DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is in response to the communication filed on 11/25/22024. Claims 1-2,5-10,13-14,16-17,19,21-24,26,30 and 34 are pending in this application.
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on 11/25/2024 is/are in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS(s) is/are being considered by the examiner.
Claim Objections
Claims 1, 7, 26 and 34 are objected to because of the following informalities:
Claims 1, 7 and 34 recite the limitation “the one more AI based models” in lines 9 and 12 of claim 1, line 2 of claim 7 and lines 8 and 11 of claim 34 respectively. It is not clear to the examiner of the limitation refers to “one or more artificial intelligence (AI) based models” recited in line 6 of claim 1 and line 5 of claim 34. For examination purpose, “the one more AI based models” will read as ““the one or more AI based models.”
In claim 26, line 8, it is not clear to the examiner if “or” merely connecting the limitations “an uplink-downlink correspondence metric” and “a number of random access channel attempts,” OR connecting the two groups of limitations “a number of random access channel attempts; a number of radio link control re-transmissions; measurements of reference signals configured for radio link monitoring; an uplink-downlink correspondence metric” and “a number of random access channel attempts; a number of radio link control retransmissions; measurements of reference signals configured for radio link monitoring; a number of consecutive hybrid automatic repeat discontinuous transmission (HARO DTX) events; and measured reference signal received power of non-radio link monitoring reference signals.” For examination purpose, the alternative of the two groups of limitations are considered for examination. Applicant is recommended to put appropriate indentation to clarify what “or” is limiting.
Appropriate correction is 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 16 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 pre-AIA the applicant regards as the invention.
Claim 16 recites the limitation “the event trigger” in line 2. The instant claim modifies the limitation “an event trigger” of claim 10 for which Dalmiya-Esswie-Lin is not relied upon, without requiring such limitation to be applied. Therefore, there is insufficient antecedent basis for this limitation in the claim. For examination purpose, “the event trigger” will read as “an event trigger.” Applicant is recommended to clarify the elements that are related to the limitation “an event trigger” in claim 16.
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 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.
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 nonobviousness.
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 1-2, 5, 8-10, 14, 16, 23 and 34 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20230145079 A1 (hereinafter Dalmiya, included in 11/25/2024 IDS), in view of US 20240187877 A1 (hereinafter Esswie), and in further view of US 20250062843 A1 (hereinafter Lin).
For Claim 1, Dalmiya teaches a method of performing artificial intelligence (AI) based compression model performance monitoring by a user equipment (UE) (Dalmiya, para. [0006] “… In aspects of the present disclosure, a method of wireless communication by a user equipment (UE) … predicting a radio link failure (RLF) for the secondary cell group based on multiple inputs to a machine learning model …”), the method comprising: …; …; …; …; …;
predicting the RLF using the one or more AI based models based on … a block error rate (BLER) of one or more reference signals (Dalmiya teaches ML model predicting RLF using BLER (PDSCH initial/residual) and plurality of radio-link inputs; para. [0027] “… According to aspects of the present disclosure, a UE predicts RLF before a secondary cell group RLF condition occurs, for example, as specified by the standards. The UE may predict with any type of machine learning technique. Based on the prediction, the UE may signal the potential RLF condition to the network …”; para. [0028] “… a machine learning model receives input variables. Based on the input variables, the machine learning model predicts whether a secondary cell group RLF will occur at a time in the future. The machine learning model generates an alert based on the prediction …”; para. [0029] “… For example, the input variables of the machine learning model may include a downlink block error rate (BLER) for the last D time slots, where D is a moving window. The input variables of the machine learning model may also include a current packet data convergence protocol (PDCP) number of holes in the receive window. Another input variable of the machine learning model may be a number of PDCP reordering timer expiration events that have occurred in the last D time slots … the input variables of the machine learning model may include a mean delay of radio link control (RLC) acknowledgements to new packet transmissions, in the last D time slots …”; the input variables of the ML model for predicting also includes downlink control information (DCI) miss rate, signal statistics, radio link management (RLM) timer along with an InSync count and an OutOfSync count, etc., as recited in para. [0086]-[0100]) or based on classifying a risk level of the RLF based on a plurality of inputs; and
transmitting an RLF prediction report to the base station based on the prediction (Dalmiya, para. [0027] “… Based on the prediction, the UE may signal the potential RLF condition to the network …”; para. [0127] “… Aspect 20: … further comprising transmitting, to a base station, an indication of a potential RLF based upon the predicting of the RLF …”).
Dalmiya does not explicitly teach, but Esswie teaches encoding, for transmission to a base station, a UE capability report (Esswie teaches a UE transmitting capability information to a RAN node; Examiner notes that Esswie teaches the claimed “encoding/decoding” sequence functionally, it teaches the underlying transmit/receive signaling operations corresponding to the claimed UE-side encoding and decoding steps since the UE must process the received signaling to implement the specified model-management operation; FIG. 4; para. [0108] “… Turning now to FIG. 4, the figure illustrates a timing diagram of an example method to configure a user equipment 115 with a learning model metric reporting configuration from a network node/RAN 105. At act 405, UE or wireless transmit and receive unit (WTRU) 115 (sometimes referred to below as merely UE 115) transmits capability information that may comprise an indication of radio function learning model information, which may comprise learning model information corresponding to one or more radio function learning models of the user equipment, to serving cell RAN 105. The capability information may comprise indications for one or more radio functions that may be implemented by, operated by, performed by, or otherwise facilitated by, UE 115. The capability information may comprise information that indicates types of AI/ML learning models ( e.g., supervised, unsupervised, reinforcement learning, and the like) that may correspond to, support, or facilitate, the radio functions …”);
decoding configuration information, received from the base station, for training one or more artificial intelligence (AI) based models for predicting radio link failure (RLF) (Esswie teaches the UE receiving AI/ML learning model management configurations including instruction to train ML models to facilitate radio functions, while Dalmiya teaches ML models predicting RLF as discussed above; FIG. 4, FIG. 7; para. [0108] “… At act 410, RAN 105 transmits, and UE/WTRU 115, receives one or more AI/ML learning model management configurations from RAN 105. A learning model management configuration may comprise format information corresponding to an AI/ML model management request that may be made by UE 115 …”; para. [0109] “… The format information may comprise learning-model-specific performance metrics to report according to a model identifier, or reporting conditions, of a model management request, including a reporting periodicity, or a learning model degradation criterion, which may be referred to as a model performance metric criterion, for example a threshold …”; para. [0123] “… Turning now to FIG. 7, the figure illustrates a flow diagram of an embodiment method 700 to manage one or more learning models that may facilitate one or more corresponding radio functions …”; para. [0130] “… The control instruction determined at act 745 may comprise an instruction to retrain a learning model for which metrics were monitored at act 720. The instruction to retrain the learning model may comprise a retraining data set, or an index that a user equipment may use to look up a retraining data set in a retraining code book that may have been transmitted from the RAN to the user equipment, for example at act 715 …”);
