DETAILED CORRESPONDANCE
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 claims
This final office action on merits is in response to the communication received on 05/19/2026. Claim 16-17 are cancelled. Amendments to claims 1, 18, and 19 are acknowledged and have been carefully considered. Claims 1-15 and 18-20 are pending and considered below.
Information Disclosure Statement
The information disclosure statement (IDS) filed on 07/16/2026 has been acknowledged. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
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 1-15, and 18-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 recites the limitations of acquiring a gut score related to a gut condition of the user, using input information containing the sound information acquired by the sound information acquiring unit and learning information prepared in advance; wherein multiple pieces of learning information are each prepared in association with the device identifying information, selecting learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit among the multiple pieces of learning information, and acquiring the gut score using the learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit. These limitations, as drafted, are processes that, under their broadest reasonable interpretations, cover performance of the limitations in the mind or by using a pen and paper. Even when considering the “a gut score acquiring unit” language, the claim encompasses a user evaluating abdominal sound information, selecting predetermined evaluation criteria (i.e., learning information ) corresponding to device identifying information, apply the selected evaluation criteria to the abdominal sound information, and determining a gut score representing the user’s gut condition in their mind or by using a pen and paper. The nominal recitation of a gut score acquiring unit does not take the claim limitations out of the mental processes grouping. Thus, the claim recites a mental process which is an abstract idea.
Independent claims 18 and 19 recite identical or nearly identical steps with respect to claim 1 (and therefore also recite limitations that fall within this subject matter grouping of abstract ideas), and these claims are therefore determined to recite an abstract idea under the same analysis.
Under Step 2A Prong Two
The claimed limitations, as per claim 1, include:
one or more processor; a memory device comprising instructions that, when executed, cause the one or more processor to implement:
a sound information acquiring unit that acquires sound information regarding abdominal sounds which are sounds generated by intestinal activity of a user;
a gut score acquiring unit that acquires a gut score related to a gut condition of the user, using input information containing the sound information acquired by the sound information acquiring unit and learning information prepared in advance;
a gut score output unit that outputs the gut score acquired by the gut score acquiring unit; and
a device identifying information acquiring unit that acquires device identifying information indicating an acoustic characteristic or recording condition of a device used to acquire the abdominal sounds,
wherein multiple pieces of learning information are each prepared in association with the device identifying information, and the gut score acquiring unit selects learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit among the multiple pieces of learning information, and the gut score acquiring unit acquires the gut score using the learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit,
wherein the sound information includes information generated by analyzing audio data obtained by recording the abdominal sounds in a predetermined frequency band and a predetermined time window; and
wherein the information processing apparatus further comprises: a microphone for recording the abdominal sounds; and
a display unit that displays the gut score output by the gut score output unit.
Examiner Note: underlined elements indicate additional elements of the claimed invention identified as performing the steps of the claimed invention.
The judicial exception expressed in claim 1 is not integrated into a practical application. The claim as a whole merely describes how to generally “apply” the concept of evaluating physiological information to determine a user’s gut condition by selecting appropriate evaluation criteria based on device identifying information and assigning a gut score in a computer environment. The claimed computer components (i.e., one or more processor; a memory device comprising instructions that, when executed, cause the one or more processor to implement, a sound information acquiring unit, a gut score acquiring unit, a gut score output unit, a device identifying information acquiring unit, wherein the sound information includes information generated by analyzing audio data obtained by recording the abdominal sounds in a predetermined frequency band and a predetermined time window) are recited at a high level of generality and are merely invoked as tools to perform a process of evaluating physiological information by selecting corresponding learning information and determining a gut score. Simply implementing the abstract idea on a generic computer is not a practical application of the abstract idea. Although the claim recites generating sound information by analyzing data within a predetermined frequency band and predetermined time window, the claim does not recite any particular improvement to audio processing technology. Instead, these limitations merely define the information used in performing the abstract evaluation and therefore amount to implementing the abstract idea using generic computer processing. Accordingly, alone and in combination, these additional elements do not integrate the abstract idea into a practical application.
The judicial exception expressed in claim 1 is not integrated into a practical application. The claim recites the additional elements of acquiring sound information regarding abdominal sounds which are sounds generated by intestinal activity of a user, acquiring device identifying information indicating an acoustic characteristic or recording condition of a device used to acquire the abdominal sounds, a microphone for recording the abdominal sounds; that outputs the gut score, and a display unit that displays the gut score output. These limitations are recited at a high level of generality (i.e., as a general means of collecting physiological input information and presenting the evaluation result), and amounts to merely data gathering and displaying the result, which are forms of insignificant extra-solution activities. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application. The claim is directed to an abstract idea.
