EXTRACTING, DERIVING, AND USING LEGAL MATTER SEMANTICS TO GENERATE E-DISCOVERY QUERIES IN AN E-DISCOVERY SYSTEM
First Claim
1. A computer-implemented method for generating e-discovery queries for an e-discovery system comprising:
- iteratively building a semantic knowledge graph during a build phase by,receiving meet and confer document instances, legal matter types, historical e-discovery queries for different legal matters, and legal semantic types extracted from the historical e-discovery queries;
adding the legal semantic types to the semantic knowledge graph;
in response to adding the legal semantic types to the semantic knowledge graph,identifying a list of terms that serve as a basis of an initial query; and
generating an e-discovery query for an e-discovery system by;
1) mapping a predicate clause of the initial query to a legal semantic type by;
identifying a metadata field and operator combination;
determining the legal semantic type from a glossary;
adding a first semantic type node to the semantic knowledge graph;
connecting the first semantic type node to a legal matter node with an edge weight; and
adding an expression term node for the metadata field with another edge weight; and
2) mapping a keyword of a text clause of the initial query to a legal semantic type by;
running a partial query for the keyword against a saved result set to generate a new result set; and
for each document in the new result set,retrieving surrounding text around a location within the document where the keyword was found;
applying Named Entity Recognition (NER) to the keyword using surrounding text as context;
adding a second semantic type node for an entity type node;
connecting the second semantic type node to the legal matter node with an edge weight; and
adding an expression term node for the keyword with another edge weight; and
modifying the e-discovery query using the semantic knowledge graph and additional input during a query generation phase by;
receiving a legal matter type and meet and confer information;
issuing a series of questions to obtain the legal semantic types that are relevant to the legal matter type and the meet and confer information, wherein a priority of an order of questions is determined by weight associated with occurrence of those legal semantic types in the semantic knowledge graph;
modifying the e-discovery query based on the obtained legal semantic types to add one or more predicates that capture historical information based on user feedback responding to the series of questions;
providing the modified e-discovery query as a suggested query; and
in response to receiving selection of the modified e-discovery query, executing the modified e-discovery query.
1 Assignment
0 Petitions
Accused Products
Abstract
Provided are techniques for extracting, deriving, and using legal matter semantics to generate e-discovery queries in an e-discovery system. A semantic knowledge graph is iteratively built by receiving meet and confer document instances, legal matter types, historical e-discovery queries for different legal matters, and legal semantic types extracted from the historical e-discovery queries. The legal semantic types are added to the semantic knowledge graph, and a list of terms that serve as a basis of an initial query are identified. An e-discovery query is generated for an e-discovery system. The e-discovery query is modified using the semantic knowledge graph and additional input by receiving a legal matter type and meet and confer information, obtaining the legal semantic types that are relevant to the legal matter type and the meet and confer information, and modifying the e-discovery query. The modified e-discovery query is provided. Then, the modified e-discovery query is executed.
-
Citations
18 Claims
-
1. A computer-implemented method for generating e-discovery queries for an e-discovery system comprising:
-
iteratively building a semantic knowledge graph during a build phase by, receiving meet and confer document instances, legal matter types, historical e-discovery queries for different legal matters, and legal semantic types extracted from the historical e-discovery queries; adding the legal semantic types to the semantic knowledge graph; in response to adding the legal semantic types to the semantic knowledge graph, identifying a list of terms that serve as a basis of an initial query; and generating an e-discovery query for an e-discovery system by; 1) mapping a predicate clause of the initial query to a legal semantic type by; identifying a metadata field and operator combination; determining the legal semantic type from a glossary; adding a first semantic type node to the semantic knowledge graph; connecting the first semantic type node to a legal matter node with an edge weight; and adding an expression term node for the metadata field with another edge weight; and 2) mapping a keyword of a text clause of the initial query to a legal semantic type by; running a partial query for the keyword against a saved result set to generate a new result set; and for each document in the new result set, retrieving surrounding text around a location within the document where the keyword was found; applying Named Entity Recognition (NER) to the keyword using surrounding text as context; adding a second semantic type node for an entity type node; connecting the second semantic type node to the legal matter node with an edge weight; and adding an expression term node for the keyword with another edge weight; and modifying the e-discovery query using the semantic knowledge graph and additional input during a query generation phase by; receiving a legal matter type and meet and confer information; issuing a series of questions to obtain the legal semantic types that are relevant to the legal matter type and the meet and confer information, wherein a priority of an order of questions is determined by weight associated with occurrence of those legal semantic types in the semantic knowledge graph; modifying the e-discovery query based on the obtained legal semantic types to add one or more predicates that capture historical information based on user feedback responding to the series of questions; providing the modified e-discovery query as a suggested query; and in response to receiving selection of the modified e-discovery query, executing the modified e-discovery query. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A computer program product for generating e-discovery queries for an e-discovery system, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by at least one processor to perform:
