DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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.
Examiner’s Note
This Office Action is in response to amendment filed on 9/3/2026, where claims 1, 9, and 22 are amended, claims 10, 13, and 19 are canceled, claims 24 and 25 are added, and claims 1-9, 11, 16, 22, 24, and 25 are currently pending.
Response to Arguments
Applicant’s arguments, see pg. 6, filed on 9/3/2026, with respect to previous rejections of claims 10, 13, and 19 under 35 U.S.C. § 103, have been fully considered and are persuasive in view of the amendment. As such, the rejections are withdrawn.
Applicant’s arguments, see pg. 6-7, with respect to previous rejection of independent claims 1 and 22 under 35 U.S.C. § 103, have been fully considered and are persuasive in view of the amendment. As such, the instant claims are currently rejected under new grounds in view of the amendment.
Applicant’s arguments, see pg. 6-8, that all dependent claims are patentably distinguished over the cited prior art at least in view of the dependency from their respective independent claims, and requests that the rejections for all dependent claims be reconsidered and withdrew for the reasons argued above. However, their respective independent claim is now rejected under new grounds in view of the amendment and thus the dependent claims are likewise rejected.
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 of this title, 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 1-3, 5, 6, 9, 16, 22, 24, and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Hunt et al., (US 2020/0384506 A1) (hereinafter Hunt) in view of Oppolzer et al., (US 2024/0241524 A1) (hereinafter Oppolzer).
Referring to claim 1, Hunt teaches a system for characterizing earthen material in an earthen material processing system comprising:
a spectral imager positioned in view of earthen material moving within the earthen material processing system, the spectral imager configured to acquire spectral image data of a spatial scene of the earthen material (¶ [0051], fig. 1A, “In one implementation the ore composition imaging system 100 is integrated after the ore is initially crushed, while it is being transported for further processing. The ore composition imaging system 100 can include an image capture system 102, which records video and/or still images of ore fragments 110 as they travel between two locations in an ore processing facility.” ¶ [0052], “The image data can include, but is not limited to…hyperspectral images”);
a processor in communication with the spectral imager, the processor programmed with a machine learned model that is configured to process the spectral image data to identify a portion of the earthen material…, the processor outputting a signal based on the identification (¶ [0051], fig. 1A, “The images from the image capture system can then be used as input to a computing system 108 that includes a machine learning model. The machine learning model can determine, using measured parameters of the ore fragments 110 ore characteristics, which can be used to adjust or modify the operation of the processing facility.”).
Hunt teaches the limitations above. However, Hunt does not explicitly teach identify a portion of the earthen material containing a clay-rich composition based on the spectral image data and in response to receiving the signal, a sorting system located in-line with a feed conveyor configured to segregate the portion of the earthen material containing the clay-rich composition from other earthen material in response to the signal.
Oppolzer teaches identify a portion of the earthen material containing a clay-rich composition based on the spectral image data and in response to receiving the signal, a sorting system located in-line with a feed conveyor configured to segregate the portion of the earthen material containing the clay-rich composition from other earthen material in response to the signal (¶ [0333], fig. 18, “conveyor loader 218 includes a conveyor belt 226 and a hopper 230 wherein conveyor belt 226 transfers raw material 210 to hopper 228 which funnels raw material 210 into one of the plurality of haul trucks 16. Sensing device 220 is positioned such that it senses chemical properties of raw material 210 on conveyor belt 226…conveyor loader 218 includes a diverter and multiple conveyor belts and hoppers such that raw material 210 is sensed on a first conveyor belt and then a diverter is used to divert material to different hoppers and/or conveyor belts based on the determined category of raw material 210 for subsequent loading into different ones of haul truck 16.” ¶ [0341], “sensing device 220 is configured to sense either the concentration of desired material or the concentration of deleterious material.” ¶ [0352], “The blasted material is optionally sorted into classification grades. Sorted material can then be loaded into different haulage trucks. For example, if the blasted material is simply sorted into high grade and low grade ore, then high grade ore is loaded into a first truck and low grade ore is loaded into a second truck. This allows the high grade ore and low grade ore to be directed to different stockpiles for different processing. Sorting of the blasted material may be based, for example, on hyperspectral imaging”. ¶ [0358], “certain sub-area of second location 206 (say, the south side) is dumped with another certain category with certain quality properties, such as high-phosphor, high-clay material.”)
Hunt and Oppolzer are analogous art to the claimed invention because they are concerning with facilities for processing earthen material (i.e., same field of endeavor).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention having Hunt and Oppolzer before them to modify the machine learning model of Hunt to incorporate the function of sorting material based on a signal by Oppolzer. One of ordinary skill in the art would have combined the elements as claimed by known methods as disclosed by Oppolzer (¶ [0333]-[0358]), because the function of sorting material based on a signal does not depend on the machine learning model. That is the function of sorting material based on a signal performs the same function independent on which interface it is incorporated onto, and therefore, the result of the combination would have been predictable to one of ordinary skill in the art. The motivation to combine would have been to separate desired material from deleterious material as suggested by Oppolzer (¶ [0341]).
