Baidu USA LLC

Google Inc.

Wei Fan

Hongliang Fei

Nan Du

Sundeep Tirumalareddy

Daniel Glasner

Shulong Tan

Thomas Richard Strohmann

Sushrut Suresh Karanjkar

Yi Zhen

Chaochun Liu

Manas Ashok Pathak

Shubhang Verma

Suddha Kalyan Basu

Wenyuan Yin

Dawen Zhou

Yusheng Xie

Yu Long Cao

Richard Chun Ching Wang

Weicheng Zhu

Jing Zhai

Erheng Zhong

Yaliang Li

Bocong Liu

Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

Embedding based retrieval for image search

Systems and methods are disclosed for question generation to obtain more related medical information based on observed symptoms from a patient. In embodiments, possible diseases associated with the observed symptoms are generated by querying a knowledge graph. In embodiments, candidate symptoms associated with the possible diseases are also identified and are combined with the observed symptoms to obtain combined symptom sets. In embodiments, discriminative scores for the candidate symptom sets are determined and candidate symptoms with top discriminative scores are selected. In embodiments, these selected candidate symptoms may be checked for conflicts with observed symptoms and removed from further consideration if a conflict exists. In embodiments, one or more questions may be generated based on the remaining selected candidate systems to aid in collecting information about the patient. In embodiments, the process may be repeated with the updated observed symptoms.

Question generation systems and methods for automating diagnosis

Presented are systems and methods that allow healthcare providers and governments to infer demand for healthcare resources to ensure effective and timely healthcare services to patients by reducing healthcare supply shortages, emergencies, and healthcare costs. In embodiments, this is accomplished by gathering data from a number of sources to generate labeled records from which entity features and relationships between entities are extracted, correlates, and/or combined with other external healthcare data. In embodiments, this information is used to train a model that predicts healthcare resource demands given a set of input conditions or factors.

Systems and methods for estimating healthcare resource demand

Presented are relation inference methods and systems that use deep learning techniques for data mining documents to discover a relation between terms of interest in a given field covering a specific topic. For example, in the healthcare domain, various embodiments of the present disclosure provide for a relation inference system that mines large-scale medical documents in a free-text database to extract symptom and disease terms and generates relation information that aids in disease diagnosis. In embodiments, this is accomplished by training and using an RNN, such as an LSTM, a Gated Recurrent Unit (GRU), etc., that takes advantage of a term dictionary to examine co-occurrences of terms of interest within documents to discover correlations between the terms. The correlation may then be used to predict statistically most probable terms (e.g., a disease) related to a given search term (e.g., a symptom).

Systems and methods for relation inference

Systems and methods are disclosed for question generation to infer the most probable cause from the observable outcome and known Noisy-OR causal relations. In embodiments, the outcomes are sorted by indices according to an order including but not limited to the outcomes' natural frequency order, expert-labeled order, machine-learning derived order, etc. According to their assigned indices, in embodiments, observed outcomes with lower indices are assigned for exact inference while observed outcomes with higher indices are assigned for variational inference. In embodiments, results of exact inference and variational inference are combined to predict the most probable cause. The unique combination of exact inference and variational inference according to outcome indices makes the probable cause inferring process faster.

Systems and methods of determining sufficient causes from multiple outcomes

Presented are systems and methods that estimate the strength of a relationship between elements gathered from online and/or offline information sources by estimating the trustworthiness both of the gathered data and the information sources from which the data originates. In one exemplary application, the relatedness between co-occurring symptom and disease terms collected from information sources, such as health-related online databases, is iteratively evaluated based on the trustworthiness of symptom-disease pairings and the trustworthiness of the information sources themselves. In various embodiments of the present disclosure, an objective function is used to extract a knowledge base that aids in identifying a potential relationship between a set of given symptoms provided by a user of an online healthcare service and co-occurring disease terms, such that a likely disease may be inferred from the set of symptoms.

Systems and methods for data and information source reliability estimation

Systems and methods are disclosed to identify entities that have a similar meaning, and may, in embodiments, be grouped into entity groups for knowledge base construction. In embodiments, the entity relations of similarity or non-similarity for an entity pair are predicted as a binary relationship. In embodiments, the prediction may be based upon similarity score between the entities and the entity features, which features are constructed using an entity feature or representation model. In embodiments, the prediction may be an iterative process involving minimum human checking and existing knowledge update. In embodiments, one or more entity groups are formed using graph search from the predicted entity pairs. In embodiments, a group centroid entity may be selected to represent each group based on one or more factors, such as its generality or popularity.

Systems and methods for homogeneous entity grouping

Growing community of inventors

Sunnyvale, CA, United States of America

Wei Fan