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 .
Notice to Applicant
The following is a Non-Final Office action. In response to Examiner’s Final Rejection of 12/16/2025, Applicant, on 2/5/2026, amended claims 1, 19 and 20; and added claim 23. Claims 1-23 are pending in this application and have been rejected below. Information Disclosure Statement filed on 3/18/2026 is acknowledged.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this
application is eligible for continued examination under 37 CFR 1.114, and the fee set
forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action
has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on
2/18/2026 has been entered.
Response to Arguments
Applicant’s arguments filed February 5, 2026 have been fully considered but they are not persuasive and/or are moot in view of the revised rejections. Applicant’s arguments will be addressed herein below in the order in which they appear in the response filed February 5, 2026.
On Pg. 8-9 of the Remarks, regarding 35 U.S.C. § 101 rejections, Applicant states the amended claim language (i) are not abstract because they recite specific machine- controlled steps and (ii) they recite various improvements to semiconductor wafer manufacturing and quality control technology. In response, Examiner finds the machine- controlled device specifically the imaging device is insufficient to amount to significantly more. (See MPEP 2106.05(f) – Mere Instructions to Apply an Exception – “Thus, for example, claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible.” Alice Corp., 134 S. Ct. at 235). Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims also fail to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, and/or an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. See 84 Fed. Reg. 55.
On Pg. 10 of the Remarks, regarding 35 U.S.C. § 103 rejections. Applicant states neither Gali nor Hu disclose amended claim language. In response, new ground(s) of rejection is made necessitated by amendment see MPEP 706.07a where Tang is now applied for Claims 1, 19 and 20. Regarding the 35 U.S.C. § 103 rejection, Applicant’s arguments with respect to claims has been considered but are moot in view of the new grounds of rejection.
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- 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 1-20 are directed to designing a workflow to perform a semiconductor inspection task.
Claim 1 recites a method for designing a workflow to perform a semiconductor inspection task, Claim 19 recites an article of manufacture for designing a workflow to perform a semiconductor inspection task and Claim 20 recites a system for designing a workflow to perform a semiconductor inspection task, which include acquiring imaging datasets of one or more portions a semiconductor object comprising integrated circuit patterns; receiving a user input as a natural language text describing one or more properties of a semiconductor inspection task of the semiconductor object; processing the user input; receiving a workflow proposal; and applying the workflow proposal, to process the imaging datasets of the one or more portions of the semiconductor object by automatically controlling execution of the semiconductor inspection task to generate processed inspection data.
As drafted, this is, under its broadest reasonable interpretation, within the Abstract idea grouping of “Mental Processes” – evaluation. The recitation of “system”; “computer”, “machine-readable hardware storage devices”, “imaging device” and “processing devices”, provide nothing in the claim elements to preclude the step from being “Mental Processes”- evaluation. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. The claims primarily recite the additional element of using computer components to perform each step. The “system”; “computer”, “machine-readable hardware storage devices”, “imaging device” and “processing devices” are recited at a high-level of generality, such that it amounts no more than mere instructions to apply the exception using a computer component. See MPEP 2106.05(f). Furthermore, the claim 1, claim 19 and claim 20 recite using one or more machine learning/NLP techniques. The specification discloses the semantic analysis at a high-level of generality, providing examples of different techniques that may be applied. The general use of a machine learning/NLP analysis does not provide a meaningful limitation to transform the abstract idea into a practical application. Therefore, currently, the machine learning/ natural language processing is solely used a tool to perform the instructions of the abstract idea. Accordingly, the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Accordingly, the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims also fail to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, and/or an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. See 84 Fed. Reg. 55. In particular, there is a lack of improvement to a computer or technical field in workflow analysis.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements “system”; “computer”, “machine-readable hardware storage devices”, “imaging device” and “processing devices” is insufficient to amount to significantly more. (See MPEP 2106.05(f) – Mere Instructions to Apply an Exception – “Thus, for example, claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible.” Alice Corp., 134 S. Ct. at 235). Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept.
The claim fails to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, adding unconventional steps that confine the claim to a particular useful application, and/or meaningful limitations beyond generally linking the use of an abstract idea to a particular environment. See 84 Fed. Reg. 55. Viewed individually or as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself. With regards to receiving data and step 2B, it is M2106.05(d)- Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information) and Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015). With regards to “machine learning” and step 2B, the machine learning is a tool to apply the judicial exception. With regards to step 2B and automatically controlling execution of the semiconductor inspection task. The specification defines the task as processing data (See Pg. 2 of Applicant’s Specification - A semiconductor inspection task can be organized as a data-flow and can comprise components such as data input, data preprocessing, data analysis, output postprocessing)
Examiner concludes that the additional elements in combination fail to amount to significantly more than the abstract idea based on findings that each element merely performs the same function(s) in combination as each element performs separately. The claim is not patent eligible. Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually.