encoding, for transmission to the base station, a notification message indicating to the base station, one or more conditions and availability of the one more AI based models for use by the UE (Esswie teaches the UE transmitting model management request with active model status/deactivation requests; FIG. 4; para. [0110] “… At act 415, on condition of the periodicity of transmitting an AI/ML learning model management request having expired or an associated reporting condition corresponding to the learning model having been fulfilled (e.g., a monitored metric failing to satisfy a criterion), UE/WTRU 115 may transmit a learning model management request, corresponding to one or more of AI/ML learning models that may be actively facilitating radio functionality at the UE models, based on a configured AI model management request format, indicating a request for deactivating one or more of active AI models …”);
decoding, from the base station, an activation instruction (Esswie teaches the UE receiving model deactivation/activation control instructions; FIG. 4; para. [0012] “… The control instruction may comprise an instruction to perform an operation to deactivate use of the first radio function learning model, wherein the control instruction comprises an instruction to activate a second radio function learning model, of the different radio function learning models, to implement the radio function …”; para. [0111] “… At act 420, RAN node 105 may transmit a model deactivation request, associated with one or more of the indicated model identifiers of one or more learning models operating on UE 115. A model deactivation request may instruct UE 115 to deactivate one or more learning models that are currently facilitating radio functions such that the radio functions revert to operation according to a previous learning model configuration, a default learning model configuration, or a default deterministic radio function model …”);
activating the one more AI based models for predicting radio link failure (RLF) based on the activation instruction (Esswie teaches the UE implementing control instructions to activate/deactivate/retrain models, while Dalmiya teaches ML models predicting RLF as discussed above; FIG. 7; para. [0128] “… At act 755, the user equipment may implement the control instruction, which, as described above, may comprise doing nothing. Or the control instruction may comprise an instruction for the user equipment to deactivate one or more learning models corresponding to the metrics monitored at act 720. The control instruction may comprise instructing the user equipment to revert to performing a radio function under the operation of, or facilitated by, a default learning model …”; para. [0130] “… The control instruction determined at act 745 may comprise an instruction to retrain a learning model for which metrics were monitored at act 720 …”);
Esswie and Dalmiya are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI radio function model management techniques of Esswie with the system of Dalmiya to improve the performance of the AI/ML models (Esswie, para. [0046]).
Dalmiya-Esswie does not explicitly teach, but Lin teaches predicting the radio link quality/failure using the one or more AI based models based on predicting a block error rate (BLER) of one or more reference signals (Lin teaches a neural network predicting the radio link quality or when a radio link is likely to fail based on predicting out-of-sync BLER using RLM-RS; FIG. 1, FIG. 2; para. [0071] “… one or more reference signals are one or more inputs to neural network 102 and a predicted quality of one or more wireless signals are one or more outputs of neural network 102 …”; para. [0075] “… FIG. 2 illustrates an example 200 of radio link monitoring and predicted radio link state. In at least one embodiment, radio link monitor 103 of UE 101 monitors (e.g., receives, analyzes) one or more reference signals 20la-201n (e.g., a radio link monitoring reference signal (RLM-RS) resource). In at least one embodiment, RLM-RS resources can be synchronization signal blocks (SSBs), channel state information reference signals (CSI-RSs), or a mix of SSBs and CSI-RSs …”; para. [0079] “… neural network 102 predicting that there will be consecutive out-of-sync 204-206 at future time instants and further predicts that afterwards there will not be consecutive in-sync 211-213 within the duration of timer 207, UE 101 may take one or more of the following actions: UE 101 notifies its serving base station 102 about the UE's prediction that the UE's radio link would fail; UE 101 notifies its serving base station 102 about the UE's prediction that the UE's radio link would fail with an associated probability, which indicates how likely the radio link would fail; UE 101 notifies its serving base station 102 about the UE's confidence level of the UE's prediction that the UE's radio link would fail and/or the associated probability, which indicates how likely the radio link would fail; UE 101 sends to its serving base station 102 a measurement report including measurement results of reference signals of serving and neighboring cells …”; para. [0080] “… neural network 102 predict that there will be a number of consecutive out-of-sync events for a downlink radio link at a number of consecutive future time instants when the neural network predicts that the radio link quality is worse than threshold (e.g., Qout) for all resources in the set of resources for radio link prediction at each of the corresponding consecutive future time instants. In at least one embodiment, a threshold is defined as a level at which a downlink radio link cannot be reliably received and shall correspond to out-of-sync block error rate (BLERout). In at least one embodiment, a threshold is derived based on a hypothetical physical downlink control channel (PDCCH) transmission parameters for out-of-sync evaluation associated with corresponding type of RLM-RS, e.g., value of BLERout is 10% …”).
Lin and Dalmiya-Esswie are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link quality prediction techniques of Lin with the system of Dalmiya-Esswie to improve the radio link monitoring (Lin, para. [0002]).
For Claim 2, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising (Examiner notes that the claim has a list of alternatives, and therefore only requires addressing one of the options to teach the claim as a whole):
collecting data at the UE for training the one or more AI based models; or
training the one or more AI based models using data collected at the UE; or
monitoring performance of the one or more AI based models activated at the UE for predicting the RLF (Esswie teaches the UE monitoring model parameter metrics (i.e. performance monitoring) for radio function models, while Dalmiya teaches ML models predicting RLF; Esswie, FIG. 7; para. [0123] “… At act 720, the user equipment monitors metrics corresponding to learning model parameters. The parameters for which metrics are monitored by the user equipment at act 720 may comprise learning model parameters such as statistical parameters as described in reference to Table 1 …”; para. [0124] “… The user equipment may determine, based on metrics monitored at act 720, whether the metrics monitored at act 720 satisfy a learning model performance metric criterion …”); or
monitoring performance of the one or more AI based models based on a prediction confidence level, a prediction accuracy, BLER measurements, a system performance metric, or a combination thereof.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI radio function model management techniques of Esswie with the system of Dalmiya to improve the performance of the AI/ML models (Esswie, para. [0046]).
For Claim 5, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising deactivating or switching the one or more AI based models based on the performance monitoring (Esswie teaches network instructed deactivation/switching via control instruction based on monitored metrics; FIG. 7; [0012] “… The control instruction may comprise an instruction to perform an operation to deactivate use of the first radio function learning model, wherein the control instruction comprises an instruction to activate a second radio function learning model, of the different radio function learning models, to implement the radio function …”; para. [0128] “… At act 755, the user equipment may implement the control instruction, which, as described above, may comprise doing nothing. Or the control instruction may comprise an instruction for the user equipment to deactivate one or more learning models corresponding to the metrics monitored at act 720. The control instruction may comprise instructing the user equipment to revert to performing a radio function under the operation of, or facilitated by, a default learning model …”).
