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 .
Response to Amendment
Applicant’s preliminary amendments filed January 9th, 2025, and January 28th, 2025, to the Claims, Abstract, and Drawings have been entered. In the preliminary remarks and amendments filed January 9th, 2025, claims 6, 7, 16, 23, and 28 are amended, and claims 19-22, 24-27, and 29-30 are cancelled. Accordingly, claims 1-18, 23, and 28 are currently pending for examination in the Application No. 18/992,808 filed January 9th, 2025.
Priority
Acknowledgment is made of applicant’s status as a U.S. National Stage Filing under 35 U.S.C. § 371 of International Application No. PCT/CN2023/091727, filed on April 28th, 2023.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on July 8th, 2025, is in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS is being considered and attached by the examiner.
Claim Objections
Claims 1, 3, 5, 8-18, and 28 are objected to because of the following informalities failing to comply with 37 CFR 1.71(a) for "full, clear, concise, and exact terms" (see MPEP § 608.01(m)):
In the last line of claim 1, the examiner respectfully suggests amending the phrase “the to-be-inspected objects” to recite “the plurality of to-be-inspected objects” to maintain consistency in terminology in the claims, and thus the phrase also recited in claims 3, 5, 8, 9, 11, and 13-18 are respectfully suggested to be amended accordingly;
In claim 10, the examiner respectfully suggests amending the phrase “wherein each of the configuration window” to recite “wherein each[[ of the]] configuration window of the different configuration windows” to ensure that the “configuration window” recited in this phrase has proper antecedent basis with the “different configuration windows” recited previously in the claim;
In claim 12, the examiner respectfully suggests amending the phrase “as the target sample to the second data set” to recite “as [[the]]a target sample to the plurality of target image sample of the second data set” to maintain consistency in terminology in the claims; and
In claims 1 and 28, the examiner respectfully suggests reviewing the term “a quality inspection result” in the claim limitation “in response to a second preset condition triggered on the control object, regulating the target production line based on a quality inspection result of at least one to-be-inspected object” is a new instantiation of a “quality inspection result” and does not refer to the “result of the quality inspection” recited previously in the claims in the limitation reciting “feed[ing] back a result of the quality inspection…”.
Appropriate correction is required.
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, as explained in MPEP § 2181, subsection I (note that the list of generic placeholders below is not exhaustive, and other generic placeholders may invoke 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 Generic Placeholder (A Term That Is Simply A Substitute for "Means")
With respect to the first prong of this analysis, a claim element that does not include the term "means" or "step" triggers a rebuttable presumption that 35 U.S.C. 112(f) does not apply. When the claim limitation does not use the term "means," examiners should determine whether the presumption that 35 U.S.C. 112(f) does not apply is overcome. The presumption may be overcome if the claim limitation uses a generic placeholder (a term that is simply a substitute for the term "means"). The following is a list of non-structural generic placeholders that may invoke 35 U.S.C. 112(f): "mechanism for," "module for," "device for," "unit for," "component for," "element for," "member for," "apparatus for," "machine for," or "system for." Welker Bearing Co., v. PHD, Inc., 550 F.3d 1090, 1096, 89 USPQ2d 1289, 1293-94 (Fed. Cir. 2008); Mass. Inst. of Tech. v. Abacus Software, 462 F.3d 1344, 1354, 80 USPQ2d 1225, 1228 (Fed. Cir. 2006); Personalized Media, 161 F.3d at 704, 48 USPQ2d at 1886–87; Mas-Hamilton Group v. LaGard, Inc., 156 F.3d 1206, 1214-1215, 48 USPQ2d 1010, 1017 (Fed. Cir. 1998). Note that there is no fixed list of generic placeholders that always result in 35 U.S.C. 112(f) interpretation, and likewise there is no fixed list of words that always avoid 35 U.S.C. 112(f) interpretation. Every case will turn on its own unique set of facts.
Such claim limitation(s) is/are:
"controller for controlling movement…" in claim 6 implemented on hardware disclosed in paras. [0069] (e.g., "programmable logic controller (PLC)");
"different first devices are configured to provide different services…" in claim 23 implemented on hardware disclosed in paras. [0089-0080] (e.g., " Different servers…"), and thus, claim(s) 28 is/are similarly interpreted; and
"production information management system is configured to regulate a process device…" in claim 28 implemented on hardware disclosed in paras. [0092] (e.g., "shown in FIG. 2…").
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.
Additional Claim Interpretations:
Regarding claim(s) 6, the claim recites the claim limitation “at least one of a start position, an end position, and a movement rate of the image acquisition apparatus” to recite “at least one of a start position, an end position, [[and]]or a movement rate of the image acquisition apparatus”, which is a conjunctive list of the elements listed therein. The plain and ordinary meaning of this claim limitation is interpreted as conjunctive (i.e., ‘at least one of a start position, at least one of an end position, and at least one of a movement’). See Superguide Corp. v. Direct TV Enterprises, Inc., 358 F.3d 870, 69 USPQ2d 1865 (Fed. Cir. 2004). Paragraph [00213-00215] of Applicant’s instant Specification supports the conjunctive interpretation the claim limitation. Therefore, the claim will be interpreted to require all elements of the conjunctive list.
Regarding claim(s) 15, the claim recites the claim limitation “at least one of the following: performing statistics…according to positions where detects occur; performing statistics… according to a time period…; and performing statistics… according to types of defects…”, which is a conjunctive list of the elements listed therein. The plain and ordinary meaning of this claim limitation is interpreted as conjunctive (i.e., ‘at least one of performing statistics…according to positions where detects occur; at least one of performing statistics… according to a time period…; and at least one of performing statistics… according to types of defects’). See Superguide Corp. v. Direct TV Enterprises, Inc., 358 F.3d 870, 69 USPQ2d 1865 (Fed. Cir. 2004). Paragraph [00337] of Applicant’s instant Specification supports the conjunctive interpretation the claim limitation. Therefore, the claim will be interpreted to require all elements of the conjunctive list.
Regarding claim(s) 16, the claim recites the claim limitation “at least one of a target defect position, a target time period, and a target defect type ”, which is a conjunctive list of the elements listed therein. The plain and ordinary meaning of this claim limitation is interpreted as conjunctive (i.e., ‘at least one of a target defect position, at least one of target time period, and at least one of a target defect type’). See Superguide Corp. v. Direct TV Enterprises, Inc., 358 F.3d 870, 69 USPQ2d 1865 (Fed. Cir. 2004). Paragraph [00349] of Applicant’s instant Specification supports the conjunctive interpretation the claim limitation. Therefore, the claim will be interpreted to require all elements of the conjunctive list.
