Michael Bordash

Systems and methods for processing calls to determine if the call is potentially fraudulent or unwanted. The system extracts a speech signal from an audio signal associated with a call. The system identifies audio characteristics based on analysis of the audio signal. The system generates textual transcript of the audio signal based on automatic speech recognition of the speech signal, which is used to assign text categories for the call based on an automated multi-label textual classification… Show more

Systems and methods for processing calls to determine if the call is potentially fraudulent or unwanted. The system extracts a speech signal from an audio signal associated with a call. The system identifies audio characteristics based on analysis of the audio signal. The system generates textual transcript of the audio signal based on automatic speech recognition of the speech signal, which is used to assign text categories for the call based on an automated multi-label textual classification of the textual transcript. The system assigns audio categories for the call based on automated multi-label acoustic classification of the speech signal. The system generates an output label for the call based on a combined analysis of the text categories, the audio categories, and the audio characteristics. The language spoken during the call may be detected and used to generate the textual transcript and to assign the text categories and the audio categories. Show less

Systems and methods for processing messages to determine if the message is potentially fraudulent. The system determines if a word in the message matches a known fraudulent word or a known safe word and labels the message as potentially fraudulent in response the word matching a known fraudulent word. Otherwise, the system determines a probability that the word is potentially fraudulent based on message context. In response to determining that the probability exceeds a first threshold, the… Show more

Systems and methods for processing messages to determine if the message is potentially fraudulent. The system determines if a word in the message matches a known fraudulent word or a known safe word and labels the message as potentially fraudulent in response the word matching a known fraudulent word. Otherwise, the system determines a probability that the word is potentially fraudulent based on message context. In response to determining that the probability exceeds a first threshold, the system determines distances for each pair of word/known safe words (e.g., known brands). The system labels the message as potentially fraudulent in response to the distance of a pair exceeding a second threshold. If the message is labeled as potentially fraudulent it is discarded, otherwise it is forwarded towards the destination. Show less

Techniques to identify segments of information space through active adaption of environment context are provided. A first user request is received by an artificial intelligence (AI) system, and a first segment of information is retrieved from a heterogeneous storage medium, where the first segment of information is located in an upper layer of the heterogeneous storage medium. Upon determining that the first segment of information does not resolve the first user request, the first segment of… Show more

Techniques to identify segments of information space through active adaption of environment context are provided. A first user request is received by an artificial intelligence (AI) system, and a first segment of information is retrieved from a heterogeneous storage medium, where the first segment of information is located in an upper layer of the heterogeneous storage medium. Upon determining that the first segment of information does not resolve the first user request, the first segment of information is sunk to a relatively lower layer of the heterogeneous storage medium, a second segment of information is retrieved from the relatively lower layer of the heterogeneous storage medium, and upon determining that the second segment of information resolves the first user request, the second segment of information is surfaced to the upper layer of the heterogeneous storage medium. Show less

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining a notification template for use in generating a notification for sending to a certain user, the notification template having a having a variable data content holder, wherein the variable data content holder specifies variable data content that varies based on a reference location for the certain user; examining, by machine logic, a location… Show more

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining a notification template for use in generating a notification for sending to a certain user, the notification template having a having a variable data content holder, wherein the variable data content holder specifies variable data content that varies based on a reference location for the certain user; examining, by machine logic, a location history of the user and based on the examining determining a reference location of the user; identifying, by machine logic, a market geographical area (MGA) region for the certain user based on the determined reference location of the certain user; and generating, by machine logic, a notification for sending to the certain user by filling in the variable data content holder of the notification template Show less

The present invention provides a method and system for cognitive rewards recognition in a mobile wallet of a user. A cognitive rewards recognition software application installed in the mobile wallet for each purchase opportunity: determines payment options and associated rewards; determines cognitive factors linking and relating the user, the payment options, and the rewards to purchases; and generates a ranked list of the payment options in response to the cognitive factors, wherein the… Show more

The present invention provides a method and system for cognitive rewards recognition in a mobile wallet of a user. A cognitive rewards recognition software application installed in the mobile wallet for each purchase opportunity: determines payment options and associated rewards; determines cognitive factors linking and relating the user, the payment options, and the rewards to purchases; and generates a ranked list of the payment options in response to the cognitive factors, wherein the rewards are distributed between purchases to maximize benefits to the user in response to the related cognitive factors. The ranked list is presented for each purchase opportunity to the user on his mobile wallet. Show less

A computing device may receive a plurality of beacon data from one or more beacons located within a geographic region, generate a plurality of beacon events based at least in part on the plurality of beacon data, accumulate the plurality of beacon events without sending the plurality of beacon events from the computing device to a remote computing device, and, in response to the occurrence of a trigger event, send the plurality of beacon events accumulated by the computing device to the remote… Show more

A computing device may receive a plurality of beacon data from one or more beacons located within a geographic region, generate a plurality of beacon events based at least in part on the plurality of beacon data, accumulate the plurality of beacon events without sending the plurality of beacon events from the computing device to a remote computing device, and, in response to the occurrence of a trigger event, send the plurality of beacon events accumulated by the computing device to the remote computing device. Show less

A method and system for improving an Internet based search is provided. The method includes generating an intent domain associated with a subject based intent classification. An unstructured data analysis process is executed with respect to a content corpus being associated with the subject based intent classification and a search phase entered in a search field of a graphical user interface with respect to a domain specific search query for specified subject matter. In response the subject… Show more

