DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Foroozan et al. (U.S. 2021/0117659 A1).
Claim 1, Foroozan teaches:
A monitoring device (Foroozan, Paragraph [0027], The radar-based assisted living (RadAL) system is a monitoring device.) comprising:
memory (Foroozan, Paragraph [0028], Long short-term memory and CNNs are used for activity recognition, image captioning, and video description. Additionally, electrical device 1800 represents one or more of the monitoring units, wherein the electrical device 1800 includes at least one processor and at least one memory (see Foroozan, Paragraphs [0093-0095]).) storing a predictive model of a neural network (Foroozan, Paragraphs [0051-0052], The system utilizes a pre-trained model used for object detection applications.); and
a processing unit comprising one or more processor (Foroozan, Fig. 1, The system 10 performs both radar signal processing and vision processing. The processing is performed by a combination of hardware, software, algorithms, and/or circuitry (see Foroozan, Paragraph [0035]).) configured to:
receive sensor data representative of a person (Foroozan, Paragraph [0033], The radar source is coupled to a point cloud. As seen in Fig. 2A, the radar generates a plurality of dots representative of reflected signals that are processed in order to determine moving objects, i.e. humans (see Foroozan, Paragraphs [0038-0039]).), the sensor data being generated by a radar sensor (Foroozan, Fig. 1: 15), the sensor data comprising at least one of the following: a plurality of consecutive sets of centroid data representative of the person and a plurality of consecutive sets of point cloud data representative of the person (Foroozan, Paragraphs [0040-0043], The system 10 receives a plurality of point clouds, i.e. consecutive sets of point cloud data, and utilizes a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to calculate a centroid of each [point cloud] cluster, i.e. consecutive sets of centroid data. The point cloud data potentially represents different body parts of a person. Fig. 7 shows a DBSCAN example implementation 70 that calculates the centroid of each cluster and estimates the boundaries of the target (see Foroozan, Paragraph [0059]).); and
execute a neural network inference engine, the neural network inference engine implementing the neural network using the predictive model for inferring one or more output based on inputs, the one or more output providing an indication of whether an event related to the person has occurred or not, the inputs comprising at least some of the sensor data (Foroozan, Figs. 8-11, Paragraphs [0064-0077], The Convolutional Neural Network (CNN) is functionally equivalent to a neural network inference engine. The CNN receives the data from both radar and cameras, i.e. the inputs, processes the clustered data, and outputs connected layers and class scores, e.g. Fig. 11 indicates a fall with a 99% score, wherein the fall represents an event related to the person.).
Foroozan does not explicitly teach:
The predictive model comprising weights of the neural network.
However, it would have been obvious to one of ordinary skill in the art, at the time of filing, for the plurality of inputs, e.g. sensor data, clusters, and centroids, to have a weight, e.g. equal weight, in order to yield fully connected layers and class scores (see Foroozan, Figs. 8-11, Paragraphs [0064-0077]). Such a modification would not change the principal operation of the system, as a whole, and would yield predictable results.
Claim 2, Foroozan further teaches:
The monitoring device of claim 1, wherein the radar sensor is integrated to the monitoring device (Foroozan, Fig. 1: 15, Paragraph [0035], All of the blocks of Fig. 1 can readily be implemented as hardware, software, algorithms, and/or circuitry of any kind, and it would have been obvious to one of ordinary skill in the art, at the time of filing, for the monitoring unit 15 to be physically integrated or a separate device from the system 10. Such a modification would not change the principal operation of the system, as a whole, and would yield predictable results. See MPEP 2144.04.).
Claim 3, Foroozan further teaches:
The monitoring device of claim 1, wherein the radar sensor is not integrated to the monitoring device (Foroozan, Fig. 1: 15, Paragraph [0035], All of the blocks of Fig. 1 can readily be implemented as hardware, software, algorithms, and/or circuitry of any kind, and it would have been obvious to one of ordinary skill in the art, at the time of filing, for the monitoring unit 15 to be physically integrated or a separate device from the system 10. Such a modification would not change the principal operation of the system, as a whole, and would yield predictable results. See MPEP 2144.04.), and the sensor data are received from the radar sensor via a communication interface of the monitoring device (Foroozan, Fig. 1: 15, As indicated by the arrows in Fig. 1, the data collected from monitoring unit 15, which includes the radar, follows the arrows towards multi-object tracking 16, which represents a communication interface.).