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 14 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.
Regarding claim(s) 14, the limitation “the statistical chart comprises at least one of a pie chart, a bar chart, a line chart, and a thermodynamic chart” recited in the claims renders the claim indefinite because it is unclear to examiner how a singular “statistical chart” comprises all three listed chart types as the limitation is interpreted as conjunctive. See Superguide Corp. v. Direct TV Enterprises, Inc., 358 F.3d 870, 69 USPQ2d 1865 (Fed. Cir. 2004). Paragraphs [00327-00329] of Applicant’s instant Specification support the interpretation of the limitation as disjunctive (i.e., a singular statistical chart is associated with a singular chart type). For examination purposes, the limitation in the claim will be read as “at least one of a pie chart, a bar chart, a line chart, [[and]]or a thermodynamic chart” as supported in Applicant’s instant Specification.
Claim Rejections - 35 USC § 102
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 (i.e., changing from AIA to pre-AIA ) 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 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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-3 and 18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Ye et al. (Ye; CN 114971433 A).
Regarding claim 1, Ye discloses a quality control method for a production line, wherein the method comprises:
in response to triggering of a first preset condition, performing quality inspection on a plurality of to-be-inspected objects produced on a target production line (description, para(s). [n0028-n0029], recite(s)
[n0028] “…the operating parameters of the target production line are acquired when the target production line is started. When the difference between the operating parameters and the standard operating parameters meets the preset standard, the camera device acquires product images of the products on the target production line at a preset sampling frequency. When the acquisition time reaches the preset time, the image acquisition is stopped, and a set of product images is obtained. The operating parameters include the production line operating speed, the product output per minute, etc.”
[n0029] “Step S20: Surface defects are identified in the product images in the product image set using a preset image recognition model, and the production yield of the target production line is determined based on the recognition results.”
, where “the target production line is started” and/or “acquir[ing[ product image” is/are at least a first preset condition, the identifying “surface defects” is quality inspection, and the “products” are a plurality of to-be-inspected objects);
feeding back a result of the quality inspection to a control object associated with the target production line, wherein the control object is used for controlling a process flow of the target production line (description, para(s). [n0032] and [n0034], recite(s)
[n0032] “Step S30: When the production yield is less than the target yield of the target production line, obtain the current control parameters corresponding to the target production line.”
[n0034] “In practice, when the yield rate of the target production line is less than the target yield rate, the control equipment determines that the target production line does not meet the production requirements and obtains the production line speed control parameters of the target production line.”
, where the determination of a “yield rate of the target production line” is received by the “control equipment” is feeding back a result of the quality inspection (e.g., “yield rate of the target production line”) to a control object (e.g., a “control equipment”)); and
in response to a second preset condition triggered on the control object, regulating the target production line based on a quality inspection result of at least one to-be-inspected object (description, para(s). [n0038] and [n0042], recite(s)
[n0038] “Step S50: When the difference between the simulated yield rate and the production yield rate is less than a preset threshold, adjust the model according to the current control parameters and the preset parameters to determine the target control function.”
[n0042] “Step S60: Determine the target control parameter based on the target control function and the current control parameter, and set the production parameter corresponding to the target production line as the target control parameter.”
, where the “preset threshold” for a “difference between the simulated yield rate and the production yield rate” is a second preset threshold and setting the “production parameter corresponding to the target production line as the target control parameter” based on the “target control function” is regulating the target production line based on a quality inspection result (e.g., “production yield rate”));
wherein the quality inspection comprises: performing at least one image acquisition on the to- be-inspected objects produced by the target production line, and inputting at least one acquired image into a defect detection model, so as to perform the quality inspection on the to-be-inspected objects (description, para(s). [n0031], recite(s)
[n0031] “…product images of the target production line are acquired by a camera device to obtain several product image sets. Surface defects are identified in the product images of each product image set using a preset image recognition model. …”
, where acquiring “product images” by the “camera device” is image acquisition and the “preset image recognition model” identifying “Surface defects” in the “product images” is at least a defect detection model).
Regarding claim 2, Ye discloses the quality control method according to claim 1, wherein the first preset condition comprises: starting operation of the target production line, and/or a quality inspection function triggered on a preset interface (description, para(s). [n0028]—see citation in claim 1 limitation “in response to triggering of a first operation…” above—, where “the target production line is started” and/or “acquir[ing[ product image” is/are at least a starting operation of the target production line).
Regarding claim 3, Ye discloses the quality control method according to claim 1, wherein the second preset condition comprises: a number of the to-be-inspected objects that fail the quality inspection being greater than or equal to a preset number, and/or preset operations triggered on the control object (description, para(s). [n0038]—see citation in claim 1 limitation “in response to a second preset condition…” above—, where the “preset threshold” for a “difference between the simulated yield rate and the production yield rate” is at least a second preset condition comprising at least preset operations (e.g., a “difference between the simulated yield rate and the production yield rate” determination) triggered on the control object).
Regarding claim 18, Ye discloses the quality control method according to claim 1, further comprising:
in a process of performing the quality inspection on the plurality of to-be-inspected objects produced on the target production line, determining a number of the to-be-inspected objects of which the quality inspection is completed within a unit time (description, para(s). [n0049], recite(s)
[n0049] “In practical implementation, the control equipment acquires the average yield rate of the products produced by the target production line when it runs under the target control parameters within each time period of a preset duration. …”
, where determining the “average yield rate” is determining a number of the to-be-inspected objects of which the quality inspection is completed within a unit of time (e.g., “time period of a preset duration”)); and
adjusting a conveying speed of the to-be-inspected objects on the target production line based on the number (description, para(s). [n0033] and [n0047], recite(s)
[n0033] “It is understandable that the target yield rate can be the yield rate of products produced by the target production line in advance. If the production yield rate is greater than or equal to the target yield rate of the target production line, the target production line is determined to meet the production requirements; otherwise, the target production line is determined to not meet the production requirements. The current control parameter can be the parameter that controls the operation of the target production line. In this embodiment, the current control parameter can be the parameter that affects the appearance of the product, and the current control parameter can be the production line speed control parameter.”
[n0047] “…determining the cumulative number of times the average production yield is less than the target yield; when the cumulative number is greater than a preset number, updating the preset parameter adjustment model according to the average production yield and the target control parameters; determining a second target control parameter through the updated preset parameter adjustment model, and setting the production parameters corresponding to the target production line as the second target control parameter.”
