DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Final Office Action is in response to the Request for Continued Examination correspondence and subsequent amendment request filed on 11/17/2025.
Claims 1-18, & 20-24 are pending and rejected.
Response to Arguments
Applicant’s arguments, see Applicant Arguments/REMARKS, filed 11/17/2025, with respect to 35 USC 101 have been fully considered and are persuasive. The rejection of claim 23 has been withdrawn.
Applicant’s arguments, see Applicant Arguments/REMARKS, filed 11/17/2025, with respect to the rejection(s) of claims 1-18, & 20-24 under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of claim amendments which warrent further search and inquiry.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-18, & 20-24 are rejected under 35 U.S.C. 103 as being unpatentable over Fjelberg et al (US 10,327,112) (hereinafter "Fjelberg") in view of Tarraf et al. (US 9,258,719) (hereinafter "Tarraf") in further view Nuss et al (US9369893B2) (hereinafter "Nuss").
Regarding claim 1, Fjelberg teaches a network node in a wireless communication network, comprising:
at least one processor (Fig. 1 170 160, col 4 lines 43-61 UEs or wireless devices within cell); and
at least one memory (Fig. 1 170 160, col 4 lines 43-61 UEs or wireless devices within cell); storing instructions, the instructions when executed by the at least one processor, cause the network node to:
- receive user equipment information from at least one user equipment present within a cell served by the network node (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, Abstract, col 3 lines 5-46, col 6 lines 1-34, col 8 lines 26-40, acquire/receive UE information from UEs within the communication network or within cell);
- based on the user equipment information, obtain at least one radio configuration parameter for the at least one user equipment by using a dual control algorithm (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 5 lines 33-55 col 12 lines 1-67 & Table 1, obtain other radio configuration parameters—using Gaussian Mixture Models—dual control algorithms—to cluster observations connected to different wireless devices and evaluating the accuracy of the model parameters); and
- transmit the at least one radio configuration parameter to the at least one user equipment; characterized in that the dual control algorithm comprises a first control algorithm and a second control algorithm (Abstract, col 3 lines 5-46, col 6 lines 1-34, col 9-col 10 lines 1-67—determining and assigning (assignment score) UEs to a proximity cell—notification to other UEs which contains key parameters—key algorithms used for cluster learning and performance – Gaussian Mixture Model/machine learning models/rule based models);
wherein the first control algorithm is configured, whenever at least one first trigger event occurs, to:
(i) group the at least one user equipment into at least one user equipment cluster based on the user equipment information (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Abstract, col 3 lines 5-46, col 6 lines 1-34; col 9 lines 34-46, grouping UEs/wireless devices into clusters based in UE/wireless device information);
wherein the second control algorithm has a performance metric and is configured, whenever at least one second trigger event occurs, to:
(i) obtain the at least one radio configuration parameter for each of the at least one user equipment cluster based on the output data from the first control algorithm (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, Abstract, col 3 lines 5-46, col 6 lines 1-34, col 5 lines 33-55 col 12 lines 1-67 & Table 1, col 15-16 lines 29-67, 1-67, obtain other radio configuration parameters—using Gaussian Mixture Models—dual control algorithms—to cluster observations connected to different wireless devices and evaluating the accuracy of the model parameters);
But Fjelberg fails to teach—
(ii) determine at least one key performance indicator requirement for each of the at least one user equipment cluster ; and
(iii) provide, to the second control algorithm, output data indicating the at least one user equipment cluster and the at least one key performance indicator requirement for each of the at least one user equipment cluster;
wherein the key performance indicator requirement comprises a quality-of-service requirement;
&
(ii) based on the at least one radio configuration parameter, whether the performance metric degrades; and
(iii) based on the performance metric degrading, provide a signal indicative of the degraded performance metric to the first control algorithm;
wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in radio conditions, there is no change in a load in the cell, and there is no change in a periodic event;
the at least one second trigger event is different from the at least one first trigger event, and the at least one first trigger event comprises an event at which the signal indicative of the degraded performance metric is provided to the first control algorithm.