Therefore, under step 2A, the claims are directed to the abstract idea, and require further analysis under Step 2B.
Under step 2B
Claim 1 does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed with respect to Step 2A, the claim as a whole merely describes how to generally “apply” the concept of evaluating physiological information to determine a user’s gut condition by selecting appropriate evaluation criteria based on device identifying information and assigning a gut score in a computer environment. Thus, even when viewed as a whole, nothing in the claim adds significantly more (i.e., an inventive concept) to the abstract idea.
For claim 1, under step 2B, the additional elements of acquiring sound information regarding abdominal sounds which are sounds generated by intestinal activity of a user, acquiring device identifying information indicating an acoustic characteristic or recording condition of a device used to acquire the abdominal sounds, a microphone for recording the abdominal sounds; that outputs the gut score, and a display unit that displays the gut score output have been evaluated. The information processing apparatus comprising one or more processor performs a general function of receiving, processing, and outputting user physiological information for subsequent evaluation, which represents a well-understood, routine, and conventional computer functions in the field of physiological data collection and analysis. The specification discloses that the processor is used in its ordinary capacity as a generic processor performing conventional functions and does not describe any improvement to the computer itself or to the functioning of the overall computer system (see [0138]). Also noted in Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016), merely collecting information for analysis without a technological improvement is no more than collecting information before evaluating information to determine a gut score, and displaying the result, and does not integrate the abstract idea into a practical application. Therefore, the claim does not recite an inventive concept and is not patent eligible.
Claims 2-4, 6-7, 9-11, and 14 recite no further additional elements, and only further narrow the abstract idea. The previously identified additional elements, individually and as a combination, do not integrate the narrowed abstract idea into a practical application for reasons similar to those explained above, and do not amount to significantly more than the narrowed abstract idea for reasons similar to those explained above.
Claims 5, 8, 12-13, 15, and 20 recite the additional elements of the gut score acquiring unit further includes an excretion score acquiring unit (claim 5), the gut score acquiring unit further includes an eating-and-drinking score acquiring unit (claim 8), the gut score acquiring unit further includes an activity status score acquiring unit (claim 12), the gut score acquiring unit (claim 13), the gut score acquiring unit includes an element score acquiring unit (claim 15), the gut score acquiring unit comprises a gut-related score acquiring unit (claim 20). However, these additional elements amount to implementing an abstract idea on a generic computing device. As such, these additional elements, when considered individually or in combination with the prior devices, do not integrate the abstract idea into a practical application or amount to significantly more than the abstract idea.
Thus, as the dependent claims remain directed to a judicial exception, and as the additional elements of the claims do not amount to significantly more, the dependent claims are not patent eligible.
Therefore, the claims here fail to contain any additional element(s) or combination of additional elements that can be considered as significantly more and the claims are rejected under 35 U.S.C. 101 for lacking eligible subject matter.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-2 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Spiegel et al. (International Publication No. WO2016112127A1), referred to hereinafter as Spiegel, in view of Singh et al. (U.S. Patent Publication 2021/0090734A1), referred to hereinafter as Singh, and Patel et al. (U.S. Patent Publication 2019/0371311A1), referred to hereinafter as Patel.
Regarding claim 1, Spiegel teaches an information processing apparatus, comprising (Spiegel [00132] “The abdominal statistics system 10 described herein may be readily implemented to include one or more computer processor devices (e.g., CPU, microprocessor, microcontroller, computer enabled ASIC, etc.) and associated memory (e.g., RAM, DRAM, NVRAM, FLASH, computer readable media, etc.) whereby programming stored in the memory and executable on the processor perform the steps of the various process methods described herein.”):
one or more processor; a memory device comprising instructions that, when executed, cause the one or more processor to implement (Spiegel [00132] “The abdominal statistics system 10 described herein may be readily implemented to include one or more computer processor devices (e.g., CPU, microprocessor, microcontroller, computer enabled ASIC, etc.) and associated memory (e.g., RAM, DRAM, NVRAM, FLASH, computer readable media, etc.) whereby programming stored in the memory and executable on the processor perform the steps of the various process methods described herein.”):
a sound information acquiring unit that acquires sound information regarding abdominal sounds which are sounds generated by intestinal activity of a user (Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”);
gut information (Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”);
abdominal information (Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”);
wherein the information processing apparatus further comprises: a microphone for recording the abdominal sounds (Spiegel [0046]” In the side view of FIG. 3, a sensor 12 is shown with housing 42 bonded (e.g., via adhesive 44) to a mounting flange 40, under which is an adhesive mounting ring 46 shown coupled to a bandage 48 (e.g. Tegaderm bandage). It is appreciated that other bandage types and brands may be utilized with the abdominal statistics system 10 for attachment to patient abdominal tissue 16. Held within the sensor housing 42 is a printed circuit board 50 (of any desired material in the art), upon which are attached a sensor electrical connection 56, a sensor microphone 52, and a sensor vibration actuator 54.”, and
Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”);
a display unit that displays (Spiegel [0064] “The abdominal statistics application software 32 preferably includes acoustic analog signal processing, digital signal processing, computation, scheduling, and data display systems along with user interactive systems including a touch screen display.”).
