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 .
Specification
Applicant is reminded of the proper language and format for an abstract of the disclosure.
The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words in length. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details.
The language should be clear and concise and should not repeat information given in the title. It should avoid using phrases which can be implied, such as, “The disclosure concerns,” “The disclosure defined by this invention,” “The disclosure describes,” etc. In addition, the form and legal phraseology often used in patent claims, such as “means” and “said,” should be avoided. Please address the “Disclosed herein” term.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 15 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 15 recites a center of the grid box location formula but does not define the variables in the formula. In other words, applicant is not pointing out and distinctly claiming the formula as it is unclear as to what the variables are in the formula. More specifically, applicant is reminded to further define the variables in the formula, such as
x
l
b
i
,
j
and
y
l
b
i
,
j
.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims under pre-AIA 35 U.S.C. 103(a), the examiner presumes that the subject matter of the various claims was commonly owned at the time any inventions covered therein were made absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and invention dates of each claim that was not commonly owned at the time a later invention was made in order for the examiner to consider the applicability of pre-AIA 35 U.S.C. 103(c) and potential pre-AIA 35 U.S.C. 102(e), (f) or (g) prior art under pre-AIA 35 U.S.C. 103(a).
Claims 1, 2, and 3 are rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Ma US 20080123900 A1 (hereinafter Ma).
Regarding claim 1, Kamal teaches a multimodal indoor positioning system comprising:
one or more Bluetooth low energy beacons; (Kamal; section 5.1 paragraph 6 - - Kamal teaches for the BLE-IPS subsystem, the BLE beacons chosen were Estimote’s Proximity Beacon).
one or more smartphones, wherein the smartphone captures one or more Bluetooth low energy signals from the one or more Bluetooth low energy beacons, (Kamal; section 5.1 paragraph 6 - - Kamal teaches for the BLE-IPS subsystem, a BLE beacon configured periodically broadcasts a data packet within its operational area. When a advertisement packet is received by a smartphone the app first parses the UUID and then the major and minor values to identify the beacon).
wherein the one or more Bluetooth low energy signals comprises a relative signal strength indicator signal, (Kamal; section 5.1 paragraph 6 - - Kamal teaches the smartphone app then forms the RSSI value based on perceived strength of the received advertisement signal and a pre-defined signal strength value at 1 meter distance).
wherein the smartphone generates a fingerprint and a location estimate from the relative signal strength indicator signal (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. This would ideally be executed within the smart phone).
one or more cameras, wherein the one or more cameras capture 2D video frames; (Kamal; section 4.2, paragraph 3 - - Kamal teaches the overhead camera captures a 2D RGB image).
and one or more edge devices, wherein the one or more edge devices are in electronic communication with the one or more cameras, (Kamal; section 4.2, paragraph 2 - - Kamal teaches that a 2D RGB image captured by the overhead camera unit is passed to the Edge device via the CSI bus).
wherein the one or more edge devices are in electronic communication with the one or more smartphones, (Kamal; section 5.1, paragraph 8 - - Kamal teaches MQTT is the chosen communication protocol with which the Edge device and all smartphones maintain device-to device communications).
wherein the one or more edge devices are in electronic communication with the one or more Bluetooth low energy beacons, (Kamal; section 4.2, paragraph 2 - - Kamal teaches in the physical layer, Bluetooth Low Beacons and the Edge device containing the overhead camera is present).
wherein the one or more edge devices receive the fingerprint and the location estimate from the one or more smartphones (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4, figure 8 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. Figure 8 teaches this information is transferred from the smartphone to the BLE-IPS edge device through the MQTT broker).
wherein the one or more edge devices receive the 2D video frames from the one or more cameras (Kamal; section 4.2, paragraph 3 - - Kamal teaches in the communication layer, a 2D RGB image captured by the overhead camera unit is passed to the Edge device via the CSI bus).
wherein the edge device generates 2D position coordinates from the 2D video frames; (Kamal; section 4.2, paragraph 5, fig. 8 - - Kamal teaches the edge device CV-IPS which consists of two modules which process the raw 2D image to extract 2D coordinates).
and wherein the one or more edge devices assigns a tracklet-ID (Kamal; section 4.2, paragraph 5, fig. 8 - - Kamal teaches the edge device CV-IPS can learn to recognize users as generic “objects” under a class called “Person” and assign a tracking id).
Kamal fails to teach assigning a tracklet-ID to each smartphone in the 2D video frames.
