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 Objections
Claims 7 and 13 are objected to because of the following informalities:
“interburs” should read as “interburst”
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 10, and 19 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Re. Claims 1, 10, and 19: Each independent claim recites controlling a device or a software application running on the device. The term “device” is interpreted to be a genus. Applicant’s Specification recites only examples where the device controlled “can be at least one of a personal computing device, an internet-of-things (IoT) device, and a mobility vehicle” (Paragraph 0029). Three disparate examples do not provide a sufficient number of representative species for a genus as broad as the claimed “device or a software application running on the device.”
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. Each claim has been analyzed to determine whether it is directed to any judicial exceptions.
Step 2A, Prong 1
Each of the claims recite steps or instructions for using features from one or more transient oscillatory or pseudo-oscillatory bursts from a subject to predict a change in mental state of the subject to transmit an input command, which is grouped as a mental process. Accordingly, each of the claims recites an abstract idea.
Independent claim 1 recites:
detecting one or more transient oscillatory or pseudo-oscillatory bursts from an ongoing neural signal recording of a subject captured by a recording device, wherein the one or more transient oscillatory or pseudo-oscillatory bursts are generated in response to a thought generated by the subject or a change in mental state evoked by the subject (data gathering/processing, additional element);
extracting, using one or more processors of a computing device communicatively coupled to the recording device, one or more burst features from the one or more transient oscillatory or pseudo-oscillatory bursts detected within a detection period of less than 100 ms (evaluation; additional element);
inputting the one or more burst features extracted within the detection period to a machine learning algorithm to obtain as an output from the machine learning algorithm a prediction (additional element; mental process); and
controlling the device or the software application running on the device with an input command based on the prediction (generic computer function).
Independent claims 10 and 19 differ by reciting the step of applying a threshold to form a prediction as opposed to the machine learning algorithm of claim 1.
As indicated above, the independent claims recites at least one step or instruction grouped as a mental process. Therefore, each independent claim recites an abstract idea. Each limitation, aside from language reciting a generic computer components, can be grouped as a mental process (see italicized portions above), and is addressed as follows:
The process of extracting one or more burst features is interpretable as identifying features from a gathered set of data using observation, judgement, or evaluation.
The use of a machine learning algorithm is recited generically enough that it encompasses a human being capable of performing hand-written evaluations necessary for, e.g., a perceptron (the simplest possible computational neural network consisting of a single neuron taking inputs and providing one output). For example, however crude or inaccurate the following example may be, an extracted burst feature may involve a maximum amplitude of a beta frequency burst, either gathered as data or observed by an individual. The individual may note that such amplitude is high enough that it may be predictive of movement intention, and thus such a signal may be weighted positively; negative weights can be applied to lesser amplitudes. Such weighted values can be summed to provide a singular output of the perceptron, and such output can be arbitrarily thresholded or binarized to identify a rudimentary degree of movement intention.
Regarding feature thresholding steps of claims 10 and 19, the process described above is analogous, and is thus also demonstrated as performable in the mind.
Thus, the each prediction step recited in each independent claim is a process that, under its broadest reasonable interpretation, covers concepts which can be performed mentally and/or by hand but for the recitation of generic computer components.
The final step of each independent claim of controlling the device or the software application running on the device with an input command based on the prediction is claimed broadly enough such that it encompasses control of a device to perform post-solution activity (e.g., displaying a result of analysis on a screen of a generic computing device), which is an insignificant application of the judicial exception.
If a claim limitation, under its broadest reasonable interpretation, covers a mental process but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas.
These limitations are similar to those found in In re Grams (888 F.2d 835, 12 USPQ2d 1824 (Fed. Cir. 1989)) and collecting information, analyzing it, and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)). Therefore, the independent claims (and claims dependent therefrom) recite the judicial exception of an abstract idea of a mental process. Thus, the claims are directed to at least one judicial exception.
The dependent claims merely include limitations that either further define the abstract idea or extra-solution components and amount to no more than generally linking the use of the abstract idea to a particular technological environment or field of use because they are merely incidental or token additions to the claims that do not alter or affect how the process steps are performed.
