Abstract: Disclosed are embodiments for providing batch performance using a stream processor. In one embodiment, a method is disclosed comprising detecting a real close of books (COB) of a data transport, the real COB associated with a set of raw events transmitted over the data transport, flushing a stream processor in response to detecting the real COB, and retrieving a set of processed events from a distributed file system after the flushing is complete. A fact COB computation is then performed on the set of processed events and the set of raw events, the fact COB computation outputting a number of missing events, each missing event representing a raw event that is not present in the set of processed events. The processed events are then certified upon determining that the number of missing events is below a threshold.

Abstract: One or more computing devices, systems, and/or methods for oversampling for imbalanced test data are provided. A classifier is configured to classify data points as either belonging to a first class or a second class. A determination may be made that the first class and the second class are imbalanced where a first number of data points estimated to be part of the first class is a threshold amount less than a second number of data points estimated to be part of the second class. An oversampling ratio is determined for the first class. The oversampling ratio is used to select a sample set of data points for editorial labeling, where the sampling set of data points comprises a total number of data points below a threshold amount.

Abstract: One or more computing devices, systems, and/or methods for determining activity patterns based upon user activity and/or performing operations based upon the activity patterns are provided. For example, activity performed using a communication interface associated with a user account may be detected. The activity may be analyzed to determine an activity pattern associated with a first set of conditions. The activity pattern may be stored in a user profile associated with the user account. The user profile may comprise a plurality of activity patterns. Each activity pattern of the plurality of activity patterns may be associated with a set of conditions of a plurality of sets of conditions. It may be determined that the first set of conditions are met. Responsive to determining that the first set of conditions are met, one or more operations associated with the activity pattern may be performed.

Abstract: In an example, first entities are extracted from user profiles. Second entities are extracted from content information associated with content item. User-associated metrics associated with the first entities are determined based upon the user profiles and/or content events. First vector representations of the first entities and second vector representations of the second entities are processed to generate an attention distribution array. Each value of the attention distribution array represents, for a user interested in an entity of the first entities, a proportion of (i) entity-specific activity, of the user, related to an entity of the second entities relative to (ii) an entirety of activity of the user. An inferred activity distribution array is generated by applying the user-associated metrics to the attention distribution array. A filtered subset of activity distribution values is generated by pruning values from the inferred activity distribution array.

Abstract: Embodiments are directed towards automatically learning user behavioral patterns when interacting with messages and based on the learned patterns, suggesting one or more predicted actions that a user might take in response to receiving subsequent message. One or more classifiers are trained and employed to predict one or more actions that a user might take in response to receiving the message. In one embodiment, the one or more predicted actions are provided suggested to the user as an action the user might take on the message. Messages may be rank ordered within a given suggested action based on a confidence level of the prediction.

Abstract: One or more computing devices, systems, and/or methods for detecting trigger phrases and transmitting electronic messages to devices are provided. For example, audio received via a microphone of a first device may be monitored. Responsive to detecting a first trigger phrase in a first audio segment identified during the monitoring, a first electronic message comprising instructions to activate a microphone function of a second device may be generated and the first electronic message may be transmitted to the second device. Responsive to detecting a second trigger phrase in a second audio segment identified during the monitoring, a second electronic message comprising instructions to activate a microphone function of a third device may be generated and the second electronic message may be transmitted to the third device.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in distributional similarity identification using randomized observations. In connection with an intrusion detection system monitoring a computing system, a pair of perturbed sample sets are generating using a pair of real sample set (or real observations) and a pair of random sample sets (of randomly-selected observations), and a similarity measuring representing a level of consistency in user behavior is determined. The systems improve the quality and accuracy of the similarity determination for use in intrusion detection.

Abstract: One or more computing devices, systems, and/or methods for generating a list of suggested queries associated with one or more keywords are provided. For example, one or more keywords may be received via a search interface. A plurality of queries associated with the one or more keywords may be determined based upon the one or more keywords and a historical query database. A plurality of relationship scores associated with the plurality of queries may be generated based upon a plurality of search sessions associated with the historical query database. The historical query database may be analyzed to determine a plurality of click rates associated with the plurality of queries. A list of suggested queries may be generated based upon the plurality of relationship scores and the plurality of click rates.

