Abstract: Systems and methods are provided for analyzing unstructured data to generate problem statements using retrieval-augmented generation techniques. Unstructured data representative of customer experiences may be obtained and analyzed to generate problem statements using a large language model augmented by a historical problem statement data set. Generated problem statements may include one or more attributes, including an identification of the source quotation from the unstructured data used as the basis for the generated problem statement. Generated problem statements may further include attributes indicating severity. The historical problem statement data set may be updated to include additional generated problem statements.

Abstract: This invention relates to consumer-generated media content. A first display area displays a marketing brand and a downcounter to show the time remaining for users to upload media items relating to the displayed brand. The first display area may also show the prize on offer and the brief that users should follow for that brand's competition. A gateway receives uploaded media items, from identified users, and which may display selected identified users' ideas related to an identified brand. A memory stores uploaded items and a processor accessible by an administrator to approve items for display in the second display area, or reject items. A second display area displays one or more uploaded and approved media items, each together with the respective brand, a downcounter to show the time remaining for access to that media item, and a score which may be derived from the number of times visitors have already accessed, voted for or commented about that media item.