Generative artificial intelligence recommendation engine in item list system

Abstract

The invention relates to a generative artificial intelligence recommendation engine in an item list system. Methods, systems, and computer storage media for providing generative artificial intelligence (AI) recommendation management using an artificial intelligence system in an item listing system. The generative AI recommendation engine supports generative AI recommendation management according to the comment-based recommendation platform, the generative AI recommendation management including offline generative AI operations, comment-based recommendation guide for items, and comment-based recommendation logic. A comment-based recommendation guide for a plurality of items is generated using a generative AI technique. The comment-based recommendation logic supports identification of comment-based recommendation items for the user in accordance with the comment data and the comment-based recommendation guide. In operation, comment data associated with a user of a first item is accessed. Based on the comment data, a comment-based recommendation guide feature of the first item is identified.

Description

Technical Field

[0001] The present invention relates to a generative artificial intelligence recommendation engine in an item listing system. Background Art

[0002] Users can interact with generative artificial intelligence technology in different types of applications and services to complete computational tasks. Generative AI refers to a class of AI systems and algorithms that are designed to generate new data or content that is similar to the data on which they are trained, or in some cases, completely different. Generative AI systems can create support for text generation, image generation, music and audio generation, video generation, and data synthesis. Specifically, generative AI systems can support an item listing system in several ways to improve operational efficiency, customer engagement, and online shopping. For example, an item listing system can adopt a generative AI system for content generation (e.g., product descriptions), personalized shopping experiences (e.g., recommendation engines), product discovery (e.g., visual search), and virtual assistants (e.g., chatbots). An item listing system can leverage generative AI through application programming interfaces (APIs), pre-trained models, and custom AI solutions to enhance item listing functionality. Summary of the Invention

[0003] Aspects of the techniques described herein generally relate to systems, methods, and computer storage media for providing generative AI recommendation management, etc. using an artificial intelligence system associated with an item listing system. The generative AI recommendation engine of the artificial intelligence system supports providing generative AI recommendation management in the item listing system. The generative AI recommendation engine supports generating review-based recommendation guidelines using a generative AI model (e.g., a large language model "LLM"). Specifically, the generative AI recommendation engine generates review-based recommendation guidelines for a user and corresponding items in an item listing database. The review-based recommendation guidelines are generated based on review data (e.g., reviews, feedback, opinions, questions, and answers), as well as one or more prompts executed on the generative AI model. The review-based recommendation guidelines are computational objects that can be deployed to support different types of recommendation services and interfaces in the item listing system. The generative AI recommendation engine also includes a mapping service associated with the review-based recommendation logic that maps items having known user preference information (e.g., features of items that a user does not like) in the review-based recommendation guidelines to other items in the item listing database of the item listing system. Based on the review-based recommendation guidelines of other users having known user preference information, an item is identified as a review-based recommended item.

[0004] In operation, access comment data associated with a user of a first item. Based on the comment data, identify comment-based recommendation guideline features of the first item. Map the comment-based recommendation guideline features of the first item to comment-based recommendation guideline features of a second item. Communicate the second item as a comment-based recommended item.

[0005] The present disclosure is provided to introduce, in a simplified form, a selection of concepts that are further described below in the detailed description. The present disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The techniques described herein will be described in detail below with reference to the accompanying drawings, in which:

[0007] Figure 1A and Figure 1B is a block diagram of an artificial intelligence system for providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein;

[0008] Figures 1C - 1E is a schematic diagram and interface associated with providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein;

[0009] Figure 2A is a block diagram of an artificial intelligence system for providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein;

[0010] Figure 2B is a block diagram of an artificial intelligence system for providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein;

[0011] Figure 3 A first exemplary method for providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein is provided;

[0012] Figure 4 A second exemplary method for providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein is provided;

[0013] Figure 5 A third exemplary method for providing generative AI recommendation management in an item listing system according to aspects of the techniques described herein is provided;

[0014] Figure 6 A block diagram of an exemplary item listing system computing environment suitable for implementing aspects of the techniques described herein is provided;

[0015] Figure 7 A block diagram of an exemplary distributed computing environment suitable for implementing aspects of the technologies described herein; and

[0016] Figure 8 is a block diagram of an exemplary computing environment suitable for implementing aspects of the technologies described herein. DETAILED DESCRIPTION

[0017] OVERVIEW

[0018] Project Listing System and Platform Support: Projects (products or assets) are stored in a project database, and a search system is provided for receiving queries and identifying search result projects based on the queries. Projects (e.g., physical or digital projects) refer to products or assets provided for listing on a project listing platform. The search system supports identifying result projects from the project database for received queries. The project database can be dedicated to a content platform or a project listing platform (e.g., the EBAY content platform developed by EBAY INC. in San Jose, California). The project listing system can also provide generative AI-supported applications ("generative AI applications") that utilize generative AI models (e.g., image generation models and large language models - "LLMs") to create, generate, or produce content, data, or output. An LLM is a specific category of generative AI model that mainly focuses on generating human-like text. Generative AI models (such as GPT (Generative Pretrained Transformer) and its variants) are designed to generate human-like text or other types of data based on the input they receive (e.g., via a prompt interface). These applications use generative AI to perform various tasks in different fields to improve automation, efficiency, and human-like interactions.

[0019] Traditionally, project listing systems have not been configured with comprehensive logic and infrastructure for effectively providing generative AI-based recommendations for a project listing system. Traditional project listing systems have difficulty integrating user feedback and reviews for making recommendations for future projects and thus face some limitations that affect the quality and relevance of the projects they recommend. The lack of user feedback hinders the system's ability to deliver personalized recommendations, resulting in general recommendations that may not match individual tastes and preferences. Without the rich insights provided by user reviews, the system lacks a detailed understanding of customer preferences, making it challenging to customize recommendations for specific needs. Additionally, the system also misses out on capturing emerging trends, valuable information related to new features, and evolving customer expectations that are often communicated through user feedback.

[0020] In the absence of a generative AI recommendation engine, implementing only a traditional knowledge graph results in insufficient functionality of the item listing system. For example, relying solely on popularity metrics without context understanding from user reviews may lead to sales volume- or view-driven recommendations, potentially overlooking niche products and reducing the overall discoverability of products. Specifically, the lack of user feedback affects the trust and credibility of the system because users may miss valuable insights from real customer experiences and reviews. The system's inability to utilize user reviews also limits the potential of its cross-selling opportunities, as patterns of complementary products that are often purchased together may be overlooked. Overall, the integration of user feedback and reviews is crucial for accommodating diverse user preferences, staying informed about market trends, and building a more trustworthy and effective recommendation system in the e-commerce domain.

[0021] The traditional item listing system can be improved by addressing these limitations through the use of advanced machine learning models and techniques, which can enhance the personalization, trust, and overall quality of recommendations. Thus, a more comprehensive item listing system with an alternative basis for performing the operations of a generative AI recommendation engine can improve the computational operations and interfaces for providing item listing recommendation services in the item listing system.

[0022] Embodiments of the present invention relate to systems, methods, and computer storage media for providing generative AI recommendation management, etc. using an artificial intelligence system associated with an item listing system. The generative AI recommendation engine of the artificial intelligence system supports providing generative AI recommendation management in the item listing system. The generative AI recommendation engine supports generating review-based recommendation guidelines using a generative AI model (e.g., a large language model "LLM"). Specifically, the generative AI recommendation engine generates review-based recommendation guidelines for a user and corresponding items in an item listing database. The review-based recommendation guidelines are generated based on review data (e.g., reviews, feedback, opinions, questions, and answers), as well as one or more prompts executed on the generative AI model. The review-based recommendation guidelines are computational objects that can be deployed to support different types of recommendation services and interfaces in the item listing system.

