DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The following is a non-final office action in response to applicant’s amendment filed on 09/19/2025 for response of the office action mailed on 05/19/2025. Claims 3-4, 12, 15-16 and 24 have been canceled. Claims 1, 10, 14 and 22 have been amended. Claims 27-30 are newly added. Claims 1-2, 5-11, 13-14, 17-23 and 25-30 are pending in this application.
Response to Arguments
Applicant’s arguments filed 09/19/2025 have been considered but are not persuasive.
First Argument:
Applicant maintains the previously submitted traversal arguments regarding Bai et al. (US 2020/0259575; hereafter "Bai") in view of Xue et al. (US 20210376895; hereafter "Xue").
Previously submitted traversal argument (with response below) on 08/14/2025: On page 9, Applicant states Claims 1-26 have been rejected under 35 U.S.C. 102 as allegedly anticipated by Bai et al. (US 2020/0259575; hereafter "Bai"). Applicant traverses the prior art rejection because the cited prior art reference fails to teach or suggest all the features recited in the rejected claims. For example, the cited prior art fails to teach or suggest the claimed invention wherein a transmission parameter is adjusted based on the deviation to improve the transmission efficiency on the radio channel in the future, wherein, in response to the deviation being above a threshold, the predicted, present channel dynamic is repredicted, and the deviation between the repredicted present channel dynamic and the calculated present channel dynamic is redetermined, wherein the reprediction and redetermination are performed until the deviation is below the threshold, and wherein, in response to the redetermined deviation being below the threshold, the transmission parameter is adjusted by reducing a reference signal rate and/or reference signal content, as recited in the independent claims.
In response to this argument, Examiner introduces Xue, which discloses the amended features recited in the independent claims. Specifically, Figure 4 shows a machine learning (ML) based channel state information (CSI) prediction module, used for predicting CSI and qualify the predictions in accordance with a measured CSI to see if the predictions are accurate or not. By predicting CSI and identifying whether the prediction is qualified or not qualified (e.g., whether the predicted CSI is within an accuracy threshold, or whether the predicted CSI falls within one or more categories that are considered to be sufficiently accurate), network performance may be increased through increases in throughput, decreases in negative effects caused from inaccurate reporting, and the like (¶0062, Xue). Xue also discloses adjusting a transmission parameter in ¶0023, ¶0071, ¶0089 and using a lower MCS, reduced rank or the like for transmission in ¶0048. Fig. 5,6 and 9 show diagrams and flow charts of communication between the UE and network entity, including generating a CSI difference value (deviation).
Response: Examiner has considered the applicant’s arguments and respectfully maintains previous response to the above argument.
Second Argument:
Further, Applicant traverses the prior art rejection for the additional reason that the cited prior art references fails to teach or suggest all the features recited in the rejected claims including adjustment of a transmission parameter for future transmission on the radio channel in response to the deviation to improve the transmission efficiency on the radio channel in the future, wherein the transmission parameter is adjusted by reducing report content by informing the network entity of the adjustment, as recited in the independent claims.
Response: Examiner has considered the applicant’s arguments and respectfully disagrees.
Examiner would like to direct Applicant’s attention to Bai, where in ¶0023, the UE predicts future channel conditions and ¶0037 shows that the future channel condition is predicted to be above or below a threshold and/or above or below a current channel condition. ¶0023 also states based on receiving the indication, the BS may adjust a communication parameter, change a beam, or hand the UE over to a different base station or cell, therefore showing based on what the UE reports about predicted channel quality, there is an adjustment for future transmission. ¶0067 shows the UE changes its reporting behavior depending on the evaluated channel (or deviation). If the channel is good, or if the deviation is within a threshold, the UE sends fewer reports, meaning report content is reduced, transmission overhead is lowered and efficiency is overall improved. When the event-based reporting reduces the number of transmitted reports, the base station is notified of the change in reporting frequency/periodicity/content. The absence of reports informs the network that the deviation did not exceed the threshold, the UE has applied the reporting rule and the transmission parameter, in this case, reporting behavior has been adjusted accordingly. Therefore the cited paragraphs in Bai show a UE predicting channel conditions, comparing them to a threshold, and altering its reporting behavior based on those outcomes. When the channel is good (i.e., the deviation is within an acceptable threshold or range), the UE uses event-based reporting to reduce the number of reports it sends, which reduces transmission overhead. The change in reporting behavior is observed by a base station, therefore informing the network of the UE’s reporting adjustment.
