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 .
The following is a Non-Final Office Action in response to communications received on November 11, 2024. Claims 1-7 are pending and addressed below.
Specification
For the record, Examiner acknowledges that the Specification submitted on November 11, 2024 has been accepted.
Drawings
For the record, Examiner acknowledges that the Drawings submitted on November 11, 2024 have been accepted.
Claim Objections
Claim 5 is objected to because of the following informalities: Claim 5 recites the phrase “the obtained preliminarily attention coefficient.” It is suggested the phrase be amended to “the calculated preliminary attention coefficient” for clarity and consistency. Also, claim 5 recites the phrase “the edge cluster”. This phrase is previously recited in the plural – i.e. “the edge clusters”. It is suggested the language be made consistently singular or plural throughout the claim language.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-7 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites the variables “(ν,ε)” and “N”. None of these variables are defined in the claim. It is unclear what they represent. Also, claim 1 recites the limitation “the expression”. There is insufficient antecedent basis for this limitation. Further, claim 1 recites the acronym “ADGAT.” This acronym is never defined in the claim and it is unclear what the acronym means. Also, claim 1 recites the function “AnomalyDetect.” This function is never defined and it is unclear what the function is. Dependent claims 2-7 are rejected for containing the same indefinite language as parent claim 1 without further remedying the indefinite language.
Claim 2 recites the acronym “VGAE.” This acronym is never defined in the claim and it is unclear what the acronym means.
Claim 3 recites the acronym “the VGAE.” This acronym is never defined in the claim and it is unclear what the acronym means. Also, there is insufficient antecedent basis for this acronym.
Claim 4 recites the numerical ranges “lower than 0.8”, “between 0.8 and 0.9”, and “higher than 0.9”. This makes it unclear of which category the exact values of 0.8 and 0.9 fall under. Dependent claims 5 and 7 are rejected for containing the same indefinite language as parent claim 4 without further remedying the indefinite language.
Claim 5 recites the limitations “the linear change of hidden layers”, “the anomaly detection result”, and “the attention purification mechanism.” There is insufficient antecedent basis for these limitations. Also, claim 5 recites the functions “softmax”, “LeakyReLU”, “attention_increase”, “attention_norm”, and “attention_decrease”. These functions are never defined and it is unclear what the function are. Further, claim 5 recites the limitation “the preliminary attention coefficient aij”. The claim previously recites the coefficient as “eij”. It is unclear if the limitation is referring to the same coefficient or a different coefficient. Dependent claim 7 is rejected for containing the same indefinite language as parent claim 5 without further remedying the indefinite language.
Claim 6 recites the functions and acronyms “q”, “N”, “GCN”, “ReLU”, and “p”. These functions and acronyms are never defined and it is unclear what the functions and acronyms are. Also, claim 6 recites the limitation “the inner product decoder”. There is insufficient antecedent basis for this limitation. Further, claim 6 recites the phrase “similarly”. The term “similarly” is a relative term which renders the claim indefinite. The term “similarly” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim 7 recites the limitations “the attention layer” and “the last hidden layer feature.” There is insufficient antecedent basis for these limitations.
Allowable Subject Matter
Claims 1-7 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action.
The following is a statement of reasons for allowance:
Claim 1 recites, inter alia, “S2: performing global prediction on the graph data by using the trained anomaly detector AD to obtain a linkpred matrix with the shape of (N, N), where N is the number of nodes of an input graph, and the expression of the global prediction is as follows: linkpred=AnomalyDetect(X,A); S3: inputting the linkpred matrix into a sigmoid function for normalization, and scaling element values of the linkpred matrix to an interval of [0, 1] as detection probability;… S4-2: in training process, according to the detection probability in the linkpred matrix, dividing three edge clusters {Edge1,Edge2,Edge3}as a low confidence edge set, a common confidence edge set and a high confidence edge set respectively, and performing an attention purification operation on different edge clusters to obtain a purified attention coefficient”.
The closest prior art made of record are:
Yehezkel et al. (U.S. Pub. No. 2023/0090205) which discloses graph-based anomaly detection (Figs. 3-4)
Sawal et al. (U.S. Pub. No. 2022/0392056) which discloses hybrid deep learning for anomaly detection using graphs (Figs. 3-4)
Xie et al. (U.S. Patent No. 12,182,256) which discloses using a matrix to construct a graph for intrusion anomaly detection (Abstract)
Chen et al. (U.S. Patent No. 11,606,389) which discloses graph-based anomaly detection and normalization with sigmoid functions (col. 7 lines 21-27 and Abstract)
While the prior art does generally disclose graph-based anomaly detection, the prior art is not considered to show the combination of cited limitations. Therefore, claim 1 is considered to recite allowable subject matter over the prior art. Dependent claims 2-7 are considered to recite allowable subject matter over the prior art based on their dependency.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THADDEUS J PLECHA whose telephone number is (571)270-7506. The examiner can normally be reached M-F 8-4:30.
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, Taghi Arani can be reached at 571-272-3787. 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.
/THADDEUS J PLECHA/Examiner, Art Unit 2438
Prosecution Insights