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 .
DETAILED ACTION
Claims 1-20 are currently pending and have been examined.
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 of this title, 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.
Claims 1-7, 9-15, 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Marolia et al. (U.S. Patent No. 9679090 B1) in view of Kulkarni et al. (U.S. Pub. No. 11500871 B1), and further in view of Shi et al. (U.S. Pub. No. 20250292120 A1).
Marolia and Kulkarni were cited in a previous office action.
As per claim 1, Marolia teaches the invention substantially as claimed including a method comprising:
responsive to a first input being entered via … interface … wherein the first input requests an emulator for a device, receiving, by a computer system, a first request for the emulator for the device (col. 6, lines 62-67 for example, the developer 102 might request that the program 108 be tested on devices having a camera and a particular version of the ANDROID operating system; col. 7, lines 3-9 Once the developer 102 has generated the program 108, a test request 112 might be transmitted to the testing service 110. In some examples, the test request 112 may include the program 108, or a reference (e.g., name or link) to the program 108. In other examples, the test request 112 might also include data identifying the devices … emulators upon which to perform the testing of the program 108); and
identifying, by the computer system, a compute instance that is loaded with the emulator for the device (col. 12, lines 4-13 In some examples, the workflow coordinator 302 may be configured to determine whether the test devices, such as the computing devices 118A-118N and/or the device emulators 122A0-122N, that may be requested in the test request 112 are available for use in testing the program 108. In other examples, the workflow coordinator 302 may be configured to determine whether the test devices that may be requested by the test manager 150 are available for use in testing the program 108; col. 7, lines 37-44 the testing service 110 also includes a host computer 116A that is executing a number of device emulators 122A-122N. The device emulators 122A-122N may be executing … within virtual machines executing on the host computer 116A); and
responsive to a second input entered via … interface … identifying an application package to be loaded in the compute instance, loading, by the computer system, the application package in the compute instance (col. 7, lines 46-48 In order to test the operation of the program 108, the program 108 may be installed on the computing devices 118A-118N and/or device emulators 122A-122N specified by the developer 102 (which may also be referred to herein as “the test devices”)); and
executing the emulator for the device based on the application package (col. 7, lines 50-52 Once the program 108 has been installed on the test devices, the test manager 150 may test the operation of the program 108 upon the test devices [upon the device emulators]).
Marolia and Kulkarni do not expressly teach: wherein the machine learning model is communicatively coupled to an inference model hosted in a server, the inference model being utilized to obtain an enhanced prediction that is used to retrain the machine learning model executed on the compute instance.
However, wherein the machine learning model is communicatively coupled to an inference model hosted in a server (par. 0025 processing is executed in an edge device using a high-speed and low-accuracy lightweight model (DNN1) or a cloud (server device) using a low-speed and highly accurate high-accuracy model (DNN2); Fig. 2-1, 2-2 described DDN1 model coupled to DNN2 model), the inference model being utilized to obtain an enhanced prediction that is used to retrain the machine learning model executed on the compute instance (par. 0032 For the DNN1, parameters of the feature extraction layer Bf2 are fixed to parameters after training of the original DNN2′, and the detection layer Bd1 in a subsequent stage is trained using learning data. Alternatively, the DNN1 is trained using the learning data for both the feature extraction layer Bf2 and the detection layer Bd1. In addition, the DNN2 and the DNN1 may perform learning independently, or the DNN2 and the DNN1 may perform learning in cooperation with each other. For example, the DNN2 may be retrained using the learning data used by the DNN1. Furthermore, training may be performed using learning data common between the DNN1 and the DNN2; Fig. 2-1 and 2-2. It is noted, model DNN1 is trained using parameters and learning data of DNN2’, similarly DNN2 can be trained using learning data by DNN1).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the technique of executing inference processing a first model in edge device and a second model in a cloud server of Shi with the system and method of Marolia and Kulkarni resulting in a system and method that includes for performing inference in a second model responsive to inference processing reliability of a first model being equal to or less than and threshold, and using the results/learned data to train the first model as in Shi. One or ordinary skill in the art would have been motivate to make this combination for the purpose of providing a processing system, a processing method, and a processing program capable of reducing an amount of data transfer from an edge device to a server device and reducing delay (par. 0007).
As per claim 2, Marolia further teaches: wherein the application package further includes a mobile application (col. 7, lines 46-48 the program 108 may be installed on the computing devices 118A-118N and/or device emulators 122A-122N).
As per claim 3, Marolia further teaches: wherein the first input identifies a manufacturer, and a device type characterizing the device (col. 6, lines 64-67 A developer 102 might be permitted to select devices, and/or device emulators, for use in testing the program 108 based upon one or more of, a device manufacturer, a device type, a device version, device hardware, operating system version, other software version, or other attributes of a device).
As per claim 4, Marolia further teaches: wherein the device type is further characterized by an operating system of the device, a form factor of the device, and a memory size of the device (col. 1, lines 11-14 different smartphone models based upon the ANDROID operating system might include different processors, different amounts of memory).
As per claim 5, Marolia further teaches: where in the compute instance is a virtual machine (col. 2, lines 50-52 a host computer might be configured to execute some number (e.g., two or three) of device emulators in virtual machine instances).