Claim 4, Foroozan further teaches:
The monitoring device of claim 1, wherein the inputs comprise the plurality of consecutive sets of centroid data representative of the person, each set of centroid data comprising at least one of the following: at least one coordinate of the centroid, at least one velocity component of the centroid, and at least one acceleration component of the centroid (Foroozan, Paragraph [0036], The detected element represents the centroid based on filtering a cluster of point cloud data (see Foroozan, Paragraphs [0040-0043]), wherein the 3D location and velocity of the detected element can be determined. It would have been obvious to one of ordinary skill in the art, at the time of filing, for the system to be capable of determining an acceleration component of the detected element. For example, the system can assume a constant velocity for an element, i.e. an acceleration component of 0 (see Foroozan, Paragraph [0046]).).
Claim 5, Foroozan further teaches:
The monitoring device of claim 1, wherein the inputs comprise the plurality of consecutive sets of point cloud data representative of the person, each set of point cloud data comprising for each point of the point cloud at least one of the following: at least one coordinate of the point, a velocity of the point, and a signal to noise ratio (SNR) of the point (Foroozan, Paragraph [0036], The detected element represents the centroid based on filtering a cluster of point cloud data (see Foroozan, Paragraphs [0040-0043]), wherein the 3D location and velocity of the detected element can be determined. The system can reduce the effect of noise (see Foroozan, Paragraphs [0038-0039]), thus it would have been obvious to one of ordinary skill in the art, at the time of filing, for the system to utilize a signal to noise ration of a set of point cloud data clusters for filtering out potential noise, e.g. noise caused by reflections of moving targets.).
Claim 6, Foroozan further teaches:
The monitoring device of claim 1, wherein the inputs further comprise at least one of the following: contextual information related to the person, contextual information related to an environment where the person is located, timing information and static coordinate data related to the environment where the person is located (Foroozan, Paragraph [0036], Location of the detected element is equivalent to contextual information related to the person, contextual information related to an environment, and static coordinate data. The point cloud data represents real-time information, i.e. timing information.).
Claim 7, Foroozan further teaches:
The monitoring device of claim 1, wherein the one or more output providing an indication of whether an event related to the person has occurred or not comprises at least one of the following: a Boolean and a probability, the one or more output optionally further comprising an indication of severity of the event (Foroozan, Fig. 11, Paragraph [0077], The connected layers are accompanies by class scores, which may be presented as a percentage, i.e. a probability. Additionally, Applicant’s specification defines in Paragraph [0061] that the one or more outputs may be Boolean or a probability, but not necessarily both, therefore only one is required. As seen in Fig. 11, one of ordinary skill in the art would recognize that a fall determination could be categorized as a “severe” event, whereas sitting or walking could be categorized as a “non-severe” event.).
Claim 8, Foroozan further teaches:
The monitoring device of claim 7, wherein the one or more output further comprises an indication of severity of the event (Foroozan, Fig. 11, Paragraph [0077], The connected layers and class scores may indicate that the person has experienced a fall, i.e. a “severe” event.).
Claim 9, Foroozan further teaches:
The monitoring device of claim 1, wherein the person is located in a room at least partially in a field of view of the radar sensor (Foroozan, Paragraph [0039], The human body and static objects are in the field of view of the radar.), and the event is a fall of the person (Foroozan, Fig. 11, Paragraph [0077]).
Claim 10, Foroozan further teaches:
The monitoring device of claim 1, wherein the one or more output is indicative of the event related to the person having occurred, and the monitoring device performs at least one of the following actions: sending via a communication interface of the monitoring device an alert message indicative of the event related to the person having occurred to a remote computing device and triggering a display of a visual indicator representative of the detection that the event related to the person has occurred (Foroozan, Paragraph [0092], In response to a detected fall, for example, the result could be sent over a network to a caregiver, a monitoring company, an emergency service, or a doctor. IT would have been obvious to one of ordinary skill in the art, at the time of filing, for the result to be presented to the receiver via a display, e.g. display device 1806 (see Foroozan, Paragraph [0100]). Such a modification would ensure that the receiver, i.e. a caregiver, a monitoring company, an emergency service, or a doctor, is able to interpret the results and act accordingly.).
