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 .
Status of the Application
Claims 1-14 have been examined in this application. This communication is the first action on the merits.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 06/20/2025 is being considered by the examiner. The submission is in compliance with the provisions of 37 CFR 1.97.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
In determining whether a claim falls within an excluded category, the Examiner is guided by the Court’s two-part framework, described in Mayo and Alice. Id. at 217-18 (citing Mayo Collaborative Servs. v. Prometheus Labs., Inc., 566 U.S. 66, 75-77 (2012)); Bilski v. Kappos, 561 U.S. 593, 611 (2010); 2019 Revised Patent Subject Matter Eligibility Guidance, 84 Fed. Reg. 50 (Jan. 7, 2019); the October 2019 Update of the 2019 Revised Guidance (Oct. 17, 2019); 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence (July 17, 2024), and the USPTO’s Paten Subject Matter Eligibility Memorandums of August 4, 2025 and December 5, 2025.
Step 1
Claims are eligible for patent protection under § 101 if they are in one of the four statutory categories and not directed to a judicial exception to patentability (i.e., laws of nature, natural phenomena, and abstract ideas). Alice Corp. v. CLS Bank Int'l, 573 U. S. ____ (2014).
The broadest reasonable interpretation of claim 1 encompasses a computer system (e.g., hardware such as a processor and memory) that implements the recited functions. If assuming that the system comprises a device or set of devices, then the system is directed to a machine, which is a statutory category of invention.
Claim 13 is directed to a statutory category, because a series of recited steps satisfies the requirements of a process (a series of acts). Step 1: Yes).
Next, the claims are analyzed to determine whether it is directed to a judicial exception.
Step 2A – Prong 1
Claim 13 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more of using a lightweight transformer model for human activity recognition. The claim recites:
13. A method using a lightweight transformer model for human activity recognition in a portable device, the method comprising:
performing a data processing process to process mmWave data and convert the mmWave data into an input form for a model;
adding location information to input data and normalizing a distribution of the input data;
splitting an input sequence into groups and independently calculating attention for each group;
converting the input data through a feed-forward network (FFN) and enhancing learning expressiveness of the model;
randomly deactivating some neurons to prevent overfitting, maintaining learning information between blocks, and mitigating a gradient vanishing problem; and
normalizing output values of each layer and generating a final feature vector to classify an output class (human activity type) through a fully connected layer.
Dependent claim 14 also recites:
wherein the calculating of the attention comprises: delivering data to next step with a sequence and location information of the data included;
splitting the input data into several groups and independently calculating attention for each group;
calculating query, key, and value vectors for each group;
calculating an attention score through a query and a key and applying a sparse mask to calculate relationships between necessary data; and
merging attention calculation results for each group to generate a final output.
The claims essentially recite processing sensor data; adding positional information; calculating attention; generating feature vectors; and classifying activity types. The recited limitations, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind and/or mathematical concepts, such as vector calculations, attention score calculations, query/key/value computations, normalization, feature extraction, which may be practically performed in the human mind using observation, evaluation, judgment, and opinion (MPEP 2106.04(a)(2), subsection III), but for the recitation of generic computer components. (Note: Examiner’s language (e.g. “processing sensor data”; “adding positional information”; etc.) is an abbreviated reference to the detailed claims steps and is not an oversimplification of the claim language; the Examiner employing such shortcuts (that refer to more specific steps) when attempting to explain the rejection). That is, other than reciting “by a processor,” nothing in the claims element precludes the step from practically being performed in the mind, and/or performed as organized human activity. The claims essentially can be characterized as mathematical processing of sensor data to classify human activity. Thus, aside from the general technological environment (addressed below), it covers purely mental concepts and/or mathematical concepts, and the mere nominal recitation of a generic network appliance (e.g. an interface for inputting or outputting data, or generic network-based storage devices and displays) does not take the claims limitation out of the mental processes and/or mathematical concepts.
