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 .
DETAILED ACTION
Claims 1-20 are pending in Instant Application.
Response to Arguments
Applicant's arguments filed in the amendment filed 05/27/2026 have been fully considered but they are not persuasive. The reasons are set forth below.
Claim Rejections - 35 USC § 103
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.
Claims 1-4, 6, 9-20 are rejected under 35 U.S.C. 103 as being unpatentable over Soulhi et al., “hereinafter Soulhi” (U.S. Patent Application: 20230156501) further in view of Polehn et al., “hereinafter Polehn”(U.S. Patent Application: 20150138989).
As per Claim 1, Soulhi discloses a management entity, comprising:
a processing system that includes processor circuitry and memory circuitry that stores code (Soulhi, Para.101, Processor 1220 may include a processor, microprocessor, or processing logic that may interpret and execute instructions. Memory 1230 may include any type of dynamic storage device that may store information and instructions for execution by processor 1220, and/or any type of non-volatile storage device that may store information for use by processor 1220.), the processing system configured to cause the management entity to:
obtain a plurality of key performance indicators associated with a plurality of cells of a wireless communications network (Soulhi, Para.18, ANO 100 may receive (at 110) performance and/or configuration data from associated carriers 105. Performance data may include various key performance indicators (“KPIs”) related to network performance attributes such as accessibility, retainability, integrity, connectivity, etc. For instance, KPIs may include a number, ratio, or other metric of events such as total calls, accepted calls, unaccepted calls, dropped calls, etc. KPIs may include and/or may be based on measured or calculated network quality or performance metrics, such as signal to noise ratio (“SNR”) metrics, Signal-to-Interference-and-Noise-Ratio (“SINR”) metrics, Received Signal Strength Indicator (“RSSI”) metrics, Reference Signal Receive Power (“RSRP”) metrics, Channel Quality Indicator (“CQI”) metrics, and/or other measures of channel or signal quality.);
receive, in accordance with one or more differences between an output of a deep auto encoder and an input to the deep auto encoder (Soulhi, Para.34, each autoencoder may “encode” input data into a latent space of the autoencoder by reducing the dimensionality of the input (e.g., by mapping or otherwise reducing input data having a first quantity of dimensions to a reduced dimension representation including a lower second quantity of dimensions). The reduced dimension representation may be “decoded” to a representation having the same dimensionality as the input data. The difference between the decoded output and the unencoded input is referred to herein as a “reconstruction error.”), an indication of a performance change in at least one key performance indicator of the plurality of key performance indicators associated with the plurality of cells, (Soulhi, Para.28, ANO 100 may evaluate and/or select one or more potential actions may by identifying possible transitions and calculating associated probabilities based on application of each potential action. For instance, if good call performance (e.g., dropped calls below a threshold proportion, percentage, etc.) is likely based on the calculated probabilities, no action may be considered or implemented. However, if dropped call performance is expected to degrade (e.g., from a “good” state to an “adequate” state) based on received KPIs, performance, and/or configuration data, one or more actions associated with improving dropped call performance may be evaluated and/or implemented., Para.18, ANO 100 may receive (at 110) performance and/or configuration data from associated carriers 105. Performance data may include various key performance indicators (“KPIs”) related to network performance attributes such as accessibility, retainability, integrity, connectivity, etc. For instance, KPIs may include a number, ratio, or other metric of events such as total calls, accepted calls, unaccepted calls, dropped calls, etc. KPIs may include and/or may be based on measured or calculated network quality or performance metrics, such as signal to noise ratio (“SNR”) metrics, Signal-to-Interference-and-Noise-Ratio (“SINR”) metrics, Received Signal Strength Indicator (“RSSI”) metrics, Reference Signal Receive Power (“RSRP”) metrics, Channel Quality Indicator (“CQI”) metrics, and/or other measures of channel or signal quality. In some embodiments, KPIs may include and/or maybe based on measures of traffic performance, such as throughput, latency, jitter, packet error rate, packet loss rate, and/or other suitable metrics or values., Para.16, multiple autoencoders associated with multiple dimensions may be used to calculate reconstruction errors or other features of data (e.g., metrics, parameters, etc.) that may be used to define operating or performance states of the network. Operating or performance states of network components may be mapped to quantum state objects (“QSOs”) for analysis using AI/ML techniques or other suitable techniques. In accordance with some embodiments, such analysis may include identification and/or implementation of actions that may result in improved network performance.), wherein the input to the deep auto encoder comprises the plurality of key performance indicators (Soulhi, Para.33, autoencoders analyzing input data (e.g., network KPI information and/or other network-related information) in one dimension, two dimensions, and three dimensions. In some embodiments, autoencoders 205 may operate in different sets of dimensions. In some embodiments, the set of autoencoders 205 may include convolutional autoencoders or other neural network techniques which may operate in a single dimension or multiple dimensions.); and
output one or more messages in accordance with receiving the indication of the performance change (Soulhi, Para.30, ANO 100 may direct (at 125) actions to be implemented at carriers 105, based on analysis of received data and the selected state model. If ANO 100 identifies a recommended action, ANO 100 may send instruction messages or commands to various resources associated with carriers 105 in order to implement the identified action. As noted above, such actions may include actions related to beamforming, such as modifications of antenna angles, transmit power at one or more RF frequency bands, and/or other suitable actions. In some embodiments, such actions may include modifications of queue weights, Quality of Service (“QoS”) treatment parameters, and/or other suitable actions.).
