Value scorer in an automated disclosure assessment system

    公开(公告)号:US10832360B2

    公开(公告)日:2020-11-10

    申请号:US14918103

    申请日:2015-10-20

    Abstract: Software that uses machine-logic based algorithms to assess the value of idea descriptions by performing the following operations: (i) receiving an idea description pertaining to an idea; (ii) generating a density score for the idea, wherein the density score is based, at least in part, on one or more publication date densities of a set of works related to the idea description; (iii) generating a novelty score for the idea, wherein the novelty score is based, at least in part, on a comparison of the idea description to the set of works related to the idea description using natural language processing; and (iv) assessing the value of the idea based, at least in part, on the generated density score and the generated novelty score.

    Value Scorer in an Automated Disclosure Assessment System

    公开(公告)号:US20170109848A1

    公开(公告)日:2017-04-20

    申请号:US14918103

    申请日:2015-10-20

    Abstract: Software that uses machine-logic based algorithms to assess the value of idea descriptions by performing the following operations: (i) receiving an idea description pertaining to an idea; (ii) generating a density score for the idea, wherein the density score is based, at least in part, on one or more publication date densities of a set of works related to the idea description; (iii) generating a novelty score for the idea, wherein the novelty score is based, at least in part, on a comparison of the idea description to the set of works related to the idea description using natural language processing; and (iv) assessing the value of the idea based, at least in part, on the generated density score and the generated novelty score.

    Cognitive system comparison and recommendation engine

    公开(公告)号:US10380152B2

    公开(公告)日:2019-08-13

    申请号:US15000417

    申请日:2016-01-19

    Abstract: Mechanisms are provided to implement a cognitive system collaboration identification and recommendation system (CSCIRS). The CSCIRS stores, in a cognitive system database, entries corresponding to a plurality of cognitive system instances. Each entry identifies operational characteristics of a corresponding cognitive system instance. The CSCIRS receives, from a requestor, a request to identify a potential collaborative cognitive system instance and identifies, based on the request and the cognitive system database, a candidate collaborative cognitive system instance. The CSCIRS generates a collaboration recommendation based on the identification and outputs an output corresponding to the collaboration recommendation.

    ENHANCED PRIORITIZATION OF TASKS IN REAL-TIME

    公开(公告)号:US20170199762A1

    公开(公告)日:2017-07-13

    申请号:US14993921

    申请日:2016-01-12

    CPC classification number: G06F9/4881 G06F13/18 G06N3/126 G06N20/00

    Abstract: Techniques are described for a real-time prioritization of service tasks. In one example, a method includes receiving one or more customer activity inputs associated with one or more service tasks for performing in a service establishment on behalf of customers of the service establishment. The method further includes receiving one or more metadata items associated with the one or more service tasks. The method also includes determining a prioritization of the one or more service tasks based on the one or more customer activity inputs, wherein determining the prioritization includes generating a prioritization value for the one or more service tasks based at least in part on at least one of the one or more metadata items or the one or more customer activity inputs, and updating the one or more service tasks based on the prioritization value.

    Utilizing temporal indicators to weight semantic values

    公开(公告)号:US09646247B2

    公开(公告)日:2017-05-09

    申请号:US14248803

    申请日:2014-04-09

    Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for utilizing temporal indicators to weight semantic values. A set of temporal characteristics is identified of a set of initial candidate answers. For each initial candidate answer in the set of initial candidate answers: a distance value is generated for each of the set of temporal characteristics of the set of initial candidate answers, a multiplier value is determined with which to weight an initial confidence score associated with the initial candidate answer using the distance value; a sentiment value is determined of the initial candidate answer, and a final weight value is determined using the multiplier value, the sentiment value, and the initial confidence score associated with the initial candidate answer. A set of temporally refined candidate answers is then provided using the determined final weight values.

    Question correction and evaluation mechanism for a question answering system

    公开(公告)号:US10671929B2

    公开(公告)日:2020-06-02

    申请号:US14472513

    申请日:2014-08-29

    Abstract: Mechanisms are provided in a question answering (QA) system comprising a QA system pipeline that analyzes an input question and generates an answer to the input question, for pre-processing the input question. The mechanisms receive an input question and input the input question to a pre-processor flow path having one or more pre-processors. The one or more pre-processors transform the input question into a transformed question by correcting errors in a formulation of the input question that are determined to be detrimental to efficient and accurate processing of the input question by a QA system pipeline of the QA system. The transformed question is then input to the QA system pipeline of the QA system which processes the transformed question to generate and output an answer to the input question.

Patent Agency Ranking