Specifically, the utilizing statistical tools to process data and to output the estimated values - said functions could be performed by a human using mental steps or basic critical thinking, which are types of activities that have been found by the courts to represent abstract ideas (e.g., mental comparison regarding a sample or test subject to a control or target data in Ambry, Myriad CAFC, or the diagnosing an abnormal condition by performing clinical tests and thinking about the results in In re Grams, 888 F.2d 835 (Fed. Cir. 1989) (Grams)). In Grams, the recited functions require obtaining data or patient information (from sensors), and analyze that data to ascertain the existence and identity of an abnormality or estimated responses, and possible causes thereof. While said functions are performed by a computer, they are in essence a mathematical algorithm, in that they represent "[a] procedure for solving a given type of mathematical problem." Gottschalk v. Benson, 409 U.S. 63, 65, 93 S.Ct. 253, 254, 34 L.Ed.2d 273 (1972). Moreover, the Federal Circuit has held, “without additional limitations, a process that employs mathematical algorithms to manipulate existing information to generate additional information is not patent eligible.” Digitech Image Techs., LLC v. Elecs. for Imaging, Inc., 758 F.3d 1344, 1351 (Fed. Cir. 2014). Here, the claimed subject matter is directed to the abstract idea of manipulating existing information (e.g., “sensor data”) to generate additional information (e.g., “output values”). See id. Further, “analyzing information by steps people go through in their minds, or by mathematical algorithms, without more, [are] essentially mental processes within the abstract-idea category.” Elec. Power, 830 F.3d at 1354; see also Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1146 (Fed. Cir. 2016). “[T]he fact that the required calculations could be performed more efficiently via a computer does not materially alter the patent eligibility of the claimed subject matter.” Bancorp Servs., L.L.C. v. Sun Life Assurance Co. of Can. (U.S.), 687 F.3d 1266, 1278 (Fed. Cir. 2012).
And the use of artificial intelligence and/or machine learning techniques (AI/ML), said recitation does not make the claims patent eligible, because said tools are utilized merely for data gathering and comparing, and are not utilized in express manipulation and control of functional aspects and/or hardware components/equipment of real-world processes and systems using output of AI models (e.g., manufacturing processes and equipment, medical treatments, communications processes and systems, logistics systems and hardware, interactive smart phone apps, etc.).
As per receiving, storing and outputting data limitations, it has been held that “As many cases make clear, even if a process of collecting and analyzing information is ‘limited to particular content’ or a particular ‘source,’ that limitation does not make the collection and analysis other than abstract.” SAP Am., Inc. v. InvestPic, LLC, 898 F.3d 1161, 1168 (Fed. Cir. 2018) (citation omitted); see also In re Jobin, 811 F. App’x 633, 637 (Fed. Cir. 2020) (claims to collecting, organizing, grouping, and storing data using techniques such as conducting a survey or crowdsourcing recited a method of organizing human activity, which is a hallmark of abstract ideas).
All these cases describe the significant aspects of the claimed invention, albeit at another level of abstraction. See Apple, Inc. v. Ameranth, Inc., 842 F.3d 1229, 1240-41 (Fed. Cir. 2016) ("An abstract idea can generally be described at different levels of abstraction. As the Board has done, the claimed abstract idea could be described as generating menus on a computer, or generating a second menu from a first menu and sending the second menu to another location. It could be described in other ways, including, as indicated in the specification, taking orders from restaurant customers on a computer.").
Therefore, if a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” and/or “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claims recite an abstract idea. (Step 2A – Prong 1: Yes).
Step 2A – Prong 2
In Prong Two, the Examiner determines whether claims 13 and 14, as a whole, recites additional elements that integrate the judicial exception into a practical application of the exception, i.e., whether the additional elements apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that the claims are no more than a drafting effort designed to monopolize the judicial exception. See Guidance, 84 Fed. Reg. at 54-55. If the additional elements do not integrate the judicial exception into a practical application, then the claim is directed to the judicial exception. See id., 84 Fed. Reg. at 54. “An additional element [that] reflects an improvement in the functioning of a computer, or an improvement to other technology or technical field” is indicative of integrating a judicial exception into a practical application. See Guidance, 84 Fed. Reg. at 55.
