Detailed Office Action
1. This communication is being filed in response to the initial submission having a mailing date of 06/28/2024, in which a three (3) month Shortened Statutory Period for Response has been set.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Acknowledgements
3. Upon new entry, claims (1 -16 and 19 -21) appear pending for examination, of which (1, 19, 20, 21) is/are the four (4) independent claims on record, being amended. Claims (17 -18) were originally cancelled.
Information Disclosure Statement
4. The Information Disclosure Statement (IDS) that was/were submitted on 06/28/2024 is/are PARTIALLY in compliance with the provisions of 37 CFR 1.97, being considered by the Examiner.
4.1. Multiple entries from the IDS have been discarded, for failure to cite the relevant pages in the publication. Each of the submitted publications must comply with the 37 CFR 1.98 provisions, in order evaluate the corresponded information listed, to be considered by the Office. See also MPEP [37 CFR 1.98(b); - Each publication must be identified by publisher, author (if any), title, relevant pages of the publication, and date and place of the publication.]
Drawings
5. The submitted Drawings on date 06/28/2024 has been accepted and considered under the 37 CFR 1.121 (d).
Claim Interpretation
6. For the sole purpose of examination, and under the broadest reasonable interpretation (BRI), consistent with the instant specification and the common knowledge of one of ordinary skill in the art, the below list of terms/limitations will be considered to read as:
6.1. Term “graph” in the claims, it will be read as - (e.g. handover related KPI(s) and user mobility related KPI(s) as a good measure of similarity for the purposes of forming the pruned relational graph; [specs; 0010]).
6.2. As a matter of claim interpretation in general terms, the Office gives the claims their broadest reasonable interpretation (BRI) consistent with the specification and the common knowledge. See “In re Morris,” 127 F.3d 1048, 1054 (Fed. Cir. 1997); and see also "In re Am. Acad. Of Sci. Tech Ctr.”, 367 F.3d 1359, 1369 (Fed. Cir. 2004); …and while the Office interprets the presented claims broadly but reasonably in light of the specification, we nonetheless must not import limitations from the specification into the claims. See also “Phillips v. A WH Corp.”, 415 F.3d 1303, 1323 (Fed. Cir. 2005).
Claim rejection section
35 USC 103
7. 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 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.
7.1. The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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 non-obviousness.
7.2. Claims (1 -16 and 19 -21) is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun; et al. (“Application of Machine Learning in Wireless networks; 2019”; hereafter “Sun”) in view of Veggalam; et al. US 12,127,056 B2; hereafter “Veggalam,”
Claim 1. (Currently Amended) Sun discloses the invention substantially as claimed - A computer-implemented method for distributed machine learning, performed in a wireless access network comprising a plurality of nodes, the method comprising, (e.g. a Machine Learning (ML) technique for Wireless Access Networks (WAN), enabling neighboring nodes to autonomously make decisions based on local observations/constrains and traffic loads, [Chap. 1]; also employing supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning (RL), [Chap. 2].
Sun specifically discloses - defining an initial set of neighbor relation edges which connect at least some of the nodes of the wireless access network, (e.g. see KNN technique for neighboring nodes, based on distance metric, voting/classification, and/or average regression; [Chap.2.2]);
where each neighbor relation edge is associated with at least one neighbor relation key performance indicator, KPI, selecting a subset of the neighbor relation edges for each node, wherein the selected subset of neighbor relation edges is associated with one or more neighbor relation KPI that meets a pre-determined acceptance criterion, forming a relational graph for each node (e.g. see neighboring nodes, graph’s configuration based on distance metric, voting and classification, and average regression; [Chap.2.2]); based on the respective selected subset of neighbor relation edges for the node, (e.g. see Key implementation of the same, including key performance indicators (KPI); [page 20 -21]);
and performing distributed machine learning over the nodes in the wireless access network based on the formed relational graph for each node; (e.g. see KNN technique for neighboring nodes, graph’s configuration based on distance metric, voting and classification, and average regression; [Chap.2.2].)
Given the teachings of Sun; et al. as a whole, and under the obvious assumption and purpose of his papers, it is noted that some of the functional steps/components as listed (i.e. no schematic architecture disclosed), are missed or not fully described in the papers.
For the purpose of additional clarification and structural support, Veggalam discloses – (e.g. a similar implementation as (e.g. a system for determining handover parameters for one or more network nodes using a trained machine-learned model, handover parameters and key performance indicators (KPI), as illustrated in at least Figs. (1-2).
Therefore, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention, to modify the implementation of Sun, with the architecture of Veggalam, in order to provide (e.g. machine learning system and model training able to determine sets of configuration parameters (i.e. handover parameters) to control the network nodes, improving/optimizing performance metrics, throughput optimization, network speed, spectrum uses, load minimization, and the like; [Overview; 2: 55].)
