Dell Products Inc.

Sandeep Ratnakar

Ramakanth Kanagovi

Ravi Shukla

Prakash Sridharan

Sumant Sahoo

Arun Swamy

Shrikrishna K Joisa

Chris Everett Peterson

Siddharth Sreekumar

Nicholas Anthony Esposito

Rachel Gabrielle Mazzini

Brennan Troy Robert Seal

Mayank Sharma

Method of generating configurations of computing products, including receiving images of a particular layout of the computing product; analyzing the particular layout, including identifying computing components of the computing product and determining a thermal mapping of the computing product; identifying physical constraints associated with the computing components of the computing product; identifying product profile of the computing product that indicates, for each computing component, features of the computing component; iteratively permutating, based on the physical constraints associated with the computing components and the thermal mapping, the particular layout to define permutated layouts; iteratively permutating each of the permutated layouts based on combinations of features of each of the computing components of the particular layout; generating, for the computing component, data table indicating each of the permutated layouts of the computing product and each of the combinations of features of each of the computing components of each of the permutated layouts.

Generating configuration of computing products

Crawling electronic documents, including: for each electronic document of a plurality of electronic documents: obtaining the electronic document including obtaining an entirety of the HyperText Markup Language (HTML) of the electronic document; analyzing the electronic document to identify a plurality of elements of the electronic document, each element of the plurality of elements including HTML tags, text associated with the HTML tags, and HTML attributes; creating a plurality of clusters of texts based on a similarity of the HTML tags, the text associated with the HTML tags, and the HTML attributes of each of the plurality of elements; labeling, for each cluster of the plurality of clusters, the cluster based on the text associated with the HTML tags of one element of the cluster; and updating, for each cluster of the plurality of clusters, an electronic document crawling model with data indicating the label of the cluster.

Crawling electronic (web) documents

An apparatus comprises at least one processing device configured to receive a query to determine associations between named entities and aspect terms for a document, to generate, utilizing a first machine learning model, a first set of encodings classifying words of the document as being aspect or non-aspect terms, to generate, utilizing a second machine learning model, a second set of encodings classifying associations of the words, and to determine, for a given aspect term, attention weights for a given subset of the words surrounding the given aspect term. The processing device is also configured to generate, utilizing a third machine learning model, predictions of association between the given aspect term and named entities recognized in the given subset of the words, and to provide a response to the query comprising at least one of the predicted associations.

Determining named entities associated with aspect terms extracted from documents having unstructured text data

An apparatus comprises at least one processing device configured to receive a query to perform sentiment analysis for a document, to generate, utilizing a first machine learning model, a first set of encodings classifying words of the document as being aspect or non-aspect terms, to generate, utilizing a second machine learning model, a second set of encodings classifying sentiment of the words of the document, and to determine, for a given aspect term, attention weights for a given subset of the words of the document surrounding the given aspect term. The processing device is also configured to generate, utilizing a third machine learning model, a given sentiment classification of the given aspect term based on the attention weights and a given portion of the second set of encodings for the given subset of the words, and to provide a response to the query comprising the given sentiment classification.

Sentiment analysis for aspect terms extracted from documents having unstructured text data

An apparatus comprises at least one processing device configured to receive a query to generate a summary of a document, to perform two or more iterations of filtering the document to produce a current version of the summary of the document, wherein each of the iterations comprises determining similarity between a first vector representation of the current version of the summary and second vector representations of respective ones of two or more portions of the unstructured text data of the document not yet added to the current version of the summary. The processing device is also configured to generate, following identification of one or more designated stopping criteria in a given iteration, a final version of the summary based at least in part on the current version of the summary produced in the given iteration, and to provide a response to the query comprising the final version of the summary.

Growing community of inventors

Bengaluru, India

Sandeep Ratnakar