Abstract: Certain aspects of the present disclosure provide techniques for executing structured query language queries having a schema associated therewith against an application programming interface using natural language. The schema can be chunked such that embeddings of the resulting chunks are stored in a vector store. Schemas (or subschemas) generated using on or more chunks of the vector store may be provided to a large language model along with a NL query to generate a structured query language query which may be executed against the application programming interface. This allows large language models to produce structured query language queries, such as GraphQL queries even if a GraphQL schema is too large to be provided to the model as context. Aspects disclosed herein also provide techniques for client code generation and client software development kit generation.

Abstract: A computer-implemented method and system having computer-executable instructions stored in a memory for processing user behavior features by neural networks to identify user segments. The method includes receiving user datasets from a database along with respective user identifiers, retention labels, static user features and interactive user features associated with an online product during a time period. A first neural network processes the interactive user features to generate a time distributed concatenation representation. A second neural network is configured to generate a vector by embedding the time distributed concatenation representation and the static user features through an embedding layer. The second neural network is configured to process the vector through a plurality of layers. A cluster model is used to determine user segments based on values extracted from nodes of a second to last layer of the second neural network.

Abstract: A method for automatically recommending to a user of a software application one or more categories of a plurality of different categories of tax deductible expenses includes providing input data to a trained machine learning model and receiving output from the trained machine learning model based on the input data. The output includes a recommendation for the user that includes (i) one or more categories of the plurality of different categories of tax deductible expenses; and (ii) a plurality of examples of tax deductible expenses for each of the one or more categories. The method includes receiving feedback from the user on the recommendation and generating updated training data for the trained machine learning model based on the feedback.

Abstract: A processor may identify a plurality of data sets subject to upcoming update processing in a next update cycle. For each of the plurality of data sets, the processor may determine a probability that data included in the data set has changed since a most recent update processing. The processor may exclude a first subset of the plurality of data sets having respective probabilities below a threshold value from the upcoming update processing until the respective probabilities are determined again in a subsequent update cycle. The processor may perform the upcoming update processing on the plurality of the data sets not included in the first subset, where the upcoming update processing may include obtaining updated data from at least one external data source.

Abstract: A method of customizing a personal software program for a user, comprising collecting attributes of each of a plurality of users registered to access the personal software program, generating a plurality of user profiles based on the collected attributes of the users, monitoring the interactions or non-interactions of the users with a module of the personal software program, deriving a reference user profile from the plurality of user profiles, linking the module with the reference user profile based on the monitored interactions or non-interactions of the users with the module, acquiring attributes of the user, generating a user profile based on the acquired attributes of the user, comparing the user profile to the reference user profile, determining a match between the user profile and the reference user profile based on the comparison, and setting the availability of the module to the user.

Abstract: Systems and methods are provided to structure event description data.

Abstract: A method for using shareable and nested transaction on hash chains includes storing transaction data of a transaction of a hash chain. A lock block is appended to the hash chain. Appending the lock block includes setting a tail block identifier of the hash chain from a preceding tail block of a preceding transaction to the lock block. A data block is appended to the hash chain. Appending the data block includes setting the tail block identifier of the hash chain to the data block. The method further includes removing the transaction data from the transaction without invalidating the hash chain. The method further includes appending an updated data block to the hash chain to update the transaction with updated transaction data.

Abstract: After a host client establishes a multimedia stream with a guest client, host data is received from a host application. A state machine is updated using the host data. The host application executes on the host client. Guest data is received from a guest application. The state machine is updated using the guest data. The guest application executes on the guest client. Transaction data is propagated between the host application and the guest application. The transaction data is presented with the multimedia stream. The transaction data includes the host data and the guest data. Provider data is generated responsive to updating the state machine with the host data and the guest data. The provider data is sent to the guest client. The provider data is presented with the multimedia stream by the guest application on the guest client.

Abstract: A method and system that proactively generate alerts for updating a scraping script to avoid scraping script errors. A predetermined number of webpages targeted by the scraping script are randomly sampled. The scraping script is appended to each webpage in the sample. A structured list of text fragments across the webpages with the appended script is generated. At predetermined time intervals, a fresh set of webpages is sampled, the scraping script is appended to the webpages, and a new structured list is generated. If the new structured list and the previous structured list do not match, the webpages may have been changed and the scraping script may have to be updated. An alert is generated indicating that such update is required and may include a location of the mismatch. Therefore, scraping script errors are proactively detected and can be rectified before an actual error occurs and propagates.

Abstract: A method implements private categorization using shared keys. The method includes selecting an encryption key, encrypting a transaction vector, generated from a transaction record, with the encryption key to generate an encrypted transaction vector, and receiving an encrypted category vector generated by a classifier model, corresponding to the encryption key, from the encrypted transaction vector. The method further includes decrypting a category from the encrypted category vector with a decryption key corresponding to the encryption key and presenting the category.

Abstract: Systems and methods for automated techniques that generate queryable database table ownership attribution information in real-time. In addition to generating ownership attribution information, system and methods provide a novel framework for creating bi-partite graphs and generating insightful graph data.