Lastly, Applicant is reminded that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See in re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR international Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007).
Third Argument:
Applicant submits that Bai, even with the addition of Xue, is still deficient because there is no real consideration of a deviation between a predicted value and an actual value with subsequent alteration of report content based on the degree of that deviation when compared to a threshold value. Xue's consideration of deviation does not match up to the values being compared in the present invention under any reasonable interpretation.
Response: Examiner has considered the applicant’s arguments and respectfully disagrees.
Xue’s predicted CSI and measured CSI in ¶0023, where the predicted CSI value is produced by a prediction model, and the measured CSI, which is the actual value obtained, with a difference between them being computed is interpreted as the deviation. Xue also suggests or teaches a degree of deviation relative to a threshold in ¶0066, when the deviation (CSI difference) is compared to a threshold, specifically the system divides the deviations into a small deviation (within a threshold) or a large deviation (exceeding a threshold). In ¶0080, the quantized CSI difference value or one-bit indicator shows the result of comparing the deviation to a threshold is encoded in a report. The content of the report changes depending on whether the deviation is small or exceeds the threshold, which the Examiner interprets as an alteration of report content based on deviation. Lastly, ¶0053 expands the alteration beyond the indicator because if the deviation repeatedly exceeds the threshold, the UE changes what it reports, and can send information instructing the model retraining/reconfiguration. Therefore, the system sends different indicator values or model-update instructions depending on whether the deviation is above or below a threshold, showing alteration of report content.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, 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.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
Claims 1-2, 5-11, 13-14, 17-23 and 25-26 are rejected under 35 U.S.C. 103 as being unpatentable over Bai et al. (US 2020/0259575), Bai hereinafter, and in view of Xue et al. (US 2021/0376895), Xue hereinafter.
Re. Claim 1, Bai teaches an apparatus for user equipment for improving a transmission efficiency on a radio channel (Fig. 4-7, 10-11 & ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance) the apparatus comprising: one or more interfaces configured to communicate with a communication device; and processing circuitry configured to control the one or more interfaces and configured to: (Fig. 8 & See Claim 33);
obtain a predictive environmental model; (Fig. 4-7, 10-11 & ¶0061 - The UE 104…may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel);
predict a present channel dynamic of the radio channel based on the predictive environmental model; (Fig. 4-7, 10-11 & ¶0058 - for UE 104 side prediction, the UE 104 may use CSI measurements from downlink reference signals, its own side information (moving speed, delay spread) and/or feedback and other side information (e.g., information from a base station 102 or from sensors of the UE 104) to predict channel quality);
receive, from a network entity, a reference signal; (Fig. 3, 4-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications. ¶0045 - FIG. 3 is a block diagram of a base station 310 in communication with a UE 350 in an access network. ¶0047 - At the UE 350, each receiver 354RX receives a signal through its respective antenna 352 … The soft decisions are then decoded … to recover the data and control signals that were originally transmitted by the base station 310 on the physical channel);
measure a present channel characteristic of the radio channel based on the reference signal; (Fig. 4-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications);
calculate the present channel dynamic of the radio channel on the received reference signal; (Fig. 4-7, 10-11 & ¶0065 - A UE 104 may predict channel quality based on past observations of some channel metric, such as one or more of an RSRP, a SNR, CQI, RI, PMI, or the like. These past observations may be based on signals, such as reference signals…);
adjust a transmission parameter for future transmission on the radio channel in response to the deviation to improve transmission efficiency on the radio channel in the future, wherein the transmission parameter is adjusted by reducing report content by informing the network entity of the adjustment, (Fig. 4-7, 10-11 & ¶0023 - In response to predicting the future channel condition, the UE may send an indication of the future channel quality to a scheduling entity, such as a base station. The base station may receive the indication of the future channel quality and may communicate with the UE based on the indication. For example, the BS may adjust a communication parameter, change a beam, or hand the UE over to a different base station or cell. ¶0037 - The indication may indicate that the future channel condition is predicted to be above or below a threshold and/or above or below a current channel condition. ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance. ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition. Please also see ¶0057);
Yet, Bai does not explicitly teach determine a deviation between the predicted present channel dynamic and the calculated present channel dynamic; compare the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; and in response to the deviation being above a threshold, the predicted, present channel dynamic is repredicted, and the deviation between the repredicted present channel dynamic and the calculated present channel dynamic is redetermined, wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, and thereafter the adjustment of the transmission parameter is performed.
