| CPC G06F 40/30 (2020.01) [G06F 16/3344 (2019.01); G06F 16/335 (2019.01); G06F 16/345 (2019.01); G06F 16/35 (2019.01); G06F 40/216 (2020.01); G06F 40/279 (2020.01); G06N 5/041 (2013.01); G06Q 50/01 (2013.01)] | 20 Claims |
|
1. A method comprising:
automatically, using a computing device:
retrieving a document corpus comprising problem reports of a network-based service;
using a topic model to generate, from the document corpus, respective sets of topic terms describing predicted topics for each of a plurality of sentences from the document corpus;
grouping the plurality of sentences of the document corpus into one or more context groups based upon similarities of topics within each respective set of topic terms for each of the plurality of sentences;
for a first context group of the one or more context groups, identify a second set of topic terms, the second set of second topic terms including the set of topic terms for each of the plurality of sentences in the first context group and a plurality of similar terms;
ordering the second set of topic terms of the first context group based upon a frequency of occurrence in the document corpus or in a second document corpus;
generating, at least one topic sentence, by processing the second set of topic terms for the first context group by using the second set of topic terms and corresponding most-probable next or most-probable previous words of the second set of topic terms for the first context group, the most-probable next or most-probable previous words determined from the document corpus or the second document corpus;
comparing the at least one topic sentence to one or more predefined topic sentences that indicate a problem with the network-based service; and
based upon the comparison of the at least one topic sentence to the one or more predefined topic sentences, performing at least one automated action on a computing device corresponding to the network-based service to fix the problem.
|