Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 13, 16 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. The application specification and claims refer to an “agent”, but the applicant’s specification doesn’t specifically disclose what agent is, the applicant specification paragraph 0024 discloses the functions of an agent, a processing system including a processor, an agent to each antenna that provides communication services in a geographic area, wherein the geographic area is partitioned into a plurality of bins, and wherein the agent executes an action that adjusts settings for network parameters for the antenna to improve coverage quality; initializing, by the processing system, random settings for the network parameters; computing, by the processing system, updated coverage quality, signal strength and interference for each bin in the plurality at a setting proposed by the agent; recording, by the processing system, the updated coverage quality, the signal strength and the interference in a history; rewarding, by the processing system, the agent for improvements, but it doesn’t specifically disclose what an agent is.
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.
Claim(s) 1, 2, 4, 6, 9, 16-18, 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1).
1, Sanders teaches a device, comprising: a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system [par 0085, Any suitable module or sub-module described above with reference to FIGS. 8, 9, and 33 may include the computer and non-transitory computer-readable memory associated with the program instructions. Alternatively, the computer and non-transitory computer-readable memory associated with the program instructions may be individual or combined components that are in operative communication with any suitable combination of the modules and sub-modules],
facilitate performance of operations, the operations comprising: partitioning a geographic area into a plurality of bins [fig 24, par 0052, FIG. 24, an exemplary set of signaling usage maps for a cluster of cellular coverage areas for a wireless network shows six 1-hour samples of signaling usage over a 24-hour period. An exemplary embodiment of a process for generating data usage maps during different hours of the day includes dividing an area of interest into sub-sector geographic areas (i.e., geo-bins). For example, a geo-bin size can represent a 50 meter by 50 meter sub-sector geographic area within the coverage area of a wireless network or a portion thereof];
assigning an agent to each antenna that provides communication services in the geographic area [par 0080, 0086, Each at least one base station including multiple sector antennas. Each sector antenna defining a sector coverage area within the cellular coverage area for the corresponding base station. At 3404, for each obtained parameter measurement, an instant geographic location of the corresponding mobile station is estimated in relation to the at least one base station serving the corresponding mobile station. FIG. 13, a functional diagram shows three base stations, each with three sector antennas, in relation to exemplary embodiments of various techniques for estimating the geographic location of a mobile station by dividing the wireless service area into different categories of circumstances for estimating the location. The applicant’s specification has specifically disclose what an agent is the examiner broadest reasonable interpretation is the base station including or with allocated antenna sectors are agent],
wherein the agent executes an action that adjusts settings for network parameters for the antenna to improve coverage quality; initializing random settings for the network parameters [par 0080, 0086,The parameter measurements having been measured during a select calendar timeframe. The network coverage area formed by a plurality of base stations. Each base station defining a cellular coverage area within the network coverage area. FIG. 13, a functional diagram shows three base stations, each with three sector antennas, in relation to exemplary embodiments of various techniques for estimating the geographic location of a mobile station by dividing the wireless service area into different categories of circumstances for estimating the location. Different types of data are available for the different categories. Thus, the techniques for estimating geographic location are adjusted for each category based on the type of data available under the corresponding circumstance];
computing updated coverage quality, signal strength and interference for each bin in the plurality at a setting proposed by the agent [par 0089, FIG. 13, for each sub-sector geographic area in the RF coverage map, a geo-bin is used to store signal strengths for the corresponding sub-sector geographic area. The RF coverage level for the sub-sector geographic area is updated over time by averaging (or by taking a median value) over multiple records of signal strength measurements. Study has shown that the longer the observation period, the more accurate the results are for the corresponding RF coverage level];
recording the updated coverage quality, the signal strength and the interference in a history [par 0089, 0097, with continued reference to FIG. 13, for each sub-sector geographic area in the RF coverage map, a geo-bin is used to store signal strengths for the corresponding sub-sector geographic area. With continued reference to FIGS. 14 and 15, signal strength measurements from category 2 circumstances can be combined with category 1 RF coverage maps and/or existing signal strength measurement information stored in geo-bins associated with neighboring sub-sector geographic areas to generate category 2 RF coverage maps. For example, in FIG. 14, in a category 1 area, including areas for subcategory 1A and subcategory 1B circumstances, an RF coverage map for base station A, sector 3 is already built from previous category 1 signal strength measurements];