However, in the analogous art, Xue explicitly discloses determine a deviation between the predicted present channel dynamic and the calculated present channel dynamic; (Fig. 4-5, 9 & ¶0023- predicting channel state information (CSI) using machine learning models and qualifying predicted CSI based on a difference between the predicted CSI and measured CSI. Examiner interprets the difference as the deviation);
compare the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; and (Fig. 4-5, 9 & ¶0066 - Generally, the quantized CSI difference value may be a value that indicates a relative level of accuracy for the CSI predicted based on the CSI prediction model. For example, rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). ¶0080 - The other value for the one-bit indicator may indicate that the CSI difference value exceeds the a priori defined threshold value (e.g., indicating that the CSI difference value corresponds to an inaccurate prediction));
in response to the deviation being above a threshold, the predicted, present channel dynamic is repredicted, and the deviation between the repredicted present channel dynamic and the calculated present channel dynamic is redetermined, (Fig. 4-6, 9 & ¶0053 - If the predictions are consistently inaccurate by more than a threshold amount, the UE can determine that the model is inaccurate and can update the training data set using recorded CSI and instruct the gNB to reconfigure the UE with an updated, retrained machine learning model. Please also see ¶0062);
wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, and (Fig. 4-6 & ¶0066 - rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). 7 & ¶0073 - FIG. 7 illustrates an example timeline of measuring CSI and predicting CSI based on the measured CSI. Timeline 700 illustrates four instances 702a-702d of CSI measurement and prediction. Please also see ¶0062 and ¶0090);
thereafter the adjustment of the transmission parameter is performed (Fig. 4-6, 9 & ¶0023 - predicting CSI based on a machine learning model and reporting whether a CSI prediction is qualified or not qualified may provide for improved reliability of connections between a network entity and a user equipment (UE) and reduce latency (e.g., in adjusting parameters of a network connection between a UE and a network entity using predicted CSI instead of waiting for the UE to report a CSI measurement. ¶0048 - For example, the transmitter can use a lower modulation and coding scheme (MCS), reduced rank, or the like for the transmission at time t+Δ.sub.2 than the CSI feedback generated based on the CSI measurement at time t−Δ.sub.1 and reported at time t may indicate. Please also see ¶0089).
Therefore, it would have been obvious to one of the ordinary skilled in the art before the effective filing date of the claimed invention to add the teaching of Xue to the teaching of Bai. The motivation would be because the use of CSI predictions for transmissions between a network entity (e.g., a gNodeB) and a UE and may result in more efficient use of wireless communications resources, improved reliability for communications between the network entity and the UE, and the like (¶0059, Xue).
Re. Claim 2, Bai and Xue teach Claim 1.
Bai further teaches a transportation vehicle comprising the apparatus of claim 1 (Fig. 1 & ¶0036 - Examples of UEs 104 include… a vehicle, a vehicle UE (VUE) or any other similar functioning device. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meter, gas pump, toaster, vehicles, heart monitor, etc.).
Re. Claim 5, Bai and Xue teach Claim 1.
Bai further teaches the reprediction is based on a new predictive environmental model (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. The prediction algorithm may utilize prediction methods or algorithms such as a deep learning neural network with long and/or short-term memory, a Kalman filter, or various other algorithms or methods).
Re. Claim 6, Bai and Xue teach Claim 1.