[0023] The generative AI recommendation engine also includes a mapping service associated with review-based recommendation logic that maps items with known user preference information (e.g., features of items that a user dislikes) in the review-based recommendation guidelines to other items identified as review-based recommended items in the item listing database of the item listing system.

[0024] Generative AI recommendations are provided using a generative AI recommendation engine that is operably integrated into an item listing system associated with an artificial intelligence system. The artificial intelligence system supports a generative AI recommendation framework for computational components associated with the operation of the generative AI recommendation engine for providing generative AI recommendation management.

[0025] At a high level, a user can provide rich information or content (e.g., review data) related to their preferences regarding various items (e.g., products) in the item listing system. The user can share specific issues they encountered while experiencing a product in the review data associated with the product. These issues can signal the attributes (e.g., item features) that the user cares about for different types of products. For example, User A may be disappointed with the battery life of earbuds or may indicate that the charger gets too hot. Due to the historical complexity associated with processing and analyzing review data, existing recommendation systems in the item listing system may not pay attention to review data; however, using a generative AI model (e.g., an LLM), valuable information can be extracted from the review data to support improving the recommendation system and other types of functionality of the item listing system.

[0026] A generative AI review-based recommendation framework is a technical solution aimed at providing generative AI recommendation management using the generative AI recommendation engine of an item listing system. The generative AI review-based recommendation framework includes a generative AI recommendation engine that supports generating review-based recommendation guidelines using a generative AI model (e.g., a large language model - "LLM"). Review-based recommendation guidelines can refer to computational objects generated to support identifying review-based recommendations.

[0027] For example, an LLM can provide natural language processing (NLP) based on a pre-trained model encoded with a large amount of information. The LLM can be utilized to understand the review data (e.g., reviews, questions, answers, feedback, opinions) of the item listing platform to extract the user's preferences regarding items or products. The generative AI model can process the review data to extract review-based recommendation guideline data (e.g., a detailed understanding of customer preferences including emerging trends, new features, and customer expectations). The review-based recommendation guideline data can include user preferences for specific product attributes and also include generative AI review-based insights associated with the user preferences (e.g., excerpts from user reviews). The review-based recommendation guideline data can be used to generate review-based recommendation guidelines for users and corresponding items.

[0028] A review-based recommendation guide can be associated with a defined data structure that supports storing different types of user preference data, as well as review-based insights based on generative AI that support making recommendations based on a user's review data. For example, a review-based recommendation guide can include item features (i.e., review attributes), as well as indications of whether a user likes a particular feature, dislikes a particular feature, or is neutral towards a particular feature. At a high level, if it is found based on user A's review or feedback that user A dislikes the sound quality of speaker X, and speaker Y has received positive reviews from other users regarding the sound quality, then speaker Y will be recommended to user A.

[0029] Further, user A can draft a review for earbuds. The review can be analyzed using an LLM that identifies a first feature (e.g., the battery life of earbud X) and determines that the user dislikes the first feature. The user preference information of user A can be stored in the review-based recommendation guide. The review-based recommendation guide feature of user A for earbud X (i.e., the battery life) can be compared with the corresponding features of the review-based recommendation guides of multiple other users for other earbuds. A review-based recommendation logic can be defined to support matching the review-based recommendation guide features of a first item with the review-based recommendation guide features in other review-based recommendation guides. In this way, earbud Y can be identified based on the review-based recommendation guides from other users. Specifically, earbud Y can be identified as having a good battery life and recommended to the user. Earbud Y can be recommended along with other review attributes from the review-based recommendation guide. For example, the review-based recommendation guide can include one or more excerpts from the corresponding users indicating that earbud Y has a good battery life.

[0030] In operation, an item listing system provides a generative AI recommendation engine to an AI system to support providing generative AI recommendation management. The generative AI recommendation engine can employ a generative AI model (e.g., an LLM) to generate review-based recommendation guides. A review-based recommendation guide can refer to a computational object that stores and utilizes review data (e.g., user reviews and feedback) to provide recommendations for items in an item listing system. Review-based recommendation guides are generated for users of corresponding items based on review data including user preference information for the items. The generative AI recommendation engine can access review data associated with the review interface of the item listing system. The review data is associated with multiple users corresponding to the items associated with the item listing system.

[0031] Using a generative AI model and review data, a generative AI recommendation engine generates review-based recommendation guideline data. The review-based recommendation guideline data includes user preferences for item features associated with each item. The review-based recommendation guideline data can refer to the output from a generative AI model that is used to generate review-based recommendation guidelines for a user and a corresponding item. For example, a user can review Earbud X, and thus, an LLM can be used to generate review-based recommendation guideline data. The user can be associated with the review-based recommendation guideline for Earbud X. Additionally, if the user indicates dislike for the battery life of Earbud X, the LLM will extract the user preference (i.e., dislike for the battery life of Earbud X), and this user preference can be stored in the review-based recommendation guideline for the battery life feature.

[0032] In this way, review-based recommendation guideline data is output from the generative AI model such that the generative AI recommendation engine can use the review-based recommendation guideline data to generate multiple review-based recommendation guidelines for a user and a corresponding item. The review-based recommendation guidelines can be associated with a review-based recommendation guideline data structure that supports storing review-based recommendation guideline features, user preference attributes, and generative AI review-based insights. The review-based recommendation guidelines can be for a specific item and the users associated with that item. Multiple review-based recommendation guidelines are deployed to support identifying review-based recommended items for a user.

[0033] The generative AI recommendation engine operates to identify review-based recommended items for a user. The generative AI recommendation engine can access the review-based recommendation guideline for a first user for a first item in an item list system. Based on the review-based recommendation guideline, the generative AI recommendation engine identifies review-based recommendation guideline features for the first item. The generative AI recommendation engine uses the generative AI model and review data to identify review-based recommendation guideline features for the first item. The generative AI recommendation engine generates review-based recommendation data that includes user preferences for item features of the item and generates a review-based recommendation guideline for the user.

[0034] The generative AI recommendation engine maps the review-based recommendation guideline features of a first item to the review-based recommendation guideline features of a second item. The mapping of the review-based recommendation guideline features is based on the review-based recommendation logic. The review-based recommendation logic indicates how items should be recommended to a user based on user preference attributes and review-based recommendation guideline features. The review-based recommendation logic is used to perform the mapping of the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of the second item, and the review-based recommendation logic compares the review-based recommendation guideline of the first item with multiple review data recommendation guidelines for matching according to the review-based recommendation guideline features.

[0035] The review-based recommendation guideline features of the second item are associated with the review-based recommendation guidelines of one or more second users. The second item is communicated as a review-based recommended item associated with review data. The second item is associated with generative AI review-based insights. The generative AI review-based insights can include one or more review data excerpts corresponding to one or more second users. In this way, a item list system client can be used to write a review (e.g., review data) for the first item, and based on the review written for the first item, the second item can be identified as a review-based recommended item.

[0036] Advantageously, embodiments of the present technical solution support providing generative AI recommendation management using the generative AI recommendation engine in the item list system. The generative AI recommendation engine supports generating review-based recommendation guidelines using a generative AI model (e.g., a large language model). The generative AI recommendation engine operates to provide a solution to problems in the item list system (e.g., the limited ability to integrate user feedback and reviews to inform recommendations for future items). The generative AI recommendation engine components, infrastructure, and an ordered combination of steps are an improvement over traditional item list systems that lack support for a generative AI recommendation engine with review-based recommendation guidelines.

