US 12,271,413 B2
Method and system for analyzing entities
Jonathan William Mugan, Buda, TX (US); Laura Hitt, Austin, TX (US); Jimmie Goode, Austin, TX (US); Russ Gregory, Austin, TX (US); and Yuan Qu, Austin, TX (US)
Assigned to Pulselight Holdings, Inc., Austin, TX (US)
Filed by PULSELIGHT HOLDINGS, INC., Austin, TX (US)
Filed on Feb. 28, 2022, as Appl. No. 17/683,321.
Application 17/683,321 is a continuation of application No. 16/601,428, filed on Oct. 14, 2019, granted, now 11,263,250.
Application 16/601,428 is a continuation of application No. 15/632,180, filed on Jun. 23, 2017, granted, now 10,445,356.
Claims priority of provisional application 62/354,612, filed on Jun. 24, 2016.
Prior Publication US 2022/0269707 A1, Aug. 25, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/30 (2020.01); G06F 16/334 (2025.01); G06F 16/34 (2019.01); G06F 40/58 (2020.01); G06N 3/08 (2023.01)
CPC G06F 16/345 (2019.01) [G06F 16/334 (2019.01); G06F 40/30 (2020.01); G06F 40/58 (2020.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An improved computational method of identifying which corpus of interaction data best matches a query, comprising:
providing two or more corpuses of interaction data, wherein a corpus of interaction data comprises a corpus of event data generated by interactions over time;
providing an object translator computer system comprising:
one or more processors coupled to non-transitory data storage media, wherein the data storage media comprises trained parameter data, and
wherein the data storage media further comprises object translator computer instructions which, when executed by the one or more processors, cause the object translator computer system to perform a recurrent neural network method using the trained parameter data to create a summary of a corpus of interaction data, and
wherein the object translator computer instructions further comprise:
encoder computer instructions to encode a corpus of interaction data into an intermediate representation of interaction data and to store the intermediate representation of interaction data in the data storage media, wherein said intermediate representation of interaction data comprises a numeric representation in a high-dimensional space, and
decoder computer instructions to decode the intermediate representation of interaction data into a summary;
for each of the two or more corpuses of interaction data, encoding the corpus of interaction data into an intermediate representation of interaction data, wherein the encoding is performed by the object translator computer system;
providing a query comprising a sequence of words or events;
for each of the two or more corpuses of interaction data, determining a cost of generating the query from the intermediate representation of interaction data, wherein determining a cost is performed by the object translator computer system; and
selecting the corpus of interaction data having the lowest cost of generating the query.