Patents by Inventor Yuhui Sun
Yuhui Sun 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: 11797764Abstract: Aspects of the present disclosure relate to a text labeling method and device, and more specifically to the field of deep learning and solving the problem of low efficiency and low accuracy of a feature extraction process. The method can include processing input information to obtain word embedding representation information of the input information, performing dynamic convolution feature extraction on the word embedding representation information to obtain a classification result of each character from the word embedding representation information, and inserting a label into the input information based on the classification result.Type: GrantFiled: July 15, 2020Date of Patent: October 24, 2023Assignee: Beijing Xiaomi Pinecone Electronics Co., Ltd.Inventors: Jingwei Li, Yuhui Sun, Xiang Li
-
Patent number: 11556761Abstract: A method for compressing a neural network model includes: obtaining a first trained teacher model and a second trained teacher model based on N training samples, N being a positive integer greater than 1; for each of the N training samples, determining a first guide component of the first teacher model and a second guide component of the second teacher model respectively, determining a sub optimization target corresponding to the training sample and configured to optimize a student model according to the first guide component and the second guide component, and determining a joint optimization target based on each of the N training samples and a sub optimization target corresponding to the training sample; and training the student model based on the joint optimization target.Type: GrantFiled: March 24, 2020Date of Patent: January 17, 2023Assignee: Beijing Xiaomi Intelligent Technology Co., Ltd.Inventors: Xiang Li, Yuhui Sun, Jingwei Li, Jialiang Jiang
-
Patent number: 11556723Abstract: A method for compressing a neural network model, includes: obtaining a set of training samples including a plurality of pairs of training samples, each pair of the training samples including source data and target data corresponding to the source data; training an original teacher model by using the source data as an input and using the target data as verification data; training intermediate teacher models based on the set of training samples and the original teacher model, one or more intermediate teacher models forming a set of teacher models; training multiple candidate student models based on the set of training samples, the original teacher model, and the set of teacher models, the multiple candidate student models forming a set of student models; and selecting a candidate student model of the multiple candidate student models as a target student model according to training results of the multiple candidate student models.Type: GrantFiled: February 7, 2020Date of Patent: January 17, 2023Assignee: Beijing Xiaomi Intelligent Technology Co., Ltd.Inventors: Xiang Li, Yuhui Sun, Jialiang Jiang, Jianwei Cui
-
Patent number: 11507888Abstract: A training method for a machine translation model, includes: obtaining a multi-domain mixed training data set; performing data domain classification on a plurality of training data pairs in the training data set to obtain at least two domain data subsets; based on each domain data subset, determining at least two candidate optimization targets for the domain data subset, and training at least two candidate single domain models corresponding to each domain data subset based on the at least two candidate optimization targets, respectively; testing the at least two candidate single domain models corresponding to each domain data subset separately, and selecting a candidate optimization target with a highest test accuracy as a designated optimization target for the domain data subset; and training a hybrid domain model based on each domain data subset in the training data set and the designated optimization target corresponding to each domain data subset.Type: GrantFiled: April 3, 2020Date of Patent: November 22, 2022Assignee: Beijing Xiaomi Intelligent Technology Co., Ltd.Inventors: Yuhui Sun, Xiang Li, Jingwei Li
-
Patent number: 11461561Abstract: A method for information processing, includes: obtaining a bilingual vocabulary containing N original bilingual word pairs, N being a positive integer; obtaining an original bilingual training set containing multiple original bilingual training sentence pairs; selecting at least one original bilingual training sentence pair matching any original bilingual word from the original bilingual training set as a bilingual sentence pair candidate; constructing a generalized bilingual sentence pattern based on at least one bilingual sentence pair candidate; and obtaining an augmented bilingual training set containing multiple augmented bilingual training sentence pairs, based on the bilingual vocabulary and the generalized bilingual sentence pattern.Type: GrantFiled: January 16, 2020Date of Patent: October 4, 2022Assignee: Beijing Xiaomi Intelligent Technology Co., Ltd.Inventors: Xiang Li, Yuhui Sun, Xiaolin Wu, Jianwei Cui
-
Publication number: 20220292347Abstract: The present disclosure relates to a method and an apparatus for processing information. The method comprises: acquiring to-be-processed information, and taking the to-be-processed information as an input of a processing model acquired by training a preset model so as to acquire target information corresponding to the to-be-processed information and output by the processing model. The preset model includes a plurality of operation modules and normalization structure corresponding to each of the plurality of operation modules, the normalization structure is configured to normalize an output of the corresponding operation module, and the processing model is acquired by removing a specified number of normalization structures according to a target probability or the number of steps for training the preset model in the process of training the preset model.Type: ApplicationFiled: September 30, 2021Publication date: September 15, 2022Applicants: BEIJING XIAOMI MOBILE SOFTWARE CO., LTD., Beijing Xiaomi Pinecone Electronics Co., Ltd.Inventor: Yuhui SUN
-
Patent number: 11436419Abstract: A bilingual corpora screening method includes: acquiring multiple pairs of bilingual corpora, wherein each pair of the bilingual corpora comprises a source corpus and a target corpus; training a machine translation model based on the multiple pairs of bilingual corpora; obtaining a first feature of each pair of bilingual corpora based on the trained machine translation model; training a language model based on the multiple pairs of bilingual corpora; obtaining feature vectors of each pair of bilingual corpora and determining a second feature of each pair of bilingual corpora based on the trained language model; determining a quality value of each pair of bilingual corpora according to the first feature and the second feature of each pair of bilingual corpora; and screening each pair of bilingual corpora according to the quality value of each pair of bilingual corpora.Type: GrantFiled: June 3, 2020Date of Patent: September 6, 2022Assignee: Beijing Xiaomi Mobile Software Co., Ltd.Inventors: Jingwei Li, Yuhui Sun, Xiang Li
