公开(公告)号：US20200226321A1

公开(公告)日：2020-07-16

申请号：US16709069

申请日：2019-12-10

申请人： THE REGENTS OF THE UNIVERSITY OF MICHIGAN

发明人： Michael L. BURNS ,  John VANDERVEST ,  Sachin KHETERPAL ,  Nirav Jitendra SHAH ,  Leif SAAGER ,  Jay JEONG ,  Anik SINHA

IPC分类号： G06F40/174 ,  G16H10/60 ,  G06F40/157 ,  G06N20/20

摘要： A method is presented for assigning billing codes for medical procedures. For each string in an input record describing a medical procedure in the input text description, comparing the string to entries in a dictionary of common misspelling and, in response to the string matching an entry in the dictionary, replacing the string with proper spelling; for each string in the input record, comparing the string to entries in another dictionary of abbreviations and, in response to the string matching an entry in the dictionary, replacing the string with expanded text for the abbreviation; constructing a feature vector by extracting features from the input record; for each billing code in a listing of possible billing codes, computing a classifier score for the feature vector using machine learning; and assigning a billing code to the input record from the listing of possible billing codes based on the classifier scores.

公开(公告)号：US20240330600A1

公开(公告)日：2024-10-03

申请号：US18128269

申请日：2023-03-30

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Yotam PERLITZ ,  Michal SHMUELI-SCHEUER ,  Liat EIN-DOR ,  Dafna SHEINWALD ,  Noam SLONIM

IPC分类号： G06F40/40 ,  G06F40/157 ,  G06F40/30

CPC分类号： G06F40/40 ,  G06F40/157 ,  G06F40/30

摘要： A table-to-text (T2T) generation model provides type control and semantic diversity. A method, system, and computer program product are configured to: train a model to generate one or more logic-type-specific natural language statements based on tabular data; in response to receiving a first input comprising first input data with a user-specified logic-type, the trained model generating a first logic-type-specific natural language statement based on the first input data and the user-specified logic-type; and in response to receiving a second input comprising second input data without a user-specified logic-type, the trained model generating plural second logic-type-specific natural language statements based on the second input data, wherein respective ones of the second logic-type-specific natural language statements are generated according to respective ones of plural predefined logic-types.

公开(公告)号：US12079841B2

公开(公告)日：2024-09-03

申请号：US17814069

申请日：2022-07-21

申请人： Bytedance Inc.

发明人： Kannan Nitin Sharma ,  Srinivasa Vedanarayanan ,  Vidhyaa Muralidharan

IPC分类号： G06Q30/02 ,  G06F11/36 ,  G06F17/16 ,  G06F18/22 ,  G06F40/157 ,  G06N20/00 ,  G06Q30/0251 ,  G16H10/60 ,  G06Q30/0242

CPC分类号： G06Q30/0269 ,  G06F11/3688 ,  G06F17/16 ,  G06F18/22 ,  G06F40/157 ,  G06N20/00 ,  G06Q30/0256 ,  G16H10/60 ,  G06Q30/0242

摘要： In general, embodiments of the present disclosure provide for a configurable relevance service platform via a relevance test driver. In embodiments, test configuration data associated with at least one test scenario for a relevance service is received via at least one relevance test driver that interfaces with a relevance test service. Additionally, one or more promotions relevant to a user identifier are determined based at least in part on the test configuration data, and output data associated with the one or more promotions is transmitted to the relevance test service.

公开(公告)号：US20240202428A1

公开(公告)日：2024-06-20

申请号：US18388217

申请日：2023-11-09

申请人： KDAN MOBILE SOFTWARE LTD.

发明人： SHENG-JUN LU ,  WEN-ZHONG YIN ,  CHAO WANG ,  PO-CHOU SU ,  WEN-WEI LIN

IPC分类号： G06F40/157 ,  G06F40/205

CPC分类号： G06F40/157 ,  G06F40/205

摘要： There is provided a method for processing tables in a PDF file, including: parsing the PDF file to obtain coordinates of start points and end points of all transverse line sections and longitudinal line sections; obtaining coordinates of crosspoints of all line sections and recording coordinates of line sections that form the crosspoints; calculating all unit grids according to the coordinates of the crosspoints and the coordinates of the line sections; and filling every character respectively into a corresponding unit grid according to character coordinates obtained in parsing the PDF file.

公开(公告)号：US11860683B1

公开(公告)日：2024-01-02

申请号：US17852232

申请日：2022-06-28

申请人： Pluralytics, Inc.

发明人： Alisa Miller ,  Richard Byrne ,  Morteza Shahriari Nia

IPC分类号： G06F40/157 ,  G06F16/332

CPC分类号： G06F40/157 ,  G06F16/3329

摘要： Disclosed subject matter benchmarks and aligns content with target audiences. A user may provide content to a language intelligence platform. Scores are then generated by analyzing the content based on values-specific dictionaries, which reflect values of targeted audiences. Based on a comparison between a generated score and a benchmark values score for the target audience, appropriate action may be taken. Disclosed teachings support multiple layers of comparisons and score calculations including comparisons and scoring of all text, segments of text, and specific phrases to achieve a more comprehensive analysis. Embodiments may determine whether headers or other sections that may garner more attention, are aligned with a benchmark. Instead of suggesting alternative content, customer-specific benchmarks may tailor the analysis to align with customer's goals and priorities, potentially resulting in additional performance indicators that support the identification of correlations and predictive lexical patterns of higher performing content.