The Examiner determined that this judicial exception is not integrated into a practical application, because there are no meaningful limitations that transform the exception into a patent eligible application. In particular, the claims recite additional elements – using a processor to perform the recited steps. However, the processor in each step is recited (or implied) at a high level of generality, i.e., as a generic processor performing a generic computer functions of processing data, including receiving, storing, comparing, and outputting data. This generic processor limitation is no more than mere instructions to apply the exception using a generic computer component. See MPEP 2106.05(f). The processor that performs the recited steps merely automates these steps which can be done mentally or manually. Thus, while the additional elements have and execute instructions to perform the abstract idea itself, this also does not serve to integrate the abstract idea into a practical application as it merely amounts to instructions to "apply it." The claims only manipulate abstract data elements into another form, and does not set forth improvements to another technological field or the functioning of the computer itself and, instead, uses computer elements as tools in a conventional way to improve the functioning of the abstract idea identified above. The required steps essentially represents an application of known mathematical techniques, such as normalization, feed-forward networks, dropout, attention scores, query/key/value vectors, to classify information.
And looking at the recited limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually; there is no indication that the combination of elements improves the functioning of a computer or improves any other technology, - their collective functions merely provide conventional computer implementation. None of the additional elements "offers a meaningful limitation beyond generally linking 'the use of the [method] to a particular technological environment,' that is, implementation via computers." Alice Corp., slip op. at 16 (citing Bilski v. Kappos, 561 U.S. 610, 611 (U.S. 2010)).
For instance, the claimed method does not quantify computational improvements, there is no specific hardware architecture required, no new transformer mechanism is recited, and the model merely produces a classification result.
Regarding the use of AI/ML techniques, said steps are nothing more than an attempt to recycle preexisting AI/ML technologies to apply for a particular computing application. There are no improvements in said AI/ML techniques, such as advances in the field of computer science itself, or designing a new neural network, and there is no controlling of a technological process using the outcome of said AI/ML operations.
As per receiving, storing and/or outputting data limitations, these recitations amount to mere data gathering and/or outputting, is insignificant post-solution or extra-solution component and represents nominal recitation of technology. Insignificant "post-solution” or “extra-solution" activity means activity that is not central to the purpose of the method invented by the applicant. However, “(c) Whether its involvement is extra-solution activity or a field-of-use, i.e., the extent to which (or how) the machine or apparatus imposes meaningful limits on the execution of the claimed method steps. Use of a machine or apparatus that contributes only nominally or insignificantly to the execution of the claimed method (e.g., in a data gathering step or in a field-of-use limitation) would weigh against eligibility”. See Bilski, 138 S. Ct. at 3230 (citing Parker v. Flook, 437 U.S. 584, 590, 198 USPQ 193, ___ (1978)). Thus, claim drafting strategies that attempt to circumvent the basic exceptions to § 101 using, for example, highly stylized language, hollow field-of-use limitations, or the recitation of token post-solution activity should not be credited. See Bilski, 130 S. Ct. at 3230.
Thus, the recited steps do not control or improve operation of a machine (MPEP 2106.05(a)), do not effect a transformation or reduction of a particular article to a different state or thing (MPEP 2106.05(c)), and do not apply the judicial exception with, or by use a particular machine (MPEP 2106.05(b)), but, instead, require receiving, storing, comparing and outputting data.
Therefore, claims 13-14 as a whole, outputs only data structure, - everything remains in the form of a code stored in the computer memory. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, the claims are directed to an abstract idea. (Step 2A – Prong 2: No).
Step 2B
If a claim has been determined to be directed to a judicial exception under revised Step 2A, examiners should then evaluate the additional elements individually and in combination under Step 2B to determine whether the provide an inventive concept (i.e., whether the additional elements amount to significantly more than the exception itself).
The Examiner determined that the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor to perform the recited steps amount to no more than mere instructions to apply the exception using a generic computer component. The claims are now re-evaluated in Step 2B to determine if it is more than what is well-understood, routine, conventional activity in the field.
