Embodiments of this application provide a for training an information recommendation model. The method includes: obtaining historical user behavior data in a plurality of product domains; generating candidate sample data of one or more target product domains according to the historical user behavior data by using a generative model; performing user-specific authenticity sample discrimination on candidate sample data of the target product domains and actual user click sample data by using a discriminative model, to obtain a discrimination result; and performing adversarial training on the generative model and the discriminative model according to the discrimination result, to obtain a trained generative adversarial network as an information recommendation model for a to-be-expanded product domain in the plurality of product domains. According to the method, the training effect of the generative model may be improved, the accuracy of generating the pseudo sample is improved, thereby further improving the recommendation effect.

The present disclosure relates to a computer-implemented process for generating and providing simulated user absorption information pertaining to users and based on target profiles and target situations, thereby providing user targeted and situationally targeted content recommendations. It is an object of the present disclosure to provide a technological solution to the long felt need in small scale content recommendation systems caused by the technical problem of generating situationally targeted and user profile targeted content recommendations for users of an interactive electronic system.

Systems and methods are described herein for generating potential feature combinations for a new item. A neural network may be utilized to identify positive and/or negative sentiment phrases from textual data. Each sentiment phrase may correspond to particular features of existing items. A machine-learning model may utilize the sentiment phrases and their corresponding features to generate a set of potential feature combinations for a new item. The potential feature combinations may be scored, for example, based on an amount by which a potential feature combination differs from known feature combinations of existing items. One or more potential feature combinations may be provided in a feature recommendation. Feedback (e.g., human feedback, sales data, page views for similar items, and the like) may be obtained and utilized to retrain the machine-learning model to better identify subsequent feature combinations that may be desirable and/or practical to manufacture.

A method includes receiving a training metric, the training metric indicating a parameter to be optimized by content recommendations. A machine learning algorithm maybe used to determine a plurality of different combinations of the recommendation algorithms in the experiment, and each of one or more of the plurality of combinations may be used to generate a content recommendation for one or more visitors. The statistical performance of each of the one or more combinations in optimizing the parameter (based on the content recommendations generated by those combinations) may be monitored and a higher percentage of visitors may be allocated to a combination that generates content recommendations that are the most effective at optimizing the parameter.

A system for a product bundle for purchase may include a user device associated with a given user, and a promotional server. The promotional server may obtain historical online browsing data associated with the given user, and obtain historical shopping data associated with the given user. The promotional server may also generate the product bundle based upon the historical shopping data and the historical online browsing data. The product bundle may include complementary products for purchase each having a purchase price associated therewith. The product bundle may have a bundle price that is less than a sum of purchase prices of each of the complementary products. The promotional server may communicate the product bundle and the bundle price to the user device for display thereon, generate a digital promotion redeemable toward the purchase of the product bundle, and communicate the digital promotion to the user device.

Methods and systems are disclosed for providing a vehicle suggestion to a user based on image analysis. The method may include: receiving one or more vehicle images via website data associated with the user; identifying one or more first-level traits from the one or more vehicle images; obtaining one or more vehicle identifications from the one or more vehicle images based on the one or more first-level traits; determining a value of each of the one or more first-level traits and/or the one or more vehicle identifications via one or more algorithms; determining the vehicle suggestion based on the value of each of the one or more first-level traits and/or the one or more vehicle identifications; and transmitting, to a device associated with the user, a notification indicating the vehicle suggestion.

A system and a method for recommending a modification to a test package for a software under test. A release note package associated to a feature of a software is received. The release note package is analysed in real time using machine learning based models. Further, a keyword is extracted from the release note package using a keyword extraction technique. The keyword corresponds to the feature of the software. The keyword is compared with nomenclatures present in a test package using a pattern matching technique. The test package is associated to the feature of the software. Finally, a modification to the test package is recommended based on the comparison. The modification comprises addition, deletion, or updating an existing element of the test package. It may he noted that the modification is recommended using an Artificial Intelligence (AI) technique.

A system and method for providing a customized bookstore for a school including creating an online bookstore associated with a school based on a catalog including book identifiers; customizing a look and feel of the online bookstore to identify the school; populating lists wherein each list of the lists includes a category, a donation flag and a booklist including a subset of book identifiers, where the lists include a school booklist and a donation booklist; receiving an order including a shipping address, a selected category and at least one book identifier from the booklist associated with the selected list identifier; and shipping an order confirmation indicating, for each of the books associated with the least one book identifier, a respective category.

This invention pertains to a system and method for a recommendation engine that helps customers find the answers and services. The engine understands the context of what the user is looking at and recommends products and services to meet the needs of the user. The engine is operated through a search index that gives access to more data and better scalability to provide answers and optimal solutions to the user. The recommendation engine functions as a search tool, whereby the user can search by fields, including title, abstract, claims, inventor, specification or assignee. The recommendation engine can also recommend products and services provided by platform partners or third party providers, and implement a tracking system for referrals to third party providers for revenue generation.

The present invention relates to a method, system, and computer program product for facilitating sharing of desired items stored in a digital wallet for gifting purposes. The invention includes selection of items by users to be saved in their digital wallets and sharing of the wallet and items saved therein with other users such as friends, relatives and others. The other users can view the content of the shared wallets and can purchase one or more items for gifting. The invention also includes registration of the sellers for listing items for sale at a discounted price, along with a percentage sharing with the server used in the digital wallet.