However Soulhi does not explicitly disclose an indication of a performance change.
Polehn disclose an indication of a performance change (Polehn, Para.12, the systems may monitor network performance and match performance changes/degradation to root-cause components and identify the solutions. The systems may be used in conjunction with self-optimizing tools to ensure peak performance of the network.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teachings as in Soulhi with the teachings as in Polehn. The motivation for doing so would have been for identify a data transmission performance pattern based on measurement of key data transmission performance indicators over a time. The key data transmission performance indicators may include latency, jitter, frame loss, etc. In some instances, devices that communicate data over a network may receive degraded data. The systems may identify one or more root-cause components of degraded performance based on correlation between a degraded data transmission performance pattern and the root-cause component in a network. The root-cause component may be a network element associated with data transmission that introduces the data transmission issue into the network. (Polehn, Para.11).
With respect to Claim 19 is substantially similar to Claim 1 and is rejected in the same manner, the same art and reasoning applying.
As per Claim 2, Soulhi in view of Polehn discloses the management entity of claim 1, wherein receiving the indication of the performance change is in accordance with computing the one or more differences between the input to the deep auto encoder and the output of the deep auto encoder (Soulhi, Para.34, each autoencoder may “encode” input data into a latent space of the autoencoder by reducing the dimensionality of the input (e.g., by mapping or otherwise reducing input data having a first quantity of dimensions to a reduced dimension representation including a lower second quantity of dimensions). The reduced dimension representation may be “decoded” to a representation having the same dimensionality as the input data. The difference between the decoded output and the unencoded input is referred to herein as a “reconstruction error.”Para.25, comparisons may be made by calculating various metrics between the available state models and the received performance and/or configuration data in order to determine respective measures of similarity between the received performance and/or configuration data and one or more candidate models. For instance, ANO 100 may calculate a similarity score, a match or mismatch score, or some other suitable measure of similarity (or dissimilarity) by comparing a difference between each sampled value and each representative value to the average of the sampled value and the representative value. As another example, quantum processing may be utilized to identify matching models, as described in more detail in reference to FIGS. 3-5 below.).
With respect to Claim 20 is substantially similar to Claim 2 and is rejected in the same manner, the same art and reasoning applying.
As per Claim 3, Soulhi in view of Polehn discloses the management entity of claim 2, wherein the processing system is further configured to cause the management entity to:
train the deep auto encoder in accordance with a first set of key performance indicator values associated with the plurality of cells, wherein the first set of key performance indicator values are associated with an absence of performance changes (Soulhi, Para.21, ANO 100 may receive or generate (at 115) state models associated with performance of carriers 105. State models may include default or training models. State models may be received from another ANO 100 and/or other appropriate resources. State models may be generated and/or modified by ANO 100 based on data received from carriers 105. Additionally, or alternatively, ANO 100 may execute one or more simulations or other suitable operations to refine such models based on simulated and/or real-world feedback, such as continuous monitoring of one or more KPIs used as reinforcement learning rewarding mechanisms as described herein.).