Bai further teaches prediction and/or reprediction is based on a machine learning model trained with a dataset indicating the predicted channel dynamic and the calculated channel dynamic (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. The prediction algorithm may utilize prediction methods or algorithms such as a deep learning neural network with long and/or short-term memory, a Kalman filter, or various other algorithms or methods. Fig. 5-7, 10-11 & ¶0066 - The method or algorithm may be required to meet a minimum accuracy requirement based on a set of test data or based on historical predictions. For example, the method or algorithm may be a specific method or algorithm agreed for predicting channel conditions for the wireless network. Examiner interprets that only one of the claimed features to be mapped because of the presence of “and/or”).
Re. Claim 7, Bai and Xue teach Claim 6.
Bai further teaches the processing circuitry is further configured to receive the dataset for training or initializing the machine learning model (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. Fig. 5-7, 10-11 & ¶0066 - The method or algorithm may be required to meet a minimum accuracy requirement based on a set of test data or based on historical predictions. Please also see ¶0073-¶0074. Examiner interprets that only one of the claimed features to be mapped because of the presence of “or”).
Re. Claim 8, Bai and Xue teach Claim 1.
Bai further teaches the adjusting of the transmission parameter is performed by reducing channel quality reporting (Fig. 5-7, 10-11 & ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. This can reduce the frequency of BFD/BFR and lead to reduced resource requirements and less disconnection time. Fig. 5-7, 10-11 & ¶0087 - For example, a reduced … modulation and coding scheme (MCS) may be selected based on a respective reduced or increased channel quality. Fig. 5-7, 10-11 & ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition).
Re. Claim 9, Bai and Xue teach Claim 1.
Bai further teaches information about the environment is obtained by: determining information about the environment using one or more sensors of the transportation vehicle; and/or receiving information about the environment (Fig. 1 & ¶0036 - Examples of UEs 104 include… a vehicle, a vehicle UE (VUE) or any other similar functioning device. Fig. 5-7, 10-11 & ¶0037 - The UE 104 may predict the future channel condition based on previous channel conditions, sensor data from one or more sensors of the UE 104, or the like. Fig. 5-7, 10-11 & ¶0071 - The sensor data may include accelerometer data, position data such as from a satellite positioning receiver, a screen use indicator, or the like. Examiner interprets that only one of the claimed features to be mapped because of the presence of “and/or”).
Re. Claim 10, Bai teaches an apparatus for a network entity for improving a transmission efficiency on a radio channel used for communication with a user equipment, the apparatus being configured to: (Fig. 4-7, 10-11 & ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance);
receive a predictive environmental model; (Fig. 4-7, 10-11 & ¶0065 - This side information may include past observations of different channels, sensor data of the UE 104, and/or configured parameters sent by a second device (such as a base station or network entity);
receive a reference signal from the network entity; (Fig. 3, 4-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications. ¶0045 - FIG. 3 is a block diagram of a base station 310 in communication with a UE 350 in an access network. ¶0047 - At the UE 350, each receiver 354RX receives a signal through its respective antenna 352 … The soft decisions are then decoded … to recover the data and control signals that were originally transmitted by the base station 310 on the physical channel);
measure a present channel characteristic of the radio channel based on the received reference signal; (Fig. 4-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications);
calculate the present channel dynamic of the radio channel on the received reference signal; (Fig. 4-7, 10-11 & ¶0065 - A UE 104 may predict channel quality based on past observations of some channel metric, such as one or more of an RSRP, a SNR, CQI, RI, PMI, or the like. These past observations may be based on signals, such as reference signals…);
adjust a transmission parameter for future transmission on the radio channel in response to the deviation to improve transmission efficiency on the radio channel in the future, wherein the transmission parameter is adjusted by reducing report content by informing the network entity of the adjustment, (Fig. 5-7, 10-11 & ¶0023 - In response to predicting the future channel condition, the UE may send an indication of the future channel quality to a scheduling entity, such as a base station. The base station may receive the indication of the future channel quality and may communicate with the UE based on the indication. For example, the BS may adjust a communication parameter, change a beam, or hand the UE over to a different base station or cell. ¶0037 - The indication may indicate that the future channel condition is predicted to be above or below a threshold and/or above or below a current channel condition. ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance. ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition. Please also see ¶0057);
Yet, Bai does not explicitly teach determine a deviation between the predicted present channel dynamic and the calculated present channel dynamic; compare the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; and in response to the deviation being above a threshold, the predicted, present channel dynamic is repredicted, and the deviation between the repredicted present channel dynamic and the calculated present channel dynamic is redetermined, wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, and thereafter the adjustment of the transmission parameter is performed.
