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 .
Status of Claims
This Office action is in response to correspondence received June 27, 2025.
Claims 1-16 are pending and have been examined.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
Claim 13:
A meat grading system, configured to perform the meat grading method according to claim 1
a meat imaging detection device configured to acquire the multi-dimensional meat imaging information of the meat piece
a true value data acquisition device configured to acquire the grading true value data of the meat piece
Claim 16:
A manual measurement device configured to segment the meat piece and directly measure at least one segmented part
A high-precision imaging device configured to acquire a high precision imaging information
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Structure for the 1121(f) substitutes is found in the following:
A meat grading system, configured to perform the meat grading method according to claim 1, in par 31: “As shown in FIG. 1, the meat grading system 1000 may include a meat imaging detection device 10, a true value data acquisition device 20, and a grading indicator parameter model 30.”
a meat imaging detection device configured to acquire the multi-dimensional meat imaging information of the meat piece
In par 33: “As an example, the meat imaging detection device 10 may include any one of an X-ray imaging device, a visible light imaging device, an infrared imaging device and an ultrasonic imaging device, and any combination thereof. By way of example, the meat imaging information MD may include any one of a computer tomography (CT) image, a digital radiography (DR) image and the like. However, the
embodiments of the present disclosure are not limited thereto.”
a true value data acquisition device configured to acquire the grading true value data of the meat piece in pars 036-038 which can be a manual measurement device; a high-precision imaging device; or an image processing device.
Claim 16:
A manual measurement device configured to segment the meat piece and directly measure at least one segmented part does not appear to have structural support in the specification.
A high-precision imaging device configured to acquire a high precision imaging information in par 37: “As an example, the high-precision imaging device may include a high-performance medical CT device.”
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 16 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
In MPEP 2163.03, if there is not sufficient structure to support the means plus function substitute in the claims, then the claim should be rejected for lack of written description:
A claim limitation expressed in means- (or step-) plus-function language "shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof." 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. If the specification fails to disclose sufficient corresponding structure, materials, or acts that perform the entire claimed function, then the claim limitation is indefinite because the applicant has in effect failed to particularly point out and distinctly claim the invention as required by 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph. In re Donaldson Co., 16 F.3d 1189, 1195, 29 USPQ2d 1845, 1850 (Fed. Cir. 1994) (en banc). Such a limitation also lacks an adequate written description as required by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, because an indefinite, unbounded functional limitation would cover all ways of performing a function and indicate that the inventor has not provided sufficient disclosure to show possession of the invention. See also MPEP § 2181.
As no structure was found for the A manual measurement device configured to segment the meat piece and directly measure at least one segmented part, this limitation (and thus claim 16) is rejected under 112(a).
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 16 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 limitation “A manual measurement device configured to segment the meat piece and directly measure at least one segmented part,” invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. A search of the specification found no structure for this limitation. Paragraph 36 describes how a person might use such a device, but does not describe the structure of the device itself. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
Therefore, claim 16 is rejected under 35 USC 112.
Claim Rejections - 35 USC § 101
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.
Claims 1-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim(s) recite(s):
Claims 1 and 13, which are similar in scope:
A meat grading method, comprising: acquiring a multi-dimensional meat imaging information of a meat piece; [taking measurement data] to acquire grading true value data of the meat piece; and calculating a grading indicator parameter calculation value based on the multi-dimensional meat imaging information, and training a grading indicator parameter model based on the grading indicator parameter calculation value and the grading true value data, so as to acquire a trained grading indicator parameter model.
The abstract idea above describes a mathematical relationship, see MPEP 2106.04(a)(2)(I) and Mental process, see MPEP 2106.04(a)(2)(II). This is because a “multi-dimensional meat imaging information” is acquired, therefore 2 or 3 dimensions, then a measurement is performed which under a broadest reasonable interpretation is a mental process step of observing; then calculating a value is a mathematical relationship. Finally, training the grading is a further mathematical relationship. For these reasons, the steps above are a mathematical relationship and mental process, and therefore a patent ineligible abstract idea.
