Abstract: Systems and methods include reception of a first request to copy a database to a second tenant. In response to the first request, first metadata associating the second tenant with a first shard and a second shard of a database table is generated. A second request to access the first shard is received from a requestor associated with the second tenant and, in response to the second request, it is determined that the first shard is not stored in any of a plurality of storage nodes of a storage layer. In response to the determination, an instruction is issued to recover the first shard to a first storage node from a first backup location, and an identifier of the first storage node is returned to the requestor.

Abstract: A system receives transaction data from payment devices of a user. The system generates a transaction profile of the user based on the received transaction data. Based on the transactional parameters, the system determines a community of the user. The system further receives one or more predefined sub-groups of the community from a database. The one or more sub-groups define subsets of activities, geographic locations, and times. The system identifies one or more rules setting limits on the transactional parameters. Absent receiving additional user interactions, the system generates a suggested community for the user as a function of the one or more rules, the activities, geographic locations, and times of the one or more sub-groups of the community. The system generates a suggested activity to the user based on the suggested community.

Abstract: In one approach, filesets to be backed up are divided into partitions and snapshots are pulled for each partition. In one architecture, a data management and storage (DMS) cluster includes a plurality of peer DMS nodes and a distributed data store implemented across the peer DMS nodes. One of the peer DMS nodes receives fileset metadata for the fileset and defines a plurality of partitions for the fileset based on the fileset metadata. The peer DMS nodes operate autonomously to execute jobs to pull snapshots for each of the partitions and to store the snapshots of the partitions in the distributed data store.

Abstract: Methods and systems are presented for assisting a user to identify and evaluate features for use in a machine learning model configured to perform a task. Based on graph data associated with a graph data structure, a user interface is provided on a device. Based on user inputs received via the user interface, a feature candidate for the machine learning model is determined. The feature candidate is associated with a particular way of traversing the graph data structure to obtain attribute values associated with one or more vertices and/or one or more edges in the graph data structure. Based on the attribute values, a value corresponding to the feature candidate can be calculated. The value can be used to evaluate the effectiveness of the feature candidate in performing the task. The feature candidate can then be incorporated into the machine learning model as one of the input features.

Abstract: Techniques for adaptive machine learning training via in-flight feature modification are described. A training monitor captures training data during the training of a machine learning model, and a metric generator creates metrics such as feature importance metrics based on the data. A rule evaluation engine determines whether any modification conditions are met for any of the features based on the metrics, and based on such a determination can cause the in-flight training job to be modified.

Abstract: A content management system generates a personalized vocabulary for a user by analyzing content items associated with a namespace of the user. The content management system receives a query. The content management system determines that the at least one search term does not occur at least a threshold number of times in the personalized vocabulary. The content management system identifies a prefix of the at least one search term. The content management system parses the personalized vocabulary based on the prefix to identify a set of search term options. The content management system generates a personalized ranking of the search term options based on (a) an edit distance; (b) a frequency of each search term option's occurrence in the personalized vocabulary; or (c) a combination of (a) and (b). The content management system presents at least a top ranked search term option to the user.

Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for filtering vehicle information. For instance, the method may include receiving a vehicle search request from a user device, the vehicle search request including conditions with corresponding weights. The method may also include, in response to receiving the vehicle search request, forming a search query based on the conditions and the weights of the vehicle search request; obtaining vehicle information; filtering the vehicle information based on the search query to obtain a result set and a partial match set; and transmitting a search result message based on the result set and the partial match set to the user device.

Abstract: A method and system for determining rank positions of elements displayed on a search engine results page (SERP) by a ranking system. During a training phase of the ranking system, an indication of user interactions associated with a first ranked list of elements is acquired. The elements of the first ranked list were visually displayed on a first SERP. A score for a first content element is determined based on a size of the first content element and a ranking of the first content element. The ranking system is trained, based on the score, to predict a predicted usefulness score for the first content element. During an in-use phase of the ranking system, a ranked list of elements is determined based on a query. The ranking system determines a ranked position for a content element in the ranked list. A SERP based on the ranked list is output.

Abstract: Embodiments of the present invention provide a computer system a computer program product, and a method that comprises converting the retrieved data to a uniform syntax for data assessment; performing a query on a plurality of external data sources for additional information associated with the converted data; analyzing a plurality of indicative markers associated with the retrieved data and the additional information; generating a plurality of machine learning models associated with the converted data based on the analysis of each indicative markers within the plurality of indicative markers; dynamically selecting at least one generated machine learning model within the plurality of generated machine learning models associated with the retrieved data based on an analysis of the plurality of indicative markers associated with the retrieved data and the additional information; and automatically verifying an accuracy value associated with the at least one selected generated machine learning model.

Abstract: This application relates to targeted search of backup data. A data storage system can provide a targeted search of backup data based on events associated with the backup data. Upon receiving a search query that identifies an event stored in an event database, the data storage system can determine an event location and an event time associated with the identified event by accessing the event database and output a search result including a portion of the backup data that is associated with the event location and the event time.