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI radio function model management techniques of Esswie with the system of Dalmiya to improve the performance of the AI/ML models (Esswie, para. [0046]).
For Claim 8, Dalmiya-Esswie-Lin teaches the method of claim 1, wherein the notification message indicates those of the one or more AI based models that are available for use at the UE and corresponding model applicability conditions (Esswie teaches the UE transmitting model management request with active model status/deactivation requests; FIG. 4; para. [0110] “… At act 415, on condition of the periodicity of transmitting an AI/ML learning model management request having expired or an associated reporting condition corresponding to the learning model having been fulfilled (e.g., a monitored metric failing to satisfy a criterion), UE/WTRU 115 may transmit a learning model management request, corresponding to one or more of AI/ML learning models that may be actively facilitating radio functionality at the UE models, based on a configured AI model management request format, indicating a request for deactivating one or more of active AI models …”).
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI radio function model management techniques of Esswie with the system of Dalmiya to improve the performance of the AI/ML models (Esswie, para. [0046]).
For Claim 9, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising decoding, from the base station, the activation instruction via downlink control information, medium access control-control element, or radio resource control signaling (Dalmiya teaches the base station configuring the UE via DCI, RRC, MAC-CE or SIB; FIG. 1; para. [0043] “… the base station 110 may configure a UE 120 via downlink control information (DCI), radio resource control (RRC) signaling, a media access control-control element (MAC-CE) or via system information ( e.g., a system information block (SIB) …”).
For Claim 10, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising (Examiner notes that the claim has a list of alternatives, and therefore only requires addressing one of the options to teach the claim as a whole):
predicting the BLER for radio link monitoring reference signals (RLM-RS) for radio link monitoring (Lin teaches Lin teaches predicting out-of-sync BLER using RLM-RS for radio link monitoring; FIG. 1, FIG. 2; para. [0075] “… FIG. 2 illustrates an example 200 of radio link monitoring and predicted radio link state. In at least one embodiment, radio link monitor 103 of UE 101 monitors (e.g., receives, analyzes) one or more reference signals 201a-201n (e.g., a radio link monitoring reference signal (RLM-RS) resource). In at least one embodiment, RLM-RS resources can be synchronization signal blocks (SSBs), channel state information reference signals (CSI-RSs), or a mix of SSBs and CSI-RSs …”; para. [0080] “… neural network 102 predict that there will be a number of consecutive out-of-sync events for a downlink radio link at a number of consecutive future time instants when the neural network predicts that the radio link quality is worse than threshold (e.g., Qout) for all resources in the set of resources for radio link prediction at each of the corresponding consecutive future time instants. In at least one embodiment, a threshold is defined as a level at which a downlink radio link cannot be reliably received and shall correspond to out-of-sync block error rate (BLERout). In at least one embodiment, a threshold is derived based on a hypothetical physical downlink control channel (PDCCH) transmission parameters for out-of-sync evaluation associated with corresponding type of RLM-RS, e.g., value of BLERout is 10% …”) or a transparent control information (TCI) state of an activated physical downlink control channel (PDCCH) based on a plurality of previous BLER measurements; or
predicting the BLER based on one or more previous BLER measurements of one or more different reference signals; or
performing BLER prediction of the RLF continuously, periodically, or based on an event trigger configured by a network; or
wherein one or more of the plurality of previous BLER measurements and predicted BLER measurements are configured by the base station; or
predicting the RLF periodically based on a periodicity configuration received from a network.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link quality prediction techniques of Lin with the system of Dalmiya-Esswie to improve the radio link monitoring (Lin, para. [0002]).
For Claim 14, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising generating a confidence level associated with each predicted BLER (Lin teaches generating a confidence level with the radio link quality or when a radio link is likely to fail based on predicting out-of-sync BLER using RLM-RS; FIG. 1, FIG. 2; para. [0079] “… neural network 102 predicting that there will be consecutive out-of-sync 204-206 at future time instants and further predicts that afterwards there will not be consecutive in-sync 211-213 within the duration of timer 207, UE 101 may take one or more of the following actions: … UE 101 notifies its serving base station 102 about the UE's confidence level of the UE's prediction that the UE's radio link would fail and/or the associated probability, which indicates how likely the radio link would fail …”; para. [0080] “… neural network 102 predict that there will be a number of consecutive out-of-sync events for a downlink radio link at a number of consecutive future time instants when the neural network predicts that the radio link quality is worse than threshold (e.g., Qout) for all resources in the set of resources for radio link prediction at each of the corresponding consecutive future time instants. In at least one embodiment, a threshold is defined as a level at which a downlink radio link cannot be reliably received and shall correspond to out-of-sync block error rate (BLERout). In at least one embodiment, a threshold is derived based on a hypothetical physical downlink control channel (PDCCH) transmission parameters for out-of-sync evaluation associated with corresponding type of RLM-RS, e.g., value of BLERout is 10% …”).
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link quality prediction techniques of Lin with the system of Dalmiya-Esswie to improve the radio link monitoring (Lin, para. [0002]).
For Claim 16, Dalmiya-Esswie-Lin teaches the method of claim 10, further comprising identifying an event trigger based upon expiration of a timer or a number of out-of-sync (OOS) indications received from a lower layer of the UE (Lin teaches predicting BLER based on a number of out-of-sync events for a downlink radio link; para. [0060] “… in radio link failure (RLF) procedures, reception of consecutive out-of-sync indications (e.g., signals or packets cannot be decoded properly or timing of said message is incorrect) from lower layers informs a UE that there is a problem with a downlink radio link …”; para. [0080] “… neural network 102 predict that there will be a number of consecutive out-of-sync events for a downlink radio link at a number of consecutive future time instants when the neural network predicts that the radio link quality is worse than threshold (e.g., Qout) for all resources in the set of resources for radio link prediction at each of the corresponding consecutive future time instants. In at least one embodiment, a threshold is defined as a level at which a downlink radio link cannot be reliably received and shall correspond to out-of-sync block error rate (BLERout). In at least one embodiment, a threshold is derived based on a hypothetical physical downlink control channel (PDCCH) transmission parameters for out-of-sync evaluation associated with corresponding type of RLM-RS, e.g., value of BLERout is 10% …”).
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link quality prediction techniques of Lin with the system of Dalmiya-Esswie to improve the radio link monitoring (Lin, para. [0002]).
For Claim 23, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising encoding, the RLF prediction report, for transmission to the base station to enable the base station to determine whether to send a handover command to back the UE based on the RLF prediction indicating a risk of radio link failure (Dalmiya teaches the UE signaling RLF prediction to the base station and the base station responding with handover command based on received RRC message; FIG. 8; para. [0027] “… Based on the prediction, the UE may signal the potential RLF condition to the network …”; para. [0102] “… At time t4, a base station of the MCG declares radio link failure for the SCG in response to receiving a radio resource control (RRC) message from the UE … the MCG base station may decide to handover the SCG communications to a new SCG base station …”).
