DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
2. 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)(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.
3. Claims 1-3, 5-9, 11, 15, 18-20, 22, 24-26, and 30-31 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Wang et al (US 20210049451, hereinafter referred to as Wang).
Re claim 1, Wang teaches a computer-implemented method, in a user equipment (UE) of a cellular communication system (UE 110, Fig. 6-9, Fig. 13), comprising:
(i) obtaining a first conditional neural network configuration (obtaining a neural network formation configuration from the base station, Fig. 7-9, Fig. 13, obtaining a candidate set to select neural network configuration, Fig. 16-17) and a first conditional neural network execution condition (processing assignment of the neural network, Par 0106-0107, Par 0167; rules specifying operating parameters related to applying the neural network configuration, Par 0168, Par 0206-0207; operating conditions associated with each neural network configuration, Par 0170-0171; determining error metric corresponding to the input characteristics of a neural network configuration, Par 0061, Par 0191-0194) (Fig. 7-9, Fig. 13, Fig. 18-19, Par 0061, Par 0105-0107, Par 0125-0126, Par 0138-0140, Par 0146, Par 0165-0171, Par 0191-0194, Par 0206-0207);
(ii) monitoring for the first conditional neural network execution condition (monitoring for the communication related to the processing assignment associated with the neural network configuration; following rules specifying operating parameters related to applying the neural network configuration, Par 0168, Par 0206-0207; analyzing operating conditions associated with each neural network configuration, Par 0170-0171; analyzing a candidate set to select a neural network configuration, Fig. 16-17) (Fig. 7-9, Fig. 13, Fig. 18-19, Par 0061, Par 0108-0113, Par 0127-0128, Par 0138-0140, Par 0146-0150, Par 0167-0173, Par 0191-0194, Par 0206-0207, Par 0211-0212);
(iii) responsive to determining the first conditional neural network execution condition has been satisfied (receiving communications related to the processing assignment associated with the neural network configuration; satisfying rules specifying operating parameters related to applying the neural network configuration; satisfying operating conditions associated with a neural network configuration, selecting a candidate neural network configuration) configuring, based on the first conditional neural network configuration, a first neural network implemented at the UE (applying/inputting the received communications from the base station at the neural network; applying/inputting uplink communications at the corresponding neural network) (Fig. 5-9, Fig. 13, Par 0091-0094, Par 0096-0098, Par 0108-0113, Par 0125-0128, Par 0146-0150, Par 0167-0173, Par 0191-0194, Par 0206-0207, Par 0211-0212); and
(iv) performing a first set of wireless communication operations using the configured first neural network (downlink processing including demodulation and decoding; uplink processing including encoding and modulating) (Fig. 5-9, Fig. 13, Par 0091-0094, Par 0096-0098, Par 0108-0113, Par 0127-0128, Par 0146-0150, Par 0167-0173).
Re claim 2, Wang teaches to obtain a second conditional neural network configuration and a second conditional neural network execution condition (receiving updated neural network configuration, Fig. 8-9; receiving neural network configurations for uplink processing, Fig. 5-6; obtaining a candidate set/plurality of neural network configurations, Fig. 16-17); monitoring for the second conditional neural network execution condition (monitoring for the communications associated with the updated neural network configuration; analyzing the candidate set/plurality of neural network configurations to select a neural network configuration); responsive to determining the second conditional neural network execution condition has been satisfied (receiving communications related to the processing assignment associated with the updated neural network configuration; selecting a neural network configuration from the candidate set/plurality of neural network configurations) configuring, based on the second conditional neural network configuration, a second neural network implemented at the UE (applying/inputting the received communications from the base station at the updated neural network; applying/inputting uplink communications at the corresponding neural network in response to processing the downlink communications; applying/inputting the received communications from the base station at the selected neural network); and performing a second set of wireless communication operations using the configured second neural network (processing further downlink communications using the updated neural network configuration; processing uplink communication using the corresponding neural network configuration), wherein the second set of wireless communication operations is different from the first set of wireless communication operations (processing further downlink communications, processing uplink communication using the corresponding neural network configuration) (Fig. 6-9, Fig. 13, Fig. 16-17, Par 0098-0100, Par 0106-0115, Par 0119-0121, Par 0125-0133, Par 0138-0144, Par 0146-0150, Par 0167-0173).
Re claim 3, Wang teaches to implementing the configured second neural network concurrently with the configured first neural network (forming the plurality of neural networks corresponding to the neural network configurations) (Fig. 6-9, Fig. 13, Fig. 16-17, Par 0095-0100, Par 0106-0109, Par 0140, Par 0146-0149, Par 0167, Par 0170, Par 0172-0173, Par 0190-0194, Par 0197-0198).