Regarding Claim 19, a product must have a physical or tangible form in order to fall within one of these statutory categories. Digitech, 758 F.3d at 1348, 111 USPQ2d at 1719. Thus, the Federal Circuit has held that a product claim to an intangible collection of information, even if created by human effort, does not fall within any statutory category. Digitech, 758 F.3d at 1350, 111 USPQ2d at. Similarly, software expressed as code or a set of instructions detached from any medium is an idea without physical embodiment. See Microsoft Corp. v. AT&T Corp., 550 U.S. 437, 449, 82 USPQ2d 1400, 1407 (2007); see also Benson, 409 U.S. 67, 175 USPQ2d 675 (An "idea" is not patent eligible). Thus, a product claim to a software program that does not also contain at least one structural limitation (such as a "means plus function" limitation) has no physical or tangible form, and thus does not fall within any statutory category.
Even when a product has a physical or tangible form, it may not fall within a statutory category. For instance, a transitory signal, while physical and real, does not possess concrete structure that would qualify as a device or part under the definition of a machine, is not a tangible article or commodity under the definition of a manufacture (even though it is man-made and physical in that it exists in the real world and has tangible causes and effects), and is not composed of matter such that it would qualify as a composition of matter. Nuijten, 500 F.3d at 1356-1357, 84 USPQ2d at 1501-03. As such, a transitory, propagating signal does not fall within any statutory category. Mentor Graphics Corp. v. EVE-USA, Inc., 851 F.3d 1275, 1294, 112 USPQ2d 1120, 1133 (Fed. Cir. 2017); Nuijten, 500 F.3d at 1356-1357, 84 USPQ2d at 1501. Specifically, in Claim 19 the BRI of machine readable media encompasses non-statutory transitory forms of signal transmission, such as a propagating electrical or electromagnetic signal per se. See In re Nuijten, 500 F.3d 1346, 84 USPQ2d 1495 (Fed. Cir. 2007). When the BRI encompasses transitory forms of signal transmission, a rejection under 35 U.S.C. 101 as failing to claim statutory subject matter would be appropriate. Thus, a claim to a computer readable medium that can be a compact disc or a carrier wave covers a non-statutory embodiment and therefore should be rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter. See, e.g., Mentor Graphics v. EVE-USA, Inc., 851 F.3d at 1294-95, 112 USPQ2d at 1134 (claims to a "machine-readable medium" were non-statutory, because their scope encompassed both statutory random-access memory and non-statutory carrier waves).
Dependent Claims 2-18 and 21-23 recite receiving an update to modify the workflow proposal; storing the input data and/or the workflow proposal in one or more databases; the workflow proposal machine learning model comprises a conditional random field; collecting meta data values for meta data items describing properties of the input data, and/or the workflow; wherein the meta data items are organized in a hierarchical way; retrieving the meta data values for the meta data items ; wherein meta data items are selected from a predefined list of meta data items, and a new meta data item is automatically added to the list of meta data items when the meta data item is indicated multiple times for the input data and/or plurality of and/or the workflow proposal; using the meta data values to find similarities between different input data, and/or workflow proposals and the workflow proposal; wherein one or more meta data items are associated with a similarity relevance value indicating the relevance of the meta data item for the similarity of different input data, different workflow proposals, workflow proposals and the workflow proposal; wherein: meta data values for meta data items are associated with workflow proposals and with the semiconductor inspection task; the workflow proposal machine learning model receives further workflow proposals as input; and the further workflow proposals are associated with meta data values that are similar to the meta data values associated with semiconductor inspection task; storing the workflow proposal in one or more databases; adding missing information to the natural language text; obtaining training data comprising workflows containing sequences of action items and natural language texts, each natural language text one or more properties of the semiconductor inspection task of the object; and modifying parameters of the workflow proposal machine learning model, thereby reducing an objective function to train the workflow proposal machine learning model; wherein the training data comprises similarities of action items; deriving rules from the training data, and using the derived rules to evaluate a validity of sequences of action items; using the training data to derive associations between evaluation metrics and action items; wherein performing the semiconductor inspection task comprises using the imaging device to acquire at least one image of the semiconductor object; wherein the semiconductor inspection task comprises at least one member selected from the group consisting of defect detection, defect localization, defect segmentation, defect assessment, structure measurements, critical dimension measurements, and repair shape generation; wherein the patterns comprise nanoscale structures and further narrowing the abstract idea. These recited limitations in the dependent claims do not amount to significantly more than the above-identified judicial exceptions in Claims 1, 19 and 20. Regarding Claims, 2-3, 5, 7, 13-15, 21 and the additional elements of “computer”; “databases”; “imaging device” - it is M2106.05(d)- Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information). Regarding claim 4, 8, 12, 15 and 20, and the additional element of machine learning model - the specification discloses the machine learning at a high-level of generality, providing examples of different techniques that may be applied. The general use of a machine learning technique does not provide a meaningful limitation to transform the abstract idea into a practical application. Therefore, currently, the machine learning is solely used a tool to perform the instructions of the abstract idea.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-22 are rejected under 35 U.S.C. 103 as being unpatentable over Tang et al., US Publication No. 2021201037 A1, [hereinafter Tang], in view of Hu et al., US Publication No. 20200151869A1, [hereinafter Hu].