rewarding the agent for improvements [par 0178, 0179, In a yet further embodiment of the angular position module 906, the source data communication sub-module 932 may also retrieve a first antenna elevation gain parameter value, a first antenna maximum gain parameter value, and a first antenna azimuth gain parameter characteristic from the storage device 936. The source data communication sub-module 932 may also retrieve a second antenna elevation gain parameter value, a second antenna maximum gain parameter value, and a second antenna azimuth gain parameter characteristic from the storage device 936. The second antenna azimuth gain parameter characteristic relating second antenna azimuth gain parameter values to the variable azimuth positions],
repeating the computing, the recording and the rewarding a preset maximum number of times at most or until an overall coverage quality improvement has reached a goal [par 0102, 0162, the RF coverage level for the sub-sector geographic area can continue to be updated in the RF coverage maps for each individual base station (i.e., sector antenna) by averaging (or by taking the median value) over multiple records for a corresponding geo-bin. Otherwise, the process 400 repeats the selecting with a different angular value, repeats the determining of the difference between the first and second transmit gains to obtain a new value for the third angular position component, repeats the adding and subtracting to form the arithmetic result and the determining of the absolute value, and continues the repeating until the absolute value is within the predetermined threshold of the desired value];
providing the history to a policy net as an epoch [par 0048, 0080, Metrics of interest, such as coverage, usage, user experience and activities, etc can be tracked for all active users during any select calendar time. In fact, tracking could be continuous using a rolling time window. Limitations on calendar time for tracking or the size of the rolling time window may arise if limitations on storage capacity are encountered. The parameter measurements having been measured during a select calendar timeframe. The network coverage area formed by a plurality of base stations. Each base station defining a cellular coverage area within the network coverage area];
and iterating the initializing, computing, recording, rewarding and repeating a maximum number of epochs at most or until the policy net has converged [par 0162,
the process 400 continues by identifying the angular value substituted for the variable azimuth position as the current angular position for the mobile station. Otherwise, the process 400 repeats the selecting with a different angular value, repeats the determining of the difference between the first and second transmit gains to obtain a new value for the third angular position component, repeats the adding and subtracting to form the arithmetic result and the determining of the absolute value, and continues the repeating until the absolute value is within the predetermined threshold of the desired value].
Sanders fail to show computing interference. In an analogous art Albert show computing interference [par 0053, That is, the controller/processor 225 can perform a blind interference sensing (BIS) process, such as performed by a BIS algorithm, and decode the received signal subtracted by the interfering signals. Any of a wide variety of other functions can be supported in the gNB 102 by the controller/processor 225. In some embodiments, the controller/processor 225 includes at least one microprocessor or microcontroller]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
2, Sanders and Albert illustrate the device of claim 1, wherein the computing selects only a subset of bins based on selected bins having an average variance in the signal strength [par 0089, geo-bin is used to store signal strengths for the corresponding sub-sector geographic area. The RF coverage level for the sub-sector geographic area is updated over time by averaging (or by taking a median value) over multiple records of signal strength measurements].
Sanders fail to show having an average variance in the signal strength computed by a geospatial ray tracing algorithm that exceeds a threshold.
In an analogous art Albert show having an average variance in the signal strength computed by a geospatial ray tracing algorithm that exceeds a threshold [par 0116, As illustrated in the calibration of the signal strength prediction tool 760 based on a trigger in block 765, CNE 135 can initiate the calibration of the signal strength prediction tool 760 for a class of BSs using the collected data tables. In certain embodiments, the signal strength prediction tool can be raytracing, a statistical channel model, or any other model. The trigger in block 765 can be, for example, an expiration of a timer, a collection of new data exceeding a threshold, an alarm indicating that the newly collected data does not fit the previously calibrated tool, and the like]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
4, Sanders and Albert discloses the device of claim 3, Sanders fail to show wherein the geospatial ray tracing algorithm analyzes a detailed 3D model of the geographic area.