As per Claim 4, Soulhi in view of Polehn discloses the management entity of claim 2, wherein the one or more differences are computed for each key performance indicator of the plurality of key performance indicators, for each cell of the plurality of cells, or both (Soulhi, Para.20, Such parameters may include transmission power of one or more antennas that operate according to a set of bands associated with carrier 105, queue weights implemented by one or more base stations associated with carrier 105, Quality of Service (“QoS”) parameters, mobility parameters (e.g., neighbor cell lists, handover-related thresholds, etc.), and/or other suitable modifications, adjustments, or other actions.).
As per Claim 6, Soulhi in view of Polehn discloses the management entity of claim 2, wherein, to receive the indication of the performance change, the processing system is configured to cause the management entity to: receive an indication of a cell of the plurality of cells associated with the performance change, an indication of a key performance indicator type associated with the performance change, an indication of whether the performance change comprises an improvement or a degradation, or any combination thereof (Soulhi, Para.28, if dropped call performance is expected to degrade (e.g., from a “good” state to an “adequate” state) based on received KPIs, performance, and/or configuration data, one or more actions associated with improving dropped call performance may be evaluated and/or implemented., Para.16, analysis may include identification and/or implementation of actions that may result in improved network performance. By applying reinforcement learning, including rewards and penalties, an autonomous network optimizer (“ANO”) of some embodiments may optimize management of network resources without outside intervention (e.g., without requiring user input or supervision).).
As per Claim 9, Soulhi in view of Polehn discloses the management entity of claim 1, wherein the processing system is further configured to cause the management entity to: perform a pre-processing of one or more key performance indicators of the plurality of key performance indicators (Soulhi, Para.18, Performance data may include various key performance indicators (“KPIs”) related to network performance attributes such as accessibility, retainability, integrity, connectivity, etc. For instance, KPIs may include a number, ratio, or other metric of events such as total calls, accepted calls, unaccepted calls, dropped calls, etc. KPIs may include and/or may be based on measured or calculated network quality or performance metrics, such as signal to noise ratio (“SNR”) metrics, Signal-to-Interference-and-Noise-Ratio (“SINR”) metrics, Received Signal Strength Indicator (“RSSI”) metrics, Reference Signal Receive Power (“RSRP”) metrics, Channel Quality Indicator (“CQI”) metrics, and/or other measures of channel or signal quality. In some embodiments, KPIs may include and/or maybe based on measures of traffic performance, such as throughput, latency, jitter, packet error rate, packet loss rate, and/or other suitable metrics or values. Performance and/or configuration data may be captured, sampled, monitored, etc. on a periodic and/or intermittent basis. For example, such data may be monitored at regular intervals, at irregular intervals, in response to events or triggers, and/or on some other suitable basis.).
As per Claim 10, Soulhi in view of Polehn discloses the management entity of claim 9, wherein, to perform the pre- processing, the processing system is configured to cause the management entity to: combine the one or more key performance indicators of the plurality of key performance indicators (Soulhi, Para.18, Performance data may include various key performance indicators (“KPIs”) related to network performance attributes such as accessibility, retainability, integrity, connectivity, etc. For instance, KPIs may include a number, ratio, or other metric of events such as total calls, accepted calls, unaccepted calls, dropped calls, etc. KPIs may include and/or may be based on measured or calculated network quality or performance metrics, such as signal to noise ratio (“SNR”) metrics, Signal-to-Interference-and-Noise-Ratio (“SINR”) metrics, Received Signal Strength Indicator (“RSSI”) metrics, Reference Signal Receive Power (“RSRP”) metrics, Channel Quality Indicator (“CQI”) metrics, and/or other measures of channel or signal quality. In some embodiments, KPIs may include and/or maybe based on measures of traffic performance, such as throughput, latency, jitter, packet error rate, packet loss rate, and/or other suitable metrics or values. Performance and/or configuration data may be captured, sampled, monitored, etc. on a periodic and/or intermittent basis. For example, such data may be monitored at regular intervals, at irregular intervals, in response to events or triggers, and/or on some other suitable basis.).