Regarding Claim 1,
Tang teaches
A method, comprising: activating an imaging device to acquire imaging datasets of one or more portions… (Tang Par. 23- “Additionally, or alternatively, the one or more artificial intelligence techniques may be used to identify, based on the one or more images, one or more discrepancies between the actual visual appearance of different parts, which may indicate relative conditions of the different parts (e.g., where an engine bay includes various parts that have dust and debris built up over time from normal driving and one particular part, such as a battery, has significantly less dust and debris, this may indicate that the one particular part is newer than the various other parts). In this way, the visual inspection based on the one or more artificial intelligence techniques can detect issues that may be in need of repair or maintenance in addition to identifying parts of the vehicle that have been repaired or replaced. In this way, computing and/or network resources may be conserved (e.g., resources that would otherwise be wasted by the potential purchaser researching or otherwise investigating whether there is an issue).”)
receiving a user input as a natural language text describing one or more properties of a… inspection task of the object (Tang Par. 17- For example, the inspection support platform may parse natural language descriptions to obtain data identifying a description of a plurality of historical inspections, outcomes of the plurality of historical inspections, information from vehicle history reports, and/or the like relating to a plurality of makes, models, and model years of vehicles, and may parse the data to identify which parts of the vehicle to be inspected are likely to be defective and/or in need of repair, and/or the like. In some implementations, the inspection support platform may determine, based on natural language processing, that a part is associated with a likelihood of being defective and/or in need of repair. Based on applying a rigorous and automated process associated with inspecting the vehicle, the inspection support platform enables recognition and/or identification of thousands or millions of data items for thousands or millions of parts, thereby increasing an accuracy and consistency of the generated workflow relative to requiring computing resources to be allocated for hundreds or thousands of technicians to manually generate a workflow based on the thousands or millions of data items.)
… to generate a prompt … from a natural language text describing one or more properties … of the object, each workflow proposal comprising a sequence of action items (Tang Par. 31-In some implementations, the extended reality device may prompt the user to provide input identifying the vehicle. For example, the extended reality device may prompt the user to select a manufacturer, model, and/or model year of the vehicle, to input the VIN, to capture an image of the VIN, to capture an image of the license plate, and/or the like. The extended reality device may provide the prompts to the user by displaying text on a display, displaying input buttons for selecting the manufacturer, model, and/or model year of the vehicle, providing audio instructions, and/or the like. The extended reality device may receive the user input, for example, via a touchscreen, a speech-based input device (e.g., a microphone), a gesture-recognition device, and/or the like.; Par. 33-34)
processing the user input … for a workflow proposal machine learning model the workflow proposal machine learning model
being configured to generate one or more workflow proposals … of the object, each workflow proposal comprising a sequence of action items (Tang Par. 3- obtaining, by the device, positional tracking information that represents a position and an orientation associated with the object depicted in the one or more video frames relative to a coordinate space that corresponds to the field of view of the device; obtaining, by the device, a workflow including a sequence of content items for visually inspecting the object using the extended reality capabilities of the device; and rendering, by the device, digital content associated with the workflow using the extended reality capabilities of the device, wherein rendering the digital content includes: placing a first set of content items on the one or more parts of the object that are depicted in the one or more video frames based on the positional tracking information, wherein the first set of content items includes information related to one or more visually observable qualities of the one or more parts; and selecting a next set of content items to be rendered by the device based on the sequence of content items associated with the workflow and feedback related to the one or more visually observable qualities of the one or more parts.: Par. 5)
receiving, from the workflow proposal machine learning model, a workflow proposal (Tang Par. 5-“ generate a workflow for visually inspecting the object based on a machine learning model generated using historical information to determine probabilities of the one or more parts of the object being defective, wherein the workflow includes a sequence of content items for visually inspecting the object using the extended reality capabilities of the device, wherein the sequence of content items includes a first set of content items to be rendered on the one or more parts of the object that are depicted in the one or more video frames, wherein the first set of content items includes information related to one or more visually observable qualities of the one or more parts, and wherein the sequence of content items includes a second set of content items to be rendered by the device based on feedback related to the one or more visually observable qualities of the one or more parts; and provide the workflow to permit the device to render the first set of content items and/or the second set of content items.);
applying the workflow proposal…to generate processed inspection data (Tang Par. 16-18- Some implementations described herein may provide an inspection support platform that generates a workflow to inspect a vehicle and operates in connection with a device having extended reality capabilities (e.g., a virtual reality device, an augmented reality device, a mixed reality device, and/or the like) to render digital content to visualize information related to a condition of the vehicle, to direct a potential purchaser through the workflow to inspect the vehicle, and to demonstrate features of the vehicle.);
Tang teaches workflow analysis but fails to teach the specific semiconductor feature and the feature is expounded upon by Hu:
…of a semiconductor object comprising integrated circuit patterns’ (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above “)
…of the semiconductor inspection task of the semiconductor object…(Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
…of the semiconductor inspection task of the semiconductor object… semiconductor inspection (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
…process the imaging datasets of the one or more portions of the semiconductor object by perform automatically controlling execution of the semiconductor inspection task. (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.
Tang and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Tang, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Regarding Claim 2, The method of claim 1, further comprising receiving an update to modify the workflow proposal (Tang Par. 81- . The inspection support platform may process the information indicating the conditions of the tire treads and transmit an updated workflow, to the extended reality device, based on the information indicating the conditions of the tire treads. For example, if the information indicated that one tire has a tread in poor condition but the other three tires have treads in good condition, the inspection support platform may process the information and update the workflow, based on the feedback regarding the tire tread conditions, to include a next step of checking the tire pressure for each of the tires because the tire with poor-conditioned tread may have low pressure or the wheel may be out of alignment.).