However, in the analogous art, Xue explicitly discloses determine a deviation between the predicted present channel dynamic and the calculated present channel dynamic; (Fig. 4-5, 9 & ¶0023- predicting channel state information (CSI) using machine learning models and qualifying predicted CSI based on a difference between the predicted CSI and measured CSI. Examiner interprets the difference as the deviation);
compare the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; and (Fig. 4-5, 9 & ¶0066 - Generally, the quantized CSI difference value may be a value that indicates a relative level of accuracy for the CSI predicted based on the CSI prediction model. For example, rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). ¶0080 - The other value for the one-bit indicator may indicate that the CSI difference value exceeds the a priori defined threshold value (e.g., indicating that the CSI difference value corresponds to an inaccurate prediction));
in response to the deviation being above a threshold, the predicted, present channel dynamic is repredicted, and the deviation between the repredicted present channel dynamic and the calculated present channel dynamic is redetermined, (Fig. 4-6, 9 & ¶0053 - If the predictions are consistently inaccurate by more than a threshold amount, the UE can determine that the model is inaccurate and can update the training data set using recorded CSI and instruct the gNB to reconfigure the UE with an updated, retrained machine learning model. Please also see ¶0062);
wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, and (Fig. 4-6 & ¶0066 - rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). Fig. 7 & ¶0073 - FIG. 7 illustrates an example timeline of measuring CSI and predicting CSI based on the measured CSI. Timeline 700 illustrates four instances 702a-702d of CSI measurement and prediction. Please also see ¶0062 and ¶0090);
thereafter the adjustment of the transmission parameter is performed (Fig. 4-6, 9 & ¶0023 - predicting CSI based on a machine learning model and reporting whether a CSI prediction is qualified or not qualified may provide for improved reliability of connections between a network entity and a user equipment (UE) and reduce latency (e.g., in adjusting parameters of a network connection between a UE and a network entity using predicted CSI instead of waiting for the UE to report a CSI measurement. ¶0048 - For example, the transmitter can use a lower modulation and coding scheme (MCS), reduced rank, or the like for the transmission at time t+Δ.sub.2 than the CSI feedback generated based on the CSI measurement at time t−Δ.sub.1 and reported at time t may indicate. Please also see ¶0089).
Therefore, it would have been obvious to one of the ordinary skilled in the art before the effective filing date of the claimed invention to add the teaching of Xue to the teaching of Bai. The motivation would be because the use of CSI predictions for transmissions between a network entity (e.g., a gNodeB) and a UE and may result in more efficient use of wireless communications resources, improved reliability for communications between the network entity and the UE, and the like (¶0059, Xue).
Re. Claim 11, Bai and Xue teach Claim 10.
Bai further teaches adjusting the transmission parameter is performed by reducing a content of a report, a reporting rate and/or a reference signal rate of the user equipment (Fig. 5-7 & ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. This can reduce the frequency of BFD/BFR and lead to reduced resource requirements and less disconnection time. Fig. 5-7 & ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition. Please also see ¶0080. Examiner interprets that only one of the claimed features to be mapped because of the presence of “and/or”).
Re. Claim 13, Bai and Xue teach Claim 10.
Bai further teaches the prediction and/or reprediction is based on a machine learning model trained with a dataset indicating the predicted channel dynamic and the calculated channel dynamic (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. The prediction algorithm may utilize prediction methods or algorithms such as a deep learning neural network with long and/or short-term memory, a Kalman filter, or various other algorithms or methods. Fig. 5-7, 10-11 & ¶0066 - The method or algorithm may be required to meet a minimum accuracy requirement based on a set of test data or based on historical predictions. For example, the method or algorithm may be a specific method or algorithm agreed for predicting channel conditions for the wireless network. Examiner interprets that only one of the claimed features to be mapped because of the presence of “and/or”).
