An input sequence re-ordering method with a multi input-precision reconfigurable scheme and a pipeline scheme for a computing-in-memory macro in a convolutional neural network application is configured to re-order a plurality of multi-bit input signals and includes performing a scanning step and a re-ordering step. The scanning step includes driving a scanner to scan one group of the multi-bit input signals to determine whether an initial value of a plurality of flag signals in one of a plurality of multi-bit section flags is changed to an inverted initial value according to a plurality of bit numbers of the one group of the multi-bit input signals. The re-ordering step includes driving a sorter to select a part of the one group of the multi-bit input signals corresponding to a plurality of the inverted initial values of the flag signals in the one of the multi-bit section flags.

Described are techniques for anomaly detection including a method comprising sorting a univariate data set in an numeric order and generating a second univariate data set based on the sorted univariate data set, where respective elements in the second univariate data set correspond to respective differences between consecutive elements in the sorted univariate data set. The method further comprises sorting the second univariate data set in numeric order and generating a third univariate data set that includes index values corresponding to respective differences in the sorted second univariate data set that are above a threshold. The method further comprises modifying the third univariate data set and defining a set of clusters based on the modified third univariate data set. The method further comprises clustering the sorted univariate data set according to the set of clusters and characterizing a new data point as anomalous in response to the clustering.

Described are techniques for anomaly detection including a method comprising sorting a univariate data set in an numeric order and generating a second univariate data set based on the sorted univariate data set, where respective elements in the second univariate data set correspond to respective differences between consecutive elements in the sorted univariate data set. The method further comprises sorting the second univariate data set in numeric order and generating a third univariate data set that includes index values corresponding to respective differences in the sorted second univariate data set that are above a threshold. The method further comprises modifying the third univariate data set and defining a set of clusters based on the modified third univariate data set. The method further comprises clustering the sorted univariate data set according to the set of clusters and characterizing a new data point as anomalous in response to the clustering.

Disclosed are some implementations of systems, apparatus, methods and computer program products for extracting topics from a corpus of exchanges. The system generates vector representations of utterances of an entity common to the exchanges and uses the vector representations to cluster the utterances. The system labels the clusters and uses the labeled clusters to generate an exchange label sequence for each of the exchanges, where each exchange label sequence corresponds to a sequence of utterances generated by the entity. The system processes the exchange label sequences to generate one or more subsets of the utterances, where each of the subsets corresponds to a particular topic.

Disclosed are some implementations of systems, apparatus, methods and computer program products for extracting topics from a corpus of exchanges. The system generates vector representations of utterances of an entity common to the exchanges and uses the vector representations to cluster the utterances. The system labels the clusters and uses the labeled clusters to generate an exchange label sequence for each of the exchanges, where each exchange label sequence corresponds to a sequence of utterances generated by the entity. The system processes the exchange label sequences to generate one or more subsets of the utterances, where each of the subsets corresponds to a particular topic.

A data management platform for intelligently managing data is provided. The data management platform includes an ETL module configured to extract, cleanse, transform, or load data; a data lake configured to store a first group of data formed by extracting raw data from a plurality of data sources by the ETL module; a data warehouse configured to store a second group of data formed by cleansing and standardizing on the first group of data; a general data layer configured to store a third group of data formed by subjecting the second group of data to data fusion; and a data mart configured to store a fourth group of data formed by transforming the third group of data by the ETL module. The general data layer is a distributed data storage storing information available for querying. The data mart is a database of NoSQL type storing information available for computational processing.

A data management platform for intelligently managing data is provided. The data management platform includes an ETL module configured to extract, cleanse, transform, or load data; a data lake configured to store a first group of data formed by extracting raw data from a plurality of data sources by the ETL module; a data warehouse configured to store a second group of data formed by cleansing and standardizing on the first group of data; a general data layer configured to store a third group of data formed by subjecting the second group of data to data fusion; and a data mart configured to store a fourth group of data formed by transforming the third group of data by the ETL module. The general data layer is a distributed data storage storing information available for querying. The data mart is a database of NoSQL type storing information available for computational processing.

Systems and methods are disclosed for utilizing sender-recipient pair data to establish sender-level trust in future communication. One method comprises receiving raw communication data over a network and testing the received raw communication data against trained machine learning data to predict whether the raw communication data is associated with expected communication data. The raw communication data is sorted for expected communication data, which is further analyzed for sender-recipient pair data and assigned an expected communication pair data score. Senders associated with an expected communication pair data score that meets or exceeds a threshold are labeled and stored in a database as trusted. As a result of the sender-recipient pair analysis, recipients at-risk for being scammed can be identified, senders misidentified as spammers can be properly classified, and machine learning techniques utilized for analyzing raw communication data can be fine-tuned.

Systems and methods are disclosed for utilizing sender-recipient pair data to establish sender-level trust in future communication. One method comprises receiving raw communication data over a network and testing the received raw communication data against trained machine learning data to predict whether the raw communication data is associated with expected communication data. The raw communication data is sorted for expected communication data, which is further analyzed for sender-recipient pair data and assigned an expected communication pair data score. Senders associated with an expected communication pair data score that meets or exceeds a threshold are labeled and stored in a database as trusted. As a result of the sender-recipient pair analysis, recipients at-risk for being scammed can be identified, senders misidentified as spammers can be properly classified, and machine learning techniques utilized for analyzing raw communication data can be fine-tuned.

A processing system of including at least one processor may obtain a query to retrieve a set of information from a graph database, the query providing a criterion for identifying graph database vertices that are relevant to the query, identify the graph database vertices that are relevant to the query in accordance with the criterion, obtain vertex identifiers of the relevant vertices, sort the vertex identifiers into a list in a sequential order, identify a first subset of the vertex identifiers in the list that corresponds to a first result index and a result size, access a first subset of the vertices that is identified as being relevant to the query and that is identified by the first subset of the vertex identifiers, retrieve a first subset of the set of information from the first subset of the vertices, and provide the first subset in a first results page.