Regarding Claim 3, The method of claim 1, further comprising storing the input data and/or the workflow proposal in one or more databases. (Tang Par. 97-98-In some implementations, the inspection support platform and/or the extended reality device may automatically apply for a loan to purchase the vehicle based on information regarding the user, such as name, address, telephone number, and/or the like, which may be stored in a remote data structure, stored on the extended reality device (e.g., when the user owns the extended reality device), and/or the like.).
Regarding Claim 4, The method of claim 1, wherein the workflow proposal machine learning model comprises a conditional random field. (Goli Par. 54; Par. 57- In one embodiment, validator 220 can also execute other static preprocessing functions. For example, validator 220 may modify extracted information to conform to a standard. For example where an extracted section number in a candidate action item row is only 5 digits, validator 220 may execute a rule to insert a leading zero into the section number, and upon confirming that the updated section number—section title pair is consistent with the corresponding pair in the master list, retain the candidate action item row rather than deleting it. Note that—as with the ‘leading zero insertion’ rule—rules may be conditional based on the content of the candidate action item object, and may not be applied fully if one or more preconditions fail. Other static preprocessing, such as deduplication, may also be performed by validator 220.).
Regarding Claim 5, The method of claim 1, further comprising collecting meta data values for meta data items describing properties of the input data, and/or of the workflow. (Tang Par. 19- In some implementations, the inspection support platform generates a workflow that includes a sequence of content items for the extended reality device to render to direct a potential purchaser through the inspection of the vehicle. For example, the sequence may include a step of checking the tires of the vehicle, and the inspection support platform may generate a workflow including digital content overlays to be rendered on the tires of the vehicle to highlight the tires and content (e.g., text, video, animation, and/or the like) instructing the user how to inspect the tires (e.g., for damage or wear). In this way, the extended reality device may direct a potential purchaser through an organized, efficient, and comprehensive inspection that conserves computing resources (e.g., processing resources, memory resources, power resources, communication resources, and/or the like) and/or network resources that would otherwise be consumed by the potential purchaser researching or investigating (e.g., via online research) the results of a haphazard, inefficient, and incomprehensive inspection and/or how to conduct an organized, efficient, and comprehensive inspection).
Regarding Claim 6, The method of claim 5, wherein the meta data items are organized in a hierarchical way. (Tang Par. 3- placing a first set of content items on the one or more parts of the object that are depicted in the one or more video frames based on the positional tracking information, wherein the first set of content items includes information related to one or more visually observable qualities of the one or more parts; and selecting a next set of content items to be rendered by the device based on the sequence of content items associated with the workflow and feedback related to the one or more visually observable qualities of the one or more parts.; Par. 41.).
Regarding Claim 7, The method of claim 5, further comprising retrieving meta data values for the meta data items . (Tang Par. 41- In some implementations, the inspection support platform may use a classification technique, such as a logistic regression classification technique, a random forest classification technique, a gradient boosting machine learning (GBM) technique, and/or the like, to determine a categorical outcome (e.g., that a part has a high likelihood of being defective, that a part has a low likelihood of being defective, and/or the like).; Par. 114).
Regarding Claim 8, The method of claim 5, further comprising applying a machine learning model for meta data extraction to the input data, and the natural language text, the machine learning model for meta data extraction being configured to collect the meta data values for the meta data items from input data and a natural language text. (Tang Par.17-For example, the inspection support platform may parse natural language descriptions to obtain data identifying a description of a plurality of historical inspections, outcomes of the plurality of historical inspections, information from vehicle history reports, and/or the like relating to a plurality of makes, models, and model years of vehicles, and may parse the data to identify which parts of the vehicle to be inspected are likely to be defective and/or in need of repair, and/or the like. In some implementations, the inspection support platform may determine, based on natural language processing, that a part is associated with a likelihood of being defective and/or in need of repair).
Regarding Claim 9, The method of claim 5, wherein meta data items are selected from a predefined list of meta data items, and a new meta data item is automatically added to the list of meta data items when the meta data item is indicated multiple times for the input data and/or workflow proposals and/or the workflow. (Tang Par. 55; Par. 146- As further shown in FIG. 5, process 500 may include rendering the plurality of content items according to a sequence defined in a workflow for guiding the user through the visual inspection of the vehicle and, when rendering the plurality of content items, identifying the one or more parts that are visible in the field of view of the device, determining a first subset of the plurality of content items that relate to a condition of the one or more parts that are visible in the field of view of the device, superimposing the first subset of the plurality of content items over images of the one or more parts of the vehicle on a display of the device based on the positional tracking information, and selecting a next subset of the plurality of content items to be rendered according to the sequence defined in the workflow based on feedback indicating that the user has finished examining the one or more parts that are visible in the field of view of the device (block 540).).