A method and system for improving an Internet based search is provided. The method includes generating an intent domain associated with a subject based intent classification. An unstructured data analysis process is executed with respect to a content corpus being associated with the subject based intent classification and a search phase entered in a search field of a graphical user interface with respect to a domain specific search query for specified subject matter. In response the subject based intent classification is determined to be associated with the search query and the subject based intent classification is compared to search results data. A subset of search results of the search results data correlating to the subject based intent classification is determined and ranked resulting in a ranked list. The subject based intent classification and the ranked list are presented to a user. Show less

A security application may provide a secure digital currency for a blockchain while maintaining anonymity and security from unauthorized third parties. One example may include one of accessing a retailer site from a device, selecting one or more items for purchase, transmitting a payment option to the retailer site for the selected one or more items, receiving a payment request message from the retailer site comprising a unique identifier linked to one or more incentives, creating a payment… Show more

A security application may provide a secure digital currency for a blockchain while maintaining anonymity and security from unauthorized third parties. One example may include one of accessing a retailer site from a device, selecting one or more items for purchase, transmitting a payment option to the retailer site for the selected one or more items, receiving a payment request message from the retailer site comprising a unique identifier linked to one or more incentives, creating a payment confirmation message comprising the unique identifier and the one or more incentives, and transmitting the payment confirmation. Show less

In embodiments, a ground truth table is used to help determine the relevance of a set of search results from a search query. The ground truth table comprises numerous items, along with a corresponding relevancy ranking for each item. Based on the user interaction with the set of search results, the ground truth table is modified, such that subsequent search queries provide improved results over time. The user interactions can include a click-through action, in which case a user clicked on (or… Show more

In embodiments, a ground truth table is used to help determine the relevance of a set of search results from a search query. The ground truth table comprises numerous items, along with a corresponding relevancy ranking for each item. Based on the user interaction with the set of search results, the ground truth table is modified, such that subsequent search queries provide improved results over time. The user interactions can include a click-through action, in which case a user clicked on (or otherwise selected) a search result entry. The user interactions can include a purchase action, wish list addition action, favorite list addition action, and/or a share action, among others. Based on the user interactions, the ranking of an entry in the ground truth table is adjusted. Then, subsequent searches that use the modified ground truth table can provide improved search results.

Show less

The present invention provides a method and system for search engine optimization based upon most popular search histories. The method includes a server receiving a search query from a user for a website, and corresponding search result data from the website. A determination is made whether a number of times the search query has been received by the website in a given time period exceeds a given popularity threshold value. The server stores the search query and corresponding search result data… Show more

The present invention provides a method and system for search engine optimization based upon most popular search histories. The method includes a server receiving a search query from a user for a website, and corresponding search result data from the website. A determination is made whether a number of times the search query has been received by the website in a given time period exceeds a given popularity threshold value. The server stores the search query and corresponding search result data to a static html page when the popularity threshold is exceeded, then generates and stores a site map corresponding to the website to include the static html page.
Show less

Embodiments of the present invention provide methods and systems for modification and/or removal of a push notification from a mobile device upon an event such as exit from an area. A positioning system tracks the location of a mobile device through an area. A push notification is presented to the mobile device while the device is in or near the area. If the user exits the area without acknowledgement of the message, the message is modified or removed.

This invention relates to a method, system and computer program for assessing enhanced dynamic keyword-based advertising campaigns, such that a site-level keyword search request of a web page is tracked, where the site-level keyword search request includes at least one search term. The frequency of usage of the search term of the site-level keyword search request is monitored, and the frequency of usage of the search term is compared with a predetermined value. At least one popular term is… Show more

This invention relates to a method, system and computer program for assessing enhanced dynamic keyword-based advertising campaigns, such that a site-level keyword search request of a web page is tracked, where the site-level keyword search request includes at least one search term. The frequency of usage of the search term of the site-level keyword search request is monitored, and the frequency of usage of the search term is compared with a predetermined value. At least one popular term is identified in response to comparing the frequency of usage of the search term with the predetermined value. The popular term is compared with a plurality of existing keyword-based advertising campaigns. It is determined whether the popular term is to be included in the advertising campaign included in the existing keyword-based advertising campaigns, whereby an effectiveness of the advertising campaign may be evaluated. Show less

Disclosed aspects include geo-fence management using a cluster analysis technique. A set of dynamic user data is received from a set of users. The set of dynamic user data may have identification information which identifies one or more users, location information which indicates location for one or more users, and context information which indicates application context for one or more users. The cluster analysis technique may be used to process the set of dynamic user data. Accordingly, a… Show more

Disclosed aspects include geo-fence management using a cluster analysis technique. A set of dynamic user data is received from a set of users. The set of dynamic user data may have identification information which identifies one or more users, location information which indicates location for one or more users, and context information which indicates application context for one or more users. The cluster analysis technique may be used to process the set of dynamic user data. Accordingly, a geo-fence opportunity event is detected using the cluster analysis technique. Based on a selection criterion with respect to the geo-fence opportunity event, it is determined to provide an opportunity for a subset of the set of users. In response to making the determination, the opportunity can be provided for/to the subset of the set of users (e.g., sending a notification to the subset of the set of users). Show less