, where “setting the production parameters corresponding to the target production line as the second target control parameter” is adjusting (e.g., “updat[ing]”) at least a conveying speed (e.g., “production line speed control parameter”) of the to-be-inspected objects on the target production line based on the number (e.g., “production yield”)).
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 (i.e., changing from AIA to pre-AIA ) 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.
Claims 4, 7, and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Ye as applied to claim 1 above, and further in view of Hino et al. (Hino; US 2020/0364841 A1).
Regarding claim 4, Ye discloses the quality control method according to claim 1, wherein before performing quality inspection on a plurality of to-be-inspected objects produced on a target production line, the method further comprises:
in response to a triggered quality inspection configuration function,(description, para(s). [n0030], [n0036], and [n0043], recite(s)
[n0030] “It is understood that the preset image recognition model can be a pre-set algorithm for identifying surface defects in product images. The preset image recognition model can be a model obtained by training a convolutional neural network with product images that have surface defects. Determining the production yield of the target production line based on the recognition results can be done by determining the number of defective products based on the recognition results and then determining the production yield of the target production line based on the number of defective products.”
[n0036] “It is understandable that the preset parameter control model can be a model that pre-sets the production line speed control parameters of the target production line; the simulated yield rate can be the yield rate output by the preset parameter control model based on the current control parameters, which is then input into the preset parameter control model.”
[n0043] “…If the difference between the simulated yield and the production yield is less than a preset threshold, the preset parameter control model is determined to be suitable for the target production line. …”
, where “pre-set[ting]” parameters is triggering a quality inspection configuration function; the “preset parameter control model” is at least a first configuration item of a device for quality inspection; and the “preset threshold” for a difference between “production yield[s]” including the “production yield” determined by the “preset image recognition model” is at least a second configuration item of the defect detection model); and
receiving configuration parameters respectively inputted through the first configuration item and the second configuration item (description, para(s). [n0030], [n0036], and [n0043]—see citation in the preceding claim limitation immediately above—, where “pre-set[ting]” the first configuration item and the second configuration item is receiving configuration parameters respectively inputted (e.g., “pre-set[ted]”) through the first and second configuration items); and
the performing quality inspection on a plurality of to-be-inspected objects produced on a target production line comprises:
performing the quality inspection on the plurality of to-be-inspected objects produced on the target production line based on the configuration parameters (description, para(s). [n0043], recite(s)
[n0043] “…A preset image recognition model is used to identify surface defects in the product images in each set. Based on the recognition results, the production yield corresponding to each product image set is determined. The average production yield of each product image set is taken as the production yield of the target production line. If the production yield is less than the target yield, the target production line is determined not to meet production requirements. The current control parameters of the target production line are input into a preset parameter control model, and the simulated yield output by the preset parameter control model is obtained. If the difference between the simulated yield and the production yield is less than a preset threshold, the preset parameter control model is determined to be suitable for the target production line. At this time, the target control function is matched in the preset parameter control model according to the current control parameters. The target control parameters are determined based on the current control parameters and the target control function. The production parameters of the target production line are set as the target control parameters, and the production parameters of the target production line are adjusted to the target control parameters based on the current control parameters.”
, where determining if the “target production line… meet[s] production requirements” based on at least the “preset parameter[s]” and “preset threshold” is performing quality inspection on the plurality of to-be inspected objects produced on the target production line based on the configuration parameters).
Where Ye does not specifically disclose
…displaying a first configuration interface, wherein the first configuration interface comprises a first configuration item of a device for the quality inspection and a second configuration item of the defect detection model;
Hino teaches in the same field of endeavor of quality inspection based on defective product recognition
…displaying a first configuration interface, wherein the first configuration interface comprises a first configuration item of a device for the quality inspection and a second configuration item of the defect detection model (para(s). [0084], [0086], and [0102], recite(s)
[0084] “When the image inspection apparatus 1 is started up, the control unit 2 generates a startup time user interface 100 as illustrated in FIG. 4 and displays this interface in the display device 4. …”
[0086] “When detecting that the sensor setting button 100 a of the startup time user interface 100 illustrated in FIG. 4 has been pressed, the mode switching section 29 illustrated in FIG. 3 performs switching to the setting mode for setting the image inspection apparatus 1. In contrast, when detecting that the operation start button 100 b of the startup time user interface 100 has been pressed, the mode switching section 29 performs switching to the run mode. That is, the mode switching section 29 switches the mode of the operation start button 100 b between the setting mode for setting the image inspection apparatus 1 and the run mode for performing an inspection. The method for switching the mode of the image inspection apparatus 1 may be performed by, for example, a signal input from the outside or the like instead of by a button operation described above. It should be noted here that “depression of a button” is performed by an operation of the touch panel 41 of the display device 4 or an operation by the keyboard 51 or the mouse of the personal computer 5. This is true of a button operation described below.”
[0102] “The inspection window setting section 27 illustrated in FIG. 3 receives the settings of learning inspection windows (learning-based inspection window) 200A and 200B for defining the range of difference detection on the master image registered by the master image registering section 23 in the setting mode in the learning inspection mode. …”
, where the “startup time user interface” is at least a first configuration interface comprising at least a first configuration item of a device (e.g., a “setting mode for setting the image inspection apparatus”) and a second configuration item of a defect detection model (e.g. “settings of learning inspection windows”)).
Since each of Ye and Hino disclose a first configuration item of a device for quality inspection and a second configuration item of a defect detection model, it would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye to incorporate a first configuration interface to input the preset parameters of the device for quality inspection and the defect detection model as taught by Hino above.
Regarding claim 7, Ye in view of Hino discloses the quality control method according to claim 4, wherein Ye further discloses the second configuration item is used for inputting a threshold parameter corresponding to the defect detection model and/or for inputting a working parameter of a server on which the defect detection model is located (description, para(s). [n0030], [n0036], and [n0043]—see citation in claim 4 limitation “receiving configuration parameters respectively inputted…” above—, where “pre-set[ting]” the “preset threshold” is inputting (e.g., “pre-set[ting]”) at least a threshold parameter (e.g., a “threshold” for a difference between “production yield[s]”)).