However, Tarraf teaches—
(ii) determine at least one Key Performance Indicator (KPI) requirement for each of the at least one UE cluster (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, determining KPIs for wireless devices within cluster); and
(iii) provide, to the second control algorithm, output data indicating the at least one user equipment cluster and the at least one KPI requirement for each of the at least one user equipment cluster (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, provide output performance data, KPI, indicating UE clusters and KPI requirements—clustering partition cluster module and network optimization device);
wherein the key performance indicator requirement comprises a quality-of-service requirement ((Fig 1 120, 100, 101, col 10 lines 49-67, col 5 lines 3-23, Tarraf explicitly discloses monitoring KPIs that include throughput, UL power, interference levels, and dropped call rates which are standard QoS indicators in wireless systems (see col 4-5 lines 57-57, 1-23 respectively);
&
(ii) based on the at least one radio configuration parameter, whether the performance metric degrades, wherein the at least one second trigger even is different from the at least one first trigger event (Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance); and
(iii) based on the performance metric degrading, provide a signal indicative of the degraded performance metric to the first control algorithm (Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance);
wherein the at least one second trigger event is different from the at least one first trigger event, and the at least one first trigger event comprises an event at which the signal indicative of the degraded performance metric is provided to the first control algorithm (col 10 lines 49-67, performance indicators can be monitored and collected from network elements (UEs, nodes) at specific times and schedules (or events)).
Fjelberg and Tarraf are considered to be analogous to the claimed invention because both are in the same field of grouping wireless devices in a communication network using KPIs and machine learning based applications. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have a motivation to combine the teaching of Fjelberg and Tarraf to create a network node that uses a radio configuration parameter optimization by using a dual control algorithm.
Fjelberg provides a general method and system for grouping wireless devices in a communications network. Furthermore, Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Combining the teachings would allow for a network node that uses a radio configuration parameter optimization by using a dual control algorithm. The motivation to combine both references is to achieve a system that features dynamically adjusted actions based on real-time performance feedback.
But Fjelberg and Tarraf fail to teach wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in the radio conditions, there is no change in a load in the cell, and there is no change in a periodic event;
wherein based on the execution the first control algorithm updates a quality of service requirement for each of the at least one user equipment cluster and provides this as the output data to the second control algorithm.
However, Nuss teaches wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in the radio conditions, there is no change in a load in the cell, and there is no change in a periodic event (col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation);
wherein based on the execution the first control algorithm updates a quality of service requirement for each of the at least one user equipment cluster and provides this as the output data to the second control algorithm (col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 2, Tarraf teaches the network node wherein the at least one memory is storing instructions that when executed by the at least one processor, cause the network node to start a periodic timer for the first control algorithm, and wherein the at least one first trigger event further comprises an event at which the periodic timer for the first control algorithm expires (col 2 lines 10-36, col 8 lines 7-47, node-cluster partitioning module is then configured to define recurring schedule set or periodic timing).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 3, Tarraf teaches the network node wherein the at least one memory is storing instructions that when executed by the at least one processor, cause the network node to start a periodic timer for the second control algorithm, and wherein the at least one second trigger event comprises an event at which the periodic timer for the second control algorithm expires . (col 2 lines 10-36, col 8 lines 7-47, node-cluster partitioning module is then configured to define recurring schedule set or periodic timing).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 4, Tarraf teaches the network node wherein the at least one memory is storing instructions that when executed by the at least one processor, cause the network node to monitor a radio condition for the cell and/or the at least one user equipment cluster ((Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance), and wherein the at least one first trigger event further comprises an event at which the radio condition for the cell and/or any of the at least one user equipment cluster changes (col 10 lines 49-67, performance indicators can be monitored and collected from network elements (UEs, nodes) at specific times and schedules (or time trigger events).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 5, Tarraf teaches the network node wherein the first control algorithm is further configured to provide, to the second control algorithm, a signal indicative of the changed radio condition for the cell and/or any of the at least one user equipment cluster, and wherein the at least one second trigger event further comprises an event at which the signal indicative of the changed radio condition for the cell and/or any of the at least one user equipment cluster is provided to the second control algorithm (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, provide output performance data, KPI, indicating UE clusters and KPI requirements—clustering partition cluster module and network optimization device).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 6, Fjelberg teaches the network node wherein the user equipment information comprises at least one of:
a user equipment type (Fig. 1 170 160, col 4 lines 43-61 UEs or wireless devices within cell),
a type and/or quality of at least one communication service to be used (Fig. 1 170 160, col 4 lines 43-61, col 5 lines 1-67, UEs or wireless devices within cell, communication services), and
a type of at least one radio configuration parameter to be used (Table 1, col 12 lines 1-67—radio network data parameters).
