公开(公告)号：US20240249318A1

公开(公告)日：2024-07-25

申请号：US18420546

申请日：2024-01-23

申请人： Evan Spiegel ,  Robert Cornelius Murphy ,  Celia Nicole Mourkogiannis ,  Edward Mata ,  Eitan Pilipski ,  Jacob Andreou ,  Jackie Assa ,  Joshua Siegel ,  Nima Khajehnouri ,  Steven Hwang ,  Daniel Moreno ,  Jacob Catalano ,  Charles Melbye

发明人： Evan Spiegel ,  Robert Cornelius Murphy ,  Celia Nicole Mourkogiannis ,  Edward Mata ,  Eitan Pilipski ,  Jacob Andreou ,  Jackie Assa ,  Joshua Siegel ,  Nima Khajehnouri ,  Steven Hwang ,  Daniel Moreno ,  Jacob Catalano ,  Charles Melbye

IPC分类号： G06Q30/0251 ,  G06Q30/0241 ,  H04L51/02

CPC分类号： G06Q30/0257 ,  G06Q30/0277 ,  H04L51/02

摘要： A system and method for determining user intent and providing targeted advertising using chatbot interactions is disclosed. The system receives user prompts during chat sessions with a chatbot and generates responses using a large language model. User intent is extracted by analyzing the chat conversations using natural language processing and machine learning techniques. The extracted user intent, comprising weighted keywords and concepts, is used to create a user intent profile. Targeted advertising content is generated based on the user intent profile and provided to the user during subsequent platform interactions. The large language model is continuously retrained using user engagement data to improve intent modeling accuracy. User privacy is maintained by limiting context extraction to chatbot conversations. The system enables personalized and relevant advertising by inferring user intent through conversational interactions.

公开(公告)号：US09110985B2

公开(公告)日：2015-08-18

申请号：US12906051

申请日：2010-10-15

申请人： Riccardo Boscolo ,  Behnam Attaran Rezaei ,  Vwani P. Roychowdhury ,  Albert Chern ,  Nima Khajehnouri

发明人： Riccardo Boscolo ,  Behnam Attaran Rezaei ,  Vwani P. Roychowdhury ,  Albert Chern ,  Nima Khajehnouri

IPC分类号： G06F17/30

CPC分类号： G06F17/30734 ,  G06F17/3089

摘要： A method for generating a conceptual association graph from structured content includes grouping content nodes into one or more topically biased clusters, the content nodes comprising structured digital content and unstructured digital content, the grouping based at least in part on the connectedness of each content node member to other content node members in the same cluster. The method also includes, responsive to the grouping, tagging the content nodes with one or more descriptive concepts. The method also includes, responsive to the tagging, establishing one or more associations between the one or more concepts, the one or more associations indicating a relevance of the one or more associations, the indicating based at least in part on patterns of co-occurrence of concepts in the tagged content nodes.

摘要翻译： 用于从结构化内容生成概念关联图的方法包括将内容节点分组成一个或多个局部偏置的集群，所述内容节点包括结构化数字内容和非结构化数字内容，所述分组至少部分地基于每个内容节点成员的连接性 到同一集群中的其他内容节点成员。 该方法还包括响应于分组，使用一个或多个描述性概念标记内容节点。 所述方法还包括响应于所述标记，在所述一个或多个概念之间建立一个或多个关联，所述一个或多个关联指示所述一个或多个关联的相关性，所述指示至少部分地基于同现的模式 的标签内容节点中的概念。

公开(公告)号：US20090300009A1

公开(公告)日：2009-12-03

申请号：US12476205

申请日：2009-06-01

申请人： Behnam A. Rezaei ,  Riccardo Boscolo ,  Nima Khajehnouri ,  Vwani P. Roychowdhury ,  Himawan Gunadhi

发明人： Behnam A. Rezaei ,  Riccardo Boscolo ,  Nima Khajehnouri ,  Vwani P. Roychowdhury ,  Himawan Gunadhi

IPC分类号： G06F17/30

CPC分类号： H04L67/22 ,  G06Q30/0251 ,  H04L67/306

摘要： A pre-computed concept map represents concepts, concept metadata, and relationships between the plurality of concepts. Online user behavior may be predicted by correlating one or more online events of a user with one or more features of the concept map, aggregating a concept map history of the user to obtain online behavior over time, aggregating online behavior of the user and one or more other users to obtain aggregated online user behavior, and predicting future online behavior of the user based at least in part on the online behavior of the user and the aggregated online user behavior. The predicted behavior may be used to target ads that the user is likely to find relevant.

摘要翻译： 预先计算的概念图表示概念，概念元数据以及多个概念之间的关系。 可以通过将用户的一个或多个在线事件与概念图的一个或多个特征相关联来预测在线用户行为，聚合用户的概念图历史以获得随时间的在线行为，聚合用户的在线行为以及一个或多个 更多其他用户获得聚合的在线用户行为，并至少部分地基于用户的在线行为和聚合的在线用户行为来预测用户的未来在线行为。 预测的行为可能用于定位用户可能会找到相关的广告。