Step 2A, Prong 2
The above-identified abstract idea is not integrated into a practical application because the additional elements, either alone or in combination, generally link the use of the above-identified abstract idea to a particular technological environment or field of use. More specifically, the additional elements of a recording device, machine learning algorithm, and processor are generically recited computer elements or sensors which do not improve the functioning of a computer, or any other technology or technical field.
Acquiring data from a generically-recited recording device amounts to insignificant, extra-solution activity in the form of mere data gathering, which does not constitute an integration into a practical application.
The machine learning algorithm is recited broadly such that the claims merely implement such a concept as a tool to perform mental process steps, and merely links the abstract idea to a technological field.
The processor is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of performing calculations on data received from extra-solution data-gathering components) such that it amounts no more than mere instructions to apply the exception using a generic computer component.
Such additional elements do not serve to apply the above-identified abstract idea with, or by use of, a particular machine, effect a transformation or apply or use the above-identified abstract idea in some other meaningful way beyond generally linking the use thereof to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. Examiner notes that the current claim scope for claims 1, 31, and 61 encompass control of any device utilizing, broadly, a prediction generated from thresholding burst features of a neural signal and/or a generally recited machine learning algorithm having no connection to the aforementioned burst features.
Moreover, the above-identified abstract idea is not integrated into a practical application because the claimed invention merely implements the above-identified abstract idea (e.g., mental process or mathematical concept) using rules (e.g., computer instructions) executed by a computer (e.g., processing circuitry or implicit algorithms of an artificial neural network). In other words, these claims are merely directed to an abstract idea with additional generic computer elements which do not add a meaningful limitation to the abstract idea because they amount to simply implementing the abstract idea on a computer. Thus, for these reasons, the abstract idea identified is not integrated into a practical application.
Accordingly, the claims are each directed to an abstract idea.
Step 2B
None of the claims include additional elements that, when viewed as a whole, are sufficient to amount to significantly more than the abstract idea.
Regarding independent claims 1, 31, and 61:
The identified element of an machine learning algorithm is not explicitly described in Applicant’s specification other than general knowledge regarding input of data and training (e.g., Paragraphs 0162-0164). Thus, it is understood that the disclosure’s lack of disclosure regarding the specifics of implementation of a particular neural network implies that the models and implementation thereof on particular data recited in Applicant’s specification would be well-apprised to one of ordinary skill in the art. Thus, in light of Applicant’s specification, the claimed term machine learning algorithm (and related terms in the specification such as neural network and variations thereof) may be reasonably construed as a well-understood, routine, and conventional algorithmic concept used to classify data.
The identified element of a processor and related term “computing device” as utilized in Applicant’s specification are described solely by function and is reasonably construed as a generic computing device.
The dependent claims merely recite additional limitations pertaining to the data gathered, additional extra-solution components, or generic computer activity (i.e., display of information) in performing the mental process.
Each dependent claim merely recites additional limitations pertaining to the data gathered, additional extra-solution components, or generic computer activity (i.e., further processing of data) in performing the mental process.
Dependent claim 6 recites the use of a particular machine learning algorithms, i.e., a long short-term memory (LSTM) network. An LSTM network and its use even in the narrower field of analyzing brain wave data is considered well-known, understood, routine, and conventional by at least:
Nam et al. (US 20230001585 A1) – Paragraph 0176: choice of a neural network being an LSTM network would be well-apprised to the skilled artisan;
Kang et al. (US 20210124419 A1) – Paragraph 0061: analysis of beta waves, among others; Paragraphs 0115-0120: model used in disclosure may be a number of types of neural networks, including LSTM networks;
Anisimov et al. (US 20200364539 A1) – Paragraph 0012: prior art example of use of a neural network; Paragraph 0200: beta frequency band analysis; Paragraph 0211: “For example, combinations of neural networks such as LSTMs or CNNs may also be used.”
Dependent claims 8, 14, and 20 recite the use of an implantable electrode array, which is considered well-understood, routine, and conventional by at least:
Williams et al. (US 20100130844 A1) – Paragraph 0003: “Various invasive microelectrode arrays such as Michigan probes [e.g., a thin film array] and the Utah electrode arrays have been developed within the last 20 years to achieve more localized neural signals;”
Frewin et al. (US 20140194719 A1) – Paragraph 0009: “Conventional implantable neural interface devices use four well-established architectures: 1) Macroelectrode wire implants; 2) Microelectrode wire arrays; 3) The Utah intracortical electrode array (UIEA); and 4) The Michigan planar microelectrode.”