[0037] Aspects of the technical solution can be described by way of example and with reference Figures 1A - 1E to. Figure 1A An item list system 100 is shown, which includes an artificial intelligence system 100A, a network 100B, a generative artificial intelligence (AI) recommendation engine 110, an item list system service 110B, an integrated API 110C, a generative AI application 110D, generative AI recommendation engine operations 112, review-based recommendation guidelines 120, an item list system client 130, and a machine learning engine 140 including a generative AI model 142. The item list system 100 (or product list system) corresponds to the item list system 600 described below with reference Figure 6 to.

[0038] The item listing system 100 provides a system (e.g., an artificial intelligence “AI” system 100A) that includes an engine (e.g., a generative AI recommendation engine 110) for performing the operations discussed herein (e.g., generative AI recommendation engine operations 112). For example, the generative AI recommendation engine 110 uses a generative AI model 142 to support a review-based recommendation guide 120 for identifying review-based recommended items. The generative AI recommendation engine 110 can also operate with an item listing system client 130 (e.g., a client device or a generative AI application client), which can access the item listing system 100 to perform tasks using an item listing system service 110D (e.g., a generative AI application 110D) associated with the corresponding generative AI model 142. For example, a user can communicate a request (e.g., a generative AI request with prompt data) to the generative AI application 110D and the generative AI model 142 associated with the machine learning engine 140 via the item listing system client 130 (e.g., a prompt interface) to process the request. Based on the communicated request, the generative AI recommendation engine 110 can perform generative AI recommendation engine operations (e.g., training, generating, deploying, integrating, mapping, predicting, and controlling operations) with components of the generative AI recommendation engine 110 to ensure processing of the request.

[0039] The generative AI recommendation engine 110 can also include item listing system services 110B corresponding to different services of the item listing system. The item listing system services can include search services and recommendation services, e.g., adopting the review-based recommendation guide 120 to provide item listing system functionality. The item listing system services can include a review-based recommendation service associated with the item listing system 100. An integrated application programming interface (API) 110C can be provided to integrate the item listing system services with the review-based recommendation guide 120. The generative AI application 110D can also adopt the review-based recommendation guide 120 to provide functionality associated with the generative AI application 110D. Other variations and combinations of item listing system services are contemplated by the embodiments described herein.

[0040] Reference Figure 1B , Figure 1BShows a project list system 100, an artificial intelligence system 100A, a generative AI recommendation engine 110, a generative AI application 120, a project list system service 110B, an integrated API 110C, review data 110E, generative AI recommendation engine operations 112, a review-based recommendation guideline data structure 114, a review-based recommendation guideline logic 116, a review-based recommendation guideline 120, a machine learning engine 140 including a generative AI model 142, and a project list system client 130 including project list system client interface data 132.

[0041] The generative AI recommendation engine 110 and the project list system client 130 provide a graphical user interface (e.g., a project list system interface and a generative AI application interface) and operations (i.e., generative AI recommendation engine operations 112). The generative AI recommendation engine 110 and the project list system client 130 can operate in a server-client relationship to provide a generative AI recommendation management function. For example, a user can communicate a request from the project list system client 130 to perform a task via the generative AI recommendation engine 110 that uses the review-based recommendation guideline 120. Based on this request, the generative AI recommendation engine 110 can perform the generative AI recommendation engine operations 112 to ensure that the request is processed in the artificial intelligence system 100A.

[0042] The generative AI recommendation engine 110 can perform the generative AI recommendation engine operations 112 to provide functions associated with generating, deploying, integrating, and using the review-based recommendation guideline 120. The generative AI recommendation engine can employ a generative AI model (e.g., an LLM) to generate a review-based recommendation guideline using review data. Review data can refer to information provided by an individual based on their experience, opinion, or evaluation of an item (e.g., a product, service, or experience). Review data can include written opinions, ratings, or other forms of expression that convey the sentiment, satisfaction level, and specific insights of a user or customer. Review data can include qualitative and quantitative opinions on aspects such as product performance, usability, customer service, and overall user satisfaction. Review data can be collected through different types of interfaces associated with the project list system.

[0043] A review-based recommendation guide can refer to a computational object that stores and utilizes review data (e.g., user reviews and feedback) to provide recommendations for items in an item list system. The review-based recommendation guide can be set in a data structure that supports the storage and adoption of the review-based recommendation guide. The review-based recommendation guide data structure provides a systematic way to organize and store information derived from user reviews to facilitate the process of generating review-based recommendations. The review-based recommendation guide data structure can include information associated with the user opinions, sentiments, and preferences expressed in the reviews. The review-based recommendation guide data structure can also include user information, item information, review details, sentiment analysis, feature-specific feedback, comparison information, recommendation likelihood, metadata, user interaction history, custom tags or markers, feature importance scores, trends and patterns, and additional attributes.

[0044] The review-based recommendation guide can be based on review-based recommendation guide data generated using a generative AI model. For example, the generative AI model 142 processes the historical review data of the item list system based on one or more prompts. The generative AI model 142 can be employed to identify different types of review-based recommendation guide data that can be constructed and provided in the review-based recommendation guide. The generative AI model 142 can extract user preference data and additional insights regarding how to construct and use the review-based recommendation guide. For instance, the generative AI model can identify or generate sentiment information, user ratings, topics, review summaries, and content analysis associated with the review data 110E.

[0045] The generative AI model 142 can also be configured to generate generative AI review-based insights for the review-based recommendation guide. The generative AI review-based insights can focus on uncovering human-like text or images of subtle patterns in sentiments and preferences. The generative AI model 142 can automatically generate key phrases, reveal semantic similarities, and conduct sentiment analysis to discern the emotional tone of user feedback. The generative AI model 142 can draft a coherent narrative that summarizes the overall user experience, identifies recurring themes, and generates custom tags for the reviews. The generative AI model can contribute to trend identification, pinpoint emerging patterns in user feedback, and can provide detailed insights into the context of product use.

[0046] Additionally, the generative AI model 142 facilitates the automatic summarization of reviews, compressing lengthy feedback into snippets of information. The generative AI model 142 can generate feature importance scores, providing a quantitative measure of user priorities, and discern shifts in sentiment over time or across different contexts. The generative AI-based insights from reviews can be used to construct the output of review-based recommendation guidelines, or the generative AI-based insights from reviews can be included as part of the identified review-based recommendations. Based on review data 110E that includes user preference information for items, review-based recommendation guidelines are generated for users corresponding to the items. The generative AI recommendation engine 110 can access review data 110E associated with the review interface of the item listing system. The review data 110E is associated with multiple users corresponding to the items associated with the item listing system.

[0047] The generative AI recommendation engine 110 operates to identify review-based recommended items for a user. The generative AI recommendation engine 110 can access the review-based recommendation guidelines for a first user for a first item. Based on the review-based recommendation guidelines, the generative AI recommendation engine 110 identifies the review-based recommendation guideline features for the first item. The generative AI recommendation engine 110 uses the generative AI model and the review data to identify the review-based recommendation guideline features for the first item. The generative AI recommendation engine 110 generates review-based recommendation data that includes user preferences for item features of the item and generates review-based recommendation guidelines for the user.

[0048] The generative AI recommendation engine 110 maps the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of a second item. The mapping of the review-based recommendation guideline features is based on the review-based recommendation logic 116. The review-based recommendation logic indicates how items should be recommended to a user based on user preference attributes and review-based recommendation guideline features. The mapping of the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of the second item is performed using the review-based recommendation logic, which compares the review-based recommendation guidelines of the first item with multiple review data recommendation guidelines for matching based on the review-based recommendation guideline features.