Referring to claim 2, Hunt further teaches the system of claim 1, wherein the spectral imager is configured to acquire the spectral image data while the earthen material is moving (¶ [0051], fig. 1A, “In one implementation the ore composition imaging system 100 is integrated after the ore is initially crushed, while it is being transported for further processing.”)
Referring to claim 3, Hunt further teaches the system of claim 1, wherein the earthen material processing system includes a conveyor, and the spectral imager is mounted over the conveyor (According to figure 1A, the imaging capture system 102 is mounted over the transport system 114).
Referring to claim 5, Hunt further teaches the system of claim 1, wherein the spectral imager captures successive captures of spectral data that are aggregated by the spectral imager or the processor to form the spectral image data (¶ [0051], “The images from the image capture system can then be used as input to a computing system 108 that includes a machine learning model. The machine learning model can determine, using measured parameters of the ore fragments 110 ore characteristics”).
Referring to claim 6, Hunt further teaches the system of claim 1, wherein the machine learned model includes a convolutional neural network (¶ [0076], “the machine learning model 204 is a convolutional neural network.”)
Referring to claim 9, Hunt further teaches the system of claim 1, wherein the processor is further configured to process the spectral image data to determine at least one earthen material characteristic including a moisture content of the earthen material (¶ [0010], “In an aspect combinable with any one of the previous aspects, the one or more characteristics includes at least one of…fragment moisture content”).
Referring to claim 16, Hunt further teaches the system of claim 1, further comprising one or more illumination sources positioned and oriented to direct illumination toward the earthen material for reflection by the earthen material to the spectral imager (¶ [0051], fig. 1A, “The ore composition imaging system 100 can optionally include an illumination system 104”).
Referring to claim 24, Hunt teaches the system of claim 1. However, Hunt does not explicitly teach the sorting system is configured to direct the portion of the earthen material containing the clay-rich composition to a stockpile separate from the other earthen material.
Oppolzer further teaches the sorting system is configured to direct the portion of the earthen material containing the clay-rich composition to a stockpile separate from the other earthen material (¶ [0352], “The blasted material is optionally sorted into classification grades. Sorted material can then be loaded into different haulage trucks. For example, if the blasted material is simply sorted into high grade and low grade ore, then high grade ore is loaded into a first truck and low grade ore is loaded into a second truck. This allows the high grade ore and low grade ore to be directed to different stockpiles for different processing.)
Referring to claim 25, Hunt teaches the system of claim 1. However, Hunt does not explicitly teach wherein the earthen material is transported by a haulage vehicle and the processor is configured to communicate sorting instructions to the haulage vehicle or to a driver of the haulage vehicle in response to identifying the clay-rich composition and the sorting instructions cause a load of the haulage vehicle containing the clay-rich to be segregated.
Oppolzer further teaches the earthen material is transported by a haulage vehicle and the processor is configured to communicate sorting instructions to the haulage vehicle or to a driver of the haulage vehicle in response to identifying the clay-rich composition and the sorting instructions cause a load of the haulage vehicle containing the clay-rich to be segregated (¶ [0027], “in response to identifying that loading of the first hauler is complete, controlling the plurality of loaders to cease loading of the first hauler; and communicating an instruction to the first hauler to move to a determined first unloading location for unloading of the loaded mined material, wherein the first unloading location is determined, at least in part, according to the first material category of mined material loaded into the first hauler.”)
Regarding claim 22, these claims recite the method performed by the system of claim 1; therefore, the same rationale of rejection is applicable.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Hunt in view of Oppolzer as applied to claim 3 above, and further in view of Brogger et al., (US 2022/0334054 A1) (hereinafter Brogger).
Referring to claim 4, Hunt further teaches the system of claim 3, wherein a second spectral imager is mounted on a…route to scan a top surface… (¶ [0056], “The ore can be transported via a number of techniques, such as…train/cart and rail, barges”).
Hunt in view of Oppolzer teach the limitations above. However, Hunt in view of Oppolzer do not explicitly teach haulage truck.
Brogger teaches a haulage truck (¶ [0170], figs. 13-14b, “Imaging device 234 captures visual images and multispectral, preferably hyperspectral, images of each truck 222 and 230 as each truck respectively enters the field of view 236 of the imaging device.”)
Hunt, Oppolzer, and Brogger are analogous art to the claimed invention because they are concerning with equipment for carrying objects (i.e., same field of endeavor).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention having Hunt in view of Oppolzer and Brogger before them to substitute the truck as taught by Brogger for the generic carrier of Hunt in view of Oppolzer. Because both Hunt and Brogger teach methods of transporting objects, it would have been obvious to one skilled in the art to substitute one known method for the other to achieve the predictable result of object transportation technology. The motivation would have been to pick the mode of transporting objects that best suited for the user’s needs.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Hunt in view of Oppolzer as applied to claim 1 above, and further in view of Coen et al., (US 2022/0307971 A1) (hereinafter Coen).