However, Ma clearly specifies assigning a tracklet-ID to each smartphone in the 2D video frames. (Ma; page 2, paragraph 17 & 18- - Ma teaches one may assign the track of, for example, a specific person, or a unique track identification designator (ID) (smartphones) and form a meaningful track in image/video frames. Ma also teaches multiple targets may be tracked).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Ma into the system of Kamal to include the feature of assigning a tracklet-ID to each smartphone in the 2D video frames, in order to provide a continuous spatiotemporal record of each smartphone’s position within the indoor space, critical for recognition of human actions in video surveillance as taught by Ma (see paragraph 0015).
Regarding claim 2, the combination of Kamal and Ma teaches the multimodal indoor positioning system of claim 1, wherein the edge device performs SORT Tracking and YOLO object detection (Kamal; 5.4 paragraph 8, section- - Kamal teaches the Simple Online and Realtime Tracking (SORT) model is chosen as the Multi Object Tracking (MOT) model, stating its simple architectures allows real-time operation on an Edge device. In addition, Kamal teaches YOLOv3 for object detection. It can reach 30FPS on MSCOCO2017dataset only when running on a GTX Titan (edge device)).
Regarding claim 3, the combination of Kamal and Ma teaches the multimodal indoor positioning system of claim 1, wherein the one or more edge devices receive the location estimate from the one or more smartphones over MQTelemetry Transport (Kamal; section 5.1 paragraph 7 - - Kamal teaches during each timestep, the Edge device using the MQTT messaging protocol “subscribes” to the pre-defined topic to acquire the Bluetooth data from users smart devices. Specifically, the localization output is available to the Edge device via the MQTT network but was not broadcasted to the users via the app due to complexity concerns).
wherein the one or more edge devices receive the fingerprint (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. This would ideally be executed within the smart phone. Figure 8 teaches this information is transferred from the smartphone to the BLE-IPS edge device through the MQTT broker).
Claims 4, 7, 11, 12, 13, 14 are rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Joo KR 101233841 B1, (hereinafter Joo).
Regarding claim 4, Kamal teaches a method comprising:
receive a Bluetooth low energy signal from Bluetooth low energy beacon (Kamal; section 5.1 paragraph 6 - - Kamal teaches for the BLE-IPS subsystem, a BLE beacon configured periodically broadcasts a data packet within its operational area. When an advertisement packet is received by a smartphone the app first parses the UUID and then the major and minor values to identify the beacon).
wherein the Bluetooth low energy signal comprises a relative signal strength indicator signal; (Kamal; section 5.1 paragraph 6 - - Kamal teaches the smartphone app then forms the RSSI value based on perceived strength of the received advertisement signal and a pre-defined signal strength value at 1 meter distance).
generate a fingerprint and a location estimate from the relative signal strength indicator signal; (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. This would ideally be executed within the smart phone).
capture 2D video frames from the one or more cameras; (Kamal; section 4.2, paragraph 3 - - Kamal teaches the overhead camera captures a 2D RGB image).
generate tracklet IDs (Kamal; section 4.2, paragraph 5, fig. 8 - - Kamal teaches the edge device CV-IPS can learn to recognize users as generic “objects” under a class called “Person” and assign a tracking id).
and 2D coordinates for one or more people in the 2D video frames (Kamal; section 4.2, paragraph 5, fig. 8 - - Kamal teaches the edge device CV-IPS which consists of two modules which process the raw 2D image to extract 2D coordinates).
Kamal fails to clearly specify a non-transitory computer readable medium comprising instructions which, when implemented by one or more computers and display the fingerprint and the location estimate.
However, Joo teaches a non-transitory computer readable medium comprising instructions which, when implemented by one or more computers (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory).
and display the fingerprint and the location estimate (Joo; paragraphs 0072, 0041 - - Joo teaches the server can create a fingerprint map application using the fingerprint map stored in the database (320) and distribute it to user terminals. Additionally, Joo teaches the UI screen is a menu for selecting a location to build a fingerprint map, and an administrator can use the menu to display a map of the selected location).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the invention of Kamal to include the feature of displaying the fingerprint map and location estimate to the user, in order to enable an administer or user to view the RSSI-based fingerprint data and the resulting location estimate on a map display and add the ability to type the name of the target location, improving the usability and interpretability of the indoor positioning system (see Joo paragraph 43).
Regarding claim 7, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory), wherein the indoor space, I, comprises a p x q grid cell configuration, wherein each grid cell is a 1 meter by 1 meter (Kamal; section 5.2 paragraph 2 - - Kamal teaches each grid cell is placed 1 meter apart and the cells are 0.5 m x 0.5 m (p x q configuration)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the system of Kamal to include the feature of storing the fingerprint map and associated grid cell of the p x q indoor grid configuration in a non-volatile memory, thereby enabling reliable retrieval of the fingerprint map and location estimates without requiring recomputation upon system restart (see Joo paragraph 0044).
