18874205DETAILED ACTION
DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Prior arts cited in this office action:
Kim et al. (KR 20220028267 A, hereinafter “Kim”)
Suyama et al. (WO 2021210618 A1, hereinafter “Suyama”)
Seo et al. (US 20200286275 A1, hereinafter “Seo”)
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 12 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (KR 20220028267 A, hereinafter “Kim”) and in view of Suyama et al. (WO 2021210618 A1, hereinafter “Suyama”).
Regarding claims 1, 12 and 20:
Kim teaches an apparatus for inspecting a battery electrodes based on artificial intelligence model (Kim [0001], [0068]-[0071] where Kim teaches invention relates to an electrode tab disconnection inspection system and an electrode tab disconnection inspection method, and more particularly, to a battery cell defect inspection system capable of automatically detecting disconnection of an electrode tab portion in a battery cell through CT imaging and a battery cell defect inspection it's about how), the apparatus comprising:
Kim fails to explicitly teach at least one processor; and a memory storing instruction executed by the at least one processor, wherein the at least one instruction includes instructions include:
an instruction to obtain an image of an inspection object, wherein the image of the
inspection object at least includes an image of an electrode surface with an area suspected
of being; and an instruction determine whether the battery electrode is defective based on the image of the inspection object using a first pre-trained learning model.
However, Kim teaches the detection unit automatically detects whether the electrode tap is disconnected through deep learning. the learning unit 320 inputs the training data converted into a two-dimensional image by the data construction unit 310 to the input layer 321 on the deep neural network. The input training data is output as a final output from the output layer 323 through the hidden layer 322 . Also, the learning unit 320 may learn an image pattern according to the occurrence of disconnection of the electrode tab portion by comparing the output with the state of the actual electrode tab and updating the weight (Kim Abstract, [0086]-[0092]). In other words, memory, processor and instruction is used to perform the functions. Nevertherless, Suyama teaches there has been known a method of removing noise from image data using a trained model by machine learning such as deep learning (see, for example, Patent Document 1 below). According to this method, noise is automatically removed from the image data, so that the object can be observed with high accuracy including object such as battery.
FIG. 3 is a block diagram showing a functional configuration of the control device 20. The control device 20 includes an acquisition unit 201, a specific unit 202, a selection unit 204, and a processing unit 205. Each functional unit of the control device 20 shown in FIG. 3 reads a program (radio image processing program of the present embodiment) on hardware such as the CPU 101 and the RAM 102, and under the control of the CPU 101, the communication module 104. , And the input / output module 106 and the like are operated, and data is read and written in the RAM 102. The CPU 101 of the control device 20 causes the control device 20 to function as each functional unit of FIG. 3 by executing this computer program, and sequentially executes processing corresponding to the radiographic image processing method described later. The CPU may be a single piece of hardware, or may be implemented in programmable logic such as FPGA, such as a soft processor. The RAM and ROM may be single-unit hardware, or may be built in programmable logic such as FPGA. Various data necessary for executing this computer program and various data generated by executing this computer program are all stored in an internal memory such as ROM 103 and RAM 102, or a storage medium such as a hard disk drive (Suyama [0002], [00015], [0025]-[0026]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to use processor, memory and corresponding instructions to analyze images using pre-trained neural network to determine whether electrode or batteries contains defect or disconnected, ect. In order to take appropriate action to insure proper functionality and/or safety.
Claims 2-11, 13-19 are rejected under 35 U.S.C. 103 as being unpatentable over Kim et al. (KR 2022028267 A, hereinafter “Kim”) and in view Suyama et al. (WO 2021210618 A1, hereinafter “Suyama”) and in view of Seo et al. (US 20200286275 A1, hereinafter “Seo”).
Regarding claims 2 and 13:
Kim in view of Suyama teaches all the limitations of this claim except wherein the instructions includes an instruction to determine the first pre-trained learning model from among a plurality of candidate pre-trained learning models according to an amount of at least one training data.
However, Seo teaches a processor; and a memory, wherein the memory stores instructions configured, when executed, to cause the processor to control the electronic device to: acquire a feature of the first image and a feature of the second image; and identify a learning model to be applied to the first image and the second image from among a first learning model included in the electronic device and a second learning model included in a server (Seo [0006], [0081], claim 1).