As per Claim 11, Soulhi in view of Polehn discloses the management entity of claim 9, wherein, to perform the pre- processing, the processing system is configured to cause the management entity to: compute a normalized log likelihood value, a log likelihood value, a likelihood value, or some combination thereof associated with the one or more key performance indicators of the plurality of key performance indicators (Soulhi, Para.53, Process 600 may further include converting (at 604) the received data to tensor form and applying normalization. The specific tensor form(s) and/or normalization(s) may be associated with various vector space(s). Such vector spaces may be associated with autoencoder operation spaces, Para.37, Reconstruction error converter 210 may merge the error data from the various autoencoders 205. Error data may be merged in various appropriate ways, such as calculating a weighted average of error data associated with each autoencoder 205, summation of errors across autoencoders 205, etc. In some embodiments, a softmax or normalized exponential function may be used to convert each of the merged values to a probabilistic value between zero and one.).
As per Claim 12, Soulhi in view of Polehn discloses the management entity of claim 1, wherein, to output the one or more messages, the processing system is configured to cause the management entity to: output an indication of the performance change to one or more of: a mobile network operator, and one or more cells of the plurality of cells (Soulhi, Para.20, mobility parameters (e.g., neighbor cell lists, handover-related thresholds, etc.), Para.88, DN 950 may be connected to one or more other networks, such as a public switched telephone network (“PSTN”), a public land mobile network (“PLMN”), and/or another network.).
As per Claim 13, Soulhi in view of Polehn discloses the management entity of claim 1, wherein the processing system is further configured to cause the management entity to: output, to one or more cells of the plurality of cells, an indication of a first change in a configuration associated with the one or more cells, wherein the performance change is associated with the first change in the configuration (Soulhi, Para.20, Configuration data may include or reflect actions implemented at each carrier 105. Such actions may include, for instance, actions related to an initial configuration, and/or actions related to modifying configurations such as initial or ongoing calibrations, responsive actions such as adjustments to configuration settings based on actual performance and/or configuration data, preventive actions such as adjustments to configuration settings based on predicted performance, and/or other appropriate modifications or updates. In some embodiments, such actions may include modifications, adjustments, and/or other actions with respect to a given carrier 105... Such parameters may include transmission power of one or more antennas that operate according to a set of bands associated with carrier 105, queue weights implemented by one or more base stations associated with carrier 105, Quality of Service (“QoS”) parameters, mobility parameters (e.g., neighbor cell lists, handover-related thresholds, etc.), and/or other suitable modifications, adjustments, or other actions. Configuration data may include log or history data indicating actions or modifications performed at certain times, and/or may include indications that no actions were implemented at certain times and/or during particular time windows.).
As per Claim 14, Soulhi in view of Polehn discloses the management entity of claim 13, wherein, to output the one or more messages, the processing system is configured to cause the management entity to: output, to one or more cells of the plurality of cells, an indication of a second change in the configuration associated with the one or more cells (Soulhi, Para.47, applying a first action 235-1 causes potential state 230-4 to replace potential state 230-2, and the probabilities associated with the states have been adjusted. Similarly, applying a second action 235-2 causes the probabilities associated with states 230-1, 230-2, and 230-3 to change, Para.20, Configuration data may include or reflect actions implemented at each carrier 105. Such actions may include, for instance, actions related to an initial configuration, and/or actions related to modifying configurations such as initial or ongoing calibrations, responsive actions such as adjustments to configuration settings based on actual performance and/or configuration data, preventive actions such as adjustments to configuration settings based on predicted performance, and/or other appropriate modifications or updates. In some embodiments, such actions may include modifications, adjustments, and/or other actions with respect to a given carrier 105.).
As per Claim 15, Soulhi in view of Polehn discloses the management entity of claim 14, wherein the second change comprises a rollback of the first change (Soulhi, Para.61, Process 700 may further include generating (at 704) a transition probability matrix based on the current state. Such a probability matrix may be generated based on previously generated state transition metrics and/or metrics generated based on current state information.).