Claim 11, Foroozan further teaches:
The monitoring device of claim 10, wherein the monitoring device sends the alert message indicative of the event related to the person having occurred to the remote computing device, the alert message comprising at least one of the following: a location where the event related to the person has occurred, the plurality of consecutive sets of centroid data representative of the person and the plurality of consecutive sets of point cloud data representative of the person (Foroozan, Fig. 12, Paragraph [0078], As per the example of Fig. 12, additional optional cloud services include remote access to the system for the doctor/nurse/relatives. It would have been obvious to one of ordinary skill in the art, at the time of filing, for the remote access to the system to include at least the location of the identified patient/event (see Foroozan, Paragraph [0036]). It is additionally noted that Paragraph [0089] of the Applicant’s specification defines the alert message “may” further comprise monitoring data, “such as” the limitations of claim 11, including the plurality of consecutive sets of centroid data representative of the person and/or the plurality of consecutive sets of point clou data representative of the person. Therefore, the limitations of claim 11 are interpreted as only requiring one limitation and/or a combination thereof.).
Claim 12, Foroozan teaches:
A method for monitoring a person based on radar sensor data (Foroozan, Paragraph [0027], The radar-based assisted living (RadAL) system is a monitoring device.), the method comprising:
storing in a memory of a computing device (Foroozan, Paragraph [0028], Long short-term memory and CNNs are used for activity recognition, image captioning, and video description. Additionally, electrical device 1800 represents one or more of the monitoring units, wherein the electrical device 1800 includes at least one processor and at least one memory (see Foroozan, Paragraphs [0093-0095]).) a predictive model of a neural network (Foroozan, Paragraphs [0051-0052], The system utilizes a pre-trained model used for object detection applications.);
collecting by a processing unit of the computing device sensor data generated by a radar sensor (Foroozan, Fig. 1, The system 10 performs both radar signal processing and vision processing. The processing is performed by a combination of hardware, software, algorithms, and/or circuitry (see Foroozan, Paragraph [0035]).), the sensor data being representative of the person (Foroozan, Paragraph [0033], The radar source is coupled to a point cloud. As seen in Fig. 2A, the radar generates a plurality of dots representative of reflected signals that are processed in order to determine moving objects, i.e. humans (see Foroozan, Paragraphs [0038-0039]).), the sensor data comprising at least one of the following:
a plurality of consecutive sets of centroid data representative of the person and a plurality of consecutive sets of point cloud data representative of the person (Foroozan, Paragraphs [0040-0043], The system 10 receives a plurality of point clouds, i.e. consecutive sets of point cloud data, and utilizes a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to calculate a centroid of each [point cloud] cluster, i.e. consecutive sets of centroid data. The point cloud data potentially represents different body parts of a person. Fig. 7 shows a DBSCAN example implementation 70 that calculates the centroid of each cluster and estimates the boundaries of the target (see Foroozan, Paragraph [0059]).); and
executing by the processing unit of the computing device a neural network inference engine, the neural network inference engine implementing the neural network using the predictive model for inferring one or more output based on inputs, the one or more output providing an indication of whether an event related to the person has occurred or not, the inputs comprising at least some of the sensor data (Foroozan, Figs. 8-11, Paragraphs [0064-0077], The Convolutional Neural Network (CNN) is functionally equivalent to a neural network inference engine. The CNN receives the data from both radar and cameras, i.e. the inputs, processes the clustered data, and outputs connected layers and class scores, e.g. Fig. 11 indicates a fall with a 99% score, wherein the fall represents an event related to the person.).
Foroozan does not explicitly teach:
The predictive model comprising weights of the neural network.
However, it would have been obvious to one of ordinary skill in the art, at the time of filing, for the plurality of inputs, e.g. sensor data, clusters, and centroids, to have a weight, e.g. equal weight, in order to yield fully connected layers and class scores (see Foroozan, Figs. 8-11, Paragraphs [0064-0077]). Such a modification would not change the principal operation of the system, as a whole, and would yield predictable results.
Claim 13, Foroozan further teaches:
The method of claim 12, wherein the inputs comprise the plurality of consecutive sets of centroid data representative of the person, each set of centroid data comprising at least one of the following: at least one coordinate of the centroid, at least one velocity component of the centroid, and at least one acceleration component of the centroid (Foroozan, Paragraph [0036], The detected element represents the centroid based on filtering a cluster of point cloud data (see Foroozan, Paragraphs [0040-0043]), wherein the 3D location and velocity of the detected element can be determined. It would have been obvious to one of ordinary skill in the art, at the time of filing, for the system to be capable of determining an acceleration component of the detected element. For example, the system can assume a constant velocity for an element, i.e. an acceleration component of 0 (see Foroozan, Paragraph [0046]).).
