US 12,456,014 B2
Intelligent keyword recommender
Neha Garg, Bangalore (IN); Sudhir Verma, Gurgaon (IN); Shilpa Viswanadha, Gurgaon (IN); Ayushi Singla, Jagadhri (IN); and Sven Herzberg, Sandhausen (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Jul. 20, 2021, as Appl. No. 17/380,934.
Prior Publication US 2023/0024135 A1, Jan. 26, 2023
Int. Cl. G06F 40/00 (2020.01); G06F 9/50 (2006.01); G06F 16/31 (2019.01); G06F 16/35 (2019.01); G06F 18/214 (2023.01); G06F 40/289 (2020.01)
CPC G06F 40/289 (2020.01) [G06F 9/5077 (2013.01); G06F 16/313 (2019.01); G06F 16/35 (2019.01); G06F 18/214 (2023.01); G06F 2209/505 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, by at least one processor, a training dataset for training, using a machine learning engine, a machine learning model,
wherein the training dataset includes a plurality of variables associated with one or more values,
wherein the plurality of variables includes one or more first variables indicative of one or more problems, one or more second variables indicative of one or more computing solutions to the one or more problems, one or more third variables indicative of user feedback entered by a user of a computing component regarding whether a corresponding solution worked to resolve a corresponding problem, one or more fourth variables indicative of one or more computing components, and one or more fifth variables identifying one or more keywords used to search for corresponding computing solution to a corresponding problem,
wherein the machine learning model is configured for determination, as a function of one or more variables in the plurality of variables, of the one or more keywords in a plurality of keywords associated with a computing solution in a plurality of computing solutions for resolving a problem with an operation of the computing component in a plurality of computing components;
training, using the machine learning engine and by the at least one processor, the machine learning model using the received training dataset including the plurality of variables, wherein the plurality of variables comprises the one or more first variables, the one or more second variables, the one or more third variables, the one or more fourth variables, and the one or more fifth variables, wherein the machine learning model is trained, using the received training dataset, to enable generation of the one or more keywords;
applying, by the at least one processor, the trained machine learning model to one or more variables to generate the one or more keywords associated with the computing solution;
updating the one or more generated keywords by repeating the receiving, the training, the applying, and the generating using an updated training dataset;
searching, using the one or more generated keywords, for the computing solution for resolving the problem with the operation of the computing component in the plurality of computing components, wherein the searching is executed using one or more views; and
retrieving, by the searching using the one or more generated keywords, the computing solution that directly solves the problem generated by the computing component without additional steps.
 
9. A system comprising:
at least one processor; and
at least one non-transitory machine-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, by at least one processor, a training dataset for training, using a machine learning engine, a machine learning model,
wherein the training dataset includes a plurality of variables associated with one or more values,
wherein the plurality of variables includes one or more first variables indicative of one or more problems, one or more second variables indicative of one or more computing solutions to the one or more problems, one or more third variables indicative of user feedback entered by a user of a computing component regarding whether a corresponding solution worked to resolve a corresponding problem, one or more fourth variables indicative of one or more computing components, and one or more fifth variables identifying one or more keywords used to search for corresponding computing solution to a corresponding problem,
wherein the machine learning model is configured for determination, as a function of one or more variables in the plurality of variables, of the one or more keywords in a plurality of keywords associated with a computing solution in a plurality of computing solutions for resolving a problem with an operation of the computing component in a plurality of computing components;
training, using the machine learning engine and by the at least one processor, the machine learning model using the received training dataset including the plurality of variables, wherein the plurality of variables comprises the one or more first variables, the one or more second variables, the one or more third variables, the one or more fourth variables, and the one or more fifth variables, wherein the machine learning model is trained, using the received training dataset, to enable generation of the one or more keywords;
applying, by the at least one processor, the trained machine learning model to one or more variables to generate the one or more keywords associated with the computing solution;
updating the one or more generated keywords by repeating the receiving, the training, the applying, and the generating using an updated training dataset;
searching, using the one or more generated keywords, for the computing solution for resolving the problem with the operation of the computing component in the plurality of computing components, wherein the searching is executed using one or more views, and
retrieving, by the searching using the one or more generated keywords, the computing solution that directly solves the problem generated by the computing component without additional steps.