Sap Se

Tu Truong

Fuming Wu

Sudhir Bhojwani

Quan Zhang

Sandeep Chakravarty

Richa Namballa

Sudha Lakshman

Lin Dong

Yue Li

Han Li

Julio C Navas

Omar Rahman

Sivakumar N

Nethaji Tummuru

Manikanta Pachineelam

Jaehun Jeong

Hanxiang Chen

Michael Kunzmann

Mario Ponce

Nazanin Zaker Habibabadi

Nalini Chandhi

Chao Zhou

Rahul Kabra

Sakshi Chopra

Zhenhua Luo

Frank Wu

Hameesh Manadath

Hansen Chen

Ajain Kuzhimattathil

Makoto Sugishita

Masamitsu Ochiai

Provided is a method and system for normalizing catalog item data to create higher quality search results. In one example, the method may include receiving a record comprising an unstructured description of an object, identifying a type of the object from among a plurality of object types and identifying a predefined attribute of the identified type of object, extracting a value from the unstructured description corresponding to the predefined attribute and modifying the extracted value to generate a normalized attribute value, and storing a structured record of the object in a structured format comprising a plurality of values of a plurality of attributes of the object from the unstructured description including the normalized attribute value for the predefined attribute of the object.

Normalization of unstructured catalog data

Technologies are provided for validating expression updates. A change to an editable expression can be detected by a client computing device and an expression update describing the detected change can be transmitted to an application server over a bidirectional communication channel. The application server can analyze the expression update to determine whether the detected change resulted in a valid expression. Analyzing the expression update can comprise locating an entity identifier in the detected change and searching a database to determine whether the identified entity exists. The application server can also determine whether a given user has permission to access the identified entity. The application server can transmit expression update validation information back to the client computing device over the bidirectional communication channel. The client computing device can update a user interface displaying the expression based on the validation information.

Expression update validation

In an example, a machine learning algorithm is used to train an entity risk evaluation model to output an entity risk score based on transaction data in a computer network. Entity risk scores for various entities may be stored in a database, and retrieved and displayed upon user interaction with one or more reports involving corresponding entities.

Machine learning models for evaluating entities in a high-volume computer network

Systems, methods, and apparatuses for activity pattern detection are described herein. Embodiments may process large amounts of data from a plurality of different database sources in order to detect events common to the data of the different database sources. Embodiments further perform data mining operations to detect patterns (e.g., two or more events appearing consecutively or non-consecutively), and present these patterns in a graphical user interface (GUI) to illustrate how a plurality of patterns may comprise a business scenario.

Systems, methods, and apparatuses for detecting activity patterns

Growing community of inventors

San Jose, CA, United States of America

Tu Truong