Regarding claim 7, Tarraf teaches the network node wherein the key performance indicator requirement comprises at least one of a throughput requirement and an uplink (UL) power requirement (Fig 1 120, 100, Col 4-5, lines 57-67, 1-23 respectively, KPI , Quality of Service, throughput, UL).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 8, Fjelberg fails to teach but Tarraf teaches the network node wherein the at least one radio configuration parameter comprises at least one of a radio resource, a transmission power control parameter, a measurement gap, an UL beamforming parameter, and a number of supported timing advance groups (Fig 1 120, 100, Col 4-5, lines 57-67, 1-23 respectively, radio parameters and configuration metrics, power, UL formation, timing parameters).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 9, Fjelberg teaches the network node wherein the first control algorithm comprises at least one of a Machine Learning (ML) algorithm and a rule-based algorithm (Fig 1 S114a, col 9 lines 25-33, col 10 lines 50 – 67, col 11 lines 1-7, col 8 lines 8-18, machine learning unsupervised learning Gaussian mixture models control algorithm, decision-making system where rules apply (rule based algorithm based on the probability of data points falling within normal Gaussian distribution).
Regarding claim 10, Fjelberg teaches the network node wherein the second control algorithm comprises a ML algorithm (Fig 1 S114a, col 10 lines 50 – 67, col 11 lines 1-7, col 8 lines 8-18 , other machine learning algorithm separate from 1st algorithm, unsupervised and supervised learning – i.e. random forest algorithm).
Regarding claim 11, Fjelberg fails to teach but Tarraf teaches the network node wherein the at least one memory is storing instructions that when executed by the at least one processor, cause the network node to receive, from another network node, user equipment-specific historical data for the at least one user equipment, the user equipment -specific historical data relating to a user equipment transmission performance over time and/or the user equipment transmission performance over a user equipment location within the cell, and wherein the first control algorithm is configured to group the at least one user equipment into the at least one user equipment cluster based on the user equipment information and the user equipment -specific historical data Fig 2 222, Fig 1, col 6 lines 1-67, configured to receive performance indicators, characteristic patterns that reveal historical data—performance parameters relating to intracell activity, cluster partitioning module grouping UEs based on data/information and performance parameters relating to intracell activity).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 12, Fjelberg teaches a method for operating a network node in a wireless communication network, comprising:
receiving user equipment information from at least one user equipment present within a cell served by the network node (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 8 lines 26-40, acquire/receive UE information from UEs within the communication network or within cell);
based on the user equipment information, obtaining at least one radio configuration parameter for the at least one UE by using a dual control algorithm (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 5 lines 33-55 col 12 lines 1-67 & Table 1, obtain other radio configuration parameters—using Gaussian Mixture Models—dual control algorithms—to cluster observations connected to different wireless devices and evaluating the accuracy of the model parameters); and
transmitting the at least one radio configuration parameter to the at least one user equipment; characterized in that the dual control algorithm comprises a first control algorithm and a second control algorithm (col 9-col 10 lines 1-67—determining and assigning (assignment score) UEs to a proximity cell—notification to other UEs which contains key parameters—key algorithms used for cluster learning and performance – Gaussian Mixture Model/machine learning models/rule based models);
wherein the first control algorithm is configured, whenever at least one first trigger event occurs, to:
(i) group the at least one user equipment into at least one user equipment cluster based on the user equipment information (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, col 9 lines 34-46, grouping UEs/wireless devices into clusters based in UE/wireless device information);
wherein the second control algorithm has a performance metric and is configured, whenever at least one second trigger event occurs, to:
(i) obtain the at least one radio configuration parameter for each of the at least one user equipment cluster based on the output data from the first control algorithm (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 5 lines 33-55 col 12 lines 1-67 & Table 1, col 15-16 lines 29-67, 1-67, obtain other radio configuration parameters—using Gaussian Mixture Models—dual control algorithms—to cluster observations connected to different wireless devices and evaluating the accuracy of the model parameters);
But, Fjelberg fails to teach—
(ii) determine at least one key performance indicator requirement for each of the at least one user equipment cluster; and
(iii) provide, to the second control algorithm, output data indicating the at least one user equipment cluster and the at least one key performance indicator requirement for each of the at least one user equipment cluster;
wherein the key performance indicator requirement comprises a quality-of-service requirement;
&
(ii) check, based on the at least one radio configuration parameter, whether the performance metric degrades; and
(iii) if the performance metric degrades, provide a signal of the degraded performance metric to the first control algorithm; and wherein the at least one second trigger event is different from the at least one first trigger event, and the at least one first trigger event comprises an event at which the signal of the degraded performance metric is provided to the first control algorithm.