Regarding Claim 10, The method of claim 5, further comprising using the meta data values to find similarities between different input data and/or work- flow proposals and the workflow proposal. (Tang Par. 34- The inspection support platform may obtain the historical information from one or more sources, such as a vehicle manufacturer, a government agency, a vehicle history aggregator, a vehicle repair shop, a vehicle dealer, a financial institution (e.g., a bank or a credit card issuer), a vehicle-part manufacturer, a vehicle-part merchant, a law enforcement agency, a service provider (e.g., offering access to the inspection support platform), a consumer protection agency, and/or the like. In some implementations, the inspection support platform may limit the data obtained to data specific to the make, model, and year of the vehicle to be inspected, to the make, model, and/or year of the vehicle to be inspected, to a similar make, a similar model, and/or a similar year of the vehicle to be inspected, and/or the like. By limiting the data, the inspection support platform may generate a workflow that is optimized to the vehicle to be inspected, which may make efficient use of computing resources during the inspection process. ).
Regarding Claim 11, The method of claim 5, wherein one or more meta data items are associated with a similarity relevance value indicating the relevance of the meta data item for the similarity of different input data, different workflow proposals, workflow proposals and the workflow proposal. (Tang Par. 37- As an example, the inspection support platform may determine whether past inspections of a part are associated with a threshold probability of that part being a defective part for a particular make, model, and model year of vehicle. In some implementations, the inspection support platform may use a scoring system (e.g., with relatively high scores and/or relatively low scores) to identify and/or classify parts as being potentially defective or in need of repair (hereinafter “defective” will cover both defective and not yet defective but in need of repair) or potentially not being defective or in need of repair (hereinafter “defect-free” will cover both not defective and not in need of repair). In this case, the inspection support platform may determine that a relatively high score (e.g., as having a high likelihood or a high probability) is to be assigned to a part that is determined to have the same or similar characteristics of a part that has been identified as defective in historical information for the same or similar make, model, and/or year of vehicle. In contrast, the inspection support platform may determine that a relatively low score (e.g., as having a low likelihood or a low probability) is to be assigned to a part that is determined to have the same or similar characteristics of a part that has been identified as defect-free in historical information for the same or similar make, model, and/or year of vehicle.).
Regarding Claim 12, The method of claim 5, wherein: meta data values for meta data items are associated with workflow …; the workflow proposal machine learning model receives further workflow proposals as input; and the further workflow proposals are associated with meta data values that are similar to the meta data values associated with the … task. (Tang Claim 15- generate, based on historical information, a model for generating a workflow; generate, based on determining the probability and generating the model, the workflow for the other device to visually inspect the one or more parts of the object; and provide, to the other device, the workflow to permit the other device to visually inspect the object.; Par. 17).
Tang teaches workflow analysis but fails to teach the specific semiconductor feature and the feature is expounded upon by Hu:
…of the semiconductor inspection task(Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
… semiconductor inspection task. (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.
Tang and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Tang, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Regarding Claim 13, The method of claim 1, further comprising storing the workflow proposal in one or more databases. (Tang Par. 97-98-In some implementations, the inspection support platform and/or the extended reality device may automatically apply for a loan to purchase the vehicle based on information regarding the user, such as name, address, telephone number, and/or the like, which may be stored in a remote data structure, stored on the extended reality device (e.g., when the user owns the extended reality device), and/or the like.).
Regarding Claim 14, The method of claim 1, further comprising: adding missing information to the natural language text. (Tang Par. 55- In some implementations, the inspection support platform may generate a dynamic workflow that changes based on information obtained during the inspection. For example, the dynamic workflow may eliminate, skip, insert, and/or add one or more later steps in the inspection process after receiving information gathered during one or more earlier steps in the inspection process. In this way, the dynamic workflow may optimize the use of computing resources (e.g., processing resources, memory resources, power resources, communication resources, and/or the like) and/or network resources.).
Regarding Claim 15, The method of claim 1, further comprising: obtaining training data comprising workflows containing sequences of action items and natural language texts, each natural language text describing one or more properties of the semiconductor inspection task …; and modifying parameters of the workflow proposal machine learning model, thereby reducing an objective function to train the workflow proposal machine learning model. (Tang Par. 18- In some implementations, the inspection support platform may generate and train a model to determine likelihoods of parts being defective and/or in need of repair using historical information relating to a plurality of historical inspections, outcomes of the plurality of historical inspections, information from vehicle history reports, and/or the like. Based on the determined likelihoods of parts being defective, the inspection support platform may generate a workflow that indicates what parts of the vehicle to inspect and in what order the parts should be inspected. In this way, computing and/or network resources may be conserved (e.g., resources that would otherwise be wasted by the potential purchaser researching or otherwise investigating which parts should be inspected and in what order).; Par. 37-40).
Goli teaches workflow analysis and the feature is expounded upon by Hu:
…a semiconductor inspection task of the object (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.
Tang and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Tang, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Regarding Claim 16, The method of claim 15, wherein the training data comprises similarities of action items. (Goli Par. 37- In this case, the inspection support platform may determine that a relatively high score (e.g., as having a high likelihood or a high probability) is to be assigned to a part that is determined to have the same or similar characteristics of a part that has been identified as defective in historical information for the same or similar make, model, and/or year of vehicle. In contrast, the inspection support platform may determine that a relatively low score (e.g., as having a low likelihood or a low probability) is to be assigned to a part that is determined to have the same or similar characteristics of a part that has been identified as defect-free in historical information for the same or similar make, model, and/or year of vehicle.).