Regarding claim 11, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory), wherein the instructions provide an Object Localization Error, wherein the Object Localization Error is the average distance between the actual and predicted location for each object throughout the object's trajectory, and wherein the Object Localization Error comprises the formula: OLE= (formula here) wherein t represents the numbers of time-steps in the trajectory of the object, n is the total number of obj are actual coordinates of an object j at a time i, and P_i,j are predicted coordinates of the object j at the time i. (Kamal; section 6.4.3. - - Kamal teaches OLE. Kamal computes positional error as the difference between actual coordinates A and predicted coordinates P, summed across both objects and time-steps).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the invention of Kamal to include the feature of storing the object localization error formula and associated trajectory coordinate data in a non-volatile memory, in order to save the positioning system’s programs and data so they are not lost when the system is turned off, thereby allowing the object localization error and location coordinates to be stored and used again when the system is turned back on (see Joo paragraph 0044).
Regarding claim 12, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory), wherein the generate a fingerprint and a location estimate from the relative signal strength indicator signal (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. This would ideally be executed within the smart phone)
comprises a Siamese network (Kamal; section 4.2 paragraph 5 - - Kamal teaches both the BLE-IPS and CV-IPS modules run in parallel).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the invention of Kamal to include the feature of storing the Siamese network model and associated RSSI-based fingerprint data in a non-volatile memory, in order to save the positioning system’s programs and data so they are not lost when the system is turned off, thereby allowing the Siamese network and fingerprint data to be stored and used again when the system is turned back on (see Joo paragraph 0044).
Regarding claim 13, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory), wherein the generate a fingerprint and a location estimate from the relative signal strength indicator signal (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. This would ideally be executed within the smart phone)
comprises a machine learning algorithm (Kamal; section 2.6.6. paragraph 2 - - Kamal teaches certain algorithms are required along with Machine Learning and Deep Learning algorithms to extract accurate location information from multimodal data.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the invention of Kamal to include the feature of storing the machine learning algorithm used to extract accurate location information from multimodal RSSI data in a non-volatile memory, in order to save the positioning system’s programs and data so they are not lost when the system is turned off, thereby allowing the algorithms to be reloaded and immediately used to extract accurate location information without requiring retraining upon a system restart (see Joo paragraph 0044).
Regarding claim 14, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 13 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory),wherein the machine learning algorithm (Kamal; section 2.6.6. paragraph 2 - - Kamal teaches certain algorithms are required along with Machine Learning and Deep Learning algorithms to extract accurate location information from multimodal data.)
comprising a random forest-based classification (Kamal; section 5.2 paragraph 4 - - The Machine Learning model chosen was the Random Forest classifier).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the invention of Kamal and to include the feature of storing the random forest-based classification algorithm and its associated multimodal training data in a non-volatile memory, in order to save the random forest-based classification and its trained decision trees so they are not lost when the system is turned off, thereby allowing the classifier to be reloaded and immediately used to extract accurate location information from multimodal data without requiring retraining upon a system restart (see Joo paragraph 0044).
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Joo KR 101233841 B1 and as applied to claim 7 above, further in view of Ashry (Wi-Fi based indoor localization using trilateration and fingerprinting methods), publication date 2019, [online] URL: https://iopscience.iop.org/article/10.1088/1757-899X/610/1/012072/meta (Year: 2019) (hereinafter referred to as “Ashry”).
Regarding claim 15, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 7 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory),
wherein the grid location comprises p x q grid cells, (Kamal; section 5.2 paragraph 2 - - Kamal teaches the cells are 0.5 m x 0.5 m (p x q configuration)).
wherein objects, s,, carrying device d is present at time t, (Kamal; section 6.1 paragraph 2 - - Kamal teaches that 20 participants are carrying 25 mobile devices while collecting data).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the system of Kamal to store the grid location and objects, s,, carrying device d is present at time t into the non-transitory computer medium, thereby enabling reliable retrieval of information without requiring recomputation upon system restart (see Joo paragraph 0044).
The combination of Kamal and Joo fails to clearly specify wherein a center of the grid box location comprises a formula:
l
b
i
,
j
=
(
x
l
b
i
,
j
,
y
l
b
i
,
j
)
, wherein Bluetooth device di, at time t.
