DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 8, 10 and 18 are objected to because of the following informalities:
Regarding claim 8, the examiner interprets that the term "retaining" should be "retraining”;
Regarding claims 10 and 18, the examiner interprets that the phrase "any of claims" was intended to be removed in the amended claim;
Appropriate corrections are required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 21 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 21 appears to be written in the form of alternatives. Otherwise, the claim could be indefinite because it would appear to require, for the same performance degradation, both identifying the cause and determining that the cause cannot be identified at the same time, which would be contradictory.
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.
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 1-5, 9, 11, 13-15, 17, 28 and 43 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Wang, Hua et al. (US 20210326726 A1, hereinafter referred to as Wang).
Regarding claim 1, Wang teaches:
a method performed by a user equipment (UE), the method comprising: sending, in response to a request from a network node, information associated with one or more machine-learning (ML) models operable by the UE (Wang discloses the UE sending a report to the base station (BS) after getting a request from the base station. The report that the UE sends has information related to an ML model. See paragraph [0107]);
and receiving, from a network node, a representation of at least one modification of one or more variables associated with at least one ML model of the one or more ML models (Wang discloses the BS sending the UE an updated ML model through a configuration. See paragraph [0109]);
wherein: the one or more variables are based on the information associated with the one or more ML models (Wang discloses that the report transmitted by the UE is used by the BS to update the model. This means that the configuration the BS sends to the UE with the updated model variables uses the information in the UE report related to the ML model. See paragraph [0107]);
and the at least one modification of the one or more variables facilitates at least partially correcting or preventing performance degradations of the at least one ML model (Wang discloses that this method is used to improve the ML algorithm, thus, improving the performance of the ML based network as a whole. See paragraphs [0033-0034]);
Regarding claim 2, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches sending the network node an indication of at least one of: information associated with performance of the one or more ML models (Wang discloses that the report may feedback data that conveys the prediction accuracy of the model and indicate if the model needs updating due to producing errors. These aspects of the report depict the model's performance. See paragraph [0031]).
Regarding claim 3, Wang teaches:
wherein the performance degradation of the at least one ML model of the one or more ML models is detected by at least one of the UE or the network node (Wang discloses that the UE can detect a performance degradation based off of a criterion. See paragraph [0007]);
and wherein when the performance degradation is detected by the network node, receiving the representation of the at least one modification comprises receiving, from the network node, one or more modifications related to the performance degradations (Wang discloses that the BS can also detect performance degradation by analyzing beam quality against a threshold and reconfiguring them as needed. See paragraphs [0028] and [0037]);
Regarding claim 4, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches wherein the detection of the performance degradation is based on at least one of: one or more outputs predicted by the at least one ML model (Wang discloses several ML models that output predictions of different radio tasks. When there is an incorrect prediction that data is sent to the BS as an indication that the performance of the model needs improvement. See Abstract and paragraphs [0032-0033]).
Regarding claim 5, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches wherein sending the information associated with the one or more ML models comprises sending at least one of: information related to data collection by the UE (Wang discloses that the report the UE sends also includes data collection executed by the UE. See paragraph [0031]).
Regarding claim 9, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches based on the received representation of the at least one modification, performing at least one of: retraining the at least one ML model based on the modified data collection (Wang discloses the BS modifying the configuration and retraining the model based off of the modifications. See paragraph [0108]).
Regarding claim 11, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches communicating with a second network node to perform one or more of: sending, to the second network node, at least one of the representation of the at least one modification or an indication of a cause of the performance degradations of the at least one ML model (Wang discloses that this method can be distributed over multiple network nodes. See paragraph [0030]).
Regarding claim 13, it is rejected for the same reasons outlined in claim 1.
Regarding claim 14, it is rejected for the same reasons outlined in claim 2.
Regarding claim 15, it is rejected for the same reasons outlined in claim 3.
Regarding claim 17, it is rejected for the same reasons outlined in claim 5.
Regarding claim 28, Wang teaches a network node for performing user equipment (UE) machine-learning (ML) model analysis, the network node comprising: a transceiver, a processor, and a memory, said memory containing instructions executable by the processor whereby the network node is operative to perform (Wang discloses a network node, referred to as a base station, that has a transceiver, processor and memory. See paragraphs [0010] and [0091]).
The following limitations are rejected for the same reasons outlined in claim 1.
Regarding claim 43, Wang teaches a user equipment (UE) comprising: a transceiver, a processor, and a memory, said memory containing instructions executable by the processor whereby the UE is operative to perform (Wang discloses a UE that has a transceiver, processor and memory. See paragraphs [0008] and [0076]).
The following limitations are rejected for the same reasons outlined in claim 1.
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.
Claims 6, 12 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Wang in view of Malboubi, Mehdi et al. (US 20210357281 A1, hereinafter referred to as Malboubi).
Regarding claim 6, Wang teaches all aspects of the claimed invention except sending, to the network node, a request to assist the UE identifying a cause of the performance degradations of the at least one ML model; and receiving an indication of the cause of the performance degradations of the at least one ML model.