This judicial exception is not integrated into a practical application. The additional elements are insignificant extra solution activity or apply it steps and therefore are not a practical application. Performing a high precision measurement (claims 1 and 13) is mere data gathering similar to determining the level of a biomarker in blood by any means, Mayo, see MPEP 2106.05(g). Then, the following elements are apply it elements (claim 13):
A meat grading system
meat imaging detection device
a true value data acquisition device
These elements are apply it because they are, in accordance with the structure in the specification, computers or ordinary machinery performing in its ordinary capacity. In combination the additional elements do not amount to a practical application because they use data acquisition devices (ie computers) to take data gathered (image and measurements) which is something within the ordinary capacity of these elements. Finally, considering the claims as a whole the additional elements are not a practical application because they merely gather data for or are applied to the abstract idea. Therefore for these reasons claims 1 and 13 do not recite a practical application of the abstract idea.
Claims 1 and 13 do not recite significantly more than the abstract idea. The apply it elements and their analysis is carried over, and then per performing a precision measurement this is similar to Mayo, see MPEP 2106.05(d), which was found to be well-understood, routine, and conventional. This is similar to Mayo because in both instances a precision measurement is performed. Wherein measuring biomarkers of blood is a precision measurement. For these reasons the additional elements of claims 1 and 13 do not recite significantly more than the abstract idea.
Per the dependent claims:
Claims 2-12, 14, and 15 further describe the abstract idea steps. Claim 12 and 16 describe segmenting the meat piece but this is insignificant extra solution activity, an insignificant application, similar to cutting hair after first determining the hair style, In re Brown, 645 Fed. App'x 1014, 1016-1017 (Fed. Cir. 2016) (non-precedential); See MPEP 2106.05(g) which is also well-understood, routine, and conventional, similar to Shuffling and dealing a standard deck of cards, In re Smith, 815 F.3d 816, 819, 118 USPQ2d 1245, 1247 (Fed. Cir. 2016).
Therefore, claims 1-16 are rejected under 35 USC 101.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-5, 13, and 14 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Aggarwal et al., US PGPUB 20210015113 A1 ("Aggarwal").
Per claims 1 and 13, which are similar in scope, Aggarwal teaches A meat grading method, comprising: acquiring a multi-dimensional meat imaging information of a meat piece In par 009: "Provided herein useful to ensuring quality of meat cuts. In some embodiments, a system for ensuring quality of meat cuts comprises a capture device, the capture device comprising an image capture device, wherein the image capture device is configured to capture an image of a cut of meat, a depth sensor, wherein the depth sensor is configured to capture depth data associated with the cut of meat,"
Aggarwal then teaches performing a high-precision measurement on the meat piece to acquire grading true value data of the meat piece In par 017: "The depth sensor 210 captures depth data associated with the cut of meat. The depth data can be, for example, the thickness of the cut of meat. The transceiver 212 transmits the image of the cut of meat and the depth data associated with the cut of meat to the control circuit 202. The microcontroller 214 controls the image capture device 208, the depth sensor 210, and the transceiver 212."
Aggarwal then teaches and calculating a grading indicator parameter calculation value based on the multi-dimensional meat imaging information In par 22: "The control circuit 202 receives the image of the cut of meat and the depth data associated with the cut of meat from the capture device 206 (e.g., via the transceiver 212). The control circuit evaluates the cut of meat based on the image of the cut of meat and the depth data associated with the cut of meat. This evaluation is performed based on a meat cut specification associated with the cut of meat. For example, if the cut of meat is a ribeye, the control circuit 202 evaluates the image of the cut of meat and the depth data associated with the cut of meat against a meat cut specification for a ribeye. The control circuit 202 retrieves the meat cut specification from the database 216. The control circuit 202 can evaluate the cut of meat based on any desired parameters, such a thickness, trimming, shape, alignment, etc. For example, the control circuit 202, based on the meat cut specification, can determine that the cut of meat is too thick or thin, has an undesirable or improper fat content, improperly trimmed (e.g., overtrimmed or undertrimmed), improperly shaped (e.g., square cow, hacked tail, etc.), misaligned (e.g., improperly positioned within the packaging), etc. The control circuit 202 classifies the cut of meat based on this evaluation. For example, if the evaluation determines that the cut of meat is too thick and undertrimmed, the control circuit 202 classifies the cut of meat as being too thick and undertrimmed."