[0049] The review-based recommendation guidelines logic 116 can include a system analysis of review-based recommendation guidelines to make review-based recommendations. The review-based recommendation guidelines logic 116 can be implemented using a machine learning model that includes a generative AI machine learning model, which employs a collaborative filtering algorithm or a deep learning model to make review-based recommendations. Specifically, based on aggregating user preference information in the review-based recommendation guidelines, the review-based recommendation guidelines logic 116 can be used to analyze different review-based recommendation guidelines 120 to make recommendations. For example, in a scenario where a first user is dissatisfied with a feature in a first item while a second user is satisfied with the same feature in a second item, various recommendation algorithms can be employed to cater to the preferences of the first user.

[0050] For example, collaborative filtering techniques, including user-based and item-based methods, can be utilized to recommend items based on the preferences of users with similar tastes or who have liked similar items in the past. Content-based filtering takes into account item features and user preferences to provide recommendations, potentially identifying items with features liked by users who like the second item. A hybrid recommendation system that combines collaborative and content-based methods provides a comprehensive approach that utilizes both user-item interactions and item characteristics for more accurate recommendations. Matrix factorization models and deep learning techniques can capture complex patterns in user behavior and characteristics to enhance personalization. Additionally, analysis of feature importance, sentiment around disliked features, and context-aware recommendation methods contribute to a nuanced and customized recommendation for the first user.

[0051] In this way, the second item can be identified as a review-based recommended item based on the features of the review-based recommendation guidelines for the second item. The review-based recommendation guidelines features of the second item are associated with the review-based recommendation guidelines of one or more second users. The second item is communicated as a review-based recommended item associated with review data. The second item is associated with generative AI review-based insights. The generative AI review-based insights can include one or more excerpts of review data corresponding to one or more second users. Other types of generative AI review-based insights are considered. Thus, an item list system client can be used to write a review (e.g., review data) for the first item, and based on writing the review for the first item, the second item can be identified as a review-based recommended item.

[0052] The item listing system client 130 can be associated with a seller interface, a buyer interface, and other item listing system service interfaces associated with the item listing system. The item listing system client 130 can display item listing system client interface data 132 associated with items associated with the item listing system 100 based on the generative AI recommendation engine 110, the generative AI model 142, the review-based recommendation guidelines 120, and functions associated with the item listing system 100. The item listing system client interface data can be associated with different outputs corresponding to the item listing system service 110B and other functional components, as well as the output of the generative AI recommendation engine 110D.

[0053] Go to Figure 1C , Figure 1C shows a schematic diagram associated with providing generative AI recommendation management using a generative AI recommendation engine according to embodiments described herein. Figure 1C includes a review-based recommendation guidelines data structure 100C, and an example tabular representation is shown below.

[0054]

[0055] The example tabular representation includes example review-based recommendation data. The review-based recommendation guidelines data structure is intended as an exemplary illustration of a review-based recommendation guidelines data structure with review-based recommendation guidelines data. The review-based recommendation guidelines data structure 100C can be associated with User A, and item A 102C (earbuds), item B 104C (jacket), and item C 106C (boots). Item A 102C, item B 104C, and item C 106C can correspond to the review data of User A.

[0056] The review-based recommendation guidelines data structure 100C can store review-based recommendation guidelines features, user preference attributes, and generative AI review-based insights. Specifically, the features, user preference attributes, and generative AI review-based insights can be generated from review-based recommendation data generated using a generative AI model. The review-based recommendation guidelines data structure 100C can support communicating review-based recommendation guidelines data for display on a graphical user interface associated with the item listing system client.

[0057] Refer to Figure 1D , Figure 1D shows a schematic diagram associated with providing a generative AI recommendation engine according to embodiments described herein. Figure 1DShows a seller feedback service interface that provides comment-based recommended items for a seller for potential future sale based on comment-based recommendation guidelines associated with items previously sold by the seller. For example, seller abc123 has previously sold item 110D and item 112D. Item 110D and item 112 can be associated with multiple comment-based recommendation guidelines that are associated with comment data from a corresponding multiple of users. A generative AI recommendation engine and comment-based recommendation logic can be used to process the comment-based recommendation guidelines to generate comment-based recommended items for the seller (e.g., item 114D, item 116D, and item 118D). Thus, comment-based recommendation guidelines for a set of items associated with a seller can be employed to generate comment-based recommended items for the seller.

[0058] Reference Figure 1E , Figure 1E Shows a schematic diagram associated with providing a comment-based recommendation interface using a generative AI recommendation engine in an item listing system. The interface can be a comment-based recommendation interface 110E for a buyer, where comment-based recommended items are generated using the comment-based recommendation guidelines and comment-based recommendation management functions described herein. The comment-based recommendation interface 110E can include item 120E, item 122E, item 130E, and item 132E, as well as corresponding generative AI comment-based insights 124E, generative AI comment-based insights 126E, generative AI comment-based insights 134E, and generative AI comment-based insights 136E. The generative AI comment-based insights information can be generated via a generative AI model based on the comment data provided in the comment-based recommendation guidelines.

[0059] For example, user A 102E may have purchased a first item (e.g., a first jacket (not shown)) and a second item (e.g., a pair of boots (not shown)), and the comment data associated with the first item and the second item is processed using the techniques described herein to generate corresponding comment-based recommendation guidelines. The comment-based recommendation guidelines for the first item can be used to provide comment-based recommendations and corresponding insights (i.e., item 120E, item 122E, and generative AI comment-based insights 124E and generative AI comment-based insights 126E), and the comment-based recommendation guidelines for the second item can be used to provide comment-based recommendations and corresponding insights (i.e., item 130E, item 132E, and generative AI comment-based insights 134E and 123E). Other variations and combinations of the comment-based recommendation interface for comment-based recommended items and generative AI comment-based insights are contemplated by the embodiments described herein.

[0060] Aspects of the technical solution can be described by way of example and reference Figure 2A and Figure 2B to the manner of. Figure 2A is based on reference Figure 6 、 Figure 7 and Figure 8 A block diagram of an exemplary technical solution environment of an exemplary environment for implementing the illustrated technical solution described by and. Generally, the technical solution environment includes a technical solution system suitable for providing an example item list system 100 that can adopt the method of the present disclosure. Specifically, Figure 2A shows a high-level architecture of the item list system 100 according to an embodiment of the present disclosure. Among other engines, managers, generators, selectors, or components (collectively referred to herein as "components") not shown, Figure 2A the item list system 100 of Figure 1A and Figure 1B .

[0061] Reference Figure 2A , Figure 2A shows the item list system 100, the artificial intelligence system 100A, the generative AI recommendation engine 110, the comment 110D, the generative AI recommendation engine operation 112, the comment-based recommendation guideline data structure 114, the comment-based recommendation guideline logic 116, the comment-based recommendation guideline 120, the item list system client 130, the item list system client interface data 132, the machine learning engine 140, and the generative AI model 142.

[0062] The item list system 100 provides the artificial intelligence system 100A and the generative AI recommendation engine 110 to support the provision of generative AI recommendation management. The generative AI recommendation engine 110 can perform the generative AI recommendation engine operation 112 to adopt the generative AI model 142 to generate the comment-based recommendation guideline 120. The generative AI recommendation engine 110 accesses the comment data 110E. The comment data 110E can be associated with the comment interface of the item list system 100. The comment interface can support providing near real-time comment-based recommended items based on the comment view data received via the comment interface. The comment data 110E is associated with multiple users for the corresponding items associated with the item list system 100.

[0063] Using the generative AI model 142 and the review data 110E, the generative AI recommendation engine 110 generates review-based recommendation guideline data. The review-based recommendation guideline data includes user preferences for item features associated with each item. The review-based recommendation guideline data is output from the generative AI model 110, and the generative AI recommendation engine 110 uses the review-based recommendation guideline data to generate multiple review-based recommendations for the user and the corresponding item. The review-based recommendation guideline 120 is associated with a review-based recommendation guideline data structure that supports storing review-based recommendation guideline features, user preference attributes, and generative AI review-based insights. Multiple review-based recommendations are deployed to support identifying review-based recommended items for the user.

