System for determining quantitative measure of dyadic ties

Abstract

Described are platforms, systems, and methods for determining quantifiable measures of dyadic ties. In one aspect, a method comprises receiving contextual data for a user from at least one data source; processing the contextual data through a first machine-learning model to determine quantifiable measures of dyadic ties between the user and each of a plurality of individuals, the first machine-learning model trained with previously received contextual data of a plurality of other users; determining a grouping for the user based on the determined quantifiable measures, the grouping comprising at least one of the individuals; and providing, through a user-interface, access to the determined quantifiable measures to members of the grouping.

What is claimed is: 
     
         1 . A computer-implemented method for determining quantifiable measures of dyadic ties, the method being executed by one or more processors and comprising:
 receiving contextual data for a user from at least one data source;   processing the contextual data through a first machine-learning model to determine quantifiable measures of dyadic ties between the user and each of a plurality of individuals, the first machine-learning model trained with previously received contextual data of a plurality of other users;   determining a grouping for the user based on the determined quantifiable measures, the grouping comprising at least one of the individuals; and   providing, through a user-interface, access to the determined quantifiable measures to members of the grouping.   
     
     
         2 . The method of  claim 1 , wherein the first machine-learning model is retrained with the determined quantifiable measures. 
     
     
         3 . The method of  claim 1 , wherein the quantifiable measures of dyadic ties are determined based on user contact detail quality, a frequency of communication, information within communications, information capacity and bandwidth, physical distance, social network ties, or timeliness of when contact information was updated. 
     
     
         4 . The method of  claim 1 , wherein the first machine-learning model determines the quantifiable measures based on a compounding impact of individual elements from the contextual data. 
     
     
         5 . The method of  claim 1 , wherein the first machine-learning model classifies relationships between the user and each of the individuals according to type, length, and age of the respective parties at a time when the respective relationship began, and wherein the first machine-learning model comprises weighted values for the classifications. 
     
     
         6 . The method of  claim 1 , comprising:
 before processing the contextual data through the first machine-learning model:
 receiving validation data for the user from at least one data enricher; and 
 processing the contextual data and the validation data through a second machine-learning model to determine contact information for the user and the individuals, the second machine-learning model trained with previously received validation data and the previously received contextual data of the other users, 
 wherein the received validation data and the determined contact information is processed through the first machine-learning model to determine the quantifiable measures. 
   
     
     
         7 . The method of  claim 6 , wherein the second machine-learning model merges the processed data to determine and verify current and previous contact information for the user and the individuals and to determine a chorological order of the contact information. 
     
     
         8 . The method of  claim 7 , comprising:
 receiving, from the user-interface, corrections for the determined contact information, wherein the first machine-learning model is retrained with the corrections.   
     
     
         9 . The method of  claim 1 , comprising:
 receiving, from the user-interface, instructions to remove the access to at least one of the determined measures.   
     
     
         10 . The method of  claim 1 , wherein the contextual data is received from at least one source data provider via an application programming interface (API). 
     
     
         11 . The method of  claim 10 , wherein the at least on source data provider comprises a social media provides, an email provider, the user's phone contacts, a messaging provider, a provider of at least one forum, a provider of an auction or selling site, or a provider of a recreational site. 
     
     
         12 . The method of  claim 1 , wherein the contextual data is received on a periodic basis. 
     
     
         13 . The method of  claim 1 , wherein the grouping includes the user. 
     
     
         14 . The method of  claim 1 , comprising:
 providing, to the user-interface, an industry strength scoring for the user determined according to the determined quantifiable measures or a regional strength scoring for the user determined according to the determined quantifiable measures.   
     
     
         15 . The method of  claim 1 , comprising:
 providing, to the user-interface, a best path to a decision maker determined according to the determined quantifiable measures.   
     
     
         16 . The method of  claim 1 , comprising:
 providing, to the user-interface, a validation of a recruiting rolodex determined according to the determined quantifiable measures.   
     
     
         17 . The method of  claim 1 , comprising:
 providing the access to the determined quantifiable measures to a calendar application or an email client accessible by at least one of the members of the grouping or the user.   
     
     
         18 . The method of  claim 1 , wherein the contextual data comprises digital footprint data for the user and digital path data for the user. 
     
     
         19 . A dyadic ties measurement system, comprising:
 a user-interface;   one or more processors; and   a computer-readable storage device coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
 receiving contextual data for a user from at least one data source; 
 processing the contextual data through a first machine-learning model to determine quantifiable measures of dyadic ties between the user and each of a plurality of individuals, the first machine-learning model trained with previously received contextual data of a plurality of other users; 
 determining a grouping for the user based on the determined quantifiable measures, the grouping comprising at least one of the individuals; and 
 providing, through the user-interface, access to the determined quantifiable measures to members of the grouping. 
   
     
     
         20 . One or more non-transitory computer-readable storage media coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
 receiving contextual data for a user from at least one data source;   processing the contextual data through a first machine-learning model to determine quantifiable measures of dyadic ties between the user and each of a plurality of individuals, the first machine-learning model trained with previously received contextual data of a plurality of other users;   determining a grouping for the user based on the determined quantifiable measures, the grouping comprising at least one of the individuals; and   providing, through a user-interface, access to the determined quantifiable measures to members of the grouping.