Abstract: A method including receiving events from different data sources for a service automatically executing in an enterprise system. A first event is enriched by providing the first event with first metadata that associates the first event with a first application used by the service. The first event is assigned to a time slice associated with the first application. A second event is enriched in a similar manner. A correlation graph of nodes and edges is built using the enriched events, with nodes representing the events and edges indicating relationships between the edges. A third event indicating a fault in the first application associated with the first node is received. The source of the error for the third event is identified using the second updated correlation graph and the time slice. The source of error is then mitigated.

Abstract: A system that communicates information is described. This system includes: a network interface, a proxy device coupled to the network interface, and an interface node coupled to the proxy device and configured to couple to a channel. Note that the network interface is configured to transmit outbound messages from the system to a location and to receive inbound messages to the system from the location, and the channel is configured to convey the outbound messages and the inbound messages. Moreover, the proxy device is configured to inspect a given message inbound or outbound based on a pre-determined profile of the location and pre-defined communication rules. Then, the proxy device is configured to restrict the given message based on a result of the inspection, where the restriction occurs after the system begins a communication session with the location and is performed for the duration of the communication session.

Abstract: A processor may receive a request for access to a first resource from a client. The processor may retrieve a decision token indicating a plurality of resource decisions for the client, each of the plurality of resource decisions including a decision permitting or forbidding access to at least one resource. The processor may identify, among the plurality of resource decisions, a first decision for the first resource. On the basis of the first decision for the first resource, the processor may enable or block access to the first resource by the client. The decision token may have been generated by the processor generating a plurality of resource decisions for the client, the plurality of resource decisions including a first decision permitting or forbidding access to the first resource and at least one additional decision permitting or forbidding access to at least one additional resource.

Abstract: Certain aspects of the present disclosure provide techniques for establishing a web session between a computing device and a web-based integrated development environment to create and/or update files (e.g., content files and/or resource files). In the web session, content file(s) can be evaluated in real-time with one or more resource files. Further, in the web session, a set of validation rules of a resource file can be updated by the computing device. To stablish the web session, a first communication connection is established between the computing device and the web-based integrated development environment. With the first communication established, a second communication connection is established for real-time, bi-directional communication between the computing device and a language server instance of the web-based integrated development environment.

Abstract: A method includes receiving a set of text documents. The method also includes generating a summary of the set of text documents by a set of large language machine learning models. The method further includes generating a set of keywords from the summary by the set of large language machine learning models. The method additionally includes generating an image prompt from the set of keywords by the set of large language machine learning models. The method also includes generating a set of images from the image prompt by a text-to-image machine learning model. The method further includes generating a video clip from the set of images. The method additionally includes presenting the video clip.

Abstract: The invention relates to a method for mapping topics. The method includes obtaining terms, obtaining tokens from each term, and identifying a first and a second set of topics. Each of the topics represents one or more of the terms. The method further includes identifying first and second topic names for the first and the second sets of topics. For each topic, the tokens associated with the terms assigned to the topic are analyzed for relevance, and a token with a high relevance is selected as the topic name. The method also includes selecting one of the first and one of the second sets of topics to obtain first and second selected topics, determining, based on the one or more terms, a similarity value between each of the first and the second selected topics, and establishing a mapping between similar first and second selected topics.

Abstract: Certain aspects of the present disclosure provide techniques for vectorization of transactions including: receiving electronic transaction information of one or more transactions of a user; for each transaction of the one or more transactions: segmenting the electronic transaction information of the transaction into one or more transaction words; generating a second transaction description related to the transaction; and identifying a category of the transaction; generating, based on the corresponding identified categories of the one or more transactions, a set of transaction history data of the user; providing the set of transaction history data of the user as an input to a machine learned model trained to output a set of word embedding vectors; determining, based on an output of the machine learned model comprising a set of word embedding vectors, a set of similar merchants; and providing the set of similar merchants for display to the user.

Abstract: The present disclosure includes computer implemented techniques for providing a survey to a user. In one embodiment, a software application receives an audio stream including utterances spoken by the user interacting with a voice-user interface of the application. The application then determines a set of paralinguistic features from the audio stream and estimates at least a first attribute of the user based on the set of paralinguistic features. The application selects survey content based on a value of the first attribute and transmits a survey including the selected survey content to the user.

Abstract: Systems and methods of generating synthetic training data for machine learning models. First, line items in source documents such as bills, invoices, and or receipts are identified and labeled. The identification and labeling generate labeled documents. Then, in the labeled documents, the line items are augmented by adding, deleting, and or swapping line items to generate synthetic training documents. An addition operation randomly selects one or more line items and adds the selected line item(s) to the same labeled document or another labeled document. A deletion operation randomly deletes one or more line items. A swapping operation randomly swaps line items in a single labeled document or across different labeled documents. These operations can generate synthetic labeled documents of any length, which form synthetic training data for training the machine learning models.

Abstract: The instant systems and methods are directed to a contextual bandits machine learning model configured to enable granular synchronized ecosystem personalization and optimization. The system and methods determine an objective and feed the objective and one more lifecycle model propensity scores as inputs to the contextual bandits machine learning model. The contextual bandits machine learning model then generates one or more potential weighted model rewards, wherein each potential weighted model reward includes at least a desired user action, a weight, a channel, and an expected change to the objective, and selects a weighted model reward that optimizes the objective. An action recommendation is subsequently transmitted to a user device based on the weighted model reward, wherein the action recommendation is presented in a selected channel associated with the weighted model reward. Feedback associated with the action recommendation is collected and used in training and fine-tuning of the model.

