-
公开(公告)号：US20200045603A1
公开(公告)日：2020-02-06
申请号：US16599942
申请日：2019-10-11
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Huahui Wang , Tae Won Cho , Gopalakrishnan Meempat , Henry Kafka , Ravi Raina , Xiaoyu Wang , Laurie Bigler
Abstract: Distribution of traffic to cells in a communication network can be controlled. A distribution management component (DMC) can determine overall device traffic throughput for cells of a sector that satisfy a defined traffic throughput criterion relating to a harmonic mean of the device traffic throughput for the cells to desirably enhance or maximize the harmonic mean of the overall device traffic throughput. Based on the overall device traffic throughput for the cells, the DMC can determine whether to adjust a characteristic associated with a cell of the cells to facilitate adjusting distribution of device traffic among the cells of the sector to achieve desirable load balancing of traffic by the sector and in the network. Load balancing can be achieved by controlling respective parameters with regard to communication devices that are in idle mode or connected mode to facilitate directing communication devices and associated traffic to desired cells.
-
公开(公告)号：US20180368037A1
公开(公告)日：2018-12-20
申请号：US15623289
申请日：2017-06-14
Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.
Inventor： Huahui Wang , Tae Won Cho , Gopalakrishnan Meempat , Henry Kafka , Ravi Raina , Xiaoyu Wang , Laurie Bigler
CPC classification number: H04W36/06 , H04L41/0816 , H04L41/0896 , H04L43/0876 , H04L43/0888 , H04L43/16 , H04L47/125 , H04W24/08 , H04W28/0205 , H04W28/0247 , H04W36/00837 , H04W88/08
Abstract: Distribution of traffic to cells in a communication network can be controlled. A distribution management component (DMC) can determine overall device traffic throughput for cells of a sector that satisfy a defined traffic throughput criterion relating to a harmonic mean of the device traffic throughput for the cells to desirably enhance or maximize the harmonic mean of the overall device traffic throughput. Based on the overall device traffic throughput for the cells, the DMC can determine whether to adjust a characteristic associated with a cell of the cells to facilitate adjusting distribution of device traffic among the cells of the sector to achieve desirable load balancing of traffic by the sector and in the network. Load balancing can be achieved by controlling respective parameters with regard to communication devices that are in idle mode or connected mode to facilitate directing communication devices and associated traffic to desired cells.
-
公开(公告)号：US20210282062A1
公开(公告)日：2021-09-09
申请号：US17330001
申请日：2021-05-25
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Huahui Wang , Tae Won Cho , Gopalakrishnan Meempat , Henry Kafka , Ravi Raina , Xiaoyu Wang , Laurie Bigler
Abstract: Distribution of traffic to cells in a communication network can be controlled. A distribution management component (DMC) can determine overall device traffic throughput for cells of a sector that satisfy a defined traffic throughput criterion relating to a harmonic mean of the device traffic throughput for the cells to desirably enhance or maximize the harmonic mean of the overall device traffic throughput. Based on the overall device traffic throughput for the cells, the DMC can determine whether to adjust a characteristic associated with a cell of the cells to facilitate adjusting distribution of device traffic among the cells of the sector to achieve desirable load balancing of traffic by the sector and in the network. Load balancing can be achieved by controlling respective parameters with regard to communication devices that are in idle mode or connected mode to facilitate directing communication devices and associated traffic to desired cells.
-
公开(公告)号：US11523316B2
公开(公告)日：2022-12-06
申请号：US17330001
申请日：2021-05-25
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Huahui Wang , Tae Won Cho , Gopalakrishnan Meempat , Henry Kafka , Ravi Raina , Xiaoyu Wang , Laurie Bigler
IPC: H04W36/06 , H04W24/08 , H04W28/02 , H04L43/0888 , H04L41/0816 , H04L41/0896 , H04W36/00 , H04W88/08 , H04L43/16 , H04L47/125 , H04L43/0876
Abstract: Distribution of traffic to cells in a communication network can be controlled. A distribution management component (DMC) can determine overall device traffic throughput for cells of a sector that satisfy a defined traffic throughput criterion relating to a harmonic mean of the device traffic throughput for the cells to desirably enhance or maximize the harmonic mean of the overall device traffic throughput. Based on the overall device traffic throughput for the cells, the DMC can determine whether to adjust a characteristic associated with a cell of the cells to facilitate adjusting distribution of device traffic among the cells of the sector to achieve desirable load balancing of traffic by the sector and in the network. Load balancing can be achieved by controlling respective parameters with regard to communication devices that are in idle mode or connected mode to facilitate directing communication devices and associated traffic to desired cells.
-
公开(公告)号：US10311367B2
公开(公告)日：2019-06-04
申请号：US14988997
申请日：2016-01-06
Inventor： Kadangode K. Ramakrishnan , Divesh Srivastava , Tae Won Cho , Yin Zhang
IPC: G06F16/30 , G06N7/00 , G06F16/48 , G06F16/242 , G06F16/9032 , G11B27/10 , H04N21/475 , H04N21/466
Abstract: Recommendation systems are widely used in Internet applications. In current recommendation systems, users only play a passive role and have limited control over the recommendation generation process. As a result, there is often considerable mismatch between the recommendations made by these systems and the actual user interests, which are fine-grained and constantly evolving. With a user-powered distributed recommendation architecture, individual users can flexibly define fine-grained communities of interest in a declarative fashion and obtain recommendations accurately tailored to their interests by aggregating opinions of users in such communities. By combining a progressive sampling technique with data perturbation methods, the recommendation system is both scalable and privacy-preserving.