[0064] The generative AI recommendation engine 110 operates to identify review-based recommended items for the user. The generative AI recommendation engine 110 accesses the review-based recommendation guideline for the first user for the first item in the item list system. Based on the review-based recommendation guideline, the generative AI recommendation engine 110 identifies the review-based recommendation guideline features for the first item. The generative AI recommendation engine 110 identifies the review-based recommendation guideline features for the first item based on using the generative AI model 142 and the review data. The generative AI recommendation engine 110 generates review-based recommendation data including user preferences for the item features of the item and generates a review-based recommendation guideline for the user.

[0065] The generative AI recommendation engine 110 maps the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of the second item. The mapping of the review-based recommendation guideline features is based on the review-based recommendation logic 116. The review-based recommendation logic 116 indicates how items should be recommended to the user based on user preference attributes and review-based recommendation guideline features. The mapping of the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of the second item is performed using the review-based recommendation logic 116, which compares the review-based recommendation guideline of the first item with multiple review data recommendation guidelines for matching based on the review-based recommendation guideline features.

[0066] The review-based recommendation guideline features of the second item are associated with the review-based recommendation guidelines of one or more second users. The second item is communicated as a review-based recommended item associated with the review data. The second item is associated with generative AI review-based insights. The generative AI review-based insights can include one or more review data excerpts associated with one or more second users.

[0067] Reference Figure 2B ,Figure 2B Shown is a generative AI recommendation engine 110, a project list system client 130, and a generative AI model 142 for providing a generative AI recommendation management function. At block 10, the generative AI recommendation engine 110 accesses comment data from a user for a corresponding item in the project list system; and at block 12, conveys a prompt and the comment data to the generative AI model to generate comment-based recommendation guideline data. At block 14, the generative AI model accesses the prompt and the comment data; at block 16, uses the prompt and the comment data to generate comment-based recommendation guideline data; and at block 18, conveys the comment-based recommendation guideline data. At block 20, the generative AI recommendation engine receives the comment-based recommendation guideline data from the generative AI model; at block 22, generates multiple comment-based recommendation guidelines for the user and the corresponding item in the project list system; and at block 14, deploys the multiple comment-based recommendation guidelines to support identifying comment-based recommended items for the user.

[0068] At block 26, the project list system client 130 conveys comment data associated with a user of a first item in the project list system. At block 28, the generative AI recommendation engine accesses the comment data associated with the comment on the first item; at block 30, based on the comment data, identifies comment-based recommendation guideline features for the first item; at block 32, maps the comment-based recommendation guideline features of the first item to comment-based recommendation guideline features of a second item; and at block 34, conveys the second item as a comment-based recommended item. At block 36, based on the conveyed comment data, the project list system client accesses the second item corresponding to the comment-based recommended item; at block 38, displays the second item on a graphical user interface associated with the project list system client.

[0069] Example method

[0070] Reference Figure 3 、 Figure 4 and Figure 5 The flowcharts show methods for providing a generative AI recommendation management function in a project list system. The methods can be performed using the project list system described herein. In an embodiment, one or more computer storage media have computer-executable or computer-usable instructions embodied thereon that, when executed by one or more processors, can cause the one or more processors to perform the methods (e.g., computer-implemented methods) in a project list platform system (e.g., a computerized system or a computer system).

[0071] Go to Figure 3, a flowchart showing method 300 for providing generative AI recommendation management functionality in a project list system is provided. At block 302, the generative AI recommendation engine accesses comment data associated with a user of a first project. At block 304, the generative AI recommendation engine identifies comment-based recommendation guideline features for the first project based on the comment data. At block 306, the generative AI recommendation engine maps the comment-based recommendation guideline features of the first project to the comment-based recommendation guideline features of a second project. At block 308, the generative AI recommendation engine conveys the second project as a comment-based recommended project associated with the comment data.

[0072] Go to Figure 4 , a flowchart showing method 400 for providing generative AI recommendation management functionality in a project list system is provided. At block 402, the generative AI recommendation engine accesses comment data from a user for a corresponding project associated with the project list system. At block 404, the generative AI recommendation engine generates comment-based recommendation guideline data including user preferences for project features associated with each project based on the comment data. At block 406, the generative AI recommendation engine generates multiple comment-based recommendation guidelines for the user and the corresponding project. At block 408, the generative AI recommendation engine deploys the multiple comment-based recommendation guidelines to support identifying comment-based recommended projects for the user.

[0073] Go to Figure 5 , a flowchart showing method 500 for providing generative AI recommendation management functionality in a project list system is provided. At block 502, the project list system client conveys comment data associated with a user of a first project in the project list system. At block 504, based on conveying the comment data, the project list system client accesses a second project and generative AI comment-based insights for the second project. The second project is a comment-based recommended project. At block 506, the project list system displays the second project and the generative AI comment-based insights on a graphical user interface associated with the project list system.

[0074] Technical improvements

[0075] Embodiments of the present invention have been described with reference to several inventive features (e.g., operations, systems, engines, and components) associated with a project list platform system. The described inventive features include: arrangements of operations, interfaces, data structures, and computing resources associated with providing the functions described herein with reference to an artificial intelligence system.

[0076] Embodiments of the present invention relate to the field of computing and, more particularly, to a project list system. Among other things, the exemplary embodiments described below provide a system, method, and program for performing generative AI recommendation engine operations that provide functionality associated with generating, deploying, and adopting generative-AI-based review-based recommendation guidelines. Accordingly, this embodiment improves the technical field of project list system technology by providing more efficient operations and interfaces. For example, the operations and interfaces described for this technical solution provide specific improvements compared to existing systems, thereby improving the functionality of the project list system. Specifically, review-based recommendation guidelines and review-based recommendations generated using a generative AI model are different from traditional recommendations. This technical solution addresses the lack of integration of traditional project list systems with artificial intelligence systems and generative AI recommendation engines to improve project list system technology by providing improved operations for project list system services based on adopting review-based recommendation guidelines for providing project list system services.

[0077] The functionality of the embodiments of the present invention, which have been described by way of implementation and anecdotal examples, to demonstrate that the operations for providing generative AI recommendation management functionality in a project list system are a solution to a specific problem in project list system technology to improve computing operations and interfaces in the project list system.

[0078] Additional support for specific embodiments of the present invention

[0079] Example project list system environment

[0080] Now refer to Figure 6 , Figure 6 FIG. shows an example project list system 600 computing environment in which embodiments of the present disclosure may be employed. Specifically, Figure 6 FIG. shows a high-level architecture of an example project list platform 610 that may host the technical solution environment or portions thereof. It should be understood that such and other arrangements described herein are presented as examples. For example, as noted above, many of the elements described herein may be implemented as discrete or distributed components, or in combination with other components, and may be implemented in any suitable combination and location. Other arrangements and elements (e.g., machines, interfaces, functions, orders, and groupings of functions) other than those shown may be used, or the shown arrangements and elements may be replaced with other arrangements or elements (e.g., machines, interfaces, functions, orders, and groupings of functions).

[0081] The item listing system 600 can be a cloud computing environment that provides computing resources for functions associated with the item listing platform 610. For example, the item listing system 600 supports the delivery of computing components and services including servers, storage devices, databases, networks, applications, and machine learning associated with the item listing platform 610 and client devices 620. Multiple client devices (e.g., client device 620) include hardware or software for accessing resources on the item listing system 600. The client device 620 can include an application (e.g., client application 622) and interface data (e.g., client application interface data 624) that support client-side functions associated with the item listing system. Multiple client devices can access the computing components of the item listing system 600 via a network (e.g., network 630) to perform computing operations.

