US 12,292,937 B2
Cognitive automation platform
Shariq Mansoor, Mountain View, CA (US)
Assigned to Aera Technology, Inc., Mountain View, CA (US)
Filed by Aera Technology, Inc., Mountain View, CA (US)
Filed on Aug. 27, 2021, as Appl. No. 17/460,018.
Claims priority of provisional application 63/071,950, filed on Aug. 28, 2020.
Prior Publication US 2022/0067109 A1, Mar. 3, 2022
Int. Cl. G06F 16/951 (2019.01); G06F 16/23 (2019.01); G06F 16/9535 (2019.01); G06F 16/9538 (2019.01); G06F 21/60 (2013.01); G06N 5/022 (2023.01); G06N 7/02 (2006.01)
CPC G06F 16/951 (2019.01) [G06F 16/2308 (2019.01); G06F 16/2358 (2019.01); G06F 16/9535 (2019.01); G06F 16/9538 (2019.01); G06F 21/602 (2013.01); G06N 5/022 (2013.01); G06N 7/023 (2013.01); G06N 7/026 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A network-accessible platform, comprising:
a memory configured to store non-transitory computer readable instructions; and
a processor communicatively coupled to the memory, wherein the processor, when executing the non-transitory computer readable instructions, is configured to:
crawl data in a transaction system using at least one data crawler run with multiple connectors in a cluster,
reducing network bandwidth consumed by compressing the at least one data crawler;
process the crawled data using at least one data processing engine configured to transform the crawled data;
receive the transformed crawled data into a cognitive data layer (CDL), wherein the CDL is configured to index the transformed crawled data, and wherein the transformed crawled data in the CDL is searchable using a natural language voice interface;
generate a knowledge graph from the transformed crawled data, wherein the knowledge graph is used to enhance natural language search results;
analyze the transformed crawled data in the CDL;
based on the analysis of the transformed crawled data in the CDL, detect at least one specified condition in the CDL;
report the at least one specified condition;
analyze an audit trail log, wherein the audit trail log comprises a list of artificial intelligence algorithms used for selecting a recommendation; and
based on the analysis of the audit trail log, generate at least one recommendation to address the at least one specified condition;
provide a drag and drop interface and a library of pre-defined visual constructs for building one or more skills; and
build, using a cognitive development kit, a specific skill application on top of a cognitive operating system.