DETAILED ACTION
This action is responsive to the amendments filed 5/26/2026.
Claims 1 and 3-23 are pending. Claims 1, 3-6, 8-15 and 17 are currently amended. Claim 2 is canceled, and Claims 18-23 are new.
The prior rejections under 35 U.S.C. § 101 are withdrawn.
The prior rejections under 35 U.S.C. § 103 are withdrawn as necessitated by amendment.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1 and 3-24 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Teng, et al., U.S. PGPUB No. 2021/0117818 (“Teng”).
With regard to Claim 1, Teng teaches an inspection system comprising:
a first measurement device configured to measure a target to obtain a first measurement result, and to make a first determination with respect to the target using a first machine learning model based on the first measurement result ([0051] describes that a first measurement is received from a sensor of a first sensing modality group using a low-power source or sensor. [0054]-[0055] describe that the first measurement can be used by an algorithm or classifier using a baseline machine learning model);
a second measurement device configured to measure the target to obtain a second measurement result and to make a second determination with respect to the target based on the second measurement result, the second measurement device having a higher reliability than the first measurement device ([0059] describes that a second measurement is received from a second sensing modality group made up of high powered sensors. [0062]-[0063] describe that a label is determined from the second measurement using an independently trained inference model or classifier); and
a control device comprising: a memory that stores a relationship between the first measurement result, the second measurement result, and the second determination ([0048] describes that a memory stores data obtained from the first and second sensing groups, as well as training sets consisting of the first measurement and the label generated using the second measurement); and
a controller configured to generate first update data of the first machine learning model and transmit the first update data to the first measurement device, the first update data including the first measurement result and at least a part of the second determination based on the stored relationship ([0070] describes that the machine learning model can be updated in real time, when a first measurement and a label generated from the second measurement are received as a training pair, where the training sets are stored on the mobile device), wherein
the first measurement device is configured to update the first measurement result based on the first update data of the first machine learning model ([0071] describes that the machine learning model is improved by training using the training sets, by updating a particular sensor measurement from the low-power sensors with a particular label generated using the high power sensor output).
Claim 17 recites a method which is carries out by the inspection system of Claim 1, and is similarly rejected.
With regard to Claim 3, Teng teaches that the first measurement device is configured to make the first determination again after updating the first machine learning model. [0071] describes that the model is trained to associate a first measurement value with a particular result, thereby causing the model to learn to associate that particular measurement value with that context.
With regard to Claim 4, Teng teaches that the second measurement device is configured to make the second determination using a second machine learning model based on the second measurement result. [0063] describes that a second, independently trained machine learning algorithm is used to generate a label using the second measurement.
With regard to Claim 5, Teng teaches that the first measurement device is configured to obtain a first feature amount of the target, the second measurement device is configured to obtain a second feature amount of the target, and the second feature amount is different from the first feature amount. [0071] describes that a first measurement can be an audio feature amount, while a second can be a GPS location. [0051] describes the first measurement device can also be a low-resolution camera, while [0059] describes the second can be a high-resolution camera. Therefore, measurements can differ in feature amounts as they are different modalities, or be different resolutions of the same modality.
With regard to Claim 6, Teng teaches that the first measurement device is configured to obtain a feature amount of the target at a first level of detail, the second measurement device is configured to obtain the feature amount at a second level of detail, and the second level of detail is higher than the first level of detail. [0051] describes the first measurement device can also be a low-resolution camera, while [0059] describes the second can be a high-resolution camera. The feature amounts are therefore captured at different levels of detail, the second being higher.
With regard to Claim 7, Teng teaches that reliability of the second determination is higher than reliability of the first determination. [0051] describes that the first measurement is taken using low power sensors, while the second is taken using high power sensors. The reliability of the second is higher, such as by having images of higher resolution, or having superior location sensing such as through GPS, versus proximity or other lower reliability sensors.
With regard to Claim 8, Teng teaches that the second measurement unit device is configured to measure the target after the first measurement unit device measures the target. [0053] describes that the low power sensing sources can be always on, and always collecting measurements. [0059] describes that the high power sensors are not always on, meaning the first measurements can be capturing data regarding a location before the second measurement device takes a measurement.
With regard to Claim 9, Teng teaches that each of the first measurement unit device and the second measurement device comprises a radar, a metal detector, a liquid detector, an X-ray diagnosis device, or a camera. [0051] describes the first measurement device can also be a low-resolution camera, while [0059] describes the second can be a high-resolution camera.
With regard to Claim 10, Teng teaches that the second measurement device comprises a metal detector or a camera. [0059] describes the second sensor can be a high-resolution camera.