Regarding claim 10, Ye discloses the quality control method according to claim 1, wherein Hino teaches in the same field of endeavor of quality inspection based on defective product recognition before the step of performing quality inspection on a plurality of to-be-inspected objects produced on a target production line, the method further comprises:
in response to a triggered model construction function, displaying a third configuration interface, wherein the third configuration interface comprises at least one trigger control, and different trigger controls are used for triggering different configuration windows in a model construction process (para(s). [0087] and [0102], recite(s)
[0087] “…The inspection type selection user interface 101 includes a learning inspection mode selecting button…When detecting that the learning inspection mode selecting button 101 a has been pressed, the inspection type selecting section 28 performs switching to the learning inspection mode. …”
[0102] “The inspection window setting section 27 illustrated in FIG. 3 receives the settings of learning inspection windows (learning-based inspection window) 200A and 200B for defining the range of difference detection on the master image registered by the master image registering section 23 in the setting mode in the learning inspection mode. …”
, where pressing the “learning inspection mode selecting button” is at least triggering a model construction function, the “window inspection window setting section” is at least a third configuration interface comprising at least one trigger control (e.g., “window setting”), and the “settings of learning inspection windows” are different trigger controls used for triggering different configuration windows in a model construction process);
determining configuration options selected in different configuration windows, wherein each of the configuration window comprises a plurality of configuration options (para(s). [0108], recite(s)
[0108] “When detecting that the learning button 104 c of the learning setting user interface 104 illustrated in FIG. 8 of the learning setting user interface 104 illustrated in FIG. 8 has been pressed, the learning image registering section 24 displays a learning user interface 106 illustrated in FIG. 10 in the display device 4. The learning user interface 106 includes an image display region 106 a in which the non-defective product image and the defective product image as learning images can be displayed, a non-defective product image obtaining operation section 106 b, a defective product image obtaining operation section 106 c, a learning start button 106 d, and a file read button 106 e, and a history read button 106 f.”
, where each “section” and “button” are a plurality of configuration options ); and
based on preset configuration parameters corresponding to the selected configuration options, obtaining the defect detection model through training by using a pre-stored first data set as a training sample (para(s). [0108]—see citation in preceding claim limitation above—, where para(s). [0114-0115] further recite(s):
[0114] “The distinguishing device generating section 30 illustrated in FIG. 3 learns the non-defective product image and the defective product image registered by the learning image registering section 24 and generates the distinguishing device that distinguishes the non-defective product image from the defective product image in the setting mode in the learning inspection mode. When detecting that the learning start button 106 d of the learning user interface 106 illustrated in FIG. 10 has been pressed, the distinguishing device generating section 30 reads the non-defective product image and the defective product image registered in the learning image registering section 24. The distinguishing device generating section 30 inputs the read non-defective product image and defective product image to the mechanical learning device including a plurality of layers.”
[0115] “Specifically, the distinguishing device generating section 30 has a neural network and may use a so-called deep learning method… The user may be provided with a neural network having the adjusted parameters (that is, learned neural network) or the user may adjust the parameters. …”
, where the “neural network” trained by “learning” the “non-defective product image and the defective product image” generated by the selected configuration options is a defect detection model obtained based on preset configuration parameters corresponding to the selected configuration options (e.g., from the “learning image registering section” and/or user “adjust[ed] parameters”) by using a pre-stored first data set (e.g., the “non-defective product image and the defective product image”) as a training sample).
Since each of Ye and Hino disclose training a defect detection model, it would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye to incorporate displaying a third configuration interface comprising different trigger controls are used for triggering different configuration windows in a model construction process in response to a triggered model construction function to obtain the defect detection model through training by using a pre-stored first data set as a training sample to obtain an improved defect detection model by allowing for adjustability of configuration parameters of the defect detection model as taught by Hino above.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Ye as applied to claim 1 above, and further in view of Hino et al. (Hino; US 2020/0364841 A1), and further more in view of Hyatt et al. (Hyatt; US 2021/0398267 A1).
Regarding claim 5, Ye discloses the quality control method according to claim 1, wherein in a process of performing the quality inspection on the plurality of to-be-inspected objects produced on the target production line, the method further comprises:
in response to a triggered quality inspection debugging function,(description, para(s). [n0047], recite(s)
[n0047] “Furthermore, after adjusting the production parameters of the target production line, the product yield of the target production line may meet the production requirements for a period of time. However, after the target production line has been running for a period of time, the product yield may drop below the target yield. In order to achieve dynamic adjustment of the production parameters of the target production line to improve the product yield, after step S60, the method further includes: obtaining the average production yield of the target production line under the target control parameters within a preset time period; determining the cumulative number of times the average production yield is less than the target yield; when the cumulative number is greater than a preset number, updating the preset parameter adjustment model according to the average production yield and the target control parameters; determining a second target control parameter through the updated preset parameter adjustment model, and setting the production parameters corresponding to the target production line as the second target control parameter.”
, where determining that “the product yield” drops “below the target yield” is triggering a quality inspection debugging function, and the “target yield” is at least a target configuration item comprising at least a first configuration item of a device for quality inspection (e.g., a “target yield”)); and
(description, para(s). [n0047]—see citation in the preceding claim limitation immediately above—, where the “product yield” is at least a statistical result about statistics on quality inspection results; and the “second target control parameter” is at least a configuration parameter modified (e.g., determined through an “updated preset parameter adjustment model”) from a current configuration parameter (e.g., “target control parameters”) of the target configuration item (e.g., the “average production yield”)); and
the performing quality inspection on a plurality of to-be-inspected objects produced on a target production line comprises:
performing the quality inspection on the plurality of to-be-inspected objects produced on the target production line after a current time based on the modified configuration parameter (description, para(s). [n0047]—see citation in the preceding claim limitation immediately above—, where description, para(s). [n0049], further recite(s):
[n0049] “…The second target control parameter is determined based on the updated preset parameter adjustment model, and the control parameters of the target production line are adjusted from the target control parameter to the second target control parameter.”
, where “adjust[ing]” the current “control parameters of the target production line to the second target control parameter” is at least performing the quality inspection on the plurality of to-be-inspected objects produced on the target production line after a current time (e.g., “target control parameters within a preset time period”) based on the modified configuration parameter (e.g., using the now “adjusted” “control parameters of the target production line”)).
Where Ye does not specifically disclose
…displaying a second configuration interface, wherein the second configuration interface comprises a target configuration item, the target configuration item comprises a first configuration item of a device for the quality inspection and/or a second configuration item of the defect detection model;
Hino teaches in the same field of endeavor of quality inspection based on defective product recognition
…displaying a second configuration interface, wherein the second configuration interface comprises a target configuration item, the target configuration item comprises a first configuration item of a device for the quality inspection and/or a second configuration item of the defect detection model (para(s). [0142] and [0167], recite(s)
[0142] “…the second inspection window result display region 120 e indicates the result of a pass/fail determination of the image in the learning inspection window 200B. In addition, the threshold adjusting button 120 g adjusts the threshold of a pass/fail determination and, when the threshold has been adjusted, the pass/fail determining section 31 makes a pass/fail determination based on the changed threshold.”