Aggarwal then teaches and training a grading indicator parameter model based on the grading indicator parameter calculation value and the grading true value data, so as to acquire a trained grading indicator parameter model In par 23: ""In embodiments that include a training phase, the control circuit 202 can generate the meat cut specifications. That is, the control circuit 202 can receive images of cuts of meats that include markings. The markings indicate proper and/or improper cutting of the meat. The control circuit 202 analyzes the images including the markings using machine learning to generate the meat cut specifications. For example, the control circuit 202 can generate the meat cut specifications used in a neural network model. In such embodiments, the neural network model is trained based on the images including the markings."" [0013] As depicted in FIG. 1, a user is classifying the cut of meat based on the image 104 of the cut of meat. The user is classifying the cut of meat by providing markings 110 on the image 104 of the cut of meat. As depicted in FIG. 1, the user has included the marking 110 indicating that a section 106 of the cut of meat is undertrimmed. The user has provided this marking 110 and selected an undertrimmed selection 108. This association is depicted by an arrow 112 in FIG. 1. The user input classifying the meat can be used in a training phase. During the training phase, the user manually classifies meat via the mobile device 102. The image 104 of the cut of meat is used by the system to learn how to classify cuts of meat. For example, the system analyzes images of the cuts of meats including markings using a neural network model. Using machine learning, the system can evaluate and classify cuts of meat in an autonomous manner. The training phase can include any suitable number of images (e.g., 100, 200, 500, etc.).
[0014] In some embodiments, the mobile device 102 can present meat cut quality information after the training phase is complete. For example, the mobile device 102 can present meat cut quality information as classified in an autonomous manner. The presentation of the meat cut quality information can include an image (e.g., the image 104 of the cut of meat), markings created by the system, as well as indications of any quality issues or variations. In such embodiments, a user can verify the system's accuracy and/or consistency."
Per claims 2 and 14, which are similar in scope, Aggarwal teaches the limitations of claims 1 and 13, above. Aggarwal further teaches grading the meat piece based on a grading indicator parameter calculation value calculated by the trained grading indicator parameter model in par 022 : “The control circuit 202 receives the image of the cut of meat and the depth data associated with the cut of meat from the capture device 206 (e.g., via the transceiver 212). The control circuit evaluates the cut of meat based on the image of the cut of meat and the depth data associated with the cut of meat. This evaluation is performed based on a meat cut specification associated with the cut of meat. For example, if the cut of meat is a ribeye, the control circuit 202 evaluates the image of the cut of meat and the depth data associated with the cut of meat against a meat cut specification for a ribeye. The control circuit 202 retrieves the meat cut specification from the database 216. The control circuit 202 can evaluate the cut of meat based on any desired parameters, such a thickness, trimming, shape, alignment, etc. For example, the control circuit 202, based on the meat cut specification, can determine that the cut of meat is too thick or thin, has an undesirable or improper fat content, improperly trimmed (e.g., overtrimmed or undertrimmed), improperly shaped (e.g., square cow, hacked tail, etc.), misaligned (e.g., improperly positioned within the packaging), etc. The control circuit 202 classifies the cut of meat based on this evaluation. For example, if the evaluation determines that the cut of meat is too thick and undertrimmed, the control circuit 202 classifies the cut of meat as being too thick and undertrimmed.”