The method would require a processor and memory in order to perform basic computer functions of receiving information, storing the information in a database, retrieving information from the database, comparing data, and outputting said information. These components are not explicitly recited and therefore must be construed at the highest level of generality. Based on the Specification, the invention utilizes conventional sensors, communication networks and generic processors, which can be found in mobile devices or desktop computers, conventional memory and display devices, and the functions performed by said generic computer elements are basic functions of a computer - performing a mathematical operation, receiving, storing, comparing and outputting data - have recognized by the courts as routine and conventional activity. Specifically, regarding the recited functions, MPEP 2106.05(d)(II) defines said functions as routine and conventional, or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) (“Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink.” (emphasis added));
ii. Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012) (“The computer required by some of Bancorp’s claims is employed only for its most basic function, the performance of repetitive calculations, and as such does not impose meaningful limits on the scope of those claims.”); collecting and comparing known information in Classen 659 F.3d 1057, 100 U.S.P.Q.2d 1492 (Fed. Cir. 2011)
iii. Electronic recordkeeping, Alice Corp., 134 S. Ct. at 2359, 110 USPQ2d at 1984 (creating and maintaining “shadow accounts”); Ultramercial, 772 F.3d at 716, 112 USPQ2d at 1755 (updating an activity log);
iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93;
v. Electronically scanning or extracting data from a physical document, Content Extraction and Transmission, LLC v. Wells Fargo Bank, 776 F.3d 1343, 1348, 113 USPQ2d 1354, 1358 (Fed. Cir. 2014) (optical character recognition); and
vi. A web browser’s back and forward button functionality, Internet Patent Corp. v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1418 (Fed. Cir. 2015).
Regarding the use of a neural model, and obtaining data via repetitive operation of said neural model, said steps are nothing more than an attempt to recycle preexisting AI/ML technologies to apply for a particular application. There are no improvements in said AI/ML techniques, such as advances in the field of computer science itself, or designing a new neural network, and there is no controlling of a technological process using the outcome of said AI/ML operations. The claims neither specify a specific
technical purpose for which the method is used, nor the claims define a specific technical implementation of the method, nor the claimed method is particularly adapted for that implementation in that its design is motivated by technical considerations of the internal functioning of the computer. Said AI/ML algorithms and computations are done inside of a computer, and do not have a real-world impact and are not tied to the functionality of the computer. Further, there is no evidence that the invention lies in the training phase or execution phase or both; said AI/ML recitation represents merely conventionally applying an existing model to an existing data.
Thus, the background of the current application does not provide any indication that the processor is anything other than a generic, off-the-shelf computer component, and the Symantec, TLI, and OIP Techs. court decisions cited in MPEP 2106.05(d)(II) indicate that mere collection or receipt of data over a network is a well‐understood, routine, and conventional function when it is claimed in a merely generic manner (as it is here).
Also, the claims do not involve a non-conventional and non-generic arrangement of known, conventional pieces, as asserted, by receiving information from an external source of data. The receiving of data from an external source over a network, such as via the Internet, can fairly be characterized as insignificant extra-solution activity that does not receive patentable weight. See Bilski, 545 F.3d 943, 963 (Fed. Cir. 2008) (en banc), aff’d sub nom Bilski v. Kappos, 561 U.S. 593 (2010) (characterizing data gathering steps as insignificant extra-solution activity). Similar to Content Extraction, 776 F.3d at 1347; Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 715 (Fed. Cir. 2014): “And we have recognized that merely presenting the results of abstract processes of collecting and analyzing information, without more (such as identifying a particular tool for presentation), is abstract as an ancillary part of such collection and analysis.” Here, the claims are clearly focused on the combination of those abstract-idea processes. The advance they purport to make is a process of gathering and analyzing information of a specified content, then outputting the results, and not any particular asserted inventive technology for performing those functions. They are therefore directed to an abstract idea. As such, the additional elements, considered individually and in combination with the other claims elements, do not make the claims as a whole significantly more than the abstract idea itself.
Accordingly, a conclusion that the recited steps are well-understood, routine, conventional activity is supported under Berkheimer Option 2. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept.