However, Tarraf teaches—
(ii) determine at least one key performance indicator requirement for each of the at least one user equipment cluster (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, determining KPIs for wireless devices within cluster); and
(iii) provide, to the second control algorithm, output data indicating the at least one user equipment cluster and the at least one key performance indicator requirement for each of the at least one user equipment cluster (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, provide output performance data, KPI, indicating UE clusters and KPI requirements—clustering partition cluster module and network optimization device);
wherein the key performance indicator requirement comprises a quality-of-service requirement ((Fig 1 120, 100, 101, col 10 lines 49-67, col 5 lines 3-23, Tarraf explicitly discloses monitoring KPIs that include throughput, UL power, interference levels, and dropped call rates which are standard QoS indicators in wireless systems (see col 4-5 lines 57-57, 1-23 respectively);
&
(ii) check, based on the at least one radio configuration parameter, whether the performance metric degrades (Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance); and
(iii) if the performance metric degrades, provide a signal of the degraded performance metric to the first control algorithm (Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance); and
wherein the at least one second trigger event is different from the at least one first trigger event, and the at least one first trigger event comprises an event at which the signal of the degraded performance metric is provided to the first control algorithm (col 10 lines 49-67, performance indicators can be monitored and collected from network elements (UEs, nodes) at specific times and schedules (or events)).
Fjelberg and Tarraf are considered to be analogous to the claimed invention because both are in the same field of grouping wireless devices in a communication network using KPIs and machine learning based applications. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have a motivation to combine the teaching of Fjelberg and Tarraf to create a network node that uses a radio configuration parameter optimization by using a dual control algorithm.
Fjelberg provides a general method and system for grouping wireless devices in a communications network. Furthermore, Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Combining the teachings would allow for a network node that uses a radio configuration parameter optimization by using a dual control algorithm. The motivation to combine both references is to achieve a system that features dynamically adjusted actions based on real-time performance feedback.
But Fjelberg and Tarraf fail to teach wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in the radio conditions, there is no change in a load in the cell, and there is no change in a periodic event;
wherein based on the execution the first control algorithm updates a quality of service requirement for each of the at least one user equipment cluster and provides this as the output data to the second control algorithm.