Therefore, taking the teachings of Kim, Suyama and Seo as a whole, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to provide a plurality of pre-trained learning model and select one of them that is the best suited for the task, in order to improve efficiency.
Regarding claim 3:
Kim in view of Suyama and in view of Seo teaches wherein the instructions include an instruction to, in response to the amount of training data being less than a predetermined reference value, determine whether the battery electrode is
defective using the first pre-trained machine learning model (Suyama claim 1; Seo [0006], [0041], [0046], [0081], claims 1 and 3).
Regarding claims 4 and 14:
Kim in view of Suyama and in view of Seo teaches Wherein the instructions include: an instruction to, in response to the amount of training data being greater than or equal to the predetermined reference value, determine whether the battery electrode is defective using a second pre-trained learning model, wherein the second pre-trained learning model is a pre-trained deep learning model (Suyama claim 1; Seo [0006], [0041], [0046], [0081], claims 1 and 3).
Regarding claims 5 and 18:
Kim in view of Suyama and in view of Seo teaches wherein the instructions include:
an instruction to extract at least one image feature value from the image of the inspection
object; and an instruction to input the at least one image feature value into the first pre-trained learning model, wherein the instruction to determine whether the battery electrode is defective is based on a result of the at least one image feature value input into the first pre-trained learning mode (Suyama claim 1; Seo Claim 1).
Regarding claim 6:
Kim in view of Suyama and in view of Seo teaches wherein the instruction to extract the at least one image feature value from the image of the inspection object extracts the at least one image feature value from the image of the inspection object using a rule-based algorithm (Kim [0083], Suyama claim 1; Seo [0006], [0041], [0046], [0081], claims 1 and 3).
Regarding claims 7 and 16:
Kim in view of Suyama and in view of Seo teaches wherein the at least one image feature value includes data extracted from the image of the inspection object regarding one or more of pixel height, pixel width, pixel maximum value, pixel minimum value, aspect ratio, and roundness (Suyama [0021], [0029]).
Regarding claim 9:
Kim in view of Suyama and in view of Seo teaches wherein the instructions include an instruction to obtain the result data by inputting the at least one image of inspection object into the second pre-trained learning model, and wherein the instruction to determine whether the battery electrode is defective is based on a result of the at least one image inspection object input into the second pre-traid learning model (Kim [0086], claim 1; Suyama [0026], claim 1; Seo Claim 1).
Regarding claim 10:
Kim in view of Suyama and in view of Seo teaches wherein the second learning model is a convolutional neural network (CNN))-based learning model (Kim [0086], Suyama [0026]).
Regarding claims 11 and 19:
wherein the at least instructions include an instruction to re-train the first pre-trained learning model by using data related to whether the battery electrode is defective as learning data (Seo [0190]).
Regarding claim 15:
Kim in view of Suyama and in view of Seo teaches Further comprising: extracting at least one image feature value from the image of the inspection object using a rule-based algorithm; and
determining whether the battery electrode is defective obtaining the result data by inputting the at least one image feature value into the first pre-traind learning model (Kim [0083], Suyama claim 1; Seo [0006], [0041], [0046], [0081], claims 1 and 3).
Regarding claim 16:
wherein the at least one image feature value includes data extracted from the image of the inspection object regarding one or more of pixel height, pixel width, pixel maximum value (Peak White), pixel minimum value (Peak Dark), aspect ratio
Regarding claim 8:
The combination above fails to explicitly teach wherein the first pre-trained learning model is a random forest-based learning model.
However, based on the teachings of Kim in view of Suyama and in view of Seo, using random forest as an option among the plurality of the learning model would have been a variable option to one of ordinary skill in the art because of predictable benefits provided by this particular model.
Regarding claim 17:
Kim in view of Suyama and in view of Seo teaches wherein the first pre-trained learning model is a random forest-based learning model, and wherein the second pre-trained learning model is a convolutional neural network (CNN)) based learning model (See rejection to claims 8 and 10 above).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WEDNEL CADEAU whose telephone number is (571)270-7843. The examiner can normally be reached Mon-Fri 9:00-5:00.
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, Chieh Fan can be reached at 571-272-3042. 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.
/WEDNEL CADEAU/Primary Examiner, Art Unit 2632 July 15, 2026
Prosecution Insights