Vector generation for distributed data sets
First Claim
Patent Images
1. A method, comprising:
- accessing, by a server, a set of data configured in a first format, the set of data being stored on a first client device and a second client device;
generating an integrated vector parameter for an integrated vector template based on the set of data stored on the first client device and the second client device;
generating the set of data in a second format, the second format having one or more first vectors including one or more vector values converted from the one or more data entries in the set of data stored on the first client device, the one or more first vectors based on the integrated vector template and generated at the first client device responsive to a conversion instruction sent by the server, and generating one or more second vectors including one or more vector values converted from the data entries stored on the second client device, the one or more second vectors based on the integrated vector template and generated at the second client device responsive to the conversion instruction sent by the server, the set of data generated in the second format by generating one or more integrated vectors based on the integrated vector template and at least one of the one or more first vectors and one or more second vectors, identifying a predetermined number of elements within the integrated vector, and inserting one or more null indicators into the integrated vector;
mapping, by the server, each data entry to a vector value to generate a conversion map, the conversion map assisting in transforming data entries, from the first or second client devices, to vector values that have a format compatible for processing by at least one machine learning algorithm;
storing the conversion map at a database accessible by the server, the conversion map indicating a mapping of data entries to vector values, and accessible to retrieve one or more mappings of data entries to vector values to generate one or more subsequent vectors from an additional set of data;
using the stored conversion map to generate at least one subsequent vector; and
processing the at least one subsequent vector using the at least one machine learning algorithm.
8 Assignments
0 Petitions
Accused Products
Abstract
In various example embodiments, a vector modeling system is configured to access a set of data distributed across client devices and stored in a structured format. The vector modeling system determines vector parameters and vector templates suitable for the set of data and transforms the set of data from the structured format into a second format including one or more vectors based on one or more transformation strategies. The vector modeling system stores the transformed data and performs machine learning analysis on the vector.
172 Citations
18 Claims
-
1. A method, comprising:
-
accessing, by a server, a set of data configured in a first format, the set of data being stored on a first client device and a second client device; generating an integrated vector parameter for an integrated vector template based on the set of data stored on the first client device and the second client device; generating the set of data in a second format, the second format having one or more first vectors including one or more vector values converted from the one or more data entries in the set of data stored on the first client device, the one or more first vectors based on the integrated vector template and generated at the first client device responsive to a conversion instruction sent by the server, and generating one or more second vectors including one or more vector values converted from the data entries stored on the second client device, the one or more second vectors based on the integrated vector template and generated at the second client device responsive to the conversion instruction sent by the server, the set of data generated in the second format by generating one or more integrated vectors based on the integrated vector template and at least one of the one or more first vectors and one or more second vectors, identifying a predetermined number of elements within the integrated vector, and inserting one or more null indicators into the integrated vector; mapping, by the server, each data entry to a vector value to generate a conversion map, the conversion map assisting in transforming data entries, from the first or second client devices, to vector values that have a format compatible for processing by at least one machine learning algorithm; storing the conversion map at a database accessible by the server, the conversion map indicating a mapping of data entries to vector values, and accessible to retrieve one or more mappings of data entries to vector values to generate one or more subsequent vectors from an additional set of data; using the stored conversion map to generate at least one subsequent vector; and processing the at least one subsequent vector using the at least one machine learning algorithm. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer implemented system, comprising:
-
one or more processors; a non-transitory machine-readable storage medium including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising; accessing, by a server, a set of data configured in a first format, the set of data being stored on a first client device and a second client device; generating an integrated vector parameter for an integrated vector template based on the set of data stored on the first client device and the second client device; generating the set of data in a second format, the second format having one or more first vectors including one or more vector values converted from the one or more data entries in the set of data stored on the first client device, the one or more first vectors based on the integrated vector template and generated at the first client device responsive to a conversion instruction sent by the server, and generating one or more second vectors including one or more vector values converted from the data entries stored on the second client device, the one or more second vectors based on the integrated vector template and generated at the second client device responsive to the conversion instruction sent by the server, the set of data generated in the second format by generating one or more integrated vectors based on the integrated vector template and at least one of the one or more first vectors and one or more second vectors, identifying a predetermined number of elements within the integrated vector, and inserting one or more null indicators into the integrated vector; generating one or more second vectors including vector values converted from the data entries stored on the second client device, the one or more second vectors based on the integrated vector template; mapping, by the server, each data entry to a vector value to generate a conversion map, the conversion map assisting in transforming data entries, from the first or second client devices, to vector values that have a format compatible for processing by at least one machine learning algorithm; storing the conversion map at a database accessible by the server, the conversion map indicating a mapping of vector values to data entries and accessible to retrieve one or more mappings of vector values and data entries to generate one or more subsequent vectors from an additional set of data; using the stored conversion map to generate at least one subsequent vector; and processing the at least one subsequent vector using the at least one machine learning algorithm. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory machine-readable storage medium including instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
-
accessing, by a server, a set of data configured in a first format, the set of data being stored on a first client device and a second client device; generating an integrated vector parameter for an integrated vector template based on the set of data stored on the first client device and the second client device; generating the set of data in a second format, the second format having one or more first vectors including one or more vector values converted from the one or more data entries in the set of data stored on the first client device, the one or more first vectors based on the integrated vector template and generated at the first client device responsive to a conversion instruction sent by the server, and generating one or more second vectors including one or more vector values converted from the data entries stored on the second client device, the one or more second vectors based on the integrated vector template and generated at the second client device responsive to the conversion instruction sent by the server, the set of data generated in the second format by generating one or more integrated vectors based on the integrated vector template and at least one of the one or more first vectors and one or more second vectors, identifying a predetermined number of elements within the integrated vector, and inserting one or more null indicators into the integrated vector; generating one or more second vectors including vector values converted from the data entries stored on the second client device, the one or more second vectors based on the integrated vector template; mapping, by the server, each data entry to a vector value to generate a conversion map, the conversion map assisting in transforming data entries, from the first or second client devices, to vector values that have a format compatible for processing by at least one machine learning algorithm; storing the conversion map at a database accessible by the server, the conversion map indicating a mapping of vector values to data entries and accessible to retrieve one or more mappings of vector values and data entries to generate one or more subsequent vectors from an additional set of data; using the stored conversion map to generate at least one subsequent vector; and processing the at least one subsequent vector using the at least one machine learning algorithm. - View Dependent Claims (16, 17, 18)
-
Specification