Pinterest, Inc.

Google Inc.

Yunsong Guo

Yu Liu

Jinfeng Zhuang

Chenyi Li

Heath Vinicombe

Ibrahim Badr

Imran R Mansuri

Jinyu Xie

Anant Srinivas Subramanian

Systems and methods for proactive query and content suggestion can include obtaining web data, determining a change event occurred, and generating a query and content suggestion. Generating the query and content suggestion can include processing data descriptive of the change event with a generative model to generate one or more model-generated query suggestions. One or more web resources can be obtained then processed to generate a change event summary. The one or more query suggestions and the change event summary can then be provided for display.

Proactive query and content suggestion with generative model generated question and answer

Systems and methods for identifying relevant content within a corpus of visual content items in response to a user's text-based query are presented. In response to a text-based query, the query is mapped to a most-engaged content item of the corpus of visual content items included in responses to the query from a plurality of users. At least one text-based term associated with the most-engaged content item is identified and combined with the query from an expanded query. The expanded query is mapped to an interest node of an interest taxonomy and content items associated with the mapped interest node are identified. At least some of the content items associated with the mapped interest node are selected and returned as response content to the received query.

Query to interest mapping

System and methods are presented for associating a user-posted content item with an interest node of an interest taxonomy. A corpus of content items and an interest taxonomy are maintained. The interest taxonomy comprises interest nodes organized in a hierarchical organization, each node having a text label descriptive of the interest node. Additionally, the content items of the corpus are associated with one or more interest nodes of the interest taxonomy. Upon receiving a user-posted content item, feature sets of the received content item are generated, these feature sets based on features and/or aspects of the received content item. After generating at least one feature set, the at least one feature set is provided to an interest prediction model that generates candidate interest nodes for the user-posted content item. At least some of the candidate interest nodes are associated with the user-posted content item in the corpus.

Associating user-provided content items to interest nodes

Systems and methods are presented for inferring an embedding vector of an item of a first type into the embedding space. Upon receiving a first time for which there is no embedding vector, documents of a document corpus that include (co-occurrence) both the received item and other items of the same type are identified. Of those other items that have embedding vectors, those embedding vectors are retrieved and averaged. The resulting averaged embedding vector is established as an inferred embedding vector for the received item.

Embedding inference

Determining emebedding vectors for an unmapped content item using embedding inferenece

Systems and methods for recommending content to an online service user are presented. In response to a request from a user, a set of n-grams of the request are generated, with each n-gram comprising one or more terms from the request and each n-gram of the set of n-grams being unique. Embedding vectors projecting the n-grams into a content item embedding space are generated, and the embedding vectors are combined into a representative embedding vector for the request. The nearest content items are identified according to a distance measure between a projection of the representative embedding vector and embedding vectors of content items of a corpus of content items in the content item embedding space. At least some of the nearest content items are returned as recommended content in response to the request from the user.

Projecting queries into a content item embedding space

Systems and methods are set forth for identifying key-words and key-phrases, collectively referred to as key-terms, from a document. A document is accessed and the document is tokenized, each token corresponding to a word or phrase occurring within the document. Term frequencies of the terms of the tokens may be determined and TF-IDF scores may be generated according to the term frequencies. Embedding vectors for the terms of the tokens may be generated and a document embedding vector may be generated according to the embedding vectors of the documents. A similarity score may be determined for each token according to the embedding vector of a token and the document embedding vector. Additionally, an overall score may be determined for each token according to the term of the token, a TF-IDF score, similarity scores, and the like. Terms from the highest scoring tokens are selected as the key-terms for the document.

Growing community of inventors

San Mateo, CA, United States of America

Yunsong Guo