Like SAP America vs Investpic, LLC (Federal Circuit 2018), it is clear, from the claims themselves and the specification, that these limitations require no improved computer resources, just already available computers and sensors, with their already available basic functions, to use as tools in executing the claimed process.
The recitation of the above-identified additional limitations in the claims amount to mere instructions to implement the abstract idea on a computer. Simply using a computer or other machinery (e.g., known sensors) in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); and TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Moreover, implementing an abstract idea on a generic computer, does not add significantly more, similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer.
For at least the above reasons, the claims are directed to applying an abstract idea on a general purpose computer without (i) improving the performance of the computer itself, or (ii) providing a technical solution to a problem in a technical field. In other words, none of the claims provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that these claims amount to significantly more than the abstract idea itself.
Taking the additional elements individually and in combination, the additional elements do not provide significantly more. Specifically, when viewed individually, the above-identified additional elements do not add significantly more because they are simply an attempt to limit the abstract idea to a particular technological environment. That is, neither the general computer elements nor any other additional element adds meaningful limitations to the abstract idea because these additional elements represent insignificant extra-solution activity. When viewed as a combination, these above-identified additional elements simply instruct the practitioner to implement the claimed functions with well-understood, routine and conventional activity specified at a high level of generality in a particular technological environment. As such, there is no inventive concept sufficient to transform the claimed subject matter into a patent-eligible application. As such, the above-identified additional elements, when viewed as whole, do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea itself. Thus, the claims merely apply an abstract idea to a computer and do not (i) improve the performance of the computer itself, or (ii) provide a technical solution to a problem in a technical field.
Therefore, none of the claims amounts to significantly more than the abstract idea itself.
Accordingly, the claims are not patent eligible and rejected under 35 U.S.C. 101 as being directed to abstract ideas implemented on a generic computer in view of the Supreme Court Decision in Alice Corporation Pty. Ltd. v. CLS Bank International, et al.
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.
Claims 1-5, 8, 10-12, 14, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over:
Merk T, Peterson V, Lipski WJ, Blankertz B, Turner RS, Li N, Horn A, Richardson RM, Neumann WJ. Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease. Elife. 2022 May 27;11:e75126. doi: 10.7554/eLife.75126. PMID: 35621994; PMCID: PMC9142148 (hereinafter – Merk).
Re. Claim 1: Merk teaches:
detecting one or more transient oscillatory or pseudo-oscillatory bursts from an ongoing neural signal recording of a subject captured by a recording device (Pages 4-7: see section titled “Grip-force decoding performance is correlated with PD motor impairment and subthalamic beta burst dynamics;” Examiner notes that beta bursts are a type of pseudo-oscillatory burst as defined in Applicant’s Specification at Paragraph 0130);
extracting, using one or more processors of a computing device communicatively coupled to the recording device, one or more burst features from the one or more transient oscillatory or pseudo-oscillatory bursts detected within a detection period of less than 100 ms (Page 2: “For the use in machine- learning models, band power feature time-series were extracted in a real- time BCI compatible implementation (Figure 1D) streamed in virtual packets of 100ms length at a sampling rate of 1000 Hz to mimic the online application. Variance as a measure of amplitude of rereferenced, band- pass filtered raw data segments was extracted at 10 Hz with an adaptive window length from 1000 to 100ms of past data for eight oscillatory features [θ (4–8 Hz), α (8–12 Hz), β (13–35 Hz), low β (13–20 Hz), high β (20–35 Hz), low γ (60–80 Hz), high- frequency activity (HFA) (90–200 Hz) and all γ (60–200 Hz)]. All features were normalized to the median of the past 10 s to compensate for potential signal changes over time. The target variable was continuously measured grip- force (z- scored for each recording session), which was cleaned from noise and baseline drift (Xie et al., 2018)”);
inputting the one or more burst features extracted within the detection period to a machine learning algorithm to obtain as an output from the machine learning algorithm a prediction (Page 3: see Figure 1, input into machine learning pipeline prediction of force gripping movement).
