DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 18, 20-22, and 24-33 have been cancelled.
Continued Examination Under 37 CFR 1.114
2. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01/08/2026 has been entered.
Status of Claims
3. This Office Action is in response to the application filed on 01/08/2026. Claims 1-17, 19, and 23 are presently pending and are presented for examination.
4. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Response to Arguments
5. Applicant's arguments filed 01/08/2026 have been fully considered but they are not persuasive.
Applicant argued that the generation of the coverage map is therefore not an abstract add-on, but a concrete downstream technical operation that depends on,
and uses the output of, the machine learning model.
Examiner respectfully disagrees. Applicant Figure 3 is recited below for examiner responses.
PNG
media_image1.png
716
1004
media_image1.png
Greyscale
The claim language does not recites inputting the physical 304 and geographic 306 into features calculator 308. Therefore, essential steps are missing. It is also hoe the 304 and 306 are input manually or automatically. Therefore, “inputting physical cell information corresponding to a first plurality of regions in a first cell of a wireless communication network” and: “inputting geographic information corresponding to the first plurality of regions” as they are claimed are considered abstract that can mentally be conceived. Further, the limitation “deriving one or more features for each of the first plurality of regions based on the cell information and the geographic information” as it has claimed seems is the outcome some mathematical computation, therefore it is also considered an abstract idea that can be mentally achieved. Further, the limitation “obtaining a set of labels indicating signal strength values corresponding to each of the first plurality of regions” as it has claimed seems is predefined values obtained manually, therefore they are also considered an abstract ideas that can be mentally achieved or physically measured. Finally, the step of “obtaining a set of labels indicating signal strength values corresponding to each of the first plurality of regions” can be the final step that can be conceived to train any learning machine. Therefore, conceptually any learning machine can be trained to perform some tasks. Finally, the limitation “generating, using the trained machine learning model (a computer program), a coverage map (a report) of the first cell, wherein the coverage map comprises both: measured signal strength values corresponding to the obtained set of labels, and the predicted signal strength values output by the trained machine learning model” is a general use of any computer program that receives one or more inputs and produces one or more outputs where the computer program can be modified for example to output the inputs and outputs side-by-side.
Final notes the obtained set of labels are the signal strength values that is the coverage map (report) reports both the signal strength values and predicted strength values. In addition, Figure 4 replicated below indicated the predicted values are outcomes of features 408 fed to trained models 414s not the obtained set of labels (the signal strength values). That is if the measured signal strength values are available why is there for a need to predict signal strength values.
PNG
media_image2.png
692
732
media_image2.png
Greyscale
Examiner believes that by amending the claim limitations creating a coverage map, template, for a cell can be used to predict signal strength values a particular cell by inputting features the particular cell. However, the method of obtaining the features seems to be inventive concept which are not claimed.
Applicant argued that Hou in view of Yang does not teach “Claims 1 and 15 have been amended to clarify that the recited coverage map is generated using a trained machine learning model, and that the coverage map comprises both measured signal strength values tied to real-world measurements (or labels) and predicted signal strength values output by the machine learning model”.
Examiner respectfully disagrees. Hou teaches The reconstructed data frames are used to train an existing ML model. This may be performed without modifying the other data in the measurement record or changing the ML model. In doing so, model prediction accuracy enhancement may be observed. This accuracy enhancement
may exceed the performance of previous models (Hou: paragraph 106). In addition, Hou teaches the model may use the ordered list of signal properties to estimate a geographic location of the mobile device. This estimate of geographic location may be used elsewhere in the network (Hou: paragraph 115). In addition, Hou teaches This application provides an improved method of estimating a geographic location of a mobile device. This application further provides an improved method of providing training data to a model, a method of generating an ordered list of signal properties and a method of correlating signal properties in an ordered list to corresponding cell
identifiers (Hou: paragraph 10). In addition Yang teaches Train the convolutional neural network using the first geographic image data, the first antenna and transmit power information of the first base station in the first geographic area, and the actual received signal strength (and the second geographic image data, the second antenna and transmit power information of the second base station in the second geographic area, and the simulated received signal strength) for predicting received signal strength representing signal strength of wireless signals received at different locations in a third geographic area (Yang: Fig. 6 “610”).
