Clari Inc.

Symantec Corporation

Clearwell Systems, Inc.

Veritas Technologies LLC

Brocade Communications Systems, Inc.

Venkat Rangan

Malay Desai

Mohan Kumar

Xin Xu

Gary Steven Lehrman

Mahesh Subedi

Edward D McClanahan

Sanjay Kumar Mahalingam

Yongqiang He

Shengke Yu

Anurag Kashyap

Michael B Schmitz

Kaiyue Wu

Medha Shewale

Chunyue Du

Xincheng Ma

Nelson Murray Wiggins

Lei Tang

Guruaj Pangal

Curt E Beckmann

Prem Kumar

According to various embodiments, described herein are systems and methods for training machine learning (ML) models to generate real-time scores to predict the probabilities of task completion. In one embodiment, an exemplary method includes the operations of receiving, from a data store, a set of features and a workflow for training a first type of ML models, the workflow specifying a data source, a number of stages and associated parameters for training the ML models; retrieving, from the data source, training data for the set of features; and segmenting the training data into different segments. The method further includes the operations of training a separate first type of ML model using each of the different segment of the training data in accordance with the workflow; and persisting the first type of trained ML models into the data storage. The method also includes using a trained ML model to generate probability scores and displaying the scores to users in real-time.

System and method for generating scores for predicting probabilities of task completion

In an embodiment, described herein is a system and method for creating a suggested task set to meet a target value. A cloud server, in response to receiving a request specifying a target value, retrieves completed task sets from a database. Each completed task set includes a same set of task categories. The cloud server derives a number of ratios from the retrieved completed task sets, including a composition ratio and a conversion rate for each task category, and an addition ratio for the number of completed task sets. Based on the derived ratios and the specified target value, the cloud server constructs the suggested task set, and displays in real-time the suggested task set together with current values for the task categories. The cloud server alerts users of a discrepancy between a current value and the corresponding suggested value for a task category when the discrepancy reaches a predetermined level.

Method for estimating amount of task objects required to reach target completed tasks

According to one embodiment, a customer relationship management (CRM) system is queried to obtain a project that is associated with an entity (e.g., a user, a group of users, a client). A first list of one or more contacts (e.g., contact persons, referred to herein target contacts) associated with the project from the CRM system. For each of the contacts in the first list, a domain name is determined based on contact information of the contacts (e.g., emails, Web addresses, name of an account associated with the contacts). A first set of email addresses, referred to as target email addresses, is determined based on the domain name and contacts using a set of email identification rules. An email server is queried to retrieve a list of one or more emails and/or calendar events based on the first set of email addresses.

Method and system for identifying emails and calendar events associated with projects of an enterprise entity

A request is received for determining a task completion rate of each of a first set of tasks associated with a set of task attributes. The first set of tasks are scheduled to be completed within a first timer period. An MAPE score is calculated or obtained for each of the completion rate predictive models, which is determined based on prior predictions performed in a second time period in the past. The duration of the second time period is a multiple of the first time period. One of the predictive models is selected based on the MAPE scores of the predictive models, where the selected model has the lowest MAPE score amongst the predictive models in the set. In another embodiment, a predictive model is selected further based on the volatility scores of the predictive models. A model with a combination of lowest MAPE score and volatility score is selected.

Method and system for predicting task completion of a time period based on task completion rates and data trend of prior time periods in view of attributes of tasks using machine learning models

Systems and methods are provided for analyzing a history of meetings, the attendees, date of occurrence, and other content to determine the value of the meetings and the attendees. The importance of people and the meetings they attend can be derived based on patterns of attendees. In one embodiment, the meta-data of meetings and the attendees can be used to determine value without requiring time-consuming manual steps or manual evaluation of people and their titles. A graph of meetings and its attendees can be generated and used by one or more automated software agents to place value to the content of the meeting, its agenda, and other meeting collateral such as meeting briefs/attachments of meetings. Accordingly, embodiments dramatically reduce the need for human examination of meeting history.

Automatic ranking and scoring of meetings and its attendees within an organization

A set of trigrams can be generated for each document in a plurality of documents processed by an e-discovery system. Each trigram in the set of trigrams for a given document is a sequence of three terms in the given document. A set of trigrams for each similar document is then determined based on the set of trigrams for the original document. To facilitate identification of the similar documents, a full text index is then generated for the plurality of documents and the set of trigrams for each document are indexed into the full text index, as individual terms. Queries can be generated into the full text index based on trigrams of a document to determine other similar or near-duplicate documents. After a set of potentially similar documents are identified, a separate distance criteria can be applied to evaluate the level of similarity between the two documents in an efficient way.

Methods and systems to efficiently find similar and near-duplicate emails and files

A server computing system determines a plurality of statistics for a plurality of test documents, determines a number of false negatives for a corpus of documents based on one or more of the plurality of statistics for the plurality of test documents. The classification of a document of the corpus of documents is a false negative if classification of the document by a classification model is negative and classification of the document by a user is positive. The server computing system calculates an effectiveness of an information retrieval system on a corpus of documents based on the number of false negatives for the corpus of documents.

Method and system for information retrieval effectiveness estimation in e-discovery

A predictive coding system updates a plurality of training documents for an untrained classification model based on a plurality of additional documents. The plurality of additional documents are selected from a plurality of unlabeled documents based on a decision hyperplane associated with a first trained classification model. The predictive coding system provides the updated plurality of training documents to the untrained classification model to cause the untrained classification model to be retrained and to cause a second trained classification model to be generated.

System and method for training data generation in predictive coding

Techniques are provided for automatic sampling evaluation. An automatic sampling evaluation system enables users to evaluate convergence of one or more search processes. For example, given a set of searches that were validated by human review, a system can implement a retrieval process that samples one or more non-retrieved collections. Each individual document's similarity in the one or more non-retrieved collections is automatically evaluated to other documents in any retrieved sets. Given a goal of achieving a high recall, documents with high similarity can then be analyzed for additional noun phrases that may be used for a next iteration of a search. Convergence can be expected if the information gain in the new feedback loop is less than previous iterations, and if the additional documents identified are below a certain threshold document count.

Methods and systems for automatic evaluation of electronic discovery review and productions

A server computing system determines a plurality of statistics for a plurality of validation documents. The server computing system determines a plurality of statistics for a plurality of test documents. The number of test documents in the plurality of test documents is determined based on the plurality of statistics for the plurality of validation documents and the effectiveness measure of interest. The server computing system calculates an effectiveness of an information retrieval system on a corpus of documents based on the plurality of statistics for the plurality of test documents.

Growing community of inventors

San Jose, CA, United States of America

Venkat Rangan