Abstract: The present disclosure provides a liquid-state reactive polyurethane adhesive, which includes a polyurethane prepolymer. The polyurethane prepolymer is blocked by an isocyanate group, and the polyurethane prepolymer is obtained by a polymerization reaction, a reactive monomer of the polymerization reaction includes a polyisocyanate, a polyol, a stabilizer, a catalyst and a hydrophobic filler. A functionality of the polyisocyanate is 2.4 to 3. A molecular weight of the polyol is 1000 to 8000, and the polyol has hydrolysis resistance. The stabilizer has a structure represented by formula (I). The catalyst has a structure represented by formula (II). Formula (I) and formula (II) are as defined in the specification.

Abstract: The present disclosure provides a liquid-state reactive polyurethane adhesive, which includes a polyurethane prepolymer. The polyurethane prepolymer is blocked by an isocyanate group, and the polyurethane prepolymer is obtained by a polymerization reaction, a reactive monomer of the polymerization reaction includes a polyisocyanate, a polyol, a stabilizer, a catalyst and a hydrophobic filler. A functionality of the polyisocyanate is 2.4 to 3. A molecular weight of the polyol is 1000 to 8000, and the polyol has hydrolysis resistance. The stabilizer has a structure represented by formula (I). The catalyst has a structure represented by formula (II). Formula (I) and formula (II) are as defined in the specification.

Abstract: The disclosure herein describes a system for generating embeddings representing sequential human activity by self-supervised, deep learning models capable of being utilized by a variety of machine learning prediction models to create predictions and recommendations. An encoder-decoder is provided to create user-specific journeys, including sequenced events, based on human activity data from a plurality of tables, a customer data platform, or other sources. Events are represented by sequential feature vectors. A user-specific embedding representing user activities in relationship to activities of one or more other users is created for each user in a plurality of users. The embeddings are updated in real-time as new activity data is received. The embeddings can be fine-tuned using labeled data to customize the embeddings for a specific predictive model.

Abstract: A thermoplastic polyurethane composite material composition includes a plastic base material and a curing agent, the plastic base material includes a thermoplastic polyurethane and a silicone gum including at least two alkenyl groups in each of molecules thereof, wherein the thermoplastic polyurethane and the silicone gum are uniformly mixed, and a weight ratio of the thermoplastic polyurethane and the silicone gum is ranging from 95.01:4.99 to 99.5:0.5. The curing agent is uniformly mixed with the plastic base material, wherein the curing agent has an adding amount enabling the silicone gum to crosslink to form a silicone rubber.

Abstract: A thermoplastic polyurethane composite material composition includes a plastic base material and a curing agent, the plastic base material includes a thermoplastic polyurethane and a silicone gum including at least two alkenyl groups in each of molecules thereof, wherein the thermoplastic polyurethane and the silicone gum are uniformly mixed, and a weight ratio of the thermoplastic polyurethane and the silicone gum is ranging from 95.01:4.99 to 99.5:0.5. The curing agent is uniformly mixed with the plastic base material, wherein the curing agent has an adding amount enabling the silicone gum to crosslink to form a silicone rubber.