Data prediction and proactive request system using artificial intelligence
Assignee7-Eleven, Inc.
InventorNicholas E. Evangelopoulos
Life of this patent
Estimating the term…
Abstract
A data prediction subsystem receives event data indicating an amount of an item removed from each of a plurality of locations over a previous period of time. For each location, prediction data is determined using the event data. The prediction data includes, for each day over a future period of time, a non-integer value indicating an anticipated amount of the item that will be removed from the location. An improved rounding process is used to round the prediction value for each day. The resulting prediction data is used to proactively request items with improved communication and computational efficiency.
Claims20
A system, comprising:
- a data prediction subsystem comprising:
- a memory operable to store instructions for implementing a process for rounding with cumulative error redistribution;
- and
- a first processor communicatively coupled to the memory, the processor configured to:
- receive event data indicating an amount of an item removed from each of a plurality of locations over a previous period of time;
- determine, for each location of the plurality of locations, prediction data using the event data, wherein the prediction data comprises, for each day over a future period of time, a non-integer value indicating an anticipated amount of the item that will be removed from the location;
- and
- decrease rounding error by executing the process for rounding with cumulative error redistribution to determine, for each day of the future period of time, an integer value based at least in part on the non-integer value of the prediction data for the day and a cumulative error value for a previous day that is one day before the day, thereby determining rounded prediction data with decreased rounding error than if the integer value for each day was determined by rounding the non-integer value for the day to a nearest integer value;
- and
- an item request device associated with a location of the plurality of locations, the item request device comprising a second processor configured to:
- receive at least a portion of the rounded prediction data associated with the location of the item request device;
- display a recommendation based on the received portion of the rounded prediction data;
- receive an input associated with the displayed recommendation;
- and
- communicate a request for a number of items based on the received input.
A method, comprising:
- storing, in a memory, instructions for implementing a process for rounding with cumulative error redistribution;
- receiving event data indicating an amount of an item removed from each of a plurality of locations over a previous period of time;
- determining, for each location of the plurality of locations, prediction data using the event data, wherein the prediction data comprises, for each day over a future period of time, a non-integer value indicating an anticipated amount of the item that will be removed from the location;
- decreasing rounding error by executing the process for rounding with cumulative error redistribution to determine, for each day of the future period of time, an integer value based at least in part on the non-integer value of the prediction data for the day and a cumulative error value for a previous day that is one day before the day, thereby determining rounded prediction data with decreased rounding error than if the integer value for each day was determined by rounding the non-integer value for the day to a nearest integer value;
- displaying a recommendation based on at least a portion of the rounded prediction data;
- receiving an input associated with the displayed recommendation;
- and
- communicating a request for a number of items based on the received input.
A data prediction subsystem comprising:
- a memory operable to store instructions for implementing a process for rounding with cumulative error redistribution;
- and
- a processor communicatively coupled to the memory, the processor configured to:
- receive event data indicating an amount of an item removed from each of a plurality of locations over a previous period of time;
- determine, for each location of the plurality of locations, prediction data using the event data, wherein the prediction data comprises, for each day over a future period of time, a non-integer value indicating an anticipated amount of the item that will be removed from the location;
- and
- decrease rounding error by executing the process for rounding with cumulative error redistribution to determine, for each day of the future period of time, an integer value based at least in part on the non-integer value of the prediction data for the day and a cumulative error value for a previous day that is one day before the day, thereby determining rounded prediction data with decreased rounding error than if the integer value for each day was determined by rounding the non-integer value for the day to a nearest integer value.
Dependencies are inferred from the claim text.