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
This action is responsive to the application filed on 3/07/2024.
This application claims benefit of Priority under 35 U.S.C. §119 (e) from Provisional U.S. Patent Application No 63/489908, filed on 03/13/2023.
Claims 1-20 are pending in the case. Claims 1, 9, and 16 are independent claims.
Claim Rejections - 35 USC § 102
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.
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1- 4, 6- 12, and 14-20 are rejected under AIA 35 U.S.C. 102 as being anticipated over Tullberg et al., U.S. Patent Application Publication No. US 2022/0322195, published on 10/06/2022 (hereinafter Tullberg).
As for Independent claim 1
Tullberg discloses system and
“A method comprising: predicting cell edges for a plurality of Access Points (APs) including a connected AP and one or more additional APs;”
(Tullberg [0009] discloses "a method for use in a network node for predicting handover comprises training a first sequential time-based machine learning model using radio link monitoring measurements for a user equipment (UE) from a plurality of geographic positions within a first cluster of cells, times of handover of the UE to target cells of the first cluster of cells... […] … The method further comprises: predict a time for a UE handover to a target cell using the first sequential time-based machine learning model.". This describes a multi-node topology defined as a "cluster of cells". Structurally, this cluster must include the active serving cell node currently serving the client (the "connected AP") and the neighboring target cell nodes to which the client is predicting a transition (the "one or more additional APs"). Also, [0049] discloses “The output (target) data is used for predicting the identifier of the cell that the user should switch to as well as when to handover will occur”. In the context of cellular networks, predicting the time of a handover is functionally identical to predicting the moment a client reaches the cell edge. This disclosure of a cell that the user should switch to necessitates both a currently connected AP and a target (additional) AP.)
“…generating a cell edge prediction for a client connected to the connected AP;”
(Tullberg [0009] discloses “The method comprises: predict a time for a UE handover to a target cell using the first or second sequential time-based machine learning model.”; and [0008] also discloses “...the first sequential time-based machine learning model using radio link monitoring measurements for a user equipment (UE) from a plurality of geographic positions…”. These explicitly disclose the generation of a prediction value: "predict a time for a UE handover Also, it identifies the subject of this predictive process as a UE (User Equipment); and that describes predicting a handover to a target cell. Furthermore, it specifies using "radio link monitoring measurements" for the UE, which can only be obtained and processed while the UE is actively connected to and communicating with the serving network node. Thus, Tullberg discloses a processing unit (circuitry) that generates a temporal prediction (handover time) for a connected device (UE) based on its current radio environment. This process inherently predicts the client's arrival at the cell edge to facilitate a transition to a target cell.)
“…the cell edge prediction comprising: an indication of one or more candidate APs for the client to roam to of the one or more additional Aps
(Tullberg [0008] discloses "(b) a method and apparatus to predict handover in terms of what cell to switch to and when the handover will occur;" This describes predicting a destination target network access node (what cell to switch to) as part of the predictive data output, which directly satisfies providing an indication of a candidate access point (AP). [0009] discloses "...times of handover of the UE to target cells of the first cluster of cells, and cell identifiers of the target cells of the first cluster of cells for each handover." This describes utilizing the model to select a target cell identifier from a cluster of neighboring alternative network access points (target cells of the first cluster of cells) to which the user equipment (UE/client) will transition, mapping directly to a client roaming to one of the additional APs.)
“…an estimated time the client will reach the cell edge of the connected AP”
(Tullberg [0017] discloses “The processing circuitry may be operable to predict the time for a UE handover to a target cell by using the first or second sequential time-based machine learning model based on a category type of the UE”. This discloses that the processing circuitry is configured to predict a time. In the context of the machine learning models (RNN/LSTM), this output is an "estimated time" based on sequential historical data. The term “handover to a target cell” is the technical event that occurs precisely when a client reaches the functional "cell edge" of its current connection. Also, [0066] discloses “the network node checks whether the estimate of the handover time is correct. The may be used as an indication of the uncertainty of the prediction.”. Furthermore, Fig. 9 disclose the handover (HO) operation will occur if when the client reaches to the cell edge of the connected BS.)
PNG
media_image1.png
417
813
media_image1.png
Greyscale
“…transmitting the cell edge prediction to the client.”
(Tullberg [0100] discloses “antenna 162, interface 190, and/or processing circuitry 170 may be configured to perform any transmitting operations described herein as being performed by a network node. Any information, data and/or signals may be transmitted to a wireless device, another network node and/or any other network equipment.”. This describes the processing circuitry can be configured for sending data from the network to the client. Tullberg literally discloses that the circuitry is configured to transmit the relevant information to client such as wireless devices (UE).)