Claim 2. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising defining the set of neighbor relation edges as edges associated with a hand-over related KPI and/or a user mobility related KPI. (The same rationale and motivation apply as given to Claim 1 above.)
Claim 3. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1 or 2, where each neighbor relation edge is associated with a third-generation partnership program, 3GPP, X2 connection between two nodes in the wireless access network; (e.g. both references disclosed support for 3GPP; [Sun (Col. 1) and Veggalam (page 21); the same motivation applies herein.)
Examiner’s note is taken; Regarding the associated to the matter Releases of 3GPP papers as: Rel.16 (year 2020); Rel. 17 (year 2022) marked the second and third phases of 3GPP’s 5G standardization, completing the initial 5G system (Rel. 15) and expanding its capabilities to support new verticals, deployment scenarios, and network automation), way before the invention was made/filed.
Claim 4. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, where a neighbor relation KPI represents a metric which involves operations in at least two nodes in the plurality of nodes; (e.g. see analogous neighbor relation KPI represents a metric in [Sun; Chap.2.2] and [Veggalam 2: 55]; the same motivation applies herein.)
Claim 5. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising executing automated neighbor relations, ANR, procedure to define the set of neighbor relation edges.
Examiner’s note is taken; Regarding the known use of ANR and SON solutions, for automatic generation, management and efficiency of neighbor relations, bw. modules in LTE and other technologies, way before the invention was made/filed.
Claim 6. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising obtaining one or more of the “neighbor relation” KPIs from a network data analytics function, NWDAF, of the wireless access network. (The same rationale and motivation apply as given to Claims (1 and 5) above.)
Claim 7. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising selecting the subset of the neighbor relation edges for each node as a number of neighbor relation edges among the neighbor relation edges associated with highest neighbor relation KPI or as a fraction of neighbor relation edges among the neighbor relation edges associated with highest neighbor relation KPI. (The same rationale and motivation apply as given to Claims (1 and 5) above.)
Claim 8. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising selecting the subset of the neighbor relation edges for each node as the neighbor relation edges having respective neighbor relation KPIs above a pre-determined acceptance threshold. (The same rationale and motivation apply as given to Claims (1 and 5) above.)
Claim 9. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising selecting the subset of the neighbor relation edges for each node based on a feature selection method such as forward selection, backwards elimination, or recursive feature elimination.
Examiner’s note is taken; Regarding the use of (i.e. forward selection, backward elimination, or recursive feature elimination (RFE)), for selecting features related to a neighbor relation in an Adaptive Neighbor Relation (ANR) context, being commonly used in telecom self-organizing networks way before the invention was made/filed.
Claim 10. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising performing the distributed machine learning in the wireless access network as a reinforcement learning, (RL), procedure involving a plurality of RL agents, such as a multi-agent RL procedure, MARL; (e.g. see Reinforcement Learning for single and multiple agents disclosed; [Sun; Chap. 2].)
Claim 12. (Currently Amended) Sun/Veggalam discloses - The method according to claim 10, comprising registering each RL agent by a network repository function, NRF, of the wireless access network.
Examiner’s note is taken; Regarding the Network Repository Function (NRF) basically acts as central service registry and/or discovery, for all Network Functions (NFs) in the operator’s network.
Claim 13. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising performing the distributed machine learning in the wireless access network as a federated learning, FL, procedure and/or as a Deep Q Learning, DQN, method; (e.g. see similar performing the distributed machine learning, as a Q Learning in [Sun; Chap. 2])
Claim 14. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising performing an optimization of a network parameter associated with the wireless access network as a distributed machine learning procedure based on the formed relational graphs; (e.g. see neighboring nodes, graph’s configuration based on distance metric, voting and classification, and average regression; [Chap.2.2]);
Claim 15. (Currently Amended) Sun/Veggalam discloses - The method according to claim 14, where the network parameter comprises an antenna tilt parameter; (e.g. see network parameters of the same; [Sun; page 6]).
Claim 16. (Currently Amended) Sun/Veggalam discloses - The method according to claim 1, comprising performing secondary carrier prediction in the wireless access network as a distributed machine learning procedure based on the formed relational graphs; (e.g. see neighboring nodes, graph’s configuration based on distance metric, voting and classification, and average regression; [Chap.2.2]);
Claim 17 -18. (Cancelled)
Claim 19. (Currently Amended) Sun/Veggalam discloses - A network node for implementing a distributed machine learning method performed in a wireless access network comprising a plurality of nodes, the network node comprising:
processing circuitry; a network interface coupled to the processing circuitry; and a memory coupled to the processing circuitry, wherein the memory comprises machine readable computer program instructions that, when executed by the processing circuitry, causes the network node to:
define a set of neighbor relation edges which connect at least some of the nodes of the wireless access network,
where each neighbor relation edge is associated with at least one neighbor relation key performance indicator, KPI, select a subset of the neighbor relation edges for each node,
wherein the selected subset of neighbor relation edges is associated with one or more neighbor relation KPI that meets a pre-determined acceptance criterion, form a relational graph for each node based on the respective selected subset of neighbor relation edges for the node, and perform distributed machine learning over the nodes in the wireless access network based on the formed relational graph for each node. (Current lists all the same elements as recite in Claim 1 above, but in “network node” form instead, and is/are therefore on the same premise.)
