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 .
Drawings
The drawings are objected to because:
In paragraphs 0021 and 0027, it describes proctoring base module for 112 in Figure 1, but drawing shows proctoring module 112;
Paragraph 0021 contains incorrect label for gaze estimation module 114, which should be gaze estimation module 116;
In paragraph 0024, 0048, and 0051, proctor device 124 is used instead of proctoring device 124 as referenced in Figure 1;
Paragraph 0040 mislabels the gaze estimation module 116 as the proctor base module 112;
Paragraph 0046 has minor informalities for Figure 5:
mislabeled step 510 as 514 for assessing whether the similarity is below the threshold;
mislabeled step 512 as 516 for flagging audio segment in recording database;
mislabeled step 514 as 518 for assessing whether the exam is complete;
mislabeled step 518 as step 520 for ending the program once the exam is complete;
Paragraph 0047 mislabels step 216 as step 600 in Figure 6;
Paragraph 0051 has minor informalities for Figure 6:
mislabeled step 614 as 616 for displaying segment on proctor verification module;
mislabeled step 616 as 618 for intervening during an examination;
mislabeled step 618 as 620 for ending student exam;
mislabeled step 212 as step 624 for ending the program;
Paragraph 0056 mislabeled service 716 as 706;
Paragraph 0052 clearly describes step 620 in Figure 6, but does not provide the reference number
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description: 602 and 624 in Figure 6.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because of the following informalities:
In paragraph 0006, line 6, “…computer screen, another face…” should be “…computer screen or another face…”;
In paragraph 0023, line 7, “Radio waves” should be “radio waves”; line 8, “Internet” should be “internet”;
In paragraph 0029 & 0044, consider changing “student device microphone 134” to “microphone 134 of the student device 128”;
In paragraph 0031, consider changing “student device camera 132” to “cameras 132 of the student devices 128”;
In paragraph 0031, line 7, “’15 s’“ is unclear. Use “15 seconds” or “15 s (15 seconds)” instead;
In paragraph 0032, line 8, “first ‘n’ frames” and “the value of ‘n’” are not clearly defined. Please revisit paragraph and revise;
In paragraph 0034, line 3, “Face” should be “face”; line 5, fix spacing in “…may return a cropped….”;
In paragraph 0035, line 2, “by face-matching service” should be “by the face matching service”;
Paragraph 0043 has the following informalities:
line 3-4: “…exam and calculate the normal yaw and pitch angle…” can be revised to say “…exam and used to calculate the normal yaw and pitch angle”;
line 5: “15s” should read “15 s” (If 15 seconds described before in paragraph 0031) or “15 seconds”;
line 9: fix spacing in “percentage such as 70%”;
In paragraph 0048, lines 3-4, consider changing “When new segments are received, identify, and display on the proctor device 124, at step 606.” to “When new segments are received, flags are identified and displayed on the proctor device for polling student exam activity at step 606”;
In paragraph 0052, line 3, fix spacing for “…adjust the weights…”;
For paragraph 0063:
in lines 8, 10, and 11, remove “etc.”;
in the same lines, replace each semicolon (;) with a comma and remove the extra commas resulting from that change;
In paragraph 0065, line 1, replace “804A through 804N” with “804A, 804B, and 804N”
In paragraph 0074, line 3, “out” should be “output”.
Appropriate correction is required.
Claim Objections
Claims 1, 7, 9, 15, and 17 are objected to because of the following informalities:
In claim 1:
line 22, “…to remove silent segments and flagging audio segments….” should read “…to remove silent segments and flag the audio segments…”;
In claim 7, fix spacing between “updated as” (line 3) and “time .” (line 4);
In claim 9:
line 14, “…to remove silent segments and flagging audio segments….” should read “…to remove silent segments and flag the audio segments…”;
In claim 15, line 3, fix spacing in “updated as” and “real time .”;
In claim 17:
line 16, “…to remove silent segments and flagging audio segments….” should read “…to remove silent segments and flag the audio segments…”;
Appropriate correction is required.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3, 6-7, 9, 11, 14-15, 17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Kulshrestha (US 2023/0274377) in view of Li (US 2022/039226).
Regarding Claim 1, Kulshrestha discloses “a system for proctoring online exams” (Kulshrestha, Paragraph [0006], where it discloses how it is “an end-to-end proctoring system using CNN (Convolutional Neural Network) to conduct secure online examinations”); “the system comprising: memory” (Kulshrestha, Abstract, where is discusses “one or more of the module(s) stored in a memory”) that “stores a face detection model” (Kulshrestha, Figure 3 (see figure below) and Paragraph [0006] disclose how their face recognition module is “configured to dynamically track a plurality of live face images of one or more users”); (Kulshrestha, Paragraph [0007], where the system has an audio analytics module that is “configured to capture and notify a count of distinct voices, silence, and noise present in a plurality of audio files of the one or more users recorded by the audio recording device”); and a proctor verification module (Kulshrestha, Paragraph [0008], where it discloses that the system has a warning module that is “configured to output a notification signal for the one or more module(s) to the one or more users and an administrator, the notification signal indicating that at least one suspicious activity is determined during the secure online examination”); (Kulshrestha, Abstract, where it discloses how “the processor is used to execute one or more modules stored in a memory”) to: “extract video frames from a video recorded from a camera of one of the student devices” (Kulshrestha, Paragraph [0006], discloses how “the system may include an image capturing device for capturing a plurality of face images”), “apply the face detection model to the extracted frames, wherein the face detection model compares detected faces to a provided image, wherein when no face is detected, more than one face is detected, or a face mismatch is detected, respective frames are flagged in a recording database” (Kulshrestha, Paragraphs [0040], [0041], disclose: “the user face recognition module is further configured to output a notification signal to the one or more users and the administrator, wherein the notification signal includes: a multiple face notification signal when the count of faces present in the plurality of live face images of the one or more users is greater than one; and a no face notification signal when the count of faces present in the plurality of live face images of the one or more users is equal to zero.”; Paragraph [0044] and Figure 5 (see below) disclose a user authentication module that functions by “matching and notifying at a pre-defined interval whether the plurality of live face images 501a of the one or more users 101 received by the input module 501 matches with a pre-stored facial feature information 501b of the one or more users 101 when non-occluded live face image 501a (Normal face 403a) of the one or more users 101 is spotted by the occlusion detection module”);
PNG
media_image1.png
775
897
media_image1.png
Greyscale
PNG
media_image2.png
602
794
media_image2.png
Greyscale
PNG