6. Applicant's arguments filed 08/28/2025 have been fully considered but they are not persuasive.
Applicant argued that the amended claims 1 and 15 recite “generating a coverage map of the cell, wherein the coverage map comprises both measured signal strength values and the predicted signal strength values.” Applicant further argued that in addition to generating a trained machine learning model, generating a coverage map of the cell that comprises both measured and predicted signal strength values. The claimed method therefore goes beyond mathematical operations in the abstract and requires a concrete, technical application in the form of a coverage map that depicts signal strength information for a wireless communication cell.
Examiner respectfully disagrees. Firstly, the amended limitation does not further limits its preceding limitation “generating a trained machine learning model for the first cell based on the derived features and the obtained set of labels.”
Secondly, Claims 1 and 15 recite the limitation "measured signal strength” and "the predicted signal strength.” There is insufficient antecedent basis for this limitation in the claim. Therefore, the amended limitation does not overcome the 35 U.S.C. § 101 rejection.
Applicant further argued that Yang does not disclose or suggest generating a coverage map that simultaneously includes both measured signal strength values and predicted signal strength values.
Examiner respectfully disagrees. Firstly, Hou teaches a MR (map) that provides both signal strength measured from neighboring cell and number of cell (see at least Table 1 and paragraph 9). Therefore, Hou teaches plurality single MR (maps) that simultaneously provide measured signal strength, PCIs, RSRPs, RSRQ, etc., (see at least table 1). Hance, it would have been obvious to a person of ordinary skill to produce a single record, a single table, a single matrix, etc., which simultaneously combine many parameters of interests.
In additions, Hou teaches by identifying that signal measurements from different measurement records relate to the same mobile device, the model may use previous estimations of the mobile device's location to determine an updated estimate of the location of the mobile device. The model may use maximum a posteriori "MAP" techniques. This may improve accuracy of the estimation of the geographic location (see paragraph 23).
In addition, Yang teaches The received signal strength matrix 130 can include a received signal strength value for each grid in the area of interest. The received signal strength matrix 130 has two dimensions, three dimensions, or higher dimensions. For example, the received signal strength value for each grid in the area of interest can be a received signal strength value for each grid in the area of interest with respect to different locations of the grid, different locations of the base station, different antenna heights of the base station, different environments (e.g., urban or rural, vegetation or foliage), different propagation media (e.g., dry or moist air), or other attributes that may affect the received signal strength value in the area of interest. In some implementations, the predicted received signal strength, as the output of the deep
neural network 120, can be represented in a table, an array, a figure, or a combination of these and other forms, in addition to or as an alternative to a received signal strength
matrix (Yang: Fig. 1 and paragraphs 66-67).
Hance, the combined teachings of Hou and Yang would have been obvious to a person of ordinary skill to produce a single record, a single table, a single matrix, a single map, etc., which simultaneously combine many parameters of interests.
Claim Rejections - 35 USC § 101
7. 35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1 is rejected under 35 U.S.C. 101 because claim 1 is directed to a method that is not necessarily computer implemented, consisting of mathematical steps, with the aim of generating a machine learning model. Although the data being processed is
arguably technical, the claim covers the execution by a human being of the mathematical steps of the method. An exemplary mathematical operation is claim 10 directed towards solving optimization function.
Claims 2-14 are rejected under 35 U.S.C. 101 because of their dependency from claim 1.
Claims 16-17, 19, and 23 are rejected under 35 U.S.C. 101 because of their dependency from claim 15.
Claim Rejections - 35 USC § 112
8. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, because it recites the limitation “inputting physical cell information corresponding to a first plurality of regions in a first cell of a wireless communication network” It is not clear to what entity the physical cell information is input.