[0167] “Step SB2 is a pass/fail determination step that inputs the inspection target image newly captured by the image-capturing unit 3 in step SB1 to the distinguishing device and makes a pass/fail determination. The user determines whether the threshold of the determination needs to be adjusted based on the determination result in step SB2. This is step SB3. When the threshold needs to be adjusted, the processing proceeds to step SB4, the threshold is adjusted, and the processing proceeds to step SBS. …”
, where the “window” comprising the “threshold adjusting button” for “pass/fail determination” is at least a second configuration interface comprising a target configuration item comprising at least a first configuration item of a device for quality inspection).
Since each of Ye and Hino disclose a target configuration item comprising at least a first configuration item of a device for the quality inspection, it would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye to incorporate a second configuration interface comprising a target configuration item comprising at least a first configuration item of a device for the quality inspection to adjust the first configuration item of the device for quality inspection in a process of performing the quality inspection on the plurality of to-be-inspected objects as taught by Hino above.
Where Ye in view of Hino does not specifically disclose
displaying a statistical result about statistics on quality inspection results of the to-be-inspected objects subjected to quality inspection on the second configuration interface;
Hyatt teaches in the same field of endeavor of a quality control method for a production line
displaying a statistical result about statistics on quality inspection results of the to-be-inspected objects subjected to quality inspection on the second configuration interface (para(s). [0001], [0078-0087], and [0103], recite(s)
[0001] “The present invention relates to visual inspection of items on a production line and more specifically to collection and analysis of data from multiple visual production line inspection appliances.”
[0078-0087] “In step 206 the collected data from VIAs 110 is analyzed by analysis engine 152 and/or used for generating reports. …preferably generated using big data methods. Optionally the analysis is performed for a combination of different type items where different type items may be any of different products, different production stages, different plants, or different industries. One or more of the following reports are preferably generated including but not limited to:
% defects detected per item;
Defect report including images of item showing where defects were detected;
% defects detected per manufacturing area;
Number of items inspected per period of time;
Personnel vs item defect report;
% defects per shift;
% defects per manufacturing type (e.g. casting lines vs molding lines);
% defects per defect type;
Defect report per period of time and production area;”
[0103] “In step 208 the results of the analyses and/or reports of step 206 are stored in DB 154 and also preferably displayed using DCAS UI 156. …”
, where displaying the “results of the analyses and/or reports” includes at least a production yield (e.g., “Number of items inspected per period of time”, “Defect report per period of time and production area”, etc.) is displaying a statistical result about statistics on quality inspection results of the to-be-inspected objects subjected to quality inspection on at least a second configuration interface (e.g., a “DCAS [Data Collection and analytics server] UI [User Interface]”)).
Since each of Ye and Hyatt disclose determining a statistical result of at least a production yield of a production line, it would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye in view of Hino to incorporate displaying the statistical result about statistics on quality inspection results of the to-be-inspected objects subjected to quality inspection on the second configuration interface to improve the quality control method for the production line as taught by Hyatt (para(s). [0006], recite(s)
[0006] “…Embodiments of the invention provide multiple automated visual inspection appliances (VIA) for a production plant and a centralized data collection and analytics server (DCAS) that gathers and analyzes data from the VIAs. The DCAS can then provide reports, dashboards and alerts to determine production trends in the manufacturing plant and thus improve the quality and productivity of the plant.”
).
Claims 8-9 are rejected under 35 U.S.C. 103 as being unpatentable over Ye in view of Hino as applied to claim 4 above, and further in view of Shen et al. (Shen; CN 110554047 B).
Regarding claim 8, Ye in view of Hino discloses the quality control method according to claim 4, wherein Ye further discloses the quality control method according to claim 4 further comprising:
when it is detected that an associated production line associated with the target production line is running, in response to a triggered parameter migration function, associating the configuration parameters to the associated production line (description, para(s). [n0032]—see citation in claim 1 limitation “feeding back a result of the quality inspection…” above—, where the determination that the “production yield is less than the target yield of the target production line” is a triggered parameter migration function and “corresponding” the “current control parameters” to the “target production line” is associating the configuration parameters to the associated production line)
Where Ye in view of Hino does not explicitly disclose
wherein defects of the to-be-inspected objects targeted by the quality inspection in the associated production line are the same as or similar to defects of the to-be-inspected objects targeted by the quality inspection in the target production line; and
performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the defect detection model based on the configuration parameters;
Shen teaches in the same field of endeavor of defect targeted quality inspection in production lines
wherein defects of the to-be-inspected objects targeted by the quality inspection in the associated production line are the same as or similar to defects of the to-be-inspected objects targeted by the quality inspection in the target production line (description, para(s). [n0070- n0071], recite(s)
[n0070] “…Production environment information refers to parameters related to the production environment of a product, such as the factory area and production line information. …”
[n0071] “In this embodiment of the application, by establishing a correspondence between the target defect detection model and product-related information, it is possible to distinguish the defect detection models corresponding to different business scenarios.
For example, different product categories may have different defects or model parameters. If the same model is used for defect detection, the defect accuracy will be low. In factories, there are usually multiple types of products produced, and the corresponding product information may be constantly changing. Production personnel need to flexibly determine the defect detection strategy based on the products being produced. Therefore, the corresponding defect detection models are different. By establishing the correspondence between the target defect detection model and the product information, the corresponding detection model can be used to perform defect detection on product images in a targeted manner.”
, where “establishing a correspondence between the target defect detection model and product-related information” is determining at least the defects of to-be-inspected objects (e.g., products) targeted by the quality inspection in an associated product line (e.g., a particular “product categor[y]”) is at least the same as or similar to defects of the to-be-inspected objects targeted by the quality inspection in the target production line (i.e., product lines producing products in the same “product categor[y]” have the same as or similar “defects”)); and
performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the defect detection model based on the configuration parameters (description, para(s). [0071]—see citation in preceding claim limitation immediately above—, where using the “corresponding detection model… to perform defect detection on product images” is performing quality inspection on the plurality of to-be-inspected objects produced on the associated production line using the defect detection model based on configuration parameters (e.g., model parameters”)).
