Hewlett-packard Development Company, L.p.

Hewlett Packard Enterprise Development LP

Micro Focus Lcc

Entit Software LLC

Riddhiman Ghosh

Mohamed E Dekhil

Meichun Hsu

Ming C Hao

Maria G Castellanos

Umeshwar Dayal

Christian Rohrdantz

Jhilmil Jain

Jun Li

Nelson L Chang

Lei Zhang

Michael Hund

Thomas Rathbone

Chetan Kumar Gupta

Kave Eshghi

Craig Peter Sayers

Renato Keshet

Daniel Keim

Kevin Smathers

Cheng Chang

Hyun Duk Kim

Arun Kumar Paruchuri

Bao-Yao Zhou

Bing Liu

A unified visualization interface is disclosed. One example is a system including an association module, a multicasting module, a data sharing module, and a unified visualization interface. The association module associates an identified event in a first visualization system with a visualization function. The multicasting module stores event data related to the identified event and the associated visualization function in a shared data source, and multicasts the identified event to a second visualization system. The data sharing module associates the event data with characteristics of the first visualization system, and shares, in response to the multicast of the identified event, the shared data source with the second visualization system. The unified visualization interface automatically invokes, without software changes, the second visualization system in response to the multicast of the identified event, the invoking based on the shared data source including the characteristics of the first visualization system.

Automatically invoked unified visualization interface

A technique for visualizing topics includes depicting topic bubbles including pixels. In one example, selected topics are identified from records based on scoring candidate terms in the records according to a user-specified metric and a metric selected from among frequencies of occurrence of records pertaining to the respective candidate terms, and negativity of sentiment expressed with respect to the candidate terms in the records. A visualization is generated including bubbles representing topics, the bubbles including pixels representing corresponding records. A bubble has a shape dependent upon a number of records and a time interval represented by the bubble. Visual indicators are assigned to the pixels in a given bubble according to values of an attribute expressed in the corresponding records for the topic represented by the given bubble, resulting in the analysis of the selected topics being less time consuming and labor intensive.

Visualizing topics with bubbles including pixels

Systems, methods, and other embodiments associated with tracking in store consumer behavior are described. One example method includes receiving a product tag data (PTD) and a personal data (PD) from a portable digital device (PDD). The PTD is associated with a scan of a product tag of a product. The example method may also include storing the PTD and the PD in a database. The example method may also include creating a virtual redeemable offer (VRO) based, at least in part, on an analysis of the PD, the PTD associated with the scan, and a product information (PI) associated with the product tag. The PI may be stored in the database and describes the product. The example method may also include providing the CRVC to the PDD.

Virtual redeemable offers

An event occurring in a particular geographic region is identified based on disseminated information containing public commentary in the particular geographic region. Attributes that are related to the event are identified, and sentiment words relating to the identified event are extracted from the disseminated information, where the extracted sentiment words are in a local language of the particular geographic region. A sentiment trend visualization is generated that depicts a trend of sentiments of at least a particular one of the identified attributes, wherein the sentiments are based on the sentiment words for at least the particular attribute.

Sentiment trent visualization relating to an event occuring in a particular geographic region

The present disclosure provides a computer-implemented method of acquiring customer insight information in a retail environment. The method includes receiving a product interaction from a mobile device, the product interaction comprising a product identifier corresponding to a product located in the retail environment. The method also includes determining a customer location within the retail environment based on a planned location of the product. The method also includes performing a business action based, at least in part, on the product interaction. The method also includes storing customer insight information corresponding to the product interaction to a data structure.

Acquiring customer insight in a retail environment

A method of capturing intentions within online text comprises with a data mining device (), identifying (block) a number of statements of intention within an online forum (), and with the data mining device (), extracting (block) a number of attributes () from the statements of intention. A system () for extracting intentions expressed within an online forum comprises a data mining device (), a forum server () comprising a number of online forums () communicatively coupled to the data mining device (), in which the data mining device identifies a number of statements of intention within the online forums () and extracts a number of attributes () from the statements of intention.

