DETAILED ACTION
Response to Amendment
The amendment filed on 04/10/2024 has been entered and considered by Examiner. Claims 1 - 20 are presented for examination. Claims 10-16 and 20 are withdrawn. Please cancel unelected claims.
Specification
The title of the invention is objected for not being descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
Election/Restrictions
Applicant elected with traverse to prosecute claims associated with Specie I related to claims 1-9 and 17-19 is acknowledge by the Primary Examiner. Accordingly, all claims pertain to the elected Specie will be prosecuted. With regard to the argument the search and examination of all of the claim can be made without serious burden to the Examiner, the Examiner respectfully disagrees with the Applicant. Each specie 1-3 corresponding to Figs. 4-6 is each unique and distinct, and they preforming unique functions. Thus, the restriction is made Final.
Information Disclosure Statement
The information disclosure statements (IDS) submitted are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the Examiner.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(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, 2, 5, 17, and 18 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Singh et al. (US Pub. 20240107443 A1).
For claims 1 and 17, Singh discloses a method performed by at least one processor of a network device in communication with a plurality of base stations (Figs. 11 and 13, Device 1320 communicates with network access nodes 1301–1303, obtains cell data from those nodes, processes the data, and sends selected antenna configurations back to the nodes. The processing is performed by one or more processors in a RIC, central unit, network access node, or other network entity.) [0084]–[0085], [0093], [0127]–[0131], [0170]–[0172], the method comprising:
receiving historical data collected by one or more base stations from the plurality of base stations (Figs. 4, 11, and 13; The cell data includes multiple past data items and time-series information. Device 1320 receives “collective cell data” associated with the cells served by network access nodes 1301–1303. The base stations obtain the data through UE reports, radio-resource-management operations, measurements, and power monitoring.) [0066]–[0067], [0094]–[0097], [0130]–[0131], [0154], [0170]–[0173],
the historical data indicating one or more of a power consumption, handover data, and quality of service (QoS) (Figs. 9 and 13; The claim is disjunctive because it requires “one or more of” the listed categories. The cell data expressly includes historical power consumption and cell-level QoS/data-throughput information, which is sufficient to meet at least one listed category.) [0066]–[0067], [0095], [0108]–[0112], [0172]–[0174];
generating, from the historical data, training data comprising a plurality of cell states and a corresponding random action for each cell state (Figs. 11 and 12; Training cell data represents various states of a cell or plurality of cells. Each training data set represents cell conditions for a particular time or period, including cell load, user density, mobility, power consumption, and throughput.) [0130]–[0131], [0144]–[0149]; and
training one or more neural network estimators based on the training data (Figs. 11–13; The training agent trains an AI/ML using training cell data, and the AI/ML is an artificial neural network having input, hidden, and output layers. The trained model predicts performance metrics from cell data. The models “estimators,” prediction functions correspond to estimators.) [0126]–[0145], [0146]–[0151], [0153]–[0160], [0174],
wherein the one or more neural network estimators comprise one or more of a power consumption estimator, a QoS estimator, and a handover prediction estimator (Figs. 12 and 13; Power-consumption prediction 1323 produces predicted power metrics, while data-throughput prediction 1324 uses cell-level QoS data to predict throughput. e.g. “one or more of” the listed estimators, the power or QoS predictor) [0156]–[0160], [0167]–[0169], [0172]–[0175], and
wherein each base station from the plurality of base stations is associated with a respective cell (Figure 4 expressly shows first base station 401 associated with first cell 410 and second base station 402 associated with second cell 420. Figure 13 similarly describes network access nodes 1301–1303 serving different respective cells.) [0060]–[0062], [0170]–[0172].
Claim 17 differs from claim 1 only by the additional recitation of the following limitation, which is also taught by the cited prior art. The cited prior art further discloses a network device in communication with a plurality of base stations, the network device comprising: a memory (Figs. 11 and 13); processing circuitry coupled to the memory, wherein the processing circuitry is configured to [0084]–[0085], [0093], [0127]–[0131], [0170]–[0172]:
All other identical limitations are rejected based on the same rationale as shown above.
For claims 2 and 18, Singh discloses each cell state indicates a different traffic pattern for a plurality of cells (Figs. 4, 13, and 14; AI/ML models learn network-data-traffic patterns from multiple cells. Cell states may be represented by traffic-related attributes such as cell load, PRB usage, user density, active users, time of day, and data throughput. Training data may represent states of a plurality of cells, and device 1320 processes collective data from different cells.) 0057]–[0058], [0065]–[0067], [0146]–[0149], [0170]–[0174], [0177], [0184].
For claim 5, Singh discloses the generating the training data further comprises:
converting the historical data to processed N minute interval data packets (Figs. 7, 11, and 12; processes historical cell data and converts it into AI/ML-compatible input-feature vectors. It also expressly provides an example in which configuration selection occurs every 15 minutes) [0067], [0087], [0107], [0130]–[0131], [0153]–[0154], [0173],
each data packet comprising, for at least one cell, a cell state, power consumption, on/off status and handovers (Figs. 5, 9, and 12; Each training-data item or input-feature vector represents conditions or a state of a cell for a particular time or period. The state can include cell load, user density, mobility, traffic, and other cell conditions.) [0068]–[0071], [0086], [0090], [0112]–[0114], [0155].