-
Patent Agency Ranking
公开(公告)号：US20160117599A1
公开(公告)日：2016-04-28
申请号：US14988997
申请日：2016-01-06
Inventor： Kadangode K. Ramakrishnan , Divesh Srivastava , Tae Won Cho , Yin Zhang
IPC: G06N7/00
CPC classification number: G06N7/005 , G06F17/30038 , G06F17/30412 , G06F17/3097 , G11B27/105 , H04N21/4661 , H04N21/4668 , H04N21/4756
Abstract: Recommendation systems are widely used in Internet applications. In current recommendation systems, users only play a passive role and have limited control over the recommendation generation process. As a result, there is often considerable mismatch between the recommendations made by these systems and the actual user interests, which are fine-grained and constantly evolving. With a user-powered distributed recommendation architecture, individual users can flexibly define fine-grained communities of interest in a declarative fashion and obtain recommendations accurately tailored to their interests by aggregating opinions of users in such communities. By combining a progressive sampling technique with data perturbation methods, the recommendation system is both scalable and privacy-preserving.
-
公开(公告)号：US11039356B2
公开(公告)日：2021-06-15
申请号：US16599942
申请日：2019-10-11
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Huahui Wang , Tae Won Cho , Gopalakrishnan Meempat , Henry Kafka , Ravi Raina , Xiaoyu Wang , Laurie Bigler
Abstract: Distribution of traffic to cells in a communication network can be controlled. A distribution management component (DMC) can determine overall device traffic throughput for cells of a sector that satisfy a defined traffic throughput criterion relating to a harmonic mean of the device traffic throughput for the cells to desirably enhance or maximize the harmonic mean of the overall device traffic throughput. Based on the overall device traffic throughput for the cells, the DMC can determine whether to adjust a characteristic associated with a cell of the cells to facilitate adjusting distribution of device traffic among the cells of the sector to achieve desirable load balancing of traffic by the sector and in the network. Load balancing can be achieved by controlling respective parameters with regard to communication devices that are in idle mode or connected mode to facilitate directing communication devices and associated traffic to desired cells.
-
公开(公告)号：US10484918B2
公开(公告)日：2019-11-19
申请号：US15623289
申请日：2017-06-14
Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.
Inventor： Huahui Wang , Tae Won Cho , Gopalakrishnan Meempat , Henry Kafka , Ravi Raina , Xiaoyu Wang , Laurie Bigler
Abstract: Distribution of traffic to cells in a communication network can be controlled. A distribution management component (DMC) can determine overall device traffic throughput for cells of a sector that satisfy a defined traffic throughput criterion relating to a harmonic mean of the device traffic throughput for the cells to desirably enhance or maximize the harmonic mean of the overall device traffic throughput. Based on the overall device traffic throughput for the cells, the DMC can determine whether to adjust a characteristic associated with a cell of the cells to facilitate adjusting distribution of device traffic among the cells of the sector to achieve desirable load balancing of traffic by the sector and in the network. Load balancing can be achieved by controlling respective parameters with regard to communication devices that are in idle mode or connected mode to facilitate directing communication devices and associated traffic to desired cells.
-
公开(公告)号：US09262553B2
公开(公告)日：2016-02-16
申请号：US14567113
申请日：2014-12-11
Inventor： Kadangode K. Ramakrishnan , Divesh Srivastava , Tae Won Cho , Yin Zhang
IPC: G06F17/30 , G11B27/10 , H04N21/475 , H04N21/466
CPC classification number: G06N7/005 , G06F17/30038 , G06F17/30412 , G06F17/3097 , G11B27/105 , H04N21/4661 , H04N21/4668 , H04N21/4756
Abstract: Recommendation systems are widely used in Internet applications. In current recommendation systems, users only play a passive role and have limited control over the recommendation generation process. As a result, there is often considerable mismatch between the recommendations made by these systems and the actual user interests, which are fine-grained and constantly evolving. With a user-powered distributed recommendation architecture, individual users can flexibly define fine-grained communities of interest in a declarative fashion and obtain recommendations accurately tailored to their interests by aggregating opinions of users in such communities. By combining a progressive sampling technique with data perturbation methods, the recommendation system is both scalable and privacy-preserving.
-
公开(公告)号：US20150100599A1
公开(公告)日：2015-04-09
申请号：US14567113
申请日：2014-12-11
Inventor： Kadangode K. Ramakrishnan , Divesh Srivastava , Tae Won Cho , Yin Zhang
IPC: G06F17/30
CPC classification number: G06N7/005 , G06F17/30038 , G06F17/30412 , G06F17/3097 , G11B27/105 , H04N21/4661 , H04N21/4668 , H04N21/4756
Abstract: Recommendation systems are widely used in Internet applications. In current recommendation systems, users only play a passive role and have limited control over the recommendation generation process. As a result, there is often considerable mismatch between the recommendations made by these systems and the actual user interests, which are fine-grained and constantly evolving. With a user-powered distributed recommendation architecture, individual users can flexibly define fine-grained communities of interest in a declarative fashion and obtain recommendations accurately tailored to their interests by aggregating opinions of users in such communities. By combining a progressive sampling technique with data perturbation methods, the recommendation system is both scalable and privacy-preserving.
Abstract translation: 推荐系统广泛应用于互联网应用。 在目前的推荐系统中，用户只能发挥被动的作用，对推荐生成过程的控制有限。 因此，这些系统提出的建议和实际用户兴趣之间经常存在很大的不匹配，这些建议是细粒度和不断发展的。 通过用户分配的推荐体系结构，个人用户可以灵活地定义精细的社区，并以声明方式定义感兴趣的社区，通过汇总用户在这些社区的意见，获得准确定制的兴趣建议。 通过将逐行采样技术与数据扰动方法相结合，推荐系统既可扩展又保密。
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.018 seconds)