As for claim 2Tullberg discloses system and
“The method of claim 1, wherein the cell edges are any one of: (i) positions beyond which an ability of the client to exchange data with a network through the connected AP or additional AP associated with the cell edge becomes marginal or (ii) positions beyond which one or more of the connected AP and the one or more additional APs can provide a better connection for the client than the connected AP or additional AP associated with the cell edge."”
(Tullberg [0004] discloses "A significant delay can result in a deteriorating signal strength causing the user to lose connection before switching to another cell. These situations are known as handover failures." This describes a cell edge boundary condition where the wireless connection degrades to a point where data exchange fails completely (lose connection). This structurally maps to positions where the client's ability to communicate with the network becomes marginal. [0005] discloses "Currently, a user equipment (UE) continuously monitors the signal strength from its serving base station. If the signal strength becomes low, the UE needs to provide measurements from neighboring cells, chose the best cell, and request a switch." This defines the cell boundary position triggering a handover as the location where the connection link to the currently active node drops to an unacceptable operational threshold (signal strength becomes low). This is the direct technical equivalent of the data exchange path becoming marginal through the connected access point.)
As for claim 3 Tullberg discloses system and
“The method of claim 2, where the positions of the cell edges are based on any one of: (i) a traffic type of the client, (ii) one or more Received Signal Strength Indicators (RSSIs) of the client, (iii) latency, (iv) delay, or (v) any combination of (i)-(v).”
(Tullberg [0007] discloses "The machine learning model learns what cell the user should switch to based on its current signal strength, which eliminates the need to monitor neighboring cells in the form of reference signal received power (RSRP) measurements." This describes a system where the handover prediction boundaries (which correspond directly to the predicted cell edge locations) are computed directly from the mobile client's current wireless signal level. In wireless telecommunications, signal strength is the generic category that encompasses standard indicators such as RSSIs or RSRPs, satisfying the requirement that the cell edge prediction parameters are based on the client's received signal strength. [0008] discloses "(a) a method and apparatus to train a learning algorithm using radio signal strength and other information from the current cell;” This explicitly details training the underlying machine learning logic using the client's radio signal strength metrics to map out handover trajectories, satisfying the choice that the underlying cell boundary thresholds are based on a signal strength indicator.)
As for claim 4 Tullberg discloses system and
“The method of claim 1, wherein predicting the cell edges comprises: performing regression training based on one or more roaming training parameters.”
(Tullberg [Abstract] discloses "According to certain embodiments, a method for use in a network node for predicting handover includes training a first sequential time-based machine learning model..."; [0124] discloses “In some embodiments, the machine learning model comprises a recurrent neural network or long short-term memory (LSTM) network.”; [0009] discloses “...predicting a time for a UE handover to a target cell using the first sequential time-based machine learning model..." This explicitly teaches training a sequential, time-based machine learning model (such as a Recurrent Neural Network or LSTM) where the designated algorithmic target output is a specific timeline calculation (predicting a time for a UE handover). In the field of machine learning, training a neural network model to output a continuous numerical scalar value—such as an absolute time index or time-to-event interval—inherently constitutes performing regression training. Furthermore, Fig, 1 explicitly describes the ML training model based on the input data provided (one or more roaming training parameters)
PNG
media_image2.png
345
655
media_image2.png
Greyscale
As for claim 6 Tullberg discloses system and
“The method of claim 1, wherein generating the cell edge prediction is based at least in part on any one of: (i) historical roaming data, (ii) a Service Set Identifier of the client, (iii) a trajectory of the client, (iv) an estimation of whether the client can maintain its traffic, (v) a time of day, or (vi) any combination of (i)-(v).”
(Tullberg [FIG. 1] and [FIG. 2] disclose: In Fig. 1, the structural matrix block fed into the predictive machine learning core (ML 14) is explicitly illustrated as an input vector:
PNG
media_image2.png
345
655
media_image2.png
Greyscale
"$I = \begin{bmatrix} Cell\ id \\ RLM \\ GPS \\ \vdots \end{bmatrix}$"
(In Fig. 2, titled "Acquiring target data for training"), these input parameters are explicitly tracked and logged sequentially across continuous intervals of time: "Time t", "Time t + 1", and "Time t + 2".)
PNG
media_image3.png
827
730
media_image3.png
Greyscale
(As visually demonstrated in Figures 1 and 2, the system logs a chronological time series of geographic coordinates (GPS) and concurrent radio metrics (RLM) from a moving mobile unit. Processing a sequential set of time-stamped location points for an active device constitutes evaluating the spatial path or trajectory of the client.)