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 of this title, 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.
Claim(s) 3, 4, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Singh et al. (US Pub. 20240107443 A1) in view of Kim (US Pub. 20230116886 A1)
For claims 3 and 19, Singh discloses all limitations this claim depended on.
But Singh doesn’t explicitly disclose the following limitation taught by Kim.
Kim discloses the corresponding random action includes turning off at least one cell while one or more cells remain turned on [0784]-[0787], [0293], [0738].
Since, all are analogous arts addressing AI telecommunication schemes used in a mobile network; Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art would have been motivated to combine the teachings of Singh with Kim to ensure proper cell selection to assist mobile handover, thus, improving network efficiency.
For claim 4, Singh discloses all limitations this claim depended on.
But Singh doesn’t explicitly disclose the following limitation taught by Kim.
Kim discloses the corresponding random action includes turning on at least one cell while one or more cells remain turned off [0784]-[0787], [0293], [0738].
Since, all are analogous arts addressing AI telecommunication schemes used in a mobile network; Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art would have been motivated to combine the teachings of Singh with Kim to ensure proper cell selection to assist mobile handover, thus, improving network efficiency.
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Singh et al. (US Pub. 20240107443 A1) in view of Canova et al. (US Pub. 20220398873 A1).
For claim 6, Singh discloses all limitations this claim depended on.
But Singh doesn’t explicitly disclose the following limitation taught by Canova.
Canova performing certainty equivalent control that replaces a stochastic cost-to-go value function with a deterministic cost-to-go value function [0038]-[0039], [0033]
wherein the stochastic cost-to-go value function represents an expected minimal total cost of completing an energy saving solution for a time step t to a last time step T [0039], [0046]-[0048].
Since, all are analogous arts addressing AI schemes used in a mobile network; Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art would have been motivated to combine the teachings of Singh with Canova to ensure proper cost optimization to assist system operation, thus, improving operational cost saving.
Claim(s) 7 and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Singh et al. (US Pub. 20240107443 A1) in view of Ding et al. (US Pub. 20210314197 A1).
For claim 7, Singh discloses he one or more neural network estimators is the power consumption estimator (Figs. 12 and 13; AI/ML 1202 predicts performance metrics including power consumption, and power-consumption prediction 1323 produces a predicted power metric from historical power data. The AI/ML is implemented as a neural network.) [0132]–[0140], [0153]–[0160], [0172]–[0174],
wherein the power consumption estimator is a multilayer neural network (a feed-forward neural network with an input layer, output layer, and multiple hidden layers. That is structurally close to an MLP) [0160], [0174].
But Singh doesn’t explicitly disclose a multilayer perceptron (MLP) neural network;
However, Ding discloses wherein the power consumption estimator is a multilayer perceptron (MLP) neural network (Fig. 7) [0072]-[0073], [0093]-[0096];
Since, all are analogous arts addressing AI predictions used in a mobile network; Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art would have been motivated to combine the teachings of Singh with Ding to ensure proper prediction of Power conditions, thus, improving network reliability.
For claim 8, Singh discloses the one or more neural network estimators is the QoS estimator (performs “data throughput prediction” using received cell-level QoS data. US 2023/0337043 additionally places an AI-enabled QoS-prediction function at a RIC and supplies predictive QoS patterns to a gNB.) [0066], [0095], [0156]–[0160], [0172]–[0175],
wherein the QoS estimator is a multilayer neural network (permits a general multilayer feed-forward neural network) [0066], [0095], [0156]–[0160], [0172]–[0175].
But Singh doesn’t explicitly disclose a multilayer perceptron (MLP) neural network;
However, Ding discloses wherein the QoS estimator is a multilayer perceptron (MLP) neural network (Fig. 7) [0072]-[0073], [0093]-[0096];
Since, all are analogous arts addressing AI predictions used in a mobile network; Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art would have been motivated to combine the teachings of Singh with Ding to ensure proper prediction of QoS conditions, thus, improving network reliability.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Singh et al. (US Pub. 20240107443 A1) in view of Kulkarni et al. (US Pat. 11109283 B1)
For claim 9, Singh discloses all limitations this claim depended on.
But Singh doesn’t explicitly disclose the following limitation taught by Kulkarni.
Kulkarni discloses the one or more neural network estimator is the handover prediction estimator (Col. 2 lines 46-65; Col. 9 lines 56 – Col. 10 line 45),
wherein the handover prediction estimator is a long short-term memory (LSTM) neural network (Col. 2 lines 46-65; Col. 9 lines 56 – Col. 10 line 45).
Since, all are analogous arts addressing AI predictions used in a mobile network; Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art would have been motivated to combine the teachings of Singh with Kulkarni to ensure proper prediction of handover conditions, thus, improving network reliability.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US-20230135872-A1; US-20230337043-A1
Inquiries
Any inquiry concerning this communication or earlier communications from the Examiner should be directed to PAKEE FANG whose telephone number is (571)270-3633. The Examiner can normally be reached on Mon-Fri 9:00AM-5:00PM.
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, Armouche, Hadi can be reached on 571-270-3618. 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.
/PAKEE FANG/
Primary Examiner, Art Unit 2409
Prosecution Insights