However, Ashry teaches wherein a center of the grid box location comprises a formula:
l
b
i
,
j
=
(
x
l
b
i
,
j
,
y
l
b
i
,
j
)
, wherein Bluetooth device di, at time t (Ashry; section 4, paragraph 2 - - Ashry teaches the department corridor is divided into 20 grid cells and the CPs (calibration points) at the center of the cells as shown in Figure 1).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Ashry into the invention of Kamal and Joo to include the feature of storing center of the p x q grid box location in a non-volatile memory, in order to persistently store the precomputed center coordinates of each grid cell so they are not lost when the system is turned off, thereby allowing the classifier to immediately retrieve the grid box center locations and obtain a unique feature vector to each cell with different RSS samples at different times (see Ashry section 4 paragraph 2), creating a distinctive fingerprint for each grid cell, all without requiring retraining upon a system restart.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Joo KR 101233841 B1 and as applied to claim 4, further in view of Grady JP 2017511188 A, (hereinafter Grady).
Regarding claim 5, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the system of Kamal to include the non-transitory computer medium, thereby enabling reliable retrieval of information without requiring recomputation upon system restart (see Joo paragraph 0044).
The combination of Kamal and Joo fail to teach wherein the Object Localization Accuracy is displayed on a screen.
However, Grady teaches wherein the Object Localization Accuracy is displayed on a screen (Grady; paragraph 27 - - Grady teaches a display may be stored in an electronic storage device (e.g., a hard drive, RAM, network drive, etc.). This representation may include an object localization model (e.g., a boundary model or a volumetric model)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Grady into the invention of Kamal and Joo to include the feature of the Object Localization Accuracy being displayed on a screen, in order to allow users to visually monitor the accuracy of the indoor positioning system in real time, thereby enabling administrators to quickly represent an object model using a set of 3D coordinates and triangles (see Grady paragraph 27), which allows for improved visual clarity.
Claims 6, 8 are rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Joo KR 101233841 B1 as applied to claim 4, further in view of Ma US 20080123900 A1.
Regarding claim 6, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the system of Kamal to include the non-transitory computer medium, thereby enabling reliable retrieval of information without requiring recomputation upon system restart (see Joo paragraph 0044).
The combination of Kamal and Joo fail to teach wherein the generated tracking IDs comprise a formula, TR = tri, tr2, ..., trm, wherein at each timestep t in an indoor space.
However, Ma teaches wherein the generated tracking IDs comprise a formula, TR = tri, tr2, ..., trm, wherein at each timestep t in an indoor space (Ma; page 2, paragraph 22 - - Ma teaches assigning unique track identification designators (IDs) to tracked targets across frames, with tracking maintained at each timestep, all in the temporal and spatial space).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Ma into the invention of Kamal and Joo to include the feature of the generated tracking IDs comprising a formula, TR = tri, tr2, ..., trm, wherein at each timestep t in an indoor space, in order to provide a systematic and organized method of assigning and maintaining unique tracking IDs to each object across every timestep, thereby enabling the indoor positioning system to continuously and reliably track multiple objects simultaneously throughout their trajectories in the indoor space. This is beneficial because the targets’ positions and velocities may automatically be initialized and do not necessarily require operator interaction (see Ma paragraph 22).
Regarding claim 8, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the system of Kamal to include the non-transitory computer medium, thereby enabling reliable retrieval of information without requiring recomputation upon system restart (see Joo paragraph 0044).
The combination of Kamal and Joo fail to teach wherein new tracking IDs are generated due to ID switching or occlusions.
However, Ma teaches wherein new tracking IDs are generated due to ID switching or occlusions (Ma; page 1, paragraph 12 - - Ma teaches tracking may be suspended on occluded objects and re-initiated when they emerge from the occlusion. Then the suspended tracklets may be matched with the new tracklets).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Ma into the invention of Kamal and Joo to include the feature of wherein new tracking IDs are generated due to ID switching or occlusions, in order to ensure continuous and uninterrupted tracking of objects in the indoor space by suspending and re-initiating tracking IDs when objects become occluded, thereby preventing the loss of object identity and also have the ability to handle changes in object appearance during tracking (see Ma paragraph 12).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Joo KR 101233841 B1 as applied to claim 4, further in view of Yang (Indoor 3D Localization Scheme Based on BLE Signal Fingerprinting and 1D Convolutional Neural Network), publication date 21 July 2021, [online] URL: https://www.mdpi.com/2079-9292/10/15/1758 (Year: 2021) (hereafter referred to as “Yang”)).