However, Nuss teaches wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in the radio conditions, there is no change in a load in the cell, and there is no change in a periodic event (col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation);
wherein based on the execution the first control algorithm updates a quality of service requirement for each of the at least one user equipment cluster and provides this as the output data to the second control algorithm (col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 13, Fjelberg fails to teach but Tarraf teaches the method further comprising starting a periodic timer for the first control algorithm, and wherein the at least one first trigger event further comprises an event at which the periodic timer for the first control algorithm expires. (col 2 lines 10-36, col 8 lines 7-47, node-cluster partitioning module is then configured to define recurring schedule set or periodic timing).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 14, FJelberg fails to teach but Tarraf teaches the method further comprising starting a periodic timer for the second control algorithm, and wherein the at least one second trigger event comprises an event at which the periodic timer for the second control algorithm expires. (col 2 lines 10-36, col 8 lines 7-47, node-cluster partitioning module is then configured to define recurring schedule set or periodic timing).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 15, FJelberg fails to teach but Tarraf teaches the method further comprising monitoring a radio condition for the cell and/or the at least one user equipment cluster, and wherein the at least one first trigger event further comprises an event at which the radio condition for the cell and/or any of the at least one UE cluster changes. ((Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance), and wherein the at least one first trigger event further comprises an event at which the radio condition for the cell and/or any of the at least one UE cluster changes (col 10 lines 49-67, performance indicators can be monitored and collected from network elements (UEs, nodes) at specific times and schedules (or time trigger events).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 16, Fjelberg fails to teach but Tarraf teaches the method wherein the first control algorithm is further configured to provide, to the second control algorithm, a signal indicative of the changed radio condition for the cell and/or any of the at least one user equipment cluster, and wherein the at least one second trigger event further comprises an event at which the signal indicative of the changed radio condition for the cell and/or any of the at least one user equipment cluster is provided to the second control algorithm. (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, provide output performance data, KPI, indicating UE clusters and KPI requirements—clustering partition cluster module and network optimization device).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 17, Fjelberg teaches the method wherein the user equipment information comprises at least one of:
a user equipment type (Fig. 1 170 160, col 4 lines 43-61 UEs or wireless devices within cell),
a type and/or quality of at least one communication service to be used (Fig. 1 170 160, col 4 lines 43-61, col 5 lines 1-67, UEs or wireless devices within cell, communication services), and
a type of at least one radio configuration parameter to be used (Table 1, col 12 lines 1-67—radio network data parameters).
Regarding claim 18, Fjelberg fails to teach biut Tarraf teaches the method wherein the key performance parameter requirement comprises at least one of a Quality-of-Service (QoS) requirement, a throughput requirement, and an uplink (UL) power requirement (Fig 1 120, 100, Col 4-5, lines 57-67, 1-23 respectively, KPI , Quality of Service, throughput, UL).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 19, Fjelberg fails to teach the method wherein the at least one radio configuration parameter comprises at least one of a radio resource, a transmission power control parameter, a measurement gap, an UL beamforming parameter, and a number of supported timing advance groups.
However, Tarraf teaches the method wherein the at least one radio configuration parameter comprises at least one of a radio resource, a transmission power control parameter, a measurement gap, an UL beamforming parameter, and a number of supported timing advance groups (Fig 1 120, 100, Col 4-5, lines 57-67, 1-23 respectively, radio parameters and configuration metrics, power, UL formation, timing parameters).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 20, Fjelberg teaches the method wherein the first control algorithm comprises at least one of a Machine Learning (ML) algorithm and a rule-based algorithm (Fig 1 S114a, col 9 lines 25-33, col 10 lines 50 – 67, col 11 lines 1-7, col 8 lines 8-18, machine learning unsupervised learning Gaussian mixture models control algorithm, decision-making system where rules apply (rule based algorithm based on the probability of data points falling within normal Gaussian distribution).
Regarding claim 21, Fjelberg teaches the method wherein the second control algorithm comprises a ML algorithm (Fig 1 S114a, col 10 lines 50 – 67, col 11 lines 1-7, col 8 lines 8-18 , other machine learning algorithm separate from 1st algorithm, unsupervised and supervised learning – i.e. random forest algorithm).
Regarding claim 22, Fjelberg fails to teach the method wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the network node to receive, from another network node, user equipment -specific historical data for the at least one user equipment, the user equipment -specific historical data relating to a user equipment transmission performance over time and/or the user equipment transmission performance over a user equipment location within the cell, and wherein the first control algorithm is configured to group the at least one user equipment into the at least one user equipment cluster based on the user equipment information and the user equipment -specific historical data.
