US 12,327,256 B2
Technical support service location recommendation using machine learning
Bijan Kumar Mohanty, Austin, TX (US); Kulin Shaival Chokshi, Round Rock, TX (US); Shijin Babu, Round Rock, TX (US); and David J. Linsey, Marietta, GA (US)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Sep. 16, 2022, as Appl. No. 17/946,223.
Prior Publication US 2024/0095750 A1, Mar. 21, 2024
Int. Cl. G06Q 30/00 (2023.01); G06Q 10/20 (2023.01); G06Q 30/016 (2023.01)
CPC G06Q 30/016 (2013.01) [G06Q 10/20 (2013.01)] 20 Claims
OG exemplary drawing
 
14. An apparatus comprising:
a processing platform comprising at least one processing device operatively coupled to a memory, said at least one processing device being configured:
to receive work order data in a work order management engine of the processing platform comprising the at least one processing device operatively coupled to the memory, wherein the work order data identifies at least one technical support issue requiring resolution, and is received in the work order management engine from a user device over a network, the processing platform further comprising a customer relationship management (CRM) system;
to maintain, via the CRM system of the processing platform, at least one set of historical work order data;
to analyze, in a machine learning system implemented in the processing platform by the at least one processing device operatively coupled to the memory, the work order data using one or more machine learning algorithms;
to predict, by at least one of the one or more machine learning algorithms in the machine learning system and based at least in part on the analyzing, whether the at least one technical support issue will be resolved at one or more respective service locations of a plurality of service locations, the at least one of the one or more machine learning algorithms comprising a plurality of distinct tree-based classifiers, arranged in parallel with one another, each processing respective distinct sets of features derived from the work order data to generate a corresponding separate prediction as to whether the at least one technical support issue will be resolved at the one or more respective service locations of the plurality of service locations, each of the distinct tree-based classifiers yielding one of a positive result and a negative result with respect to whether the at least one technical support issue will be resolved at the one or more respective service locations of the plurality of service locations, wherein different ones of the distinct tree-based classifiers are trained using respective different portions of the set of historical work order data maintained by the CRM system, the different portions of the set of historical work order data corresponding to the respective distinct sets of features;
to generate, in the processing platform and based at least in part on the predicting by the at least one of the one or more machine learning algorithms, a recommendation to respond to the at least one technical support issue at a given service location of the plurality of service locations;
to generate, in the processing platform, an order to respond to the at least one technical support issue at the given service location;
to automatically execute a dispatch process in the CRM system of the processing platform to execute a repair at the given service location in accordance with the generated order, wherein in conjunction with executing the dispatch process the CRM system automatically performs one or more dispatch support operations relating to the given service location; and
to automatically execute one or more data migrations from a device corresponding to the at least one technical support issue to at least one of a replacement device and a designated storage location in response to generating the order.