Re. Claim 14, Bai teaches a method for user equipment for improving a transmission efficiency on a radio channel, the method comprising: (Fig. 4-7, 10-11 & ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance)
obtaining a predictive environmental model; (Fig. 4-7, 10-11 & ¶0061 - The UE 104…may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel)
predicting a present channel dynamic of the radio channel based on the predictive environmental model; (Fig. 4-7, 10-11 & ¶0058 - for UE 104 side prediction, the UE 104 may use CSI measurements from downlink reference signals, its own side information (moving speed, delay spread) and/or feedback and other side information (e.g., information from a base station 102 or from sensors of the UE 104) to predict channel quality);
receiving a reference signal from a network entity; (Fig. 3-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications. ¶0045 - FIG. 3 is a block diagram of a base station 310 in communication with a UE 350 in an access network. ¶0047 - At the UE 350, each receiver 354RX receives a signal through its respective antenna 352 … The soft decisions are then decoded … to recover the data and control signals that were originally transmitted by the base station 310 on the physical channel);
measuring a present channel characteristic of the radio channel based on the received reference signal; (Fig. 4-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications);
calculating a present channel dynamic of the radio channel based on the received reference signal; (Fig. 4-7, 10-11 & ¶0065 - A UE 104 may predict channel quality based on past observations of some channel metric, such as one or more of an RSRP, a SNR, CQI, RI, PMI, or the like. These past observations may be based on signals, such as reference signals…);
adjusting a transmission parameter for future transmission on the radio channel in response to the deviation to improve transmission efficiency on the radio channel in the future, wherein the transmission parameter is adjusted by reducing report content by informing the network entity of the adjustment, (Fig. 4-7, 10-11 & ¶0023 - In response to predicting the future channel condition, the UE may send an indication of the future channel quality to a scheduling entity, such as a base station. The base station may receive the indication of the future channel quality and may communicate with the UE based on the indication. For example, the BS may adjust a communication parameter, change a beam, or hand the UE over to a different base station or cell. ¶0037 - The indication may indicate that the future channel condition is predicted to be above or below a threshold and/or above or below a current channel condition. ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance. ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition. Please also see ¶0057);
Yet, Bai does not explicitly teach determining a deviation between the predicted present channel dynamic and the calculated present channel dynamic; comparing the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; and in response to the deviation being above the threshold, repredicting the predicted, present channel dynamic, and redetermining the deviation between the repredicted present channel dynamic and the calculated present channel dynamic, wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, and thereafter the adjustment of the transmission parameter is performed.
However, in the analogous art, Xue explicitly discloses determining a deviation between the predicted present channel dynamic and the calculated present channel dynamic; (Fig. 4-5, 9 & ¶0023- predicting channel state information (CSI) using machine learning models and qualifying predicted CSI based on a difference between the predicted CSI and measured CSI. Examiner interprets the difference as the deviation);
comparing the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; (Fig. 4-5, 9 & ¶0066 - Generally, the quantized CSI difference value may be a value that indicates a relative level of accuracy for the CSI predicted based on the CSI prediction model. For example, rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). ¶0080 - The other value for the one-bit indicator may indicate that the CSI difference value exceeds the a priori defined threshold value (e.g., indicating that the CSI difference value corresponds to an inaccurate prediction));
and in response to the deviation being above the threshold, repredicting the predicted, present channel dynamic, and redetermining the deviation between the repredicted present channel dynamic and the calculated present channel dynamic, (Fig. 4-6, 9 & ¶0053 - If the predictions are consistently inaccurate by more than a threshold amount, the UE can determine that the model is inaccurate and can update the training data set using recorded CSI and instruct the gNB to reconfigure the UE with an updated, retrained machine learning model. Please also see ¶0062);
wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, (Fig. 4-6 & ¶0066 - rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). 7 & ¶0073 - FIG. 7 illustrates an example timeline of measuring CSI and predicting CSI based on the measured CSI. Timeline 700 illustrates four instances 702a-702d of CSI measurement and prediction. Please also see ¶0062 and ¶0090);
and thereafter the adjustment of the transmission parameter is performed (Fig. 4-6, 9 & ¶0023 - predicting CSI based on a machine learning model and reporting whether a CSI prediction is qualified or not qualified may provide for improved reliability of connections between a network entity and a user equipment (UE) and reduce latency (e.g., in adjusting parameters of a network connection between a UE and a network entity using predicted CSI instead of waiting for the UE to report a CSI measurement. ¶0048 - For example, the transmitter can use a lower modulation and coding scheme (MCS), reduced rank, or the like for the transmission at time t+Δ.sub.2 than the CSI feedback generated based on the CSI measurement at time t−Δ.sub.1 and reported at time t may indicate. Please also see ¶0089).