Regarding Claim 17, The method of claim 15, further comprising deriving rules from the training data, and using the derived rules to evaluate a validity of sequences of action items. (Tang Par 40- In some implementations, the inspection support platform may perform a training operation when generating the model. For example, the inspection support platform may portion data of the historical information into a training set (e.g., a set of data to train the model), a validation set (e.g., a set of data used to evaluate a fit of the model and/or to fine tune the model), a test set (e.g., a set of data used to evaluate a final fit of the model), and/or the like. In some implementations, the inspection support platform may preprocess and/or perform dimensionality reduction to reduce the data of the historical information to a minimum feature set. In some implementations, the inspection support platform may train the model on this minimum feature set, thereby reducing processing to train the machine learning model, and may apply a classification technique, to the minimum feature set.).
Regarding Claim 18, The method of claim 15, further comprising using the training data to derive associations between evaluation metrics and action items. (Tang Par 95- In some implementations, after completing the workflow, the inspection support platform and/or the extended reality device may automatically perform one or more actions (e.g., based on information regarding the vehicle obtained during the inspection, based on user feedback on the one or more demonstrated features of the vehicle, and/or the like). For example, the one or more actions may include recommending an estimated value of the vehicle based on results of an inspection of the vehicle (e.g., number of and/or cost of repairing defective parts, odometer reading, condition of the vehicle, and/or the like), aggregated pricing data for similar vehicles (e.g., same manufacturer, same model, same model year, same feature package, same color, same class of vehicle, and/or the like), the location of the vehicle, and/or the like. In this way, computing and/or network resources may be conserved because the user may avoid performing research to determine an estimated value of the vehicle based on results of the inspection of the vehicle.)
Regarding Claim 19,
Tang teaches
One or more machine-readable hardware storage devices comprising instructions that are executable by a computer to perform operations comprising: activating an imaging device to acquire imaging datasets of one or more portions… (Tang Par. 5; Par. 23- “Additionally, or alternatively, the one or more artificial intelligence techniques may be used to identify, based on the one or more images, one or more discrepancies between the actual visual appearance of different parts, which may indicate relative conditions of the different parts (e.g., where an engine bay includes various parts that have dust and debris built up over time from normal driving and one particular part, such as a battery, has significantly less dust and debris, this may indicate that the one particular part is newer than the various other parts). In this way, the visual inspection based on the one or more artificial intelligence techniques can detect issues that may be in need of repair or maintenance in addition to identifying parts of the vehicle that have been repaired or replaced. In this way, computing and/or network resources may be conserved (e.g., resources that would otherwise be wasted by the potential purchaser researching or otherwise investigating whether there is an issue).”)
receiving a user input as a natural language text describing one or more properties of a… inspection task of the object (Tang Par. 17- For example, the inspection support platform may parse natural language descriptions to obtain data identifying a description of a plurality of historical inspections, outcomes of the plurality of historical inspections, information from vehicle history reports, and/or the like relating to a plurality of makes, models, and model years of vehicles, and may parse the data to identify which parts of the vehicle to be inspected are likely to be defective and/or in need of repair, and/or the like. In some implementations, the inspection support platform may determine, based on natural language processing, that a part is associated with a likelihood of being defective and/or in need of repair. Based on applying a rigorous and automated process associated with inspecting the vehicle, the inspection support platform enables recognition and/or identification of thousands or millions of data items for thousands or millions of parts, thereby increasing an accuracy and consistency of the generated workflow relative to requiring computing resources to be allocated for hundreds or thousands of technicians to manually generate a workflow based on the thousands or millions of data items.)
processing the user input to generate a prompt for a workflow proposal machine learning model, the workflow proposal machine learning model being configured to generate one or more workflow proposals from a natural language text describing one or more properties of the …inspection task of the … object, each workflow proposal comprising a respective sequence of … inspection action items (Tang Par. 31-In some implementations, the extended reality device may prompt the user to provide input identifying the vehicle. For example, the extended reality device may prompt the user to select a manufacturer, model, and/or model year of the vehicle, to input the VIN, to capture an image of the VIN, to capture an image of the license plate, and/or the like. The extended reality device may provide the prompts to the user by displaying text on a display, displaying input buttons for selecting the manufacturer, model, and/or model year of the vehicle, providing audio instructions, and/or the like. The extended reality device may receive the user input, for example, via a touchscreen, a speech-based input device (e.g., a microphone), a gesture-recognition device, and/or the like.; Par. 3-5; Par. 33-34)
receiving, from the workflow proposal machine learning model, a workflow proposal (Tang Par. 5-“ generate a workflow for visually inspecting the object based on a machine learning model generated using historical information to determine probabilities of the one or more parts of the object being defective, wherein the workflow includes a sequence of content items for visually inspecting the object using the extended reality capabilities of the device, wherein the sequence of content items includes a first set of content items to be rendered on the one or more parts of the object that are depicted in the one or more video frames, wherein the first set of content items includes information related to one or more visually observable qualities of the one or more parts, and wherein the sequence of content items includes a second set of content items to be rendered by the device based on feedback related to the one or more visually observable qualities of the one or more parts; and provide the workflow to permit the device to render the first set of content items and/or the second set of content items.);
applying the workflow proposal…to generate processed inspection data (Tang Par. 16-18- Some implementations described herein may provide an inspection support platform that generates a workflow to inspect a vehicle and operates in connection with a device having extended reality capabilities (e.g., a virtual reality device, an augmented reality device, a mixed reality device, and/or the like) to render digital content to visualize information related to a condition of the vehicle, to direct a potential purchaser through the workflow to inspect the vehicle, and to demonstrate features of the vehicle.);
Tang teaches workflow analysis but fails to teach the specific semiconductor feature and the feature is expounded upon by Hu:
…of a semiconductor object comprising integrated circuit patterns’ (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above “)
…of the semiconductor inspection task of the semiconductor object…(Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
…of the semiconductor inspection task of the semiconductor object… semiconductor inspection (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
…process the imaging datasets of the one or more portions of the semiconductor object by perform automatically controlling execution of the semiconductor inspection task. (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.
Tang and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Tang, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Regarding Claim 20,
Tang teaches
A system, comprising: one or more processing devices; an imaging device; and one or more machine-readable hardware storage devices comprising instructions that are executable by one or more processing devices to perform operations comprising: activating an imaging device to acquire imaging datasets of one or more portions… (Tang Par. 119-123’ Par. 23- “Additionally, or alternatively, the one or more artificial intelligence techniques may be used to identify, based on the one or more images, one or more discrepancies between the actual visual appearance of different parts, which may indicate relative conditions of the different parts (e.g., where an engine bay includes various parts that have dust and debris built up over time from normal driving and one particular part, such as a battery, has significantly less dust and debris, this may indicate that the one particular part is newer than the various other parts). In this way, the visual inspection based on the one or more artificial intelligence techniques can detect issues that may be in need of repair or maintenance in addition to identifying parts of the vehicle that have been repaired or replaced. In this way, computing and/or network resources may be conserved (e.g., resources that would otherwise be wasted by the potential purchaser researching or otherwise investigating whether there is an issue).”)
receiving a user input as a natural language text describing one or more properties of a … inspection task of the …object (Tang Par. 17- For example, the inspection support platform may parse natural language descriptions to obtain data identifying a description of a plurality of historical inspections, outcomes of the plurality of historical inspections, information from vehicle history reports, and/or the like relating to a plurality of makes, models, and model years of vehicles, and may parse the data to identify which parts of the vehicle to be inspected are likely to be defective and/or in need of repair, and/or the like. In some implementations, the inspection support platform may determine, based on natural language processing, that a part is associated with a likelihood of being defective and/or in need of repair. Based on applying a rigorous and automated process associated with inspecting the vehicle, the inspection support platform enables recognition and/or identification of thousands or millions of data items for thousands or millions of parts, thereby increasing an accuracy and consistency of the generated workflow relative to requiring computing resources to be allocated for hundreds or thousands of technicians to manually generate a workflow based on the thousands or millions of data items.)
processing the user input to generate a prompt for a workflow proposal machine learning model, the workflow proposal machine learning model being configured to generate one or more workflow proposals from a natural language text describing one or more properties of the … inspection task of the … object, each workflow proposal comprising a respective sequence of … inspection action items (Tang Par. 3-5 Par. 31-In some implementations, the extended reality device may prompt the user to provide input identifying the vehicle. For example, the extended reality device may prompt the user to select a manufacturer, model, and/or model year of the vehicle, to input the VIN, to capture an image of the VIN, to capture an image of the license plate, and/or the like. The extended reality device may provide the prompts to the user by displaying text on a display, displaying input buttons for selecting the manufacturer, model, and/or model year of the vehicle, providing audio instructions, and/or the like. The extended reality device may receive the user input, for example, via a touchscreen, a speech-based input device (e.g., a microphone), a gesture-recognition device, and/or the like.; Par. 33-34)
receiving, from the workflow proposal machine learning model, a workflow proposal (Tang Par. 5-“ generate a workflow for visually inspecting the object based on a machine learning model generated using historical information to determine probabilities of the one or more parts of the object being defective, wherein the workflow includes a sequence of content items for visually inspecting the object using the extended reality capabilities of the device, wherein the sequence of content items includes a first set of content items to be rendered on the one or more parts of the object that are depicted in the one or more video frames, wherein the first set of content items includes information related to one or more visually observable qualities of the one or more parts, and wherein the sequence of content items includes a second set of content items to be rendered by the device based on feedback related to the one or more visually observable qualities of the one or more parts; and provide the workflow to permit the device to render the first set of content items and/or the second set of content items.);
and applying the workflow proposal…to generate processed inspection data (Tang Par. 16-18- Some implementations described herein may provide an inspection support platform that generates a workflow to inspect a vehicle and operates in connection with a device having extended reality capabilities (e.g., a virtual reality device, an augmented reality device, a mixed reality device, and/or the like) to render digital content to visualize information related to a condition of the vehicle, to direct a potential purchaser through the workflow to inspect the vehicle, and to demonstrate features of the vehicle.);
Tang teaches workflow analysis but fails to teach the specific semiconductor feature and the feature is expounded upon by Hu:
…of a semiconductor object comprising integrated circuit patterns’ (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above “)
…of the semiconductor inspection task of the semiconductor object…(Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
…of the semiconductor inspection task of the semiconductor object… semiconductor inspection (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
…process the imaging datasets of the one or more portions of the semiconductor object by perform automatically controlling execution of the semiconductor inspection task. (Hu Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.
Tang and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Tang, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Regarding Claim 21, Tang in view of Hu teach the method of claim 1…
using the imaging device to acquire at least one image (Tang Par. 26- The extended reality device, when running the application, may access a camera of the extended reality device and display (e.g., on a touchscreen display) a field of view of the camera. The user may orient the extended reality device such that a vehicle (e.g., a real vehicle to be inspected) is within the field of view.)
Tang teaches workflow analysis but fails to teach the specific semiconductor feature and the feature is expounded upon by Hu:
wherein performing the semiconductor inspection task comprises using the imaging device to acquire at least one image of the semiconductor object (Hu Abstract-“ Scheduling automated visual inspection tasks includes capturing an image of a component to be inspected. A visual inspection model is formed with a model engine as a composite model of utility modules and functional modules to perform visual inspection of the image of the component. An abstract processing workflow of the visual inspection model is derived with a scheduler including dependencies between the utility modules and the functional modules; Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
Tang and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Tang, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Regarding Claim 22, Tang in view of Hu teach the method of claim 1…
wherein the…inspection task comprises at least one member selected from the group consisting of defect detection, defect localization, defect segmentation, defect assessment, structure measurements, critical dimension measurements, and repair shape generation (Tang Par. 17-18)
Tang teaches workflow analysis but fails to teach the specific semiconductor feature and the feature is expounded upon by Hu:
wherein the semiconductor inspection task comprises at least one member selected from the group consisting of defect detection, defect localization, defect segmentation, defect assessment, structure measurements, critical dimension measurements, and repair shape generation. (Hu Abstract-“ Scheduling automated visual inspection tasks includes capturing an image of a component to be inspected. A visual inspection model is formed with a model engine as a composite model of utility modules and functional modules to perform visual inspection of the image of the component. An abstract processing workflow of the visual inspection model is derived with a scheduler including dependencies between the utility modules and the functional modules; Par. 38-“ According to an embodiment of the present invention, a visual inspection system can include a composite model 400 to identify defects 401 in an image 101 of a component on a production line. The composite model 400 can be a utility model that includes models 410 corresponding to categories of components or portions of components. For example, for visual inspection of a semiconductor chip, a model engine, such as the model engine of FIG. 2 described above, can implement the composite model 400 by initializing a model 410 corresponding to the shell, a model 410 corresponding to electrodes, a model 410 corresponding to an antenna, as well as models for any other portion of the chip to be inspected, as model instances on, e.g., a server or virtual machine.”)
Goli and Hu are directed to workflow analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon specific types of inspection tasks of Goli, as taught by Hu, by utilizing semiconductor inspection with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Goli with the motivation of improving the efficiency of executing each processing flow, the visual inspection system (Hu Par. 21).
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Tang et al., US Publication No. 2021201037 A1, [hereinafter Tang], in view of Hu et al., US Publication No. 20200151869A1, [hereinafter Hu], in further view of Wei et al, "Electrical Characterization of FEOL Bridge Defects in Advanced Nanoscale Devices Using TCAD Simulations," 2018 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA), Singapore, 2018, pp. 1-4, [hereinafter Wei].
Tang in view Hu teach inspection tasks and the feature is expounded upon by Wei:
wherein the patterns comprise nanoscale structures. (Wei Abstract-“ In this work, we present the electrical characterization of various Front-End-Of-Line (FEOL) bridge defects location using Technology Computer Aided Design (TCAD) based simulation. The electrical characteristics obtained from simulation is useful in identifying the possible locations of the bridge defects. The simulation result correlates well with nano-probing result collected on actual failing devices. Furthermore, simulation of potential defects provides a quick way of understanding how the defect may influence the electrical behavior of transistors.”)
Tang, Hu and Wei are directed to inspection analysis. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon inspection analysis of Tang in view of Hu, as taught by Wei, by utilizing additional inspection analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Tang in view of Hu with the motivation of understanding influence of defect analysis (Wei Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: US Patent No. US11847400B2 to Pillai et al.- Abstract-“ Methods for generation of shape data for a set of electronic designs include inputting a set of shape data, where the set of shape data represents a set of shapes for a device fabrication process. A convolutional neural network is used on the set of shape data to determine a set of generated shape data, where the convolutional neural network comprises a generator trained with a pre-determined set of discriminators. The set of generated shape data comprises a scanning electron microscope (SEM) image.”
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Chesiree Walton, whose telephone number is (571) 272-5219. The examiner can normally be reached from Monday to Friday between 8 AM and 5 PM. If any attempt to reach the examiner by telephone is unsuccessful, the examiner’s supervisor, Patricia Munson, can be reached at (571) 270-5396. The fax telephone numbers for this group are either (571) 273-8300 or (703) 872-9326 (for official communications including After Final communications labeled “Box AF”).
Another resource that is available to applicants is the Patent Application Information Retrieval (PAIR). Information regarding the status of an application can be obtained from the (PAIR) system. Status information for published applications may be obtained from either Private PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, please feel free to contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
Applicants are invited to contact the Office to schedule an in-person interview to discuss and resolve the issues set forth in this Office Action. Although an interview is not required, the Office believes that an interview can be of use to resolve any issues related to a patent application in an efficient and prompt manner.
Sincerely,
/CHESIREE A WALTON/ Examiner, Art Unit 3624
Prosecution Insights