Spiegel fails to explicitly teach a score acquiring unit that acquires a score related to a condition of the user, using input information containing the sound information acquired by the sound information acquiring unit and learning information prepared in advance; a score output unit that outputs the score acquired by the score acquiring unit; a device identifying information acquiring unit that acquires device identifying information indicating an acoustic characteristic or recording condition of a device used to acquire the sounds; wherein multiple pieces of learning information are each prepared in association with the device identifying information; the score acquiring unit selects learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit among the multiple pieces of learning information, and the score acquiring unit acquires the score using the learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit; and wherein the sound information includes information generated by analyzing audio data obtained by recording the sounds in a predetermined frequency band and a predetermined time window; the score output by the score output unit.
Singh teaches a score acquiring unit that acquires a score related to a condition of the user, using input information containing the sound information acquired by the sound information acquiring unit and learning information prepared in advance (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms.”, and
Singh [0022] “In an aspect, the control unit can be configured to classify, using a deep convolutional neural network (CNN) trained model, each of the spectrograms into any or a combination of the normal spectrogram and the abnormal spectrogram.”);
a score output unit that outputs the score acquired by the score acquiring unit (Singh [0092] “In an embodiment, the control unit 106 can be configured to compute any or a combination of a mean and standard deviation of the classification scores to remove any deviation (anomaly etc.), if present, in the classification scores. The control unit can be configured to store an audio slice corresponding to an obtained higher classification score in any or a combination of database 114 or in a CNN training database. The CNN training database can serve as a growing training database for re-training the CNN model for improved accuracy. Further, the heart signal classification along with scores can be transferred to mobile application installed on remote computing or mobile device.”);
the score acquiring unit selects learning information and the score acquiring unit acquires the score (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms.”, and
Singh [0022] “In an aspect, the control unit can be configured to classify, using a deep convolutional neural network (CNN) trained model, each of the spectrograms into any or a combination of the normal spectrogram and the abnormal spectrogram.”);
wherein the sound information includes information generated by analyzing audio data obtained by recording the sounds in a predetermined frequency band and a predetermined time window (Singh [0073] “In an exemplary embodiment, each heart sound can be converted from a typical audio format (e.g., mp3, way, etc.) to a mel-frequency spectrogram with tilt and amplitude normalization over a pre-selected frequency range (400 Hz to 4 kHz). For computational efficiency, the input audio can be low-pass filtered to about 5/4 of the top of the selected frequency range and then down sampled accordingly. For example, using 4 kHz as the top of our frequency range of interest and using 44.1 kHz as the input audio sampling rate, the input audio can be low-pass filtered using a simple finite impulse response (FIR) filter with an approximate frequency cut between 5 and 5.5 kHz and then subsampled to a 11.025 kHz sampling rate. To minimize volume-change effects, the audio sample energy can be normalized using the local average energy, taken over a tapered, centred 10-second window. To minimize aperture artifacts, the average energy can also be computed using a tapered Hamming window.”, and
Singh [0074] “A spectrogram “slice rate” of 100 Hz (that is, a slice step size of 10 ms) can be used. For the slices, audio data can be taken, a tapered window (to avoid discontinuity artifacts in the output) applied, and then an appropriately sized Fourier transform can be applied. The Fourier magnitudes are “de-tilted” using a single-pole filter to reduce the effects of low-frequency bias and then “binned” (averaged) into B frequency samples at mel-scale frequency spacing (e.g., B=32).”);
the score output by the score output unit (Singh [0092] “In an embodiment, the control unit 106 can be configured to compute any or a combination of a mean and standard deviation of the classification scores to remove any deviation (anomaly etc.), if present, in the classification scores. The control unit can be configured to store an audio slice corresponding to an obtained higher classification score in any or a combination of database 114 or in a CNN training database. The CNN training database can serve as a growing training database for re-training the CNN model for improved accuracy. Further, the heart signal classification along with scores can be transferred to mobile application installed on remote computing or mobile device.”).
