Patents by Inventor Keqing Liang
Keqing Liang 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: 20240135240Abstract: Embodiments of the disclosed technologies include generating a reward score for an entity. A rate distribution is determined using the reward score. A sampled rate value is generated by sampling the rate distribution. A probability score is generated for a pair of the entity and a user using the sampled rate value. A probability distribution is determined using the probability score. A sampled probability value is generated by sampling the probability distribution. A machine learning model is trained using the sampled probability value.Type: ApplicationFiled: October 19, 2022Publication date: April 25, 2024Inventors: Yafei Wei, Andrew O. Hatch, Keqing Liang, Liyan Fang, Ankan Saha
-
Publication number: 20240134867Abstract: Embodiments of the disclosed technologies include generating a reward score for an entity. A rate distribution is determined using the reward score and a number of times the entity has been selected for ranking. A sampled rate value is generated by sampling the rate distribution. A probability score is generated for a pair of the entity and a user based on the sampled rate value. A probability distribution is determined using the probability score. A sampled probability value is generated by sampling the probability distribution. A machine learning model is trained using the sampled probability value.Type: ApplicationFiled: October 19, 2022Publication date: April 25, 2024Inventors: Liyan Fang, Andrew O. Hatch, Keqing Liang, Yafei Wei, Ankan Saha
-
Publication number: 20240112281Abstract: In an example embodiment, a blending model is presented based on a linear programming approach. The blending model produces a slate of sponsored and non-sponsored pieces of content for display in a graphical user interface, with the ordering and placement of the sponsored and non-sponsored pieces of content selected in order to maximize an objective function. Such an approach can fine tune each piece of content using content-level parameters and holistically examine global constraints and opportunities. It establishes a robust optimization framework that can adapt to content and domain changes without requiring tuning through online experiments.Type: ApplicationFiled: September 23, 2022Publication date: April 4, 2024Inventors: Keqing Liang, Konstantin Salomatin, Noureddine El Karoui
-
Patent number: 11763264Abstract: Sponsored and organic pieces of content are displayed in accordance with a blending model that is used to first identify a pattern of slots to which to assign either sponsored or organic pieces of content. This blending model is applied to a combination of both sponsored and non-sponsored pieces of content being considered for display to a user. This pattern only determines the slot assignments. The actual ranking of the pieces of content, and more particularly the actual ranking of the organic pieces of content, is determined by an ordering other than the ranking determined by the blending model, such as by using the original ordering of the second list. The pieces of content are then displayed in the order of this actual ranking, but in the slots indicated as having been assigned to be either sponsored or organic in the pattern determined by the blending model.Type: GrantFiled: September 27, 2021Date of Patent: September 19, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Keqing Liang, Giorgio Paolo Martini, Shan Zhou, Linda Fayad, Wen Pu, Austin Qingfeng Lu
-
Publication number: 20230095289Abstract: Sponsored and organic pieces of content are displayed in accordance with a blending model that is used to first identify a pattern of slots to which to assign either sponsored or organic pieces of content. This blending model is applied to a combination of both sponsored and non-sponsored pieces of content being considered for display to a user. This pattern only determines the slot assignments. The actual ranking of the pieces of content, and more particularly the actual ranking of the organic pieces of content, is determined by an ordering other than the ranking determined by the blending model, such as by using the original ordering of the second list. The pieces of content are then displayed in the order of this actual ranking, but in the slots indicated as having been assigned to be either sponsored or organic in the pattern determined by the blending model.Type: ApplicationFiled: September 27, 2021Publication date: March 30, 2023Inventors: Keqing Liang, Giorgio Paolo Martini, Shan Zhou, Linda Fayad, Wen Pu, Austin Qingfeng Lu
-
Patent number: 11556897Abstract: Methods, systems, and computer programs are presented for presenting return-on-investment (ROI) information, for budgeted services that resulted in a successful service delivery, on a user interface for setting the budget for a service request. One method includes an operation for identifying daily budgets for budgeted services that resulted in a successful service delivery (BSSSD). Each daily budget indicates an amount for spending in promotion of the BSSSD in an online service. The method further includes receiving a request, in a graphical user interface (GUI) of the online service, for posting a daily budget for a first budgeted service. Further, a performance value, associated with the daily budgets of the BSSSD that are similar to the first budgeted service, is selected. Further, the method includes causing presentation, by the one or more processors, of the performance value in the GUI.Type: GrantFiled: June 12, 2020Date of Patent: January 17, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Keqing Liang, Sumedha Swamy, Qianqi Shen, Qing Duan
-
Patent number: 11263661Abstract: In an example embodiment, a bid of an impression of a piece of content, while dynamically set at impression time, may be based on a base bid that is something of a rough indicator of what the estimated price will be. That base bid then is adjusted dynamically up or down at impression time. This base bid can be determined by dividing the expected number of impressions for a day by a total daily budget. The expected number of impressions may be determined by using the empirical number of impressions from the previous day. As such, in an example embodiment, the prediction of the number of impressions for a day utilizes a corrected version of the empirical number of impressions from the prior day, with the corrected version based on a specialized formula with weights trained by a machine learning algorithm.Type: GrantFiled: June 8, 2020Date of Patent: March 1, 2022Assignee: Microsoft Technology Licensing, LLCInventor: Keqing Liang