Therefore, it would have been obvious to one of the ordinary skilled in the art before the effective filing date of the claimed invention to add the teaching of Xue to the teaching of Bai. The motivation would be because the use of CSI predictions for transmissions between a network entity (e.g., a gNodeB) and a UE and may result in more efficient use of wireless communications resources, improved reliability for communications between the network entity and the UE, and the like (¶0059, Xue).
Re. Claim 17, Bai and Xue teach Claim 14.
Bai further teaches the reprediction is based on a new predictive environmental model (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. The prediction algorithm may utilize prediction methods or algorithms such as a deep learning neural network with long and/or short-term memory, a Kalman filter, or various other algorithms or methods).
Re. Claim 18, Bai and Xue teach Claim 14.
Bai further teaches the prediction and/or reprediction is based on a machine learning model trained with a dataset indicating the predicted channel dynamic and the calculated channel dynamic (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. The prediction algorithm may utilize prediction methods or algorithms such as a deep learning neural network with long and/or short-term memory, a Kalman filter, or various other algorithms or methods. Fig. 5-7, 10-11 & ¶0066 - The method or algorithm may be required to meet a minimum accuracy requirement based on a set of test data or based on historical predictions. For example, the method or algorithm may be a specific method or algorithm agreed for predicting channel conditions for the wireless network. Examiner interprets that only one of the claimed features to be mapped because of the presence of “and/or”).
Re. Claim 19, Bai and Xue teach Claim 18.
Bai further teaches receiving the dataset for training or initializing the machine learning model (Fig. 5-7, 10-11 & ¶0061 - The UE 104… may repeatedly feed a set of one or more previous measurements or other data into a prediction algorithm to generate a future curve, a predicted chance of failure within a specific time period (e.g., within a number X of slots), or other prediction for the channel. Fig. 5-7, 10-11 & ¶0066 - The method or algorithm may be required to meet a minimum accuracy requirement based on a set of test data or based on historical predictions. Please also see ¶0073-¶0074. Examiner interprets that only one of the claimed features to be mapped because of the presence of “or”).
Re. Claim 20, Bai and Xue teach Claim 14.
Bai further teaches adjusting the transmission parameter is performed by reducing a channel quality reporting (Fig. 5-7, 10-11 & ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. This can reduce the frequency of BFD/BFR and lead to reduced resource requirements and less disconnection time. Fig. 5-7, 10-11 & ¶0087 - For example, a reduced or increased modulation and coding scheme (MCS) may be selected based on a respective reduced or increased channel quality. Fig. 5-7, 10-11 & ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition).
Re. Claim 21, Bai and Xue teach Claim 14.
Bai further teaches information about the environment is obtained by: determining information about the environment using one or more sensors of the transportation vehicle; and/or receiving information about the environment (Fig. 1 & ¶0036 - Examples of UEs 104 include… a vehicle, a vehicle UE (VUE) or any other similar functioning device. Fig. 5-7, 10-11 & ¶0037 - The UE 104 may predict the future channel condition based on previous channel conditions, sensor data from one or more sensors of the UE 104, or the like. Fig. 5-7, 10-11 & ¶0071 - The sensor data may include accelerometer data, position data such as from a satellite positioning receiver, a screen use indicator, or the like. Examiner interprets that only one of the claimed features to be mapped because of the presence of “and/or”).
