Updating a document based on transaction analysis

Abstract

A platform receives transaction information for an entity, where the transaction information identifies a plurality of transactions associated with the entity, and receives entity information associated with the entity. The platform identifies, using a first model, a selected set of transactions based on the transaction information and the entity information, where the first model outputs information identifying the selected set of transactions based on the selected set of transactions being associated with an event, a theme, or a transaction parameter. The platform determines, using a second model, potential modifications to a document based on the selected set of transactions, where the second model receives the information identifying the selected set of transactions or information identifying the event, the theme, or the transaction parameter, and where the second model outputs information identifying the potential modifications. The platform provides the information identifying the potential modifications.

What is claimed is: 
     
         1 . A method, comprising:
 accessing, by a computing device, a first model trained on transaction information associated with at least one of events or themes;   identifying, by the computing device and using the first model, one or more user transactions that are associated with one or more of the events or themes,
 wherein the first model receives, as input, user transaction information, and 
 wherein the first model outputs information identifying the one or more user transactions based on the user transaction information; 
   determining, by the computing device and using a second model, one or more potential modifications to a document based on the one or more user transactions and the one or more events or themes; and   providing to a user, by the computing device and via a network, information identifying the one or more potential modifications.   
     
     
         2 . The method of  claim 1 , further comprising:
 performing a preprocessing operation when generating the first model by preprocessing the transaction information to remove one or more of:   health information, or   information for which an entity has not provided permission or access.   
     
     
         3 . The method of  claim 1 , wherein determining the one or more potential modifications to the document comprises:
 determining the one or more potential modifications based on a pattern of related transactions.   
     
     
         4 . The method of  claim 1 , wherein the one or more of the themes are associated with one of:
 a charitable organization,   legal services, or   education.   
     
     
         5 . The method of  claim 1 , wherein another potential modification, of the one or more potential modifications, relates to adding, removing, or modifying a charitable endowment. 
     
     
         6 . The method of  claim 1 , wherein the computing device is part of a cloud computing environment. 
     
     
         7 . The method of  claim 1 , further comprising:
 performing another potential modification of the one or more potential modifications based on receiving an input regarding the other potential modification.   
     
     
         8 . A device, comprising:
 one or more memories; and   one or more processors, coupled to the one or more memories, configured to:   access a first model trained on transaction information associated with at least one of events, themes, or transaction parameters;   identify, using the first model, one or more user transactions that are associated with one or more of the events, themes, or transaction parameters,
 wherein the first model receives, as input, user transaction information, and 
 wherein the first model outputs information identifying the one or more user transactions based on the user transaction information; 
   determine, using a second model, one or more potential modifications to a document based on the one or more user transactions and the one or more events, themes, or transaction parameters; and   provide, via a network, information identifying the one or more potential modifications.   
     
     
         9 . The device of  claim 8 , wherein the one or more processors are further configured to:
 update the second model based on determining a result associated with the one or more potential modifications.   
     
     
         10 . The device of  claim 8 , wherein the second model outputs information identifying the one or more potential modifications. 
     
     
         11 . The device of  claim 8 , wherein the one or more transaction parameters are associated with one of:
 a size of the transaction,   a dollar amount associated with the transaction,   a counterparty of the transaction, or   a location associated with the transaction.   
     
     
         12 . The device of  claim 8 , wherein the one or more events are associated with one of:
 a vehicle purchase,   a change in circumstance,   a marriage,   a charitable donation,   a pattern of transactions that suggest a charitable donation, or   a move from one jurisdiction to another.   
     
     
         13 . The device of  claim 8 , wherein the one or more processors, when determining the one or more potential modifications to the document, are configured to:
 determine the one or more potential modifications based on a pattern of related transactions.   
     
     
         14 . The device of  claim 8 , wherein the one or more processors are further configured to:
 receive the transaction information from multiple sources as a data stream.   
     
     
         15 . A non-transitory computer-readable medium storing instructions, the instructions comprising:
 one or more instructions that, when executed by one or more processors, cause the one or more processors to:
 access a first model trained on transaction information associated with at least one of events or themes; 
 identify, using the first model, one or more user transactions that are associated with one or more of the events or themes,
 wherein the first model receives, as input, user transaction information, and 
 wherein the first model outputs information identifying the one or more user transactions based on the user transaction information; 
 
 determine, using a second model, one or more potential modifications to a document based on the one or more user transactions and the one or more events or themes; and 
 provide information identifying the one or more potential modifications. 
   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to:
 perform a preprocessing operation when generating the first model.   
     
     
         17 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, that cause the one or more processors to determine the one or more potential modifications to the document, cause the one or more processors to:
 determine the one or more potential modifications based on a pattern of related transactions.   
     
     
         18 . The non-transitory computer-readable medium of  claim 15 , wherein another potential modification, of the one or more potential modifications, relates to modifying a charitable endowment. 
     
     
         19 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to:
 perform a preprocessing operation when generating the first model by preprocessing the transaction information to remove confidential information.   
     
     
         20 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to:
 perform another potential modification of the one or more potential modifications based on receiving an input regarding the other potential modification.