Patel teaches a device identifying information acquiring unit that acquires device identifying information indicating an acoustic characteristic or recording condition of a device used to acquire the sounds (appropriate acoustic model 314. The metadata can include any meaningful information that would assist in the selection of the appropriate acoustic model 314. For example, the metadata can include either or both of a device type and a specific device condition. Specifically, the metadata can include (i) a unique identification of the washing machine 306 (e.g., device type, model number, serial number, etc.), (ii) usage conditions, such as temperature and/or environmental conditions in the laundry room, (iii) other environmental conditions, such as outdoor weather, (iv) information that could affect the surrounding acoustics, (v) information related to other types of noises that could interfere with the accuracy of the acoustic model, (vi) current operating conditions of the washing machine 306 as well as operating conditions of other devices located nearby, such as a dryer or laundry tub, and (vii) information regarding one or more hardware and software components of the washing machine 306 or other components involved in the receiving of the speech audio and/or for providing audio feedback to the user. Generally, the ability of a system to optimize the choosing or adapting of an acoustic model is improved by having more metadata information with utterances.”, and
Patel [0039] “Once the phrase interpreter 312 receives the speech audio and the metadata, the phrase interpreter 312 (or some other component of the overall system or platform that performs the speech recognition) can decide which acoustic model would be the best for extracting phonemes. Some embodiments use only the model number or device type of the washing machine 306, and the phrase interpreter 312 is able to select an acoustic model that has been created or tuned for that specific device type. The same goes for the other possibilities of metadata, as described above. Furthermore, if the user of the washing machine 406 can be identified, then an acoustic model that is tuned for that specific user's voice can be implemented.”);
wherein multiple pieces of learning information are each prepared in association with the device identifying information (Patel [0038] “The phrase interpreter 312 then uses the metadata for selection of an appropriate acoustic model 314. The metadata can include any meaningful information that would assist in the selection of the appropriate acoustic model 314. For example, the metadata can include either or both of a device type and a specific device condition. Specifically, the metadata can include (i) a unique identification of the washing machine 306 (e.g., device type, model number, serial number, etc.), (ii) usage conditions, such as temperature and/or environmental conditions in the laundry room, (iii) other environmental conditions, such as outdoor weather, (iv) information that could affect the surrounding acoustics, (v) information related to other types of noises that could interfere with the accuracy of the acoustic model, (vi) current operating conditions of the washing machine 306 as well as operating conditions of other devices located nearby, such as a dryer or laundry tub, and (vii) information regarding one or more hardware and software components of the washing machine 306 or other components involved in the receiving of the speech audio and/or for providing audio feedback to the user. Generally, the ability of a system to optimize the choosing or adapting of an acoustic model is improved by having more metadata information with utterances.”, and
Patel [0039] “Once the phrase interpreter 312 receives the speech audio and the metadata, the phrase interpreter 312 (or some other component of the overall system or platform that performs the speech recognition) can decide which acoustic model would be the best for extracting phonemes. Some embodiments use only the model number or device type of the washing machine 306, and the phrase interpreter 312 is able to select an acoustic model that has been created or tuned for that specific device type. The same goes for the other possibilities of metadata, as described above. Furthermore, if the user of the washing machine 406 can be identified, then an acoustic model that is tuned for that specific user's voice can be implemented.”);
corresponding to the device identifying information acquired by the device identifying information acquiring unit among the multiple pieces of learning information; and using the learning information corresponding to the device identifying information acquired by the device identifying information acquiring unit (Patel [0038] “The phrase interpreter 312 then uses the metadata for selection of an appropriate acoustic model 314. The metadata can include any meaningful information that would assist in the selection of the appropriate acoustic model 314. For example, the metadata can include either or both of a device type and a specific device condition. Specifically, the metadata can include (i) a unique identification of the washing machine 306 (e.g., device type, model number, serial number, etc.), (ii) usage conditions, such as temperature and/or environmental conditions in the laundry room, (iii) other environmental conditions, such as outdoor weather, (iv) information that could affect the surrounding acoustics, (v) information related to other types of noises that could interfere with the accuracy of the acoustic model, (vi) current operating conditions of the washing machine 306 as well as operating conditions of other devices located nearby, such as a dryer or laundry tub, and (vii) information regarding one or more hardware and software components of the washing machine 306 or other components involved in the receiving of the speech audio and/or for providing audio feedback to the user. Generally, the ability of a system to optimize the choosing or adapting of an acoustic model is improved by having more metadata information with utterances.”, and
Patel [0039] “Once the phrase interpreter 312 receives the speech audio and the metadata, the phrase interpreter 312 (or some other component of the overall system or platform that performs the speech recognition) can decide which acoustic model would be the best for extracting phonemes. Some embodiments use only the model number or device type of the washing machine 306, and the phrase interpreter 312 is able to select an acoustic model that has been created or tuned for that specific device type. The same goes for the other possibilities of metadata, as described above. Furthermore, if the user of the washing machine 406 can be identified, then an acoustic model that is tuned for that specific user's voice can be implemented.”);
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the abdominal statistics system of Spiegel to incorporate the machine learning acoustic analysis and scoring techniques taught by Singh. Spiegel teaches acquiring and processing gastrointestinal acoustic signals to provide actionable information concerning a patient's gastrointestinal condition, while Singh teaches analyzing physiological acoustic signals using predetermined acoustic features and a trained convolutional neural network to classify the physiological signals and generate corresponding classification scores. Singh further teaches processing physiological acoustic data over a preselected frequency range and predetermined temporal windows. One of ordinary skill in the art would have been motivated to apply Singh's known machine learning and signal processing techniques to the gastrointestinal acoustic signals acquired by Spiegel in order to provide an automated and quantitative assessment of the gastrointestinal acoustic information, which improves the efficiency with which the acquired physiological acoustic signals are evaluated and providing a score indicative of the patient's gastrointestinal condition.
