Abstract: A data processing method includes: receiving a data processing request carrying a query statement; converting the query statement into a corresponding relational algebra tree based on the data processing request; determining an operation type corresponding to the query statement based on the relational algebra tree; delivering the query statement to a first database in response to the operation type being a first type; and completing the data processing request in the first database based on the query statement.

Abstract: One embodiment of the present invention sets forth a technique for sampling from a dataset. The technique includes determining a plurality of embeddings for a plurality of data points included in the dataset. The technique also includes populating a tree structure with the plurality of embeddings by generating a first node that stores a first set of embeddings included in the plurality of embeddings and generating a first plurality of nodes as children of the first node, where each node in the first plurality of nodes stores a different subset of embeddings in the first set of embeddings. The technique further includes sampling a subset of embeddings from the plurality of embeddings via a traversal of the tree structure, and generating a sampled dataset that includes a subset of data points corresponding to the subset of embeddings.

Abstract: A method may include generating, for a heterogeneous graph comprising a plurality of vertex tables and/or edge tables, an adjacency structure including a vertex adjacency structure specifying a plurality of neighboring vertices in the heterogeneous graph and an edge adjacency structure specifying a plurality of neighboring edges in the heterogeneous graph. A graph processing algorithm operating on the heterogeneous graph may be executed based on the adjacency structure. Related systems and computer program products are also provided.

Abstract: Embodiments are disclosed for managing text co-editing in a conflict-free replicated data type (CRDT) environment. A method of co-editing management includes detecting a burst operation to be performed on a sequential data structure being edited by one or more client devices. A segment of the sequential data structure associated with the burst operation is determined based on a logical index associated with the burst operation. A tree structure associated with the segment is generated, where a root node of the tree structure corresponds to the burst operation. A global index for the root node of the tree structure is determined and an update corresponding to the burst operation, including the root node and the global index, is sent to the one or more client devices.

Abstract: An indexer retrieves a set of messages generated by a given data source of a plurality of data sources from a data storage. The indexer also processes the set of messages to generate processed data for the given data source and stores the processed data in a cache. The processed data includes a data file with data from the given data source and an index file identifying a location of the data file. The indexer determines when the processed data for the given generation source reaches a threshold size. The indexer also stores the data file of the processed data in the data storage and updates the index file for the processed data to identify the data storage as the location of the data file.

Abstract: A machine analyzes an entity resolution data graph using a curated peer review set of data structures. The machine uses independent peer data structures that model similar or related yet different universes and entities. These data structures may include other entity resolution data graphs or file-based data structures. The machine first performs candidate screening to determine which of these data structures meet the requirements for use in the analysis. The machine then selects from among the candidate peer data structures with which to perform the analysis. Finally, the entity resolution data graph is analyzed using queries against the selected peer data structures to provide an analysis of the quality of its data graph.

Abstract: Arrangements for controlling data retrieval are provided. In some aspects, a data request may be received by a computing platform. A pre-fetch engine may be executed to analyze the data request and generate, using a machine learning model, a pre-fetch template identifying data sets responsive to the request. The pre-fetch template may be transmitted to one or more data repositories and at least one data repository may transmit response data sets to the computing platform. An issue in the mesh network through which the data sets are transmitted may be detected and the data sets may be stored at a data silo associated with a node of the mesh network. An alternate transmission path may be generated and the data may be transmitted from the data silo of the node to another node in the mesh network based on the alternate transmission path.

Abstract: One example method includes generating a fingerprint:tag dictionary that includes a group of fingerprints and a group of tags, and the fingerprint:tag dictionary identifies, for each fingerprint, the tag or tags which include that fingerprint, computing a similarity matrix based on the fingerprint:tag dictionary, and the similarity matrix identifies, for each pair of tags in the fingerprint:tag dictionary, a relative similarity of the tags in the pair to each other, running a clustering algorithm to identify groups of similar tags in the similarity matrix, and deduplicating, based on the groups of similar tags, respective data associated with the fingerprints.

Abstract: Systems and methods for searching datasets and classifying datasets are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a test dataset from a client device and generating a test data model output using a data model, based on the test dataset. The operations may include processing test data model output by implementing an encoding method, a factorizing method, and/or a vectorizing method. The operations may include retrieving a reference data model output from a dataset index, based on a reference dataset. The operations may include generating a similarity metric based on the reference data model output and the test data model output. The operations may include classifying the test dataset based on the similarity metric and transmitting, to the client device, information comprising the classification.