With regard to Claim 11, Teng teaches a third measurement device configured to measure the target to obtain a third measurement result, and to make a third determination with respect to the target based on the third measurement result, wherein the third measurement device is configured to measure the target after the first measurement device measures the target, and the second measurement device is configured to measure the target after the third measurement device measures the target.
[0051] describes several different types of sensor devices which can take measurements. [0055] describes that the model is trained for each measurement x, meaning an additional third measurement can be taken and input to a third model. [0053] describes that the low power sensing sources can be always on, and always collecting measurements. [0059] describes that the high power sensors are not always on, meaning the third measurement can be capturing data regarding a location before the second measurement device takes a measurement.
With regard to Claim 12, Teng teaches that the third measurement device is configured to make the third determination using a third machine learning model based on the third measurement result, the controller is configured to generate second update data of the third machine learning model based on a result of the second determination, and the control device is configured to transmit the second update data to the third measurement device, and the third measurement device is configured to update the third machine learning model based on the second update data.
[0070] describes that the machine learning model can be updated in real time, when a measurement and a label generated from the second measurement are received as a training pair, where the training sets are stored on the mobile device. [0071] describes that the machine learning model is improved by training using the training sets, by updating a particular sensor measurement from the low-power sensors with a particular label generated using the high power sensor output. Therefore, the third measurement can be used to update the machine learning model for the particular sensor measurement.
With regard to Claim 13, Teng teaches that the third measurement device is configured to make the third determination again after updating the third machine learning model. [0071] describes that the model is trained to associate a first measurement value with a particular result, thereby causing the model to learn to associate that particular measurement value with that context.
With regard to Claim 14, Teng teaches that the first measurement device is configured to obtain a first feature amount of the target, the second measurement device is configured to obtain a second feature amount of the target, the third measurement device is configured to measure a third feature amount of the target, the second feature amount is different from the first feature amount, and the third feature amount is different from the second feature amount. [0051] describes a variety of always-on measurement devices, each of which produces different feature amounts. [0084] describes an example of an accelerometer and a gyroscope, each of which produces different output amounts in different units. [0059] describes additional, different devices of the high power type also producing feature values, which will differ from those of the low power devices.
With regard to Claim 15, Teng teaches that the first measurement device is configured to measure a feature amount of the target at a first level of detail, the third measurement device is configured to measure the feature amount at a third level of detail, the second measurement device is configured to measure the feature amount at a second level of detail, and the second level of detail is higher than the first level of detail and the third level of detail. [0051] describes that the sensors are low power, lower resolution sensors, while [0059] describes the other sensors as high power.
With regard to Claim 16, Teng teaches that reliability of the second determination is higher than reliability of the first determination and reliability of the third determination. [0051] describes that the sensors are low power, lower resolution sensors, while [0059] describes the other sensors as high power.
With regard to Claim 18, Teng teaches that the first determination is whether the target includes a predetermined object. [0029] describes that context identified from the sensor measurements can include traveling within an object such as a plane, car, or bus.
With regard to Claim 19, Teng teaches that the second determination is that the target includes an object. [0029] describes that context identified from the sensor measurements can include traveling within an object such as a plane, car, or bus.
With regard to Claim 20, Teng teaches that the second determination is that the target includes an object and a location of the object. [0071] describes the determination of a user environment including a subway, as well as GPS location data.
With regard to Claim 21, Teng teaches that the first measurement device is configured to measure the target again after updating the first machine learning model. [0053] describes that the first measurements are provided continuously, and [0055] describes that the model to which first measurement data is input is trained, thereby indicating that the first measurement is taken by the always on sensor after training has updated a machine learning model.
With regard to Claim 22, Teng teaches that the first measurement device is configured to measure the target with a first resolution; the second measurement device is configured to measure the target with a second resolution; and the second resolution is different from the first resolution. [0051] describes the first measurement device can also be a low-resolution camera, while [0059] describes the second can be a high-resolution camera.
With regard to Claim 23, Teng teaches that the first measurement device is configured to measure the target at a first time; the second measurement device is configured to measure the target at a second time; and the second time is different from the first time. [0053] describes that the low power sensing sources can be always on, and always collecting measurements. [0059] describes that the high power sensors are not always on, meaning the first measurements can be capturing data regarding a location before the second measurement device takes a measurement.
Response to Arguments
Applicant’s arguments 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 KEITH D BLOOMQUIST whose telephone number is (571)270-7718. The examiner can normally be reached M-F, 8:30-5 PM.
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, Kieu Vu can be reached at 571-272-4057. 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.
/KEITH D BLOOMQUIST/Primary Examiner, Art Unit 2171
7/21/2026
Prosecution Insights