Patents by Inventor Songtao Guo
Songtao Guo 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).
-
Publication number: 20240092948Abstract: The present invention relates to a process for continuously producing an ultra-high molecular weight polyethylene by the ethylene slurry polymerization, wherein raw materials containing ethylene and optionally at least one comonomer are subjected to a continuous slurry polymerization in a hydrogen free atmosphere in the ethylene slurry polymerization condition by using 2-6 ethylene slurry polymerization reaction tanks connected in series, and the deviations of the polymerization temperatures, the polymerization pressures, and the gas phase compositions between the tanks each other are controlled to certain ranges. The ultra-high molecular weight polyethylene having the viscosity-average molecular weight of 150-800×104 g/mol can be continuously produced. This process has flexible polymerization manner, large room for adjusting and controlling, and stable polymer performance.Type: ApplicationFiled: January 26, 2022Publication date: March 21, 2024Inventors: Chuanfeng LI, Wenrui WANG, Kun JING, Minghua CHEN, Yuejun XING, Huimin XIA, Feng GUO, Zhonglin YOU, Shaohui CHEN, Jianhong ZHAI, Liu YANG, Songtao TU
-
Publication number: 20230257917Abstract: The present invention discloses a highly effective flame-retardant lightweight and soft multi-fiber blended fabric and a preparation method thereof. The fabric comprises 82 to 87 wt % of base fabric, 5 to 8 wt % of flame retardant and 8 to 10 wt % of antistatic agent. The base fabric comprises 45 to 48 wt % of polyacrylonitrile fibers, 40 to 42 wt % of cellulose fibers, 6 to 9 wt % of polyacrylate fibers and 6 to 8 wt % of polyamide fibers in parts by mass. The material has the characteristics of highly effective flame retardance, lightweightness and softness, with the gram weight being 215 g/m. A test shows that the material can come up to the NFPA2112 standard, and the arc-proof ATPV is greater than 8 cal/cm2.Type: ApplicationFiled: September 2, 2022Publication date: August 17, 2023Inventors: Jun SHANG, Keqin WANG, Xuejian GUO, Songtao GUO
-
Patent number: 11580099Abstract: Methods are presented for providing dynamic search filter suggestions that are updated and ranked based on the user filter selections. One method includes detecting a query received in a user interface (UI), calculating, by a search-candidate model, first search results, and calculating, by a suggestions model, first filter suggestions for filter categories to filter responses to the query. The suggestions model is obtained by training a machine-learning algorithm utilizing pairwise learning-to-rank modeling. The first search results and the first filter suggestions are presented in the UI. When a selection in the UI of a filter suggestion is detected, the search-candidate model calculates second search results for the filter categories based on the query and the selected filter suggestion, and the suggestions model calculates second first filter suggestions based on the query and the selected filter suggestion. The second search results and the second filter suggestions are presented in the UI.Type: GrantFiled: September 30, 2020Date of Patent: February 14, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Wenxiang Chen, William Tang, Runfang Zhou, Tanvi Sudarshan Motwani, Jeremy Lwanga, Sara Smoot Gerrard, Daniel Sairom Krishnan Hewlett, Alexandre Patry, Songtao Guo, Sai Krishna Bollam
-
Publication number: 20220198263Abstract: In an example embodiment, a machine-learned model is trained to specifically identify anomaly points in time series data. The model is capable of being applied in parallel to many different time series simultaneously, allowing for a scalable solution for large scale online networks. The model classifies each data point in a specified time window and outputs rich contextual information for downstream applications, such as ranking and display of the anomalous data points.Type: ApplicationFiled: December 23, 2020Publication date: June 23, 2022Inventors: Songtao Guo, Patrick Ryan Driscoll, Michael Mario Jennings, Robert Perrin Reeves, Bo Yang
-
Publication number: 20220198264Abstract: In an example embodiment, a machine-learned model is trained to rank anomaly points in time series data. The model is capable of being applied in parallel to many different time series simultaneously, allowing for a scalable solution for large scale online networks. The model outputs a ranking score for an input anomaly and allows for ranking of anomalies not just in the same time series but anomalies across multiple time series as well. This ranking can then be used to determine how best to present the ranked anomalies to users in a graphical user interface.Type: ApplicationFiled: December 23, 2020Publication date: June 23, 2022Inventors: Songtao Guo, Robert Perrin REEVES, Bo YANG, Wan Qi GAO, William TANG, Patrick Ryan DRISCOLL, Shan ZHOU, Taylor Shelby BURFIELD, Adriana Dominique MEZA
-