media_image3.png
877
835
media_image3.png
Greyscale
, “apply the speaker verification model to audio segments to remove silent segments and flagging audio segments with an utterance below a second similarity threshold based on a comparison with a reference audio captured from the student” (Kulshrestha, Paragraph [0031], discloses: “the CNN 116 may process the plurality of audio files 103a by pre-processing them and later extracting the features of the plurality of audio files 103a to recognise the various types of speech (i.e., voice 111a), non-speech (i.e., silence 111b), and noise 111c elements present in the plurality of audio files 103a.”; Paragraph [0050] discloses: “The plurality of audio files 103a may be initially pre-processed to remove the background silence 111b and the noise 111c and may be again pre-processed to remove more noise 111c from the plurality of audio files 103a.”; Figure 7 (see below));
and “apply the proctor verification module to calculate suspicion scores of flagged segments and determining that an intervention is required” (Kulshrestha, Paragraphs [0006], [0008], disclose: “the warning module configured to output a notification signal for the one or more module(s) to the one or more users and an administrator, the notification signal indicating that at least one suspicious activity is determined during the secure online examination”). Although Kulshrestha discloses that their proctoring system utilizes a face recognition module, user authentication module, and audio analytics module (please refer to Paragraphs [0006] and [0007] that disclose each of these modules), it does not explicitly disclose a module for head movement or gaze for the purpose of proctoring online exams, more specifically, a “gaze estimation model to the extracted frames by monitoring a yaw and pitch of a detected head in the extracted frames and comparing the yaw and pitch with a baseline yaw and pitch of the respective student, wherein video segments with frames that have a yaw and pitch below a first similarity threshold in comparison to the baseline yaw and pitch are flagged”. However, in an analogous field of endeavor, Li discloses a visual analytics system that “may detect various types of abnormal head movements, such as face disappearance and abnormal head pose, by analyzing head positions and head poses in the recorded video” (Li, Paragraph [0057]). The system may implement neural network models to estimate head poses, where it determines “an abnormal head pose in response to at least one of a yaw, a pitch, and a roll angles being greater than a threshold value” (Li, Paragraph [0058]). Li does not, however, describe using audio data to differentiate speakers via specific utterances during an online examination.
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the audio analytics, user authentication, and face recognition modules seen in Kulshrestha as well as the visual analytics system seen in Li to yield predictable results for the modules (face matching, gaze estimation, speaker verification) used in the online exam proctoring system seen in the aforementioned claims. One of ordinary skill in the art would be motivated to combine the two references in order to ensure a comprehensive evaluation of the face, gaze, and audio of a student in their testing environment while using the invention to proctor during online examinations. Therefore, it would have been obvious to combine Kulshrestha and Li to obtain the claimed invention in Claim 1.
Regarding Claim 3, the combination of Kulshrestha and Li teaches “the system of claim 1” (Kulshrestha, Paragraph [0006], please refer to the above-described analysis for Claim 1); wherein “the audio segments are flagged by using trained neural networks that recognize speech by processing many utterances at once, wherein vectors featuring a plurality of speakers and a plurality of utterance from each speaker are batched” (Kulshrestha, Paragraph [0051], where it describes “ the embeddings of the speech event i.e., the voice 111a may be generated to encode the one or more users 101 characteristics of an utterance into a fixed-length vector. For generating the embeddings of the voice 111a, a deep learning algorithm may be used to generate a high-level representation of the voice 111a. The deep learning algorithm may further create a summary vector of 256 values of the voice 111a that may summarize the characteristics of the voice 111a spoken by the one or more users 101. The embeddings may be a vector representation of the voice 111a which may be used by the deep learning algorithm.”; Paragraph [0052] discloses: “the clusters of the embeddings may be created of the speech events, i.e., the voice 111a based on the frequency, pitch, and tone characteristics of the one or more users 101. While clustering, the embeddings of the segments belonging to the same user’s 101 voice 111a may be labelled into one cluster, and the embeddings of the segments belonging to some other user 101 may be labelled into another cluster. The number of clusters created from the embeddings of the voice 111a may conclude the count of distinct voices 111a present in the plurality of audio files 103a of the one or more users 101.). Therefore, it would have been obvious to someone of ordinary skill of the art before the effective filing date of the claimed invention to substitute the unsupervised online clustering algorithm with trained neural networks to obtain predictable results to differentiate the flagged segments effectively, which can be seen in Claim 3.
Regarding Claim 6, the combination of Kulshrestha and Li teaches of a similar “system of claim 1” (Li, Paragraph [0006], discloses: “The system for proctoring online exams comprises a client-side computing system and a visual analytics system. The client-side computing system comprises a camera configured to obtain video data corresponding to a user while taking an exam and one or more input devices configured to obtain interaction data, wherein the interaction data includes mouse movements of the user while taking the exam. The visual analytics system is configured to obtain the video data and the interaction data from the client-side computing system, analyze the exam data to detect abnormal behavior by the user, generate one or more visualizations of the analyzed exam data, and display the one or more visualizations to a reviewer to facilitate the reviewer determining whether or not the user has cheated during the exam.”); wherein “the baseline yaw and pitch are calculated from a reference video” (Li, Paragraph [0056] discloses: “The visual analytics system may determine a rectangular bounding box 350 that appropriately encloses the student's face, and set the center of the rectangular bounding box 350 as the origin 340 of the 3D coordinate system” and “the pitch angle 315, the yaw angle 325 and the roll angle 335 may be associated with head rotations with respect to the X-axis 310, Y-axis 320 and Z-axis 330, respectively”); and “wherein a yaw angle is associated with the respective student looking left or right of a screen and a pitch angle is associated with the respective student looking up and down from the screen” (Li, Paragraph [0059] and Figure 3 (see below), disclose: “The pitch angle (e.g., the angle 315 as shown in FIG. 3) indicates where the student looks vertically, and the yaw angle (e.g., the angle 325 as shown in FIG. 3) indicates where the student looks horizontally)”).
