Benny F Lin

US Patent:

6905232, Jun 14, 2005

Filed:

Jun 11, 2003

Appl. No.:

10/458313

Inventors:

Benny Lin - Commerce CA, US

International Classification:

F21V021/00

US Classification:

362374, 362369, 362375

Abstract:

A lamp structure including a lamp housing, and a circular ring piece, a lamp holder, and a lamp locking-collar all assembled in the lamp housing sequentially. The lamp housing has holes on a surface for extending a wire through and has a stepped portion on an inner wall. The circular ring piece is placed in the lamp housing supported and fixed by the stepped portion. The lamp holder has a space for receiving a lamp bulb, and a protrusion on an external periphery engaging a notch provided on an adjustable compressible portion when the lamp holder is mounted. The lamp holder abuts against and is fixed on the circular ring piece. The lamp locking-collar and the lamp housing both have grooves for an elongated member (spring). The lamp locking-collar has gaskets for a waterproof seal.

US Patent:

20220279220, Sep 1, 2022

Filed:

Mar 1, 2021

Appl. No.:

17/189073

Inventors:

- New York NY, US
Benny LIN - New York NY, US
Anthony LIVHITS - Forest Hills NY, US
Erik Gregory MATLICK - Miami Beach FL, US
Christian Michael BURTON - New York NY, US
Robert James ARMSTRONG - Reno NV, US

Assignee:

BOMBORA, INC. - New York NY

International Classification:

H04N 21/231
H04L 29/08
H04N 21/25

Abstract:

Disclosed embodiments include a content consumption monitor (CCM) determines surges in content consumption based on changes in content consumptions scores. The CCM determines the content consumptions scores for domains and/or organizations (orgs) based on session events generated by different devices/users from the org and/or domain, a number of events generated by the org/domain, content and/or user interactions with the content indicated by the events, relevancy scores of the content to one or more topics, and/or other criteria. The CCM detects surges in consumption or interest in a topic for the domain/org when the consumption score reaches a threshold and/or within a period of time. The CCM may adjust the consumption score based on the changes in the relevancy, number of events and/or the number of users over different time periods. Other embodiments may be described and/or claimed.

US Patent:

20220230078, Jul 21, 2022

Filed:

Jan 20, 2021

Appl. No.:

17/153673

Inventors:

- New York NY, US
Robert James ARMSTRONG - Reno NV, US
Benny LIN - New York NY, US
Nicholaus Eugene HALECKY - Reno NV, US
Will KURT - Boston MA, US

Assignee:

BOMBORA, INC. - New York NY

International Classification:

G06N 5/04
G06N 20/00

Abstract:

Disclosed embodiments includes a network classification system (NCS) that generates a set of machine learning (ML) features from information about information objects accessed by various users, and determines an organization (org) type associated with the network address based on the set of ML features. Obtained network events may include the information about the accessed information objects. A content consumption monitor (CCM) generates consumption scores for the network addresses based on the identified org types. The CCM can generate more accurate intent and consumption data by filtering out events unrelated to content consumption for that org type. The NCS and the CCM may be implemented as the same network function, or the NCS and CCM may be implemented as separate network functions. Other embodiments may be described and/or claimed.

US Patent:

20220188699, Jun 16, 2022

Filed:

Mar 11, 2021

Appl. No.:

17/199268

Inventors:

- New York NY, US
Robert J. ARMSTRONG - Reno NV, US
Nicholaus E. HALECKY - Reno NV, US
Benny LIN - New York NY, US

Assignee:

BOMBORA, INC. - New York NY

International Classification:

G06N 20/00
G06N 5/04

Abstract:

Disclosed embodiments include a resource classification system (RCS) identifies one or more features in information objects (InObs) and uses the features to classify the InObs. The features may be based on structural semantics of the InObs, content semantics of InObs, content interaction behavior with the InObs, types of users accessing the InObs, and/or the like. The RCS may generate vectors that represent the different features. The vectors may be used to train a machine learning model to predict resource classifications of the InObs. The predicted resource classifications provide more accurate intent, consumption, and surge score predictions than existing solutions. Other embodiments may be described and/or claimed.