Since each of Ye and Shen disclose associating the configuration parameters to an associated production line, it would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye in view of Hino to have the defects of the to-be-inspected objects targeted by the quality inspection in the associated production line to be the same as or similar to defects of the to-be-inspected objects targeted by the quality inspection in the target production line and performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the defect detection model based on the configuration parameters to perform defect detection on product images in a targeted manner in a system comprising of multiple product lines as taught by Shen above.
Regarding claim 9, Ye, as modified by Hino and Shen, discloses the quality control method according to claim 8, wherein before performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the defect detection model based on the configuration parameters, Ye further discloses the method quality control method according to claim 8 further comprises:
obtaining a target data set corresponding to the associated production line (description, para(s). [n0030], recite(s)
[n0030] “It is understood that the preset image recognition model can be a pre-set algorithm for identifying surface defects in product images. The preset image recognition model can be a model obtained by training a convolutional neural network with product images that have surface defects. Determining the production yield of the target production line based on the recognition results can be done by determining the number of defective products based on the recognition results and then determining the production yield of the target production line based on the number of defective products.”
, where the “product images that have surface defects” used for training the “preset image recognition model” is at least a target data set corresponding to the associated (“target”) production line), wherein the target data set comprises image samples after image acquisition(description, para(s). [n0030]—see citation in preceding claim limitation immediately above—, where the “product images” are image samples after image acquisition on the plurality of to-be-inspected objects on the associated production line)
Where Ye does not specifically disclose
…wherein the target data set comprises image samples after image acquisition and labeling on the plurality of to-be-inspected objects on the associated production line; and
in response to a triggered model migration function, updating the defect detection model by using the target data set to obtain a migration model; and
the performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the defect detection model based on the configuration parameters comprises:
performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the migration model based on the configuration parameters;
Shen further teaches
…wherein the target data set comprises image samples after image acquisition and labeling on the plurality of to-be-inspected objects on the associated production line (description, para(s). [n0057], recite(s)
[n0057] “Step S204: Obtain the corresponding training images and the defect categories corresponding to the training images based on the model training parameters to obtain training samples.”
[n0058] “Specifically, training samples are used for model training, including training images and corresponding labels, where the labels represent the corresponding defect categories. …”
, where the “training images” are image samples after image acquisition and labeling (e.g., “corresponding labels”)); and
in response to a triggered model migration function, updating the defect detection model by using the target data set to obtain a migration model (description, para(s). [n0091] and [n0114], recite(s)
[n0091] “…incorrectly labeled images can be output so that production personnel can re-label the images and retrain the model using the re-labeled images.”
[n0114] “The product defect detection data processing method of this application embodiment can be used to detect defects in products manufactured in a factory.
Since product defect detection in factories varies with changes in product time, process parameters, sites, and defect detection standards, the product defect detection model must also be able to be updated or new models produced as needed. The method provided in this application can encapsulate complex model training methods, and at least one of the defect learning categories or training image information related to model training can be flexibly configured by the user as needed. Therefore, factory personnel can configure parameters at any time according to production needs, and quickly build models from 0 to 1 and 1 to N to obtain a product defect detection model that meets the requirements, where N refers to the model version.”
, where “re-label[ing] images” is at least a triggered model migration function and a “retrain[ed]” and/or “updated” “product defect detection model” is at least a migration model obtained by updating the defect detection model by using the target data set (e.g., “re-label[ed]” training images)); and
the performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the defect detection model based on the configuration parameters comprises:
performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the migration model based on the configuration parameters (description, para(s). [n0065], recite(s)
[n0065] “…when the system has already deployed a defect detection model, the deployed defect detection model is also trained based on images.
Therefore, the production terminal can display the corresponding option information for historical images and new images respectively. Users can choose at least one of historical images and new images as the images used for model training. Historical images refer to the training images used when training existing defect detection models. New images refer to images other than historical images, such as images taken during the production process after historical images. When a user selects historical images and new images for training, the trained model can learn parameters to detect newly emerging defects while retaining the ability to detect previous defects.”
, where using a newly trained “deployed defect detection model” (i.e., a re-trained defect detection model, such as for “detect[ing] newly emerging defects”) is at least using a migration model based on configuration parameters (e.g., “learn[ed] parameters”) to perform the quality inspection).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye, as modified by Hino and Shen, to incorporate updating the defect detection model by using the target data set to obtain a migration model in response to a triggered model migration function and performing the quality inspection on the plurality of to-be-inspected objects produced on the associated production line by using the migration model based on the configuration parameters to obtain a product defect detection model that meets the production needs of a production line as taught by Shen above.
Claims 11-12, 23, and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Ye as applied to claim 1 above, and further in view of Shen et al. (Shen; CN 110554047 B).
Regarding claim 11, Ye discloses the quality control method according to claim 1, wherein Shen teaches in the same field of endeavor of defect targeted quality inspection in production lines that after performing quality inspection on a plurality of to-be-inspected objects produced on a target production line, the method further comprises:
obtaining a second data set in response to a triggered model update function, wherein the second data set comprises a plurality of target image samples (description, para(s). [n0065] and [n00129], recite(s)
[n0065] “In some embodiments, when the system has already deployed a defect detection model, the deployed defect detection model is also trained based on images.
Therefore, the production terminal can display the corresponding option information for historical images and new images respectively. Users can choose at least one of historical images and new images as the images used for model training. Historical images refer to the training images used when training existing defect detection models. New images refer to images other than historical images, such as images taken during the production process after historical images. When a user selects historical images and new images for training, the trained model can learn parameters to detect newly emerging defects while retaining the ability to detect previous defects.”
[n00129] “The model training system can provide functions such as new model training, model iteration and improvement, online model evaluation, question bank testing, and model image management, allowing users to create new defect detection models based on new and historical data, and to retrain the model after labeling images that were judged incorrectly.”
, where the “new… data” (or “New images”) are a second data set comprising a plurality of target image samples obtained in response to a triggered model update function (e.g., “retrain[ing]” and/or “training” an “already deployed… defect detection model”)), and the target image samples comprises regions for re-labeling defect regions of the to-be-inspected objects subjected to the quality inspection (description, para(s). [n0088], [n0092], and [n00126], recite(s)
[n0088] “…training images also include regions without defects in addition to defects, we can select candidate regions that better reflect the features of defects and use these candidate regions for model training…”
[n0092] “…incorrectly labeled images can be output so that production personnel can re-label the images and retrain the model using the re-labeled images.”