PNG
media_image4.png
507
711
media_image4.png
Greyscale
Figure 3. From Li, discussing how they measure yaw and pitch of student’s head
It is evident that this technique has been used before to analyze the head position or movement to assess online exam activities. Therefore, it would have been obvious for one of ordinary skill of the art before the effective filing date of the claimed invention to use the known technique of assessing the yaw and pitch of the head via extracting video frames from a camera to yield predictable results.
Regarding Claim 7, the combination of Kulshrestha and Li teach “the system of claim 1” (Li, Paragraph [0006], please refer to the above-described analysis for Claim 6), wherein “the baseline yaw and pitch are calculated from a reference video of a time period of the respective student taking the exam” (Li, Paragraph [0060], discloses: “The visual analytics system may take into account different exam settings by different students, which may lead to different ranges of head positions and head poses. For instance, the visual analytics system may normalize each student's head positions and head poses at each video frame to (−1, 1) by applying min-max normalization, which is performed based on the minimum and maximum values of head positions and/or head poses for each student.”) wherein “a standard baseline yaw and pitch is updated as a machine-learning model accumulates more datapoints from the reference video in real time” (Li, Paragraph [0059] discloses: “the visual analytics system may implement neural network models to estimate head poses”). As described in the combination of Kulshrestha and Li, neural networks are classified as a subset of machine learning for a multitude of systems and models for various scientific and computational purposes. Therefore, it would have been obvious for one of ordinary skill of the art before the effective filing date of the claimed invention to use the known technique of assessing the yaw and pitch of the head via extracting video frames from a camera to improve the gaze estimation model via machine learning as described in Claim 7.
Regarding Claim 9, Kulshrestha teaches “a method of proctoring online exams, the method comprising:” (Kulshrestha, Paragraph [0007] discloses “an end-to-end proctoring method based on CNN for conducting the secure online examination”); (Kulshrestha, Paragraph [0007] discloses how the method captures “a plurality of live face images of one or more users by an image capturing device”); “applying a face detection model to the extracted frames, wherein the face detection model compares detected faces to a provided image, wherein when no face is detected, more than one face is detected, or a face mismatch is detected, respective frames are flagged in a recording database” (Kulshrestha, Paragraphs [0040], [0041], please refer to the above-described analysis for Claim 1); (Kulshrestha, Paragraphs [0031] and [0050] and Figure 7, please refer to the above-described analysis for Claim 1); and applying a proctor verification module to calculate suspicion scores of flagged segments and determining that an intervention is required (Kulshrestha, Paragraph [0006], discloses: “a warning module; wherein a notification signal for the one or more modules including, but not limited to, the user face recognition module, the occlusion detection module, the user authentication module, and the audio analytics module is outputted to the one or more users and an administrator by the warning module, wherein, the notification signal indicating that at least one suspicious activity is determined during the secure online examination”). Kulshrestha does not disclose a method for the gaze estimation model described as “monitoring a yaw and pitch of a detected head in the extracted frames and comparing the yaw and pitch with a baseline yaw and pitch of the student, wherein video segments with frames that have a yaw and pitch below a first similarity threshold in comparison to the baseline yaw and pitch are flagged”. However, in an analogous field of endeavor, Li discloses that their method for proctoring online exams utilizes a visual analytics system that assesses the student by “analyzing head poses and head positions of the user based on the video data; and determining abnormal head movements based on the head poses and head positions” (Li, Paragraph [0011]) through “determining an abnormal head pose in response to at least one of a yaw, a pitch, and a roll angles being greater than a threshold value” (Li, Paragraph [0012]).
Accordingly, it would be obvious to one of ordinary skill of the art before the effective filing date of the claimed invention to have combined the method containing the facial recognition, user authentication, and audio analytics modules described in Kulshrestha as well as the Li’s method of using a visual analytics system to assess head movement to yield predictable results. Using both of these methods, proctors can have the ability to fully evaluate the activity and behavior of each student adequately without leaving room open for cheating during online examinations. Both methods combined also offer a method for utilizing both the camera and the microphone of the student device to effectively analyze specific flagged segments when proctors access the system. Therefore, it would have been obvious to combine Kulshrestha and Li to obtain the method shown in Claim 9.
Regarding Claim 11, the combination of Kulshrestha and Li teach “The method of claim 9” (Kulshrestha, Paragraph [0007], please refer to the above-described analysis for Claim 9); wherein “the audio segments are flagged by using trained neural networks that recognize speech by processing many utterances at once, wherein vectors featuring a plurality of speakers and a plurality of utterance from each speaker are batched” (Kulshrestha, Paragraphs [0051] and [0052], please refer to the above-described analysis of claim 3). Therefore, it would have been obvious to someone of ordinary skill of the art before the effective filing date of the claimed invention to substitute the unsupervised online clustering algorithm with trained neural networks to obtain predictable results to differentiate the flagged segments effectively, which can be seen in Claim 11.