Merk does not explicitly use the prediction output from the machine learning model to control a device or software application running on a device with an input command based on the prediction.
However, the problem which Merk addresses is in the field of brain signal decoding in the context of brain computer interfaces (Abstract). Merk discusses preparation of data for “use in machine-learning models… in a real-time compatible BCI compatible implementation” (Page 2) and also states that the models described could be generalized to BCI (brain-computer interfaces) (Page 10). Brain computer interfaces entail a device and/or software thereof to be provided with a output resulting from analysis of brain signals in order to carry out some form of interaction or control. Thus, Merk makes obvious that a core application of the analysis disclosed is controlling a device or the software application running on the device using predictions of the analysis.
Re. Claim 2: Merk teaches the invention according to claim 1. Merk further teaches the invention wherein the one or more transient oscillatory or pseudo-oscillatory bursts are generated in response to a thought generated by the subject or a change in mental state evoked by the subject (Page 2: “We analyzed sensorimotor ECoG and subthalamic LFP data recorded intraoperatively from 11 PD patients undergoing DBS implantation during performance of a Go/No- Go based cued grip- force task (Figure 1A)”).
Re. Claim 3: Merk teaches the invention according to claim 2. Merk further teaches the invention wherein the thought of the subject is a thought generated by the subject to move one or more body parts of the subject (see citation of rejection of claim 2 – grip force cuing tasks entail movement of muscles responsible for applying grip force).
Re. Claim 4: Merk teaches the invention according to claim 1. Merk further teaches the invention wherein the ongoing neural signal recording of the subject is made by recording raw electrical signals from the brain of the subject using the recording device, and
wherein detecting the one or more transient oscillatory or pseudo-oscillatory bursts further comprises:
filtering the raw electrical signals in one or more desired frequency bands using one or more frequency decomposition methods (Fig. 1A: ECoG, STN data obtained and processed to extract various frequency bands, as described at Page 17);
converting voltage values of the filtered raw electrical signals into magnitude or power-related values for each of the desired frequency bands (Fig. 1A: band power extraction, amplitude estimation described at Page 17);
applying at least one of a power threshold to the magnitude or power-related values for each of the desired frequency bands and a duration threshold for each of the desired frequency bands (Page 6: “Beta bursts were defined as threshold crossings of the beta feature vector above the 75th percentile of the baseline period;” Page 20: “To investigate a potential relationship between grip- force decoding performance and beta burst activity, we have adopted a previously validated approach to movement related burst analyses (Torrecillos et al., 2018; Lofredi et al., 2019). Therefore, the beta feature time- series were used and a threshold constituting the 75th percentile of the rest periods were calculated. Next, threshold crossings of at least 100ms lengths in the motor preparation (−1–0 s with respect to movement) and movement execution (0–1 s with respect to movement execution) were marked as bursts”); and
identifying one of the transient oscillatory or pseudo-oscillatory bursts in response to at least one of the magnitude or power-related values exceeding the power threshold and the filtered raw electrical signals exceeding the duration threshold for each of the desired frequency bands (see previous citation).
Re. Claim 5: Merk teaches the invention according to claim 4. Merk further teaches the invention wherein the at least one of the power threshold and the duration threshold is selected based on at least one training session conducted with the subject, wherein the at least one training session comprises:
instructing or prompting the subject to generate a thought or evoke a change in a mental state of the subject;
recording the raw electrical signals from the brain of the subject using the recording device after prompting the subject to generate the thought;
filtering the raw electrical signals in the one or more desired frequency bands using one or more frequency decomposition methods;
converting the voltage values of the filtered raw electrical signals into power values for each of the desired frequency bands; and
selecting the at least one of the power threshold and the duration threshold to be applied for each of the desired frequency bands in order to distinguish the transient oscillatory or pseudo-oscillatory bursts from background noise
(see citations of rejection of claim 4: measurements performed in cued task (i.e., a training session), and Beta bursts were defined as threshold crossings of the beta feature vector above the 75th percentile of the baseline period).
