Wei Hai Peng

US Patent:

8312056, Nov 13, 2012

Filed:

Sep 13, 2011

Appl. No.:

13/231321

Inventors:

Wei Peng - Fremont CA, US
Tong Sun - Penfield NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 17/30

US Classification:

707802, 705319

Abstract:

A system and method for identifying a key influencer in a social media environment for enterprise marketing utilizing topic modeling and social diffusion analysis. A user interest profile can be generated by analyzing historical data stored in a database utilizing. A social graph can be generated and an influence measuring process based on the social graph data can be performed utilizing a static diffusion model and a dynamic diffusion model to calculate a set of key influencers. The dynamic diffusion model considers time stamp information to assess an impact of each user communication on the growth of a conversation within a time period. The key influencer can be identified in a specific topic area and a number of total users that can be reached via the influencer within a specific time window can be predicted.

US Patent:

20120259616, Oct 11, 2012

Filed:

Apr 8, 2011

Appl. No.:

13/082963

Inventors:

Wei Peng - Sunnyvale CA, US
Dae Hoon Park - Champaign IL, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 17/27

US Classification:

704 9, 704E11001

Abstract:

Embodiments generally relate to systems and methods for generating a sentiment dictionary and calculating sentiment scores of adjectives within the sentiment dictionary. A set of seed words can be identified and expanded using synonyms and antonyms of the set of seed words. Social media data can be parse to identify adjectives that link to the set of seed words with the words “and” or “but.” Matrices representing the attraction and repulsion among the linked adjectives can be generated. A factorization algorithm can be minimized to determine an output matrix that comprises positive and negative sentiment scores for each of the adjectives. In embodiments, a sentiment score for part of all of the social media data can be calculated using the output matrix, and one or more parts of the social media data can be classified as a positive or negative sentiment.

US Patent:

20130080212, Mar 28, 2013

Filed:

Sep 26, 2011

Appl. No.:

13/245039

Inventors:

Lei Li - Miami FL, US
Tong Sun - Penfield NY, US
Wei Peng - Fremont CA, US

Assignee:

XEROX CORPORATION - Norwalk CT

International Classification:

G06Q 10/00

US Classification:

705 738

Abstract:

A system and method for measuring engagement effectiveness with respect to a service agent by analyzing a conversation between the agent and a customer in a social media environment. A conversation history between the agent and the customer can be mapped into a multi-resolution space based on different time frames via a mapping module. A polarized topical and sentimental distance between the continuous conversations can be calculated by applying a topic-sentiment mixture model and a divergence theorem onto the conversation history with respect to the time frame. Finally, the polarized topical distances can be aggregated in a time-sensitive way based on a time function and an effectiveness score can be calculated and represented as a weighted pyramid kernel of multiple levels. Such a time-sensitive pyramid kernel function based on the implicit topical and sentimental correspondences between daily conversations enables discriminative evaluation for the agent engagement in a customer care.

US Patent:

20130086072, Apr 4, 2013

Filed:

Oct 3, 2011

Appl. No.:

13/251731

Inventors:

Wei Peng - Fremont CA, US
Anuj Jaiswal - State College PA, US
Tong Sun - Penfield NY, US
Matthew DeRoller - Webster NY, US

Assignee:

XEROX CORPORATION - Norwalk CT

International Classification:

G06F 17/30

US Classification:

707743, 707754, 707E1711, 707E17018

Abstract:

Methods, systems and processor-readable media for extracting and classifying location information utilizing social media messages and/or data thereof. The social media messages can be sampled from a social media database and the messages filtered based on a heuristic rule. A geolocation entity from the unstructured social media messages can be extracted utilizing a geolocation entity extracting module. The messages with the geoentities can be uploaded onto a crowd sourcing platform to manually annotate the messages with a label. A text classification model can be built and learned from the label utilizing a machine learning algorithm and the messages can be classified by a location classifier in order to extract the user location. The user location can then be transformed into a geocode so that a spatial search can be enabled and the distance between the locations can be easily calculated.

US Patent:

20130151531, Jun 13, 2013

Filed:

Dec 13, 2011

Appl. No.:

13/324391

Inventors:

Lei Li - Miami FL, US
Wei Peng - Fremont CA, US
Tong Sun - Penfield NY, US

Assignee:

Xerox Corporation - Norwalk CT

International Classification:

G06F 17/30

US Classification:

707740, 707E17005, 707E17089

Abstract:

Embodiments generally relate to systems and methods for detecting topics in social media data. More particularly, the systems and methods can extract a concept hierarchy from a set of data, wherein the concept hierarchy comprises a plurality of layers. Further, the systems and methods can train topic models based on the content in each of the layers. Still further, the systems and methods can select the most appropriate topic model for social media data by balancing the complexity of the model and the accuracy of the topic detection result. Moreover, the systems and methods can use the most appropriate topic model to detect topics in social media data.

US Patent:

20220343008, Oct 27, 2022

Filed:

May 14, 2021

Appl. No.:

17/320880

Inventors:

- Mountain View CA, US
Wei Hua Peng - San Francisco CA, US

International Classification:

G06F 21/62
G06F 21/60

Abstract:

Systems and methods for controlling access to data in applications using client-side encryption. In that regard, in some examples, a first application (e.g., an email application, calendar application, messaging application, word processing application, file storage application, etc.) hosted from a particular web domain may be configured to invoke a second application hosted from a different origin (e.g., a different web domain or subdomain) to handle receiving and encrypting any sensitive information from a client entered through a client application (e.g., a web browser), and to handle decrypting information to be provided to the client through the client application. This second application may be loaded in an inline frame or similar subwindow or subroutine configured to prevent or limit the first application from having access to sensitive information in the second application.

US Patent:

20230044773, Feb 9, 2023

Filed:

Aug 6, 2021

Appl. No.:

17/396290

Inventors:

- San Francisco CA, US
Wei Peng - San Francisco CA, US

International Classification:

G06Q 30/06

Abstract:

An online concierge shopping system identifies recipes to users to encourage them to include items from the recipes in orders. The online concierge system generates a recipe vector for each recipe based on items included in a recipe. A dimension of a recipe vector identifies an item included in a corresponding recipe and may include an importance score of the item to the recipe. The importance score of an item to a recipe is based on a term frequency of the item in the recipe and an inverse document frequency of the item across multiple recipes. The online concierge system determines overlap between items in recipe vectors an order vector generated from items included in an order from a user and selects a recipe for the user based on overlapping items in the recipe vector and in the order vector.

US Patent:

20210110163, Apr 15, 2021

Filed:

Oct 13, 2020

Appl. No.:

17/069638

Inventors:

- Mountain View CA, US
Wei Peng - Fremont CA, US
Nicolas Crowell - San Francisco CA, US

International Classification:

G06K 9/00
G06K 9/62
G06N 5/02

Abstract:

In one aspect, a method includes obtaining videos and for each video: obtaining a set of anchors for the video, each anchor beginning at the playback time and including anchor text; identifying, from text generated from audio of the video, a set of entities specified in the text, wherein each entity in the set of entities is associated with a times stamp at which the entity is mentioned; determining, by a language model and from the text generated from the audio of the video, an importance value for each entity; for a subset of the videos, receiving rater data that describes, for each anchor, the accuracy of the anchor text in describing subject matter of the video; and training, using the human rater data, the importance values, the text, and the set of entities, an anchor model that predicts an entity label for an anchor for a video.