-
公开(公告)号：US10776578B2
公开(公告)日：2020-09-15
申请号：US16118104
申请日：2018-08-30
发明人： Miao Fan , Mingming Sun , Wutao Lin , Ping Li
IPC分类号： G06F17/27 , G06F40/247 , G06N3/08 , G06F40/30 , G06F40/242 , G06F17/21
摘要： A method for building the synonymy discriminating model comprises: obtaining a text pair in training samples; using a word vector dictionary to obtain a quantization matrix of texts in the text pair; regarding the quantization matrix of respective texts as input of a convolutional neural network, regarding a synonymy annotation result corresponding to the text pair as output of the convolutional neural network, and training the convolutional neural network to obtain a synonymy discriminating model. The method for discriminating the synonymous text comprises: obtaining a text pair to be discriminated; using a word vector dictionary to obtain a quantization matrix corresponding to texts in the text pair; regarding the quantization matrix of the texts as input of a synonymy discriminating model, and determining a synonymy discrimination result of the text pair according to output of the synonymy discriminating model.
-
公开(公告)号：US20190287142A1
公开(公告)日：2019-09-19
申请号：US16421921
申请日：2019-05-24
发明人： Miao Fan , Yue Feng , Mingming Sun , Ping Li , Haifeng Wang
摘要： According to an exemplary embodiment of the present disclosure, a method, apparatus for evaluating a review, a device and a computer readable storage medium are provided. The method for evaluating a review includes obtaining a first vectorized representation of a set of text items in a review for a target object. The method further includes extracting a semantic feature of at least two consecutive text items of the set of text items based on the first vectorized representation. The method further includes determining a degree of importance of the at least two consecutive text items in a context of the review, and determining a degree of the review helping a user to evaluate the target object, based on the degree of importance and the semantic feature. In this way, an automatic, efficient, and accurate evaluation of the value of a review may be achieved.
-
3.发明授权公开(公告)号：US11847147B2
公开(公告)日：2023-12-19
申请号：US17311772
申请日：2020-09-24
发明人： Jizhou Huang , Haifeng Wang , Miao Fan
IPC分类号： G06F16/332 , G06F16/33 , G06F16/338 , G06F16/335 , G06N3/04 , G06F18/22 , G06F18/214
CPC分类号： G06F16/3322 , G06F16/335 , G06F16/338 , G06F16/3347 , G06F18/214 , G06F18/22 , G06N3/04
摘要： The present application discloses a method for building a ranking model, a query auto-completion method and corresponding apparatuses, which relates to the technical field of intelligent search. An implementation includes: acquiring from a POI query log a query prefix input when a user selects a POI from query completion suggestions, POIs in the query completion suggestions corresponding to the query prefix and the POI selected by the user in the query completion suggestions; constructing positive and negative example pairs using the POI selected by the user and the POIs not selected by the user in the query completion suggestions corresponding to the same query prefix; and performing a training operation using the query prefix and the positive and negative example pairs corresponding to the query prefix to obtain the ranking model.
-
公开(公告)号：US11836174B2
公开(公告)日：2023-12-05
申请号：US17416705
申请日：2020-11-25
发明人： Jizhou Huang , Haifeng Wang , Miao Fan
CPC分类号： G06F16/3347 , G06F11/3438 , G06F16/335 , G06F18/22 , G06N3/045 , G06N3/08
摘要： The present disclosure provides a method of retrieving a geographic location as well as a method and an apparatus of establishing a similarity model including: acquiring training data from a historical click log, wherein the training data contains a search term, a clicked geographic location associated with the search term as a positive sample, and a non-clicked geographic location as a negative sample; expanding the positive sample and the negative sample based on a co-occurrence relationship between geographic locations by using a historical browsing log; and determining a vector representation of the search term by using the first neural network, and determining a vector representation of the positive sample expanded and a vector representation of the negative sample expanded, by using the second neural network; and training the first neural network and the second neural network so as to maximum a difference between a first similarity and a second similarity.
-
公开(公告)号：US11238050B2
公开(公告)日：2022-02-01
申请号：US16459282
申请日：2019-07-01
发明人： Miao Fan , Chao Feng , Mingming Sun , Ping Li , Haifeng Wang
IPC分类号： G06F16/00 , G06F16/2457 , G06F16/248
摘要： According to exemplary embodiments of the present disclosure, a method and an apparatus for determining a response for user input data, a device, and a computer-readable storage medium are provided. The method includes: obtaining search results associated with the user input data. The method also includes: determining correlation degrees between the search results and the user input data. The method also includes: building candidate content for the user input data based on the search results and the correlation degrees. The candidate content includes a paragraph associated with the user input data in the search results. The method also includes: determining the response for the user input data from the candidate content.