Abstract: One or more computing devices, systems, and/or methods for cross-domain action prediction are provided. Action sequence embeddings are generated based upon a textual embedding and a graph embedding utilizing past user action sequences corresponding to sequences of past actions performed by users across a plurality of domains. An autoencoder is trained to utilize the action sequence embeddings to project the action sequence embeddings to obtain intent space vectors. A service switch classifier is trained using the intent space vectors. In response to the service switch classifier predicting that a current user will switch from a current domain to a next domain, the current user is provided with a recommendation of an action corresponding to the next domain.

Abstract: Methods, programming, and system for modifying a slot value are described herein. In a non-limiting embodiment, an intent may be determined based on a first utterance. A first slot-value pair may be obtained for the first utterance based on the intent, the first slot-value pair including a first slot and a first value associated with the first slot. A second value associated with the first slot may be identified, the second value being identified from a second utterance that was previously received. Based on the intent and the first slot, a type of update to be performed with respect to the second value may be determined. The second value may then be updated based on the first value and the type of update.

Abstract: The present teaching relates to method, system, medium, and implementations for machine learning. A training sample is first received from a source. A prediction is generated according to the training sample and based on one or more parameters associated with a model. A metric characterizing the prediction is also determined. The prediction and the metric are transmitted to the source to facilitate a determination on whether a ground truth label for the training sample is to be provided. When the ground truth label is received from the source, the one or more parameters of the model are updated based on the prediction and the ground truth label.

Abstract: Disclosed are systems and methods for managing online identity authentication risk in a nuanced identity system. For example, a method may include receiving a request by a user for a transaction on an electronic platform; determining a risk associated with the requested transaction; determining a current level of assurance associated with the user on the electronic platform; determining that the risk exceeds the current level of assurance; adjusting the current level of assurance such that the adjusted level of assurance exceeds the risk; and executing the requested transaction on the electronic platform after adjusting the current level of assurance.

Abstract: A device, system, and method are directed towards facilitating composing, editing, and displaying a message that includes text and graphics inline. An edit window provides a mechanism for editing the text inline. The message, including text and graphics, may be sent to a remote device. The remote device may display the message, and edit the text and graphics inline, and send a reply message to the original sender.

Abstract: 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.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for privacy-aware machine learning using an improved data encoding that withholds more information. The disclosed systems and methods encode a corpus of data and encode each query used in searching and generating query results from the corpus of encoded data.

Abstract: A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for presenting a search result in a search result card, the method includes receiving from a user, an input associated with a search query; fetching one or more search results in accordance with the search query; generating a search result card for each of the one or more search results; and presenting to the user, one or more search result cards as a response to the search query, the one or more search result cards corresponding to the one or more search results, respectively.

Abstract: One or more computing devices, systems, and/or methods for entity disambiguation are provided. For example, a document may be analyzed to identify a first mention and a second mention. One or more techniques may be used to select and link a candidate entity, from a first set of candidate entities, to the first mention and select and link a candidate entity, from a second set of candidate entities, to the second mention.

Abstract: Disclosed are embodiments for providing batch performance using a stream processor. In one embodiment, a method is disclosed comprising receiving an event, such as a streaming event, from a client. The method determines that the event comprises a primary event and, if so, writes the primary event to a cache and returning the primary event to the client. The method later receives a second event from the client, the second event associated with the first event, annotates the second event based on the primary event, and returns the annotated second event to the client.

Abstract: The present teaching, which includes methods, systems and computer-readable media, relates to providing query suggestions based on a number of data sources that include person's personal data and non-personal data. The disclosed techniques may include receiving an input from a person, obtaining a first set of suggestions based on a person corpus derived from at least one data source private to the person, obtaining a second set of suggestions based on information from an additional data source, ranking the first and second sets of suggestions to generate a ranked list of suggestions, and presenting at least some of the ranked suggestions.

Abstract: Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.