Regarding claim 9, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 4 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory),
wherein the generate a fingerprint and a location estimate from the relative signal strength indicator signal (Kamal; section 2.4.1 paragraph 3, section 4.2 paragraph 4 - - Kamal teaches utilizing the Fingerprinting technique (a ML model) to predict the user’s location based on RSSI data. Further, Kamal teaches the proximity algorithm uses RSSI values to infer user’s position. This would ideally be executed within the smart phone).
comprises a machine learning algorithm (Kamal; section 2.6.6. paragraph 2 - - Kamal teaches certain algorithms are required along with Machine Learning and Deep Learning algorithms to extract accurate location information from multimodal data.
and a random forest-based classification model (Kamal; section 5.2 paragraph 4 - - The Machine Learning model chosen was the Random Forest classifier).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the invention of Kamal to include the feature of storing the machine learning algorithm and random forest-based classification model in a non-volatile memory, in order to save the random forest classifier and its trained parameters so they are not lost when the system is turned off, thereby allowing the model to extract accurate location information from multimodal RSSI data without requiring the system to be retrained after a system (see Joo paragraph 0044).
The combination of Kamal and Joo fails to clearly specify wherein the model is trained to detect a grid location of each of the devices at each time period (interpreted as a moment in time).
However, Yang teaches wherein the model is trained to detect a grid location of each of the devices at each time period (interpreted as a moment in time) (Yang; section 4.1 paragraph 2, fig. 4 - -Yang teaches a training phase and a positioning phase. The 1D CNN model is trained using the training dataset in the training phase. Next, the trained model is used to predict the location of the target from the input data. Figure 4 shows the grids with unit size of 1m x 1m).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Yang into the invention of Kamal and Joo to include the features of a random forest-based classification model, in order to improve the accuracy of grid location detection by replacing the 1D CNN model with a random forest classifier trained to detect the grid location of each device at each time period, thereby providing a more robust and accurate indoor positioning system that can effectively predict locations across the grid space shown in figure 4 of Yang (see section 4.1).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Kamal (Anonymous Multi-User Tracking in Indoor Environment Using Computer Vision and Bluetooth), publication date Fall 2021, [online] URL: https://www.proquest.com/docview/2631909061?fromopenview=true&pq-origsite=gscholar&fromunauthdoc=true&sourcetype=Dissertations%20&%20Theses (Year: 2021) (hereinafter referred to as “Kamal”), in view of Joo KR 101233841 B1 as applied to claim 11 above, further in view of Jain (Low-cost BLE based Indoor Localization using RSSI Fingerprinting and Machine Learning), publication date 11 May 2021, [online] URL: https://ieeexplore.ieee.org/abstract/document/9419388?casa_token=HA5p_juNVwAAAAAA:s_tgPIJTpEVmFwBzxb9cFERJjULsOhddElnEXpryEjUevJcFaqLuUNKmj24xzIBljSGcUZyT (Year: 2021) (hereafter referred to as “Jain”)).
Regarding claim 17, the combination of Kamal and Joo teaches the non-transitory computer medium of claim 11 (Joo; paragraph 0044 - - Joo teaches various programs required for the operation of the device (100) can be stored in the storage unit (140), which is a non-volatile memory).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Joo into the system of Kamal to include the non-transitory computer medium, thereby enabling reliable retrieval of information without requiring recomputation upon system restart (see Joo paragraph 0044).
The combination of Kamal and Joo fail to teach wherein the instructions provide an average Object Localization Error from about 37% to about 43%.
However, Jain teaches wherein the instructions provide an average Object Localization Error from about 37% to about 43% (Jain; section B, experimental results, and table I - - Jain teaches the raw experimental results of the random forest have a 39% error).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have incorporated the teachings of Jain into the invention of Kamal and Joo to include the feature of the instructions providing an average Object Localization Error from about 37% to about 43%, in order to establish a baseline Object Localization Error for the random forest classifier operating on raw RSSI fingerprint data, thereby allowing the system to quantify the reduction in localization error achievable through data augmentation and identify the performance improvement needed to reach the 4% error achieved with augmented data (see section B in Jain).
Allowable Subject Matter
Claims 10 and 16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. More specifically, Kamal, Joo, the other cited references, and a thorough search in the art fail to disclose or suggest providing an Object Localization Accuracy comprising a fraction of cells for which the predicted grid cell matches the ground truth grid cell of the object, wherein the Object Localization Accuracy comprises a formula: OLA =, wherein a is the total number of accurately predicted grid cells over the trajectory for object, I is the total number of grid cells for trajectories for object during the scenario, and n is the total number objects.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDRES RAFAEL SANCHEZ whose telephone number is (571)272-8776. The examiner can normally be reached 7:30-9:00.
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, Anthony Addy can be reached at 571-272-7795. 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.
/ANDRES RAFAEL SANCHEZ/Examiner, Art Unit 2645
/ANTHONY S ADDY/Supervisory Patent Examiner, Art Unit 2645
Prosecution Insights