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.
Claim(s) 1, 3, 6, 8, 10, 13, 15, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over WO 2022/215239 Nakashima et al., hereinafter “Nakashima” (cited previously), in view of WO 2022/208874 TSUJIKAWA et al., hereinafter “Tsujikawa”.
Regarding claim 1, Nakashima discloses an apparatus for determining stress (Para 1 and Figure 3, element 4), comprising: a communication interface (Figure 3, element 44 and Para 42); and a processor connected to the communication interface (Para 42), wherein the processor is configured to: collect biometric data (Figure 3, elements 401 and 411; Para 43) and survey data (Figure3, element 402 and 412; Para 43) of a user through the communication interface (Para 189), generate a first stress classification model based on the survey data (Figure 3, element 403 and 414); generate training data from the biometric data and the survey data using the first stress classification model and a pre-stored biometric data-based second stress classification model (Figure 3, elements 407 and 415), by: obtaining a first prediction result by inputting target survey data to the first stress classification model (Figure 3, element 409 and Para 58); labeling the target biometric data with the prediction result and storing the labeled target biometric data as the training data (Figure 3, element 415): generate a personalized stress classification model based on the training data (Figure 3, element 416; Para 34, 58, and 61; Figure 3, model 416 is generated based on trained data 415), and determine whether the user is stressed using the personalized stress classification model (Para 58).
Nakashima does not disclose obtaining a second prediction result by inputting target biometric data corresponding in time to the target survey data to the second stress classification model; and when the first prediction result matches the second prediction result, labeling the target biometric data with the second prediction result and storing the labeled target biometric data as the training data.
However, Tsujikawa discloses a device/method for stress determination (Para 1) and teaches obtaining a second prediction result by inputting target biometric data corresponding in time to the target survey data to the second stress classification model (Para 34, 65, and 68 disclose multiple estimation models that classify different features); and when the first prediction result matches the second prediction result, labeling the target biometric data with the second prediction result and storing the labeled target biometric data as the training data (Para 77).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed multiple classification models as taught by Tsujikawa, in the invention of Nakashima, in order to allow each model to observe a single feature that can determine stress of the subject (Tsujikawa; Para 68).
Regarding claim 3, Nakashima discloses the processor extracts feature data from the survey data, clusters the feature data through unsupervised machine learning, and generates the first stress classification model based on the clustered feature data (Para 18, 46-47, and 53).
Regarding claim 6, Nakashima discloses the processor receives the biometric data of the user through the communication interface, and determines whether the user is stressed based on a result output by inputting the received biometric data to the personalized stress classification model (Para 79 the output of the estimation model is the stress level. This (416), as shown in Figure 3, is fed with information that includes biometric data 411 and survey data 412).
Regarding claim 8, Nakashima discloses a method of determining stress (Para 1 and Figure 3, element 4), which is performed by a computing device including a processor (Para 42), comprising: collecting biometric data (Figure 3, elements 401 and 411; Para 43) and survey data of a user (Figure3, element 402 and 412; Para 43); generating a first stress classification model based on the survey data (Figure 3, element 403 and 414); generating training data from the biometric data and the survey data using the first stress classification model and a pre-stored biometric data-based second stress classification model (Figure 3, elements 407 and 415), by: obtaining a first prediction result by inputting target survey data to the first stress classification model (Figure 3, element 409 and Para 58); labeling the target biometric data with the prediction result and storing the labeled target biometric data as the training data (Figure 3, element 415): generating a personalized stress classification model based on the training data (Figure 3, element 416; Para 34, 58, and 61; Figure 3, model 416 is generated based on trained data 415), and determining whether the user is stressed using the personalized stress classification model (Para 58).
Nakashima does not disclose obtaining a second prediction result by inputting target biometric data corresponding in time to the target survey data to the second stress classification model; and when the first prediction result matches the second prediction result, labeling the target biometric data with the second prediction result and storing the labeled target biometric data as the training data.