[0082] The item listing platform 610 is responsible for providing a computing environment or architecture including infrastructure that supports the provision of item listing platform functions (e.g., e-commerce functions). The item listing platform supports storing items in an item database and providing a search system for receiving queries and identifying search results based on the queries. The item listing platform can also provide a computing environment with features for managing, selling, buying, and recommending different types of items. The item listing platform 610 can be dedicated to a content platform (e.g., the EBAY content platform or e-commerce platform developed by EBAY INC. of San Jose, California).

[0083] The item listing platform 610 can provide item listing operations 630 and an item listing interface 640. The item listing operations 630 can include service operations, communication operations, resource management operations, security operations, and fault tolerance operations that support specific tasks or functions in the item listing platform 610. The item listing interface 640 can include service interfaces, communication interfaces, resource interfaces, security interfaces, and management and monitoring interfaces that support functions between item listing platform components. The item listing operations 630 and the item listing interface 640 can enable communication, coordination, and seamless operation of the item listing system 600.

[0084] For example, the functions associated with the item listing platform 610 may include: shopping operations (such as product search and browsing, product selection and shopping cart, checkout and payment, and order tracking); user account operations (such as user registration and authentication, and user profiles); seller and product management operations (such as seller registration, and product listing and inventory management); payment and financial operations (such as payment processing, refunds and returns); order fulfillment operations (such as order processing and fulfillment, and inventory management); customer support and communication interfaces (such as customer support chat / email and notifications); security and privacy interfaces (such as authentication and authorization, payment security); recommendation and personalization interfaces (such as product recommendations, and customer reviews and ratings); analytics and reporting interfaces (such as sales and inventory reports, and user behavior analysis); and API and integration interfaces (such as APIs for third-party integration).

[0085] The item listing platform 610 may provide an item listing platform database (such as the item listing platform database 650) to efficiently manage and store different types of data. The item listing platform database 650 may include a relational database, a NoSQL database, a search database, a cache database, a content management system, an analytics database, a payment gateway database, a customer relationship management database, a log and error database, an inventory and supply chain database, and a multi-channel database that are used in combination to efficiently manage data and provide an e-commerce experience for users.

[0086] The item listing platform 610 supports the application of computer programs or software components or services (such as the application 660) as service-specific functions or function sets to meet specific item listing platform requirements or user requirements. The applications can be client-side (user-facing) and server-side (backend). The applications can also include applications without any AI support (such as the application 662), applications supported by traditional AI models (such as the application 664), and applications supported by generative AI models (such as the application 666). For example, the applications can include online storefront applications, mobile shopping applications, administrative and management consoles, payment gateway integrations, user account and authentication applications, search and recommendation engines, inventory and stock management applications, order processing and fulfillment applications, customer support and communication tools, content management systems, analytics and reporting applications, marketing and promotion applications, multi-channel integration applications, log and error tracking applications, customer relationship management (CRM) applications, security applications, and APIs and web services used in combination to efficiently provide an e-commerce experience for users.

[0087] The project listing platform 610 may include a machine learning engine (e.g., machine learning engine 670). The machine learning engine 670 refers to a machine learning framework or machine learning platform that provides infrastructure and tools for designing, training, evaluating, and deploying machine learning models. The machine learning engine 670 can serve as the backbone for developing and deploying machine learning applications and solutions. The machine learning engine 670 can also provide tools for visualizing data and model results, as well as interpretive model decision-making for gaining insights into how the model makes predictions.

[0088] The machine learning engine 670 can provide the necessary libraries, algorithms, and utilities to perform various tasks in the machine learning workflow. The machine learning workflow can include data processing, model selection, model training, model evaluation, hyperparameter tuning, scalability, model deployment, inference, integration, customization, data visualization. The machine learning engine 670 can include pre-trained models for various tasks, thus simplifying the development process. In this way, the machine learning engine 670 can streamline the entire machine learning process from data preparation and model training to deployment and inference, making it accessible and efficiently usable by different types of users (e.g., customers, data scientists, machine learning engineers, and developers) working on a wide range of machine learning applications.

[0089] The machine learning engine 670 can be implemented as a component in the project listing system 600 that utilizes machine learning algorithms and techniques (e.g., machine learning algorithm 672) to enhance various aspects of the project listing system functionality. The machine learning engine 670 can provide a selection of machine learning algorithms and techniques for teaching a computer to learn from data and make predictions or decisions without explicit programming. These techniques are widely used in various applications across different industries and can include the following examples: supervised learning (e.g., linear regression: classification, support vector machine (SVM)); unsupervised learning (e.g., clustering, principal component analysis (PCA), association rules (e.g., apriori)); reinforcement learning (e.g., Q-learning, deep Q-network (DQN)); deep learning (e.g., neural networks, convolutional neural networks (CNN), and recurrent neural networks (RNN)); and ensemble learning random forest.

[0090] Machine learning training data 120 supports the process of building, training, and fine-tuning machine learning models. Machine learning training data 120 consists of a labeled dataset used to teach a machine learning model to recognize patterns, make predictions, or perform a specific task. Training data typically consists of two main components: input features (X) and labels or target values (Y). Input features can include variables, attributes, or characteristics used as inputs to the machine learning model. Depending on the nature of the problem, the input features (X) can be numerical, categorical, or even text. For example, in a model for predicting house prices, the input features might include the number of bedrooms, square footage, neighborhood, etc. Labels or target values (Y) include the values that the model is intended to predict or classify. The label represents the expected output or ground truth for each corresponding set of input features. For example, in a spam classifier, the label will indicate whether each email is spam (i.e., binary classification). The training process involves presenting the training data to the model, and the model learns to make predictions or decisions by identifying patterns and the relationships between the input features (X) and the target values (Y). Machine learning algorithms adjust their internal parameters during training to minimize the difference between their predictions and the actual labels in the training data. The machine learning engine 670 can use historical and real-time data to train models and make predictions, thus continuously improving performance and the user experience.

[0091] The machine learning engine 670 can include machine learning models (e.g., machine learning model 676) generated using the machine learning engine workflow. The machine learning model 676 can include both generative AI models and traditional AI models that can be adopted in the project list system 600. Generative AI models are designed to generate new data (usually in the form of text, images, or other media) based on patterns and knowledge learned from existing data. Generative AI models can be adopted in various ways, including content generation, product image generation, personalized product recommendations, natural language chatbots, and content summarization. Traditional AI models cover a wide range of algorithms and technologies and can be adopted in various ways, including recommendation systems, predictive analytics, search algorithms, fraud detection, customer segmentation, image classification, natural language processing (NLP), and A / B testing and optimization. In many cases, a combination of both generative AI models and traditional AI models can be adopted to provide a comprehensive and efficient e-commerce experience by combining data-driven insights and creativity.

[0092] The machine learning engine 670 can be used to analyze data, make predictions, and automate processes to provide users with a more personalized and efficient shopping experience. For example, product recommendation search and filtering, pricing optimization, inventory and stock management, customer segmentation, customer churn prediction and retention, fraud detection, sentiment analysis, customer support and chatbots, image and video analysis, and advertising targeting and marketing. The specific applications of machine learning within the project list platform 610 can vary depending on specific goals, available data, and resources.