Per claim 3, Aggarwal teaches the limitations of claim 2, above. Aggarwal further teaches wherein the grading indicator parameter calculation value comprises at least a morphological and structural information and a composition information of the entire meat piece, and a morphological and structural information and a composition information of at least one part of the meat piece, and the method further comprises: grading the meat piece based on the morphological and structural information and the composition information required for grading with reference to a grading standard in 22: "he control circuit 202 can evaluate the cut of meat based on any desired parameters, such a thickness, trimming, shape, alignment, etc. For example, the control circuit 202, based on the meat cut specification, can determine that the cut of meat is too thick or thin, has an undesirable or improper fat content, improperly trimmed (e.g., overtrimmed or undertrimmed), improperly shaped (e.g., square cow, hacked tail, etc.), misaligned (e.g., improperly positioned within the packaging), etc. "
Per claim 4, Aggarwal teaches the limitations of claim 3, above. Aggarwal further teaches wherein the grading indicator parameter calculation value comprises a segmentation information of at least one part of the meat piece and a position information of at least one part of the meat piece in Par 22: ". For example, if the evaluation determines that the cut of meat is too thick and undertrimmed, the control circuit 202 classifies the cut of meat as being too thick and undertrimmed."
Per claim 5, Aggarwal teaches the limitations of claim 4, above. Aggarwal further teaches wherein the morphological and structural information comprises: at least one of a shape information, a length information, a width information, a thickness information or a weight information of the entire meat piece, and at least one of a shape information, a length information, a width information, a thickness information or a weight information of each of at least one part of the meat piece in par 22: The control circuit 202 can evaluate the cut of meat based on any desired parameters, such a thickness, trimming, shape, alignment, etc. For example, the control circuit 202, based on the meat cut specification, can determine that the cut of meat is too thick or thin, has an undesirable or improper fat content, improperly trimmed (e.g., overtrimmed or undertrimmed), improperly shaped (e.g., square cow, hacked tail, etc.), misaligned (e.g., improperly positioned within the packaging), etc."
Aggarwal then teaches and the composition information comprises: at least one of a mass percentage, a lean meat rate or a fat rate of the entire meat piece, and at least one of a mass percentage, a lean meat rate or a fat rate of each of at least one part of the meat piece in par 22: " has an undesirable or improper fat content."
Therefore, claims 1-5, 13, and 14 are rejected under 35 USC 102.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
Claim(s) 6 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Aggarwal et al., US PGPUB 20210015113 A1 ("Aggarwal") in view of Doros, US PGPUB 20240068952 A1 ("Doros").
Per claim 6, Aggarwal teaches the limitations of claim 1, above. Aggarwal does not teach wherein training the grading indicator parameter model comprises: calculating a difference between the grading indicator parameter calculation value and the grading true value data, and training the grading indicator parameter model by comparing the difference with a corresponding reference data.
Doros teaches a multi sensor test device for quality control scanning. See abstract.
Doros teaches wherein training the grading indicator parameter model comprises: calculating a difference between the grading indicator parameter calculation value and the grading true value data, and training the grading indicator parameter model by comparing the difference with a corresponding reference data in par 17: "In this case, the test system 106 may train a model to compare obtained measurements of a DUT with the set of reference measurements and predict or identify defects in the DUT based on a difference between the obtained measurements and the set of reference measurements. For example, the model may be trained to filter signal (e.g., relevant differences between the set of reference measurements and the obtained measurements, such as a shadow from a crack in a surface of a DUT) from noise (e.g., differences between the set of reference measurements and the obtained measurements that may not correlate with a defect, such as a difference in image brightness or a presence of a shadow of an operator in an image). In some implementations, the test system 106 may train and/or obtain a computer vision model. For example, the test system 106 may use a computer vision model with feature engineering to analyze image data regarding the DUT and identify aspects, characteristics, and/or features of the DUT that may correspond to defects."
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the finding difference between reference and obtained measurements in order to train a model teaching of Doros because Doros teaches in par 011 that: “Moreover, by using one or more artificial intelligence models to analyze sensor data from multiple types of sensors, the multi-sensor test device increases a likelihood of successfully detecting defects, thereby reducing a likelihood of deploying defecting DUTs, components, or other objects. By reducing a likelihood of deploying DUTs, components, or other objects with defects, the multi-sensor test device reduces a wastage of resources associated with replacement or repair of defective DUTs, components, or other objects.” As defects are increasingly likely to be detected, one would be motivated to modify Aggarwal with Doros.
