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.

The technology described herein provides for identifying matching documents for a search query using a bit vector search index. When a search query is received, a term is identified from the search index, and a number of bit vectors corresponding to the term are identified. Each bit vector comprises an array of bits in which at least one bit in each bit vector indicates that a corresponding document includes the term. Each bit vector also includes other bits indicating other documents include other terms. A determination is made that an unacceptable number of possible matching documents is likely to be returned. In response to the determination, a strengthening row bit vector is selected to reduce the number of possible matching documents. The identified bit vectors and the selected strengthening row are intersected to identify matching documents that contain the term.

A system and method are provided for indexing and mining content of multiple data sources. The method includes: providing a database of learned content of multiple data sources learned using text analysis, the learned content identifying one or more concepts to which a data source relates, wherein the concepts are cognitively associated with the data source and include concepts not explicitly referenced in the data source and providing an index of the learned content including associations between concepts with mappings between concepts and the multiple data sources. The method further includes receiving input of a query and using text analysis to analyze the query to determine one or more query concepts to which it relates and mining the indexed concepts in response to the query concepts to return a list of referenced data sources.

Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second subset.

Systems and methods are described for extracting data from digital documents, indexing the data, and providing a user interface for filtering the data and generating a document based on the filtered data. In one implementation, a method includes extracting data from one or more digital documents, the extracted data including elements of a first type, the elements of the first type including key-value pairs; indexing the extracted data; hosting a web-based application instance, the web-based application instance including a user interface for searching the indexed data and filtering elements of the first type based on rules defined by a user of the user interface; receiving rules for filtering the elements of the first type; and filtering the elements of the first type based on the received rules.

A database system performs queries on fields storing arrays of a database (i.e., array fields) using de-duplication indexes. The system generates de-duplication indexes for array fields. The de-duplication indexes include unique entries for corresponding distinct values stored by the array fields. The system uses the de-duplication indexes to perform efficient queries specifying corresponding array fields. The system may further generate de-duplication indexes corresponding one or more fields storing various types of values. In various embodiments, the system selects an optimal index from various indexes usable to execute a query, such as a de-duplication index and a conventional index.

The problem of ever-increasing huge volume of unstructured data, mainly documents, and within that the scanned documents, needs to have a solution to expedite the overall turnaround time in document centric business processing. Majority of these documents often do not strictly follow a specific format or a template, and creating a generic OCR solution, which would work on any kind of document format is needed to enhance overall efficacy of processes. Embodiments of the present disclosure provide system and method that extract tabular and text information from scanned documents. More specifically, method and system are provided to extract user filled tabular data, textual information, selected radio-buttons and checked checkboxes, stamps, barcodes from scanned copies of any filled form with or without any template being pre-defined or without any prior knowledge about format of input forms. The system converts extracted information in a structured form for further for analytics and reporting.

According to one embodiment, a data processing apparatus includes a processor provided with hardware. The processor extracts a first event data item, a second event data item, and a third event data item from input first document data. When a first relational data item indicating a presence of transitivity between the first event data item and the second event data item is extracted and a second relational data item indicating a presence of transitivity between the second event data item and the third event data item is extracted, the processor generates a third relational data item indicating a presence of a relation between the first event data item and the third event data item.

Embodiments described herein are generally directed to various use cases involving turning text data into actionable evidence. According to an example, text-based information relating to an issue associated with a product or service of a vendor is receive via a self-service SaaS portal and includes one or both of structured data and unstructured data. The text-based information is classified and analyzed by parsing out a first set of facts from the structured data. A second set of facts is identified by applying a taxonomy to the text-based information. A lookup value is created by aggregating the first and second sets of facts. Guidance, representing a proposed resolution of the issue, a recommended next troubleshooting step in connection with evaluation of the issue, or other guidance relating to the issue, is then extracted from a lookup table based on the lookup value.