For Claim 34, Dalmiya teaches an apparatus of a base station comprising: one or more processors, coupled to a memory (Dalmiya, FIG. 3; para. [0054] “… The SOC 300 may be included in the base station 110 or UE 120 … Instructions executed at the CPU 302 may be loaded from a program memory associated with the CPU 302 or may be loaded from a memory block 318 …”; ), configured to: …; …; …; …;
The UE predicting the RLF using the one or more AI based models based on … a block error rate (BLER) of one or more reference signals (Dalmiya teaches ML model predicting RLF using BLER (PDSCH initial/residual) and plurality of radio-link inputs; para. [0027] “… According to aspects of the present disclosure, a UE predicts RLF before a secondary cell group RLF condition occurs, for example, as specified by the standards. The UE may predict with any type of machine learning technique. Based on the prediction, the UE may signal the potential RLF condition to the network …”; para. [0028] “… a machine learning model receives input variables. Based on the input variables, the machine learning model predicts whether a secondary cell group RLF will occur at a time in the future. The machine learning model generates an alert based on the prediction …”; para. [0029] “… For example, the input variables of the machine learning model may include a downlink block error rate (BLER) for the last D time slots, where D is a moving window. The input variables of the machine learning model may also include a current packet data convergence protocol (PDCP) number of holes in the receive window. Another input variable of the machine learning model may be a number of PDCP reordering timer expiration events that have occurred in the last D time slots … the input variables of the machine learning model may include a mean delay of radio link control (RLC) acknowledgements to new packet transmissions, in the last D time slots …”; the input variables of the ML model for predicting also includes downlink control information (DCI) miss rate, signal statistics, radio link management (RLM) timer along with an InSync count and an OutOfSync count, etc., as recited in para. [0086]-[0100]) or based on classifying a risk level of the RLF based on a plurality of inputs; and
decode, an RLF prediction report, received from the UE, based on the prediction (Dalmiya teaches the UE transmitting RLF prediction report to the base station; Examiner notes that Dalmiya teaches the claimed “decoding” functionally, it teaches the underlying transmit/receive signaling operations corresponding to the claimed base station-side decoding step since the base station must process the received signaling to select modulation and coding schemes for UE; FIG. 1; para. [0027] “… Based on the prediction, the UE may signal the potential RLF condition to the network …”; para. [0047] “… At the base station 110, a transmit processor 220 may receive data from a data source 212 for one or more UEs, select one or more modulation and coding schemes (MCS) for each UE based at least in part on channel quality indicators (CQis) received from the UE …”; para. [0127] “… Aspect 20: … further comprising transmitting, to a base station, an indication of a potential RLF based upon the predicting of the RLF …”).
Dalmiya does not explicitly teach, but Esswie teaches decode a user equipment (UE) capability report received from a UE (Esswie teaches a RAN node receiving capability information to a UE; Examiner notes that Esswie teaches the claimed “encoding/decoding” sequence functionally, it teaches the underlying transmit/receive signaling operations corresponding to the claimed RAN-side encoding and decoding steps since the RAN node must process the received signaling to implement the specified model-management operation; FIG. 4; para. [0108] “… Turning now to FIG. 4, the figure illustrates a timing diagram of an example method to configure a user equipment 115 with a learning model metric reporting configuration from a network node/RAN 105. At act 405, UE or wireless transmit and receive unit (WTRU) 115 (sometimes referred to below as merely UE 115) transmits capability information that may comprise an indication of radio function learning model information, which may comprise learning model information corresponding to one or more radio function learning models of the user equipment, to serving cell RAN 105. The capability information may comprise indications for one or more radio functions that may be implemented by, operated by, performed by, or otherwise facilitated by, UE 115. The capability information may comprise information that indicates types of AI/ML learning models ( e.g., supervised, unsupervised, reinforcement learning, and the like) that may correspond to, support, or facilitate, the radio functions …”);
encode, for transmission to the UE, configuration information, for training one or more artificial intelligence (AI) based models for predicting radio link failure (RLF) (Esswie teaches the RAN node transmitting AI/ML learning model management configurations including instruction to train ML models to facilitate radio functions, while Dalmiya teaches ML models predicting RLF as discussed above; FIG. 4, FIG. 7; para. [0108] “… At act 410, RAN 105 transmits, and UE/WTRU 115, receives one or more AI/ML learning model management configurations from RAN 105. A learning model management configuration may comprise format information corresponding to an AI/ML model management request that may be made by UE 115 …”; para. [0109] “… The format information may comprise learning-model-specific performance metrics to report according to a model identifier, or reporting conditions, of a model management request, including a reporting periodicity, or a learning model degradation criterion, which may be referred to as a model performance metric criterion, for example a threshold …”; para. [0123] “… Turning now to FIG. 7, the figure illustrates a flow diagram of an embodiment method 700 to manage one or more learning models that may facilitate one or more corresponding radio functions …”; para. [0130] “… The control instruction determined at act 745 may comprise an instruction to retrain a learning model for which metrics were monitored at act 720. The instruction to retrain the learning model may comprise a retraining data set, or an index that a user equipment may use to look up a retraining data set in a retraining code book that may have been transmitted from the RAN to the user equipment, for example at act 715 …”);
decode a notification message, received from the UE, indicating to the base station one or more conditions and availability of the one or more AI based models for use by the UE (Esswie teaches the RAN node receiving model management request with active model status/deactivation requests from the UE; FIG. 4; para. [0110] “… At act 415, on condition of the periodicity of transmitting an AI/ML learning model management request having expired or an associated reporting condition corresponding to the learning model having been fulfilled (e.g., a monitored metric failing to satisfy a criterion), UE/WTRU 115 may transmit a learning model management request, corresponding to one or more of AI/ML learning models that may be actively facilitating radio functionality at the UE models, based on a configured AI model management request format, indicating a request for deactivating one or more of active AI models …”);
encode, for transmission to the UE, an activation instruction to indicated to the UE to activate the one or more AI based models for predicting radio link failure (RLF) based on the activation instruction (Esswie teaches the RAN node transmitting model deactivation/activation control instructions for the UE to implement control instructions to activate/deactivate/retrain models, while Dalmiya teaches ML models predicting RLF as discussed above; FIG. 4, FIG. 7; para. [0012] “… The control instruction may comprise an instruction to perform an operation to deactivate use of the first radio function learning model, wherein the control instruction comprises an instruction to activate a second radio function learning model, of the different radio function learning models, to implement the radio function …”; para. [0111] “… At act 420, RAN node 105 may transmit a model deactivation request, associated with one or more of the indicated model identifiers of one or more learning models operating on UE 115. A model deactivation request may instruct UE 115 to deactivate one or more learning models that are currently facilitating radio functions such that the radio functions revert to operation according to a previous learning model configuration, a default learning model configuration, or a default deterministic radio function model …”; para. [0128] “… At act 755, the user equipment may implement the control instruction, which, as described above, may comprise doing nothing. Or the control instruction may comprise an instruction for the user equipment to deactivate one or more learning models corresponding to the metrics monitored at act 720. The control instruction may comprise instructing the user equipment to revert to performing a radio function under the operation of, or facilitated by, a default learning model …”; para. [0130] “… The control instruction determined at act 745 may comprise an instruction to retrain a learning model for which metrics were monitored at act 720 …”) and ….