Per claim 7, Aggarwal and Doros teach the limitations of claim 6, above. Aggarwal does not teach wherein training the grading indicator parameter model further comprises: when the difference is greater than the reference data, updating model parameters of the grading indicator parameter model to recalculate the grading indicator parameter calculation value, comparing the difference between the recalculated grading indicator parameter calculation value and the grading true value data with the reference data, and repeating calculation and comparison until the difference is less than or equal to the reference data.
Doros teaches wherein training the grading indicator parameter model further comprises: when the difference is greater than the reference data, updating model parameters of the grading indicator parameter model to recalculate the grading indicator parameter calculation value, comparing the difference between the recalculated grading indicator parameter calculation value and the grading true value data with the reference data, and repeating calculation and comparison until the difference is less than or equal to the reference data [0022] As shown in FIG. 1D, and by reference number 170, the test device 108 may provide output associated with processing the set of measurements. For example, the test device 108 may provide, to a client device 114 (e.g., for display to a user), output identifying a defect identified with the DUT 112. Additionally, or alternatively, the test device 108 may provide, to the test system 106, new measurement data identifying the set of measurements (e.g., to enable the test system 106 to update the one or more models). [0033] As an example, the machine learning system may obtain training data for the set of observations based on a set of measurements performed by a set of different sensors and collected by test data source 340. Additionally, or alternatively, the machine learning system may obtain training data for the set of observations by test device 330. For example, when the test device 330 performs a set of measurements (and performs a defect detection determination using a first set of model parameters from the machine learning system), the test device 330 may provide the set of measurements to enable the machine learning system to generate an updated set of model parameters (and output the updated set of model parameters to the test device 330 to enable more accurate subsequent determinations by the test device 330).
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the finding difference between reference and obtained measurements in order to train a model teaching of Doros because Doros teaches in par 011 that: “Moreover, by using one or more artificial intelligence models to analyze sensor data from multiple types of sensors, the multi-sensor test device increases a likelihood of successfully detecting defects, thereby reducing a likelihood of deploying defecting DUTs, components, or other objects. By reducing a likelihood of deploying DUTs, components, or other objects with defects, the multi-sensor test device reduces a wastage of resources associated with replacement or repair of defective DUTs, components, or other objects.” As defects are increasingly likely to be detected, one would be motivated to modify Aggarwal with Doros.
Claim(s) 8-12, 15, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Aggarwal et al., US PGPUB 20210015113 A1 ("Aggarwal") in view of Welwitigoda et al., US PGPUB 20230343069 A1 ("Welwitigoda").
Per claim 8, Aggarwal teaches the limitations of claim 1, above. Aggarwal does not teach wherein calculating the grading indicator parameter calculation value comprises: performing, by the grading indicator parameter model, image processing on the meat imaging information to segment the meat imaging information, and calculating, by the grading indicator parameter model, the grading indicator parameter calculation value based on the segmented meat imaging information.
Weltwitigoda teaches a meat identification system. See abstract.
Weltwitigoda teaches wherein calculating the grading indicator parameter calculation value comprises: performing, by the grading indicator parameter model, image processing on the meat imaging information to segment the meat imaging information, and calculating, by the grading indicator parameter model, the grading indicator parameter calculation value based on the segmented meat imaging information in [0053] The database 14 includes run data 21, one or more training datasets 31 and one or more test datasets 41. The run data 21, for example, can include information associated with operation of the system 10-1 and its components, and can include information obtained by the system 10-1 concerning the cuts of meat 18 and stored to the run data 21. Moreover, the run data refers to any data associated with configuration of the meat identification system 10, and any post-operation outputs of the system 10. These can include: the image data 24 that the imaging system 20 obtains during run-time operation, and any information that the system 10 extracts or calculates from the image data (such as the predicted class of meat for each cut of meat) and/or is otherwise related to the image data, in examples. This information is typically stored in the form of time-stamped records to the run data 21 for later analysis and comparison.