-
Patent number: 11188609Abstract: Techniques for the dynamic slotting of content items within electronic content are provided. In response to receiving a request, a first set of content items is identified and a first score is generated for each based on a first objective. Based on the first scores, a first ranking of the first set of content items is generated. A subset of the first set is selected based on the first ranking. A second set of content items that includes the subset is identified and a second score is generated for each item in the second set based on a second objective that is different than the first objective. Based on the second scores, a second ranking of the second set is generated. A subset of the second set is selected based on the second ranking. The second subset is presented on a computing device that is associated with the request.Type: GrantFiled: September 30, 2019Date of Patent: November 30, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Giorgio Paolo Martini, Nikhil Devanur Rangarajan, Wen Pu, Keqing Liang
-
Patent number: 11132645Abstract: Techniques for predicting relevance of social networking service member accounts to a job posting. In an embodiment, a candidate predictor engine of a system encodes data representing an applicant quality (AQ) score for each job/applicant pair for a plurality of applicants to a job posting. Additionally, the system stores the encoded data and assigns member-level weights to each of the applicants. Moreover, the system calculates weighted AQ scores for each of the job/applicant pairs, the weighted AQ scores being products of respective AQ scores and member-level weights. Furthermore, the system sums the weighted AQ scores to derive a total weighted score for the job posting. Then, the candidate predictor engine generates a job-level probability of confirmed hire (pCH) based on the total weighted score, the job-level pCH indicating a likelihood of the posting being filled by an applicant. Also, the system transmits the job-level pCH to a client for display.Type: GrantFiled: July 26, 2017Date of Patent: September 28, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Keqing Liang, Vibhu Prakash Saxena, Jason Phan
-
Publication number: 20210103861Abstract: The disclosed embodiments provide a system for performing dynamic job bidding optimization. During operation, the system obtains historical data containing a time series of interactions with a job. Next, the system uses the historical data to calculate an initial price of a job based on a predicted number of interactions with the job. The system then determines a first dynamic adjustment to the initial price that improves utilization of a budget for the job and a second dynamic adjustment to the initial price that improves a performance of the job. Finally, the system applies the first and second adjustments to the initial price to produce an updated price for the job and delivers the job within an online system based on the updated price.Type: ApplicationFiled: December 18, 2020Publication date: April 8, 2021Inventors: Keqing Liang, Wen Pu, Sahin Cem Geyik, Yu Wang, Ying Chen, Yin Zhang, Sumedha K. Swamy
-
Publication number: 20210097126Abstract: Techniques for the dynamic slotting of content items within electronic content are provided. In response to receiving a request, a first set of content items is identified and a first score is generated for each based on a first objective. Based on the first scores, a first ranking of the first set of content items is generated. A subset of the first set is selected based on the first ranking. A second set of content items that includes the subset is identified and a second score is generated for each item in the second set based on a second objective that is different than the first objective. Based on the second scores, a second ranking of the second set is generated. A subset of the second set is selected based on the second ranking. The second subset is presented on a computing device that is associated with the request.Type: ApplicationFiled: September 30, 2019Publication date: April 1, 2021Inventors: Giorgio Paolo Martini, Nikhil Devanur Rangarajan, Wen Pu, Keqing Liang
-
Publication number: 20200349604Abstract: The disclosed embodiments provide a system that performs pacing for balanced delivery. During operation, the system obtains predicted response rates associated with impressions of a content item delivered within an online system and a cost per action (CPA) for the content item. Next, the system determines an impression-based spending for the content item based on the predicted response rates and the CPA. The system then calculates a pacing score for the content item based on the impression-based spending. Finally, the system adjusts subsequent interactions with the content item based on the pacing score.Type: ApplicationFiled: May 2, 2019Publication date: November 5, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Sahin C. Geyik, Xi Chen, Yu Wang, Keqing Liang, Wen Pu
-
Publication number: 20200311764Abstract: The disclosed embodiments provide a system for performing an experiment strategy for member-based ramping. During operation, the system divides members of an online system into a control group and a treatment group. Next, the system configures delivery of content to the control group over a first set of channels that charge for actions related to the content and delivery of the content to the treatment group over a second set of channels that charge for the actions related to the content, wherein the second set of channels is smaller than the first set of channels. The system then performs a first experiment that selects an adjustment factor for content delivered over the second set of channels to the treatment group to achieve revenue neutrality and/or engagement neutrality between the treatment and control groups.Type: ApplicationFiled: March 29, 2019Publication date: October 1, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Wen Pu, Keqing Liang, Jianqiang Shen, Sumedha K. Swamy, Prashanth Govindarajan
-