In an analogous art Albert show wherein the geospatial ray tracing algorithm analyzes a detailed 3D model of the geographic area [par 0028, For example, the 3D maps required for ray-tracing for just one 500 m×500 m region can be cost intensive. Apart from cost, such maps may be unavailable for many regions globally]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
6, Sanders and Albert reveal the device of claim 1, wherein the network parameters include antenna tilt, power, beam width, transmission frequency, or a combination thereof [Sanders par 0147, The composite graph reflects differences in relation to varying azimuth position that follows the azimuth gain characteristics and a relatively steady state component from the elevation gain characteristics because the elevation tilt of the antennas is not changing]
9, Sanders and Albert creates the device of claim 1, Sanders fail to show wherein the processing system comprises a plurality of processors operating in a distributed computing environment.
In an analogous art Albert show wherein the processing system comprises a plurality of processors operating in a distributed computing environment [par 0101-0106, The collected user data may include among others such as: whether the measurement was taken outdoors, inside a car, in a building, or the like, whether the measurement was collected using special, highly accurate equipment or a cell phone app intended for mass distribution, or the like];
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
16, Sanders reveal a method, comprising: assigning, by a processing system including a processor[par 0085, Any suitable module or sub-module described above with reference to FIGS. 8, 9, and 33 may include the computer and non-transitory computer-readable memory associated with the program instructions. Alternatively, the computer and non-transitory computer-readable memory associated with the program instructions may be individual or combined components that are in operative communication with any suitable combination of the modules and sub-modules],
an agent to each antenna that provides communication services in a geographic area[par 0080, 0086, Each at least one base station including multiple sector antennas. Each sector antenna defining a sector coverage area within the cellular coverage area for the corresponding base station. At 3404, for each obtained parameter measurement, an instant geographic location of the corresponding mobile station is estimated in relation to the at least one base station serving the corresponding mobile station. FIG. 13, a functional diagram shows three base stations, each with three sector antennas, in relation to exemplary embodiments of various techniques for estimating the geographic location of a mobile station by dividing the wireless service area into different categories of circumstances for estimating the location. The applicant’s specification has specifically disclose what an agent is the examiner broadest reasonable interpretation is the base station including or with allocated antenna sectors are agent],
wherein the geographic area is partitioned into a plurality of bins[fig 24, par 0052, FIG. 24, an exemplary set of signaling usage maps for a cluster of cellular coverage areas for a wireless network shows six 1-hour samples of signaling usage over a 24-hour period. An exemplary embodiment of a process for generating data usage maps during different hours of the day includes dividing an area of interest into sub-sector geographic areas (i.e., geo-bins). For example, a geo-bin size can represent a 50 meter by 50 meter sub-sector geographic area within the coverage area of a wireless network or a portion thereof];
and wherein the agent executes an action that adjusts settings for network parameters for the antenna to improve coverage quality; initializing, by the processing system, random settings for the network parameters[par 0080, 0086,The parameter measurements having been measured during a select calendar timeframe. The network coverage area formed by a plurality of base stations. Each base station defining a cellular coverage area within the network coverage area. FIG. 13, a functional diagram shows three base stations, each with three sector antennas, in relation to exemplary embodiments of various techniques for estimating the geographic location of a mobile station by dividing the wireless service area into different categories of circumstances for estimating the location. Different types of data are available for the different categories. Thus, the techniques for estimating geographic location are adjusted for each category based on the type of data available under the corresponding circumstance];
computing, by the processing system, updated coverage quality, signal strength
and for each bin in the plurality at a setting proposed by the agent[par 0089, FIG. 13, for each sub-sector geographic area in the RF coverage map, a geo-bin is used to store signal strengths for the corresponding sub-sector geographic area. The RF coverage level for the sub-sector geographic area is updated over time by averaging (or by taking a median value) over multiple records of signal strength measurements. Study has shown that the longer the observation period, the more accurate the results are for the corresponding RF coverage level];
recording, by the processing system, the updated coverage quality, the signal
strength and the interference in a history[par 0089, 0097, with continued reference to FIG. 13, for each sub-sector geographic area in the RF coverage map, a geo-bin is used to store signal strengths for the corresponding sub-sector geographic area. With continued reference to FIGS. 14 and 15, signal strength measurements from category 2 circumstances can be combined with category 1 RF coverage maps and/or existing signal strength measurement information stored in geo-bins associated with neighboring sub-sector geographic areas to generate category 2 RF coverage maps. For example, in FIG. 14, in a category 1 area, including areas for subcategory 1A and subcategory 1B circumstances, an RF coverage map for base station A, sector 3 is already built from previous category 1 signal strength measurements];;