As for claim 7
Tullberg discloses system and
“The method of claim 1, wherein the cell edge prediction further comprises any one of: (i) probabilities of roaming to the one or more candidate APs, (ii) information associated with how the cell edge prediction is determined, or (iii) a combination of (i) and (ii).”
(Tullberg [0024] discloses "The prediction model is a supervised learning method in the initial training mode and in the deployed prediction mode performs online updates to the model using reinforcement learning. Particular embodiments machine learning techniques that have memory and account for sequential information, for example recurrent neural networks/long-short term memory, etc. For online learning. the same technique may be used but updated based on the accuracy of the prediction." This details exactly how the underlying predictive module determines its outputs by explicitly outlining the training configurations, supervised initialization combined with real-time reinforcement feedback loops, and structural neural designs (RNNs or LSTMs that have memory and process sequential parameters). This directly provides descriptive metadata and information associated with how the cell edge/handover prediction is determined. Tullberg [FIG. 4] discloses a system operational diagram explicitly showing a "Prediction of Handover 46" module tracking a terminal trajectory, routing into a decision point checking if there is "Enough time to switch 48", which then dynamically updates the primary logic via an "Update model 52" link or outputs a verified "Correct Prediction 54" flag.)
PNG
media_image4.png
247
470
media_image4.png
Greyscale
(This visual process flow demonstrates that the calculation system generates and couples its handover tracking blocks with descriptive status flags identifying accuracy ratings and optimization updates, fulfilling the inclusion of information associated with how the prediction is determined.)
As for claim 8 Tullberg discloses system and
“The method of claim 1, further comprising: requesting feedback of the cell edge prediction from the client; and…”
(Tullberg [0064] discloses “Some embodiments may use the ACK/NACK information to track the success of the handover predictions and so update the prediction model… if the handover is successful, the method returns to step 42 and continues to collect inputs. If the handover is unsuccessful, the method continues to step 52 which triggers an update of the machine learning model before returning to step 42.” This describes the machine learning model may be further trained using a feedback loop; the outcome of the handover then may be used as feedback as [FIG. 4] discloses a system flowchart detailing an online prediction loop where a "Prediction of Handover 46" block leads to an operational step to "Request switch 50".)
PNG
media_image4.png
247
470
media_image4.png
Greyscale
(As visually modeled in Fig. 4, when the machine learning system generates an upcoming cell transition prediction, it initiates an over-the-air protocol signal request (Request switch 50) toward the client hardware, which structurally functions to request validation or acknowledgment signaling from the terminal client.)
“…and receiving the feedback from the client.”
(Tullberg [0024] discloses: > "For online learning. the same technique may be used but updated based on the accuracy of the prediction." This describes an online update step where the machine learning model adjusts itself based on the performance outcome of its previous calculations. Determining the "accuracy of the prediction" requires receiving signaling reports and connection status logs from the client terminal to verify if the client successfully reached the target cell edge. [FIG. 5] shows process path where the execution of the switch request receives an inbound "YES / ACK" response link that routes directly into an "Update model 52" block or a "Correct Prediction 54" block. As visually demonstrated by the flow mapping in Fig. 4, the network node actively listens for and receives validation signals (ACK) and tracking outcomes generated by the roaming client device, using this feedback data to score prediction hits or update neural weights.)
As for claim 9, claim 9 reflects article of manufacture comprising a memory storage; and a processing unit coupled to the memory storage for implementing method in claim 1 and is rejected along the same rationale (Tullberg [0090, 0092, 0093] discloses “In FIG. 8, network node 160 includes processing circuitry 170, device readable medium 180, interface 190... Processing circuitry 170 is configured to perform any determining, calculating, or similar operations... may execute instructions stored in device readable medium 180 or in memory within processing circuitry” The method of Claim 1 is implemented on standard network hardware disclosed in Tullberg to perform the claimed processing and transmission steps.)
As for claim 10, limitation of parent claim 9 have been discussed above. Claim 10 reflects article of manufacture comprising computer executable instructions for implementing method in claim 2 and is rejected along the same rationale.
As for claim 11, limitation of parent claim 9 have been discussed above. Claim 11 reflects article of manufacture comprising computer executable instructions for implementing method in claim 3 and is rejected along the same rationale.
As for claim 12, limitation of parent claim 9 have been discussed above. Claim 12 reflects article of manufacture comprising computer executable instructions for implementing method in claim 4 and is rejected along the same rationale.