Re. Claim 8: Merk teaches the invention according to claim 1. Merk further teaches the invention wherein the recording device is an implantable electrode array (Fig. 1A: ECoG and STN electrodes are both implanted).
Re. Claim 10: Merk teaches:
detecting one or more transient oscillatory or pseudo-oscillatory bursts from an ongoing neural signal recording of a subject captured by a recording device (Pages 4-7: see section titled “Grip-force decoding performance is correlated with PD motor impairment and subthalamic beta burst dynamics;” Examiner notes that beta bursts are a type of pseudo-oscillatory burst as defined in Applicant’s Specification at Paragraph 0130);
extracting, using one or more processors of a computing device communicatively coupled to the recording device, one or more burst features from the one or more transient oscillatory or pseudo-oscillatory bursts detected within a detection period of less than 100 ms (Page 2: “For the use in machine- learning models, band power feature time-series were extracted in a real- time BCI compatible implementation (Figure 1D) streamed in virtual packets of 100ms length at a sampling rate of 1000 Hz to mimic the online application. Variance as a measure of amplitude of rereferenced, band- pass filtered raw data segments was extracted at 10 Hz with an adaptive window length from 1000 to 100ms of past data for eight oscillatory features [θ (4–8 Hz), α (8–12 Hz), β (13–35 Hz), low β (13–20 Hz), high β (20–35 Hz), low γ (60–80 Hz), high- frequency activity (HFA) (90–200 Hz) and all γ (60–200 Hz)]. All features were normalized to the median of the past 10 s to compensate for potential signal changes over time. The target variable was continuously measured grip- force (z- scored for each recording session), which was cleaned from noise and baseline drift (Xie et al., 2018)”);
applying a feature threshold to the one or more burst features extracted within the detection period using the one or more processors of the computing device (Page 6: “Beta bursts were defined as threshold crossings of the beta feature vector above the 75th percentile of the baseline period;” Page 20: “To investigate a potential relationship between grip- force decoding performance and beta burst activity, we have adopted a previously validated approach to movement related burst analyses (Torrecillos et al., 2018; Lofredi et al., 2019). Therefore, the beta feature time- series were used and a threshold constituting the 75th percentile of the rest periods were calculated. Next, threshold crossings of at least 100ms lengths in the motor preparation (−1–0 s with respect to movement) and movement execution (0–1 s with respect to movement execution) were marked as bursts”);
predicting, using the one or more processors of the computing device, a thought generated by the subject or a change in mental state evoked by the subject when the one or more burst features extracted within the detection period meets or exceeds the feature threshold (Page 3: see Figure 1, input into machine learning pipeline prediction of force gripping movement, whereby prediction is based on identification of beta bursts using activity surpassing a particular threshold).
Merk does not explicitly use the prediction output from the machine learning model to control a device or software application running on a device with an input command based on the prediction.
However, Merk suggests reasons whereby it would be obvious to do so (see rejection of claim 1).
Re. Claim 11: Merk teaches the invention according to claim 10. Merk further teaches the invention wherein the one or more transient oscillatory or pseudo-oscillatory bursts are generated in response to the thought generated by the subject or the change in mental state evoked by the subject (Page 2: “We analyzed sensorimotor ECoG and subthalamic LFP data recorded intraoperatively from 11 PD patients undergoing DBS implantation during performance of a Go/No- Go based cued grip- force task (Figure 1A)”).
Re. Claim 12: Merk teaches the invention according to claim 11. Merk further teaches the invention wherein the thought of the subject is a thought generated by the subject to move one or more body parts of the subject (see citation of rejection of claim 11 – grip force cuing tasks entail movement of muscles responsible for applying grip force).
Re. Claim 14: Merk teaches the invention according to claim 10. Merk further teaches the invention wherein the recording device is an implantable electrode array (Fig. 1A: ECoG and STN electrodes are both implanted).
Re. Claim 19: See rejection of claim 10; claim 19 recites limitations of claim 10 mutatis mutandis as a system claim.