-
Patent number: 11392779Abstract: A bilingual corpora screening method includes: acquiring multiple pairs of bilingual corpora, wherein each pair of the bilingual corpora comprises a source corpus and a target corpus; training a machine translation model based on the multiple pairs of bilingual corpora; obtaining a first feature of each pair of bilingual corpora based on the trained machine translation model; training a language model based on the multiple pairs of bilingual corpora; obtaining feature vectors of each pair of bilingual corpora and determining a second feature of each pair of bilingual corpora based on the trained language model; determining a quality value of each pair of bilingual corpora according to the first feature and the second feature of each pair of bilingual corpora; and screening each pair of bilingual corpora according to the quality value of each pair of bilingual corpora.Type: GrantFiled: June 3, 2020Date of Patent: July 19, 2022Assignee: Beijing Xiaomi Mobile Software Co., Ltd.Inventors: Jingwei Li, Yuhui Sun, Xiang Li
-
Publication number: 20210271811Abstract: Aspects of the present disclosure relate to a text labeling method and device, and more specifically to the field of deep learning and solving the problem of low efficiency and low accuracy of a feature extraction process. The method can include processing input information to obtain word embedding representation information of the input information, performing dynamic convolution feature extraction on the word embedding representation information to obtain a classification result of each character from the word embedding representation information, and inserting a label into the input information based on the classification result.Type: ApplicationFiled: July 15, 2020Publication date: September 2, 2021Applicant: Beijing Xiaomi Pinecone Electronics Co., Ltd.Inventors: Jingwei LI, Yuhui SUN, Xiang LI
-
Publication number: 20210182733Abstract: A training method for a machine translation model, includes: obtaining a multi-domain mixed training data set; performing data domain classification on a plurality of training data pairs in the training data set to obtain at least two domain data subsets; based on each domain data subset, determining at least two candidate optimization targets for the domain data subset, and training at least two candidate single domain models corresponding to each domain data subset based on the at least two candidate optimization targets, respectively; testing the at least two candidate single domain models corresponding to each domain data subset separately, and selecting a candidate optimization target with a highest test accuracy as a designated optimization target for the domain data subset; and training a hybrid domain model based on each domain data subset in the training data set and the designated optimization target corresponding to each domain data subset.Type: ApplicationFiled: April 3, 2020Publication date: June 17, 2021Inventors: Yuhui SUN, Xiang LI, Jingwei LI
-
Publication number: 20210182503Abstract: A bilingual corpora screening method includes: acquiring multiple pairs of bilingual corpora, wherein each pair of the bilingual corpora comprises a source corpus and a target corpus; training a machine translation model based on the multiple pairs of bilingual corpora; obtaining a first feature of each pair of bilingual corpora based on the trained machine translation model; training a language model based on the multiple pairs of bilingual corpora; obtaining feature vectors of each pair of bilingual corpora and determining a second feature of each pair of bilingual corpora based on the trained language model; determining a quality value of each pair of bilingual corpora according to the first feature and the second feature of each pair of bilingual corpora; and screening each pair of bilingual corpora according to the quality value of each pair of bilingual corpora.Type: ApplicationFiled: June 3, 2020Publication date: June 17, 2021Inventors: Jingwei LI, Yuhui SUN, Xiang LI
-
Publication number: 20210158126Abstract: A method for compressing a neural network model includes: obtaining a first trained teacher model and a second trained teacher model based on N training samples, N being a positive integer greater than 1; for each of the N training samples, determining a first guide component of the first teacher model and a second guide component of the second teacher model respectively, determining a sub optimization target corresponding to the training sample and configured to optimize a student model according to the first guide component and the second guide component, and determining a joint optimization target based on each of the N training samples and a sub optimization target corresponding to the training sample; and training the student model based on the joint optimization target.Type: ApplicationFiled: March 24, 2020Publication date: May 27, 2021Inventors: Xiang LI, Yuhui SUN, Jingwei LI, Jialiang JIANG
-
Publication number: 20210124880Abstract: A method for information processing, includes: obtaining a bilingual vocabulary containing N original bilingual word pairs, N being a positive integer; obtaining an original bilingual training set containing multiple original bilingual training sentence pairs; selecting at least one original bilingual training sentence pair matching any original bilingual word from the original bilingual training set as a bilingual sentence pair candidate; constructing a generalized bilingual sentence pattern based on at least one bilingual sentence pair candidate; and obtaining an augmented bilingual training set containing multiple augmented bilingual training sentence pairs, based on the bilingual vocabulary and the generalized bilingual sentence pattern.Type: ApplicationFiled: January 16, 2020Publication date: April 29, 2021Inventors: Xiang Li, Yuhui Sun, Xiaolin Wu, Jianwei Cui
-
Publication number: 20210124881Abstract: A method for compressing a neural network model, includes: obtaining a set of training samples including a plurality of pairs of training samples, each pair of the training samples including source data and target data corresponding to the source data; training an original teacher model by using the source data as an input and using the target data as verification data; training intermediate teacher models based on the set of training samples and the original teacher model, one or more intermediate teacher models forming a set of teacher models; training multiple candidate student models based on the set of training samples, the original teacher model, and the set of teacher models, the multiple candidate student models forming a set of student models; and selecting a candidate student model of the multiple candidate student models as a target student model according to training results of the multiple candidate student models.Type: ApplicationFiled: February 7, 2020Publication date: April 29, 2021Inventors: Xiang LI, Yuhui SUN, Jialiang JIANG, Jianwei CUI