However, Tsujikawa discloses a device/method for stress determination (Para 1) and teaches obtaining a second prediction result by inputting target biometric data corresponding in time to the target survey data to the second stress classification model (Para 34, 65, and 68 disclose multiple estimation models that classify different features); and when the first prediction result matches the second prediction result, labeling the target biometric data with the second prediction result and storing the labeled target biometric data as the training data (Para 77).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed multiple classification models as taught by Tsujikawa, in the invention of Nakashima, in order to allow each model to observe a single feature that can determine stress of the subject (Tsujikawa; Para 68).
Regarding claim 10, Nakashima discloses the generating of the first stress classification model includes: extracting feature data from the survey data; clustering the feature data through unsupervised machine learning; and generating the first stress classification model based on the clustered feature data (Para 18, 46-47, and 53).
Regarding claim 13, Nakashima discloses the determining of whether the user is stressed includes: receiving the biometric data of the user; and determining whether the user is stressed based on a result output by inputting the received biometric data to the personalized stress classification model (Para 79 the output of the estimation model is the stress level. This (416), as shown in Figure 3, is fed with information that includes biometric data 411 and survey data 412).
Regarding claim 15, Nakashima discloses a system for determining stress (Para 1 and Figure 3, element 4), comprising: a wearable device (Figure 3, element 7) configured to detect a biometric signal related to stress from a user and generate biometric data (Para 39); a user device (Figure 3, element 4) configured to receive the biometric data transmitted from the wearable device (Para 41), provide questions related to stress to the user (Figure3, element 402 and 412; Para 43), and generate survey data based on user inputs that are input by the user in response to the questions (Figure3, element 402 and 412; Para 43); and a server configured to collect biometric data and survey data from the user device (Para 61; estimation model generating device), generate a first stress classification model based on the survey data (Figure 3, element 403 and 414); generate training data from the biometric data and the survey data using the first stress classification model and a pre-stored biometric data-based second stress classification model (Figure 3, elements 407 and 415), by: obtaining a first prediction result by inputting target survey data to the first stress classification model (Figure 3, element 409 and Para 58); labeling the target biometric data with the prediction result and storing the labeled target biometric data as the training data (Figure 3, element 415): generate a personalized stress classification model based on the training data (Figure 3, element 416; Para 34, 58, and 61; Figure 3, model 416 is generated based on trained data 415), and determine whether the user is stressed using the personalized stress classification model (Para 58).
Nakashima does not disclose obtaining a second prediction result by inputting target biometric data corresponding in time to the target survey data to the second stress classification model; and when the first prediction result matches the second prediction result, labeling the target biometric data with the second prediction result and storing the labeled target biometric data as the training data.
However, Tsujikawa discloses a device/method for stress determination (Para 1) and teaches obtaining a second prediction result by inputting target biometric data corresponding in time to the target survey data to the second stress classification model (Para 34, 65, and 68 disclose multiple estimation models that classify different features); and when the first prediction result matches the second prediction result, labeling the target biometric data with the second prediction result and storing the labeled target biometric data as the training data (Para 77).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed multiple classification models as taught by Tsujikawa, in the invention of Nakashima, in order to allow each model to observe a single feature that can determine stress of the subject (Tsujikawa; Para 68).
Regarding claim 17, Nakashima discloses the server extracts feature data from the survey data, clusters the feature data through unsupervised machine learning, and generates the first stress classification model on the basis of the clustered feature data (Para 18, 46-47, and 53).
Regarding claim 20, Nakashima discloses the server receives the biometric data of the user from the user device, and determines whether the user is stressed based on a result output by inputting the received biometric data to the personalized stress classification model (Para 79 the output of the estimation model is the stress level. This (416), as shown in Figure 3, is fed with information that includes biometric data 411 and survey data 412).
Claim(s) 4, 7, 11, 14, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over WO 2022/215239 Nakashima et al., hereinafter “Nakashima”, in view of WO 2022/208874 TSUJIKAWA et al., hereinafter “Tsujikawa”, further in view of US 2021/0169415 Kon et al., hereinafter “Kon” (cited previously).