As per Claim 16, Soulhi in view of Polehn discloses the management entity of claim 13, wherein the configuration comprises one or more of a tilt associate with the one or more cells of the plurality of cells, an azimuth associated with the one or more cells of the plurality of cells, a transmission power used by the one or more cells of the plurality of cells, or any combination thereof (Soulhi, Para.20, Configuration data may include or reflect actions implemented at each carrier 105. Such actions may include, for instance, actions related to an initial configuration, and/or actions related to modifying configurations such as initial or ongoing calibrations, responsive actions such as adjustments to configuration settings based on actual performance and/or configuration data, preventive actions such as adjustments to configuration settings based on predicted performance, and/or other appropriate modifications or updates. In some embodiments, such actions may include modifications, adjustments, and/or other actions with respect to a given carrier 105. Such actions modifications, adjustments, etc. may include physical adjustments to one or more antennas that operate according to a set of bands associated with carrier 105, such as adjustments to an azimuth angle of one or more antennas, tilt angle of one or more antennas, and/or other physical adjustments to one or more antennas or other physical components via which carrier 105 is implemented. In some embodiments, other types of adjustments may be made with respect to a given carrier 105, such as an adjustment of parameters associated with one or more devices or systems that implement carrier 105, and/or that are communicatively coupled to devices or systems that implement carrier 105. Such parameters may include transmission power of one or more antennas that operate according to a set of bands associated with carrier 105, queue weights implemented by one or more base stations associated with carrier 105, Quality of Service (“QoS”) parameters, mobility parameters (e.g., neighbor cell lists, handover-related thresholds, etc.), and/or other suitable modifications, adjustments, or other actions. Configuration data may include log or history data indicating actions or modifications performed at certain times, and/or may include indications that no actions were implemented at certain times and/or during particular time windows.).
As per Claim 17, Soulhi in view of Polehn discloses the management entity of claim 1, wherein the deep auto encoder is configured to encode the plurality of key performance indicators via a first one or more neural networks to generate an encoded plurality of key performance indicators, to decode the encoded plurality of key performance indicators via a second one or more neural networks to generate a decoded plurality of key performance indicators, and to compute a difference between the plurality of key performance indicators and the decoded plurality of key performance indicators (Soulhi, Para.34, Each autoencoder 205 may be, include, or implement a type of artificial neural network or other suitable technique that learns efficient data encoding and/or decoding schemes in an unsupervised manner. Autoencoders 205 may reduce the dimensionality of one or more data sets for more efficient analysis and/or processing that ignores or reduces signal noise. For example, each autoencoder may “encode” input data into a latent space of the autoencoder by reducing the dimensionality of the input (e.g., by mapping or otherwise reducing input data having a first quantity of dimensions to a reduced dimension representation including a lower second quantity of dimensions). The reduced dimension representation may be “decoded” to a representation having the same dimensionality as the input data. The difference between the decoded output and the unencoded input is referred to herein as a “reconstruction error.”).
As per Claim 18, Soulhi in view of Polehn discloses the management entity of claim 1, wherein a drop rate associated with one or more cells of the plurality of cells, an access failure rate associated with one or more cells of the plurality of cells, a quantity of handover attempts performed by one or more cells of the plurality of cells, a quantity of successful handovers performed by one or more cells of the plurality of cells, a throughput associated with one or more cells of the plurality of cells, a latency associated with one or more cells of the plurality of cells, an uplink traffic volume associated with one or more cells of the plurality of cells, a downlink traffic volume associated with one or more cells of the plurality of cells, or any combination thereof (Soulhi, Para.26, Each state model may represent a network operating or performance state associated with one or more KPIs or other performance metrics. In some embodiments, such metrics may be on a per-carrier basis, a per-network slice basis (e.g., where different “slices” of a network refer to different instances of some or all of the components of a network, where different slices may provide differentiated levels of service), or on some other suitable basis. For instance, one state model may be associated with a 5% rate of dropped calls and another state model may be associated with a 10% rate of dropped calls. In some embodiments, state models may be associated with various performance targets or thresholds. For instance, state models may be associated with multiple ranges of values, each range associated with a level, score, descriptor, or other classifier of performance, such as “poor” for performance below a specified threshold, “adequate” for performance between two specified thresholds, “good” for performance above a specified threshold, etc. Thus, for instance, a “poor” state (e.g., “poor” in the context of KPIs related to call success or failure rate) may be associated with more than 5% of dropped calls, an “adequate” state may be associated with between 1% and 5% dropped calls, and a “good” state may be associated with less than 1% dropped calls, Para.18, ANO 100 may receive (at 110) performance and/or configuration data from associated carriers 105. Performance data may include various key performance indicators (“KPIs”) related to network performance attributes such as accessibility, retainability, integrity, connectivity, etc. For instance, KPIs may include a number, ratio, or other metric of events such as total calls, accepted calls, unaccepted calls, dropped calls, etc. KPIs may include and/or may be based on measured or calculated network quality or performance metrics, such as signal to noise ratio (“SNR”) metrics, Signal-to-Interference-and-Noise-Ratio (“SINR”) metrics, Received Signal Strength Indicator (“RSSI”) metrics, Reference Signal Receive Power (“RSRP”) metrics, Channel Quality Indicator (“CQI”) metrics, and/or other measures of channel or signal quality. In some embodiments, KPIs may include and/or maybe based on measures of traffic performance, such as throughput, latency, jitter, packet error rate, packet loss rate, and/or other suitable metrics or values. Performance and/or configuration data may be captured, sampled, monitored, etc. on a periodic and/or intermittent basis. For example, such data may be monitored at regular intervals, at irregular intervals, in response to events or triggers, and/or on some other suitable basis.).