Regarding Claim 14, the combination of Kulshrestha and Li teach of a similar “method of claim 9” (Li, Paragraph [0015], discloses “a method for proctoring online exams using a visual analytics system. The method for proctoring online exams comprises collecting exam data corresponding to a user taking an exam, analyzing the exam data to detect abnormal behavior by the user, generating one or more visualizations of the analyzed exam data, and displaying the visualizations to a reviewer to facilitate the reviewer determining whether or not the user has cheated during the exam.); wherein “the baseline yaw and pitch are calculated from a reference video” (Li, Paragraph [0056], please refer to the above-described analysis for Claim 6); and “wherein a yaw angle is associated with the respective student looking left or right of a screen and a pitch angle is associated with the respective student looking up and down from the screen” (Li, Paragraph [0059] and Figure 3, please see the above-described analysis for Claim 6). It is evident that this technique has been used in before to analyze the head position or movement to assess online exam activities. Therefore, it would have been obvious for one of ordinary skill of the art before the effective filing date of the claimed invention to use the known technique of assessing the yaw and pitch of the head via extracting video frames from a camera to yield predictable results.
Regarding Claim 15, the combination of Kulshrestha and Li teaches “the method of claim 9” (Li, Paragraph [0015], please refer to the above-described analysis for Claim 6); wherein “the baseline yaw and pitch are calculated from a reference video of a time period of the respective student taking the exam” (Li, Paragraph [0060], please refer to the above-described analysis for Claim 7); wherein “a standard baseline yaw and pitch is updated as a machine-learning model accumulates more datapoints from the reference video in real time” (Li, Paragraph [0059], please refer to the above-described analysis for Claim 7). As described in the combination of Kulshrestha and Li, neural networks are classified as a subset of machine learning for a multitude of systems and models for various scientific and computational purposes. Therefore, it would have been obvious for one of ordinary skill of the art before the effective filing date of the claimed invention to use the known technique of assessing the yaw and pitch of the head via extracting video frames from a camera to improve the gaze estimation model via machine learning as described in Claim 15.
Regarding Claim 17, Kulshrestha teaches (Kulshrestha, Paragraph [0007], please refer to the above-described analysis for Claim 9) (Kulshrestha, Paragraphs [0040], [0041], please refer to the above-described analysis for Claim 1); (Kulshrestha, Paragraphs [0031] and [0050] and Figure 7, please refer to the above-described analysis for Claim 1); and applying a proctor verification module to calculate suspicion scores of flagged segments and determining that an intervention is required (Kulshrestha, Paragraph [0006], please refer to the above-described analysis for Claim 9). Kulshrestha does not disclose “a non-transitory, computer-readable storage medium, having embodied thereon instructions executable by a computing system” to perform the method it describes for its online exam proctoring system as well as the gaze estimation model to monitor head movements. However, in an analogous field of endeavor, Li teaches of “a non-transitory computer-readable medium having processor-executable instructions stored thereon for proctoring online exams using a visual analytics system. The visual analytics system executes the instructions to facilitate collecting exam data corresponding to a user taking an exam, analyzing the exam data to detect abnormal behavior by the user, generating one or more visualizations of the analyzed exam data, and displaying the visualizations to a reviewer to facilitate the reviewer determining whether or not the user has cheated during the exam.” (Li, Paragraph [0024]). In addition, as stated before, the visual analytics system detects abnormal behavior by “analyzing head poses and head positions of the user based on the video data; and determining abnormal head movements based on the head poses and head positions” (Li, Paragraph [0011]) through deciding “an abnormal head pose in response to at least one of a yaw, a pitch, and a roll angles being greater than a threshold value” (Li, Paragraph [0012]).
Thus, it would have been obvious for a person of ordinary skill of the art before the effective filing date of the claimed invention to combine the method utilizing the modules (facial recognition, audio analytics, user authentication) seen in Kulshrestha with the non-transitory computer storage medium containing the visual analytics system for proctoring online exams seen in Li to yield predictable results. By having the non-transitory computer readable storage medium, it would be intuitive to contain all four of the modules seen in the proctoring module (face matching, gaze estimation, speaker verification, and proctor verification) in order to keep everything in one place when monitoring student activity. By storing it in this fashion, the proctoring app accessing the proctoring module can be quickly able to access the audio and video data from each student without having to utilize a browser that may take a longer time to access the main information needed to proctor the online exam. With all that said, it would have been obvious to have combined Kulshrestha and Li to obtain the same storage system as described in Claim 17.
Regarding Claim 19, the combination of Kulshrestha and Li teaches “the non-transitory, computer-readable storage medium of claim 17” (Li, Paragraph [0024], please refer to the above-described analysis for Claim 17); wherein “the audio segments are flagged by using trained neural networks that recognize speech by processing many utterances at once, wherein vectors featuring a plurality of speakers and a plurality of utterance from each speaker are batched” (Kulshrestha, Paragraphs [0051] and [0052], please refer to the above-described analysis of claim 3). Therefore, it would have been obvious to someone of ordinary skill of the art before the effective filing date of the claimed invention to substitute the unsupervised online clustering algorithm with trained neural networks to obtain predictable results to differentiate the flagged segments effectively, which can be seen in Claim 19.
Claims 5, 8, 13, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Kulshrestha in view of Li as applied to claims 1, 3, 6-7, 9, 11, 14-15, 17, and 19 above, and further in view of Neelakanta (US 2021/0304339).