rewarding, by the processing system the agent for improvements [par 0178, 0179, In a yet further embodiment of the angular position module 906, the source data communication sub-module 932 may also retrieve a first antenna elevation gain parameter value, a first antenna maximum gain parameter value, and a first antenna azimuth gain parameter characteristic from the storage device 936. The source data communication sub-module 932 may also retrieve a second antenna elevation gain parameter value, a second antenna maximum gain parameter value, and a second antenna azimuth gain parameter characteristic from the storage device 936. The second antenna azimuth gain parameter characteristic relating second antenna azimuth gain parameter values to the variable azimuth positions],
repeating, by the processing system, the computing, the recording and the rewarding a preset maximum number of times at most or until an overall coverage quality improvement has reached a goal[par 0102, 0162, the RF coverage level for the sub-sector geographic area can continue to be updated in the RF coverage maps for each individual base station (i.e., sector antenna) by averaging (or by taking the median value) over multiple records for a corresponding geo-bin. Otherwise, the process 400 repeats the selecting with a different angular value, repeats the determining of the difference between the first and second transmit gains to obtain a new value for the third angular position component, repeats the adding and subtracting to form the arithmetic result and the determining of the absolute value, and continues the repeating until the absolute value is within the predetermined threshold of the desired value];
providing, by the processing system, the history to a policy net as an epoch; and
iterating, by the processing system, the initializing, computing, recording,
rewarding and repeating a maximum number of epochs at most or until the policy net has converged [par 0162, the process 400 continues by identifying the angular value substituted for the variable azimuth position as the current angular position for the mobile station. Otherwise, the process 400 repeats the selecting with a different angular value, repeats the determining of the difference between the first and second transmit gains to obtain a new value for the third angular position component, repeats the adding and subtracting to form the arithmetic result and the determining of the absolute value, and continues the repeating until the absolute value is within the predetermined threshold of the desired value].
Sanders fail to show computing interference. In an analogous art Albert show computing interference [par 0053, That is, the controller/processor 225 can perform a blind interference sensing (BIS) process, such as performed by a BIS algorithm, and decode the received signal subtracted by the interfering signals. Any of a wide variety of other functions can be supported in the gNB 102 by the controller/processor 225. In some embodiments, the controller/processor 225 includes at least one microprocessor or microcontroller]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
17, Sanders and Albert show the method of claim 16, wherein the computing selects only a subset of bins[par 0089, geo-bin is used to store signal strengths for the corresponding sub-sector geographic area. The RF coverage level for the sub-sector geographic area is updated over time by averaging (or by taking a median value) over multiple records of signal strength measurements].
Sanders fail to show where each bin selected has an average variance in the signal strength that exceeds a threshold
In an analogous art Albert show where each bin selected has an average variance in the signal strength that exceeds a threshold [par 0116, As illustrated in the calibration of the signal strength prediction tool 760 based on a trigger in block 765, CNE 135 can initiate the calibration of the signal strength prediction tool 760 for a class of BSs using the collected data tables. In certain embodiments, the signal strength prediction tool can be raytracing, a statistical channel model, or any other model. The trigger in block 765 can be, for example, an expiration of a timer, a collection of new data exceeding a threshold, an alarm indicating that the newly collected data does not fit the previously calibrated tool, and the like]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
18, Sanders and Albert determine the method of claim 17, Sanders fail to show wherein the average variance is computed by a geospatial ray tracing algorithm.
In an analogous art Albert show wherein the average variance is computed by a geospatial ray tracing algorithm[par 0116, As illustrated in the calibration of the signal strength prediction tool 760 based on a trigger in block 765, CNE 135 can initiate the calibration of the signal strength prediction tool 760 for a class of BSs using the collected data tables. In certain embodiments, the signal strength prediction tool can be raytracing, a statistical channel model, or any other model. The trigger in block 765 can be, for example, an expiration of a timer, a collection of new data exceeding a threshold, an alarm indicating that the newly collected data does not fit the previously calibrated tool, and the like]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
20, Sanders and Albert provide the method of claim 17, wherein the network parameters include antenna tilt [Sanders par 0147, The composite graph reflects differences in relation to varying azimuth position that follows the azimuth gain characteristics and a relatively steady state component from the elevation gain characteristics because the elevation tilt of the antennas is not changing]
6. Claim(s) 3, 5, 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1) in further view of FOREGEAT et al. (U.S. Pub No. 2026/0006461 A1).
