Docket search and analytics engine

Abstract

The present invention provides an improved docket search and analytics engine for determining the outcome of a case for a particular entity or party, for predicting the outcome of a case for a particular entity or party, or for predicting the time to resolution of a case for a particular entity or party. More specifically, the present invention provides a system and engine for accessing and retrieving docket and other data from a plurality of databases and applying by one or more engines a set of models to the retrieved data to make a determination or prediction as to the outcome of a case for an entity or party involved in the case.

1 . A computer-implemented system for detecting an outcome of a legal case, the system comprising:
 a computing device having a processor in electrical communication with a memory, the memory adapted to store data and instructions for executing by the processor;   a outcome detection engine operating on the computing device and comprising:
 a data access module adapted to access a first set of docket entry data stored in either the memory or a database, the first set of docket entry data including a set of docket entries and a corresponding set of identified dispositive outcomes in a legal case or an issue disposed of in a legal case; 
 a sequence tagging classifier; and 
 at least one machine sequence learning module adapted to receive the first set of docket entry data and, based on the received first set of docket entry data, train the sequence tagging classifier; 
 wherein upon training the sequence tagging classifier is configured to be executed by the processor against a second set of docket entry data, the second set of docket entry data being associated with at least one subject docket other than the at least one existing docket, the second set of docket entry data having an associated set of parties, the trained sequence tagging classifier adapted to process docket entries from the second set of docket entry data associated with each party in the set of parties to determine a dispositive outcome attribute associated with at least one party from the set of parties; and 
   an output adapted to transmit a signal related to the determined dispositive outcome attribute associated with the at least one party.   
     
     
         2 . The system of  claim 1 , wherein the at least one machine sequence learning module is adapted to train the sequence tagging classifier using at least one of a Hidden Markov Model (HMM) and a Conditional Random Field (CRF) model. 
     
     
         3 . The system of  claim 2 , wherein the at least one machine sequence learning module receives and uses annotated data for training the at least one of a Hidden Markov Model (HMM) and a Conditional Random Field (CRF) model to detect a dispositive outcome associated with a docket entry. 
     
     
         4 . The system of  claim 3 , wherein the machine sequence learning module is adapted to derive a set of features are derived from n-grams of text from the first set of docket entry data. 
     
     
         5 . The system of  claim 1 , wherein the Outcome Detection Engine is adapted to determine a dispositive outcome attribute associated with at least one party from the set of parties. 
     
     
         6 . The system of  claim 1 , wherein the trained sequence tagging classifier is adapted to process docket entries from the second set of docket entry data associated with each party in the set of parties using the “room model” to determine dispositive outcome attributes. 
     
     
         7 . The system of  claim 1 , wherein the Outcome Detection Engine is adapted to rapidly process large amounts of docket data via an Apache SPARK implementation. 
     
     
         8 . The system of  claim 1 , wherein the Outcome Detection Engine is further adapted to apply a conditional random field (CRF) to implement the sequence tagging classifier. 
     
     
         9 . The system of  claim 1 , wherein the sequence tagging classifier comprises one or more of the following components: a masker, featurization, classification, and interparty inference. 
     
     
         10 . The system of  claim 1 , wherein the first set of docket entry data includes a set of docket entries for each party for which the docket entries represent a dispositive outcome in a legal case or an issue disposed of in a legal case. 
     
     
         11 . The system of  claim 1 , wherein the docket entries of the first set of docket entries are annotated. 
     
     
         12 . The system of  claim 1 , wherein the sequence tagging classifier is further adapted to determine whether any party from the set of parties has been removed, terminated, withdrawn, or otherwise the subject of a dispositive action in the legal case or an issue resolved in the legal case and generate a signal representative of the nature of the dispositive outcome. 
     
     
         13 . The system of  claim 1  further comprising a docket resolution time detection module adapted to determine, based on data from the first set of docket entry data, time parameters representing the amount of time from a docket open data or a party.