Abstract: A media application determines, based on pixels of images or videos from a collection of media items, clusters of media items such that the media items in each cluster have a visual similarity, wherein the collection of media items is associated with a user account. The media application selects a subset of the clusters of media from corresponding clusters of media items based on the media items in each cluster having a visual similarity within a range of threshold similarity values. The media application causes a user interface to be displayed that includes the subset of the clusters of media.

Abstract: System and method for associating user-entered consumable item description to an entry in a consumable item database. In one embodiment, formally structured restaurant menu item is matched to a large database of food items that has been constructed via crowd-sourcing. A novel, practical, and scalable machine learning solution architecture, consisting of two major steps is utilized. First a query generation approach is applied, based on a Markov Decision Process algorithm, to reduce the time complexity of searching for matching candidates. That is then followed by a re-ranking step, using deep learning techniques, to ensure matching quality goals are met.

Abstract: In one embodiment, a method includes receiving a user input including an ambiguous mention by a user from the user's client system, analyzing the user input to identify intents and slots based on a natural-language understanding module, where at least one slot is an ambiguous slot corresponding to the ambiguous mention, identifying candidate entities corresponding to the ambiguous slot, ranking the candidate entities based on the user's user profile data, sending to the user's client system instructions for prompting the user to select a candidate entity from a set of candidate entities having a rank greater than a threshold rank, where the selected candidate entity is resolved to the ambiguous slot, and storing the selected candidate entity together with the ambiguous mention as a mention-entity pair as part of the user profile data responsive to receiving the selection from the user.

Abstract: System extracts backup metadata, comprising system committed change numbers, system change numbers, types, and database version identifiers, for backup copies. System generates data structure, comprising start system change numbers, based on minimums of system committed change numbers, end system change numbers, based on maximums of system change numbers, database version identifiers, and identifiers for archive log backup copies. System identifies dependent system change numbers, based on start system change number to end system change number for backup copy corresponding to database version identifier. System identifies, in data structure, backed-up system change numbers, based on start system change numbers to end system change numbers for archive log backup copies corresponding to database version identifier, which are included in dependent system change numbers.

Abstract: Systems and methods are disclosed for processing and executing queries in a data intake and query system. The data intake and query system receives a query identifying a set of data to be processed and a manner of processing the set of data. The data intake and query system identifies buckets that are to be searched and search nodes to execute the query. The data intake and query system maps the identified buckets to the search nodes and executes the query using the identified bucket and search nodes.

Abstract: A system for receiving and propagating efficient search updates includes one or more processors configured to receive, from a first external system via a network, a first entity change request to modify data in an entity associated with the first external system. The first entity change request is saved in an entity store. The received entity change request is pushed from the entity store to an event publisher for forwarding to a streaming service. The first entity change request is classified and forwarded, from the streaming service, to a search index database. The search index is then updated based on the classified entity change request.

Abstract: Embodiments of systems and methods for a search system that is adapted to utilize a family search operator are disclosed. Such a family search operator may return all documents that match the inner expression encompassed by the family search operator or having a family member that matched the inner expression of the family search operator.

Abstract: Provided are a method, a system, and a non-transitory computer readable record medium for providing a multi-profile. A multi-profile providing method may include identifying a relationship between a first member in an online social networking service with each of a plurality of other members in the online social networking service; classifying the plurality of other members into a plurality of groups based on the relationship between the first member and each of the plurality of other members; setting a plurality of profiles of the first member for the plurality of groups, respectively; and in response to a request to provide profile information of the first member being received from a second member among the plurality of other members, identifying one of the plurality of groups to which the second member belongs, and providing the second member with a first profile of the first member that is set for the group to which the second member belongs, among the plurality of profiles.

Abstract: A backup management system may include a data management server, a warm-tier data store, and a cold-tier data store. Snapshots may be captured from various client devices. A data block stored in the warm-tier data store may be referenced by multiple backup snapshots and/or referenced by one or more users. When a data block's total reference count is equal to the cold reference count or equal to or less than a threshold total reference count, the data management server may determine that the data block is ready to be migrated to the cold-tier data store. The data management server may send the data block into a candidate queue. In the queue, data blocks with similar retention periods or similar expected restoration may be grouped as a unit. The unit may be transmitted to the cold-tier data store in a single write request.

Abstract: The present invention is related to a method for processing a question in natural language received at a server (2), comprising performing by a processing unit (21) of the server (2) steps of: (a) for each n-gram of the question which is not a stop word, from at least one given knowledge base of entities linked by relations, identifying as initial entities and initial relations the entities and relations of the knowledge base matching said n-gram; (b) generating a set of possible queries for entities or relations of said given knowledge base, as a function of the initial entities and initial relations identified for all the n-gram of the question; (c) ranking each query of said set of possible queries as a function of at least one predetermined criterion, so as to identify a top-ranked possible query; (d) executing said top-ranked possible query, and returning the result entities or relations.