As per claim 6, Marolia further teaches: wherein the computer system includes a notebook session manager an emulator instance controller, and the identifying is performed by the emulator instance controller (col. 12, lines 4-13 In some examples, the workflow coordinator 302 may be configured to determine whether the test devices, such as the computing devices 118A-118N and/or the device emulators 122A0-122N, that may be requested in the test request 112 are available for use in testing the program 108.), and wherein the receiving, the loading, and the executing are performed by the notebook session manager (col. 3, lines 1-17 When the test request is received, a test manager, workflow coordinator, or some other component or device in the testing service may determine whether the computing devices and/or device emulators that the program is to be tested on are available for use (i.e. not in use testing another program). If the devices and/or device emulators that the program is to be tested on are not available for use, a workflow component may cause the test request to be queued until such time as the devices and/or device emulators required for testing become available for use. If the devices and/or device emulators are available for use, the workflow coordinator, in conjunction with other components in the service provider network, may cause the program to be installed on the devices and/or device emulators upon which testing is to be performed. The program is then launched and executed on the devices and/or device emulator).
As per claim 7, Marolia further teaches: provisioning, by the emulator instance controller, a plurality of compute instances, each of which is preloaded with an operating system and a particular emulator for a particular device (col. 17, lines 22-24 service provider network 320 can provide virtual machine instances and computing resources on a permanent or an as-needed basis; col. 18, lines 21-28 Each of the server computers 802 may be configured to execute an instance manager (not shown) capable of instantiating and managing computing resources and instances of computing resources. In the case of virtual machine instances, for example, the instance manager might be a hypervisor or another type of program configured to enable the execution of multiple virtual machine instances).
As per claim 9, it is a non-transitory computer-readable memory having similar limitation as claim 1. Thus, claim 9 is rejected for the same rationale as applied to claim 1.
As per claim 10, it is a non-transitory computer-readable memory having similar limitation as claim 2. Thus, claim 10 is rejected for the same rationale as applied to claim 2.
As per claim 11, it is a non-transitory computer-readable memory having similar limitation as claim 3. Thus, claim 11 is rejected for the same rationale as applied to claim 3.
As per claim 12, it is a non-transitory computer-readable memory having similar limitation as claim 4. Thus, claim 12 is rejected for the same rationale as applied to claim 4.
As per claim 13, it is a non-transitory computer-readable memory having similar limitation as claim 5. Thus, claim 13 is rejected for the same rationale as applied to claim 5.
As per claim 14, it is a non-transitory computer-readable memory having similar limitation as claim 6. Thus, claim 14 is rejected for the same rationale as applied to claim 6.
As per claim 15, it is a non-transitory computer-readable memory having similar limitation as claim 7. Thus, claim 15 is rejected for the same rationale as applied to claim 7.
As per claim 17, it is a computer system having similar limitation as claim 1. Thus, claim 17 is rejected for the same rationale as applied to claim 1. Marolia further teaches: a processor; and a memory storing executable instructions (col. 21, lines 63-65 A non-transitory computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to).
As per claim 18, it is a non-transitory computer-readable memory having similar limitation as claim 2. Thus, claim 18 is rejected for the same rationale as applied to claim 2.
As per claim 19, it is a computer system having similar limitation as claim 3. Thus, claim 19 is rejected for the same rationale as applied to claim 3.
As per claim 20, it is a computer system having similar limitation as in claims 4 and 5. Thus, claim 20 is rejected for the same rationale as applied to claims 4 and 5.
Claims 8 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Marolia in view of Kulkarni, Morinaga and Shi as applied to claims 1 and 9, and further in view of Wang et al. (U.S. Pub. No. 20160134881 A1).
Wang was cited in a previous office action.
As per claim 8, Marolia, Kulkarni and Shi do not expressly disclose: responsive to a third input entered in the notebook indicating a termination of the emulator for the device, receiving, by the computer system, a third request indicating the third input; uninstalling the emulator for the device from the compute instance; and releasing the compute instance to a pool of available compute instances.
However, Wang teaches: receiving, by the computer system, a third request indicating the third input; uninstalling the emulator for the device from the compute instance; and releasing the compute instance to a pool of available compute instances (par. 0022 the controller can command the media splitter and Its associated virtual machine to be deleted from the cloud 14 or the controller can release the virtual machine to the resource pools for subsequent reuse).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the technique of releasing virtual machines to resource pool of Wang with the system and method of Marolia, Kulkarni and Shi resulting in a system and method in which compute instances are released to a pool of resources responsive to completion of a process/termination request as in Wang. The ordinary skill in the art would have been motivated to make this combination for the purpose of freeing up computing resources in the cloud for subsequent reuse (par. 0022, 0030).
As per claim 16, it is a non-transitory computer-readable memory having similar limitation as claim 8. Thus, claim 16 is rejected for the same rationale as applied to claim 8.
Response to Arguments
Applicant's arguments with respect to claims 1, 9 and 17 have been considered but are moot in view of the new ground(s) of rejection.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Pub. No. 20240095581 A1 teaches a processing method executed by a processing system that performs first inference in an edge device and performs second inference in a server device.
U.S. Pub. No. 20220036202 A1 teaches a system and method for providing intelligent traffic classification at a mobile edge using Artificial Intelligence (AI).
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 Willy W. Huaracha whose telephone number is (571) 270-5510. The examiner can normally be reached on M-F 8:30-5:00pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Bradley Teets can be reached on (571) 272-3338. 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 http://pair-direct.uspto.gov. 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.
/WH/
Examiner, Art Unit 2195
/BRADLEY A TEETS/Supervisory Patent Examiner, Art Unit 2197