Publication number: 20220180181Abstract: In an example embodiment, a model is trained to specifically identify reversal points in data and then to rank these reversal points in order of importance. A reversal point shall be defined as a point in which a particular metric, specifically a first order derivative, crosses over from positive to negative or vice-versa. Users are more likely to be interested in abnormal and significant changes in data, and thus the machine-learned model is trained to evaluate a reversal point based on two dimensions: abnormality and significance.Type: ApplicationFiled: December 9, 2020Publication date: June 9, 2022Inventors: Bo YANG, Chaofan HUANG, Songtao GUO, Robert Perrin REEVES, Wan Qi GAO, Patrick Ryan DRISCOLL, Kristina Caroline RYAN, Michael Mario JENNINGS, Jeremy LWANGA, Manzarul Azad KAZI
-
Publication number: 20220100746Abstract: Methods are presented for providing dynamic search filter suggestions that are updated and ranked based on the user filter selections. One method includes detecting a query received in a user interface (UI), calculating, by a search-candidate model, first search results, and calculating, by a suggestions model, first filter suggestions for filter categories to filter responses to the query. The suggestions model is obtained by training a machine-learning algorithm utilizing pairwise learning-to-rank modeling. The first search results and the first filter suggestions are presented in the UI. When a selection in the UI of a filter suggestion is detected, the search-candidate model calculates second search results for the filter categories based on the query and the selected filter suggestion, and the suggestions model calculates second first filter suggestions based on the query and the selected filter suggestion. The second search results and the second filter suggestions are presented in the UI.Type: ApplicationFiled: September 30, 2020Publication date: March 31, 2022Inventors: Wenxiang Chen, William Tang, Runfang Zhou, Tanvi Sudarshan Motwani, Jeremy Lwanga, Sara Smoot Gerrard, Daniel Sairom Krishnan Hewlett, Alexandre Patry, Songtao Guo, Sai Krishna Bollam
-
Patent number: 11250340Abstract: In an example, for each feature of one or more features of a target sample data, feature values for one or more pseudo-samples are generated using, localized stratified sampling. The one or more pseudo-samples are fed into the trained machine learned model to obtain their prediction values. A piecewise linear regression model is trained using the one or more pseudo-samples and their prediction values, the piecewise linear regression model having two coefficients for each feature, a first coefficient describing prediction change when a corresponding feature value is increased and a second coefficient describing prediction change when a corresponding feature value is decreased. A top positive feature influencer is identified based on a feature of the one or more features of the target sample having a greatest magnitude of positive first coefficient or greatest magnitude of negative second coefficient.Type: GrantFiled: December 14, 2017Date of Patent: February 15, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Jilei Yang, Wei Di, Nidhi Sehgal, Songtao Guo
-
Patent number: 11068848Abstract: A member profile including a vector containing a field for each of a plurality of skills and a rating of one or more of the skills in the vector for a member of a social networking service is obtained. A first distance indicating a vector distance between the vector of the member profile and a vector of a hypothetical member profile representing the perfect job candidate is obtained. A hypothetical member profile for the member is created by combining the vector of the member profile with the indication of how each of the one or more skills is improved through taking the course from course information. A second distance between the member and the hypothetical perfect candidate for the job is obtained, and the difference between the first distance and the second distance is calculated to determine an estimate of how much the course will increase the member's job chances.Type: GrantFiled: July 30, 2015Date of Patent: July 20, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Aman Grover, Siyu You, Krishnaram Kenthapadi, Parul Jain, Fedor Vladimirovich Borisyuk, Christopher Matthew Degiere, Songtao Guo
-
Patent number: 10970325Abstract: In an embodiment, the disclosed technologies include receiving a set of digital inputs; where the set of digital inputs includes a candidate entity-member entity pair that includes candidate entity data and member entity data; where the member entity data has been extracted from a node of an online service; where an exact match has not been found between the candidate entity data and the member entity data; in response to the set of digital inputs, outputting models of the candidate entity data and the member entity data, respectively; where the models indicate weight values assigned to text in the candidate entity data and weight values assigned to text in the member entity data, respectively; calculating a similarity score using the models; in response to the similarity score matching a threshold, inputting the candidate entity-member entity pair to a classifier to produce a classification; where the classifier uses a machine learning model that has been trained using features derived from previously-analyzType: GrantFiled: December 26, 2018Date of Patent: April 6, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Qiannan Yin, Songtao Guo, Yi Wang, Albert Cui, Joonhyung Lim, Qunzeng Liu, Lizabeth Li, Carrie Peng, Yang Zhou