Regarding Claim 5, the combination of Kulshrestha and Li is not relied on to disclose “The system of claim 1, wherein the processor further executes the instructions to: receive an indication to not intervene based on the flagged segments; and retrain the face detection model, the gaze estimation model, or the speaker verification model based on the respective model that flagged the flagged segments, wherein the retraining adjusts weights to deprioritize aspects associated with the flagged segments.” In an analogous field of endeavor, Neelakanta teaches “the processor further executes the instructions” (Neelakanta, Paragraph [0021], discloses: “The memory includes a plurality of modules in the form of programmable instructions executable by the one or more hardware processors.”); to: “receive an indication to not intervene based on the flagged segments” (Neelakanta, Paragraph [0009], discloses: “notification generator module is configured to generate a notification message indicating violation of the test conditions by the user based on the generated trust score”); and retrain the face detection model, the gaze estimation model, or the speaker verification model based on the respective model that flagged the flagged segments, wherein the retraining adjusts weights to deprioritize aspects associated with the flagged segments” (Neelakanta, Paragraph [0008], discloses: “The data assessment module is configured to determine locally on the user device whether the extracted one or more user assessment parameters violates the set of predefined test assessment criteria based on a machine learning based user assessment model. The user assessment model represents a dynamic relationship between the extracted one or more user assessment parameters and a set of predefined test assessment criteria.”; Paragraph [0037] discloses: “The data assessment module 120 is further configured to determine locally on the user device 200 whether the extracted one or more user assessment parameters matches with corresponding pre-stored user assessment parameters present in the set of predefined test assessment criteria by comparing the extracted one or more user assessment parameters with the corresponding pre-stored user assessment parameters. The data assessment module 120 determines a deviation in the extracted one or more user assessment parameters based on the comparison. The data assessment module 120 further, determines whether the deviation is non-acceptable and intentional by the user using the generated machine learning based user assessment model.”). However, it does not directly teach any of the modules pertaining to facial recognition, gaze estimation, or audio analytics as the other references describe (although it is implicitly described due to the broad nature of the system and method). With that said, it would be obvious to one of ordinary skill of the art before the effective filing date of the invention to use each of the methods described in Neelakanta in combination with Kulshrestha and Li, proctoring the exam using the proctoring app in the claimed invention would be easier to track, as it will consistently be able to train the model based off of the data received from the exam taker’s device. Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date of the invention to pursue the known ways of these machine learning methods with a reasonable expectation of success.
Regarding Claim 8, the combination of Kulshrestha and Li teaches “the system of claim 7” (Kulshrestha, Paragraph [0006] and Li, Paragraph [0006], please refer to the above-described analysis for Claims 1 and 6). Kulshrestha, Li and Neelakanta describe “wherein the processor further executes the instructions” (Li, Paragraph [0024], discloses: “a non-transitory computer-readable medium having processor-executable instructions stored thereon for proctoring online exams using a visual analytics system”; Neelakanta, Paragraph [0007], discloses: “The system includes one or more hardware processors on a user device and a memory on the user device coupled to the one or more hardware processors. The memory includes a plurality of modules in the form of programmable instructions executable by the one or more hardware processors.”); to: “cause to present a display that generates real-time indications of the suspicion scores” (Li, Paragraph [0006], disclose how the system can “generate one or more visualizations of the analyzed exam data, and display the one or more visualizations to a reviewer to facilitate the reviewer determining whether or not the user has cheated during the exam.”; Neelakanta, Paragraph [0009], discloses: “a display module configured to output the trust score and the generated notification message on a user interface of the user device”). The combination of Kulshrestha and Li teaches (Li, Paragraph [0013], discloses: “generating a bounding box corresponding to the face of the user on an image frame in the video data, wherein the size of the bounding box is based on a distance between the face of the user and a screen on the image frame”; Figure 8B (see below) & Paragraph [0081] describe the inspection process during an online exam, where:
“the proctor may inspect the behavior chart 822 for a current student, the corresponding heatmap 824 by all students and the suspected case chart 826 identified for the current student. The behavior chart 822 may include a dot plot 828 for mouse positions and a line plot 830 for head poses”. Upon inspection, the proctor may “may further check the size of the bounding box as the range of the shadowed area plotted in the behavior chart 822. If the bounding box becomes smaller (e.g., at a second moment 834), the proctor confirms that the distance between the student's face and the screen becomes larger. Then, the proctor may inspect the student's head poses according to the behavior chart 822 and the heatmap 824 in the Behavior View 430”.
PNG
media_image5.png
622
795
media_image5.png
Greyscale
Further explained for Figure 8B, “the proctor may find that the student's head poses are frequently outside his normal range of pitch angles by comparing the behavior chart 822 of the current student with the heatmap 824 by all students. Then, the proctor may inspect the related video in the Playback View 440. For example, the proctor may find that the student raised his/her head at the second moment 834, a third moment 836 and a fourth moment 838, and afterward looked at something other than the laptop screen. Screenshots 842, 844, 846 and 848 are captured for the moments 832, 834, 836 and 838, respectively. The screenshots 842, 844, 846 and 848 may be presented in the Playback View 440 as shown in FIG. 4 or 8A. Based on this evidence, the proctor may determine this case to be a potential cheating case.”). However, the combination of Kulshrestha and Li does not explicitly teach of any method of the proctor “receiving an indication” directly from the system to observe a change to the standard baseline yaw and pitch through showing a flagged segment.
Neelakanta further teaches, in its own system, each of its modules. They explain the following: “The score generator module is configured to generate a trust score for the user based on whether the extracted one or more user assessment parameters is determined to violate the set of predefined test assessment criteria. The notification generator module is configured to generate a notification message indicating violation of test by the user based on the generated trust score. The display module is configured to output the trust score and the generated notification message on a user interface of the user device” (Neelakanta, Paragraph [0009]). In addition to this, the system “is configured in the user's device locally to capture user's audio and video feeds from the user device including the continuous screen capture of display screen of the user device, receiving the captured audio and video feeds, monitoring a plurality of factors including number of users on the screen, direction of the eye gaze, audio cues, sudden changes to user environment, application in focus and the like. The user's device acts as a stand-alone device to perform the computerised test assessment of the users. Report generated after assessment is communicated to a remote server or to an administrator” (Neelakanta, Paragraph [0024]). However, it does not explicitly teach any methods of monitoring the yaw and pitch, although it is directly implied through the data extraction modules extracting continuous video and audio from the user device.