Re. Claim 20: See rejection of claim 14; claim 20 recites limitations of claim 14 mutatis mutandis as a system claim.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over:
Merk T, Peterson V, Lipski WJ, Blankertz B, Turner RS, Li N, Horn A, Richardson RM, Neumann WJ. Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease. Elife. 2022 May 27;11:e75126. doi: 10.7554/eLife.75126. PMID: 35621994; PMCID: PMC9142148 (hereinafter – Merk) in view of
Al-Saggaf et al. (US 11179089 B1) (hereinafter – Al-Saggaf).
Re. Claim 6: Merk teaches the invention according to claim 1, but does not teach the invention wherein the machine learning algorithm is a long short-term memory (LSTM) neural network. Examiner notes that Merk compares the performance of neural networks to their selected model of gradient boosted trees with an XGBOOST framework (Pages 17-20); however, Merk does not compare the relative performance of long short-term memory networks (LSTM), and instead compares the performance of variations in architecture of a typical neural network (Page 19). Thus, Merk does not recite an explicit teaching against the use of LSTM networks.
Al-Saggaf teaches analogous art in the technology of analyzing EEG signals in specific frequency bands using machine learning techniques, including interaction (e.g., control of a display) with software based on the results of the machine learning analysis (Abstract). Al-Saggaf further teaches wherein the machine learning algorithm is a long short-term memory (LSTM) neural network (Fig. 8). Particularly, Al-Saggaf teaches application of a neural network of this architecture for use in analyzing data analogous to that of Merk (Al-Saggaf: Col. 13, lines 13-19: “The feature extraction operation 702 takes as input a combined signal of filtered frequency bands and extracts significant features while removing irregularity within the data. The frequency bands include alpha, beta, and theta bands of the EEG signal. The classification operation 704 uses extracted features to classify the signal…”).
Since each individual element and its function are shown in the prior art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself. That is in the substitution of the use of LSTM networks for analysis of features of filtered frequency bands of an EEG signal as taught in Al-Saggaf for the XGBoosted tree model of Merk. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious.
Additionally or alternatively, the skilled artisan would recognize inherent advantages in using LSTM networks over boosted tree models while weighing disadvantages of using LSTM networks, dependent on clinical application, dataset size, temporal contexts to tasks, etc.
Claims 7 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over:
Merk T, Peterson V, Lipski WJ, Blankertz B, Turner RS, Li N, Horn A, Richardson RM, Neumann WJ. Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease. Elife. 2022 May 27;11:e75126. doi: 10.7554/eLife.75126. PMID: 35621994; PMCID: PMC9142148 (hereinafter – Merk) in view of
Harpaz et al. (US 20230371872 A1) (hereinafter – Harpaz).
Re. Claims 7 and 13: Merk teaches the invention according to claims 1 and 10, but does not teach the invention wherein the one or more burst features is at least one of a burst count, an [interburst] interval length, burst timing pattern, and time domain waveform of a burst, or change thereof.
Harpaz teaches analogous art in the technology of analyzing EEG brain wave patterns (Abstract),and analyzes such data relative to when a subject performs a task-of-interest or background task (Paragraph 0024), and uses a machine learning algorithm to analyze burst features of analogous frequency bands of EEG data (Paragraph 0145). Examiner also notes that identifying a burst in Harpaz is also performed similarly to Applicant (Paragraph 0285: “Energy above a predetermined threshold was considered as a “burst”, and segments were defined according the detected bursts”). Harpaz further teaches wherein the one or more burst features is at least one of a burst count, an [interburst] interval length, burst timing pattern, and time domain waveform of a burst, or change thereof (Paragraph 0145: “The method proceeds to 244 at which classification features are extracted from each segment. The classification features are optionally and preferably based at least on the frequency of the EG data in the segment. For example, the method can determine, for example, using a Fourier Transform, the brain wave bands within the segment (e.g., Alpha band, Beta band, Delta band, Theta band and Gamma band), and extract one or more features for each brain wave band. A representative example of a feature that can be extracted is the energy content of each brain wave band. These embodiments are particularly useful when the segmentation 242 employs a sliding window. When the segmentation is according to energy bursts the features can include, at least one of: peak amplitude of the burst in the respective frequency band, the area under the envelope curve in the respective frequency band, and the duration of the burst in the respective frequency band”).