Claim 1 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, because it recites the limitation “inputting geographic information corresponding to the first plurality of regions” It is not clear to what entity the geographic information is input.
Claim 1 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, because it recites the limitation “generating a coverage map of the cell, wherein the coverage map comprises measured signal strength values ...” There is insufficient antecedent basis for “ measured signal strength values” limitation in the claim.
Claims 2-14 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, because of their dependance from claim 1.
Claim 15 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, because it recites the limitation “generating a coverage map of the cell, wherein the coverage map comprises both measured signal strength values and the predicted signal strength values.” There is insufficient antecedent basis for this limitation in the claim.
Claims 16-17, 19, and 23 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, because of their dependance from claim 15.
Claim Rejections - 35 USC § 103
9. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-8, 12-17, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Hou (US 2023/0247579 A1) in view of Yang et al. (US 2019/0150006 A1).
For claim 1 Hou teaches a method of generating a machine learning model (paragraph 6 “a method of providing training data to a model ( e.g. a classifier, support vector machine, neural network, or other machine learning component) for estimating a geographic location of a mobile device based on a plurality of signal measurements is provided”), the method comprising:
inputting physical cell information corresponding to a first plurality of regions in a first cell of a wireless communication network (Fig. 8 “collect Physical Cell IDS (PCIs)” and generate PCI, RSRP, etc. For all cells” and paragraphs 167-168 “determines a cell identifier indicating which cell transmitted the signal… generates a measurement record from the signal measurement and cell identifier information…the MR may be sent (input) to another entity in the network”);
inputting geographic information corresponding to the first plurality of regions (Fig. 5 “geographic location to the model”, pargraph 101 “feeding the model geographical area signal (information)”, paragraph 104 “records collected in a geo-area of interest”, paragraph 168 “the MR may be sent (input) to another entity in the network”);
deriving one or more features for each of the first plurality of regions based on the cell information and the geographic information (Fig. 8 “PCI related feature”, paragraph 8 “feature scaling, which attempts to normalize the ranges of the features in the MR for the models”, and paragraph 146 “nominal numbering' with actual neighbor cell PCls as new features/columns, and associated radio signal profiles (RSRP) which may provide more relevant and useful information for ML models to learn patterns”);
obtaining a set of labels indicating signal strength values corresponding to each of the first plurality of regions (Fig, 8 “generate RSRP for all cells” and paragraph 146 “nominal numbering' with actual neighbor cell PCls as new features/columns, associated radio signal profiles (RSRP) which may provide more relevant and useful information for ML models to learn patterns”, and paragraph “148 “obtaining for ML model associated radio profiles, labels, RSRP”); and
generating a trained machine learning model for the first cell based on the derived features and the obtained set of labels ( Fig. 8 apply the updated data sets to train and test ML models”, paragraph 10 “training data to a model”, paragraphs 24-25 “providing training data to a model for estimation a geographical location…trained model using signal properties that are provided in a predefined order, the model identifies relationships between the location data and signal measurement data” and Fig. 3 “information input into Model 310”); and
Hou does not explicitly teach generating, using the trained machine learning model, a coverage map of the first cell, wherein the first cell,
However, Yang teaches train the convolutional neural network (trained machine learning) using the first geographic image data (geographical information), the first antenna and transmit power information of the first base station (first cell) in the first geographic area (Yang: Fig. 6 “610”), wherein the coverage map comprises both: measured signal strength values corresponding to the obtained set of labels, and predicted signal strength values output by the trained machine learning model (Yang: Fig. 6 “610: the actual received signal strength (measured signal strength)…for predicting received signal strength at different geographical area…and simulated received signal strength” and paragraph 50 “predict signal coverage. With information of a transmitted signal strength”, paragraph 61 “the deep neural network can be first trained using simulated received signal strength data and corresponding GIS maps”, and paragraph 67 “a map of received signal strength and predicted received signal strength”).
Hou does not explicitly teach inputting geographic information.
