US 11,727,020 B2
Artificial intelligence based problem descriptions
Muhammed Fatih Bulut, New York, NY (US); Hongtan Sun, Armonk, NY (US); Pritpal Arora, Bangalore (IN); Klaus Koenig, Essenheim (DE); Naga A. Ayachitula, Elmsford, NY (US); Jonathan Richard Young, Guildford (GB); and Maja Vukovic, New York, NY (US)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Oct. 11, 2018, as Appl. No. 16/157,740.
Prior Publication US 2020/0117739 A1, Apr. 16, 2020
Int. Cl. G06N 3/08 (2023.01); G06N 3/042 (2023.01); G06Q 30/016 (2023.01); G06F 16/2458 (2019.01); G06N 3/044 (2023.01)
CPC G06F 16/2465 (2019.01) [G06N 3/042 (2023.01); G06N 3/044 (2023.01); G06N 3/08 (2013.01); G06Q 30/016 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A system, comprising:
a memory that stores computer-executable components;
a processor, operably coupled to the memory, and that executes the compute r-executable components stored in the memory, wherein the computer-executable components comprise:
a query component that generates key performance indicators and maturity scores from a query, wherein a maturity score is an indicator of a position in time that a problem related to a key performance indicator occurs such that a low maturity score is indicative of the problem occurring prior to and having increased urgency than a second problem in time, and wherein the query component determines a subset of key performance indicators that individually have a performance below a threshold and maps the subset of key performance indicators to operational metrics;
a learning component that generates, using artificial intelligence, problem descriptions from one or more of the subset of key performance indicators or the operational metrics by computing a correlation between the subset of key performance indicators and the operational metrics and transmits the problem descriptions to a first database, wherein the problem descriptions comprise identification of risks based on prediction of outages or failures in at least an electronic device; and
a content component that retrieves the problem descriptions from the first database, searches a second database for a recommendation based on the problem descriptions, and provides the recommendation for an entity;
wherein the query component further generates a context description from the key performance indicators and the learning component uses the context description to train the artificial intelligence.