Oracle International Corporation

Michael Malak

Mark L Kreider

Luis E Rivas

Glenn Allen Murray

Robert James Oberbreckling

Alexander Sasha Stojanovic

Philip Ogren

Manisha Gupta

Nikhil Surve

Douglas C Savolainen

Chaohui Yu

Luis Ramirez

In accordance with an embodiment, described herein is a system and method for use of text analytics to transform, analyze, and visualize data, including support for data flows of unstructured text or other types of textual data input. Additionally described are various examples of algorithmic processes and user interfaces that can be used to enable text analytics in particular environments or use cases. In accordance with an embodiment, the system can be implemented within a cloud environment that enables self-service text analytics. A user, for example an organizational business user who may not be expert in the use of machine learning as applied to data processing, can interact with the system via a user interface, to apply natural language processing or other text analysis techniques to a data flow or set of input data, to generate visualizations or other types of useful information associated with the data.

System and method for use of text analytics to transform, analyze, and visualize data

Techniques for generated regular expressions are disclosed. In some embodiments, a regular expression generator may receive input data comprising one or more character sequences. The regular expression generator may convert character sequences into a sets of regular expression codes and/or span data structures. The regular expression generator may identify a longest common subsequence shared by the sets of regular expression codes and/or spans, and may generate a regular expression based upon the longest common subsequence. A negative example may be used to generate the regular expression. Context from the negative example may be determined in order to generate the regular expression.

Regular expression generation for negative example using context

Disclosed herein are techniques related to automated generation of regular expressions. In some embodiments, a regular expression generator may receive input data comprising one or more character sequences. The regular expression generator may convert character sequences into a sets of regular expression codes and/or span data structures. The regular expression generator may identify a longest common subsequence shared by the sets of regular expression codes and/or spans, and may generate a regular expression based upon the longest common subsequence.

Regular expression generation based on positive and negative pattern matching examples

Regular expression generation using longest common subsequence algorithm on combinations of regular expression codes

The present disclosure related to techniques for analyzing data from multiple different data sources to determine a relationship between the data (also referred to herein a 'data relationship discovery'). The relationships between any two compared datasets may be used to determine one or more recommendations for merging (e.g., joining), or 'blending,' the data sets together. Relationship discovery may include determining a relationship between a subset of data, such as a relationship between a pair of columns, or column pair, each column in a different dataset of the datasets that are compared. Given two datasets to process for relationship discovery, relationship discovery may identify and recommends a ranked subset of column pairs between two compared datasets. The ranked column pairs identified as a relationship may be useful for blending the datasets with respect to those column pairs.

Techniques for relationship discovery between datasets

Techniques are provided for identifying attributes associated with a neologism or an unknown word or name. Real world characteristics can be predicted for the neologism. Trigrams are identified for an input word and word embedding model vector values are calculated for the identified trigrams and entered into a matrix. Trigrams are identified for nearest names. Classification values are calculated based on the trigrams for the input word and the trigrams from the nearest names and the classification values are entered into the matrix. A convolutional neural network can process the matrix to identify one or more characteristics associated with the neologism.

Neologism classification techniques with trigrams and longest common subsequences

Techniques for generated regular expressions are disclosed. In some embodiments, a regular expression generator may receive input data comprising one or more character sequences. The regular expression generator may convert character sequences into a sets of regular expression codes and/or span data structures. The regular expression generator may identify a longest common subsequence shared by the sets of regular expression codes and/or spans, and may generate a regular expression based upon the longest common subsequence. Alignment of span data structures may be performed when generating the regular expression.

Regular expression generation using span highlighting alignment

Techniques are provided for performing sentiment analysis on words in a first data set. An example embodiment includes generating a word embedding model including a first plurality of features. A value indicating sentiment for the words in the first data set can be determined using a convolutional neural network (CNN). A second plurality of features are generated based on bigrams identified in the data set. The bigrams can be generated using a co-occurrence graph. The model is updated to include the second plurality of features, and sentiment analysis can be performed on a second data set using the updated model.

Techniques for sentiment analysis of data using a convolutional neural network and a co-occurrence network

The present disclosure relates to performing similarity metric analysis and data enrichment using knowledge sources. A data enrichment service can compare an input data set to reference data sets stored in a knowledge source to identify similarly related data. A similarity metric can be calculated corresponding to the semantic similarity of two or more datasets. The similarity metric can be used to identify datasets based on their metadata attributes and data values enabling easier indexing and high performance retrieval of data values. A input data set can labeled with a category based on the data set having the best match with the input data set. The similarity of an input data set with a data set provided by a knowledge source can be used to query a knowledge source to obtain additional information about the data set. The additional information can be used to provide recommendations to the user.

Techniques for similarity analysis and data enrichment using knowledge sources

Techniques for generated regular expressions are disclosed. In some embodiments, a regular expression generator may receive input data comprising one or more character sequences. The regular expression generator may convert character sequences into a sets of regular expression codes and/or span data structures. The regular expression generator may identify a longest common subsequence shared by the sets of regular expression codes and/or spans, and may generate a regular expression based upon the longest common subsequence. Generation of the regular expressions can be implemented on an interactive user interface. Commands can be applied to the one or more character sequences and regular expressions are generated based on the applied commands.

User interface commands for regular expression generation

User interface for regular expression generation

Regular expression generation using combinatoric longest common subsequence algorithms

Regular expression generation using longest common subsequence algorithm on spans

Techniques are disclosed for toponym disambiguation. Toponym disambiguation can be performed for a set of geographic location data, such as placenames. A subset of the data and additional location information associated with the subset of the data can be initially determined. The remaining geographic location data in the set of geographic location data can be scored in order to determined additional location information for the remaining geographic location data. Additional location information for the remaining geographic location data can be determined based on calculated scores.

Growing community of inventors

Denver, CO, United States of America

Michael Malak