Esswie and Dalmiya are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI radio function model management techniques of Esswie with the system of Dalmiya to improve the performance of the AI/ML models (Esswie, para. [0046]).
Dalmiya-Esswie does not explicitly teach, but Lin teaches predicting the radio link quality/failure using the one or more AI based models based on predicting a block error rate (BLER) of one or more reference signals (Lin teaches a neural network predicting the radio link quality or when a radio link is likely to fail based on predicting out-of-sync BLER using RLM-RS; FIG. 1, FIG. 2; para. [0071] “… one or more reference signals are one or more inputs to neural network 102 and a predicted quality of one or more wireless signals are one or more outputs of neural network 102 …”; para. [0075] “… FIG. 2 illustrates an example 200 of radio link monitoring and predicted radio link state. In at least one embodiment, radio link monitor 103 of UE 101 monitors (e.g., receives, analyzes) one or more reference signals 20la-201n (e.g., a radio link monitoring reference signal (RLM-RS) resource). In at least one embodiment, RLM-RS resources can be synchronization signal blocks (SSBs), channel state information reference signals (CSI-RSs), or a mix of SSBs and CSI-RSs …”; para. [0079] “… neural network 102 predicting that there will be consecutive out-of-sync 204-206 at future time instants and further predicts that afterwards there will not be consecutive in-sync 211-213 within the duration of timer 207, UE 101 may take one or more of the following actions: UE 101 notifies its serving base station 102 about the UE's prediction that the UE's radio link would fail; UE 101 notifies its serving base station 102 about the UE's prediction that the UE's radio link would fail with an associated probability, which indicates how likely the radio link would fail; UE 101 notifies its serving base station 102 about the UE's confidence level of the UE's prediction that the UE's radio link would fail and/or the associated probability, which indicates how likely the radio link would fail; UE 101 sends to its serving base station 102 a measurement report including measurement results of reference signals of serving and neighboring cells …”; para. [0080] “… neural network 102 predict that there will be a number of consecutive out-of-sync events for a downlink radio link at a number of consecutive future time instants when the neural network predicts that the radio link quality is worse than threshold (e.g., Qout) for all resources in the set of resources for radio link prediction at each of the corresponding consecutive future time instants. In at least one embodiment, a threshold is defined as a level at which a downlink radio link cannot be reliably received and shall correspond to out-of-sync block error rate (BLERout). In at least one embodiment, a threshold is derived based on a hypothetical physical downlink control channel (PDCCH) transmission parameters for out-of-sync evaluation associated with corresponding type of RLM-RS, e.g., value of BLERout is 10% …”).
Lin and Dalmiya-Esswie are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link quality prediction techniques of Lin with the system of Dalmiya-Esswie to improve the radio link monitoring (Lin, para. [0002]).
Claim Rejections - 35 USC § 103
Claims 6-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20230145079 A1 (hereinafter Dalmiya, included in 11/25/2024 IDS), in view of US 20240187877 A1 (hereinafter Esswie), in view of US 20250062843 A1 (hereinafter Lin), in view of US 20220400373 A1 (hereinafter Zhu, included in 11/25/2024 IDS), in view of US 20230189085 A1 (hereinafter Park, included in 11/25/2024 IDS), and in further view of US 20220053477 A1 (hereinafter Yao).
For Claim 6, Dalmiya-Esswie-Lin teaches the method of claim 1 and support for temporal prediction of block error rate (BLER) of a reference signal for radio link monitoring (Lin teaches a neural network predicting the radio link quality or when a radio link is likely to fail based on predicting out-of-sync BLER using RLM-RS; FIG. 1, FIG. 2; para. [0071], [0075], [0079], [0080]).
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link quality prediction techniques of Lin with the system of Dalmiya-Esswie to improve the radio link monitoring (Lin, para. [0002]).
Dalmiya-Esswie-Lin does not explicitly teach, but Zhu teaches wherein the UE capability report indicates support for… for radio link monitoring (RLM) (Zhu, para. [0067] “… the radio capability of the UE may indicate a capability of the UE to perform one or more wireless communications management procedures, which may be ML-based. For example, the radio capability of the UE may indicate … a capability to perform an (ML-based) radio link monitoring (RLM) procedure, a capability to perform an (ML-based) channel state information (CSI) measurement procedure …”), …
Zhu and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link monitoring techniques of Zhu with the system of Dalmiya-Esswie-Lin to facilitate managing and optimizing the use of finite wireless channel resources in complex and dynamic environments (Lin, para. [0002]).
Dalmiya-Esswie-Lin-Zhu does not explicitly teach, but Park teaches a UE supporting a maximum number of history samples and predicted samples for BLER prediction, a maximum number of predicted samples (Park teaches signal strength prediction configuration with input/output window sizes that correspond to the history/predicted samples; FIG. 6; para. [0085] “… the terminal may predict a received signal strength for a time after a specific time based on the measured received signal strength …”; para. [0089] “… the base station may configure the signal strength measurement prediction as needed for a terminal capable of signal strength measurement prediction according to capability of the terminal …”; para. [0106] “… the prediction configuration information may include one or more [inputWindowSize, outputWindowSize] pairs. For example, a measurement period may be 40 msec. The terminal may perform separate predictions for a time (T1+ TTT) and a time (Tl+MTS) at a time T1. In addition, the terminal may make the prediction using a measurement result from 1 sec before the time T1 to the time T1. A trigger time (TTT) may be, for example, 160 msec. A minimum time-of-stay (MTS) may be 1 sec, for example …”; para. [0107] “… the prediction configuration information may include one or more [inputWindowSize, outputWindowSize] pairs. For example, a measurement period may be 40 msec. The terminal may perform separate predictions for a time (T1+ TTT) and a time (T1+MTS) at a time T1. In addition, the terminal may make the prediction using a measurement result from 1 sec before the time Tl to the time Tl. A trigger time (TTT) may be, for example, 160 msec. A minimum time-of-stay (MTS) may be 1 sec, for example …”), and …
Park and Dalmiya-Esswie-Lin-Zhu are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin-Zhu to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
Dalmiya-Esswie-Lin-Zhu-Park does not explicitly teach, but Yao teaches a UE supporting a maximum number of parallel predictions (Yao teaches the UE reporting maximum resource capabilities to support the concurrent CSI-RS processing requests; FIG. 7; para. [0146] “… From the perspective of the network, requests made to the UE should respect the maximum number of resources for each codebook type. In addition, the network can ensure that any/all CSI requests made to the UE use less than the total number of CSI resources for all codebook types as reported by the UE in 552. In other words, as long as the {max# ports per CSI-RS, max# CSI-RS, total# ports) across all activated concurrent CSI-RS processing is below the total UE reported capability (summed across all codebook types), then the UE will have the resources to support the multiple concurrent CSI requests …”).
