Patents by Inventor Tzu-Chiang Liou
Tzu-Chiang Liou has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11915158Abstract: One or more computing devices, systems, and/or methods for cross-domain action prediction are provided. Action sequence embeddings are generated based upon a textual embedding and a graph embedding utilizing past user action sequences corresponding to sequences of past actions performed by users across a plurality of domains. An autoencoder is trained to utilize the action sequence embeddings to project the action sequence embeddings to obtain intent space vectors. A service switch classifier is trained using the intent space vectors. In response to the service switch classifier predicting that a current user will switch from a current domain to a next domain, the current user is provided with a recommendation of an action corresponding to the next domain.Type: GrantFiled: January 16, 2023Date of Patent: February 27, 2024Assignee: Yahoo Assets LLCInventors: Su-Chen Lin, Zhungxun Liao, Jian-Chih Ou, Tzu-Chiang Liou
-
Patent number: 11914582Abstract: One or more computing devices, systems, and/or methods for generating a list of suggested queries associated with one or more keywords are provided. For example, one or more keywords may be received via a search interface. A plurality of queries associated with the one or more keywords may be determined based upon the one or more keywords and a historical query database. A plurality of relationship scores associated with the plurality of queries may be generated based upon a plurality of search sessions associated with the historical query database. The historical query database may be analyzed to determine a plurality of click rates associated with the plurality of queries. A list of suggested queries may be generated based upon the plurality of relationship scores and the plurality of click rates.Type: GrantFiled: June 28, 2022Date of Patent: February 27, 2024Assignee: Yahoo Assets LLCInventors: Su-Chen Lin, Jian-Chih Ou, Tzu-Chiang Liou, Wei-Lun Su
-
Publication number: 20230153660Abstract: One or more computing devices, systems, and/or methods for cross-domain action prediction are provided. Action sequence embeddings are generated based upon a textual embedding and a graph embedding utilizing past user action sequences corresponding to sequences of past actions performed by users across a plurality of domains. An autoencoder is trained to utilize the action sequence embeddings to project the action sequence embeddings to obtain intent space vectors. A service switch classifier is trained using the intent space vectors. In response to the service switch classifier predicting that a current user will switch from a current domain to a next domain, the current user is provided with a recommendation of an action corresponding to the next domain.Type: ApplicationFiled: January 16, 2023Publication date: May 18, 2023Inventors: Su-Chen Lin, Zhungxun Liao, Jian-Chih Ou, Tzu-Chiang Liou
-
Patent number: 11556822Abstract: One or more computing devices, systems, and/or methods for cross-domain action prediction are provided. Action sequence embeddings are generated based upon a textual embedding and a graph embedding utilizing past user action sequences corresponding to sequences of past actions performed by users across a plurality of domains. An autoencoder is trained to utilize the action sequence embeddings to project the action sequence embeddings to obtain intent space vectors. A service switch classifier is trained using the intent space vectors. In response to the service switch classifier predicting that a current user will switch from a current domain to a next domain, the current user is provided with a recommendation of an action corresponding to the next domain.Type: GrantFiled: May 27, 2020Date of Patent: January 17, 2023Assignee: YAHOO ASSETS LLCInventors: Su-Chen Lin, Zhungxun Liao, Jian-Chih Ou, Tzu-Chiang Liou
-
Publication number: 20220374761Abstract: The instant system and methods solves the cold start problem through various systems and methods directed to aggregating user interaction data associated with a user over a period of time, generating an embedding model based on the aggregated user interaction data, generating a content embedding vector based on the embedding model, generating an embedding profile vector based on the embedding model, storing the embedding profile vector in a storage device, receiving each of the content embedding vector and embedding vector profile for training a ranking model, and generating a predicted list of one or more content items of interest for recommending to the user.Type: ApplicationFiled: May 6, 2021Publication date: November 24, 2022Inventors: Peng-Yu CHEN, Yu-Ting CHANG, Chi-Chia HUANG, Yi-Ting TSAO, Cheng-En YEN, Tzu-Chiang LIOU
-
Publication number: 20220327163Abstract: One or more computing devices, systems, and/or methods for generating a list of suggested queries associated with one or more keywords are provided. For example, one or more keywords may be received via a search interface. A plurality of queries associated with the one or more keywords may be determined based upon the one or more keywords and a historical query database. A plurality of relationship scores associated with the plurality of queries may be generated based upon a plurality of search sessions associated with the historical query database. The historical query database may be analyzed to determine a plurality of click rates associated with the plurality of queries. A list of suggested queries may be generated based upon the plurality of relationship scores and the plurality of click rates.Type: ApplicationFiled: June 28, 2022Publication date: October 13, 2022Inventors: Su-Chen Lin, Jian-Chih Ou, Tzu-Chiang Liou, Wei-Lun Su