公开(公告)号：US11709993B2

公开(公告)日：2023-07-25

申请号：US17332493

申请日：2021-05-27

申请人： Microsoft Technology Licensing, LLC

发明人： Jeffrey James Duzak

IPC分类号： G06F40/18 ,  G06F16/332 ,  G06F16/31 ,  G06F40/123 ,  G06F40/157

CPC分类号： G06F40/18 ,  G06F16/328 ,  G06F16/332 ,  G06F40/123 ,  G06F40/157

摘要： Systems and methods are directed to providing efficient and fast invocation of concurrent sheet defined functions (SDFs) including dynamic arrays by front-loading the work. At SDF creation time, a SDF cell table, a formula table, and a spill area table are generated. The SDF cell table represents cells from a worksheet that are used for the SDF. The formula table comprises an index of formulas used by the SDF, whereby index identifiers are stored in cells of the SDF cell table. The spill area table comprises an index of spill areas where each dynamic array may automatically spill into. The SDF cell table, formula table, and spill area table are shared between a plurality of invocations of the SDF during invocation time.

公开(公告)号：US11681874B2

公开(公告)日：2023-06-20

申请号：US17067335

申请日：2020-10-09

申请人： OPEN TEXT CORPORATION

发明人： Martin Brousseau ,  Renaud Levert

IPC分类号： G06F16/30 ,  G06F40/295 ,  G06F40/49 ,  G06F40/55 ,  G06F40/157

CPC分类号： G06F40/295 ,  G06F16/30 ,  G06F40/157 ,  G06F40/49 ,  G06F40/55

摘要： An AI platform may receive a request for information on text. The text is processed through a text mining pipeline for dynamic attribute extraction. An engine determines entities in the text and utilizes the entities to determine a relationship pattern. The engine identifies a trigger by matching one of the entities with a predefined entity in a utility authority file, locates an entity in close proximity to the trigger, identifies a value or regular expression in close proximity to the trigger in the text, and creates a triplet containing the entity, the trigger, and the value or regular expression, the triplet representing the relationship pattern. The engine applies an action to the triplet, wherein the action comprises obtaining the value from the text or translating the regular expression. The engine attaches the value or a result from the translating to the entity as a dynamic attribute of the entity.

公开(公告)号：US20220374477A1

公开(公告)日：2022-11-24

申请号：US17880861

申请日：2022-08-04

申请人： Roblox Corporation

发明人： Aswath MANOHARAN ,  Nikolaus SONNTAG ,  Shailendra RATHORE

IPC分类号： G06F16/9032 ,  A63F13/85 ,  G06F16/36 ,  G06F40/157 ,  G06F40/242

摘要： A method and system is disclosed that generates a dictionary of terms comprising terms associated with games of a collaboration platform. The method further identifies search terms associated with previous search queries. The method compares the search terms with the terms of the dictionary to determine whether the search terms associated with the previous search queries are in the dictionary of terms. The method identifies a first set of the search terms that are candidates to receive search suggestions and a second set of the search terms that are to be the search suggestions based on the comparison. The method also generates a record that associates candidate search terms of the first set of the search terms with respective search suggestions of the second set of the search terms. The record is used to provide a search suggestion for a search term of a new search query.

公开(公告)号：US20220180044A1

公开(公告)日：2022-06-09

申请号：US17111392

申请日：2020-12-03

申请人： International Business Machines Corporation

发明人： Peter Zhong ,  Antonio Jose Jimeno Yepes

IPC分类号： G06F40/157 ,  G06K9/00 ,  G06N3/08 ,  G06N3/04

摘要： Aspects of the present invention disclose a method for automatic delineation and extraction of tabular data in portable document format (PDF). The method includes one or more processors extracting metadata corresponding to tabular data in a text-based portable document format (PDF), wherein the metadata is associated with characters and border lines of the tabular data. The method further includes generating a graph structure corresponding to the tabular data in the text-based PDF based at least in part on the metadata. The method further includes generating a vector representation of the graph structure. The method further includes constructing a tree structure corresponding to the tabular data based at least in part on the vector representation.

公开(公告)号：US11295068B2

公开(公告)日：2022-04-05

申请号：US15631250

申请日：2017-06-23

申请人： salesforce.com, inc.

发明人： Kelly Henvy

IPC分类号： G06F16/907 ,  G06F40/157 ,  G06F16/23

摘要： Techniques for maintaining a data dictionary within a computing platform that provides a multitenant environment in which multiple tenants utilizing the multitenant environment share a single instance of a database. The data dictionary is maintained with referential integrity utilizing custom database objects to provide metadata corresponding to the data dictionary. The data dictionary tracks attributes for the custom database objects utilizing natively supported field attributes and the custom database objects maintain tenant-specific information. The custom database objects are automatically updated corresponding to the data dictionary. A notification to one or more users is generated for custom database objects that correspond to the data dictionary that cannot be updated automatically, if any.