These important aspects of Neelakanta’s system show how they implement real-time trust scores and feedback based on what they observe with the student behavior obtained from the data extraction modules. It also shows how the proctor can be easily notified and shown specific aspects of student activity as an exam takes place concurrently. Thus, it would be obvious to combine the method of monitoring the head poses using a reference video (such as a bounding box) seen in the combination of Kulshrestha and Li and the score generator, notification generator, and display modules seen in Neelakanta to yield predictable results for Claim 8.
Regarding Claim 13, the combination of Kulshrestha, Li, and Neelakanta teaches “the method of claim 9” (Neelakanta, Abstract, discloses: “The system and method include acquisition of one or more user data associated with a user during a test session. The test session is hosted locally on the user device. One or more user assessment parameters are extracted from the acquired one or more user data locally on the user device. It is determined locally on the user device, whether the extracted one or more user assessment parameters violates the set of predefined test assessment criteria based on a machine learning based user assessment model. This determination happens on the device directly, without it having to be processed by a server. A trust score is generated based on the violations the user commits during the test. Further, a notification message is generated indicating violation of test by the user. The trust score and the generated notification message are displayed on a user interface of the user device.”); further comprising: “receiving an indication to not intervene based on the flagged segments” (Neelakanta, Paragraph [0009], please refer to the above-described analysis for Claim 5); and “retraining the face detection model, the gaze estimation model, or the speaker verification model based on the respective model that flagged the flagged segments, wherein the retraining adjusts weights to deprioritize aspects associated with the flagged segments” (Neelakanta, Paragraph [0008], please refer to the above-described analysis for Claim 5). However, it does not directly teach any of the modules pertaining to facial recognition, gaze estimation, or audio analytics as the other references describe (although it is implicitly described due to the broad nature of the system and method). Thus, it would be obvious to one of ordinary skill of the art before the effective filing date of the claimed invention to use each of the methods described in Neelakanta in combination with Kulshrestha and Li to make proctoring the exam using the proctoring app easier to track student activity, as it will consistently be able to train the model based off of the data received from the exam taker’s device. Therefore, it would have been obvious to one of ordinary skill of the art before the effective filing date of the claimed invention to pursue the known ways of these machine learning methods with a reasonable expectation of success.
Regarding Claim 16, the combination of Kulshrestha and Li teaches “the method of claim 15” (Kulshrestha, Paragraph [0006] & Li, Paragraph [0006], please refer to the above-described analysis for Claim 8); Kulshrestha, Li and Neelakanta describe “wherein the processor further executes the instructions” (Li, Paragraph [0024] & Neelakanta, Paragraph [0007], please refer to the above described analysis for Claim 8); to: “cause to present a display that generates real-time indications of the suspicion scores” (Li, Paragraph [0006] & Neelakanta, Paragraph [0007], please refer to the above-described analysis for Claim 8). The combination of Kulshrestha and Li describes (Li, Paragraph [0013], Figure 8B & Paragraph [0081], please refer to the above-described analysis for Claim 8). However, the combination of Kulshrestha and Li does not explicitly teach of any method of the proctor “receiving an indication” directly from the system to observe a change to the standard baseline yaw and pitch through showing a flagged segment.
However, Neelakanta further teaches, in its own system, about each of its modules. They explain the following: “The score generator module is configured to generate a trust score for the user based on whether the extracted one or more user assessment parameters is determined to violate the set of predefined test assessment criteria. The notification generator module is configured to generate a notification message indicating violation of test by the user based on the generated trust score. The display module is configured to output the trust score and the generated notification message on a user interface of the user device” (Neelakanta, Paragraph [0009]). In addition to this, the system “is configured in the user's device locally to capture user's audio and video feeds from the user device including the continuous screen capture of display screen of the user device, receiving the captured audio and video feeds, monitoring a plurality of factors including number of users on the screen, direction of the eye gaze, audio cues, sudden changes to user environment, application in focus and the like. The user's device acts as a stand-alone device to perform the computerised test assessment of the users. Report generated after assessment is communicated to a remote server or to an administrator” (Neelakanta, Paragraph [0024]). However, it does not directly teach any methods of monitoring the yaw and pitch, although it is directly implied through the data extraction modules extracting continuous video and audio from the user device.
These important aspects of Neelakanta’s system show how they implement real-time trust scores and feedback based on what they observe with the student behavior obtained from the data extraction modules. It also shows how the proctor can be easily notified and shown specific aspects of student activity as an exam takes place concurrently. Thus, it would be obvious to combine method of monitoring the head poses using a bounding box seen in the combination of Kulshrestha and Li and the score generator, notification generator, and display modules seen in Neelakanta to yield predictable results for Claim 16.
Claims 2, 10, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Kulshrestha in view of Li as applied to claims 1, 3, 6, 9, 11, 14, 17, and 19 above, and further in view of Lee (KR 20210158466 A).