Further, similar to Electric Power Group v Alstom S.A. (Fed Cir, 2015-1778, 8/1/2016) (Power Group), claims’ invocation of computers, networks, and displays does not transform the claimed subject matter into patent-eligible applications. Claims 13 and 14 do not require any nonconventional computer, network, or display components, or even a “non-conventional and non-generic arrangement of known, conventional pieces,” but merely call for performance of the claimed information collection, analysis, and display functions on a set of generic computer components and display devices. Nothing in the claims, understood in light of the specification, requires anything other than off-the-shelf, conventional computer, network, and display technology for gathering, sending, and presenting the desired information. Analogous to Power Group, the claims do not even require a new source or type of information, or new techniques for analyzing it. As a result, the claims do not require an arguably inventive set of components or methods, such as measurement devices or techniques that would generate new data. The claims do not invoke any assertedly inventive programming. Merely requiring the selection and manipulation of information - to provide a “humanly comprehensible” amount of information useful for users - by itself does not transform the otherwise-abstract processes of information collection and analysis into patent eligible subject matter. Merely obtaining and selecting information, by content or source, for collection, analysis, and display does nothing significant to differentiate a process from ordinary mental processes, whose implicit exclusion from § 101 undergirds the information-based category of abstract ideas. Therefore, the recited steps represent implementing the abstract idea on a generic computer, or “reciting a commonplace business method aimed at processing business information despite being applied on a general purpose computer” Versata, p. 53; Ultramerical, pp. 11-12.
Furthermore, the recited functions do not improve the functioning of computers itself, including of the processor(s) or the network elements. There are no physical improvements in the claims, like a faster processor or more efficient memory, and there is no operational improvement, like mathematical computation that improve the functioning of the computer. The claims do not recite unconventional data structures, improved signal processing, machine-learning innovations, reduced processor usage, improved sensor operations, or any technical solution to a technical problem. Even when considering the ordered combination as a whole, the recited elements are routine: vector generation, attention score calculations, normalization, sparse masking, and classification. These are standard, mathematical concepts in signal processing platforms. The additional elements merely implement those calculations on generic computers. “However, it is not apparent how appellant’s programmed digital computer can produce any synergistic result. Instead, the computer will simply do the job it is instructed to do. Where is there any surprising or unexpected result? The unlikelihood of any such result is merely one more reason why patents should not be granted in situations where the only novelty is in the programming of general purpose digital computers”. See Sakraida v. Ag. Pro, Inc., 425 U.S. 273 [ 96 S.Ct. 1532, 47 L.Ed.2d 784], 189 USPQ 449 (1976) and A P Tea Co. V. Supermarket Corp., 340 U.S. 147 [ 71 S.Ct. 127, 95 L.Ed. 162], 87 USPQ 303 (1950).
Furthermore, there is no transformation recited in the claims as understood in view of 35 USC 101. The recited steps merely represent abstract ideas which cannot meet the transformation test because they are not physical objects or substances. Bilski, 545 F.3d at 963. Said steps are nothing more than mere manipulation or reorganization of data, which does not satisfy the transformation prong. It is further noted that the underlying idea of the recited steps could be performed via pen and paper or in a person's mind. Moreover, “We agree with the district court that the claimed process manipulates data to organize it in a logical way such that additional fraud tests may be performed. The mere manipulation or reorganization of data, however, does not satisfy the transformation prong.” and “Abele made clear that the basic character of a process claim drawn to an abstract idea is not changed by claiming only its performance by computers, or by claiming the process embodied in program instructions on a computer readable medium. Thus, merely claiming a software implementation of a purely mental process that could otherwise be performed without the use of a computer does not satisfy the machine prong of the machine-or-transformation test”. CyberSource, 659 F.3d 1057, 100 U.S.P.Q.2d 1492 (Fed. Cir. 2011)
Therefore, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, because, when considered separately and in combination, the claims elements do not add significantly more to the exception. Considered separately and as an ordered combination, the claims elements do not provide an improvement to another technology or technical field; do not provide an improvement to the functioning of the computer itself; do not apply the judicial exception by use of a particular machine; do not effect a transformation or reduce a particular article to a different state or thing; and do not add a specific limitation other than what is well-understood, routine and conventional in the operation of a generic computer. None of the hardware recited "offers a meaningful limitation beyond generally linking 'the use of the [method] to a particular technological environment,' that is, implementation via computers." Id., slip op. at 16 (citing Bilski v. Kappos, 561 U.S. 610, 611 (U.S. 2010)). As per “A method using a lightweight transformer model for human activity recognition in a portable device” recitations, these limitations do not add significantly more because they are simply an attempt to limit the abstract idea to a particular technological environment, that is, implementation via computers." Id., slip op. at 16 (citing Bilski v. Kappos, 561 U.S. 610, 611 (U.S. 2010)). Limiting the claims to the particular technological environment is, without more, insufficient to transform the claim into patent-eligible applications of the abstract idea at their core.