As for claim 14, limitation of parent claim 9 have been discussed above. Claim 14 reflects article of manufacture comprising computer executable instructions for implementing method in claim 6 and is rejected along the same rationale.
As for claim 15, limitation of parent claim 9 have been discussed above. Claim 15 reflects article of manufacture comprising computer executable instructions for implementing method in claim 7 and is rejected along the same rationale.
As for claim 16, claim 16 reflects article of manufacture comprising a non-transitory computer-readable medium that stores a set of instructions which when executed perform a method in claim 1 and is rejected along the same rationale (Tullberg [0090] discloses “In FIG. 8, network node 160 includes processing circuitry 170, device readable medium 180, interface 190”; [0022] further discloses “…a computer program product comprising a non-transitory computer readable medium storing computer readable program code, the computer readable program code operable, when executed by processing circuitry to perform any of the methods performed by the network node described.” The method of Claim 1 is implemented on standard network hardware disclosed in Tullberg to perform the claimed processing and transmission steps.)
As for claim 17, limitation of parent claim 16 have been discussed above. Claim 17 reflects article of manufacture comprising computer executable instructions for implementing method in claim 2 and is rejected along the same rationale.
As for claim 18, limitation of parent claim 16 have been discussed above. Claim 18 reflects article of manufacture comprising computer executable instructions for implementing method in claim 4 and is rejected along the same rationale.
As for claim 19, limitation of parent claim 16 have been discussed above. Claim 19 reflects article of manufacture comprising computer executable instructions for implementing method in claim 6 and is rejected along the same rationale.
As for claim 20, limitation of parent claim 16 have been discussed above. Claim 20 reflects article of manufacture comprising computer executable instructions for implementing method in claim 7 and is rejected along the same rationale.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 5 and 13 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Tullberg et al., U.S. Patent Application Publication No. US 2022/0322195, published on 10/06/2022 (hereinafter Tullberg) in view of Garg et al., U.S. Patent Application Publication No. US 2015/0098387, published on 04/09/2015 (hereinafter Garg)
As for claim 5 Tullberg system and
“The method of claim 4, wherein the one or more roaming training parameters comprise any one of: (i) one or more previous APs, (ii) one or more RSSI values at Basic Service Set entry, (iii) one or more traffic mix profiles, (iv) one or more Modulation and Coding Scheme slopes, (v) one or more RSSI values when roaming, (vi) one or more next APs, (vii) Key Performance Indicators for sensitive traffic, or (viii) any combination of (i)-(vii), for one or more of the client and one or more other clients.”
(Tullberg [Fig. 1] discloses the “Input Data 10” which describes as the “roaming training parameters”)
PNG
media_image2.png
345
655
media_image2.png
Greyscale
(As shown visually in [Fig. 1], the sequential machine learning model is trained on a continuous vector input block that pairs geographic coordinates (GPS) with Radio Link Monitoring (RLM) data. Monitoring link metrics during active user motion explicitly matches utilizing received signal strength tracking parameters (RSSI values) when roaming.)
Tullberg does not appear to explicitly disclose method and system comprising
“…for one or more of the client and one or more other clients.”
However, Garg discloses method and system limitation
“…for one or more of the client and one or more other clients.”
(Garg [0004] discloses " In one embodiment, statistics relating to mobile device cell usage are collected and monitored. The statistics may include UE measurements (RSRP/RSRQ), UE location, number of connection requests, duration of connectivity, average traffic load associated with the users, channel utilization, and other statistics...." This explicitly discloses a database querying step where historical parameter logs are pooled for “mobile device cell usage are collected” and analyzed based on collective behavior (the users). Training predictive networks using parameters compiled from a plurality of concurrent users’ equipment directly satisfies using training parameters for the client and one or more other clients.)
Accordingly, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to combine Garg with Tullberg with Garg to combine the sequential machine learning handover framework of with the past trajectory and handover tracking for optimizing wireless mobility to eliminate connection drops during client roaming. This is a finding that one of ordinary skill in the art would have recognize that applying the known technique would have yielded predictable results and resulted in an improved system.
As for claim 13, limitation of parent claim 9 have been discussed above. Claim 13 reflects article of manufacture comprising computer executable instructions for implementing method in claim 5 and is rejected along the same rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THOMAS NGUYEN whose telephone number is (571)272-9758. The examiner can normally be reached Tue-Fri 8-5.
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, Jeanette J. Parker can be reached at 571-270-3647. 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.
/THOMAS NGUYEN/Examiner, Art Unit 2646
/JEANETTE J PARKER/Supervisory Patent Examiner, Art Unit 2646
Prosecution Insights