Claim 14, Foroozan further teaches:
The method of claim 12, wherein the inputs comprise the plurality of consecutive sets of point cloud data representative of the person, each set of point cloud data comprising for each point of the point cloud at least one of the following: at least one coordinate of the point, a velocity of the point, and a signal to noise ratio (SNR) of the point (Foroozan, Paragraph [0036], The detected element represents the centroid based on filtering a cluster of point cloud data (see Foroozan, Paragraphs [0040-0043]), wherein the 3D location and velocity of the detected element can be determined. The system can reduce the effect of noise (see Foroozan, Paragraphs [0038-0039]), thus it would have been obvious to one of ordinary skill in the art, at the time of filing, for the system to utilize a signal to noise ration of a set of point cloud data clusters for filtering out potential noise, e.g. noise caused by reflections of moving targets.).
Claim 15, Foroozan further teaches:
The method of claim 12, wherein the inputs further comprise at least one of the following: contextual information related to the person, contextual information related to an environment where the person is located, timing information and static coordinate data related to the environment where the person is located (Foroozan, Paragraph [0036], Location of the detected element is equivalent to contextual information related to the person, contextual information related to an environment, and static coordinate data. The point cloud data represents real-time information, i.e. timing information.).
Claim 16, Foroozan further teaches:
The method of claim 12, wherein the one or more output providing an indication of whether an event related to the person has occurred or not comprises at least one of the following: a Boolean and a probability, the one or more output optionally further comprising an indication of severity of the event (Foroozan, Fig. 11, Paragraph [0077], The connected layers are accompanies by class scores, which may be presented as a percentage, i.e. a probability. Additionally, Applicant’s specification defines in Paragraph [0061] that the one or more outputs may be Boolean or a probability, but not necessarily both, therefore only one is required. As seen in Fig. 11, one of ordinary skill in the art would recognize that a fall determination could be categorized as a “severe” event, whereas sitting or walking could be categorized as a “non-severe” event.).
Claim 17, Foroozan further teaches:
The method of claim 16, wherein the one or more output further comprises an indication of severity of the event (Foroozan, Fig. 11, Paragraph [0077], The connected layers and class scores may indicate that the person has experienced a fall, i.e. a “severe” event.).
Claim 18, Foroozan further teaches:
The method of claim 12, wherein the person is located in a room at least partially in a field of view of the radar sensor (Foroozan, Paragraph [0039], The human body and static objects are in the field of view of the radar.), and the event is a fall of the person (Foroozan, Fig. 11, Paragraph [0077]).
Claim 19, Foroozan further teaches:
The method of claim 12, wherein the one or more output is indicative of the event related to the person having occurred, and the method further comprises at least one of following: sending an alert message indicative of the event related to the person having occurred to a remote computing device and triggering a display of a visual indicator representative of the detection that the event related to the person has occurred (Foroozan, Paragraph [0092], In response to a detected fall, for example, the result could be sent over a network to a caregiver, a monitoring company, an emergency service, or a doctor. IT would have been obvious to one of ordinary skill in the art, at the time of filing, for the result to be presented to the receiver via a display, e.g. display device 1806 (see Foroozan, Paragraph [0100]). Such a modification would ensure that the receiver, i.e. a caregiver, a monitoring company, an emergency service, or a doctor, is able to interpret the results and act accordingly.).
Claim 20, Foroozan further teaches:
The method of claim 19, wherein the method further comprises sending the alert message indicative of the event related to the person having occurred to the remote computing device, the alert message comprising at least one of the following: a location where the event related to the person has occurred, the plurality of consecutive sets of centroid data representative of the person and the plurality of consecutive sets of point cloud data representative of the person (Foroozan, Fig. 12, Paragraph [0078], As per the example of Fig. 12, additional optional cloud services include remote access to the system for the doctor/nurse/relatives. It would have been obvious to one of ordinary skill in the art, at the time of filing, for the remote access to the system to include at least the location of the identified patient/event (see Foroozan, Paragraph [0036]). It is additionally noted that Paragraph [0089] of the Applicant’s specification defines the alert message “may” further comprise monitoring data, “such as” the limitations of claim 11, including the plurality of consecutive sets of centroid data representative of the person and/or the plurality of consecutive sets of point clou data representative of the person. Therefore, the limitations of claim 11 are interpreted as only requiring one limitation and/or a combination thereof.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAMES J YANG whose telephone number is (571)270-5170. The examiner can normally be reached 9:30am-6:00p M-F.
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, BRIAN ZIMMERMAN can be reached at (571) 272-3059. 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.
/JAMES J YANG/Primary Examiner, Art Unit 2686
Prosecution Insights