Accordingly, claims 13 and 14 is not directed to significantly more than the exception itself, and is not eligible subject matter under § 101. (Step 2B: No).
Because Applicant’s apparatus claims 1-12 add nothing of substance to the underlying abstract idea, they too are patent ineligi-ble under §101.
Citations of pertinent art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Keyan Cao et al. “Human behavior recognition based on sparse transformer with channel attention mechanism”, ORIGINAL RESEARCH article Front. Physiol., 01 November 2023 Sec. Computational Physiology and Medicine Volume 14 - 2023 pp. 1-10, – discloses human activity recognition aspect, sparse transformer, sparse attention matrix, reduced computational burden, lightweight transformer, attention calculated only among selected data, mobile and wearable deployment, channel-attention mechanisms, transformer encoder architecture. Keyan Cao et al. further discloses replacing traditional self-attention with a sparse attention mechanism comprised of local and random attention patterns to reduce FLOPs while maintaining global feature extraction.
Sannara EK et al. “Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition”, Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG F-38000, Grenoble, France, 2022, pp. 1-20, discloses lightweight transformer for HAR, mobile/portable device deployment, positional information, transformer encoder blocks, query-key-value attention, layer normalization, classification head, reduced FLOPs and parameter count. However, Sannara EK et al. (Sannara) fails to disclose mmWave radar input.
Sha Huan et al. “A lightweight hybrid vision transformer network for radar-based human activity recognition” Scientific Reports | (2023) pp. 1-12, discloses radar-based HAR, lightweight transformer, activity classification, transformer feature extraction, resource-efficient architecture, radar micro-Doppler processing.
Anthapur et al. - US 2025/0336543 A1 – discloses generating patient care instructions based on real-time sensor processing, comprising generating, in real time, activity pattern data by processing the enriched sensor data of the patient by using a pattern recognition model. In use, the pattern recognition comprising segmenting the sensor data into time-windowed data blocks, computing, for each block a feature
vector that includes statistical measures of the sensor data and correlation measures between the sensor data and the medical data, classifying each feature vector by applying a neural network classifier to produce classification data, wherein the classification data comprises a class label or probability scores corresponding to predefined categories related to the patient's health, and generating activity pattern data that maps the classification data to the corresponding time-windowed data blocks, wherein the activity pattern data represents behaviors of the patient, including mobility, sleep patterns, and medication adherence, and serves as a baseline for detecting anomalies and predicting potential health risks.
Distinguishable Subject Matter
The present claims remain distinguishable from the prior art of record. While the prior art of record discloses human activity recognition aspect, sparse transformer, sparse attention matrix, reduced computational burden, lightweight transformer, attention calculated only among selected data, mobile and wearable deployment, channel-attention mechanisms, transformer encoder architecture, and radar-based HAR, the prior art alone or combine fails to disclose a particular combination of the inventive features as specifically recited in the claims. Thus, the Examiner has not made a prior art rejection under 35 USC §102 or §103.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Igor Borissov whose telephone number is 571-272-6801. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor Kambiz Abdi can be reached on 571-272-6702. 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 Center system.
For more information about the Patent Center, https://patentcenter.uspto.gov. Should you have questions on access to the Patent Center system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/IGOR N BORISSOV/Primary Examiner, Art Unit 3685 06/05/2025
Prosecution Insights