[0093] Example Distributed Computing System Environment

[0094] Now refer to Figure 7 , Figure 7 , which shows an example distributed computing environment 700 in which embodiments of the present disclosure can be employed. Specifically, Figure 7 shows a high-level architecture of an example cloud computing platform 710 that can host a technical solution environment or a part thereof (e.g., a data trustee environment). It should be understood that such and other arrangements described herein are merely illustrative as examples. For example, as described above, many of the elements described herein can be implemented as discrete or distributed components, or in combination with other components, and can be implemented in any suitable combination and location. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, and function groupings) other than those shown can be used, or the shown arrangements and elements can be replaced with other arrangements or elements (e.g., machines, interfaces, functions, sequences, and function groupings).

[0095] The data center can support the distributed computing environment 700, the cloud computing platform 710, the racks 720, and the nodes 730 (e.g., computing devices, processing units, or blade servers) in the racks 720. The technical solution environment can be implemented using the cloud computing platform 710 that runs cloud services across different data centers and geographical regions. The cloud computing platform 710 can implement a structure controller 740 component for resource allocation, deployment, upgrade, and management of the cloud services. Generally, the cloud computing platform 710 is used to store data or run service applications in a distributed manner. The cloud computing infrastructure 710 in the data center can be configured to host and support the operation of endpoints of specific service applications. The cloud computing infrastructure 710 can be a public cloud, a private cloud, or a dedicated cloud.

[0096] The node 730 may be equipped with a host 750 (e.g., an operating system or a runtime environment) that runs a defined software stack on the node 730. The node 730 may also be configured to perform specialized functions (e.g., a compute node or a storage node) within the cloud computing platform 710. The node 730 is allocated to run one or more parts of a tenant's service application. A tenant may refer to a customer who utilizes the resources of the cloud computing platform 710. The service application components of the cloud computing platform 710 that support a specific tenant may be referred to as a multi-tenant infrastructure or a tenant environment. The terms service application, application, or service may be used interchangeably herein and broadly refer to any software or part of software that runs on top of a data center or accesses the storage and computing device locations within a data center.

[0097] When the node 730 supports more than one separate service application, the node 730 may be partitioned into virtual machines (e.g., virtual machines 752 and 754). A physical machine may also run separate service applications simultaneously. A virtual machine or a physical machine may be configured as a personalized computing environment supported by resources 760 (e.g., hardware resources and software resources) in the cloud computing platform 710. It is contemplated that resources may be configured for a specific service application. In addition, each service application may be partitioned into functional parts such that each functional part can run on a separate virtual machine. In the cloud computing platform 710, multiple servers may be used to run service applications and data storage operations may be performed in a cluster. Specifically, the servers may perform data operations independently but are exposed as a single device called a cluster. Each server in the cluster may be implemented as a node.

[0098] The client device 780 may be linked to a service application in the cloud computing platform 710. The client device 780 may be any type of computing device that may correspond to the computing device 700 described with reference to Figure 7 For example, the client device 780 may be configured to issue commands to the cloud computing platform 710. In an embodiment, the client device 780 may communicate with the service application via a virtual Internet Protocol (IP) and a load balancer, or other means that direct communication requests to a specified endpoint in the cloud computing platform 710. The components of the cloud computing platform 710 may communicate with each other via a network (not shown), which may include but is not limited to one or more local area networks (LANs) and / or wide area networks (WANs).

[0099] Example Computing Environment

[0100] After briefly describing an overview of embodiments of the present invention, an example operating environment in which embodiments of the present invention may be implemented is described below to provide a general context for aspects of the present invention. Specifically, first refer to Figure 8, which shows an example operating environment for implementing an embodiment of the present invention, which is generally designated as computing device 800. Computing device 800 is one example of a suitable computing environment and is not intended to imply any limitation as to the scope of use or functionality of the present invention. Computing device 800 should also not be construed as having any dependency or requirement related to any one or combination of the components shown.

[0101] The present invention may be described in the general context of computer-executable instructions, such as program modules, executed by a computer or other machine, such as a personal data assistant or other handheld device. Generally, program modules, including routines, programs, objects, components, data structures, etc., refer to code that performs particular tasks or implements particular abstract data types. The present invention may be implemented in a variety of system configurations, including handheld devices, consumer electronics, general-purpose computers, more specialized computing devices, etc. The present invention may also be implemented in a distributed computing environment where tasks are performed by remote processing devices linked via a communications network.

[0102] Referring Figure 8 , computing device 800 includes bus 810, which directly or indirectly couples the following devices: memory 812, one or more processors 814, one or more presentation components 816, input / output ports 818, input / output components 820, and example power supply 822. Bus 810 represents one or more buses (e.g., an address bus, a data bus, or a combination thereof). For clarity of concept, lines are used to represent Figure 8 the various blocks, and other arrangements of the components and / or component functions are also contemplated. For example, a presentation component, such as a display device, may be considered an I / O component. Additionally, a processor has memory. We recognize this as being in the nature of the art and reiterate Figure 8 that the figures only illustrate example computing devices that may be used in conjunction with one or more embodiments of the present invention. Since all categories, such as "workstation", "server", "laptop", "handheld device", etc., are contemplated within the Figure 8 scope of, and are referred to as "computing device", no distinction is made between such categories.

[0103] Computing device 800 generally includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by computing device 800 and includes both volatile and nonvolatile media, removable and non-removable media. By way of example and not limitation, computer-readable media may include computer storage media and communication media.

[0104] Computer storage media includes volatile and non-volatile media, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to: RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage devices, magnetic tape cartridges, tapes, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by computing device 800. Computer storage media itself does not include signals.

[0105] Communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal (e.g., a carrier wave or other transmission mechanism), and includes any information delivery medium. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media (e.g., a wired network or direct wired connection) and wireless media (e.g., acoustic, RF, infrared, and other wireless media). Any of the foregoing combinations should also be included within the scope of computer-readable media.

[0106] Memory 812 includes computer storage media in the form of volatile and / or non-volatile memory. The memory can be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, etc. Computing device 800 includes one or more processors that read data from various entities (e.g., memory 812 or I / O component 820). Presentation component 816 presents data indications to a user or other device. Exemplary presentation components include display devices, speakers, printing components, vibration components, etc.

[0107] I / O port 818 allows computing device 800 to be logically coupled to other devices including I / O component 820, some of which may be built-in. Illustrative components include microphones, joysticks, gamepads, satellite dishes, scanners, printers, wireless devices, etc.

[0108] Additional structural and functional features of embodiments of the technical solution

[0109] After determining the various components utilized herein, it should be understood that any number of components and arrangements may be employed to achieve the desired functionality within the scope of the present disclosure. For example, for clarity of concept, lines are used to represent the components in the embodiments depicted in the figures. Other arrangements of these and other components may also be implemented. For example, although some components are depicted as single components, many of the elements described herein may be implemented as discrete or distributed components, or in combination with other components, and may be implemented in any suitable combination and location. Some elements may be entirely omitted. Additionally, the various functions described herein as being performed by one or more entities may be performed by hardware, firmware, and / or software, as described below. For example, various functions may be performed by a processor executing instructions stored in a memory. Thus, other arrangements and elements (e.g., machines, interfaces, functions, sequences, and groupings of functions) other than those shown may be used, or the shown arrangements and elements may be replaced by other arrangements or elements (e.g., machines, interfaces, functions, sequences, and groupings of functions).

[0110] The embodiments described in the following paragraphs may be combined with one or more of the specifically described alternatives. Specifically, the claimed embodiments may include alternative references to more than one other embodiment. The claimed embodiments may specify further limitations of the claimed subject matter.

[0111] The subject matter of the embodiments of the present invention has been specifically described herein to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. On the contrary, in combination with other existing or future technologies, the inventors have envisioned that the claimed subject matter may also be embodied in other ways, to include different steps or combinations of steps similar to those described in this document. Additionally, although the terms "step" and / or "block" may be used herein to denote different elements of the methods employed, these terms should not be construed as implying any particular order among or between the steps disclosed herein, unless the order of the steps is explicitly described.