[n0126] “Model training can be performed based on candidate regions… The image annotation system can also have a manual review function, which means that the annotated images can be returned to the terminal for manual review. The model can be trained with the accurately annotated images to ensure the accuracy and effectiveness of the training images.”
, where “re-label[ing] images” including “regions without defects in addition to defects” is re-labeling defect regions);
updating the defect detection model by using the second data set as a training sample (description, para(s). [n0065] and [n00129]—see citations in the first claim limitation in the current claim above—, where “retrain[ing]” and/or “training” an “already deployed… defect detection model” using “New images” is updating the defect detection model by using the second data set as a training sample); and
replacing the defect detection model performing the quality inspection at a current time with an updated defect detection model (description, para(s). [n0064], recite(s)
[n0064] “…update the parameters of an existing model. In other words, the model can be continuously iterated and upgraded with new training images as production changes.”
, where the “existing [defect detection] model” is updated or “upgraded” as “production changes” is replacing the defect detection model performing the quality inspection at a current time with an updated defect detection model).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye to incorporate replacing the defect detection model performing the quality inspection at a current time with an updated defect detection model by using a second data set comprising a plurality of target image samples, including regions for re-labeling defect regions of the to-be-inspected objects subjected to the quality inspection, in response to a triggered model update function to obtain a product defect detection model that meets the production needs of a production line as taught by Shen above.
Regarding claim 12, Ye in view of Shen discloses the quality control method according to claim 11, wherein Shen further teaches the second data set is obtained by:
in response to a triggered data labeling function, obtaining a plurality of quality inspection results of the plurality of to-be-inspected objects subjected to the quality inspection, and displaying the plurality of quality inspection results (description, para(s). [n0088], [n0092], and [n00126]—see citations in claim 11 limitation “…and the target sample comprises…” above—, where the “manual review” and/or “re-label[ing]” due to “incorrectly labeled images” is a triggered data labeling function; the “output[ted]” “labeled images” are a plurality of quality inspection results; and “return[ing]” the “annotated images” to a “terminal for manual review” is displaying the plurality of quality inspection results);
in response to an error correction operation triggered for a target quality inspection result among the plurality of quality inspection results, displaying at least one target image corresponding to the target quality inspection result, wherein the target image is marked with a defect region (description, para(s). [n0088], [n0092], and [n00126]—see citations in claim 11 limitation “…and the target sample comprises…” above—, where “re-label[ing]” “incorrectly labeled images” is an error correction operation; “return[ing]” the “annotated images” (e.g., an “incorrectly labeled image”) to a “terminal for manual review” is displaying at least one target image marked with a defect region (e.g., “regions… in addition to defects”));
labeling a modified defect region on the target image in response to a modification operation for the defect region (description, para(s). [n0088], [n0092], and [n00126]—see citations in claim 11 limitation “…and the target sample comprises…” above—, where “re-label[ing]” the target image comprising the “defect” region is labeling a modified defect region on the target image; wherein the “re-label[ing]” is a modification operation“); and
adding a target image labeled with the modified defect region as the target image sample to the second data set (description, para(s). [n0092]—see citation in claim 11 limitation “…and the target sample comprises…” above—, where “retrain[ing]” the defect detection model “using the re-labeled images” is adding at least the target image labeled with the modified defect region as a target image sample to the second data set).
Regarding claim 23, Ye discloses a quality control system, comprising an infrastructure layer and a quality control layer (description, para(s). [n0023], recite(s)
[n0023] “In the industrial internet-based quality control device shown in Figure 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the industrial internet-based quality control device of the present invention can be set in the industrial internet-based quality control device, and the industrial internet-based quality control device calls the industrial internet-based quality control program stored in the memory 1005 through the processor 1001 and executes the industrial internet-based quality control method provided in the embodiment of the present invention.”
, where the “network server” is at least an infrastructure layer” and the “internet-based quality control device” is at least a quality control layer)
the quality control layer is in communication with the infrastructure layer (description, para(s). [n0020], recite(s)
[n0020] “As shown in Figure 1, the quality control device based on the Industrial Internet may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. …”
, where “realiz[ing] the connection and communication between these components” is at least the quality control layer is in communication with the infrastructure layer) and is configured to perform the quality control method according to claim 1 (see the rejection of claim 1 above).
Where Ye does not specifically disclose
…wherein the infrastructure layer comprises a plurality of first devices, and different first devices are configured to provide different services required by the quality inspection;
Shen teaches in the same field of endeavor of defect targeted quality inspection in production lines
…wherein the infrastructure layer comprises a plurality of first devices, and different first devices are configured to provide different services required by the quality inspection (para(s). [n0135], recite(s)
[n0135] “Figure 12 shows the system architecture diagram of the product defect detection system in some embodiments. The product defect detection system is a cluster composed of multiple devices. The load balancing device performs load balancing processing on the received product defect detection requests (also known as inference requests). The inference service node is used to provide product defect detection services. There can be multiple inference service nodes. One inference service node can provide multiple inference services. One inference service can deploy one product defect detection model.”
, where “multiple devices” and/or “service nodes” are a plurality of first devices and difference first devices configured to provide different services (e.g., “multiple inference services”) required by the quality inspection).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye to incorporate a plurality of first devices, and different first devices are configured to provide different services required by the quality inspection, in the infrastructure layer of a quality control system to improve defect detection by providing multiple inference services as taught by Shen above.
Regarding claim 28, Ye in view of Shen discloses a manufacturing platform, comprising a computer integrated system (Ye; description, para(s). [n0020]—see citation in claim 23 above—, where the “quality control device based on the Industrial Internet” is at least a manufacturing platform comprising a computer integrated system (e.g., “CPU)), and the quality control system according to claim 23 (Ye in view of Shen—see rejection of claim 23 above), wherein the quality control system is integrated into the computer integrated system, and the computer integrated system is provided with a production information management system (Ye; description, para(s). [n0020]—see citation in claim 23 above—, where the “the quality control device based on the Industrial Internet” includes at least a “CPU” is the quality control system being integrated into the computer integrated system; and the “industrial Internet” is at least a product information management system);
wherein the quality control system is in communication with the production information management system (Ye; description, para(s). [n0020]—see citation in claim 23 above—, where “realiz[ing] the connection and communication between these components” is at least the quality control system is in communication with the product information management system);
the quality control system is configured to in response to triggering of a first preset condition, perform quality inspection on a plurality of to-be-inspected objects produced on a target production line (Ye; description, para(s). [n0028-n0029]—see similar limitation in claim 1 above);
feed back a result of the quality inspection to a control object associated with the target production line, wherein the control object is used for controlling a process flow of the target production line (Ye; description, para(s). [n0032] and [n0034]—see similar limitation in claim 1 above);
in response to a second preset condition triggered on the control object, regulate the target production line based on a quality inspection result of at least one to-be-inspected object (description, para(s). [n0038] and [n0042]—see similar limitation in claim 1 above); and
send a debugging instruction to the production information management system when regulating the target production line (Ye; description, para(s). [n0038] and [n0042]—see citations in claim 1 limitation “in response to a second preset condition triggered…” above—, where determining that the “difference between the simulated yield rate and the production yield rate is less than a threshold” is sending a debugging instruction to the production information management system when regulating the target production line); and
the production information management system is configured to regulate a process device in the target production line according to the debugging instruction (Ye; description, para(s). [n0038] and [n0042]—see citations in claim 1 limitation “in response to a second preset condition triggered…” above—, where setting the “production parameter corresponding to the target production line as the target control parameter” when the “difference between the simulated yield rate and the production yield rate is less than a threshold” is at least regulating the target production line based on the debugging instruction).