US Patent:

20220188700, Jun 16, 2022

Filed:

Apr 7, 2021

Appl. No.:

17/224903

Inventors:

- New York NY, US
Benny LIN - New York NY, US
Anthony LIVHITS - Forest Hills NY, US
Erik Gregory MATLICK - Miami Beach FL, US
Christian Michael BURTON - New York NY, US
Robert James ARMSTRONG - Reno NV, US

Assignee:

BOMBORA, INC. - New York NY

International Classification:

G06N 20/00
G06N 7/00
G06F 40/279

Abstract:

Disclosed embodiments include a distributed hyperparameter (HP) tuning system, which includes a manager and a plurality of trainers. The manager continuously estimates HP sets for a machine learning (ML) model and distributes each HP set to respective trainers. Each trainer obtains a respective HP set and trains a local version of the ML model using the respective HP set. Each trainer determines a performance value for an HP sets used to train its local version of the ML model, and sends the performance value and the HP set to the manager. The manager estimates a new HP set from the HP set received from each trainer. The HP set estimation continues until convergence takes place. Other embodiments may be described and/or claimed.

US Patent:

20210073661, Mar 11, 2021

Filed:

Sep 10, 2020

Appl. No.:

17/017425

Inventors:

- New York NY, US
Nicholaus Eugene Halecky - Reno NV, US
Benny Lin - New York NY, US

Assignee:

Bombora, Inc. - New York NY

International Classification:

G06N 5/04
G06N 20/00
H04L 29/12

Abstract:

An IP-to-Domain (IP2D) resolution system predicts which domain is most likely associated with an IP address. The resolution system generates unique source vote features (FSV) from (IP, domain, source) data. The FSV features are used to train a computer learning model that predicts which domain is most likely associated with an IP address. The domain predictions can then be used to more efficiently process events, more accurately calculate consumption scores, and more accurately detect associated company surges.

US Patent:

20200410514, Dec 31, 2020

Filed:

Sep 14, 2020

Appl. No.:

17/020309

Inventors:

- New York NY, US
Cynthia HUYNH - Nutley NJ, US
Hassan AHMED - Brooklyn NY, US
Benny LIN - Brooklyn NY, US
Robert ARMSTRONG - Brooklyn NY, US
Erik MATLICK - New York NY, US
Mark HERSCHBERG - New York NY, US

Assignee:

BOMBORA, INC. - New York NY

International Classification:

G06Q 30/02

Abstract:

A content consumption monitor (CCM) generates intent data that identifies topics of real-time interest to users. The CCM uses the intent data to direct information to more interested audiences and reduce the information noise/overload that may prevent users from viewing information. This targeted information may increase user conversion rates for seminars, advertising, documents downloads, or any other activity associated with published information. In one example, the CCM generates the intent data from third party content. Using a wide variety of third party content enables the CCM to better identify current user interests. The CCM may aggregate the intent data for different demographics, such as for companies, job positions, age, gender, or geographic locations.

US Patent:

20190294642, Sep 26, 2019

Filed:

Jun 7, 2019

Appl. No.:

16/435382

Inventors:

- New York NY, US
Robert J. Armstrong - Reno NV, US
Nicholaus Eugene Halecky - Reno NV, US
Benny Lin - New York NY, US

International Classification:

G06F 16/951
G06F 16/955
G06F 16/958

Abstract:

A website classification system identifies one or more features in websites and uses the features to classify the websites. The website classification system may generate features identifying structural semantics of webpages, content semantics of webpages, content interaction behavior with the webpages, or types of users accessing the webpages. The website classification system may generate vectors that represent the different features. A first set of vectors from classified websites are used for training a computer learning model. Vectors from unclassified websites are then fed into the trained learning model to predict a particular website classification. The predicted website classifications provide more accurate intent, consumption, and surge score predictions.