However, Tarraf teaches the method wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the network node to receive, from another network node, user equipment -specific historical data for the at least one user equipment, the user equipment -specific historical data relating to a user equipment transmission performance over time and/or the user equipment transmission performance over a user equipment location within the cell, and wherein the first control algorithm is configured to group the at least one user equipment into the at least one user equipment cluster based on the user equipment information and the user equipment -specific historical data (Fig 2 222, Fig 1, col 6 lines 1-67, configured to receive performance indicators, characteristic patterns that reveal historical data—performance parameters relating to intracell activity, cluster partitioning module grouping UEs based on data/information and performance parameters relating to intracell activity).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 23, Fjelberg teaches a computer program product comprising a computer-readable storage medium, wherein the computer-readable storage medium stores a computer code which, when executed by at least one processor, causes an apparatus to perform:
receiving User Equipment information from at least one user equipment present within a cell served by the network node (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 8 lines 26-40, acquire/receive UE information from UEs within the communication network or within cell);
- based on the user equipment information, obtaining at least one radio configuration parameter for the at least one user equipment by using a dual control algorithm (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 5 lines 33-55 col 12 lines 1-67 & Table 1, obtain other radio configuration parameters—using Gaussian Mixture Models—dual control algorithms—to cluster observations connected to different wireless devices and evaluating the accuracy of the model parameters); and
- transmitting the at least one radio configuration parameter to the at least one user equipment; characterized in that the dual control algorithm comprises a first control algorithm and a second control algorithm (col 9-col 10 lines 1-67—determining and assigning (assignment score) UEs to a proximity cell—notification to other UEs which contains key parameters—key algorithms used for cluster learning and performance – Gaussian Mixture Model/machine learning models/rule based models);
wherein the first control algorithm is configured, whenever at least one first trigger event occurs, to:
(i) group the at least one user equipment into at least one user equipment cluster based on the user equipment information (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, col 9 lines 34-46, grouping UEs/wireless devices into clusters based in UE/wireless device information);
wherein the second control algorithm has a performance metric and is configured, whenever at least one second trigger event occurs, to:
(i) obtain the at least one radio configuration parameter for each of the at least one user equipment cluster based on the output data from the first control algorithm (Fig 1 160, 170, Fig 2B 110 210a, Fig 4 S102, Fig 5 S102, col 5 lines 33-55 col 12 lines 1-67 & Table 1, col 15-16 lines 29-67, 1-67, obtain other radio configuration parameters—using Gaussian Mixture Models—dual control algorithms—to cluster observations connected to different wireless devices and evaluating the accuracy of the model parameters);
But Fjelberg fails to teach—
(ii) determine at least one key performance indicator requirement for each of the at least one user equipment cluster ; and
(iii) provide, to the second control algorithm, output data indicating the at least one user equipment cluster and the at least one key performance indicator requirement for each of the at least one user equipment cluster;
wherein the key performance indicator requirement comprises a quality-of-service requirement;
&
(ii) check, based on the at least one radio configuration parameter, whether the performance metric degrades; and
(iii) based on the performance metric degrading, provide a signal indicative of the degraded performance metric to the first control algorithm; and
wherein the at least one second trigger event is different from the at least one first trigger event, and the at least one first trigger event comprises an event at which the signal indicative of the degraded performance metric is provided to the first control algorithm.
However, Tarraf teaches—
(ii) determine at least one Key Performance Indicator (KPI) requirement for each of the at least one UE cluster (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, determining KPIs for wireless devices within cluster); and
(iii) provide, to the second control algorithm, output data indicating the at least one user equipment cluster and the at least one KPI requirement for each of the at least one user equipment cluster (Fig 1 120, 100, 101, col 4-5 lines 57-67 & 1-23 respectively, , col 6 lines 1-67, provide output performance data, KPI, indicating UE clusters and KPI requirements—clustering partition cluster module and network optimization device);
wherein the key performance indicator requirement comprises a quality-of-service requirement ((Fig 1 120, 100, 101, col 10 lines 49-67, col 5 lines 3-23, Tarraf explicitly discloses monitoring KPIs that include throughput, UL power, interference levels, and dropped call rates which are standard QoS indicators in wireless systems (see col 4-5 lines 57-57, 1-23 respectively);
&
(ii) check, based on the at least one radio configuration parameter, whether the performance metric degrades (Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance); and
(iii) if the performance metric degrades, provide a signal indicative of the degraded performance metric to the first control algorithm (Fig 4 408, 410, col 13 lines 29-43, col 14 lines 55 67, performance indicator modification-monitor performance of UE and cluster and subsequent network optimization can be configured based on subpar performance); and
wherein the at least one second trigger event is different from the at least one first trigger event, and the at least one first trigger event comprises an event at which the signal indicative of the degraded performance metric is provided to the first control algorithm (col 10 lines 49-67, performance indicators can be monitored and collected from network elements (UEs, nodes) at specific times and schedules (or events)).