Re claim 5, Wang teaches that the first set of wireless communication operations and the second set of wireless communication operations each comprises one or more of: channel estimation; cell measurement; beam management; signal modulation (modulating uplink communication); signal demodulation (demodulating downlink communication); Random Access Channel procedures; data streaming; or UE positioning (Fig. 5-9, Par 0090-0094, Par 0096-0099, Par 0108-0115, Par 0125-0128, Par 0146-0150, Par 0167-0173).
Re claim 6, Wang teaches that the first conditional neural network execution condition includes two or more operating conditions (processing assignment of the neural network, Par 0106-0107, Par 0167; rules specifying operating parameters related to applying the neural network configuration, Par 0168, Par 0206-0207; operating conditions associated with each neural network configuration, Par 0170-0171; determining error metric corresponding to the input characteristics of a neural network configuration, Par 0061, Par 0191-0194).
Re claim 7, Wang teaches to receive, from a network component of the cellular communication system, an index associated with the first conditional neural network configuration (index associated with a neural network table, Fig. 7-9, Fig. 12-13, Fig. 16); and obtain the first conditional neural network configuration from a storage structure using the index (retrieving the neural network configuration from the table) (Par 0106-0108, Par 0125-0127).
Re claim 8, Wang teaches that the first conditional neural network configuration is obtained from a network component of the cellular communication system (receiving the neural network configuration from a base station) (Fig. 7-9, Fig. 13, Par 0106-0108, Par 0125-0127, Par 0167).
Re claims 9, 20, Wang teaches to receive, receiving, from the network component of the cellular communication system, a Radio Resource Control (RRC) message comprising the first conditional neural network configuration (RRC message used to transmit neural network table including the neural network configuration) (Fig. 13, Par 0164-0167, Par 0172); or receiving, from the network component of the cellular communication system, a System Information Block (SIB) message comprising the first conditional neural network configuration.
Re claim 11, Wang teaches to execute a timer based on timer information received from a network component of the cellular communication system (rules indicating a time instance); and responsive to the timer expiring, configure the first neural network based on the first conditional neural network configuration (applying neural network configuration upon expiring the time instance) (Par 0119-0120, Par 0140, Par 0147-0149, Par 0168, Par 0207, Par 0219).
Re claim 15, Wang teaches that the first conditional neural network execution condition comprises at least one of: an air interface condition; or a UE operating condition (processing assignment of the neural network, Par 0106-0107, Par 0167; rules specifying operating parameters related to applying the neural network configuration, Par 0168, Par 0206-0207; operating conditions associated with each neural network configuration, Par 0170-0171; determining error metric corresponding to the input characteristics of a neural network configuration, Par 0061, Par 0191-0194).
Claim 18 recites a device performing the steps recited in claim 1 and thereby, is rejected for the reasons discussed above with respect to claim 1. Wang further teaches that the device (UE) comprises a radio frequency (RF) antenna interface (radio frequency front end, antenna 202, Fig. 2); at least one processor coupled (210) to the RF antenna interface; and a memory storing executable instructions (212, Fig. 2) (Par 0041-0042).
Re claim 19, Wang teaches a computer-implemented method, in a managing infrastructure component of a cellular communication system (base station, Fig. 6-9, Fig. 13), comprising:
(i) transmitting a conditional neural network configuration to a user equipment (UE) of the cellular communication system (transmitting a neural network formation configuration to the UE, Fig. 7-9, Fig. 13, transmitting a candidate set to select a neural network configuration, Fig. 16-17); and transmitting a set of conditional neural network execution conditions to the UE (processing assignment of the neural network, Par 0106-0107, Par 0167; rules specifying operating parameters related to applying the neural network configuration, Par 0168, Par 0206-0207; operating conditions associated with each neural network configuration, Par 0170-0171; determining error metric corresponding to the input characteristics of a neural network configuration, Par 0061, Par 0191-0194) (Fig. 7-9, Fig. 13, Fig. 18-19, Par 0061, Par 0105-0107, Par 0125-0126, Par 0138-0140, Par 0146, Par 0165-0171, Par 0191-0194, Par 0206-0207).
Claim 31 recites a device performing the steps recited in claim 19 and thereby, is rejected for the reasons discussed above with respect to claim 19. Wang further teaches that the device (base station) comprises a network interface (radio frequency front end, inter-base station interface, core network interface, Fig. 2); at least one processor coupled (260) to the network interface; and a memory storing executable instructions (262, Fig. 2) (Par 0046-0050).