Publication number: 20200302477Abstract: In an example embodiment, a bid of an impression of a piece of content, while dynamically set at impression time, may be based on a base bid that is something of a rough indicator of what the estimated price will be. That base bid then is adjusted dynamically up or down at impression time. This base bid can be determined by dividing the expected number of impressions for a day by a total daily budget. The expected number of impressions may be determined by using the empirical number of impressions from the previous day. As such, in an example embodiment, the prediction of the number of impressions for a day utilizes a corrected version of the empirical number of impressions from the prior day, with the corrected version based on a specialized formula with weights trained by a machine learning algorithm.Type: ApplicationFiled: June 8, 2020Publication date: September 24, 2020Inventor: Keqing Liang
-
Publication number: 20200302400Abstract: Methods, systems, and computer programs are presented for presenting return-on-investment (ROI) information, for budgeted services that resulted in a successful service delivery, on a user interface for setting the budget for a service request. One method includes an operation for identifying daily budgets for budgeted services that resulted in a successful service delivery (BSSSD). Each daily budget indicates an amount for spending in promotion of the BSSSD in an online service. The method further includes receiving a request, in a graphical user interface (GUI) of the online service, for posting a daily budget for a first budgeted service. Further, a performance value, associated with the daily budgets of the BSSSD that are similar to the first budgeted service, is selected. Further, the method includes causing presentation, by the one or more processors, of the performance value in the GUI.Type: ApplicationFiled: June 12, 2020Publication date: September 24, 2020Inventors: Keqing Liang, Sumedha Swamy, Qianqi Shen, Qing Duan
-
Publication number: 20200210908Abstract: The disclosed embodiments provide a system for performing dynamic job bidding optimization. During operation, the system obtains historical data containing a time series of interactions with a job. Next, the system uses the historical data to calculate an initial price of a job based on a predicted number of interactions with the job. The system then determines a first dynamic adjustment to the initial price that improves utilization of a budget for the job and a second dynamic adjustment to the initial price that improves a performance of the job. Finally, the system applies the first and second adjustments to the initial price to produce an updated price for the job and delivers the job within an online system based on the updated price.Type: ApplicationFiled: December 26, 2018Publication date: July 2, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Keqing Liang, Wen Pu, Sahin C. Geyik, Yu Wang, Ying Chen, Yin Zhang, Sumedha K. Swamy
-
Publication number: 20200202299Abstract: The disclosed embodiments provide a system for performing delivery-based optimizations for jobs. During operation, the system obtains historical data comprising delivery rates related to overdelivery and underdelivery of jobs with respect to fixed budgets for the jobs. Next, the system applies an optimization technique to the historical data to determine a change to an initial price for a job that improves a utilization of a fixed budget for the job. The system then applies the change to the initial price to produce an updated price for the job and delivers the job within an online system based on the updated price.Type: ApplicationFiled: December 21, 2018Publication date: June 25, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Keqing Liang, Yin Zhang
-
Publication number: 20190370752Abstract: Methods, systems, and computer programs are presented for determining a recommended daily budget for a job post. One method includes operations for identifying an initial budget value for recommending a daily budget when a job poster is adding a job post, and for performing a test to determine responses of job posters when the recommended daily budget is presented as a function of a multiplier applied to the initial budget value. Further, the method includes operations for defining a model to determine committed bookings as a function of the multiplier, determining based on the model a value of the multiplier that maximizes the committed bookings, and setting a new initial budget value to the initial budget value times the value of the multiplier that maximizes the committed bookings. Additionally, the new initial budget value is presented in a user interface when job posters add new job posts.Type: ApplicationFiled: May 31, 2018Publication date: December 5, 2019Inventors: Keqing Liang, Monica Marie Lewis, Sumedha Swamy, Qing Duan, Wen Pu
-
Publication number: 20190034883Abstract: Techniques for predicting relevance of social networking service member accounts to a job posting. In an embodiment, a candidate predictor engine of a system encodes data representing an applicant quality (AQ) score for each job/applicant pair for a plurality of applicants to a job posting. Additionally, the system stores the encoded data and assigns member-level weights to each of the applicants. Moreover, the system calculates weighted AQ scores for each of the job/applicant pairs, the weighted AQ scores being products of respective AQ scores and member-level weights. Furthermore, the system sums the weighted AQ scores to derive a total weighted score for the job posting. Then, the candidate predictor engine generates a job-level probability of confirmed hire (pCH) based on the total weighted score, the job-level pCH indicating a likelihood of the posting being filled by an applicant. Also, the system transmits the job-level pCH to a client for display.Type: ApplicationFiled: July 26, 2017Publication date: January 31, 2019Inventors: Keqing Liang, Vibhu Prakash Saxena, Jason Phan
-
Patent number: 10037359Abstract: Systems and methods for improving search results using social routing are provided. In example embodiments, an affinity metric and match metric are determined for a plurality of users. The affinity metric indicates an interaction level between a given user and the match metric indicates how well the given user matches parameters of a search string. Based on a correlation between the affinity metric and the match metric, one or more items of content may be transmitted to one or more selected users. Improved search results can then be generated based on interactions with the one or more items of content.Type: GrantFiled: May 23, 2016Date of Patent: July 31, 2018Assignee: Microsoft Technology Licensing, LLCInventors: Matthew Steven Tague, Peter Hume Rigano, John Brendan Browne, Lorenzo Canlas, Qiang Zhu, Keqing Liang, Rebecca Page White