At&t Intellectual Property I, L.p.

At&t Mobility Ii LLC

Home Depot Product Authority, LLC

James Morgan White

Rudolph Mappus

Jeremy Fix

Herani Soewarto Brotman

Ravishankar Doejode

Rudolph L Mappus, Iv

Faizan Javed

Haozheng Tian

Meng Zhao

A system and method for machine learning classification of user sentiment is disclosed. The method includes storing including a plurality of category information. The plurality of category information includes a set of domain-specific category information. The method further includes extracting a plurality of aspects from textual data. The method further includes generating a sentiment by a machine learning model. The method further includes receiving the plurality of aspects and the set of domain-specific category information. The method further includes generating a sentiment based on the plurality of aspects and the set of domain-specific category information.

Classification of user sentiment based on machine learning

A method includes receiving a plurality of product query arrays each including a plurality of individual product queries received during a single user search session. The method further includes inputting the plurality of product query arrays into the query rewrite model. Text of each of the plurality of individual product queries in each product query array is treated as a whole token. The method further includes receiving a product query from a user electronic device. The method further includes determining a query rewrite for the product query using the query rewrite model and determining search results for the product query using the query rewrite. The method further includes sending information for presenting the search results on a display of the user electronic device responsive to the product query.

Query rewrite for low performing queries based on customer behavior

Aspects of the subject disclosure may include, for example, a process by which first data is received from a mobile device regarding first objects detected by the mobile device in an area, the first data having been collected by the mobile device at a number of first collection points while moving along a first path from an initial position in the area to a boundary of the area. The first data is aggregated with second data previously collected regarding second objects in the area, the second data having been collected at a number of second collection points along a second path different from the first path. The second data includes a position indicator for each of the second objects indexed by the initial position. A map of the area is generated based on the aggregating and the map is transmitted to the mobile device. Other embodiments are disclosed.

Apparatus and method for detecting objects and navigation

Determining a location of a user equipment (UE) based on historical location data and historical sector transition data is disclosed. A correlation between historic location information and a historic sector transition can be determined. The correlation can be stored in a searchable data set. A location of a current UE can be inferred based on a sector transition of the current UE. The sector transition of the current UE can be searched against the data set to indicate a likely location of the current UE based on historical information. The searchable data set can be based on sparse location data enabling location determinations for a current UE that can otherwise lack location services. Moreover, an order of a sector transition can imbue a directionality to stored location information such that a likely location in a sector can be correlated to a transition from a prior sector of a network session of the UE.

Inferring user equipment location data based on sector transition

More efficient mobile device location data can be obtained by estimating a most likely location point in a coverage pattern using a kernel density estimation technique. The kernel density estimation technique can provide a continuous estimate of the most frequented locations of a mobile device(s) within a coverage area. For each wireless sector, the collected location data can grouped to the closest geographic coordinate system, and an inference can be made based on the grouped data.

Facilitation of mobile device geolocation

Determining a location of a user equipment (UE) based on historical location data and historical sector transition data is disclosed. A correlation between historic location information and a historic sector transition can be determined. The correlation can be stored in a searchable data set. A location of a current UE can be inferred based on a sector transition of the current UE. The sector transition of the current UE can be searched against eh data set to indicate a likely location of the current UE based on historical information. The searchable data set can be based on sparse location data enabling location determinations for a current UE that can otherwise lack location services. Moreover, an order of a sector transition can imbue a directionality to stored location information such that a likely location in a sector can be correlated to a transition from a prior sector of a network session of the UE.

Aspects of the subject disclosure may include, for example, a method in which a mobile device determines a current position and direction; detects objects within an area including the current position; collects first data regarding the objects; buffers the first data; and transmits the first data to a remote system responsive to the mobile device reaching a boundary of the area. The method also comprises obtaining a map of the area from the remote device; the map includes information based on second data previously collected regarding objects in the area, the second data includes a position indicator and a direction indicator for each of the second objects indexed by the current position, and the remote device aggregates the first data and the second data to generate an updated map of the area. Navigation instructions are generated based on the current position and the map, Other embodiments are disclosed.

Growing community of inventors

Atlanta, GA, United States of America

James Morgan White