However, Yang teaches inputting the geographic data (information) and the antenna and transmit power information into the convolutional neural network; predicting received signal strength using the convolutional neural network that includes a number of convolution layers based on the received geographic data and the antenna and transmit power information, the received signal strength representing signal strength of wireless signals received at different locations in the geographic area; and outputting the predicted received signal strength (Yang: paragraph 7). In addition, Yang teaches geographical data includes geographical information system (GIS) data includes one or more of building height map layer, a terrain layer, or a clutter layer…the site or area of interest can be for example, a cell in a cellular communication network (Yang: paragraphs 14 and 66).
Thus, it would have been obvious to a person of ordinary skill in the art before the effective filing date of claimed invention to use the teachings of Yang in the machine learning of Hou to enter geographical and as well as other design requirements inputs to train a learning machine and use the trained to predict some outcome (e.g., a signal strength in a coverage area ) by inputting signal strength of geographical information of a cell and a cell identification (Yang: paragraph 7).
For claim 2 Hou in view of Yang teaches the method, further comprising:
applying the model to determine a predicted signal strength value corresponding to one or more regions of a second plurality of regions in the first cell (Yang: paragraph 7 “predict the received signal strength”),
wherein the second plurality of regions are different than the first plurality of regions (Yang: paragraph 11 “signal received at different location in the geographical area”).
For claim 3 Hou in view of Yang teaches the method, wherein the first cell is served by a node having an antenna, and the physical cell information comprises one or more of:
an identifier of the first cell (Hou: Fig. 8 “PCIs”) ;
(iv) azimuth of the antenna (Yang: paragraph 42 “azimuth angle”);
(v) antenna tilt (Yang: paragraph 42 “tilt angle”);
(vi) antenna altitude (Yang: paragraph 66 “antenna height”);
(vii) antenna transmit power (Yang: paragraph 80 “power information of a base station”); and
(viii) antenna beam width (Yang: paragraph 57 “spatial width”).
For claim 4 Hou in view of Yang teaches the method, wherein the geographic information comprises one or more of clutter information and elevation information (Yang: paragraph 67 “different antenna height of the base station”).
For claim 5 Hou in view of Yang teaches the method, wherein the first cell is served by a node having an antenna, and the derived features comprise one or more of:
delta tilt (Yang: paragraph 92 “azimuth and tilt angles”);
delta azimuth (Yang: paragraph 92 “azimuth and tilt angles”);
log distance (Yang: paragraph 92 “distance relative to antenna”);
For claim 6 Hou in view of Yang teaches the method, wherein the obtained set of labels are geo-located signal strength measurements corresponding to signals from an antenna of the first cell azimuth (Yang: paragraph 110 “signal strength from an antenna”).
For claim 7 Hou in view of Yang teaches the method of claim 6, wherein the set of labels are obtained from one or more of the following sources:
measurement messages sent from User Equipment, UEs, located within the first plurality of regions azimuth (Yang: paragraph 115 “receiving actual received signal strength includes receiving the actual received signal strength from a usage or service report that records signal strength received by one or more UEs at different locations in the first geographic area”);
For claim 8 Hou in view of Yang teaches the method, wherein the step of obtaining the labels comprises:
predicting one more signal strength values based at least in part of deviations in signal strength between first and second frequency bands, and wherein one or more of the labels in the obtained set of labels is the one or more predicted signal strength values (see Hou: paragraph 110 “spectrum frequency dependance”).
For claim 12 Hou in view of Yang teaches the method, further comprising:
obtaining one or more features for at least one region located in a second cell of the wireless communication network (Yang: “Receive second geographic image data representing geographic information of a second geographic area and second antenna and transmit power information of a second base station in the second geographic area”); and
obtaining one or more labels indicating signal strength values corresponding to the at least one region of the second cell, wherein the generating a machine learning model for the first cell is based at least in part on the features and labels for the at least one region of the second cell Yang: “Receive second geographic image data representing geographic information of a second geographic area and second antenna and transmit power information of a second base station in the second geographic area”).