-
公开(公告)号：US11651015B2
公开(公告)日：2023-05-16
申请号：US16670814
申请日：2019-10-31
发明人： Miao Fan , Lin Guo , Chao Feng , Mingming Sun , Ping Li , Haifeng Wang
IPC分类号： G06F16/30 , G06F16/338 , G06F16/33 , G06N3/04 , G06N3/084
CPC分类号： G06F16/338 , G06F16/3347 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G06N3/084
摘要： Embodiments of the present disclosure provide a method and apparatus for presenting information. The method may include: acquiring target release information and a comment information set associated with the target release information; and generating, for comment information in the comment information set, usefulness probabilities and predicted comment scores of the comment information based on the comment information and the target release information. The method may further include: presenting, based on obtained usefulness probability set and predicted comment score set, the comment information in the comment information set.
-
公开(公告)号：US11514247B2
公开(公告)日：2022-11-29
申请号：US16713062
申请日：2019-12-13
发明人： Miao Fan , Sen Ye , Mingming Sun , Ping Li , Haifeng Wang
摘要： A method, an apparatus, a computer device and a readable medium for knowledge hierarchical extraction of a text are disclosed. The method comprises: performing word segmentation on a designated text to obtain a word list, the word list including at least one word arranged in a sequence in the designated text; analyzing part-of-speech of each word in the word list in the designated text, to obtain a part-of-speech list corresponding to the word list; predicting a SPO triple included in the designated text according to the word list, the part-of-speech list and a pre-trained knowledge hierarchical extraction model. By the technical solutions, the SPO triple included in any designated text however loose its organization and structure is may be accurately extracted based on the pre-trained knowledge hierarchical extraction model. Compared to the prior art, the efficiency and accuracy of knowledge hierarchical extraction may be effectively improved.
-
公开(公告)号：US11461399B2
公开(公告)日：2022-10-04
申请号：US16706218
申请日：2019-12-06
发明人： Miao Fan , Chao Feng , Mingming Sun , Ping Li , Haifeng Wang
IPC分类号： G06F40/30 , G06F16/9032
摘要： According to embodiments of the present disclosure, a method and an apparatus for responding to a question, and a storage medium are provided. The method includes: determining a question characteristic representation corresponding to a question for an object; determining a comment characteristic representation corresponding to a first comment for the object; generating a first target characteristic representation by utilizing the question characteristic representation and the comment characteristic representation; and determining an answer for the question based on the first target characteristic representation.
-
公开(公告)号：US11409964B2
公开(公告)日：2022-08-09
申请号：US16709304
申请日：2019-12-10
发明人： Miao Fan , Yue Feng , Chao Feng , Mingming Sun , Ping Li , Haifeng Wang
IPC分类号： G06F40/30 , G06F40/279 , G06N3/04 , G06N3/08
摘要： Embodiments of the present disclosure provide a method, an apparatus, a device and a storage medium for evaluating quality of an answer. The method includes extracting a question feature expression of a question and an answer feature expression of an answer with respect to the question, the question and the answer being represented in a form of text; determining a measurement of textual quality of the answer based on the answer feature expression; determining a measurement of correlation on semantics between the question and the answer based on the question feature expression and the answer feature expression; and determining a quality score of the answer with respect the question based on the measurement of textual quality and the measurement of correlations. Therefore, a high-quality answer may be accurately obtained.
-
10.发明申请公开(公告)号：US20200380211A1
公开(公告)日：2020-12-03
申请号：US16713062
申请日：2019-12-13
发明人： Miao Fan , Sen YE , Mingming Sun , Ping LI , Haifeng Wang
IPC分类号： G06F40/30 , G06F40/253 , G06N5/02 , G06N3/04 , G06K9/62
摘要： A method, an apparatus, a computer device and a readable medium for knowledge hierarchical extraction of a text are disclosed. The method comprises: performing word segmentation on a designated text to obtain a word list, the word list including at least one word arranged in a sequence in the designated text; analyzing part-of-speech of each word in the word list in the designated text, to obtain a part-of-speech list corresponding to the word list; predicting a SPO triple included in the designated text according to the word list, the part-of-speech list and a pre-trained knowledge hierarchical extraction model. By the technical solutions, the SPO triple included in any designated text however loose its organization and structure is may be accurately extracted based on the pre-trained knowledge hierarchical extraction model. Compared to the prior art, the efficiency and accuracy of knowledge hierarchical extraction may be effectively improved.
-
-
-
-
-
-
-
-
-
搜索结果
19 条记录 (耗时 0.021 秒)
