A system, method and computer processor execute functions for grouping messages in a one-to-many messaging platform. Response text messages are received from a corresponding number of users in response to a first text message from a client. The first text message is transmitted via one or more messaging services that interface with the messaging platform, analyze one or more attributes associated with each of the response text messages are analyzed by the computer processor, to generate metadata representing one or more attributes associated with each of the response text messages or a user associated therewith. The metadata is stored for each of the response text messages in a database, the storing further including linking the metadata with the content of each of the plurality of response text messages.

A messaging system includes a messaging platform having one or more interfaces for communicating with one or more messaging services, the one or more messaging services transmitting client text messages associated with the client, and receiving user text messages from individual ones of the plurality of users. The messaging system further includes a machine learning module that executes one or more artificial intelligence algorithms, the machine learning module being configured to receive the user text messages, process the user text messages according to the one or more artificial intelligence algorithms and, based on one or more of variables associated with the user text messages, generate metadata for each of the user text messages, the metadata representing one or more attributes associated with content of each of the plurality of user text messages or a user associated with the user text messages.

A system and method for segmenting users of a messaging platform includes receiving a first text message from a client for transmission to a number of users that are registered with the messaging platform. The users are segmented based on one or more user attributes that are defined by static metadata that is generated when each user is registered with the messaging platform, and by dynamic information about user behavior using the messaging platform and/or the one or more second messaging services. The first text message is customized into a set of one or more second text messages according to the segmenting, the customizing providing a context to each of the set of second text messages, the context corresponding to the one or more user attributes.

A system and method for multivariate testing of messages to a subgroup in a one-to-many messaging platform. A client text message is generated for transmission to a number of users via one or more messaging services. A subset of users is defined according to one or more attributes of the text message or the users, and the client text message is transmitted only to users in the subgroup. The transmission is analyzed for performance metrics, such as actions or reactions by users in the subgroup, and based on the performance metrics, the message is optimized for transmission to the larger group of users. Optimization happens rapidly.

A service provider launches an index analysis computing system instance to evaluate indexes generated by a virtual computing system server to identify events encountered by the server. In response to a notification from an index subject indicating presence of a new index for the server, the index analysis computing system instance obtains the index from a datastore and evaluates the index to identify a log for the server that specifies data that can be used to identify the events. The index analysis computing system instance obtains, from a second datastore, the identified log and used the log to identify the events. The index analysis computing system instance provides event data corresponding to the events to a data processing datastore where the data can be aggregated and processed.

Embodiments of the invention include method, systems and computer program products for using a target similarity calculation to identify relevant content in a corpus of documents or records. The computer-implemented method includes creating, by a processor, a term frequency (TF) list for one or more documents of a corpus. The processor calculates an inverse document frequency (IDF) for each listed term. The processor calculates a TF-IDF for each listed term. The processor determines a similarity ranking for one or more documents of the corpus using a target similarity calculation using the TF-IDF for each listed term.

A system for handling a graphical representation of data associated with a question answering (QA) input document includes a memory having instructions therein and includes at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to derive, at least from a portion of the QA input document, first metadata regarding a context of the graphical representation of data. The at least one processor is also configured to execute the instructions to derive, at least from a portion of the graphical representation of data, tabular data. The at least one processor is also configured to execute the instructions to determine, at least in part by comparing at least a portion of the first metadata to existing table annotations from a QA knowledge base, how to incorporate the tabular data into the QA knowledge base.

A computer-implemented method for domain-specific full-text document search including indexing of documents set of steps and querying documents set of steps in which three main processes are involved: preparation of embeddings, indexing of a set of relevant documents, and querying of the indexed documents.

This invention relates to a system for and a method (100) of searching a collection of digital information (150) comprising a number of digital documents (110), the method comprising receiving or obtaining (102) a search query, the query comprising a number of search terms, searching (103) an index (300) using the search terms thereby providing information (301) about which digital documents (110) of the collection of digital information (150) that contains a given search term and one or more search related metrics (302; 303; 304; 305; 306), ranking (105) at least a part of the search query search result according to one or more predetermined criteria providing a ranked search result, and providing at least a part of the ranked search result (106), wherein the ranking provides robust likelihood for low count terms by using the one or more search related metrics (302; 303; 304; 305; 306). In this way, a method of and a system for information retrieval or searching is readily provided that enhances the searching quality (i.e. the number of relevant documents retrieved and such documents being ranked high) when (also) using queries containing many search terms.

Methods, and systems, including computer programs encoded on computer storage media for generating compressed representations from a co-occurrence matrix. A method includes obtaining a set of sub matrices of a co-occurrence matrix, where each row of the co-occurrence matrix corresponds to a feature from a first feature vocabulary and each column of the co-occurrence matrix corresponds to a feature from a second feature vocabulary; selecting a sub matrix, wherein the sub matrix is associated with a particular row block and column block of the co-occurrence matrix; assigning respective d-dimensional initial row and column embedding vectors to each row and column from the particular row and column blocks, respectively; and determining a final row embedding vector and a final column embedding vector by iteratively adjusting the initial row embedding vectors and the initial column embedding vectors using the co-occurrence matrix.