In the same field of endeavor, Malboubi discloses a UE sending a request to the BS to assist in root cause analysis. A solution for the root cause will define what the root cause has been identified to be. See paragraphs [0065-0066] and Figure 1.
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate the method of root cause analysis and explicitly indicating the root cause in a report. The motivation to combine is to perform targeted and verifiable solutions along with reduced recurrence.
Regarding claim 12, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches all aspects of the claimed invention except receiving, from the second network node, one or more of: an indication of an error cause analysis of the at least one ML model.
In the same field of endeavor, Malboubi discloses the concept of providing a root cause analysis and indicate the cause in a solution report. See paragraphs [0041] and [0066].
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate indicating the root cause of an error has occurred. The motivation to combine is to prevent recurrence and improve quality and efficiency.
Regarding claim 19, it is rejected for the same reasons outlined in claim 6.
Claims 7, 10 and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Wang in view of Winter, Christian et al. (US 20210160719 A1, hereinafter referred to as Winter).
Regarding claim 7, Wang teaches all aspects of the claimed invention except sending, to the network node, a request to assist the UE preventing the performance degradations of the at least one ML model.
In the same field of endeavor, Winter discloses the UE sending an instruction, which the examiner interprets as a request, to the BS to update the model to improve a detected issue. See paragraph [0089].
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate the BS aiding the UE in preventing the decrease in performance. The motivation to combine is to optimize resource allocation, proactively manage the radio link and adapt to channel and network conditions.
Regarding claim 10, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches all aspects of the claimed invention except performing at least one of: stopping using the at least one ML model.
In the same field of endeavor, Winter disclose an entity that cause an issue, which can be a ML model as a whole, to cease and desist. The examiner interprets this to mean that if the ML model is causing issues, then the system can stop it's use from continuing. See paragraph [0089].
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate pausing the use of a ML model when needed. The motivation to combine is to protect the model quality and maintain operational stability.
Regarding claim 22, it is rejected for the same reasons outlined in claim 7.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Wang in view of Vasseur, Jean-Philippe et al. (US 20200099709 A1, hereinafter referred to as Vasseur).
Regarding claim 8, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches all aspects of the claimed invention except based on the received representation of the at least one modification, performing at least one of: modifying one or more input features of the at least one ML model.
In the same field of endeavor, Vasseur discloses modifying input features in a ML based network. See Abstract.
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate the adjustment of input features after the model update. The motivation to combine is to recalibrate features and ensure compatibility with new data.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Wang in view of Yang, Jin et al. (US 20210084671 A1, hereinafter referred to as Yang).
Regarding claim 18, Wang teaches all aspects of the claimed invention except tracking modifications of the one or more variables based on the information associated with the one or more ML models, wherein the tracked modifications facilitate at least partially correcting or preventing the performance degradations.
In the same field of endeavor, Yang discloses using long short-term memory (LSTM) in a recurrent neural network architecture. LSTM can be used to track the model updates which is used to predict changes over time. See paragraph [0022].
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate using a data tracking system like LSTM to facilitate in the improvement of model performance. The motivation to combine is to retain and leverage long term patterns.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Wang in view of Malboubi and further in view of Chen, Xiaoyu et al. (US 20240323717 A1, hereinafter referred to as Chen).
Regarding claim 20, it appears to recite alternative limitations. Accordingly, only one of the recited alternatives needs be taught or suggested by the prior art. Wang teaches all aspects of the claimed invention except wherein identifying the cause of the performance degradations is based on at least one of: determining whether the one or more variables have modifications within a time window.
In the same field of endeavor, Chen discloses using a timer to trigger the event of updating a ML model. See paragraph [0083].
Therefore, it would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify Wang to incorporate using a time constraint as a factor of updating a ML model. The motivation to combine is to ensure the models have accurate and relevant information and improve efficiency.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Bai, Tianyang et al. (US 20210410219 A1, USER EQUIPMENT BEHAVIOR WHEN USING MACHINE LEARNING-BASED PREDICTION FOR WIRELESS COMMUNICATION SYSTEM OPERATION)
Ottersten, Johan et al. (US 20210345134 A1, HANDLING OF MACHINE LEARNING TO IMPROVE PERFORMANCE OF A WIRELESS COMMUNICATIONS NETWORK)
Kulkarni, Apeksha Jayateerth et al. (US 11109283 B1, HANDOVER SUCCESS RATE PREDICTION AND MANAGEMENT USING MACHINE LEARNING FOR 5G NETWORKS)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CAMILLE J ETIENNE whose telephone number is (571)721-1789. The examiner can normally be reached Mon-Thurs 9:00- 7:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ricky Ngo can be reached at (571) 272-3139. 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.
/C.J.E./Examiner, Art Unit 2464
/RICKY Q NGO/Supervisory Patent Examiner, Art Unit 2464
Prosecution Insights