gillies et al. Theme and topic: How qualitative research and topic modeling can be brought together
US20070129937A1 (en) Apparatus and method for deterministically constructing a text question for application to a data source
JP2001216311A (ja) イベント分析装置、及びイベント分析プログラムが格納されたプログラム装置
Heilmann et al. Analyzing the effects of entrenched grammatical constructions on translation
Miedema Towards successful interaction between humans and databases
Grammel User interfaces supporting information visualization novices in visualization construction
Ham The Design of an Interactive Topic Modeling Application for Media Content

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG UZ VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
REG Reference to national code

Ref country code: DE

Ref legal event code: 8642

122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP

点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载