Claims 5 is rejected under 35 U.S.C. 103 as being unpatentable over Soulhi et al., “hereinafter Soulhi” (U.S. Patent Application: 20230156501) in view of Polehn et al., “hereinafter Polehn”(U.S. Patent Application: 20150138989) and further in view of KAJÓ et al., “hereinafter KAJÓ”( U.S. Patent Application: 20230418907).
As per Claim 5, Soulhi in view of Polehn discloses the management entity of claim 2,
However Soulhi in view of Polehn does not disclose the indication of the performance change is in accordance with a mean-squared error associated with the one or more differences satisfying a threshold mean-squared error.
KAJÓ discloses the indication of the performance change is in accordance with a mean-squared error associated with the one or more differences satisfying a threshold mean-squared error ((20230418907) KAJÓ, Para.113, the autoencoder receives input data 400, processes data with the encoder 404, the clustering module 500, and decoder encoder 404. The reconstruction loss 410 utilising mean-squared error 1200).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teachings as in Soulhi, Polehn with the teachings as in KAJÓ. The motivation for doing so would have been for implementing a special type of Deep Neural Networks called Deep Autoencoders can transform input data into a low-dimensional space, learning and modelling the behaviour of the system that generated the data in the process. In general, Autoencoders comprise two parts: an encoder and a decoder network. The simplified, lower-dimensional representation (the encoding) can be found between these parts, in the middle of the autoencoder Because of the lower dimensional representation they produce, (deep) autoencoders are often used for feature reduction. (KAJÓ, Para.11).
Claims 7, 8 are rejected under 35 U.S.C. 103 as being unpatentable over Soulhi et al., “hereinafter Soulhi” (U.S. Patent Application: 20230156501) in view of Polehn et al., “hereinafter Polehn”(U.S. Patent Application: 20150138989) and further in view of Abu-Suleiman et al., “hereinafter Abu-Suleiman”(U.S. Patent Application: 20250254543).
As per Claim 7, Soulhi in view of Polehn discloses the management entity of claim 1,
However Soulhi in view of Polehn do not disclose the plurality of key performance indicators comprise key performance indicators from the plurality of cells that are associated with a same weekday, a same time of day, a same range of weekdays, or any combination thereof.
Abu-Suleiman discloses the plurality of key performance indicators comprise key performance indicators from the plurality of cells that are associated with a same weekday, a same time of day, a same range of weekdays, or any combination thereof (Abu-Suleiman, Para.24, Dates/times can include one or more and/or different combinations of: rush hour, non-rush hour, weekday, weekend, holiday, non-holiday, night, day, business hours, non-business hours, winter, summer, spring, fall, etc.). (20250254543)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teachings as in Soulhi, Polehn with the teachings as in Abu-Suleiman. The motivation for doing so would have been for use artificial intelligence (AI) to derive a more efficiently and effectively (e.g., intelligent quantitative) performance index for a cellular base station (cell tower). AI can be utilized to identify leading (performance) indicators in cellular network metrics. AI can be utilized to identify performance similarities among geographically segregated cellular base stations (cell towers). AI can be used to scale for any cellular network size. AI can be used to derive dynamic scores adapting to different cellular traffic patterns and using smart thresholds. AI models can consider time of a metric degradation for impacting scores/indexes. (Abu-Suleiman, Para.15).