It would further have been obvious to modify the combined system of Spiegel and Singh according to the teachings of Patel to select learning information corresponding to characteristics or recording conditions associated with the device used to acquire the acoustic information. Patel teaches receiving metadata identifying a device or conditions affecting acquisition of an acoustic signal, including device type, device condition, environmental conditions, surrounding acoustics, interfering noise, and hardware and software involved in receiving the audio, and using such metadata to select an acoustic model created or tuned for the corresponding device or condition. One of ordinary skill in the art would have been motivated to apply Patel's device and condition dependent acoustic model selection to the physiological acoustic analysis of Spiegel as modified by Singh because acoustic signals acquired using different devices or under different recording conditions may exhibit different acoustic characteristics. Selecting a corresponding trained acoustic model based on such device or recording condition information would have been a predictable use of Patel's known technique to account for those variations and improve the reliability and accuracy of the acoustic analysis.
Accordingly, the proposed combination represents the predictable use of known elements according to their established functions: Spiegel's acquisition and analysis of gastrointestinal sounds, Singh's trained model classification, scoring, and frequency and time window processing of physiological acoustic signals, and Patel's selection of an appropriate acoustic model based on device and acoustic condition metadata. The combination would have yielded the predictable result of analyzing gastrointestinal acoustic information using learning information selected according to the characteristics or recording conditions of the acquisition device to obtain and output a gut score, with a reasonable expectation of success.
Regarding claim 2, Spiegel, Singh, and Patel teach the invention in claim 1, as discussed above, and further teach wherein the input information further contains life information regarding a life state of the user (Spiegel [00110] “(a) Abdominal statistics monitoring before, during and after a period of meal ingestion type, quantity, and schedule may be varied to enable development of a diagnostic model for an individual subject.”).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) at the time of the invention to modify the apparatus of claim 1 to further include input information containing life information regarding a life state of the user, as recited in claim 2. Spiegel teaches monitoring abdominal statistics before, during, and after meal ingestion, and varying meal type, quantity, and schedule to develop a diagnostic model for an individual subject. Meal timing, quantity, and type constitute lifestyle or behavioral information reflecting the user’s life state. Because gastrointestinal acoustic activity is known to be influenced by lifestyle factors, particularly dietary behavior, a PHOSITA would have recognized that incorporating such life information into the input data would predictably improve the personalization and diagnostic accuracy of the gut condition assessment. Accordingly, including life state information represents a predictable use of known health data to enhance physiological signal interpretation.
Claims 18-19 are analogous to claim 1, thus claims 18-19 are similarly analyzed and rejected in a manner consistent with the rejection of claim 1.
Claims 3-8, 13-15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Spiegel et al. (International Publication No. WO2016112127A1), referred to hereinafter as Spiegel, in view of Singh et al. (U.S. Patent Publication 2021/0090734A1), referred to hereinafter as Singh, and Patel et al. (U.S. Patent Publication 2019/0371311A1), referred to hereinafter as Patel, and further in view of Masamori et al. (International Publication No. WO2020075627A1), referred to hereinafter as Masamori.
Regarding claim 3, Spiegel, Singh, and Patel teach the invention in claim 2, as discussed above, and further teach wherein the life information (Spiegel [00110] “(a) Abdominal statistics monitoring before, during and after a period of meal ingestion type, quantity, and schedule may be varied to enable development of a diagnostic model for an individual subject.”).
Spiegel, Singh, and Patel fail to explicitly teach contains excretion-related information regarding an excretion status of the user.