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the segmenting the image teaching of Weltwitigoda because Weltwitigoda teaches in par 16 that “To facilitate identification, the classification system may be configured to segment the at least one frame to produce segmented information, and subsequently form a bounding box around the cut of meat using the segmented information. The classification system can then extract pixels of the cut of meat enclosed by the bounding box into an instance of object data for the cut of meat.” As Aggarwal is identifying meat which, as Aggarwal teaches, identifying characteristics of meat, one would be motivated by Weltwitigoda’s teaching because one would want to facilitate identification, as specifically taught in par 16. As this is done through segmentation, one would be motivated to combine this specific teaching which would facilitate identification. For these reasons one would be motivated to modify Aggarwal with Weltwitigoda.
Per claim 9, Aggarwal teaches the limitations of claim 1, above. Aggarwal further teaches wherein calculating the grading indicator parameter calculation value comprises: and calculating, by the grading indicator parameter model, the grading indicator parameter calculation value in par 22: “The control circuit 202 can evaluate the cut of meat based on any desired parameters, such a thickness, trimming, shape, alignment, etc. For example, the control circuit 202, based on the meat cut specification, can determine that the cut of meat is too thick or thin, has an undesirable or improper fat content, improperly trimmed (e.g., overtrimmed or undertrimmed), improperly shaped (e.g., square cow, hacked tail, etc.), misaligned (e.g., improperly positioned within the packaging), etc. "
Aggarwal does not teach receiving, by the grading indicator parameter model, a meat imaging information which is segmented by image processing, based on the segmented meat imaging information. Weltwitigoda teaches receiving, by the grading indicator parameter model, a meat imaging information which is segmented by image processing, based on the segmented meat imaging information in [0096] In step 408, the segmentation phase, the classification module 180 segments the image data 24. In more detail, the classification module 180 detects one or more cuts of meat 18 in the frame of image data 24 and creates bounding boxes around the cuts of meat 18. In one example, the classification module 180 extracts the bounding boxes of each cut of meat 18 that is fully within the field of view 23 by generating a semantic mask for each. To achieve this, logic and/or a deep learning model is specifically trained to generate semantic masks of the cuts of meat 18 from the frame of RGB image data 24 as the cuts of meat lay on the conveyor belt 76 and in the field of view 23. These semantic masks may be used to convert to corresponding bounding boxes.
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the segmenting the image teaching of Weltwitigoda because Weltwitigoda teaches in par 16 that “To facilitate identification, the classification system may be configured to segment the at least one frame to produce segmented information, and subsequently form a bounding box around the cut of meat using the segmented information. The classification system can then extract pixels of the cut of meat enclosed by the bounding box into an instance of object data for the cut of meat.” As Aggarwal is identifying meat which, as Aggarwal teaches, identifying characteristics of meat, one would be motivated by Weltwitigoda’s teaching because one would want to facilitate identification, as specifically taught in par 16. As this is done through segmentation, one would be motivated to combine this specific teaching which would facilitate identification. For these reasons one would be motivated to modify Aggarwal with Weltwitigoda.
Per claim 10, Aggarwal teaches the limitations of claim 8, above. Aggarwal does not teach wherein the image processing comprises at least one of image segmentation and positioning processing, image noise reduction processing, or image enhancement processing
Weltwitigoda teaches wherein the image processing comprises at least one of image segmentation and positioning processing, image noise reduction processing, or image enhancement processing in [0096] In step 408, the segmentation phase, the classification module 180 segments the image data 24. In more detail, the classification module 180 detects one or more cuts of meat 18 in the frame of image data 24 and creates bounding boxes around the cuts of meat 18. In one example, the classification module 180 extracts the bounding boxes of each cut of meat 18 that is fully within the field of view 23 by generating a semantic mask for each. To achieve this, logic and/or a deep learning model is specifically trained to generate semantic masks of the cuts of meat 18 from the frame of RGB image data 24 as the cuts of meat lay on the conveyor belt 76 and in the field of view 23. These semantic masks may be used to convert to corresponding bounding boxes.
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the segmenting the image teaching of Weltwitigoda because Weltwitigoda teaches in par 16 that “To facilitate identification, the classification system may be configured to segment the at least one frame to produce segmented information, and subsequently form a bounding box around the cut of meat using the segmented information. The classification system can then extract pixels of the cut of meat enclosed by the bounding box into an instance of object data for the cut of meat.” As Aggarwal is identifying meat which, as Aggarwal teaches, identifying characteristics of meat, one would be motivated by Weltwitigoda’s teaching because one would want to facilitate identification, as specifically taught in par 16. As this is done through segmentation, one would be motivated to combine this specific teaching which would facilitate identification. For these reasons one would be motivated to modify Aggarwal with Weltwitigoda.
Per claims 11 and 15, which are similar in scope, Aggarwal and Weltwitigoda teach the limitations of claim 8 (per claim 10) and Aggarwal teaches the limitations of claim 13, above. Aggarwal does not teach further comprising: training an image segmentation and positioning model using the meat imaging information and a part of the grading truth data, and providing a part of the grading indicator parameter calculation value based on the meat imaging information using an output of the trained image segmentation and positioning model.
Weltwitigoda teaches further comprising: training an image segmentation and positioning model using the meat imaging information and a part of the grading truth data, and providing a part of the grading indicator parameter calculation value based on the meat imaging information using an output of the trained image segmentation and positioning mode in [0104] In more detail, the object tracking module 186 might access the object data obtained for each frame of image data 24 in the tracking group, and for the same cut of meat 18, select the highest confidence score among the instances of object data for the same cut of meat. The classification system 40 can then use the selected confidence score to update/finalize the prediction of the class of meat 42 for the cut of meat 18. [0102] According to step 416, the object tracking module 186 tracks the objects (i.e. the object data for the cuts of meat 18) across the frames of image data 24 in the tracking group, using the references to the object data in the tracking group. The object tracking module 186 can then generate a final prediction of the classes of meat 42 encountered over the timeframe of the tracking group, based upon the confidence scores of the object data in the tracking group. Accordingly, a final prediction 42 with the highest confidence score for a given cut of meat 18 may be used to identify the cut of meat 18 itself. This has the effect of increasing the overall accuracy of the classification system 40.
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the segmenting the image teaching of Weltwitigoda because Weltwitigoda teaches in par 16 that “To facilitate identification, the classification system may be configured to segment the at least one frame to produce segmented information, and subsequently form a bounding box around the cut of meat using the segmented information. The classification system can then extract pixels of the cut of meat enclosed by the bounding box into an instance of object data for the cut of meat.” As Aggarwal is identifying meat which, as Aggarwal teaches, identifying characteristics of meat, one would be motivated by Weltwitigoda’s teaching because one would want to facilitate identification, as specifically taught in par 16. As this is done through segmentation, one would be motivated to combine this specific teaching which would facilitate identification. For these reasons one would be motivated to modify Aggarwal with Weltwitigoda.
Per claims 12 and 16, which are similar in scope, Aggarwal teaches the limitations of claims 1 and 13, above. Aggarwal further teaches wherein the high-precision measurement comprises: acquiring the grading truth data of the meat piece using a high-precision imaging device In par 23: ""In embodiments that include a training phase, the control circuit 202 can generate the meat cut specifications. That is, the control circuit 202 can receive images of cuts of meats that include markings. The markings indicate proper and/or improper cutting of the meat. The control circuit 202 analyzes the images including the markings using machine learning to generate the meat cut specifications. For example, the control circuit 202 can generate the meat cut specifications used in a neural network model. In such embodiments, the neural network model is trained based on the images including the markings."" [0013] As depicted in FIG. 1, a user is classifying the cut of meat based on the image 104 of the cut of meat. The user is classifying the cut of meat by providing markings 110 on the image 104 of the cut of meat. As depicted in FIG. 1, the user has included the marking 110 indicating that a section 106 of the cut of meat is undertrimmed. The user has provided this marking 110 and selected an undertrimmed selection 108. This association is depicted by an arrow 112 in FIG. 1. The user input classifying the meat can be used in a training phase. During the training phase, the user manually classifies meat via the mobile device 102. The image 104 of the cut of meat is used by the system to learn how to classify cuts of meat. For example, the system analyzes images of the cuts of meats including markings using a neural network model. Using machine learning, the system can evaluate and classify cuts of meat in an autonomous manner. The training phase can include any suitable number of images (e.g., 100, 200, 500, etc.)."
