Adaptive collaborative matching
AssigneeRealm IP, LLC
InventorsJULIE L. FAUPEL, HUNTER ALBRIGHT, EDWARD DOMBROWER
Life of this patent
Estimating the term…
Abstract
An adaptive collaborative platform applies various machine learning techniques to correlate potential purchasers with high-value articles of property that may be of interest. Attributes, characteristics, preferences, and the like of a potential purchaser are scored against attributes and features of articles. The platform learns from interaction by the agents and the potential purchasers and adapts to become more attuned to the desires and lifestyle of purchasers and to gain more and more pertinent information from the listing agents regarding high-value articles, so as to ultimately to arrive at a better match between a high value article for sale and a likely purchaser.
Claims15
A adaptive matching system, the system comprising:
- data comprising first structured empirical data and unstructured data;
- a machine user interface;
- a machine capable of executing instructions embodied as software;
- and
- a plurality of software portions, wherein
- one of said software portions is configured to collect data including the first structured empirical data and unstructured data and convert the unstructured data into second structured empirical data and thereafter modify the first structured empirical data and the second structured empirical data into a predefined format;
- one of said software portions is configured to group the first structured empirical data and the second structured empirical data into a plurality of data fields according to a plurality of factors;
- one of said software portions is configured to store the grouped structured empirical data in a computer data store;
- one of said software portions is configured to create a plurality of tags and store the plurality of tags in the computer data store, each tag of the plurality of tags being a combination of related factors from the plurality of factors and wherein each factor is assigned a factor weight;
- one of said software portions is configured to store a plurality of entities in the computer data store, and, for each entity of the plurality of entities assign a plurality of tags, a tag score, and a tag confidence score for each tag, wherein each assignment is based on a combination of the first structured empirical data and the second structured empirical data, the plurality of factors, and the assigned factor weight of each of the plurality of factors;
- one of said software portions is configured to create and store, in the computer data store, an attribute score for each entity of the plurality of entities, wherein the attribute score is based on a combination of the plurality of tags, a weighted combination of the assigned tag scores, and the assigned tag confidence scores;
- one of said software portions is configured to create a first matching model by iteratively correlating the plurality of entities based on the attribute score, the plurality of tags and the assigned tag scores;
- and
- one of said software portions is configured to list, by the machine user interface, entity correlations based on the first matching model and receive, by the machine user interface, a user feedback score of the first matching model for the entity correlations, and wherein based on the user feedback score of the first matching model form a second matching model.
Dependencies are inferred from the claim text.