Claims 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Ye as applied to claim 1 above, and further in view of Oostendorp et al. (Oostendorp; US 2022/0086399 A1).
Regarding claim 14, Ye discloses the quality control method according to claim 1, wherein the feeding back a result of the quality inspection to a control object associated with the target production line comprises:
in response to a triggered quality inspection statistics function, performing statistics on quality inspection results of the plurality of to-be-inspected objects to obtain a statistical result (description, para(s). [n0047]—see citation in the first limitation of claim 5 above—, where “obtain[ing]” the “average production yield” is at least triggering a quality inspection statistics function; and determining the “product yield” is at least obtaining a statistical result about statistics on quality inspection results)
Where Ye does not specifically disclose
generating a statistical chart based on the statistical result; and
sending the statistical chart to the control object, wherein the statistical chart comprises at least one of a pie chart, a bar chart, a line chart, and a thermodynamic chart;
Oostendorp teaches in the same field of endeavor of performing statistics on quality inspection results of a plurality of to-be-inspected objects produced on a production line
generating a statistical chart based on the statistical result (para(s). [0093] and [0095] and Fig. 9B, recite(s)
[0093] “With regard to operation 1010, additional quality metrics can be computed based on the more comprehensive pass/fail measurements calculated in operation 1006. Exemplary quality metrics include the total number of defects, defect frequency, number of defects by shift, number of defects by type of defect, and defect correlation to other recorded factors. Examples of these quality metrics are depicted in the user interface 450 and discussed below with respect to FIG. 9B.”
[0095] “In operation 1014, the digital image, measurement, and quality metric are displayed. With reference again to FIG. 5, the information is displayed on the remote terminal 240 as web content. FIGS. 9A and 9B depict exemplary user interface screens 400, 450 that may be displayed on the remote terminal 240. … As shown in FIG. 9B, quality metrics are depicted, including total number of defects 451, defect frequency 452, and number of defects by type 453.”
PNG
media_image1.png
288
346
media_image1.png
Greyscale
, where the “displayed” quality metric is at least a statistical chart as depicted in Fig. 9B above based on the statistical result (e.g., a production yield such as “total number of defects, defect frequency, number of defects by shift, number of defects by type of defect, and defect correlation to other recorded factors”)); and
sending the statistical chart to the control object, wherein the statistical chart comprises at least one of a pie chart, a bar chart, a line chart, and a thermodynamic chart (Fig. 9B—see figure in preceding claim limitation immediately above—, where the statistical chart is at least a bar chart as depicted in Fig. 9B above).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the presently filed invention to modify the system of Ye to incorporate generating a statistical chart comprising at least a bar chart based on the statistical result and sending the statistical chart to the control object to monitor quality inspections nearly simultaneously with their occurrence at multiple inspection stations in a production facility as taught by Oostendorp (para(s). [0093], recite(s)
[0096] “The process 1000 depicted in FIG. 6A offers multiple advantages over traditional machine-vision systems. For example, using process 1000 updated quality metrics can be displayed on the remote terminal in near real time. That is, in a relatively short period of time, new measurement data is transmitted to the vision server in operation 1006, the data metric is recalculated in operation 1010 and then displayed at the remote terminal in operation 1014. Using process 1000, the operator can monitor inspections nearly simultaneously with their occurrence at multiple inspection stations in the production facility.”
).
Regarding claim 15, Ye in view of Oostendorp discloses the quality control method according to claim 14, wherein Oostendorp further teaches the performing statistics on quality inspection results of the plurality of to-be-inspected objects comprises at least one of the following:
performing statistics on the quality inspection results of the plurality of to-be-inspected objects according to positions where defects occur (para(s). [0092], recite(s)
[0092] “…Exemplary quality metrics include a mean location, deviation from the mean location, and the like. The quality metrics may also include results generated by statistical processing, such as regression analysis, distribution analysis, or Nelson rules of process control and other control charting techniques.”
, where “quality metrics” are statistics; and “a mean location” where “deviation[s]” occur is at least positions where defects occur);
performing statistics on the quality inspection results of the plurality of to-be-inspected objects according to a time period in which the to-be-inspected objects are produced (para(s). [0096], recite(s)
[0096] “…updated quality metrics can be displayed on the remote terminal in near real time. That is, in a relatively short period of time, new measurement data is transmitted to the vision server in operation 1006, the data metric is recalculated in operation 1010 and then displayed at the remote terminal in operation 1014. Using process 1000, the operator can monitor inspections nearly simultaneously with their occurrence at multiple inspection stations in the production facility.”
, where the “quality metrics can be displayed in near real time” is performing statistics on the quality inspection results according to a time period in which the to-be-inspected objects are produced (e.g., “their occurrence”)); and
performing statistics on the quality inspection results of the plurality of to-be-inspected objects according to types of the defects, wherein the quality inspection is used for detecting a plurality of defect types of the to-be-inspected objects (para(s). [0093]—see citation in claim 14 above—, where displaying the “number of defects by defect type” is performing statistics on the quality inspection results according to types of defects).
Allowable Subject Matter
Claims 6, 13, and 16-17 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JULIA Z YAO whose telephone number is (571)272-2870. The examiner can normally be reached Monday - Friday (8:30AM - 5PM).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Emily Terrell can be reached at (571)270-3717. 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.
/J.Z.Y./Examiner, Art Unit 2666
/MING Y HON/Primary Examiner, Art Unit 2666
Prosecution Insights