-
iteratively building a semantic knowledge graph during a build phase by, receiving meet and confer document instances, legal matter types, historical e-discovery queries for different legal matters, and legal semantic types extracted from the historical e-discovery queries; adding the legal semantic types to the semantic knowledge graph; in response to adding the legal semantic types to the semantic knowledge graph, identifying a list of terms that serve as a basis of an initial query; and generating an e-discovery query to for e-discovery system by; 1) mapping a predicate clause of the initial query to a legal semantic type by; identifying a metadata field and operator combination; determining the legal semantic type from a glossary; adding a first semantic type node to the semantic knowledge graph; connecting the first semantic type node to a legal matter node with an edge weight; and adding an expression term node for the metadata field with another edge weight; and 2) mapping a keyword of a text clause of the initial query to a legal semantic type by; running a partial query for the keyword against a saved result set to generate a new result set; and for each document in the new result set, retrieving surrounding text around a location within the document where the keyword was found; applying Named Entity Recognition (NER) to the keyword using the surrounding text as context; adding a second semantic type node for an entity type node; connecting the second semantic type node to the legal matter node with an edge weight; and adding an expression term node for the keyword with another edge weight; and modifying the e-discovery query using the semantic knowledge graph and additional input during a query generation phase by; receiving a legal matter type and meet and confer information; issuing a series of questions to obtain the legal semantic types that are relevant to the legal matter type and the meet and confer information, wherein a priority of an order of questions is determined by weight associated with occurrence of those legal semantic types in the semantic knowledge graph; modifying the e-discovery query based on the obtained legal semantic types to add one or more predicates that capture historical information based on user feedback responding to the series of questions; providing the modified e-discovery query as a suggested query; and in response to receiving selection of the modified e-discovery query, executing the modified e-discovery query. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A computer system for generating e-discovery queries for an e-discovery system, comprising:
-
one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to perform operations comprising; iteratively building a semantic knowledge graph during a build phase by, receiving meet and confer document instances, legal matter types, historical e-discovery queries for different legal matters, and legal semantic types extracted from the historical e-discovery queries; adding the legal semantic types to the semantic knowledge graph; in response to adding the legal semantic types to the semantic knowledge graph, identifying a list of terms that serve as a basis of an initial query; and generating an e-discovery query to for e-discovery system by; 1) mapping a predicate clause of the initial query to a legal semantic type by; identifying a metadata field and operator combination; determining the legal semantic type from a glossary; adding a first semantic type node to the semantic knowledge graph; connecting the first semantic type node to a legal matter node with an edge weight; and adding an expression term node for the metadata field with another edge weight; and 2) mapping a keyword of a text clause of the initial query to a legal semantic type by; running a partial query for the keyword against a saved result set to generate a new result set; and for each document in the new result set, retrieving surrounding text around a location within the document where the keyword was found; applying Named Entity Recognition (NER) to the keyword using surrounding text as context; adding a second semantic type node for an entity type node; connecting the second semantic type node to the legal matter node with an edge weight; and adding an expression term node for the keyword with another edge weight; and modifying the e-discovery query using the semantic knowledge graph and additional input during a query generation phase by; receiving a legal matter type and meet and confer information; issuing a series of questions to obtain the legal semantic types that are relevant to the legal matter type and the meet and confer information, wherein a priority of an order of questions is determined by weight associated with occurrence of those legal semantic types in the semantic knowledge graph; modifying the e-discovery query based on the obtained legal semantic types to add one or more predicates that capture historical information based on user feedback responding to the series of questions; providing the modified e-discovery query as a suggested query; and in response to receiving selection of the modified e-discovery query, executing the modified e-discovery query. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification