DETAILED ACTION
Notice of Pre-AIA or AIA Status
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 1/28/26 has been entered.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-5, 7-15 and 17-22 are pending in the application. Claims 1, 11 and 20 have been amended , and claims 6 and 16 have been canceled.
Response to Arguments
Applicant’s arguments filed 1/28/2026 with respect to claim(s) 1 have been considered but are moot in view of new ground(s) of rejections. The scope of claim 1 has been changed due to the amendment.
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.
Claim(s) 1, 5, 8, 10-11, 15, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (US 2018/0293552 A1, hereafter Zhang), in view of Tsubota (US 20050251303 A1).
As per claim 1, Zhang teaches an analysis apparatus (Abstract; FIG. 12-13) comprising:
a hardware processor (FIG. 12); and
a database, wherein the database stores a correspondence relationship between a recognition class and predetermined information (para. [0086] “In this implementation, each damage type can be set to correspond to one maintenance plan. For example, severe deformation corresponds to component replacement, minor deformation needs metal plating, and a slight scrape needs spray paint”);
the hardware processor
acquires input data including an image (FIG. 1 S1 “TO-BE-PROCESSED IMAGES”);
identifies any one of predetermined recognition classes by inputting the acquired input data to a machine learning model trained in advance with training data, wherein the predetermined recognition classes are different defects of a product (FIG. 1 S4; FIG. 5; para. [0067] “In this implementation, the damage type can include types such as a slight scrape, a severe scrape, minor deformation, moderate deformation, severe deformation, damage, and in need of disassembling for an examination”; para. [0068] “In this implementation, a damage identification model used to identify a damaged part and a damage type in an image can be pre-constructed by using a designed machine learning algorithm. After sample training, the damage identification model can identify one or more damaged parts in the to-be-processed images and corresponding damage types”; Before identifying the predetermined recognition classes, Zhang identifies damaged components and one or more damaged parts in the damaged components. The damaged components include, for example, a front bumper, a left front door, a rear tail lamp, etc. The identified vehicle components are regarded as respective products. See FIG. 1-3, para. [0040]);
analyzes the correspondence relationship between the recognition class and the predetermined information by using the database (para. [0086]; para. [0088]); and
outputs an analysis result (FIG. 13; FIG. 14 #1416).
Zhang, however, does not teach the amended limitation: “the predetermined information are corresponding causes of the defects of the predetermined recognition classes” and “the correspondence relationship is based on knowledge of a skilled worker, a past repair history, or both”.
Tsubota in an analogous field discloses a server includes statistical processing section for sequentially statistically processing a ranking of causes of a defect on the basis of defect information on a vehicle transmitted by the inspection terminal (Abstract). The server 2 is provided with an inspection master database 11 and an inspection result database 12. The inspection master database 11 is provided with a library 11a that stores inspection jobs and repair methods for defects and their causes (See FIG. 1, para. [0030]-[0031]). If any defect is eliminated as a result of the inspections, defect information (inspection target, inspection contents, inspection site, and defect) and the cause of the defect are transmitted to the server 2 and stored in the inspection result database 12. The server 2 statistically processes ranking information on the causes of defects contained in defect information, on a daily basis (para. [0039]-[0040]). As shown in FIG. 6 and described in para. [0055-0056], the displayed ranking information on the causes of the defect includes, for example, "causes unknown (probability: 25%)", which is displayed first, and "inappropriate mounting (probability: 25%)", which is displayed second. The repairer selects a cause with a higher probability from the ranking information on the causes of the defect. Note each defect corresponds to a class. Therefore, either database 11 or 12 stores correspondence relationship between a recognized defect class and causes of the defect.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Zhang to include the teaching of Tsubota to include a database that stores predetermined information which are corresponding causes of the defects of the predetermined recognition classes. Doing so would “provide a system for managing vehicle inspections which enables the display of ranking of possible causes of a defect and which also enables the display of ranking of possible repair methods for the cause of the defect to support identification of the cause of the defect and the repair method for the cause” (Tsubota [0010]).
Tsubota further teaches that in conventional automobile production lines the estimation of the cause of the defect during a repair stage depends on the worker’s knowledge and experience. The probability of correctly estimating the cause of the defect also depends on the skill of the worker (para. [0007]-[0008]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Zhang to include the teaching of Tsubota to identify defect classes and corresponding causes based on knowledge of a skilled worker. The motivation for including Tsubota is to provide a conventional cause estimation method as suggested by Tsubota (para. [0005]).
As per claim 5, dependent upon claim 1, Zhang in view of Tsubota teaches
the machine learning model is a neural network (Zhang FIG. 5; para. [0068] “In another implementation of the method provided by the present application, the damage identification model can be constructed based on a convolutional neural network (Convolutional Neural Network, CNN) and a region proposal network (Region Proposal Network, RPN) with reference to a fully connected layer and damage sample pictures trained by an input model”), and
the hardware processor inputs the input data to the neural network and converts the input data into any one of the recognition classes and a certainty factor of the recognition class (Zhang FIG. 1 S1, S4 and S5; FIG. 5; para. [0075] “… and data information of a confidence level that indicates an authenticity degree of the damage type”).
As per claim 8, dependent upon claim 5, Zhang in view of Tsubota teaches the hardware processor weights the certainty factor in accordance with a degree of importance set for each of the recognition classes converted by the hardware processor (Zhang para. [0079] “In a specific example, in an image P, vehicle components are identified as a left front door and a left front fender in S2, component regions of the two vehicle components respectively located in the image P at (r1, r2), corresponding to confidence levels (p1, p2). In S3, it is identified that there is a slight scrape (one of the damage types) in the image P, the damage region of the mild scratch in the picture P is r3, and the confidence level is p3. After processing the correspondence of the picture location region, the mild scratch region r3 is identified in the component region r1 of the front left door. Therefore, it is identified that the damaged component is the front left door, and the damage region of the damaged component is r3. The damage type of the damaged component in the single image P is a slight scrape, and a confidence level is p1*p3”; Therefore the certainty factor (e.g. p3) of a damage type (e.g. slight scrape) is weighted by a degree of importance (e.g. p1)), and analyzes, using the database, a correspondence relationship between the recognition class having a highest weighted certainty factor and the predetermined information (para. [0081] “Correspondingly, the damage type with the highest damage degree is determined as the damage type of the damaged component”).
As per claim 10, Zhang in view of Tsubota teaches an analysis system comprising: the analysis apparatus according to claim 1 (See rejections applied to claim 1); and a storage section that stores the machine learning model and the database (Zhang FIG. 12-13; para. [0073] “ In addition, an algorithm server can further be set up to store a constructed damage identification model”; para. [0086] “In this implementation, each damage type can be set to correspond to one maintenance plan. For example, severe deformation corresponds to component replacement, minor deformation needs metal plating, and a slight scrape needs spray paint”).
Per claim 11, an independent medium claim, all the limitations recited therein have been analyzed in rejections applied to apparatus claim 1 above.
Claim 15, dependent upon claim 11, is rejected as applied to claim 5 above.
Claim 18, dependent upon claim 15, is rejected as applied to claim 8 above.
Per claim 20, an independent method claim, all the limitations recited therein have been analyzed in rejections applied to apparatus claim 1 above.
Claim(s) 2, 9, 12, 19 and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Tsubota, as applied above to claims 1 and 11 respectively, and further in view of HIROSHI et al. (JP 2005197437 A, published 2005-07-21, see attached English translation, hereafter HIROSHI).
As per claim 2, Zhang in view of Tsubota does not teach the claimed limitations.
HIROSHI in an analogous field discloses a system for defect detection and corresponding cause identification. Specifically, once a defect is detected, a defect mode database, which includes a one-to-one correspondence between defect modes (defect classification, defect distribution, etc.) and contaminant elements and types of apparatuses, i.e., a type of an apparatus which is a cause of the defect, is used to identify the apparatus type (Abstract; Description para. [0008-0009]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Zhang and Tsubota to include the teaching of HIROSHI to include a database that stores a correspondence relationship between the recognition class of a defect and an apparatus type, and analyze the correspondence relationship between the recognition class of the defect and the apparatus type by using the database. Doing so would provide a technology that enables the accurate identification of the equipment causing an abnormality as recognized by HIROSHI (para. [0005]).
As per claim 9, dependent upon claim 2, Zhang in view of Tsubota and HIROSHI teaches the hardware processor accumulates identification results by the hardware processor of respective images of different analysis targets of a same product, and detects the apparatus type through analysis based on a plurality of accumulated identification results (Zhang para. [0103] “Further, in another implementation, the combining damaged parts belonging to the same damaged component can include: selecting and combining damaged parts in K to-be-processed images in descending order of confidence levels from to-be-processed images that belong to the same damage component in an image cluster, where K≥2”; That is to say, the identification result from K images with damaged parts belonging to the same damaged component is used to identify the damage type, and the corresponding damaged component is determined.)
Claim 12, dependent upon claim 11, is rejected as applied to claim 2 above.
Claim 19, dependent upon claim 12, is rejected as applied to claim 9 above.
As per claim 21, dependent upon claim 1, Zhang in view of Tsubota and HIROSHI teaches that the predetermined information is a type of the apparatus that has caused the defect of the product (HIROSHI Abstract; Description para. [0008-0009]), a monitoring place where the defect of the product has occurred, or relevance of the abnormal behavior.
Claim 22, dependent upon claim 11, is rejected as applied to claim 21 above.
Claim(s) 3-4 and 13-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Tsubota, as applied above to claims 1 and 11 respectively, and further in view of Ucar et al. (US Publication 2021/0221382 A1, hereafter Ucar) and Nakashima et al. (US Publication 2022/0188952 A1, hereafter Nakashima).
As per claim 3, Zhang in view of Tsubota teaches performing classification using image as input data to a machine learning model (Zhang FIG. 1). Zhang in view of Tsubota, however, does not teach classifying behavior using image as input data to a machine learning model.
Ucar is evidenced that performing aggressive/distracted/reckless (ADR) driving behavior classification using image as input data to a machine learning model is well-known and practiced (para. [0034], [0063]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Zhang in view of Tsubota to include the teaching of Ucar to perform behavior classification based on image data. Using image data can provide straightforward means for result verification as suggested by Ucar (para. [0056]).
Zhang in view of Tsubota and Ucar further does not disclose the rest limitations.
Nakashima teaches using a machine learning model to classify behaviors. Nakashima further teaches a database for storing behavioral pattern data in which the time frame, the location information and the behavior is associated with one another, for each of the plurality of cooperators (para. [0063]; FIG. 4). Nakashima also teaches analyzing the correspondence relationship between behavior type and associated location (FIG. 4; para. [0008] “… acquiring location information and a current status for each of a plurality of cooperators capable of performing rescue of a person to be rescued, and transmitting a rescue request to a cooperator who is located within a predetermined range from the person to be rescued and is in a predetermined status, among the plurality of cooperators, as a target cooperator, when a person to be rescued is present”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Zhang, Tsubota and Ucar to incorporate the teaching of Nakashima to perform analysis based on behavior-location correspondence. Doing so would allow an available cooperator to be identified accurately and timely when a rescue is desired (Nakashima para. [0045], [0100]).
As per claim 4, dependent upon claim 1, Zhang in view of Tsubota, Ucar and Nakashima teaches the input data is an image, the database stores a correspondence relationship between the recognition class of a behavior and applicability to a detection target behavior, and the hardware processor analyzes the correspondence relationship between the recognition class of the behavior and the applicability to the detection target behavior by using the database (See rejections applied to claim 3 regarding using image data as input to a machine learning model for classifying behavior. Nakashima further stores a database representing a correspondence between behavior and applicability to a detection target behavior (FIG. 9 “BEHAVIOR” versus “RESPONSE AVAILABILITY”)).
Claim 13, dependent upon claim 11, is rejected as applied to claim 3 above.
Claim 14, dependent upon claim 11, is rejected as applied to claim 4 above.
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Tsubota, as applied above to claims 5 and 15 respectively, in view of Wang et al. (US Publication 2021/0223308 A1, hereafter Wang).
As per claim 7, Zhang in view of Tsubota does not teach the recited limitations.
Wang discloses a defect classification method by using a machine learning model (para. [0044]; FIG. 4). When the predicted probability is lower than a preset threshold value, the corresponding image data is filtered out from further processing, such as the processing in S470 in FIG. 5. See FIG. 5, para. [0053].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Zhang in view of Tsubota to incorporate the teaching of Wang to not perform analysis when the classification confidence is less than a threshold. Doing so would allow images with higher classification confidence to be used in further processing as suggested by Wang (para. [0044]).
Claim 17, dependent upon claim 15, is rejected as applied to claim 7 above.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XUEMEI G CHEN whose telephone number is (571)270-3480. The examiner can normally be reached Monday-Friday 9am-6pm.
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, John M Villecco can be reached at (571) 272-7319. 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.
/XUEMEI G CHEN/Primary Examiner, Art Unit 2661