Regarding Claim 2, the combination of Kulshrestha and Li is not relied on to teach wherein “the face detection model compares the detected faces to the provided image by calculating a Euclidean distance between an embedding of each face detected in the extracted frames and a face detected from the provided image”. However, in an analogous field of endeavor, Lee teaches of a similar “system of claim 1” (Lee, Paragraph [0001], discloses: “an online test system using artificial intelligence for preventing cheating using voice recognition and a method thereof and, more specifically, to an online test system based on a tablet pc, a smartphone, and a pc using facial contour recognition artificial intelligence for preventing cheating using voice recognition and a method thereof, wherein in a non-face-to-face online test and a ubt test, an artificial intelligence face recognition module, a five-point scale cheating prevention module of a feature point of a face, a tablet pc equipped with a voice recognition module, a smartphone, and a pc-based online test and a ubt test, when a facial contour is not recognized at the time of face recognition, a camera image of the tablet pc deviates from a photographed test screen (when a distance in a corresponding direction such as an eye/ear distance, a nose/ear distance, and the like exceeds a certain value depending on whether three eyes/nose points approach two ears at both ends), voice data of an examinee is transmitted to the online test or the ubt test server when a voice signal of the examinee sensed by a micro of an examinee terminal generates a sound of a reference decibel db or more of gaussian noise, is output to a supervisor terminal through the test server, a warning message or an alarm is output to the corresponding examinee terminal or stored in an information device of the corresponding examinee terminal and then transmitted to the test server at the end of the test, and a scoring result is provided to the examinees.”); wherein “the face detection model compares the detected faces to the provided image by calculating a Euclidean distance between an embedding of each face detected in the extracted frames and a face detected from the provided image” (Lee, Paragraph [0184] and Figure 10 (see below) disclose: “A face recognition module of an examinee terminal recognizes a face behavior pattern photographed by a front camera of the examinee terminal, extracts a face object, extracts feature points of a face on a 5-point scale of eyes/noses/ears, recognizes an outline of the face of the examinee and eye/noses/ears feature points, calculates a Euclidean distance (d) and similarity between left/right ears of the feature points of the face of the eyes/noses/ears and a center point (pupil) of the left/right eyes, respectively, detects an abnormal behavior pattern of the face related to cheating by detecting a head movement to the right/left according to whether three points of the eyes/noses approach two points of both ends of the ears, transmits a face picture related to cheating to a test server to prevent cheating when a facial outline is not recognized at the time of face recognition and deviates from a test screen of the examinee terminal (when a distance in a corresponding direction of the distance of the eyes/ears and the distance of the noses/ears exceeds a predetermined reference value according to whether the three points of the eyes/noses approach two points of both ends of the ears). and/or transmits a face picture related to cheating to a test server to prevent cheating.”).
PNG
media_image6.png
793
852
media_image6.png
Greyscale
Therefore, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate this system that utilizes the Euclidean distances on features of the face into the face matching module to accurately assess the student as he or she is facing the screen. By doing this, they can clearly identify the student before he/she takes the exam and the system tracks their activity throughout the session. With that said, it is obvious that one of ordinary skill of the art would have recognized that the Euclidean distance approach for the face recognition module would have yielded predictable results and resulted in an improved system for Claim 2.
Regarding Claim 10, the combination of Kulshrestha and Li is not relied on to teach wherein “the face detection model compares the detected faces to the provided image by calculating a Euclidean distance between an embedding of each face detected in the extracted frames and a face detected from the provided image”. However, in an analogous field of endeavor, Lee teaches of a similar “method of claim 9” (Lee, Claim 13, discloses of a method involving the following steps: “The step that the member information is registered, and that the examinee information and front side face picture are registered after the log-in / user authentication as the online test or the ubt test server and stored; The step that the online test or the ubt test server it issues the quick response code corresponding to the examinee information and front side face photograph; The step that the on-line test or the ubt test server it notifies the test schedule and place according to the supervision test; The step that the supervisor terminal the recognition result of the front side face photograph of the camera is received in the online test or the ubt test server as the front side face recognition algorithm is used in the examinee terminal equipped with the face recognition module is received to the online test or the ubt test server and the examinee information, the photograph and feature points are compared and it confirms the examinee oneself whether or not and it prevents the proxy test and it determines whether or not to take the test or not; A step of transmitting the face image and voice data of the examinee to a test server, outputting the face image and voice data to a supervisor terminal through the test server, and receiving a warning message or an alarm from the test server to a corresponding examinee terminal when detecting the auditory cheating of the examinee taking the online test detected by the camera and the micro in the examinee terminal And; Providing a test program (app) and an online test sheet to the examinee terminal and the supervisor terminal, storing and managing examinee information, a field face picture of the examinee, and supervisor information in a database of a test server, storing a test sheet writing answer in each examinee terminal for a predetermined test time during an online test or a ubt test, receiving and storing the test sheet writing answer from the examinee terminal to the test server when the test is finished, and providing a scoring result of the test sheet writing answer of the examinees to the examinee terminal”); wherein “the face detection model compares the detected faces to the provided image by calculating a Euclidean distance between an embedding of each face detected in the extracted frames and a face detected from the provided image” (Lee, Paragraph [0184] and Figure 10, please refer to the above-described analysis for Claim 2).
Therefore, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate this system that utilizes the Euclidean distances on features of the face into the face matching module to accurately assess the student as he or she is facing the screen. By doing this, they can clearly identify the student before he/she takes the exam and the system tracks their activity throughout the session. With that said, it is obvious that one of ordinary skill of the art would have recognized that the Euclidean distance approach for the face recognition module would have yielded predictable results and resulted in an improved system for Claim 10.
Regarding Claim 18, the combination of Kulshrestha, Li, and Lee teach of a “non-transitory storage medium of claim 19” (Lee, Paragraph [0241], discloses: “the present invention (described in [0001]) may be implemented in the form of program instructions that may be executed through various computer means and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, and data structures alone or in combination. The non-transitory computer-readable recording medium may include magnetic media such as a storage, a hard disk, a floppy disk, and a magnetic tape, optical media such as a cd-rom and a dvd, magneto-optical media such as a floptical disk, and hardware devices configured to store and perform program instructions in storage media such as a read-only memory (rom), a random access memory (ram), a flash memory, and the like.”); and “the face detection model compares the detected faces to the provided image by calculating a Euclidean distance between an embedding of each face detected in the extracted frames and a face detected from the provided image” (Lee, Paragraph [0184] and Figure 10, please refer to the above-described analysis for Claim 2).
Therefore, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate this system that utilizes the Euclidean distances on features of the face into the face matching module to accurately assess the student as he or she is facing the screen. By doing this, they can clearly identify the student before he/she takes the exam and the system tracks their activity throughout the session. With that said, it is obvious that one of ordinary skill of the art would have recognized that the Euclidean distance approach for the face recognition module would have yielded predictable results and resulted in an improved system for Claim 18.
Claim(s) 4, 12, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kulshrestha in view of Li as applied to claims 1-3, 6-11, and 13-19 above, and further in view of Heigold (US 2017/0069327).