It would have been obvious to one having skill in the art before the effective filing date to have modified Merk to additionally utilize the features and analysis technique such as taught by Harpaz, the motivation being that doing so allows for the system to determine task-specific attention (Paragraph 0024), which allows for identification of a degree of focus or intent of a user of the brain computer interface application as suggested by Merk.
Claims 9 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over:
Merk T, Peterson V, Lipski WJ, Blankertz B, Turner RS, Li N, Horn A, Richardson RM, Neumann WJ. Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease. Elife. 2022 May 27;11:e75126. doi: 10.7554/eLife.75126. PMID: 35621994; PMCID: PMC9142148 (hereinafter – Merk) in view of
Lee et al. (US 20210055794 A1) (hereinafter – Lee).
Re. Claims 9 and 15: Merk teaches the invention according to claims 8 and 14, including wherein the recording device comprises a plurality of electrodes (see citation of rejection of claims 8 and 14).
Merk does not teach the invention wherein the method further comprises applying a weighting factor to one or more electrodes of the recording device such that the transient oscillatory or pseudo-oscillatory bursts detected at the one or more electrodes is weighted more than the transient oscillatory or pseudo-oscillatory bursts detected at another electrode of the recording device.
Lee teaches analogous art in the technology of control systems based on brain function and motor control (Abstract). Lee further teaches wherein the method further comprises applying a weighting factor to one or more electrodes of the recording device such that signals detected at the one or more electrodes is weighted more than signals detected at another electrode of the recording device (Paragraph 0044: “A weight may be given to the specific location, i.e., the specific electrode through spatial filtering, and through this, in recognizing the user's specific command, a feature vector is extracted by giving a weight to the largest spatially influential part”).
It would have been obvious to one having skill in the art before the effective filing date to have modified Merk to include spatial filtering as taught by Lee to apply weighting to the burst signal recordings of Merk, the motivation being that doing so allows for extraction of a feature vector by giving a weight to a specific location (electrode) having a great change due to a high relevance to the corresponding intention (Paragraph 0044).
Claims 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over:
Merk T, Peterson V, Lipski WJ, Blankertz B, Turner RS, Li N, Horn A, Richardson RM, Neumann WJ. Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease. Elife. 2022 May 27;11:e75126. doi: 10.7554/eLife.75126. PMID: 35621994; PMCID: PMC9142148 (hereinafter – Merk) in view of
Truccolo et al. (US 20130261490 A1) (hereinafter – Truccolo).
Re. Claim 16: Merk teaches the invention according to claim 10, but does not teach the invention wherein the feature threshold is a burst rate threshold. Merk is silent regarding the use of burst rates.
Truccolo teaches analogous art in the technology of analyzing neural signals for detection of neurological events (Abstract). Truccolo further teaches that mean spiking rates have predictive power in determining neurological events, including tasks involving grasping and reaching (Figs. 8, 11; Paragraphs 0066, 0073).
Thus, it would have been obvious to one having skill in the art before the effective filing date to have modified Merk to include utilizing mean burst rate as a feature and selecting a burst rate having suitable predictive power (i.e., a threshold), the motivation being that doing so provides an additional variable by which motion intent may be assessed for use in neural interfaces (Paragraph 0126).
Re. Claim 17: Merk as modified by Truccolo teaches the invention according to claim 16. Truccolo, in teaching further detail regarding the modification, further teaches wherein the burst rate threshold is a median burst rate calculated from previous detection periods (Examiner notes that an average requires computation from a previous period, and that a median is merely a type of an average which the skilled artisan would understand to have benefits over an arithmetic average, such as reduction of the influence of extreme outliers in the data set).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over:
Merk T, Peterson V, Lipski WJ, Blankertz B, Turner RS, Li N, Horn A, Richardson RM, Neumann WJ. Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease. Elife. 2022 May 27;11:e75126. doi: 10.7554/eLife.75126. PMID: 35621994; PMCID: PMC9142148 (hereinafter – Merk) in view of
Panken et al. (US 20090082829 A1) (hereinafter – Panken).