[0112] For the purposes of the present disclosure, the word "comprising" has the same broad meaning as the word "including", and the word "access" includes "receiving", "referencing", or "retrieving". Additionally, the word "communicate" has the same broad meaning as the words "receive" or "send" as implemented by a software or hardware bus, receiver, or transmitter using the communication media described herein. Further, unless otherwise indicated to the contrary, words such as "a" and "an" include both the plural and the singular. Thus, for example, when there is one or more features, the constraint of "a feature" is satisfied. Additionally, the term "or" includes conjunctive, disjunctive, and both (thus, a or b includes a, or b, and a and b).

[0113] For purposes of the foregoing detailed discussion, embodiments of the present invention are described with reference to a distributed computing environment; however, the distributed computing environment described herein is merely exemplary. Components may be configured to perform novel aspects of the embodiments, where the term "configured to" may refer to "programmed to" perform a particular task or implement a particular abstract data type using code. Additionally, while embodiments of the present invention may generally refer to the technical solution environments and diagrams described herein, it will be understood that the described techniques may extend to other implementation contexts.

[0114] Embodiments of the present invention have been described with respect to specific embodiments that are intended in all respects to be illustrative and not restrictive. Alternative embodiments will become apparent to those skilled in the art to which the present invention pertains without departing from the scope of the present invention.

[0115] From the foregoing, it will be seen that the present invention is well suited to attain all the ends and objects hereinabove set forth, together with those inherent and obvious advantages of the structures.

[0116] It will be understood that certain features and subcombinations are useful and may be employed without reference to other features or subcombinations. This is contemplated by the claims and is within the scope of the claims.

Claims

1. A computerized system comprising: one or more computer processors; as well as A computer memory storing computer usable instructions that, when used by the one or more computer processors, cause the one or more computer processors to perform operations comprising: accessing review data associated with a first user of a first item in the item listing system; Based on the review data, identifying review-based recommendation guideline features for the first project, wherein the review-based recommendation guideline features are associated with a review-based recommendation guideline, the review-based recommendation guideline identifying user preferences for project features for the corresponding project, wherein the review-based recommendation guideline is generated using a generative artificial intelligence (AI) model and the user's review data; mapping the review-based recommendation guideline features of the first item to review-based recommendation guideline features of a second item, wherein the review-based recommendation guideline features of the second item are associated with review-based recommendation guidelines of one or more second users; The second item is communicated as a review-based recommended item associated with the review data.

2. The system according to claim 1, wherein: The review data is associated with a review interface of the item listing system, the review interface enabling near real-time review-based recommended items based on the review data received via the review interface.

3. The system according to claim 1, wherein: Identifying the review-based recommendation guideline features for the first item is based on: generating review-based recommendation data including user preferences for project features of projects using the generative AI model and the review data; as well as The review-based recommendation guide for the user is generated.

4. The system according to claim 1, wherein: The review-based recommendation guideline features are mapped according to a review-based recommendation logic, the review-based recommendation logic indicating how items should be recommended to a user according to the user preference attributes and the review-based recommendation guideline features.

5. The system according to claim 1, wherein: Mapping the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of the second item is performed using review-based recommendation logic, and the review-based recommendation logic compares the review-based recommendation guideline of the first item with multiple review data recommendation guidelines to match according to the review-based recommendation guideline features.

6. The system according to claim 1, wherein: The review-based recommendation guideline is associated with a review-based recommendation guideline data structure, which supports storing review-based recommendation guideline features, user preference attributes, and generative AI review-based insights.

7. The system according to claim 1, wherein: The second item is associated with a generative AI review-based insight comprising one or more review data excerpts corresponding to the one or more second users.

8. The system of claim 1, wherein the operations further comprise: accessing review data from a plurality of users of corresponding items associated with the item listing system; generating review-based recommendation guide data using a generative artificial intelligence (AI) model and the review data, wherein the review-based recommendation guide data includes user preferences for item features associated with each item; generating a plurality of review-based recommendation guidelines for the user and the corresponding items; as well as The plurality of review-based recommendation guidelines are deployed to support identifying review-based recommendation items for a user.

9. The system of claim 1, wherein the operations further comprise: communicating review data associated with a user of a first item in an item listing system; accessing a second item and a generative AI-based insight for the second item based on communicating the review data, wherein the second item is a recommended item based on the review; as well as The second item and the generative AI's review-based insights are displayed on a graphical user interface associated with the review data.

10. The system according to claim 9, wherein: The generative AI review-based insights include one or more review data excerpts corresponding to the one or more second users.

11. One or more computer storage media having computer executable instructions embodied thereon, which when executed by a computing system having a processor and a memory, cause the processor to perform operations comprising: communicating review data associated with a user of a first item in an item listing system; Based on communicating the review data, accessing a second item and a generative AI-based insight for the second item, wherein the second item is a review-based recommended item, the second item is associated with a review-based recommendation guide for the second item, wherein the review-based recommendation guide is generated using a generative artificial intelligence (AI) model and the user's review data; and The second item and the generative AI's review-based insights are displayed on a graphical user interface associated with the review data.

12. The medium according to claim 11, wherein The review data is associated with a review interface of the item listing system, the review interface enabling near real-time review-based recommended items based on the review data received via the review interface.

13. The medium according to claim 11, wherein The generative AI review-based insights include one or more review data excerpts corresponding to one or more second users.

14. The medium according to claim 11, wherein The second item is identified based on: identifying a review-based recommendation guideline feature for the first item, wherein the review-based recommendation guideline feature is associated with a review-based recommendation guideline that identifies a user preference for an item feature for a corresponding item; mapping the review-based recommendation guideline features of the first item to the review-based recommendation guideline features of the second item, wherein the review-based recommendation guideline features of the second item are associated with review-based recommendation guidelines of one or more second users; and The second item is communicated as a review-based recommended item associated with the review data.

15. The medium according to claim 11, wherein The review-based recommendation guideline is associated with a review-based recommendation guideline data structure, which supports storing review-based recommendation guideline features, user preference attributes, and generative AI review-based insights.

16. A computer-implemented method, the method comprising: accessing review data from a plurality of users of corresponding items associated with the item listing system; Using a generative artificial intelligence (AI) model and the review data, generating review-based recommendation guide data, the review-based recommendation guide data including user preferences for item features associated with each item; generating a plurality of review-based recommendation guidelines for the user and the corresponding items using the review-based recommendation guide data; as well as The plurality of review-based recommendation guidelines are deployed to support identifying review-based recommendation items for a user.

17. The method according to claim 16, the operation further comprising: accessing a review-based recommendation guide of a first user for a first item in the item listing system; identifying review-based recommendation guideline features for the first item based on the review-based recommendation guideline; mapping the review-based recommendation guideline features of the first item to review-based recommendation guideline features of a second item, wherein the review-based recommendation guideline features of the second item are associated with review-based recommendation guidelines of one or more second users; as well as The second item is communicated as a review-based recommended item associated with the review data.

18. The method according to claim 17, wherein: The review-based recommendation guideline features are mapped according to a review-based recommendation logic that indicates how items should be recommended to a user based on the user preference attributes and the review-based recommendation guideline features.

19. The method according to claim 17, wherein: The second item is associated with a generative AI review-based insight comprising one or more review data excerpts corresponding to the one or more second users.

20. The method according to claim 19, wherein: The review-based recommendation guideline is associated with a review-based recommendation guideline data structure, which supports storing review-based recommendation guideline features, user preference attributes, and generative AI review-based insights.

Images