3, Sanders and Albert the device of claim 1, Sanders and Albert fail to show wherein the agent executes an action that adjusts settings for network parameters for the antenna to decrease interference.
In an analogous art FORGEAT show wherein the agent executes an action that adjusts settings for network parameters for the antenna to decrease interference [par 0012, 0043, a facility, incrementing or decrementing a network parameter, adjusting a key performance indicator of the network, achieving a target signal-to-interference-plus-noise ratio (SINR) value for all user equipment connected to an antenna, improving coverage for user equipment served by an antenna, maximizing throughput, or maximizing coverage. The agents are a set of agents that can fulfill a reduced power consumption consisting of: a set of agents controlling the emitted power of a set of antennas (one agent per antenna), and an agent controlling the amount of compute resources allocated to a virtual MME. The action spaces of the agents are, respectively, a set of possible power levels for the antenna and a set of compute resource configurations for the virtual MME].
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, and FORGEAT because this achieves a target signal-to-interference-plus-noise ratio (SINR) value for all user equipment connected to an antenna, improving coverage for user equipment served by an antenna, maximizing throughput, or maximizing coverage.
5, Sanders and Albert discloses the device of claim 1, Sanders and Alert fail to show wherein the computing of the signal strength includes a multi-path coefficient.
In an analogous art Xin to show wherein the computing of the signal strength includes a multi-path coefficient [par 0009, The relationship between the direct wave and the reflected wave of the q number of waves is given by a multi-path coefficient to indicate the complex attenuation of the reflected wave s.sub.k(n) with respect to the direct wave].
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, and Xin because this provides a method and device for estimating the directions of a cyclostationary signals [Xin par 0018]
19, Sanders and Albert the method of claim 17, Sanders and Albert fail to show wherein the computing of the signal strength includes a multi-path coefficient.
In an analogous art Xin show wherein the computing of the signal strength includes a multi-path coefficient[par 0009, The relationship between the direct wave and the reflected wave of the q number of waves is given by a multi-path coefficient to indicate the complex attenuation of the reflected wave s.sub.k(n) with respect to the direct wave].
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, and Xin because this provides a method and device for estimating the directions of a cyclostationary signals [Xin par 0018]
7. Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1) in further view of HELLGREN et al. (U.S. Pub No. 2024/0220896 A1).
7, Sanders and Albert provide the device of claim 1, Sanders and Albert fail to show wherein the rewarding comprises a stepwise penalty, an individual improvement reward, a global improvement reward, a winning reward, a lose penalty, or a combination thereof.
In an analogous art Hellgren show wherein the rewarding comprises a stepwise penalty, an individual improvement reward, a global improvement reward, a winning reward, a lose penalty, or a combination thereof [par 0055, The mission completion time deviation part may provide a time corridor around the mission completion time, within which corridor the contribution to the reward parameter value is relatively high, and outside of which corridor, the parameter value is relatively low. Thereby, a stepwise penalty may be provided].
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, and Hellgren because improve the control of a plurality of vehicles performing missions along a respective route to allow an increase of the productivity, while keeping operating costs as low as possible. [Hellgren par 0005]
8. Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1) in further view of Fedder et al. (U.S. Pub No. 2024/0302185 A1).
8, Sanders and Albert illustrate the device of claim 1, Sanders and Albert fail to show wherein the policy net comprises a three-layer feed-forward neural network with a rectified linear unit activation.
In an analogous art Fedder show wherein the policy net comprises a three-layer feed-forward neural network with a rectified linear unit activation [par 0094, An L2 regularization may be adopted during the training process of the neural network to prevent an over-fitting model. A rectified linear unit activation function and a dynamic learning rate may be used to improve speed and avoid gradient vanishing in the training phase. In addition to studying the drift-compensation results using the three-layer neural network]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, and Fedder because the neural network may be tuned using hyperparameters to improve regression models incorporated by the network. [fedder par 0094]
9. Claim(s) 10-12, 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1) in further view of Xin (U.S. Pub No. 2006/0007043 A1).