Claim 20. (Currently Amended) Sun/Veggalam discloses - A computer-implemented method for distributed machine learning, performed in a wireless access network comprising a plurality of nodes, the method comprising
initializing a reinforcement learning, RL, agent for each node in the plurality of nodes,
constructing a network graph for the wireless access network comprising the nodes at least partially interconnected by pair-wise neighbor relation edges,
assigning a graph edge weight to each neighbor relation edge in the network graph, based on an associated neighbor relation key performance indicator, KPI,
filtering the neighbor relation edges based on the neighbor relation KPIs and on a pre- determined acceptance criterion, and
for each RL agent, obtaining the graph edge weights of the filtered neighbor relation edges associated with the RL agent, receiving a policy update from each of the RL agents associated with the filtered neighbor relation edges, and updating the policy of the RL agent based on the policy updates received by the RL agent. (Current lists all the same elements as recite in Claim 1 above, but in “method” form instead, and is/are therefore on the same premise.)
Claim 21. (Currently Amended) Sun/Veggalam discloses - A network node for implementing a distributed machine learning method performed in a wireless access network comprising a plurality of nodes, the network node comprising:
processing circuitry; a network interface coupled to the processing circuitry; and a memory coupled to the processing circuitry, wherein the memory comprises machine readable computer program instructions that, when executed by the processing circuitry, causes the network node to:
initialize a reinforcement learning, RL, agent for each node in the plurality of nodes, construct a network graph for the wireless access network comprising the nodes at least partially interconnected by pair-wise neighbor relation edges,
assign a graph edge weight to each neighbor relation edge in the network graph, based on an associated neighbor relation key performance indicator, KPI, filter the neighbor relation edges based on the neighbor relation KPIs and on a pre- determined acceptance criterion, and
for each RL agent, obtain the graph edge weights of the filtered neighbor relation edges associated with the RL agent,
receive a policy update from each of the RL agents associated with the filtered neighbor relation edges (420), and
update the policy of the RL agent based on the policy updates received by the RL agent. (Current lists all the same elements as recite in Claim 1 above, but in “network node” form instead, and is/are therefore on the same premise.)
Claim Objection section
8. Claim (11) is/are objected to, because of the feature associated with - a new gradient message for each of the agents, using a data analytic function, as detailed described in [specs; 0074], but it may be considered for allowance if f incorporated into all the language of the recorded parallel running independent claims (1, 19, 20 and 21).
8.1. The cited above claim appears as:
Claim 11. (Currently Amended) The method according to claim 10, comprising initializing (Si) a plurality of RL agents, where each RL agent is associated with a node in the wireless access network and also with a respective RL agent policy, where the method further comprises updating the RL policy of an RL agent associated with a node based on one or more gradient updates received from other RL agents in the relational graph for the node.
Prior Art Citations
9. The following List of prior art, made of record and not relied upon, is/are considered
pertinent to applicant's disclosure:
9.1. Patent documentation:
US 12,666,326 B2 Veijalainen; et al.
US 12,127,056 B2 Veggalam; et al.
US 12,628,224 B2 Ryden; et al.
US 12,524,611 B2 Zhong; et al.
9.2. Non-Patent documentation:
_ Application of Machine Learning in Wireless networks; 2019;
_ Machine Learning for Wireless Networks with Artificial Intelligence; Chen -2017;
_ Network Architecture for Machine Learning. A Network Operators Perspective; July 2022;
CONCLUSIONS
10. Any inquiry concerning this communication or earlier communications from the examiner should be directed to LUIS PEREZ-FUENTES (luis.perez-fuentes@uspto.gov) whose telephone number is (571) 270 -1168. The examiner can normally be reached on Monday-Friday 8am-5pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, WILLIAM VAUGHN can be reached on (571) 272-3922. The fax phone number for the organization where this application or proceeding is assigned is (571) 272 -3922. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated system, please call (800) 786 -9199 (USA OR CANADA) or (571) 272 -1000.
/LUIS PEREZ-FUENTES/
Primary Examiner, Art Unit 2481.
Prosecution Insights