Fjelberg and Tarraf are considered to be analogous to the claimed invention because both are in the same field of grouping wireless devices in a communication network using KPIs and machine learning based applications. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have a motivation to combine the teaching of Fjelberg and Tarraf to create a network node that uses a radio configuration parameter optimization by using a dual control algorithm.
Fjelberg provides a general method and system for grouping wireless devices in a communications network. Furthermore, Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Combining the teachings would allow for a network node that uses a radio configuration parameter optimization by using a dual control algorithm. The motivation to combine both references is to achieve a system that features dynamically adjusted actions based on real-time performance feedback.
But Fjelberg and Tarraf fail to teach wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in the radio conditions, there is no change in a load in the cell, and there is no change in a periodic event;
wherein based on the execution the first control algorithm updates a quality of service requirement for each of the at least one user equipment cluster and provides this as the output data to the second control algorithm.
However, Nuss teaches wherein the second control algorithm triggers execution of the first control algorithm in the network node even when all trigger events for the first control algorithm are absent, the absence of all trigger events being that there is no change in the radio conditions, there is no change in a load in the cell, and there is no change in a periodic event (col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation);
wherein based on the execution the first control algorithm updates a quality of service requirement for each of the at least one user equipment cluster and provides this as the output data to the second control algorithm (col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Regarding claim 24, Fjelberg, Tarraf fails to teach wherein absence of all trigger events mean that there is no change in radio conditions, there is no change in a load in the cell, and there is no change in a periodic event.
But Nuss teaches wherein absence of all trigger events mean that there is no change in radio conditions, there is no change in a load in the cell, and there is no change in a periodic event ((col 6 lines 15-20, col 7 lines 17-29, col 9 lines 23-27 & 58-66, col 14 lines 1-2, col 11 lines 55-67, discloses a centralized SON acting as a supervisory control algorithm that coordinates and contr4ols execution of individual SON functions operating in network nodes; the cSON assigns priorities, manages scheduling, enables or disables SON functions, preempts ongoing actions, and intervenes when dSON functions fail to resolve conditions or when conflicts or oscillations are detected; in particular, the cSON triggers execution, suspension, or resumption of SON functions, rather than based on changes in radio conditions, cell load, or periodic events; the cSON intervenes when no parameter change is detected within a defined period, temporarily disabling or re-invoking SON functions to enforce correct operation).
Fjelberg discloses a network in a wireless communication network where execution of the code causes the node to receive UE information from UEs in a cell, group UEs into clusters based on UE information, and determine group-specific network requirements. Fjelberg teaches using unsupervised and supervised machine learning for grouping (first control algorithm type) and generating per-cluster requirements that are later used for network parameter configuration. Tarraf provides methods and apparatus for partitioning wireless network cells into time-based clusters using KPIs. Furthermore, Nuss discloses a centralized self-organizing network (SON) controller that supervises, prioritizes, and coordinates execution of multiple distributed SON optimization functions in cellular networks nodes, including triggering, suspending, or overriding those functions based on coordination logic and conflict resolution rather than solely on local radio, load or periodic trigger conditions. It further teaches detecting when a performance metric degrades, triggering algorithmic adjustments, and feeding updated KPI or QoS requirements back into earlier processing stages. This maps to the claimed second control algorithm that obtains radio configuration parameters based on KPI/cluster information, checks performance metrics, and provides feedback to the first algorithm when degradation occurs.
It would have been obvious to a POSITA to combine the combination of references of Fjelberg, Tarraf, and Nuss in order to produce a network node that employs a dual control algorithm. The motivation for the combination is to improve network efficiency and responsiveness by allowing radio configuration parameters to be tailored to dynamically formed UE clusters and adjusted in real time based on monitored performance degradation or trigger events, rather than using static or global configuration. Such integration represents a predictable use of known techniques such as machine learning-based clustering and KPI optimization algorithms—which working together to yield enhanced adaptability and performance in wireless networks.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL WILLIAM ABBATINE whose telephone number is (571)272-0192. The examiner can normally be reached Monday-Friday 0830-1700 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Nishant Divecha can be reached at (571) 270-3125. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MICHAEL WILLIAM ABBATINE JR./Examiner, Art Unit 2419
/Nishant Divecha/Supervisory Patent Examiner, Art Unit 2419