Capturing intentions within online text

An example system includes an extraction module, an intention processing module, and an intention visualization module. The extraction module is configured to ingest textual data from a text source. The intention processing module is configured to process the textual data and identify one or more intention statements within the textual data. The intention visualization module is configured to provide an interactive interface that facilitates filtering and visualization of aspects of the one or more intention statements.

Intention statement visualization

A technique includes obtaining a plurality of n-grams from a plurality of messages, determining a temporal histogram for each n-gram, and determining synonyms among the n-grams based on a combination of a correlation of the histograms and a distance measure between n-grams.

Synonym determination among n-grams

There is provided a computer-implemented method of performing sentiment analysis. An exemplary method comprises performing a first sentiment analysis on microblogging data based on a method using an opinion lexicon. The method also includes training a classifier using training data from the first sentiment analysis. Additionally, the method includes identifying a new opinion term in the microblogging data by performing a statistical test. The new opinion terms are not in the opinion lexicon. The method also includes identifying new microblogging data based on the new opinion term. Further, the method includes performing a second sentiment analysis on the new microblogging data using the classifier.

Performing sentiment analysis on microblogging data, including identifying a new opinion term therein

A system and method is disclosed for generating a user profile. The method discloses: receiving a user profile request from a profile requester; identifying profile fragments with a profile mediator, from existing profiles in a profile corpus which are responsive to the user profile request; aggregating the identified profile fragments into the user profile response; and transmitting the user profile response to the profile requestor. The system discloses various means and modules for effecting the method.

System and method for generating a user profile

A method for generating summaries of text is described. The method includes the step of extracting features from text of text lists from summaries. The explanatoriness of the text is then evaluated, wherein evaluating the explanatoriness of text includes evaluating the features of the text, including at least the step of evaluating the discriminativeness of the features of the text by comparing the text to a first text data set, wherein the first text data set is derived from a topic label. The evaluated text is then ranked based on the explanatoriness evaluation.

Generation of explanatory summaries

An example system includes at least one memory and at least one processing device. The at least one memory comprises instructions that when executed by the at least one processing device cause the system to receive a text corpus, filter the text corpus to obtain a plurality of attributes, determine the semantic cohesion between the plurality of attributes, and create an attribute cloud including the plurality of attributes, where the placement of the plurality of attributes within the attribute cloud is based at least in part on the determined semantic cohesion between the plurality of attributes.

Attribute cloud

There is provided a computer-implemented method of performing sentiment analysis. An exemplary method comprises identifying one or more sentences in a microblog. The microblog comprises an entity. The method further includes identifying one or more opinion words in the sentences based on an opinion lexicon. Additionally, the method includes determining, for each of the sentences, an opinion value for the entity. The opinion value is determined based on an opinion value for each of the opinion words in an opinion lexicon.

Performing sentiment analysis

Data records containing user feedback regarding at least one offering are received. From among candidate attributes in the received data records, a subset of attributes that relate to user sentiment regarding the at least one offering is selected, where the selecting is according to selection criteria including frequency of occurrence of the candidate attributes, relative amounts of negative and positive feedback associated with the candidate attributes, and time density of feedback associated with the candidate attributes. A visualization of at least one sentiment characteristic of the selected subset of attributes that relate to user sentiment is presented for display.

Selecting sentiment attributes for visualization

A method for managing devices is described. The method includes receiving wireless fingerprints from a plurality of devices, each of the wireless fingerprints comprising a unique device identifier, a wireless signal strength indicator that corresponds to a relative position a device is located with respect to one or more wireless access points and unique identifiers associated with the access points. The method further includes identifying a similarity between a first wireless fingerprint associated with a first of the plurality of devices and a second wireless fingerprint associated with a second of the plurality of devices and determining the first device is located physically close to the second device based on the similarity.

Growing community of inventors

Sunnyvale, CA, United States of America

Riddhiman Ghosh