10, Sanders discloses a non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor[par 0085, Any suitable module or sub-module described above with reference to FIGS. 8, 9, and 33 may include the computer and non-transitory computer-readable memory associated with the program instructions. Alternatively, the computer and non-transitory computer-readable memory associated with the program instructions may be individual or combined components that are in operative communication with any suitable combination of the modules and sub-modules],
Sanders fail to show facilitate performance of operations, the operations comprising: implementing a geospatial ray tracer that computes signal strength of a radio frequency emission from an antenna at a location bin in a geographical area,
wherein the geospatial ray tracer uses a multi-path coefficient to compute the signal strength, wherein the geospatial ray tracer computes coverage quality for the location bin responsive to an average variance of the signal strength exceeding a threshold, and wherein the coverage quality is provided to a reinforcement learning model;
and training the reinforcement learning model to discover network parameter settings that maximize radio communication coverage and minimize radio frequency interference in the geographical area.
In an analogous art Albert show facilitate performance of operations, the operations comprising: implementing a geospatial ray tracer that computes signal strength of a radio frequency emission from an antenna at a location bin in a geographical area [par 0028, The first approach is to use a pre-determined statistical channel model, for example, a Hata model, a 3GPP channel model, (see FIG. 6), and the like. An advantage of such statistical models is that they require minimal inputs for the signal strength prediction. However, such statistical channel models are not accurate since they are not calibrated for each specific type of BS and surrounding clutter. Furthermore, such statistical channel models are not resilient to errors in the data used for training the models. Another approach for signal strength prediction is to use ray-tracing data. With ray-tracing data, the details on AoA, AoD, ZoA, ZoD, power for each ray/path between transmitter and receiver can be captured. Therefore, ray-tracing technique can be quite accurate in predicting the coverage of wireless communication networks]
wherein the geospatial ray tracer computes coverage quality for the location bin responsive to an average variance of the signal strength exceeding a threshold[par 0116, As illustrated in the calibration of the signal strength prediction tool 760 based on a trigger in block 765, CNE 135 can initiate the calibration of the signal strength prediction tool 760 for a class of BSs using the collected data tables. In certain embodiments, the signal strength prediction tool can be raytracing, a statistical channel model, or any other model. The trigger in block 765 can be, for example, an expiration of a timer, a collection of new data exceeding a threshold, an alarm indicating that the newly collected data does not fit the previously calibrated tool, and the like]
and wherein the coverage quality is provided to a reinforcement learning model [par 0108, in one illustrative example, how preprocessing of data may involve transformations, which enable models trained in one location to be applied at other locations, is provided. It is noted that scope of such transformations are not limited to those described herein]
and training the reinforcement learning model to discover network parameter settings that maximize radio communication coverage and minimize radio frequency interference in the geographical area [par 0101-0106, As described above, these user reports along with the BS parameters can be stored in a data table at CNE 135 and herein will be referred to as the training data. In the second phase, a calibrated model can be used to predict signal strength at a given location from target gNB 103 based on known or nominal values of the target BS parameters, and the like. These known or nominal values are referenced as the test data. Training and test data can be collected at the same level of detail regarding, for example, whether LoS/nLoS classification or indoor/outdoor classification of area around the BS, and so forth, is available. The collected user data may include among others such as: RSRP level measured at the user; location information such as: latitude, longitude, or height relative to ground/sea level; Line-of-Sight indicator; whether the measurement was taken outdoors, inside a car, in a building, or the like; whether the measurement was collected using special, highly accurate equipment or a cell phone app intended for mass distribution, or the like];
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
Sanders and Albert fail to show wherein the geospatial ray tracer uses a multi-path coefficient to compute the signal strength
In an analogous art Xin show wherein the geospatial ray tracer uses a multi-path coefficient to compute the signal strength[par 0009, The relationship between the direct wave and the reflected wave of the q number of waves is given by a multi-path coefficient to indicate the complex attenuation of the reflected wave s.sub.k(n) with respect to the direct wave].