-
Patent number: 10769426Abstract: In an example embodiment, a member profile corresponding to a member of a social networking service is obtained. Usage information for the member is then obtained, and one or more member metrics are calculated based on the member profile and usage information for the corresponding member. A plurality of features are extracted from the member profile and the one or more member metrics. The plurality of features is inserted into an organization name confidence score model to obtain a confidence score for an organization name in the member profile.Type: GrantFiled: October 30, 2015Date of Patent: September 8, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Songtao Guo, Ke Wang, Alex Ching Lai, Aarti Kumar, Keith Wai Kit Tsang, Rekha Thakur, Song Lin, Christopher Matthew Degiere
-
Publication number: 20200210466Abstract: In an embodiment, the disclosed technologies include receiving a set of digital inputs; where the set of digital inputs includes a candidate entity-member entity pair that includes candidate entity data and member entity data; where the member entity data has been extracted from a node of an online service; where an exact match has not been found between the candidate entity data and the member entity data; in response to the set of digital inputs, outputting models of the candidate entity data and the member entity data, respectively; where the models indicate weight values assigned to text in the candidate entity data and weight values assigned to text in the member entity data, respectively; calculating a similarity score using the models; in response to the similarity score matching a threshold, inputting the candidate entity-member entity pair to a classifier to produce a classification; where the classifier uses a machine learning model that has been trained using features derived from previously-analyzType: ApplicationFiled: December 26, 2018Publication date: July 2, 2020Inventors: Qiannan Yin, Songtao Guo, Yi Wang, Albert Cui, Joonhyung Lim, Qunzeng Liu, Lizabeth Li, Carrie Peng, Yang Zhou
-
Patent number: 10523736Abstract: Methods, systems and computer program products for identifying a relationship between sub-units of an entity are described. The sub-units are segmented into one or more candidate related groups based on one or more general attributes and a pair of the sub-units of the one or more candidate related sub-units is selected. The pair of sub-units is analyzed to determine a relationship between the sub-units and the relationship between the sub-units is identified based on the determined relationship.Type: GrantFiled: March 30, 2015Date of Patent: December 31, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Ke Wang, Songtao Guo, Baoshi Yan, Alex Ching Lai
-
Patent number: 10380701Abstract: Methods and systems for generating tailored user interface presentations based on skills clusters and automatically modified member profiles are presented. According to various embodiments, a set of skills are accessed and a skills matrix generated. A set of co-occurrences among the set of skills are identified. A set of skills clusters is automatically generated based on identifying of the co-occurrences and the skills clusters are automatically validated. A graphical representation of the validated skills cluster is presented with user interface elements for modifying the validated skills cluster and data representing member profiles is presented based on the validated skills cluster.Type: GrantFiled: August 31, 2015Date of Patent: August 13, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Song Lin, Cindy Zhou, Songtao Guo
-
Publication number: 20190197411Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of coefficients from a linear model that uses a set of features inputted into a statistical model to estimate an output of the statistical model. Next, the system combines the set of coefficients with a set of feature values of the features to calculate a set of local contributions of the features toward the output of the statistical model, wherein each local contribution in the set of local contribution is calculated by multiplying each feature value in the set of feature values by a coefficient for a corresponding feature in the linear model. The system then outputs, based on a first ranking of the set of features by the set of local contributions, a first subset of the features for use in characterizing a local performance of the statistical model.Type: ApplicationFiled: December 21, 2017Publication date: June 27, 2019Applicant: Microsoft Technology Licensing, LLCInventors: Wei Di, Songtao Guo