Re. Claim 22, Bai teaches a method for a network entity for improving a transmission efficiency on a radio channel used for communication with user equipment, (Fig. 4-7, 10-11 & ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance)
the method comprising receiving a predictive environmental model; (Fig. 4-7, 10-11 & ¶0065 - This side information may include past observations of different channels, sensor data of the UE 104, and/or configured parameters sent by a second device (such as a base station or network entity);
predicting a channel dynamic of the radio channel based on the predictive environmental model; (Fig. 4-7, 10-11 & ¶0058 - for UE 104 side prediction, the UE 104 may use CSI measurements from downlink reference signals, its own side information (moving speed, delay spread) and/or feedback and other side information (e.g., information from a base station 102 or from sensors of the UE 104) to predict channel quality);
receiving a reference signal; (Fig. 3-7, 10-11 & ¶0068 - The second device, … a base station 102, or other wireless communication device, may receive the report or other indication of a prediction by the UE 104);
measuring a present channel characteristic of the radio channel based on the received reference signal; (Fig. 4-7, 10-11 & ¶0022 - channel quality may be tracked based on reference signals or other communications);
calculating a present channel dynamic of the radio channel based on the received reference signal; (Fig. 4-7, 10-11 & ¶0065 - A UE 104 may predict channel quality based on past observations of some channel metric, such as one or more of an RSRP, a SNR, CQI, RI, PMI, or the like. These past observations may be based on signals, such as reference signals…);
adjusting a transmission parameter for future transmission on the radio channel in response to the deviation to improve transmission efficiency on the radio channel in the future, wherein the transmission parameter is adjusted by reducing report content by informing the network entity of the adjustment, (Fig. 4-7, 10-11 & ¶0023 - In response to predicting the future channel condition, the UE may send an indication of the future channel quality to a scheduling entity, such as a base station. The base station may receive the indication of the future channel quality and may communicate with the UE based on the indication. For example, the BS may adjust a communication parameter, change a beam, or hand the UE over to a different base station or cell. ¶0037 - The indication may indicate that the future channel condition is predicted to be above or below a threshold and/or above or below a current channel condition. ¶0089 - the method 700 may allow communication between the first device 702 and another device to proactively adjust to changes in channel condition before those changes lead to degraded performance. ¶0056 - Based on predictions, the UE 104, BS 102, or other device can proactively switch beams or links in advance. ¶0067 - Event based reporting may reduce the number or reports that need to be sent on the channel when the channel remains in good condition. Please also see ¶0057);
Yet, Bai does not explicitly teach determining a deviation between the predicted present channel dynamic and the calculated present channel dynamic comparing the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; and in response to the deviation being above the threshold, repredicting the predicted, present channel dynamic, and redetermining the deviation between the repredicted present channel dynamic and the calculated present channel dynamic, wherein the reprediction and redetermination, and the comparison are performed until the deviation is below the threshold, and thereafter the adjustment of the transmission parameter is performed.
However, in the analogous art, Xue explicitly discloses determining a deviation between the predicted present channel dynamic and the calculated present channel dynamic comparing the determined deviation with a threshold to determine whether the determined deviation is greater than the threshold; (Fig. 4-5, 9 & ¶0023- predicting channel state information (CSI) using machine learning models and qualifying predicted CSI based on a difference between the predicted CSI and measured CSI. Examiner interprets the difference as the deviation. ¶0066 - Generally, the quantized CSI difference value may be a value that indicates a relative level of accuracy for the CSI predicted based on the CSI prediction model. For example, rules for quantizing the CSI difference value may quantize the difference value into one of two values representing a coarse classification of the difference value (e.g., within a threshold amount or not within the threshold amount). ¶0080 - The other value for the one-bit indicator may indicate that the CSI difference value exceeds the a priori defined threshold value (e.g., indicating that the CSI difference value corresponds to an inaccurate prediction));
and in response to the deviation being above the threshold, repredicting the predicted, present channel dynamic, and redetermining the deviation between the repredicted present channel dynamic and the calculated present channel dynamic, (Fig. 4-6, 9 & ¶0053 - If the predictions are consistently inaccurate by more than a threshold amount, the UE can determine that the model is inaccurate and can update the training data set using recorded CSI and instruct the gNB to reconfigure the UE with an updated, retrained machine learning model. Please also see ¶0062);
wherein the reprediction and redetermination