Masamori teaches contains excretion-related information regarding an excretion status of the user (Masamori, page 6, “The calculation unit 12 may determine information regarding the contents in the digestive tract based on the obtained activity score. The information about the contents includes, for example, the presence / absence of the contents, the position of the contents, the moving speed of the contents, and the high possibility that the contents are excreted (for example, the possibility of being excreted when the user steps on the toilet). Height, etc.) and the time until the contents are excreted.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Spiegel's system to include the excretion information taught by Masamori as part of the life information regarding the user. Spiegel teaches considering user life state information, including meal ingestion type, quantity, and schedule, in connection with abdominal statistics monitoring to develop an individualized diagnostic model, while Masamori teaches determining gastrointestinal information indicative of a user's excretion status, including the likelihood that digestive tract contents will be excreted and the time until excretion. One of ordinary skill in the art would have been motivated to incorporate Masamori's excretion status information into Spiegel's gastrointestinal assessment because such information provides additional information regarding the state and activity of the user's digestive tract, which provides a more comprehensive assessment of the user's gastrointestinal condition.
Regarding claim 4, Spiegel, Singh, Patel, and Masamori teach the invention in claim 3, as discussed above, and further teach wherein the excretion-related information contains information indicated by Bristol Stool Form Scale input by the user (Masamori, page 6, “The information on excretion includes, for example, the time of excretion, the time of feeling feces, the amount of excrement (for example, a metaphorical expression based on the number of bananas), the hardness of excrement (for example, the classification of feces on the Bristol scale).”).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) at the time of the invention to further specify that the excretion-related information includes information indicated by the Bristol Stool Form Scale, as taught by Masamori. Masamori discloses that excretion-related information may include hardness of excrement classified according to the Bristol scale. The Bristol Stool Form Scale is a well-established medical tool for evaluating bowel condition and gastrointestinal function. Because gastrointestinal acoustic activity is physiologically correlated with bowel motility and stool characteristics, a PHOSITA would have recognized that incorporating standardized stool classification data into a gastrointestinal acoustic monitoring system would improve the accuracy and interpretation of gut condition assessment. The combination represents the predictable use of a known clinical indicator of bowel health with known gastrointestinal sound analysis techniques to enhance diagnostic reliability, and therefore would have been obvious.
Regarding claim 5, Spiegel, Singh, Patel, and Masamori teach the invention in claim 3, as discussed above, and further teach wherein the gut score acquiring unit further includes an excretion score acquiring unit that acquires an excretion score based on the excretion-related information, and acquires the gut score using the excretion score acquired by the excretion score acquiring unit (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms.”,
Singh [0022] “In an aspect, the control unit can be configured to classify, using a deep convolutional neural network (CNN) trained model, each of the spectrograms into any or a combination of the normal spectrogram and the abnormal spectrogram.” and
Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”, and
Masamori, page 6, “The information on excretion includes, for example, the time of excretion, the time of feeling feces, the amount of excrement (for example, a metaphorical expression based on the number of bananas), the hardness of excrement (for example, the classification of feces on the Bristol scale).”,
Masamori, page 6-7, “By using these pieces of information as the input information of the arithmetic unit 12, it is possible to expect an improvement in certainty in guessing the information about the contents. For example, the time for the peristaltic movement of the digestive tract can be predicted based on the time taken for food and drink. Since the moving speed of the contents changes according to the type of food and drink, the possibility of excretion of the contents can be predicted more accurately based on the type of food and drink. The size of the content can be estimated based on the amount of food and drink. Since the harder the excrement is, the more time it takes for digestion, the time required for the contents to move through the digestive tract can be estimated based on the hardness of the excrement. Based on the time of excretion, the time of next excretion can be predicted.”
Masamori, page 12, “The extraction step of the computing device 32 extracts information about the activity of the peristaltic movement from the measurement information about the bioactivity acquired by the acquisition device 31. Further, the calculation step of the calculation device 32 obtains an activity score indicating the degree of activity of the peristaltic movement, based on the information regarding the activity of the peristaltic movement. The detailed steps of the acquisition device 31 and the calculation device 32 are the same as the detailed steps of the acquisition unit 11 and the calculation unit 12 of the peristaltic movement automatic measurement device 1 described above. The arithmetic unit 32 can be realized as a physical server or a virtual server, for example. The peristaltic movement automatic measurement system 30 may include a plurality of acquisition devices 31 or a plurality of arithmetic devices 32.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the system of Spiegel, as modified by Singh and Patel, to incorporate the excretion information and gastrointestinal activity scoring taught by Masamori. Masamori teaches collecting excretion information, including excretion time, amount of excrement, and stool hardness, using such information to evaluate and predict the movement and excretion of digestive tract contents, and quantitatively evaluating gastrointestinal activity by calculating an activity score representing the degree of peristaltic activity. One of ordinary skill in the art would have been motivated to quantify Masamori's excretion assessment as an excretion score and use that score as an additional input in determining the overall gut score because excretion status provides additional information indicative of gastrointestinal condition and activity, which predictably provides a more comprehensive quantitative assessment of the user's gut condition.