-
Publication number: 20220245507Abstract: One or more computing devices, systems, and/or methods for implementing an automated model update pipeline are provided. User behavior data associated with content provided to users may be collected. An automatic model training is invoked to train a new model to output a set of model parameters based upon a configuration specifying a target audience, features extracted from user behavior data, and training model parameters.Type: ApplicationFiled: February 2, 2021Publication date: August 4, 2022Inventors: Cheng-En Yen, Yi-ting Tsao, Yu-Ting Chang, Chi-Chia Huang, Peng-Yu Chen, Tzu-Chiang Liou
-
Patent number: 11372924Abstract: One or more computing devices, systems, and/or methods for generating a list of suggested queries associated with one or more keywords are provided. For example, one or more keywords may be received via a search interface. A plurality of queries associated with the one or more keywords may be determined based upon the one or more keywords and a historical query database. A plurality of relationship scores associated with the plurality of queries may be generated based upon a plurality of search sessions associated with the historical query database. The historical query database may be analyzed to determine a plurality of click rates associated with the plurality of queries. A list of suggested queries may be generated based upon the plurality of relationship scores and the plurality of click rates.Type: GrantFiled: June 21, 2019Date of Patent: June 28, 2022Assignee: YAHOO ASSETS LLCInventors: Su-Chen Lin, Jian-Chih Ou, Tzu-Chiang Liou, Wei-Lun Su
-
Publication number: 20210374577Abstract: One or more computing devices, systems, and/or methods for cross-domain action prediction are provided. Action sequence embeddings are generated based upon a textual embedding and a graph embedding utilizing past user action sequences corresponding to sequences of past actions performed by users across a plurality of domains. An autoencoder is trained to utilize the action sequence embeddings to project the action sequence embeddings to obtain intent space vectors. A service switch classifier is trained using the intent space vectors. In response to the service switch classifier predicting that a current user will switch from a current domain to a next domain, the current user is provided with a recommendation of an action corresponding to the next domain.Type: ApplicationFiled: May 27, 2020Publication date: December 2, 2021Inventors: Su-Chen Lin, Zhungxun Liao, Jian-Chih Ou, Tzu-Chiang Liou
-
Publication number: 20210295410Abstract: Disclosed are systems and methods for improving interactions with and between computers in content providing, searching and/or hosting systems supported by or configured with devices, servers and/or platforms. The disclosed systems and methods provide a novel recommendation framework that automatically applies transfer learning from a knowledge-base and generating a multi-variable based unified recommendation. The framework dynamically develops a universal word dictionary between a source language and a target language based on Natural Language Processing (NLP word embeddings. This not only leverages the accuracy of multi-lingual product embeddings, but also increases the efficiency and effectiveness in how it can be applied. The disclosed systems and methods, therefore, provides a novel computerized solution for how different knowledges learnt from one electronic platform can be adapted to a global platform for providing global users electronic information.Type: ApplicationFiled: March 23, 2020Publication date: September 23, 2021Inventors: Wei-Lun SU, Pei-Ling CHEN, Chia-Chuan HO, Tzu-Chiang LIOU
-
Publication number: 20210141825Abstract: The present teaching relates to a method, system, and programming for searching content. A sketch of an object is obtained from a user. The sketch is processed by a neural network to generate an image corresponding to the sketch of the object. One or more features are extracted from the image, and one or more images previously stored are identified that have features similar to the one or more features. The one or more images are provided to the user.Type: ApplicationFiled: November 12, 2019Publication date: May 13, 2021Inventors: Wei-Lun Su, Wen-Hsuan Wu, Ching-Han Chang, Tzu-Chiang Liou
-
Publication number: 20200401629Abstract: One or more computing devices, systems, and/or methods for generating a list of suggested queries associated with one or more keywords are provided. For example, one or more keywords may be received via a search interface. A plurality of queries associated with the one or more keywords may be determined based upon the one or more keywords and a historical query database. A plurality of relationship scores associated with the plurality of queries may be generated based upon a plurality of search sessions associated with the historical query database. The historical query database may be analyzed to determine a plurality of click rates associated with the plurality of queries. A list of suggested queries may be generated based upon the plurality of relationship scores and the plurality of click rates.Type: ApplicationFiled: June 21, 2019Publication date: December 24, 2020Inventors: Su-Chen Lin, Jian-Chih Ou, Tzu-Chiang Liou, Wei-Lun Su