System and method for authoring electronic messages

    公开(公告)号:US10922490B2

    公开(公告)日:2021-02-16

    申请号:US15630287

    申请日:2017-06-22

    发明人: Varun Jain

    摘要: Systems, methods and apparatus for authoring an electronic message. In one example, the system, method, and apparatus include receiving an electronic message; categorizing the electronic message based on a message layout type associated with the electronic message; determining, with a sentiment analyzer, a sentiment type and a sentiment score associated with the electronic message; identifying a first plurality of words in the electronic message associated with the sentiment type; and outputting one or more selected from the group consisting of the message layout type, the sentiment type, and the sentiment score associated with the electronic message.

    Code vector embeddings for similarity metrics

    公开(公告)号:US10891352B1

    公开(公告)日:2021-01-12

    申请号:US15927188

    申请日:2018-03-21

    申请人: Optum, Inc.

    摘要: Aggregate vectors corresponding to non-textual information/data are provided in a multi-dimensional space. A computing entity access a plurality of instances of medical information comprising medical codes. The computing entity generates one or more medical sentences from the plurality of instances of medical information. Each medical sentence comprises one or more medical codes. The computing entity generates an embedding vector dictionary comprising a plurality of multi-dimensional vectors based on a medical embedding model trained using machine learning and the one or more medical sentences. Each multi-dimensional vector corresponds to a medical code. The computing entity generates a plurality of aggregate vectors based on the embedding vector dictionary and analyzes at least a portion of the plurality of aggregate vectors to identify two or more aggregate vectors that are similar or different based on a distance between the two or more aggregate vectors in the multi-dimensional space.

    Universal asynchronous receiver/transmitter unit, and memory controller and memory system including the same

    公开(公告)号:US10649937B2

    公开(公告)日:2020-05-12

    申请号:US16017053

    申请日:2018-06-25

    申请人: SK hynix Inc.

    发明人: Dong Sop Lee

    摘要: There are provided a universal asynchronous receiver/transmitter (UART) unit, and a memory controller and a memory system, which have the UART unit. A UART unit includes: a WORD table to store text information and a plurality of word codes corresponding to the text information, and to output a first word code corresponding to first text information when the first text information is received by the WORD table, wherein the text information includes a plurality of words, and the first text information includes a first word among the plurality of words; a UART controller to output the first text information to the WORD table by extracting the first word from output information, and to output an output code based on the output information and the first word code when the first word code is received from the WORD table; and a UART to output debugging information based on the output code.

    Synthetic intelligent extraction of relevant solutions for lifecycle management of complex systems

    公开(公告)号:US11966686B2

    公开(公告)日:2024-04-23

    申请号:US16443077

    申请日:2019-06-17

    摘要: The present disclosure provides for predictive query processing for complex system lifecycle management by identifying a seed document including natural language text describing an issue with a complex system; creating a synthesized document for the seed document by: removing portions of the seed document determined to satisfy filtering rules; identifying a first term set included in the natural language text that map to terminology identified in a data dictionary; extracting term-order data based on locations of the first term set in the natural language text; and including the first term set and the term-order data in the synthesized document; identifying, from a corpus of historic electronic documents, a first document set that are related to the seed document based on the term-order data included in the synthesized document; and outputting at least a portion of the first set of historic electronic documents.

    METHOD AND SYSTEM FOR MERGING PDF FILES IN A LARGE BATCH

    公开(公告)号:US20240005083A1

    公开(公告)日:2024-01-04

    申请号:US18035161

    申请日:2022-03-30

    发明人: Junyi LIANG

    摘要: Disclosed are a method and system for merging a large batch of PDF files. The method comprises: outputting header information of a target PDF file, outputting catalog dictionary information, and generating an object number of a PDF page object and recording same; parsing in sequence PDF files to be merged, and acquiring the object number and the offset of all indirect objects and the catalog dictionary information; parsing in sequence, from within the catalog dictionary information, page object dictionary information corresponding to the PDF files to be merged, and reading in sequence object number information of each page object; invoking a global object number generator to generate a new object number, and recording the correspondence between original object number information and the new object number in a map; invoking an output class of a PDF indirect object, outputting a page object of the PDF files to be merged into a page object of the target PDF file, and recording same in the start position and length in the target PDF file; and checking whether all PDF files to be merged have completed merging.

    PERMUTATION INVARIANCE FOR REPRESENTING LINEARIZED TABULAR DATA

    公开(公告)号:US20230409806A1

    公开(公告)日:2023-12-21

    申请号:US17807461

    申请日:2022-06-17

    IPC分类号: G06F40/157 G06F40/284

    CPC分类号: G06F40/157 G06F40/284

    摘要: An embodiment for encoding permutation-invariant representations of linearized tabular data. The embodiment may receive input including tabular data and linearize a column or row within the received tabular data. The embodiment may automatically assign an increasing sequence of position identifiers to each non-delimiting tokenized cell in the linearized column or row until a header delimiter is reached. The embodiment may, in response to reaching the header delimiter, automatically assign a monotonically increasing sequence of position identifiers for each non-delimiting tokenized cell positioned after the header delimiter, restarting from an integer corresponding to 1 greater than the position identifier assigned to the header delimiter for each non-delimiting tokenized cell positioned after cell delimiters. The embodiment may automatically assign a static position identifier for each of the cell delimiters in the linearized column or row and output an encoded permutation-invariant representation of the linearized column or row.

    DYNAMIC ATTRIBUTE EXTRACTION SYSTEMS AND METHODS FOR ARTIFICIAL INTELLIGENCE PLATFORM

    公开(公告)号:US20230259710A1

    公开(公告)日:2023-08-17

    申请号:US18302494

    申请日:2023-04-18

    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.

    DYNAMICALLY ADAPTABLE VIRTUAL KEYBOARD

    公开(公告)号:US20230065549A1

    公开(公告)日:2023-03-02

    申请号:US17894824

    申请日:2022-08-24

    申请人: Telia Company AB

    发明人: Anders BAER

    摘要: The invention relates to a method, the method comprising: recording user input through a virtual keyboard of a device for generating a user input history; determining, based on the user input history, at least one character associated with at least one correction operation in a context of the user input through the virtual keyboard of the device; generating a control signal for adjusting an output of the at least one character on the virtual keyboard, the at least one character is selected based on the at least one correction operation. The invention also relates to a computer program and to an apparatus.