Abstract: This disclosure addresses deficiencies in existing methods for analyzing spikes in time-series data, particularly when dealing with vast document repositories. A method includes receiving a user specification of objects of interest, and by subsequently identifying spikes of mentions of these objects in the documents. The method includes retrieving metric data and context data related to mentions of objects of interest in relevant documents from a repository, both from spikes and other time intervals. By analyzing these documents, it is possible to pinpoint the key factors driving the spikes. Finally, use of an LLM provides capabilities to generate comprehensive explanations. This is achieved by submitting one or more prompts to LLM(s), where the prompts incorporate the specification of the objects of interest (or a reformulation thereof), the identified driving factors and a number of representative documents connected to the key driving factors.

Abstract: This disclosure addresses deficiencies in existing methods for analyzing spikes in time-series data, particularly when dealing with vast document repositories. A method includes receiving a user specification of objects of interest, and by subsequently identifying spikes of mentions of these objects in the documents. The method includes retrieving metric data and context data related to mentions of objects of interest in relevant documents from a repository, both from spikes and other time intervals. By analyzing these documents, it is possible to pinpoint the key factors driving the spikes. Finally, use of an LLM provides capabilities to generate comprehensive explanations. This is achieved by submitting one or more prompts to LLM(s), where the prompts incorporate the specification of the objects of interest (or a reformulation thereof), the identified driving factors and a number of representative documents connected to the key driving factors.

Abstract: The present disclosure comprises systems and methods to mine association rules from a dataset provided in the input. This comprises methodologies for optimizing the dataset for efficient computation of association rules, other than methodologies for handling partially true data. Moreover, it includes methodologies for evaluating the mining process automatically and removing uninteresting rules. In addition, it includes methodologies for integrating experts in the evaluation of the rules. Finally, methodologies to automatically detect outliers, correct outliers, update truth values and complete missing data in the original dataset. The overall methodology is completely automated and provides numerous tuning parameters to fit most of the use cases, including a default value for each of the tuning parameters to simplify its usage.

Abstract: Methods and systems for enriching an information system containing information about companies with additional competitor information. The information system, which could be a database, a knowledge base, or a knowledge graph, is assumed to contain information about a plurality of single companies, the information comprising data such as industry codes, competitors, and possibly also keywords for each company. The disclosed methods determine new competitor pairs by combining (i) the generation of new competitor candidate pairs by inference from existing competitors and other company-specific knowledge with (ii) the validation of such competitor candidates pairs by checking for joint occurrence in documents of a document repository.

Abstract: The present disclosure comprises systems and methods to convert Existential Datalog source code into Differential Dataflow source code, whereby databases or knowledge graphs, some of whose relations are defined from other relations using Existential Datalog rules can be maintained incrementally.