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, and Xin because this provides a method and device for estimating the directions of a cyclostationary signals [Xin par 0018]
11, Sanders, Albert, and Xin convey the non-transitory machine-readable medium of claim 10, Sanders and Xin fail to show wherein the geospatial ray tracer analyzes a detailed 3D model of the geographic area.
In an analogous art Albert show wherein the geospatial ray tracer analyzes a detailed 3D model of the geographic area [par 0028, For example, the 3D maps required for ray-tracing for just one 500 m×500 m region can be cost intensive. Apart from cost, such maps may be unavailable for many regions globally]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Xin, and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
12, Sanders, Albert, and Xin reveals the non-transitory machine-readable medium of claim 10, wherein the network parameter settings include antenna tilt [Sanders par 0147, The composite graph reflects differences in relation to varying azimuth position that follows the azimuth gain characteristics and a relatively steady state component from the elevation gain characteristics because the elevation tilt of the antennas is not changing]
15, Sanders, Albert, and Xin define the non-transitory machine-readable medium of claim 10, Sanders and Xin fail to show wherein the processing system comprises a plurality of processors operating in a distributed computing environment.
In an analogous art Albert show wherein the processing system comprises a plurality of processors operating in a distributed computing environment [par 0101-0106, The collected user data may include among others such as: whether the measurement was taken outdoors, inside a car, in a building, or the like, whether the measurement was collected using special, highly accurate equipment or a cell phone app intended for mass distribution, or the like];
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders and Albert because this provides generation and calibration of a signal strength prediction in an wireless communication system. [Albert par 0004]
10. Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1) in further view of Xin (U.S. Pub No. 2006/0007043 A1), in view of HELLGREN et al. (U.S. Pub No. 2024/0220896 A1).
13, Sanders, Albert and Xin the non-transitory machine-readable medium of claim 10, Sanders, Albert and Xin fail to show wherein the reinforcement learning model rewards an agent for each antenna, and wherein the rewarding comprises a stepwise penalty, an individual improvement reward, a global improvement reward, a winning reward, a lose penalty, or a combination thereof.
In an analogous art Hellgren show wherein the reinforcement learning model rewards an agent for each antenna, and wherein the rewarding comprises a stepwise penalty, an individual improvement reward, a global improvement reward, a winning reward, a lose penalty, or a combination thereof [par 0055, The mission completion time deviation part may provide a time corridor around the mission completion time, within which corridor the contribution to the reward parameter value is relatively high, and outside of which corridor, the parameter value is relatively low. Thereby, a stepwise penalty may be provided].
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, Xin, and Hellgren because improve the control of a plurality of vehicles performing missions along a respective route to allow an increase of the productivity, while keeping operating costs as low as possible. [Hellgren par 0005]
11. Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sanders et al. (U.S. Pub No. 2013/0005297 A1) in view of Albert et al. (U.S. Pub No. 2022/0053345 A1) in further view of Xin (U.S. Pub No. 2006/0007043 A1), in view of Fedder et al. (U.S. Pub No. 2024/0302185 A1).
14, Sanders, Albert and Xin creates the non-transitory machine-readable medium of claim 10, Sanders, Albert and Xin fail to show wherein the reinforcement learning model comprises a three-layer feed-forward neural network with a rectified linear unit activation.
In an analogous Fedder show wherein the reinforcement learning model comprises a three-layer feed-forward neural network with a rectified linear unit activation [par 0094, An L2 regularization may be adopted during the training process of the neural network to prevent an over-fitting model. A rectified linear unit activation function and a dynamic learning rate may be used to improve speed and avoid gradient vanishing in the training phase. In addition to studying the drift-compensation results using the three-layer neural network]
Before the effective filing date it would have been obvious to one of ordinary skill in the art to combine the teachings of Sanders, Albert, Xin, and Fedder because the neural network may be tuned using hyperparameters to improve regression models incorporated by the network. [fedder par 0094]
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JASON A HARLEY whose telephone number is (571)270-5435. The examiner can normally be reached 7:30-300 6:30-8:30.
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, Marcus Smith can be reached at (571) 270-1096. 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.
/JASON A HARLEY/Examiner, Art Unit 2468
Prosecution Insights