Machine learning for management of positioning techniques and radio frequency usage
AssigneeCisco Technology, Inc.
InventorsGino M. Corleto, Robert E. Barton, Jerome Henry, Malcolm M. Smith
Life of this patent
Estimating the term…
Abstract
Techniques for improved networking are provided. An indication that a mobile device is in a first region of a physical space is received, and one or more current exogenous factors are determined for the physical space. Positioning technique accuracy is predicted for each respective positioning technique of a plurality of positioning techniques by processing the indication of the first region and the one or more current exogenous factors using a machine learning model. A first positioning technique of the plurality of positioning techniques is selected based on the predicted positioning technique accuracies.
Claims20
A method, comprising:
- receiving location information comprising a plurality of location estimations generated using a plurality of positioning techniques for a first region of a physical space and a plurality ground truth locations corresponding to the plurality of location estimations;
- identifying, for the first region, a most accurate position technique of the plurality of positioning techniques based on the plurality of location estimations and the plurality of ground truth locations;
- determining a time period when the plurality of location estimations were collected;
- determining exogenous data for the physical space during the determined time period;
- and
- training a machine learning model, based on the location information, the most accurate position technique, and the exogenous data, to predict positioning technique accuracy, comprising processing the exogenous data and at least a subset of the location information as input to the machine learning model.
A non-transitory computer-readable medium containing computer program code that, when executed by one or more computer processors, performs an operation comprising:
- receiving location information comprising a plurality of location estimations generated using a plurality of positioning techniques for a first region of a physical space and a plurality ground truth locations corresponding to the plurality of location estimations;
- identifying, for the first region, a most accurate position technique of the plurality of positioning techniques based on the plurality of location estimations and the plurality of ground truth locations;
- determining a time period when the plurality of location estimations were collected;
- determining exogenous data for the physical space during the determined time period;
- and
- training a machine learning model, based on the location information, the most accurate position technique, and the exogenous data, to predict positioning technique accuracy, comprising processing the exogenous data and at least a subset of the location information as input to the machine learning model.
A system, comprising:
- one or more computer processors;
- and
- a memory containing a program which when executed by the one or more computer processors performs an operation, the operation comprising:
- receiving location information comprising a plurality of location estimations generated using a plurality of positioning techniques for a first region of a physical space and a plurality ground truth locations corresponding to the plurality of location estimations;
- identifying, for the first region, a most accurate position technique of the plurality of positioning techniques based on the plurality of location estimations and the plurality of ground truth locations;
- determining a time period when the plurality of location estimations were collected;
- determining exogenous data for the physical space during the determined time period;
- and
- training a machine learning model, based on the location information, the most accurate position technique, and the exogenous data, to predict positioning technique accuracy, comprising processing the exogenous data and at least a subset of the location information as input to the machine learning model.
Dependencies are inferred from the claim text.