As per Claim 8, Soulhi in view of Polehn discloses the management entity of claim 1,
However Soulhi in view of Polehn do not disclose the plurality of key performance indicators exclude one or more key performance indicators associated with a holiday.
Abu-Suleiman discloses the plurality of key performance indicators exclude one or more key performance indicators associated with a holiday (Abu-Suleiman, Para.24, Dates/times can include one or more and/or different combinations of: rush hour, non-rush hour, weekday, weekend, holiday, non-holiday, night, day, business hours, non-business hours, winter, summer, spring, fall, etc.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to utilize the teachings as in Soulhi, Polehn with the teachings as in Abu-Suleiman. The motivation for doing so would have been for use artificial intelligence (AI) to derive a more efficiently and effectively (e.g., intelligent quantitative) performance index for a cellular base station (cell tower). AI can be utilized to identify leading (performance) indicators in cellular network metrics. AI can be utilized to identify performance similarities among geographically segregated cellular base stations (cell towers). AI can be used to scale for any cellular network size. AI can be used to derive dynamic scores adapting to different cellular traffic patterns and using smart thresholds. AI models can consider time of a metric degradation for impacting scores/indexes. (Abu-Suleiman, Para.15).
The applicant Argue:
Argument 1:
Applicant argues that the reference Soulhi in view of Polehn fails to teach or suggest “receive, in accordance with one or more differences between an output of a deep auto encoder and an input to the deep auto encoder, an indication of a performance change in at least one key performance indicator of the plurality of key performance indicators associated with the plurality of cells, wherein the input to the deep auto encoder comprises the plurality of key performance indicators” as recited in claim 1, 19.
In response, Examiner would like to point out that the reference Soulhi does teach in in Para.33, “autoencoders analyzing input data (e.g., network KPI information and/or other network-related information) in one dimension, two dimensions, and three dimensions. In some embodiments, autoencoders 205 may operate in different sets of dimensions. In some embodiments, the set of autoencoders 205 may include convolutional autoencoders or other neural network techniques which may operate in a single dimension or multiple dimensions.” And in Para.34, “each autoencoder may “encode” input data into a latent space of the autoencoder by reducing the dimensionality of the input (e.g., by mapping or otherwise reducing input data having a first quantity of dimensions to a reduced dimension representation including a lower second quantity of dimensions). The reduced dimension representation may be “decoded” to a representation having the same dimensionality as the input data. The difference between the decoded output and the unencoded input is referred to herein as a “reconstruction error.”, and in Para.18, “ANO 100 may receive (at 110) performance and/or configuration data from associated carriers 105. Performance data may include various key performance indicators (“KPIs”) related to network performance attributes such as accessibility, retainability, integrity, connectivity, etc. For instance, KPIs may include a number, ratio, or other metric of events such as total calls, accepted calls, unaccepted calls, dropped calls, etc. KPIs may include and/or may be based on measured or calculated network quality or performance metrics, such as signal to noise ratio (“SNR”) metrics, Signal-to-Interference-and-Noise-Ratio (“SINR”) metrics, Received Signal Strength Indicator (“RSSI”) metrics, Reference Signal Receive Power (“RSRP”) metrics, Channel Quality Indicator (“CQI”) metrics, and/or other measures of channel or signal quality. In some embodiments, KPIs may include and/or maybe based on measures of traffic performance, such as throughput, latency, jitter, packet error rate, packet loss rate, and/or other suitable metrics or values” and in Para.16, “multiple autoencoders associated with multiple dimensions may be used to calculate reconstruction errors or other features of data (e.g., metrics, parameters, etc.) that may be used to define operating or performance states of the network. Operating or performance states of network components may be mapped to quantum state objects (“QSOs”) for analysis using AI/ML techniques or other suitable techniques. In accordance with some embodiments, such analysis may include identification and/or implementation of actions that may result in improved network performance”.
The reference Soulhi discloses in Para.34 discloses “difference between an output of a deep auto encoder and an input to the deep auto encoder” and in Para.33, discloses “the input to the deep auto encoder comprises the plurality of key performance indicators”.
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 NORMIN ABEDIN whose telephone number is (571)270-5970. The examiner can normally be reached Monday to Friday from 10 am to 6 pm.
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, Vivek Srivastava can be reached at 5712727304. 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.
/NORMIN ABEDIN/Primary Examiner, Art Unit 2449
Prosecution Insights