Yao and Dalmiya-Esswie-Lin-Zhu-Park are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the UE capability reporting techniques of Yao with the system of Dalmiya-Esswie-Lin-Zhu-Park to improve the communication between the UE and the base station (Yao, para. [0005]).
For Claim 7, Dalmiya-Esswie-Lin teaches the method of claim 1 and BLER prediction.
Dalmiya-Esswie-Lin does not explicitly teach, but Zhu teaches wherein the configuration information comprises an indication of each type of the one more AI based models (Zhu, para. [0004] “… ML configuration information indicating at least one neural network function (NNF) and at least one ML model corresponding to the at least one NNF …”; para. [0090] “… in the ML configuration information, the at least one NNF is indicated by an NNF identifier (ID) and the at least one ML model is indicated by an ML model ID …”), …
Zhu and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the AI based radio link monitoring techniques of Zhu with the system of Dalmiya-Esswie-Lin to facilitate managing and optimizing the use of finite wireless channel resources in complex and dynamic environments (Lin, para. [0002]).
Dalmiya-Esswie-Lin-Zhu does not explicitly teach, but Park teaches the configuration information comprises a prediction window length for BLER prediction (Park teaches signal strength prediction configuration with input/output window sizes that correspond to prediction window length; FIG. 6; para. [0085] “… the terminal may predict a received signal strength for a time after a specific time based on the measured received signal strength …”; para. [0089] “… the base station may configure the signal strength measurement prediction as needed for a terminal capable of signal strength measurement prediction according to capability of the terminal …”; para. [0106] “… the prediction configuration information may include one or more [inputWindowSize, outputWindowSize] pairs. For example, a measurement period may be 40 msec. The terminal may perform separate predictions for a time (T1+ TTT) and a time (Tl+MTS) at a time T1. In addition, the terminal may make the prediction using a measurement result from 1 sec before the time T1 to the time T1. A trigger time (TTT) may be, for example, 160 msec. A minimum time-of-stay (MTS) may be 1 sec, for example …”; para. [0107] “… the prediction configuration information may include one or more [inputWindowSize, outputWindowSize] pairs. For example, a measurement period may be 40 msec. The terminal may perform separate predictions for a time (T1+ TTT) and a time (T1+MTS) at a time T1. In addition, the terminal may make the prediction using a measurement result from 1 sec before the time Tl to the time Tl. A trigger time (TTT) may be, for example, 160 msec. A minimum time-of-stay (MTS) may be 1 sec, for example …”), and …
Park and Dalmiya-Esswie-Lin-Zhu are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin-Zhu to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
Dalmiya-Esswie-Lin-Zhu-Park does not explicitly teach, but Yao teaches the configuration information comprises a number of parallel predictions (Yao teaches the configuration specifying the UE maximum resource capabilities to support the concurrent CSI-RS processing requests; FIG. 7; para. [0146] “… From the perspective of the network, requests made to the UE should respect the maximum number of resources for each codebook type. In addition, the network can ensure that any/all CSI requests made to the UE use less than the total number of CSI resources for all codebook types as reported by the UE in 552. In other words, as long as the {max# ports per CSI-RS, max# CSI-RS, total# ports) across all activated concurrent CSI-RS processing is below the total UE reported capability (summed across all codebook types), then the UE will have the resources to support the multiple concurrent CSI requests …”).
Yao and Dalmiya-Esswie-Lin-Zhu-Park are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the UE capability reporting techniques of Yao with the system of Dalmiya-Esswie-Lin-Zhu-Park to improve the communication between the UE and the base station (Yao, para. [0005]).
Claim Rejections - 35 USC § 103
Claim 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20230145079 A1 (hereinafter Dalmiya, included in 11/25/2024 IDS), in view of US 20240187877 A1 (hereinafter Esswie), in view of US 20250062843 A1 (hereinafter Lin), in view of US 20220311499 A1 (hereinafter Zhang), and in further view of US 20190319682 A1 (hereinafter Zhang2).
For Claim 13, Dalmiya-Esswie-Lin teaches the method of claim 1. Dalmiya-Esswie-Lin does not explicitly teach, but Zhang teaches further comprising decoding assistance information, received from the base station, comprising a … beam correlation between first and second reference signals (Zhang teaches a RAN node transmitting correlation messages to a UE, the correlation messages comprising beam spatial correlation between two reference signals; FIG. 1; para. [0024] “… Systems as described in relation to FIG. 1 may be able to be improved (e.g., perform a beam search in less time, resulting in lower latency beam searching) when information about a spatial correlation of two or more searched-for signals is provided by the gNB to the UE …”; para. [0025] “… Signals that are spatially correlated may be understood to be signals that are transmitted by a gNB such that a projected measurement (e.g., a Reference Signal Receive Power (RSRP) measurement or a Signal-to-Interference Plus Noise Ratio (SINR) measurement) difference of a reception at an Rx beam of the UE of a first correlated signal on a first Tx beam and a reception at the same Rx beam of the UE of a second correlated signal on a second Tx beam is less than a threshold. For example, an SSB transmitted on a first beam may be spatially correlated with a second SSB, a CSI-RS, or another signal that is transmitted on a second beam if a change in a signal measurement (e.g., RSRP or SINR) between the two signals at the same Rx beam of the UE is not projected to exceed a threshold … A gNB (or other entity) that is determining spatial correlations between signals and transmitting them accordingly may be said to be transmitting signals according to a spatial correlation configuration …”).
Zhang and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the communicating beam correlation information techniques of Zhang with the system of Dalmiya-Esswie-Lin to facilitate controlling signaling for beam searching latency reduction (Zhang, para. [0001]).