Re. Claim 18: Merk teaches the invention according to claim 10, but does not teach the invention wherein the feature threshold is a dynamic threshold adjusted over time by the computing device. Instead, Merk utilizes a static threshold a 75th percentile crossing to define beta bursts relative to baseline.
Panken teaches analogous art in the technology of identifying volitional patient input via biosignals in the brain as detected by frequency components of EEG signals (Abstract). Panken further teaches the invention wherein the feature threshold is a dynamic threshold adjusted over time by the computing device (Paragraph 0210: “Comparator 280 compares the measured power from lowpass filter 277 with the baseline power threshold from threshold tracker 278. If the measured power is greater than the baseline power threshold, comparator 280 may output a trigger signal to a processor of a medical device to control therapy and/or recording of diagnostic information. If the measured power is equal to or less than the baseline power threshold, comparator 280 outputs a power tracking measurement to threshold tracker 278, as indicated by the line from comparator 280 to threshold tracker 278. Threshold tracker 278 may include a median filter that creates the baseline threshold level after filtering the power of the signal in the selected frequency band for several minutes. In this way, the measured power of the signal in the selected frequency band may be used by the threshold tracker 278 to update and generate the baseline power threshold of the selected frequency band for the patient. Hence, the baseline power threshold may be dynamically adjusted as the sensed signal changes over time. A signal above or below the baseline power threshold may signify an event that may support generation of a trigger signal”).
It would have been obvious to one having skill in the art before the effective filing date to have modified Merk to include dynamically adjusting a threshold as taught by Panken, the motivation being that doing so allows for the threshold of detection for a burst feature to change as the sensed signal (and its corresponding baseline) may change over time.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims of the instant application are rejected on the ground of nonstatutory double patenting as being unpatentable over claims of U.S. Patent No. 12,186,089 (hereinafter – “the ‘089 patent”). Although the claims at issue are not identical, they are not patentably distinct from each other because subject matter of each of the present claims are encompassed as follows:
Re. Claim 1: Claim 1 of the patent is narrower than claim 1 of the instant application and thus teaches each aspect of claim 1.
Re. Claim 2: Claim 2 recites limitations which are encompassed by claim 1 of the ‘089 patent.
Re. Claims 3 and 4: Claims 3 and 4 recite verbatim language to that of claim 2 of the ‘089 patent.
Re. Claim 5: Claim 5 recites verbatim language to that of claim 3 of the ‘089 patent.
Re. Claim 6: Claim 6 recites limitations which are encompassed by claim 13 of the ‘089 patent.
Re. Claim 7: Claim 7 recites limitations which are encompassed by any one of claims 92, 93, 94, and 95 of the ‘089 patent.
Re. Claim 8: Claim 8 recites limitations which are encompassed by claim 26 of the ‘089 patent.
Re. Claim 9: Claim 9 recites limitations which are encompassed by claim 25 of the ‘089 patent.
Re. Claim 10: Claim 10 recites limitations which are encompassed by any one of claims 2 or 61 of the ‘089 patent.
Re. Claim 11: Claim 11 recites limitations which are encompassed by claim 61 of the ‘089 patent.
Re. Claim 14: Claim 11 recites limitations which are encompassed by claim 26 of the ‘089 patent.
Re. Claim 15: Claim 15 recites limitations which are encompassed by claim 25 of the ‘089 patent.
Re. Claim 19: Claim 19 recites limitations which are encompassed by any one of claims 2 or 61 of the ‘089 patent.
Re. Claim 20: Claim 20 recites limitations which are encompassed by claim 26 of the ‘089 patent.
Claims 12, 13, and 16-18 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims of the ‘089 patent in view of prior art teachings as recited in the rejections under 35 U.S.C. 103 above.
Claims 2 or 61 of the ‘089 patent encompass independent claim 10 of the instant application; dependent claims of claim 10 of the instant application recite limitations disclosed in the prior art in the rejections above. Motivation to modify claims of the ‘089 patent would be identical.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JUSTIN XU whose telephone number is (571)272-6617. The examiner can normally be reached Mon-Fri 7:30-5:00.
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, Alexander Valvis can be reached at (571) 272-4233. 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.
/JUSTIN XU/Primary Examiner, Art Unit 3791