Regarding claim 6, Spiegel, Singh, and Patel teach the invention in claim 2, as discussed above, and further teach wherein the life information (Spiegel [00110] “(a) Abdominal statistics monitoring before, during and after a period of meal ingestion type, quantity, and schedule may be varied to enable development of a diagnostic model for an individual subject.”).
Spiegel, Singh, and Patel fail to teach contains eating-and-drinking information regarding an eating-and-drinking status of the user.
Masamori teaches contains eating-and-drinking information regarding an eating-and-drinking status of the user (Masamori, page 6, “Alternatively, the peristaltic movement automatic measurement device 1 may be provided with the input unit 17, and the user may be prompted to input information regarding the contents. The information input by the user includes, for example, information about food and drink put in the mouth, information about excretion, and the like. The information about the food and drink put in the mouth includes, for example, the time when the food and drink are put in the mouth, the type of food and drink (vegetables, meats, etc.), the amount of food and drink (for example, the user with respect to the entire food and drink provided. The ratio of eating and drinking) and the like.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the system of Spiegel to incorporate the eating-and-drinking information taught by Masamori as part of the user's life information. Spiegel already teaches monitoring abdominal statistics in relation to meal ingestion type, quantity, and schedule, while Masamori teaches receiving information regarding food and drink consumed by the user, including the time, type, and amount of food and drink. One of ordinary skill in the art would have been motivated to incorporate Masamori's eating-and-drinking information into Spiegel's user information because such information provides additional contextual information concerning factors associated with gastrointestinal activity, which predictably provide a more comprehensive assessment of the user's gastrointestinal condition.
Regarding claim 7, Spiegel, Singh, Patel, Masamori and teach the invention in claim 6, as discussed above., and further teach wherein the eating-and-drinking information contains at least one of information regarding the amount of water consumed, information regarding whether or not alcohol was consumed or the amount of alcohol consumed, information regarding whether or not a meal was taken or the content thereof, and information regarding whether or not a particular group of food was consumed or the amount thereof consumed (Masamori, page 6, “Alternatively, the peristaltic movement automatic measurement device 1 may be provided with the input unit 17, and the user may be prompted to input information regarding the contents. The information input by the user includes, for example, information about food and drink put in the mouth, information about excretion, and the like. The information about the food and drink put in the mouth includes, for example, the time when the food and drink are put in the mouth, the type of food and drink (vegetables, meats, etc.), the amount of food and drink (for example, the user with respect to the entire food and drink provided. The ratio of eating and drinking) and the like.”).
It would have been obvious to a person having ordinary skill in the art (PHOSITA) at the time of the invention to modify the gastrointestinal acoustic monitoring system of Spiegel to further include eating-and-drinking information such as the amount of water consumed, alcohol consumption, meal intake, food content, or specific food group consumption, as taught by Masamori. Masamori discloses prompting a user to input information regarding food and drink put in the mouth, including the time of ingestion, type of food (vegetables, meats), and amount of food and drink consumed. Such disclosures encompass meal content, food groups, and quantities of consumption, and reasonably include beverages such as water and alcohol. Because gastrointestinal acoustic activity and peristaltic movement are directly affected by dietary intake, a PHOSITA would have recognized that incorporating detailed eating-and-drinking information into a gastrointestinal monitoring system would predictably improve contextual interpretation and diagnostic accuracy of gut condition assessment. The modification represents the predictable integration of known dietary intake tracking with known gastrointestinal sound analysis techniques, and therefore would have been obvious.
Regarding claim 8, Spiegel, Singh, Patel, and Masamori teach the invention in claim 6, as discussed above, and further teach wherein the gut score acquiring unit further includes an eating-and-drinking score acquiring unit that acquires an eating-and-drinking score based on the eating-and-drinking information, and acquires the gut score using the eating-and-drinking score acquired by the eating-and-drinking score acquiring unit (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms.,
Singh [0022] “In an aspect, the control unit can be configured to classify, using a deep convolutional neural network (CNN) trained model, each of the spectrograms into any or a combination of the normal spectrogram and the abnormal spectrogram.” and
Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”, and
Masamori, page 6, “Alternatively, the peristaltic movement automatic measurement device 1 may be provided with the input unit 17, and the user may be prompted to input information regarding the contents. The information input by the user includes, for example, information about food and drink put in the mouth, information about excretion, and the like. The information about the food and drink put in the mouth includes, for example, the time when the food and drink are put in the mouth, the type of food and drink (vegetables, meats, etc.), the amount of food and drink (for example, the user with respect to the entire food and drink provided. The ratio of eating and drinking) and the like.”