Dalmiya-Esswie-Lin-Zhang does not explicitly teach, but Zhang2 teaches providing a long-term beam correlation (Zhang2 teaches determining beam correlation using long-term reference signal; FIG. 5; para. [0046] “… At step 3 of FIG. 5, the UE 132 receives the long-term reference signal transmitted via each of a plurality of transmit beams (transmitted at step 1). The UE 132 measures the power (e.g., RSRP) of the reference signal received via each transmit beam. UE 132 determines the beam index (e.g., i) for the m transmit beams having the greatest/highest RSRP … Thus, the UE 132 reports to BS 134 the power and indices of the m highest power beams …”; para. [0047] “… At step 4 of FIG. 5, the BS 134 transmits a short term reference signal (e.g., CSI-RS) via n transmit beams. The short term reference signal may be a reference signal with a relatively short period (e.g., a shorter period than the long-term reference signal transmitted in step 1) … the short term reference signal may be transmitted to the UE 132 to allow the UE 132 to perform channel or CSI (channel state information) measurement, such as channel coefficients (h), rank indication (RI), channel quality indication (CQI) …”; para. [0048] “… At step 5 of FIG. 5, the BS 134 selects or determines, e.g., based on a reported RSRP value and a beam index for each of the m BS transmit beams, a first number (n1) of diagonal correlation (auto-correlation) coefficients of a correlation matrix and a second number (n2) of nondiagonal correlation ( cross-correlation) coefficients of the correlation matrix …”).
Zhang2 and Dalmiya-Esswie-Lin-Zhang are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the long-term reference signal to determine beam correlation techniques of Zhang2 with the system of Dalmiya-Esswie-Lin-Zhang to provide the UE with a more stable correlation relationship for selecting receive beams and reduce measurement/search overhead.
Claim Rejections - 35 USC § 103
Claims 17, 19, 21-22, 24, 26 and 30 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 20230145079 A1 (hereinafter Dalmiya, included in 11/25/2024 IDS), in view of US 20240187877 A1 (hereinafter Esswie), in view of US 20250062843 A1 (hereinafter Lin), and in further view of US 20230189085 A1 (hereinafter Park, included in 11/25/2024 IDS).
For Claim 17, Dalmiya-Esswie-Lin teaches the method of claim 1. Dalmiya-Esswie-Lin does not explicitly teach, but Park teaches further comprising periodically reporting the RLF prediction to a primary cell via radio resource control signaling (Park teaches periodic RLF prediction reporting to serving base station (i.e. primary cell) via RRC; FIG. 12; para. [0124] “… the terminal may periodically report the measurement prediction result to the base station …”; para. [0161] “… The terminal may perform RLF prediction according to the received RLF prediction information. Upon receiving the RLF prediction information, the terminal may transmit an RRC reconfiguration complete message to the base station in response (S1202) …”; para. [0163] “… Thereafter, when the terminal may declare the RLF according to the configured RLF prediction information, the terminal may transmit an RLF prediction report message including an RLF prediction result to the base station (S1203) …”) wherein the RLF prediction report indicates a BLER prediction error between predicted BLER measurements and actual BLER measurements (Park teaches measurement prediction model feedback reporting with measurement/prediction result IEs and loss function (i.e. prediction error); FIG. 9, FIG. 12; para. [0130] “… Meanwhile, the measurement prediction model feedback report information may include a received signal strength measurement result at a measurement time and a received signal strength prediction result for a prediction time …”; para. [0131] “… Meanwhile, the condition for transmitting may be a condition for periodically transmitting a measurement prediction model feedback signal or the measurement prediction model feedback information availability indicator …”; para. [0132] “… Alternatively, the base station may configure the measurement prediction model feedback configuration information as a measurement prediction error configuration IE (i.e., measPreErrorConfig IE). Here, the measurement prediction error configuration IE may include one of machine learning loss functions …”; para. [0133] “… the loss function may be a mean absolute error (MAE), a mean square error (MSE), a root mean square error (RMSE), or the like …”; para. [0163] “… the RLF prediction report message may additionally include a measurement result IE (i.e., measResults IE) that is a signal strength measurement result, and may further include a measurement prediction result IE (i.e., measPredictionResults IE) that is a signal strength measurement prediction result …”).
Park and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
For Claim 19, Dalmiya-Esswie-Lin teaches the method of claim 1. Dalmiya-Esswie-Lin does not explicitly teach, but Park teaches further comprising (Examiner notes that the claim has a list of alternatives, and therefore only requires addressing one of the options to teach the claim as a whole):
encoding, the RLF prediction report, for transmission to a secondary cell via a medium access control control element (MAC-CE) or radio resource control (RRC) signaling when a first event is triggered, wherein the first event comprises a reference signal measurement exceeding a predetermined threshold or
encoding, the RLF prediction report, for transmission to a secondary cell via a MAC-CE or RRC signaling when a second event is triggered, wherein the second event comprises expiration of a timer (Park teaches transmitting measurement prediction report to a base station via RRC triggered by a timer; FIG. 6; para. [0084] “… The terminal may perform signal strength measurement prediction according to the signal strength measurement prediction configuration information of the measurement prediction configuration IE. Then, the terminal may transmit an RRC reconfiguration complete message to the base station in response (S602) …”; para. [0086] “… Then, the terminal may periodically report, to the base station, the signal strength measurement prediction result including the predicted received signal strength of the neighboring base station through a measurement prediction report message according to measurement prediction report configuration (S603) …”; para. [0109] “… the prediction configuration information may include one or more sets of [ event, duration, continuous, report_timestep] for the terminal to report a measurement prediction result to the base station as needed … 'Report_timestep' may be set as a timestep or a unit time for reporting the prediction results …”).
Park and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
For Claim 21, Dalmiya-Esswie-Lin teaches the method of claim 19. Dalmiya-Esswie-Lin does not explicitly teach, but Park teaches further comprising transmitting a scheduling request to the base station when the second event is triggered (Park teaches the UE transmitting availability indicators to the base station so as to requesting scheduling work based on a timer; FIG. 9, FIG. 13; para. [0135] “… when a specific event occurs, the terminal may transmit a UE information response message including a measurement prediction model feedback information availability indicator to the base station according to the measurement prediction model feedback configuration information (S903) …”; para. [0167] “… the terminal may transmit an RRC re-establishment complete message including an RLF prediction information availability (i.e., rlfPredictioninfoAvailable) indicator to the second base station to inform presence of an RLF prediction report to the second base station (S1303) …”).
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
For Claim 22, Dalmiya-Esswie-Lin teaches the method of claim 1. Dalmiya-Esswie-Lin does not explicitly teach, but Park teaches further comprising periodically reporting the RLF prediction report to a secondary cell via medium access control control element (MAC-CE) or radio resource control (RRC) signaling when a second event is triggered, wherein the second event comprises expiry of a timer (Park teaches periodically transmitting measurement prediction report to a base station via RRC triggered by a timer; FIG. 6; para. [0084] “… The terminal may perform signal strength measurement prediction according to the signal strength measurement prediction configuration information of the measurement prediction configuration IE. Then, the terminal may transmit an RRC reconfiguration complete message to the base station in response (S602) …”; para. [0086] “… Then, the terminal may periodically report, to the base station, the signal strength measurement prediction result including the predicted received signal strength of the neighboring base station through a measurement prediction report message according to measurement prediction report configuration (S603) …”; para. [0109] “… the prediction configuration information may include one or more sets of [ event, duration, continuous, report_timestep] for the terminal to report a measurement prediction result to the base station as needed … 'Report_timestep' may be set as a timestep or a unit time for reporting the prediction results …”).