For claim 13 Hou in view of Yang teaches the method of claim 12, wherein obtaining the one or more features for the at least one region located in the second cell comprises:
deriving the features based on the physical cell information and the geographic information of the at least one region located in the second cell (Yang: “Receive second geographic image data representing geographic information of a second geographic area and second antenna and transmit power information of a second base station in the second geographic area” and paragraph 58 “deriving trainable parameter”).
For claim 14 Hou in view of Yang teaches the method of claim 12, wherein the at least one region of the second cell has similar physical cell properties and similar geographic properties of a region located in the first cell (Hou: paragraph 102 “There are 504 available PCls for use in an LTE telecommunications network. To avoid PCI collisions, neighboring cells must not share a PCI. To avoid PCI con fusion, no cell in the network can have two neighbors that share the same PCI”).
For claim 15 Hou in view of Yang teaches a method of managing a wireless communication network, the method comprising:
obtaining one or more features for at least one region of a cell in the wireless communication network, wherein the one or more features are based at least in part on physical cell properties and geographic properties of the at least one region (as discussed in claim 1);
predicting a signal strength value for the at least one region by applying the one or more features to a machine learning model corresponding to the cell (as discussed in claim 1); and
generating, using the machine learning model, a coverage map of the cell, wherein the coverage map comprises both: one or more measured signal strength values corresponding to the at least one region, and the predicted signal strength values output by the machine learning model (as discussed in claim 1).
For claim 16 Hou in view of Yang teaches the method, wherein obtaining the one or more features comprises:
inputting physical cell information corresponding to the at least one region (as discussed in claim 1);
inputting geographic information corresponding to the at least one region; and deriving the one or more features from the input physical cell and geographic information (as discussed in claim 1).
For claim 17 Hou in view of Yang teaches the method, further comprising:
transmitting a report comprising one or more predicted signal strength values (Hou: Fig. 8 “reported RSRP” and as discussed in claim 1).
For claim 19 Hou in view of Yang teaches the method, wherein applying the one or more features to the machine learning model comprises multiplying the features by a set of coefficients (Hou: paragraph 8 “prior art method is "data normalization" or "feature scaling", which attempts to normalize the ranges of the features in the MR for the models” and this is a mathematical operation).
For claim 23 Hou in view of Yang teaches the method, further comprising:
configuring one or more parameters relevant for operation of the wireless communication network based at least in part on a predicted signal strength value (Yang: paragraph 58 “trainable parameters values are derived by training process”).
10. Claims 9 are rejected under 35 U.S.C. 103 as being unpatentable over Hou (US 2023/0247579 A1) in view of Yang et al. (US 2019/0150006 A1) further in view of Zhang in view of et al. (US 2013/0279292 A1).
For claim 9 Hou in view of Yang does not explicitly teach the method, wherein the step of generating the machine learning model comprises performing a constrained least squares optimization using the derived features and set of labels.
Applying constrained least squares optimization is a design mathematical choice. Zhang teaches solving the least-square optimization problem (Zhang: paragraph 37). In addition, Zhang teaches The nonlinear solver component 402 provides the capabilities as previously described and further comprises a least-squares component 702 for optimizing the pseudo-density function with a least-squares technique (Zhang: paragraph 44).
Thus, it would have been obvious to a person of ordinary skill in the art before the effective filing date of claimed invention to use the teachings of Zhang in the combined machine learning of Yang and Hou to input geographical and as well as other design requirements inputs in order stabilize non-linear equations Zhang: paragraph 9).
Conclusion
11. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Thampy et al. (US 2020/0092159 A1) and Alabbasi et al. (US 2023/0196111 A1).
12. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
13. Any inquiry concerning this communication or earlier communications from the examiner should be directed to David M OVEISSI whose telephone number is (571)270-3127. The examiner can normally be reached Monday-Friday 8Am-5PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jeffrey Rutkowski can be reached at (571) 270 - 1215. 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.
/MANSOUR OVEISSI/Primary Examiner, Art Unit 2415
Prosecution Insights