Firetide, Inc.

Cadence Design Systems, Inc.

Accenture Global Solutions Limited

[24]7.ai, Inc.

24/7 Customer, Inc.

Ravi Prakash

Jorjeta Gueorguieva Jetcheva

Bhargav Ramachandra Bellur

Amar Singhal

Sachin Kanodia

Mohan Natarajan

Vinay Gupta

Alok Jain

Kranthi Mitra Adusumilli

Subhash Ramchandra Kulkarni

Kavita Ravi

Ravi Vijayaraghavan

Robert Paul Kurshan

Ziyad Hanna

Habeeb Farah

Vijay Desai

Vinaya Kumar Singh

Xiaoqun Du

Manu Chopra

Ronald H Hardin

Rajdeep Mukherjee

Benjamin Meng-Ching Chen

Pratik Mahajan

Darshan Hegde

Ashok Rajaraman

An Artificial Intelligence (AI) based document processing and validation system identifies anomalies such as errors, fraud, and duplicates of received documents and enables automatic actions for valid documents using machine learning (ML) techniques. The received documents are processed for determining probabilities for errors, fraud, and duplicates. A validation worklist is generated with the documents arranged in descending order of the probabilities and invalid documents with higher probabilities are flagged for review while the valid documents with lower probabilities are further processed for the execution of automatic actions. The feedback from the invalid document review is used to further train the models in determining the probabilities.

Artificial intelligence (AI) based document processing and validation

Channel assignment for wireless access networks is directed toward improved overall communication capability of the networks. A network is formed of wireless access points (APs) coupled via wired (and/or wireless) links and enabled to communicate with clients via radio channels of each of the APs. Local information is collected at each of the APs and processed to determine channel assignments according to a Neighbor Impact Metric (NIM) that accounts for one-hop and two-hop neighbors as well as neighbors not part of the network. Optionally, the NIM accounts for traffic load on the APs. The channel assignments are determined either on a centralized resource (such as a server or one of the APs) or via a distributed scheme across the APs. The local information includes how busy a channel is and local operating conditions such as error rate and interference levels.

Channel assignment for wireless access networks

Enhanced mesh network performance is provided by computation of a path metric with respect to multi-hop paths between nodes in a mesh network and determination of a path through the mesh network that is optimal according to the path metric. Information is communicated in the mesh network according to the determined path. Nodes in the mesh network are enabled to communicate via one or more wireless links and/or one or more wired links. The path metric optionally includes an effective bandwidth path metric having elements (listed from highest to lowest conceptual priority) including an inverse of a sustainable data rate, a number of wireless links, and a number of wireless and wired links. The sustainable data rate is a measure of communication bandwidth that is deliverable by a path for a period of time. Accounting is made for interference between contiguous wireless links operating on the same channel.

Effective bandwidth path metric and path computation method for wireless mesh networks with wired links

The present disclosure relates to a computer-implemented method for use in a formal verification of an electronic design. Embodiments may include receiving a reference model including a software specification, an implementation model at a register transfer level, and a property that analyzes equivalence between the reference model and the implementation model. The method may further include generating one or more case split hints based upon the reference model, that may be used to decompose the design state space into smaller partitions and performing an abstraction operation on a portion of design logic associated with one or more partitions in order to eliminate design elements that are irrelevant to a particular property. Embodiments may also include performing model checking on the abstract models to determine their accuracy.

System, method, and computer program product for sequential equivalence checking in formal verification

Online browsing behavior is used to predict the intent of online users dynamically. The category of online user is predicted and the prediction can be used to provide assistance to the user, if required. Such prediction is based on a combination of a Na&#xef;ve's Bayes classifier and a Markov model.

Dynamic prediction of online shopper's intent using a combination of prediction models

Embodiments of the invention relate to managing user interactions and, more particularly, to performing analysis on data generated by user interactions. Embodiments of the invention use text mining to extract personal information of users from user interactions automatically. A topic model is used to reduce the number of dimensions required to represent the text, yet all the information of interest is highly pronounced. This enables a lower dimensional representation of the data leading to significantly faster computations.

Method and apparatus for extracting journey of life attributes of a user from user interactions

Aspects of computing design invariants, by using approximate reachability analysis, include reducing the circuit model for verification and synthesis. Further included is computing invariants using approximate reachability analysis to optimize a circuit model by identifying a plurality of next states for a present state, the plurality of next states capable of being reached from the present state in one transition. The plurality of bits of the next states are compared with a plurality of bits of the present state, and each bit of the present state that is different from at least one next state is changed to variant.

Design optimization using approximate reachability analysis

Growing community of inventors

Bengaluru, India

Ravi Prakash