SYSTEM AND METHOD FOR ELECTRONIC CHAT PRODUCTION
Systems, methods, and computer program products for adaptively splitting electronic chats are provided. One embodiment includes receiving an electronic chat comprising a set of electronic chat messages, each of the electronic chat messages in the set of electronic chat messages having a timestamp; determining a set of time gaps between the electronic chat messages from the set of electronic chat messages; determining a set of models that model the set of time gaps, selecting an optimum model from the set of models; based on selecting the single Gaussian distribution as the optimum model, determining that the electronic chat comprises a single electronic chat, and storing the set of electronic chat messages as the single electronic chat.
1 . An electronic discovery system, comprising:
a computer processor; and
a non-transitory computer-readable medium storing instructions that, when executed by the computer processor, cause the system to perform operations comprising:
receiving a set of electronic chat messages, each electronic chat message in the set of electronic chat messages having a timestamp;
determining a set of time gaps, each time gap in the set of time gaps representing a time difference between temporally adjacent electronic chat messages in the set of electronic chat messages;
generating a plurality of models based on the set of time gaps, each model being configured to provide a distinct representation of characteristics of the set of time gaps;
selecting one of the models based on selection criteria, the selected one of the models being a splitting model;
splitting the set of electronic chat messages into a plurality of electronic chat conversations in accordance with the splitting model; and
storing the plurality of electronic chat conversations.
2 . The electronic discovery system of claim 1 , wherein the plurality of models comprises one or more distribution models representing a single Gaussian distribution of the set of time gaps and one or more Gaussian mixture models representing a mixture of Gaussian distributions of the set of time gaps.
3 . The electronic discovery system of claim 1 , wherein one or more selection criteria comprise a Bayesian Information Criterion (BIC).
4 . The electronic discovery system of claim 1 , wherein each electronic chat conversation in the plurality of electronic chat conversations is distinct.
5 . The electronic discovery system of claim 1 , further comprising indexing each electronic chat conversation so that content from each electronic chat conversation is electronically searchable.
6 . The electronic discovery system of claim 1 , wherein receiving the set of electronic chat messages is based on the set of electronic chat messages meeting a predefined chat query criterion.
7 . The electronic discovery system of claim 1 , wherein each electronic chat conversation in the plurality of electronic chat conversations comprises at least a predefined minimum number of electronic chat messages.
8 . A non-transitory computer-readable medium storing instructions that, when executed by a computer processor of an electronic discovery system, cause the electronic discovery system to perform operations comprising:
receiving a set of electronic chat messages, each electronic chat message in the set of electronic chat messages having a timestamp;
determining a set of time gaps, each time gap in the set of time gaps representing a time difference between temporally adjacent electronic chat messages in the set of electronic chat messages;
generating a plurality of models based on the set of time gaps, each model being configured to provide a distinct representation of characteristics of the set of time gaps;
selecting one of the models based on selection criteria, the selected one of the models being a splitting model;
splitting the set of electronic chat messages into a plurality of electronic chat conversations in accordance with the splitting model; and
storing the plurality of electronic chat conversations.
9 . The non-transitory computer-readable medium of claim 8 , wherein the plurality of models comprises one or more distribution models representing a single Gaussian distribution of the set of time gaps and one or more Gaussian mixture models representing a mixture of Gaussian distributions of the set of time gaps.
10 . The non-transitory computer-readable medium of claim 8 , wherein one or more selection criteria comprise a Bayesian Information Criterion (BIC).
11 . The non-transitory computer-readable medium of claim 8 , wherein each electronic chat conversation in the plurality of electronic chat conversations is distinct.
12 . The non-transitory computer-readable medium of claim 8 , wherein the instructions further cause the electronic discovery system to index each electronic chat conversation so that content from each electronic chat conversation is electronically searchable.
13 . The non-transitory computer-readable medium of claim 8 , wherein receiving of the set of electronic chat messages is based on the set of electronic chat messages meeting a predefined chat query criterion.
14 . The non-transitory computer-readable medium of claim 8 , wherein each electronic chat conversation in the plurality of electronic chat conversations comprises at least a predefined minimum number of electronic chat messages.
15 . A method of processing electronic chat data in an electronic discovery system, the method comprising:
receiving, by a computer processor of the electronic discovery system, a set of electronic chat messages, each electronic chat message in the set of electronic chat messages having a timestamp;
determining, by the computer processor, a set of time gaps, each time gap in the set of time gaps representing a time difference between temporally adjacent electronic chat messages in the set of electronic chat messages;
generating, by the computer processor, a plurality of models based on the set of time gaps, each model being configured to provide a distinct representation of characteristics of the set of time gaps;
selecting one of the models based on selection criteria, the selected one of the models being a splitting model;
splitting, by the computer processor, the set of electronic chat messages into a plurality of electronic chat conversations in accordance with the splitting model; and
storing the plurality of electronic chat conversations.
16 . The method of claim 15 , wherein the plurality of models comprises one or more distribution models representing a single Gaussian distribution of the set of time gaps and one or more Gaussian mixture models representing a mixture of Gaussian distributions of the set of time gaps.
17 . The method of claim 15 , wherein one or more selection criteria comprise a Bayesian Information Criterion (BIC).
18 . The method of claim 15 , wherein each electronic chat conversation in the plurality of electronic chat conversations is distinct.
19 . The method of claim 15 , further comprising indexing, by the computer processor, each electronic chat conversation so that content from each electronic chat conversation is electronically searchable.
20 . The method of claim 15 , wherein receiving of the set of electronic chat messages is based on the set of electronic chat messages meeting a predefined chat query criterion.