Abstract: The disclosed concepts relate to leveraging a generative language model for interactive constraint solving. For instance, a generative language model can be prompted to generate a constraint data structure that represents a user preference expressed in natural language. The constraint data structure can be parsed to extract constraint parameters that can be programmatically solved by a constraint solver. The generative language model can also be prompted to generate constraint-checking code that can be invoked by the constraint solver.

Abstract: A computer-implemented method, system and computer program product for developing a strategic plan by a strategic planning system. The strategic planning system collects structured and unstructured data. The collected structured and unstructured data is then aggregated by the strategic planning system. A client's needs and interests are then defined based on analyzing the aggregated collected data. Such needs and interests may be identified using natural language processing and a statistical model, where the statistical model includes words that are associated with a need or interest. The strategic planning system further labels the aggregated data with labels that contain vectors of interest across different areas. A supervised deep learning model is then trained to predict future needs and interests of the client based on the aggregated collected data and the labels. The predicted future need and interest of the client is then matched with a solution using a recommender system.