Aggarwal further teaches and measuring the at least one part independently to acquire the grading truth data of the meat piece [0014] In some embodiments, the mobile device 102 can present meat cut quality information after the training phase is complete. For example, the mobile device 102 can present meat cut quality information as classified in an autonomous manner. The presentation of the meat cut quality information can include an image (e.g., the image 104 of the cut of meat), markings created by the system, as well as indications of any quality issues or variations. In such embodiments, a user can verify the system's accuracy and/or consistency.
Aggarwal does not teach and/or segmenting the meat piece to acquire at least one part of the meat piece
Weltwitigoda teaches and/or segmenting the meat piece to acquire at least one part of the meat piece in [96] In step 408, the segmentation phase, the classification module 180 segments the image data 24. In more detail, the classification module 180 detects one or more cuts of meat 18 in the frame of image data 24 and creates bounding boxes around the cuts of meat 18. In one example, the classification module 180 extracts the bounding boxes of each cut of meat 18 that is fully within the field of view 23 by generating a semantic mask for each. To achieve this, logic and/or a deep learning model is specifically trained to generate semantic masks of the cuts of meat 18 from the frame of RGB image data 24 as the cuts of meat lay on the conveyor belt 76 and in the field of view 23. These semantic masks may be used to convert to corresponding bounding boxes.[0103] In this way, the classification system 40 can obtain a predicted class of meat 42 based on the image data 24 to identify the cut of meat, and obtain a range of successive frames of image data that include the cut of meat as the meat moves along the path 11. The classification system 40 can then use information relating to the cut of meat obtained across the range of frames of image data (e.g., the metadata of the instances of object data in the tracking group, for the range of frames) to finalize the prediction of the class of meat 42.
Under a broadest reasonable interpretation, segmenting the meat piece is taught by segmenting the image of the meat piece.
It would have been obvious to one ordinarily skilled in the art before the effective filing date of the claimed invention to modify the meat image analysis, modeling, and training teaching of Aggarwal with the segmenting the image teaching of Weltwitigoda because Weltwitigoda teaches in par 16 that “To facilitate identification, the classification system may be configured to segment the at least one frame to produce segmented information, and subsequently form a bounding box around the cut of meat using the segmented information. The classification system can then extract pixels of the cut of meat enclosed by the bounding box into an instance of object data for the cut of meat.” As Aggarwal is identifying meat which, as Aggarwal teaches, identifying characteristics of meat, one would be motivated by Weltwitigoda’s teaching because one would want to facilitate identification, as specifically taught in par 16. As this is done through segmentation, one would be motivated to combine this specific teaching which would facilitate identification. For these reasons one would be motivated to modify Aggarwal with Weltwitigoda.
Therefore, claims 6-12, 15, and 16 are rejected under 35 USC 103.
Prior Art Made of Record
The following prior art is considered relevant to Applicant’s disclosure:
Barbar et al, Artificial intelligence-driven automation is how we achieve the next level of efficiency in meat processing, Animal Frontiers, April 2022. Available at: https://pmc.ncbi.nlm.nih.gov/articles/PMC9056041/
Teaches several aspects of the independent and dependent claims including segmenting meat (in other words, cutting), see page 58, and using computer vision (images) to identify cuts, see page 58, and grading the meat, see page 57, contaminated, subprimal, etc.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RICHARD W. CRANDALL whose telephone number is (313)446-6562. The examiner can normally be reached M - F, 8:00 AM - 5:00 PM.
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, Anita Coupe can be reached at (571) 270-3614. 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.
/RICHARD W. CRANDALL/ Primary Examiner, Art Unit 3619