Park and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
For Claim 24,, Dalmiya-Esswie-Lin teaches the method of claim 23. Dalmiya-Esswie-Lin does not explicitly teach, but Park teaches further comprising (Examiner notes that the claim has a list of alternatives, and therefore only requires addressing one of the options to teach the claim as a whole):
decoding, the handover command, received via a secondary cell based on the RLF prediction indicating a radio link quality level below a quality threshold level on a primary cell (Park teaches receiving handover command via RRC reconfiguration based on RLF prediction (i.e. signal strength below threshold); para. [0067] “… the handover command message may be included in a radio resource control (RRC) reconfiguration message transmitted from the serving base station to the terminal …”; para. [0098] “… The serving base station may receive the handover preparation response message from the target base station. The serving base station may transmit a handover command message for instructing the terminal to perform the handover indicated by the handover preparation response message. In this case, when a time required for handover preparation is shorter than the trigger time, the serving base station may transmit the handover command message to the terminal at …”; para. [0160] “… the information for predicting an RLF may be information for declaring an RLF when a prediction result of a received signal strength for a time after a specific time is lower than a specific threshold …”; para. [0163] “… The RLF prediction report message may further include a remaining time until a time at which the RLF is predicted to occur or an absolute time of the time at which the RLF is predicted to occur …”); or
decoding, a handover command, from the base station based on the RLF prediction indicating the radio link quality level is above a quality threshold level.
Park and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
For Claim 26, Dalmiya-Esswie-Lin teaches the method of claim 1, further comprising predicting the RLF using the one or more AI based models with one or more of the plurality of inputs, wherein the plurality of inputs are (Examiner notes that the claim has a list of alternatives, and therefore only requires addressing one of the options to teach the claim as a whole):
a number of random access channel attempts; a number of radio link control re-transmissions; measurements of reference signals configured for radio link monitoring; and an uplink-downlink correspondence metric (Park teaches RLF prediction inputs comprising reference signal measurements (RSRP, RSRQ, or SINR for RLM), historical measurement/prediction results (equations 1-4), terminal mobility (UL-DL correspondence); para. [0085] “… the terminal may measure a received signal strength (e.g., RSRP, RSRQ, or SINR) of a neighboring base station according to the signal strength measurement prediction configuration information …”; para. [0119] “… the terminal may predict a received signal strength after a specific time based on a received signal strength measurement result and a received signal strength prediction result. As shown in Equation 2, the terminal may add a predicted change amount ∆ to a sum of values obtained by multiplying k received signal strength measurement results among received signal strength measurement results until now by the weights wi and values obtained by multiplying a received signal strength prediction result from the current time before the specific time by weights Wj …”; para. [0123] “… the terminal may predict a change amount in consideration of the terminal's movement speed, position information, movement direction, and/or the like …”; para. [0124] “… The terminal may perform prediction of RSRP, RSRQ, and/or SINR measurement to which the L1 filtering is applied according to configuration of the base station …”) or
a number of random access channel attempts; a number of radio link control retransmissions; measurements of reference signals configured for radio link monitoring; a number of consecutive hybrid automatic repeat discontinuous transmission (HARQ DTX) events; and measured reference signal received power of non-radio link monitoring reference signals.
Park and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
For Claim 30, Dalmiya-Esswie-Lin teaches the method of claim 1. Dalmiya-Esswie-Lin does not explicitly teach, but Park teaches further comprising autonomously switching between the one or more AI based models based on a performance threshold (Park teaches autonomous model selection via useModelId and model switching via activation/deactivation messages using performance threshold (error events); Examiner notes that the claim has a list of alternatives, and therefore only requires addressing one of the options to teach the claim as a whole; para. [0105] “… In the measurement prediction configuration IE, 'useModelId' may provide an identifier of a machine learning model to be used for measurement prediction. The terminal may manage a measurement prediction machine learning model by itself … Alternatively, the base station may manage measurement prediction machine learning models. In this case, the base station may indicate information on the machine learning model to be used by transmitting information on the corresponding machine learning model identifier to the terminal …”; para. [0135] “… the terminal may transmit a UE information response message to the base station when an error between a received signal strength measurement result at a specific time and a received signal strength prediction result for a prediction time is equal to or greater than a specific error threshold …”; para. [0137] “… The base station may receive the measurement prediction model feedback report information from the terminal, improve machine learning performance of the measurement prediction model based on the measurement prediction model feedback report information, and update the measurement prediction model of the terminal as needed …”) or a change in reference signals.
Park and Dalmiya-Esswie-Lin are analogous art because they are both related to wireless communication networks.
Before the effective filing date of the claimed invention it would have been obvious to one of ordinary skill in the art to use the managing signal strength prediction configuration techniques of Park with the system of Dalmiya-Esswie-Lin to facilitate seamless communication services and reduce data interruption possibilities (Park, para. [0006]).
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure is listed below, thank you:
i. US 20220338189 A1 (Madadi) teaches that Machine learning (ML) assisted channel state information (CSI) reporting or ML assisted CSI prediction includes receiving CSI reporting configurations that include indications that enable or disable at least one of: ML-assisted CSI prediction and artificial intelligence channel feature information (AI-CFI) reporting. ML model training is performed or trained ML model parameters are received, and CSI reference signals corresponding to at least one of the CSI reporting configurations are received. If ML-assisted CSI prediction is enabled, the CSI reporting configurations further include: a timing offset for future CSI prediction, and ML configurations including indication of an ML model used for the ML-assisted CSI prediction. If AI-CFI reporting is enabled, the CSI reporting configurations further include: a configuration for a report of the AI-CFI, and ML configurations including indication of an ML model used for the ML assisted-CS! feedback determination (Abstract).
ii. US 20230300654 A1 (Silva) teaches a method performed by a UE (103) of a wireless communications network (100). The UE (103) predicts information related to at least one of the following failures: a failure during operation with a serving cell; and a failure accessing a neighbor cell. The UE (103) transmits a message to a network node (101). The message indicates the predicted information (Abstract).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZONGHUA DU whose telephone number is (408)918-7596. The examiner can normally be reached Monday - Friday 8 AM - 5 PM PST.
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, John Follansbee can be reached on (571) 272-3964. 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.
/Z.D./Examiner, Art Unit 2444
/SCOTT B CHRISTENSEN/Primary Examiner, Art Unit 2444