Abstract: In one or more embodiments, transaction data between multiple users and multiple merchants is retrieved. The retrieved transaction data is aggregated for each of the multiple users and each of the multiple merchants. The aggregated data may then be normalized. An example normalization process may include income normalization, where a user's total transaction amount at a particular merchant is normalized by the user's income. Other forms of normalization may also be employed. Using the normalized data, user-merchant affinity may be predicted based on collaborative filtering models, cascading tree models, and or cosine similarity models. A recommendation engine may provide personalized advertisements based on the predicted affinity. Because of the normalization of the data, the affinity and therefore the recommendation is less biased toward larger merchants.

Abstract: A method comprising generating, during multiple user sessions of a first user with a software application, first clickstream data from the multiple user sessions, and extracting, from the first clickstream data, a first plurality of task instances of the first user performing a first plurality of tasks. The method also includes decomposing, from the first clickstream data, each task instance of the first plurality of task instances into a first plurality of steps to obtain a first plurality of decomposed task instances. The first plurality of steps in the first plurality of decomposed task instances are each associated with a timestamp. The method further includes training a first user model with the first plurality of decomposed task instances to learn a user optimal order to perform the first plurality of tasks and presenting, to the first user, the user optimal order to perform the first plurality of tasks.

Abstract: Certain aspects of the present disclosure provide techniques for providing sentiment analysis of content. In order to determine the overall sentiment of content, a request is received by a sentiment analyzer, which then identifies a content identification number and retrieves comments associated with the content identification number. The sentiment analyzer pre-processes the comments, which includes removing all personal identifying information from the comments. The sentiment analyzer sends the pre-processed comments to a natural language processing service, and in turn, receives sentiment indications corresponding to the comments provided. Based on the sentiment scores, the sentiment analyzer generates a sentiment analysis and displays the sentiment analysis in the graphical user interface generated by the sentiment analyzer.

Abstract: Methods, computer systems and computer program product are provided for retrieving contextually relevant documents in near real time. When text data it's received from an application, the text data is processed through a text segmentation model to generate a set of documents. Each document corresponds to a segment of the text data. A first vector representation is generated for a first document of the set of documents. A machine learning process compares the first vector representation and a set of vector representations for a set of documents within a data repository to determine a subset of the documents. A composite rank is generated for each respective document of the subset. The subset of documents is then presented through an interface, sorted according to the respective composite ranks.

Abstract: Certain aspects of the present disclosure provide techniques for generating a unified knowledge graph. In one example, a method includes receiving entity data from a data source comprising a plurality of entities; forming a plurality of type-specific groups of entity data based on the received entity data; for each respective type-specific group of entity data of the plurality of type-specific groups of entity data; disambiguating the entity data within the respective type-specific group of entity data; creating a plurality of entity relationships based on the disambiguated entity data; and exporting the plurality of entity relationships to a type-specific subgraph; and forming a unified knowledge graph based on a plurality of type-specific subgraphs, wherein each type-specific subgraph of the plurality of type-specific subgraphs is associated with a single type-specific group of entity data of the plurality of type-specific groups of entity data.

Abstract: A method may include executing a baseline classifier on unreviewed transaction features of an unreviewed transaction record to obtain a baseline account identifier, and executing a comparison model on (i) an unreviewed transaction vector of the unreviewed transaction record and (ii) reviewed transaction vectors to obtain comparison scores. The reviewed transaction vectors may correspond to reviewed transaction records each having a user-approved account identifier. The method may further include selecting, using the comparison scores, a reviewed transaction record. The reviewed transaction record may correspond to a comparison score. The comparison score may correspond to a user-approved account identifier of the reviewed transaction record.

Abstract: Certain aspects of the present disclosure provide techniques for adjusting access control policies of access controlled systems, such as techniques for identifying a vulnerability or for identifying parameters and values achieving a specified result from a system whose access is controlled by the policy. Requests to the system can be made using a testing system that executes test scripts using avatars having various parameter types and values. The avatar information and results of the test scripts are provided as training data to a machine learning model training system to generate a model that provides recommendations for parameter types and values likely to achieve a particular result. The recommendations are used to execute the test script to determine results including a rate of success for the recommended parameters and/or values. Various actions, such as adjusting or adding a rule to an access control policy, can be performed based on the results.

Abstract: Systems and methods are described for automatically documenting queries and dynamically populating interactive graphical user interfaces with query recommendations. A computing system receives an initial query from an interactive graphical user interface and asynchronously parses the query for strings matching predetermined phrases. In response to determining that the initial query recites strings matching the predetermined phrases, the system extracts metadata and identifies a table name in the initial query, and modifies a table data in key-value data structure corresponding to the table. Subsequent queries related to the initial query cause the system to asynchronously populate the graphical user interface with query recommendations related to the initial query.

Abstract: Certain aspects of the present disclosure provide techniques for medoid-based data compression. One example method generally includes receiving item data indicative of one or more items, determining one or more medoids based on the item data, determining, for each item of the one or more items, a corresponding medoid based on the one or more medoids, identifying, for each item of the one or more items, a difference between the item and the corresponding medoid for the item, storing the one or more medoids, and storing, for each item of the one or more items, the identified difference between the item and the corresponding medoid.