Regarding claim 4, Nakashima discloses the survey data is data in which questions (Para 47), and scores for the questions are recorded for each of items (Para 47, PSS score), and the processor uses a value obtained by summing the scores of each item for each emotion factor, a value obtained by summing all the scores of each item, and the score of each item itself as the feature data (Para 47; the PSS stress questionnaire scores every answer, sums up the responses to get an overall score that determines stress levels).
Nakashima does not disclose emotion factors related to the questions.
However, Kon discloses a stress determining device/method (Abstract) and teaches emotion factors related to the questions (Para 137).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed emotion factors as taught by Kon, in the invention of Nakashima, in order to induce different categories of stress, each combined to an emotion (Kon; Para 137).
Regarding claim 7, Nakashima discloses the communication interface, determines whether the user is stressed through the personalized stress classification model (Para 79).
Nakashima does not disclose the processor receives reference biometric data, to which a label indicating whether the user is stressed is attached, compares a result of the determination and the label, performs a process of storing results of the comparison for each piece of the reference biometric data, and calculates accuracy of a third stress classification model based on the stored results of the comparison
However, Kon teaches the processor receives reference biometric data (Para 111), to which a label indicating whether the user is stressed is attached, compares a result of the determination and the label, performs a process of storing results of the comparison for each piece of the reference biometric data (Para 111), and calculates accuracy of a third stress classification model based on the stored results of the comparison (Para 111).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed a comparison to expected results as taught by Kon, in the invention of Nakashima, in order to verify the accuracy of the model (Kon; Para 111).
Regarding claim 11, Nakashima discloses the survey data is data in which questions (Para 47), and scores for the questions are recorded for each of items (Para 47, PSS score), and in the extracting of the feature data, a value obtained by summing the scores of each item for each emotion factor, a value obtained by summing all the scores of each item, and the score of each item itself as the feature data are used (Para 47; the PSS stress questionnaire scores every answer, sums up the responses to get an overall score that determines stress levels).
Nakashima does not disclose emotion factors related to the questions.
However, Kon discloses a stress determining device/method (Abstract) and teaches emotion factors related to the questions (Para 137).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed emotion factors as taught by Kon, in the invention of Nakashima, in order to induce different categories of stress, each combined to an emotion (Kon; Para 137).
Regarding claim 14, Nakashima discloses determining whether the user is stressed through the personalized stress classification model (Para 79).
Nakashima does not disclose receiving reference biometric data to which a label indicating whether the user is stressed is attached; comparing a result of the determination and the label, and performing a process of storing results of the comparison for each piece of the reference biometric data; and calculating accuracy of a third stress classification model based on the stored results of the comparison.
However, Kon teaches receiving reference biometric data to which a label indicating whether the user is stressed is attached (Para 111); comparing a result of the determination and the label, and performing a process of storing results of the comparison for each piece of the reference biometric data (Para 111); and calculating accuracy of a third stress classification model based on the stored results of the comparison (Para 111).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed a comparison to expected results as taught by Kon, in the invention of Nakashima, in order to verify the accuracy of the model (Kon; Para 111).
Regarding claim 18, Nakashima discloses the survey data is data in which questions (Para 47), and scores for the questions are recorded for each of items (Para 47, PSS score), and the processor uses a value obtained by summing the scores of each item for each emotion factor, a value obtained by summing all the scores of each item, and the score of each item itself as the feature data (Para 47; the PSS stress questionnaire scores every answer, sums up the responses to get an overall score that determines stress levels).
Nakashima does not disclose emotion factors related to the questions.
However, Kon discloses a stress determining device/method (Abstract) and teaches emotion factors related to the questions (Para 137).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to have disclosed emotion factors as taught by Kon, in the invention of Nakashima, in order to induce different categories of stress, each combined to an emotion (Kon; Para 137).
Response to Arguments
Applicant’s arguments have been fully considered but are moot because the new ground of rejection.
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 extension fee 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AYA ZIAD BAKKAR whose telephone number is (313)446-6659. The examiner can normally be reached on 7:30 am - 5:00 pm M-Th.
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, Carl Layno can be reached on (571) 272-4949. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AYA ZIAD BAKKAR/
Examiner, Art Unit 3796
/CARL H LAYNO/Supervisory Patent Examiner, Art Unit 3796