Re claim 22, Wang teaches to transmit transmitting the set of conditional neural network execution conditions to the UE in a Radio Resource Control (RRC) message (neural network configuration table includes the corresponding processing assignment, Par 0164, Par 0167, Par 0172).
Re claim 24, Wang teaches that the set of conditional neural network execution conditions is transmitted as part of the conditional neural network configuration (processing assignment of the neural network, Par 0106-0107, Par 0167; rules specifying operating parameters related to applying the neural network configuration, Par 0168, Par 0206-0207; operating conditions associated with each neural network configuration, Par 0170-0171; determining error metric corresponding to the input characteristics of a neural network configuration, Par 0061, Par 0191-0194) (Fig. 7-9, Fig. 13, Fig. 18-19, Par 0061, Par 0105-0107, Par 0125-0126, Par 0138-0140, Par 0146, Par 0165-0171, Par 0191-0194, Par 0206-0207).
Re claim 25, Wang teaches to transmit timer information associated with the conditional neural network configuration to the UE, wherein the timer information configures the UE to implement a timer and apply the conditional neural network configuration responsive to the set of conditional neural network execution conditions being satisfied for a duration of the timer (time threshold value), and otherwise maintain an initial conditional neural network configuration (default/same neural network configuration) (Par 0119-0120, Par 0140, Par 0147-0149, Par 0168, Par 0207, Par 0242).
Re claim 26, Wang teaches that the conditional neural network configuration comprises at least one of a neural network architecture, one or more neural network weights, or one or more neural network architecture biases to be applied by the UE (Fig. 4Par 0058-0060, Par 0070-0072, Par 0075-0077, Par 0106, Par 0124).
Re claim 30, Wang teaches to receive a capabilities message indicating one or more capabilities of the UE; and responsive to the capabilities message having been received, transmitting at least one of an updated conditional neural network configuration or an updated set of conditional neural network execution conditions to the UE (Fig. 8-9, Fig. 13, Par 0052, Par 0057, Par 0103-0105, Par 0115-0119, Par 0122-0123, Par 0125-0127, Par 0138-0139, Par 0165-0167, Par 0176).
Claim Rejections - 35 USC § 103
4. 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.
5. Claims 13 are rejected under 35 U.S.C. 103 as being unpatentable over Wang as applied to claim 1 above and further in view of Bao et al (US 20210185515 A1, hereinafter referred to as Bao).
Re claims 13, 27, Wang does not explicitly disclose to maintain a presently implemented neural network architecture of the first neural network and changing one or more weights of the first neural network or one or more biases of the first neural network; or change a presently implemented neural network architecture of the first neural network and maintaining at least one of one or more presently implemented weights of the first neural network or one or more presently implemented biases of the first neural network.
Bao teaches to maintain a presently implemented neural network architecture of the first neural network and changing one or more weights of the first neural network or one or more biases of the first neural network (changing weight value) (Par 0017-0021, Par 0042-0046, Par 0178-0179, Par 0183, Par 0188, Par 0231, Par 0234, Par 0240, Par 0326-0329); or change a presently implemented neural network architecture of the first neural network and maintaining at least one of one or more presently implemented weights of the first neural network or one or more presently implemented biases of the first neural network.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Wang by including the step to maintain a presently implemented neural network architecture of the first neural network and changing one or more weights of the first neural network or one or more biases of the first neural network; or change a presently implemented neural network architecture of the first neural network and maintaining at least one of one or more presently implemented weights of the first neural network or one or more presently implemented biases of the first neural network, as taught by Bao for the purpose of providing neural network configuration to increase reliability of some communications and improve signal throughput, as taught by Bao (Par 0002, Par 0080).
6. Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Wang as applied to claim 1 above and further in view of Wang et al (US 20210064996 A1, hereinafter referred to as Wang ‘996).
Re claim 23, Wang does not explicitly disclose to transmit the set of conditional neural network execution conditions to the UE in a System Information Block (SIB) message.
Wang ‘996 teaches to transmit the set of conditional neural network execution conditions to the UE in a System Information Block (SIB) message (Par 0234, Par 0240).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Wang by including the step to transmit the set of conditional neural network execution conditions to the UE in a System Information Block (SIB) message, as taught by Wang ‘996 for the purpose of providing neural network formation configurations to improve communication quality by reducing bit errors, as taught by Wang ‘996 (Par 0039).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HARUN UR R CHOWDHURY whose telephone number is (571)270-3895. The examiner can normally be reached Monday-Friday 9AM-5PM.
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, Kwang B Yao can be reached at 5712723182. 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.
/HARUN CHOWDHURY/Examiner, Art Unit 2473
Prosecution Insights