Abstract: Aspects of the present disclosure provide techniques for predicting content relevant to questions based on reference links. Embodiments include receiving a set of question and answer (Q/A) pairs and identifying a set of references in the set of Q/A pairs that link pairs of Q/A pairs of the set of Q/A pairs. Embodiments include identifying popular Q/A pairs of the set of Q/A pairs based on the set of references. The popular Q/A pairs may be referenced by a subset of the set of Q/A pairs and each respective Q/A pair of the subset of the set of Q/A pairs may comprise a respective question of a plurality of questions. Embodiments include training a model based on the plurality of questions, the popular Q/A pairs, and the set of references, to predict Q/A pairs of the set of Q/A pairs that are relevant to a given question.

Abstract: Database transaction records that are received for committing data to a database may be associated with one or more validation tasks. When one of the validation tasks fails, the fault is detected and processing of the transaction record is halted. Instead of terminating the transaction record and requiring the submitting system to reinitiate the process, the system may use a mapping table to determine whether an automatic resubmission is possible. A new transaction record may be generated that copies an invocation context from the original transaction record, and portions of the transaction payload may be copied to the new transaction record with changes that ensure the new transaction record will pass the validation tasks. The new transaction record can then be submitted through the same interface that received the original transaction record, and the original transaction record can be removed from a transaction data store.

Abstract: An information processing method, an electronic device, and a storage medium are provided, which relate to the field of artificial intelligence technologies such as big data, knowledge graphs, deep learning and the like. The method includes: determining a first independence relationship according to a plurality of variables and values respectively corresponding to the plurality of variables, wherein the first independence relationship includes: at least two variables of the plurality of variables being relatively independent; determining a first adjustment scheme according to the plurality of variables and the first independence relationship; adjusting the first independence relationship according to the first adjustment scheme, to obtain a second independence relationship; and obtaining a causal relationship information processing result according to the second independence relationship.

Abstract: System and methods are presented for associating a user-posted content item with an interest node of an interest taxonomy. A corpus of content items and an interest taxonomy are maintained. The interest taxonomy comprises interest nodes organized in a hierarchical organization, each node having a text label descriptive of the interest node. Additionally, the content items of the corpus are associated with one or more interest nodes of the interest taxonomy. Upon receiving a user-posted content item, feature sets of the received content item are generated, these feature sets based on features and/or aspects of the received content item. After generating at least one feature set, the at least one feature set is provided to an interest prediction model that generates candidate interest nodes for the user-posted content item. At least some of the candidate interest nodes are associated with the user-posted content item in the corpus.

Abstract: One or more embodiments of the invention is a medium recommendation system for recommending media or sets of media in a game that proceeds as a user selects media from a possessed medium group constructed to include D media and places the media in a game field, the recommended media or sets of media being media or sets of media to be added to a medium in order to construct at least a portion of the possessed medium group from the medium, the medium recommendation system including: an input acceptance unit that accepts the input of a single medium among the T kinds of media; a table storage unit that stores first tables; and a medium recommendation unit that is capable of outputting, as recommendation information, media or sets of media with which the single medium accepted by the input acceptance unit is associated in the first tables.

Abstract: A method, non-transitory computer-readable storage medium and system is disclosed for using context-based dictionaries to search through multimedia data using input that specifies tags, words, phrases, descriptions, environments, emotions, sentiments, multimedia objects or content, or other relevant attributes. The system retrieves original content, analyzes and processes it, and presents to the user synchronized multimedia content and text content that is automatically tagged for searching.

Abstract: Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.

Abstract: Efficient evaluation of sets of resources is disclosed, including: determining a first plurality of representations from identifying information associated with a first set of resources; updating a first data structure corresponding to the first set of resources using portions of respective ones of the first plurality of representations; determining a second plurality of representations from identifying information associated with a second set of resources; updating a second data structure corresponding to the second set of resources using portions of respective ones of the second plurality of representations; and using the first data structure and the second data structure to compute a derived value associated with the first set of resources and the second set of resources.

Abstract: Techniques are described herein for enabling more computationally efficient organization of files within a cloud storage system. A method includes: receiving information identifying a document and a set of folders; for each folder in the set of folders, using a trained model to predict a similarity measure between the folder and the document; for each folder in the set of folders, determining a score for the folder based on the predicted similarity measure for the folder; selecting a candidate folder from the set of folders using the scores of the folders within the set of folders; and providing, on a user interface, a selectable option to associate the document with the candidate folder.

Abstract: A records retention cloud application service and automated document importing and tagging system and the automated document importing and tagging processes for records retention are disclosed. The automation of the file importing and tagging enables faster centralization and management of large numbers of records.

Abstract: Techniques for performing machine learning inference calls in database query processing are described. A method for performing machine learning inference calls in database query processing may include generating a query plan to optimize a query for batch processing of data stored in a database service, the query plan including a batch mode operator to execute a function reference and an execution context associated with the batch mode operator, executing the query plan to invoke a function associated with the function reference, wherein the function sends a batch of requests, generated using the execution context, to a remote service and obtains a plurality of responses from the remote service, and generating a query response based on the plurality of responses.