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 .
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.
Claim(s) 1-4, 6, 8-14, 16 and 19-21is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 (U.S. PG-PUB NO. 2018/0336452) in view of D2 (U.S. PG-PUB NO. 2017/0352099).
-Regarding claim 1, D1 discloses a method, comprising: determining a set of images depicting a component, the set of images comprising a time series of at least two images (CNN can accept data from fifteen days ago, and the CNN 314 can accept current data 414, [0064]); for each image in the set of images, extracting a feature vector from the image to generate a time series of feature vectors (the resulting outputs of a topmost convolutional layer (e.g., the third hidden layer 208) can be combined by a fully connected layer (e.g., the fourth hidden layer 210) into a one-dimensional feature vector (e.g., the output neurons 211), [0052]); and using a recurrent neural network, determining processing the time series of feature vectors at a specified time based on the feature vectors (recurrent neural networks (RNN) such as the LSTM network 300 can be used to process sequential inputs such as time series, [0058]).
D1 is silent to teaching that a property and to predict a state of the component of the property. However, the claimed limitation is well known in the art as evidenced by D2.
In the same field of endeavor, D2 teaches a property and to predict a state of the component of the property (the system may identify whether there is damage somewhere on a section of the roof, [0046]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of D1 with the teaching of D2 in order to provide more consistent and efficient process.
-Regarding claim 2, the combination further discloses determining the state of the component comprises: determining a set of scores based on the feature vectors using the neural network (D1, first output neuron 216 represents a calculated likelihood, [0050]; D2, combine the scores from all determinations to yield a final probability that the damage is consistent with a natural storm or the property damage is legitimate, [0056]); and determining the state of the component based on the set of scores (D1, prediction score 806 can be a score determined using a LSTM, [0072]; D2, combine the various probability scores for each damage determination using known or later developed fusion techniques, [0057]).
-Regarding claim 3, the combination further discloses the component comprises a roof (D2, roof, [0046]).
-Regarding claim 4, the combination further discloses the state of the component comprises a condition of the roof (D2, the system may identify roof damage at various segments (referred to as levels) of the roof, [0046]).
-Regarding claim 6, the combination further discloses the neural network is trained to be invariant to temporary features (D1, a mask can be used to skip the invalid values while training and predicting, [0046]).
-Regarding claim 8, the combination further discloses the state of the component is associated with a first timestamp (D1, time step t=t1, [0019]), the method further comprising determining a second state of the component of the property associated with a second timestamp (D1, time step t=t2, [0019]).
-Regarding claim 9, the combination further discloses determining a change in the component based on the state of the component and the second state of the component (D1, a determination can be made that a fire occurred between t1 and t2 in the area, [0019]).
-Regarding claim 10, the combination further discloses the state of the component comprises at least one of: roof damage or new roof installation (D2, the system may identify roof damage at various segments (referred to as levels) of the roof, [0046]).
-Regarding claim 11, D1 discloses a method, comprising: determining a time series of images (CNN can accept data from fifteen days ago, and the CNN 314 can accept current data 414, [0064]); generating at least two feature vectors based on the time series of images to form a time series of feature vectors, wherein the at least two feature vectors are associated with the area at different timestamps (the resulting outputs of a topmost convolutional layer (e.g., the third hidden layer 208) can be combined by a fully connected layer (e.g., the fourth hidden layer 210) into a one-dimensional feature vector (e.g., the output neurons 211), [0052]); and using a machine learning model comprising a recurrent neural network, determining a score based on the at least two feature vectors processing the time series of feature vectors to determine a score for the area at a specified time (recurrent neural networks (RNN) such as the LSTM network 300 can be used to process sequential inputs such as time series, [0058]).
D1 is silent to teaching that depicting a property; and score for the property. However, the claimed limitation is well known in the art as evidenced by D2.
In the same field of endeavor, D2 teaches depicting a property; and score for the property (the system may identify whether there is damage somewhere on a section of the roof, [0046]; combine the scores from all determinations to yield a final probability that the damage is consistent with a natural storm or the property damage is legitimate, [0056]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of D1 with the teaching of D2 in order to provide more consistent and efficient process.
-Regarding claim 12, the combination further discloses the score for the property comprises a score for a condition of the property (D2, the system may identify roof damage at various segments (referred to as levels) of the roof, [0046]).
-Regarding claim 13, the combination further discloses the score for the condition of the property comprises a score for a condition of a roof of the property (D1, prediction score 806 can be a score determined using a LSTM, [0072]; D2, the system may identify roof damage at various segments (referred to as levels) of the roof, [0046]; combine the various probability scores for each damage determination using known or later developed fusion techniques, [0057]).
-Regarding claim 14, the combination further discloses the machine learning model further comprises a convolutional neural network to generate the time series of feature vectors (CNN can accept data from fifteen days ago, and the CNN 314 can accept current data 414, [0064]).
-Regarding claim 16, the combination further discloses the score for the property is associated with a timestamp (D1, prediction score 806 can be a score determined using a LSTM that uses the first 818, second 820, third 822, and fourth 824 time periods as a time sequence, [0072]).
-Regarding claim 19, the combination further discloses the machine learning model is trained to detect at least one of: shingle conditions, shingle displacement, missing shingles, streaking, or spots (D2, Damage to the shingles may be classified in at least two ways: “cosmetic” damage and “functional” damage, [0044]).
-Regarding claim 20, the combination further discloses the set of images comprises aerial images (D2, [0072]).
-Regarding claim 21, the combination further discloses extracting the feature vector from each image to generate the time series of feature vectors is performed using a convolutional neural network (D1, CNN can accept data from fifteen days ago, and the CNN 314 can accept current data 414, [0064]).
Claim(s) 7, 17 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over D1 (U.S. PG-PUB NO. 2018/0336452) in view of D2 (U.S. PG-PUB NO. 2017/0352099) and further in view of D3 (U.S. PG-PUB NO. 2007/0110309).
-Regarding claim 7, the combination is silent to teaching that temporary features comprise shadows. However, the claimed limitation is well known in the art as evidenced by D3.
In the same field of endeavor, D3 teaches temporary features comprise shadows (shadows are detected in an image by using a novel application of the homogeneity property of shadows, [0016]).
Therefore, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to combine the teaching of the combination with the teaching of D3 in order to provide an improved system and method to process shadow information in image data.
-Regarding claim 17, the combination further discloses the machine learning model is trained to be invariant to temporary features (D3, shadows are detected in an image by using a novel application of the homogeneity property of shadows, [0016]).
-Regarding claim 18, the combination further discloses temporary features comprise shadows (D3, shadows, [0016]).
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-4, 6-14 and 16-21 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PING Y HSIEH whose telephone number is (571)270-3011. The examiner can normally be reached Monday-Friday, 9am-4pm.
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, Jennifer Mehmood can be reached at (571) 272-2976. 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.
/PING Y HSIEH/ Primary Examiner, Art Unit 2664
Prosecution Insights