Regarding Claim 4, the combination of Kulshrestha and Li is not relied on to disclose “wherein a similarity matrix defined as scaled cosine similarities extracted from one speaker and one utterance, and wherein the second similarity threshold is determined based on the similarity of compared vectors.” However, in an analogous field of endeavor, Heigold teaches of a similar “the system of claim 3” (Heigold, Paragraph [0050], discloses: “the computing system 120 selects samples of training utterances to provide to the neural network 140 for supervised training of the neural network 140. In some implementations, the utterances in the training samples 122 may each consist of one or more predetermined words spoken by many different training speakers, the utterances having been previously recorded and made accessible for use by the computing system 120.”); wherein “a similarity matrix defined as scaled cosine similarities extracted from one speaker and one utterance” (Heigold, Paragraph [0079], discloses: "For example, the measure of similarity may be a cosine distance between a vector of values for the speaker representation and a vector of values for the simulated speaker model."), and wherein “the second similarity threshold is determined based on the similarity of compared vectors” (Heigold, Paragraph [0079], discloses: “The measure of similarity may then be used to estimate a classification of the first set of training data as either a matching speakers sample or a non-matching speakers sample. For example, if the measure of similarity is sufficiently high (e.g., meets a threshold similarity score), then a logistic regression may be used to map the set of training data to a class of matching speakers. On the other hand, if the measure of similarity is too low (e.g., does not meet the threshold similarity score), then the logistic regression may be used to map the set of training data to a class of non-matching speakers”).
Thus, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize this technique to distinguish speakers from one another to ensure that each voice is categorized. By implementing this into the current system, one of ordinary skill of the art could improve the online exam proctoring system to identify whether there are unknown speakers within the environment, ultimately being able to flag that recorded segment for a proctor to view within the app, Therefore, it is obvious that one of ordinary skill in the art could have applied the method seen in Heigold of using a similarity matrix and similarity of compared vectors to differentiate speakers from audio in the same way to improve the online proctoring system through the limitation seen in Claim 4.
Regarding Claim 12, the combination of Kulshrestha and Li is not relied on to disclose “wherein a similarity matrix defined as scaled cosine similarities extracted from one speaker and one utterance, and wherein the second similarity threshold is determined based on the similarity of compared vectors.” However, in an analogous field of endeavor, Heigold teaches “the method of Claim 11” (Heigold, Paragraph [0004] discloses: “The method can include selecting, at a computing system, multiple different subsets of training data for training a neural network. Each subset of training data can include a plurality of first components that characterize respective utterances of a first speaker and a second component that characterizes an utterance of the first speaker or a second speaker. For each of the selected subsets of training data, the method can include: inputting each of the first components into the neural network to generate a respective first speaker representation corresponding to each of the first components; inputting the second component into the neural network to generate a second speaker representation corresponding to the second component; determining a simulated speaker model for the first speaker based on an average of the respective first speaker representations for the plurality of first components; comparing the second speaker representation with the simulated speaker model to classify the utterance characterized by the second component as an utterance of the first speaker or as an utterance of a speaker other than the first speaker; and adjusting the neural network based on whether the utterance characterized by the second component was correctly classified as an utterance of the first speaker or as an utterance of a speaker other than the first speaker.”); wherein “a similarity matrix defined as scaled cosine similarities extracted from one speaker and one utterance” (Heigold, Paragraph [0079], please refer to the above-described analysis for Claim 4), and wherein “the second similarity threshold is determined based on the similarity of compared vectors” (Heigold, Paragraph [0079], please refer to the above-described analysis for Claim 4).
Thus, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize this technique to distinguish speakers from one another to ensure that each voice is categorized. By implementing this into the current system, one of ordinary skill of the art could improve the online exam proctoring system to identify whether there are unknown speakers within the environment, ultimately being able to flag that recorded segment for a proctor to view within the app, Therefore, it is obvious that one of ordinary skill in the art could have applied the method seen in Heigold of using a similarity matrix and similarity of compared vectors to differentiate speakers from audio in the same way to improve the online proctoring system through the limitation seen in Claim 12.
Regarding Claim 20, the combination of Kulshrestha and Li is not relied on to disclose “wherein a similarity matrix defined as scaled cosine similarities extracted from one speaker and one utterance, and wherein the second similarity threshold is determined based on the similarity of compared vectors.” However, in an analogous field of endeavor, Heigold teaches (Heigold, Paragraph [0079], please refer to the above-described analysis for Claim 4); and wherein “the second similarity threshold is determined based on the similarity of compared vectors” (Heigold, Paragraph [0079], please refer to the above-described analysis for Claim 4).
Thus, it would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to utilize this technique to distinguish speakers from one another to ensure that each voice is categorized. By implementing this into the current system, one of ordinary skill of the art could improve the online exam proctoring system to identify whether there are unknown speakers within the environment, ultimately being able to flag that recorded segment for a proctor to view within the app, Therefore, it is obvious that one of ordinary skill in the art could have applied the method seen in Heigold of using a similarity matrix and similarity of compared vectors to differentiate speakers from audio in the same way to improve the online proctoring system through the limitation seen in Claim 20.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Azim (EP 23158610 A) teaches a system for proctoring online exams using two recording devices (one for monitoring user and environment, another for monitoring first recording device and workspace) to detect any possible instances of cheating.
Smetters (US 11645935) teaches systems and methods for analyzing data collected from online examinations through flagging one or more proctoring events associated with exam violations.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SORIE I KOROMA JR whose telephone number is (571)272-9259. The examiner can normally be reached Monday - Friday 8AM-6:00PM; Alternate Fridays Off.
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, Amandeep Saini can be reached at 571-272-3382. 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.
/SORIE I KOROMA JR/Examiner, Art Unit 2662
/Siamak Harandi/
Primary Examiner, Art Unit 2662