Abstract: Techniques are disclosed for dynamically generating a data set representative of search results in response to a query and using the data set to accurately rank search results in response to a domain specific search query. Upon receiving the search query, features of the query and features of each search result are extracted. A relevance ranking may be assigned to each search result based on a comparison of the features of the query and each search result. The relevance ranking of each search result may be adjusted based on metrics related to user interactions. A data set may be created which includes the query, search results, extracted features, and metrics. The data set may be used to train a machine learning model to accurately determine a ranking of search results in response to a subsequent search query.

Abstract: Certain aspects of the present disclosure provide techniques for detecting and preventing web service usage anomalies. Embodiments include forecasting, based on a model, a number of resource instances for one or more web services for a time period. Embodiments include receiving, after the time period has elapsed, a detected number of resource instances for the one or more web services for the time period. Embodiments include comparing the detected number of resource instances to the forecasted number of resource instances. Embodiments include determining, based on the comparing, a usage anomaly. Embodiments include determining an impact of the usage anomaly. Embodiments include outputting an indication of the usage anomaly and the impact of the usage anomaly.

Abstract: The present disclosure provides techniques for recommending vendors using machine learning models. One example method includes receiving transaction data indicative of a transaction, identifying, based on the transaction data, an associated merchant of one or more merchants and an associated time window of one or more time windows, receiving historical transaction data indicative of one or more historical transactions, wherein the one or more historical transactions are associated with the associated merchant and the associated time window, generating features based on the transaction data and the historical transaction data, and determining, using a classification model, that the transaction is fraudulent, based on the generated features.

Abstract: Certain aspects of the present disclosure provide techniques for operation of a feature management platform. A feature management platform is an end-to-end platform developed to manage the full lifecycle of data features. For example, to create a stateful feature, the feature management platform can receive a processing artifact from a computing device. The processing artifact defines the stateful feature, including the data source to retrieve event data from, when to retrieve the event data, the type of transform to apply, etc. Based on the processing artifact, the feature management system generates a processing job (e.g., the API defines a pipeline), which when initiated generates a vector that encapsulates the stateful feature. The vector is transmitted to the computing device that locally hosts a model, which generates a prediction that is transmitted to the feature management platform. Subsequently, the predication and stateful feature can be transmitted to other computing devices.

Abstract: Certain aspects of the present disclosure provide techniques for detecting errors in account numbers. One example method generally includes receiving, from a user device, an entered number associated with a user and determining, based on a first portion of the entered number, an entity associated with the entered number. The method further includes obtaining, from an account number database, a plurality of account numbers associated with the entity and generating, from the plurality of account numbers, an account number matrix. The method further includes attempting to solve a multiplication equation of the account number matrix, wherein a solution of the multiplication equation is a vector of constants, upon determining a solution to the multiplication equation, determining whether the entered vector is a valid number for the entity and upon determining the entered vector is a valid number for the entity, storing the entered number in the account number database.

Abstract: Systems and methods that may be used to provide in-context editing of a webpage-based user interface (UI).

Abstract: A browser executing on a computer terminal associated with a merchant receives a payment request for a purchase by a customer from the merchant. The computer terminal transmits, over a communications network to a mobile communication device associated with the customer, a push notification including the payment request and a set of instructions. The payment request indicates an identifier and amount of the purchase. The set of instructions causes the mobile communication device to activate a card reader using a mobile payment app, present the purchase amount to the customer on a touch-sensitive display of the mobile computing device, receive an acceptance of the purchase amount from the customer via the touch-sensitive display, and authorize the card reader to process payment for the purchase amount based on the acceptance. The computer terminal receives, over the communications network, a confirmation of the processed payment from the mobile computing device.

Abstract: A method and system assists experts associated with an electronic bookkeeping system to increase a rate at which users select to receive the services of the expert. The method and system retain information regarding the selection rates of a plurality of experts, and the profiles of the plurality of experts. The method and system trains an analysis model with a machine learnings process to learn how the attributes in the profiles relate to the selection rates. The method and system then utilizes the analysis model to predict changes to the profile that an expert can make to increase the selection rate of the expert. The method and system outputs recommendation data to the expert recommending one or more changes in the expert's profile that will likely result in an increase in the expert's selection rate.

Abstract: Certain aspects of the present disclosure provide techniques for training and using machine learning models to extract key-value sets from a document. An example method generally includes identifying regions of a document including key-value sets corresponding to inputs to a data processing application based on a first machine learning model and an electronic version of the document. One or more keys and one or more values are identified in the document based on a second machine learning model. One or more key-value sets are generated based on matching keys of the one or more keys and values of the one or more values in the region of the document. The one or more key-value sets are provided to a data processing application for processing.

Abstract: This disclosure provides systems, methods and apparatuses for converting natural language text in financial documents to mathematical operations for a financial management program. In some implementations, a computing device may obtain a first segment of computer readable text associated with a text capture in a financial document, parse only a portion of the first segment to generate a parsed segment, and determine translation information associated with the parsed segment to translate the parsed segment. The computing device may also store the parsed segment and the translation information in a data structure in memory, translate the parsed segment in the data structure based on the translation information, and output one or more computer readable mathematical operations corresponding to the translated segment. In this manner, the computing device may output the one or more computer readable mathematical operations without parsing all of the segment.