Referring to claim 7, Hunt in view of Oppolzer teach the system of claim 1. Hunt further teaches performing image enhancement prior to recording of the plurality of images (¶ [0023]). However, Hunt in view of Oppolzer do not explicitly teach preprocess the spectral image data to perform radiometric or geometric corrections prior to processing by the machine learned model.
Coen teaches preprocess the spectral image data to perform radiometric or geometric corrections prior to processing by the machine learned model (¶ [0194], “Preprocessing may include lighting and/or measurement correction step 240. Step 240 may comprise radiometric correction”).
Hunt, Oppolzer, and Coen are analogous art to the claimed invention because they are concerning with interface for capturing and processing spectral images (i.e., same field of endeavor).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention having Hunt in view of Oppolzer and Coen before them to modify the processing facility of Hunt in view of Oppolzer to incorporate the function of performing radiometric correction preprocessing by Coen. One of ordinary skill in the art would have combined the elements as claimed by known methods as disclosed by Coen (¶ [0185]-[0196]), because the function of performing radiometric correction preprocessing does not depend on the processing facility. That is the function of performing radiometric correction preprocessing performs the same function independent on which interface it is incorporated onto, and therefore, the result of the combination would have been predictable to one of ordinary skill in the art. The motivation to combine would have been to normalizing image values to create uniform basis for spectral signatures as suggested by Coen (¶ [0220]).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Hunt in view of Oppolzer as applied to claim 1 above, and further in view of Qiu et al., (CN 114639009 B) (hereinafter Qiu).
Referring to claim 8, Hunt in view of Oppolzer teach the system of claim 1. However, Hunt in view of Oppolzer do not explicitly teach perform dimensionality reduction on the spectral image data prior to processing by the machine learned model.
Qiu teaches perform dimensionality reduction on the spectral image data prior to processing by the machine learned model (Abstract, “The invention discloses a longan dry variety classification method and device based on hyperspectral image and machine learning, the method comprises: taking multiple different samples of the same variety of longan as a group to perform hyperspectral imaging to obtain a hyperspectral image set; pre-processing the images of all high-spectrum image sets to obtain a longan dry high-spectrum sample set; marking the types of different types of longan dry images in the high spectrum sample set; performing data dimension reduction on the hyperspectral sample set to obtain a data set after dimension reduction; respectively leading the data set after dimension reduction into SVM and KNN learning models to supervise and learn”).
Hunt, Oppolzer, and Qiu are analogous art to the claimed invention because they are concerning with interface for processing captured images (i.e., same field of endeavor).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention having Hunt in view of Oppolzer and Qiu before them to modify the processing facility of Hunt in view of Oppolzer to incorporate the function of performing dimension reduction by Qiu. One of ordinary skill in the art would have combined the elements as claimed by known methods as disclosed by Qiu (pg. 10 lines 7-32), because the function of performing dimension reduction does not depend on the processing facility. That is the function of performing dimension reduction performs the same function independent on which interface it is incorporated onto, and therefore, the result of the combination would have been predictable to one of ordinary skill in the art. The motivation to combine would have been to reduce training difficulties of model as suggested by Qiu (pg. 10 lines12-14).
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Hunt in view of Oppolzer as applied to claim 9 above, and further in view of Xu et al., (CN 113310949 A) (hereinafter Xu).
Referring to claim 11, Hunt in view of Oppolzer teach the system of claim 9. However, Hunt in view of Oppolzer do not explicitly teach a second spectral imager is located within a reclaim tunnel of the earthen material processing system.
Xu teaches a second spectral imager is located within a reclaim tunnel of the earthen material processing system (Pg. 2 lines 61-65, “The invention claims a TBM tunnel carrying type rock slag mineral identification system and method based on high spectrum imaging, comprising a conveying belt; the conveying belt is orderly provided with…a high spectrum imaging device”).
Hunt, Oppolzer, and Xu are analogous art to the claimed invention because they are concerning with facilities for processing ore (i.e., same field of endeavor).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention having Hunt in view of Oppolzer and Xu before them to modify the processing facility of Hunt in view of Oppolzer to incorporate the function of providing a high spectrum imaging device in the tunnel by Xu. One of ordinary skill in the art would have combined the elements as claimed by known methods as disclosed by Xu (pg. 2 lines 61-75), because the function of providing a high spectrum imaging device in the tunnel does not depend on the processing facility. That is the function of providing a high spectrum imaging device in the tunnel performs the same function independent on which interface it is incorporated onto, and therefore, the result of the combination would have been predictable to one of ordinary skill in the art. The motivation to combine would have been to ensure quick analyze mineral content information as suggested by Xu (pg. 2 lines 61-75).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
US 2011/0317001 (Massen) – discloses multisensory array for optically inspecting and sorting bulk materials.
US 2012/0306257 (Silversides) – discloses method and system for determining rock types using hyperspectral images.
US 2007/0263212 (Mound) – discloses system for processing bulk materials.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MONG-SHUNE CHUNG whose telephone number is (571)270-5817. The examiner can normally be reached on M-F (9-5) EST.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Scott Baderman, can be reached at telephone number (571)270-5817. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR for authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/MONG-SHUNE CHUNG/
Primary Examiner, Art Unit 2118