-
Publication number: 20190188588Abstract: In an example, for each feature of one or more features of a target sample data, feature values for one or more pseudo-samples are generated using, localized stratified sampling. The one or more pseudo-samples are fed into the trained machine learned model to obtain their prediction values. A piecewise linear regression model is trained using the one or more pseudo-samples and their prediction values, the piecewise linear regression model having two coefficients for each feature, a first coefficient describing prediction change when a corresponding feature value is increased and a second coefficient describing prediction change when a corresponding feature value is decreased. A top positive feature influencer is identified based on a feature of the one or more features of the target sample having a greatest magnitude of positive first coefficient or greatest magnitude of negative second coefficient.Type: ApplicationFiled: December 14, 2017Publication date: June 20, 2019Inventors: Jilei Yang, Wei Di, Nidhi Sehgal, Songtao Guo
-
Patent number: 10282606Abstract: In an example embodiment, a web page is obtained using a web page address stored in a first record and is parsed to extract one or more images from the web page along with a first plurality of features for each of the one or more images from the web page. Information about each image of the web page and the extracted first plurality of features for the web page are input into a supervised machine learning classifier to calculate a logo confidence score for each image of the web page, the logo confidence score indicating the probability that the image is an organization logo. In response to a particular image in the web page having a logo confidence score transgressing a first threshold, the particular image is injected into an organization logo field of the first record.Type: GrantFiled: March 27, 2018Date of Patent: May 7, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Songtao Guo, Christopher Matthew Degiere, Jingjing Huang, Aarti Kumar, Alex Ching Lai, Xian Li
-
Patent number: 10242258Abstract: In an example embodiment, a fuzzy join operation is performed by, for each pair of records, evaluating a first plurality of features for both records in the pair of records by calculating term frequency-inverse term frequency (TF-IDF) for each token of each field relevant to each feature and based on the calculated TF-IDF for each token of each field relevant to each feature, computing a similarity score based on the similarity function by adding a weight assigned to the TF-IDF for any token that appears in both records. Then a graph data structure is created, having a node for each record in the plurality of records and edges between each of the nodes, except, for each record pair having a similarity score that does not transgress a first threshold, causing no edge between the nodes for the record pair to appear in the graph data structure.Type: GrantFiled: October 30, 2015Date of Patent: March 26, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Songtao Guo, Christopher Matthew Degiere, Aarti Kumar, Alex Ching Lai, Xian Li
-
Publication number: 20190019258Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains member features for members of a social network, wherein the member features include a company. The system also obtains a definition of a member segment, wherein the definition includes one or more of the member features. Next, the system identifies a subset of the members for inclusion in the member segment using the one or more of the member features. The system then aggregates the member features by the company to generate a set of company features for the company and aggregates the company features by the member segment to generate additional company features for inclusion in the set of company features. Finally, the system outputs the company features for use in processing queries related to the company.Type: ApplicationFiled: July 12, 2017Publication date: January 17, 2019Applicant: LinkedIn CorporationInventors: Songtao Guo, Wei Di, Juan Wang
-
Publication number: 20180336280Abstract: Methods, systems, and computer programs are presented for searching a database of learning modules to provide recommendations based on user and team data. One method includes an operation for detecting a search query for a training module for a user. The search query is detected in an area associated with a team in a social network, and the user is part of the team. Further, the method includes an operation for expanding the search query with information about the user and with information about the team. Additionally, the method includes an operation for executing the expanded search query to search for training modules in a database of training modules. In addition, the method includes an operation for presenting the results from executing the expanded search query, wherein the results are presented in the social network to the user.Type: ApplicationFiled: May 17, 2017Publication date: November 22, 2018Inventors: Tony Yin, Songtao Guo