Request for quotation (RFQ) is a lengthy document soliciting vendor products and services according to rigid specifications. This research develops an integrated natural language processing (NLP), text mining, and machine learning approach for intelligent RFQ summarization. Over 1,300 power transformer RFQ requests are used to build a word-embedding model for training and testing. Domain keywords are extracted using N-gram TF-IDF. The method automatically extracts essential specifications such as voltage, capacity, and impedance from RFQs using text analytics. The K-means algorithm groups the sentences of each specification. The TextRank algorithm identifies important sentences of all specifications to generate RFQ summaries. The summarization system helps engineers shorten the time to identify all specifications and reduces the risk of missing important requirements during manual RFQ reading. The system helps improve the complex product design for manufacturers and improve the cost estimation and competitiveness of quotations in a highly competitive marketplace.

Global online sales for products, where many are substantially identical or deceptively similar, are the cause of a growing number of trademark (TM) infringement lawsuits. This research proposes an intelligent trademark legal precedent recommendation system to assist trademark owners to find relevant past cases, laws, and judgments to form legal arguments to defend against infringement. Judicial precedent and applicable laws from the USA are used to construct an ontology of trademark litigation knowledge. The ontology is used to analyze potential infringement cases with similar laws and precedents used to resolve previous legal disputes. The analysis provides a basis for proceeding with legal action necessary to protect a company's brand equity when arguing potential trademark infringement. Using the Python programming language, the precedent-based recommendation system provides a means for continuously updating trademark case data and assists TM owners to quickly identify similar cases to support infringement allegations.

E-commerce provides a global platform supporting product transactions through the consumer purchase lifecycle including communications of perceived satisfaction and dissatisfaction. The customer feedback functions and social networks of many e-commerce websites allow for the creation of extremely large databases that can be mined to model the customers' perceptions toward online purchases. This research uses online customer reviews as the business intelligence corpus to help companies redesign products that better satisfy consumer preferences and differentiate their product offerings. After identifying the specific webpages of customer reviews, a web crawler collects review text. Computer-supported text mining, cluster analysis, and perceptual mapping are combined as a systematic analytic approach to compare products in a given domain. The study assists phone manufacturers to understand the positive and negative perceptions of customers related to their post-purchase experiences. The customer-preferred product functions, features, and price positions provide valuable strategic intelligence for new product designs and market differentiation.

The growth of global patents increased over the last decade as enterprises and inventors sought greater protection of their intellectual property (IP) rights. Global patents represent state-of-the-art knowledge for given domains. This research develops a hierarchical Latent Dirichlet Allocation (LDA)-based approach as a computational intelligent method to discover topics and form a top-down ontology, a semantic schema, representing the collective patent knowledge. To validate the knowledge extraction, 1,546 smart retailing patents collected from the Derwent Innovation platform from 2011 and 2016 are used to build the domain ontology schema. The patent set focuses on in-use, globally established, and non-disputed IP covering payment, user experience, and information integration for smart retailing. The clustering and LDA-based ontology system automatically build the knowledge map, which identifies the technology trends and the technology gaps enabling the development of competitive R&D and management strategies.

An ontology-based patent roadmap and valuation analysis approach provides competitive foresights for a corporation's associated patent portfolios and the underlying business processes. To demonstrate the methodology and computer supported analysis system, the patent portfolios of two global smart e-retailers are compared. The patents in each company's portfolio are text mined and categorized based on the smart retailing ontology schema. Both cases' text mining results are plotted as patent portfolio roadmaps, linking patents to innovation categories, commercial applications, and business process models. The three-dimensional (3-D) patent valuation analysis method provides foresights of the companies' competitive advantages related to “patent scope” (PS), “patent importance” (PI), and “patent innovation” (PIN). The research implements a computer supported system to provide evidence how companies utilize patent portfolios as key strategies for protecting business related intellectual properties (IPs) while implementing sustainable and competitive business processes.