Masamori, page 6-7, “By using these pieces of information as the input information of the arithmetic unit 12, it is possible to expect an improvement in certainty in guessing the information about the contents. For example, the time for the peristaltic movement of the digestive tract can be predicted based on the time taken for food and drink. Since the moving speed of the contents changes according to the type of food and drink, the possibility of excretion of the contents can be predicted more accurately based on the type of food and drink. The size of the content can be estimated based on the amount of food and drink. Since the harder the excrement is, the more time it takes for digestion, the time required for the contents to move through the digestive tract can be estimated based on the hardness of the excrement. Based on the time of excretion, the time of next excretion can be predicted.”
Masamori, page 12, “The extraction step of the computing device 32 extracts information about the activity of the peristaltic movement from the measurement information about the bioactivity acquired by the acquisition device 31. Further, the calculation step of the calculation device 32 obtains an activity score indicating the degree of activity of the peristaltic movement, based on the information regarding the activity of the peristaltic movement. The detailed steps of the acquisition device 31 and the calculation device 32 are the same as the detailed steps of the acquisition unit 11 and the calculation unit 12 of the peristaltic movement automatic measurement device 1 described above. The arithmetic unit 32 can be realized as a physical server or a virtual server, for example. The peristaltic movement automatic measurement system 30 may include a plurality of acquisition devices 31 or a plurality of arithmetic devices 32.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the system of Spiegel, as modified by Singh and Patel, to incorporate the eating-and-drinking information and gastrointestinal scoring taught by Masamori. Masamori teaches obtaining eating-and-drinking information including the timing, type, and amount of food and drink consumed, using such information as input to evaluate gastrointestinal conditions including the timing of peristaltic movement, movement of digestive tract contents, and likelihood of excretion, and quantitatively evaluating gastrointestinal activity by calculating an activity score representing the degree of peristaltic activity. One of ordinary skill in the art would therefore have been motivated to quantify the eating-and-drinking information as an eating-and-drinking score and use that score as an additional input in determining the overall gut score because Masamori establishes that eating-and-drinking information affects and is useful in evaluating gastrointestinal activity, which predictably provide a more comprehensive quantitative assessment of the user's gut condition.
Regarding claim 13, Spiegel, Singh, and Patel teach the invention in claim 1, as discussed above, and further teach wherein the learning information is generated such that learning input information containing sound information is taken as information that is to be input; and the gut score acquiring unit acquires the gut score acquired using the learning information (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms.”,
Singh [0022] “In an aspect, the control unit can be configured to classify, using a deep convolutional neural network (CNN) trained model, each of the spectrograms into any or a combination of the normal spectrogram and the abnormal spectrogram.”
Singh [0023] “In an aspect, the system can be configured to: compute any or a combination of a mean and standard deviation of the classification scores to remove any deviation, if present, in the classification scores; and store, in the database, an audio slice corresponding to an obtained higher classification score. The purpose of storing the higher classification score is to enable retraining of the CNN model.”
Singh [0024] “In an aspect, the CNN trained model can be configured to, based on any or a combination of the classification scores, the mean and the standard deviation of the classification scores, detect at least one of heart sound patterns and valvular heart disorders associated with the patient.”, and
Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”).
Spiegel, Singh, and Patel fail to teach a value of a predetermined output indicator regarding an activity state of the guts is taken as information that is to be output; and using the value of the output indicator.
Masamori teaches a value of a predetermined output indicator regarding an activity state of the guts is taken as information that is to be output; and using the value of the output indicator (Masamori, page 8, “Therefore, the calculation unit 12 may infer the position, the moving direction, or the like of the content based on the change over time in the activity score. For example, as shown in FIG. 7, the activity scores of “ascending colon, transverse colon, descending colon, and sigmoid colon” arranged in order from the anus are (1) (2) (3) (4). It is assumed that the order has changed. State (1) has the respective activity scores of “3, 1, 1, 1”, state (2) has the respective activity scores of “1, 3, 1, 1”, and the state (3) Assume that each has an activity score of “1, 1, 3, 1” and state (4) has each of an activity score of “1, 1, 1, 3”. In FIG. 7, in the state (1), the activity score of the ascending colon far from the anus is 3 and is high, but the activity score of the sigmoid colon near the anus is 1 and is low. Since it is estimated that the content is present at a location with a high activity score, it can be inferred that the content is present at a position far from the anus. After that, as the state changes to (2), (3), and (4), the part with a high activity score approaches the anus. From this event it can be inferred that the contents are moving towards the anus. Further, the calculation unit 12 may predict the likelihood of excretion of the content based on the estimated movement distance of the content, the time required for the movement, and the length of the digestive tract.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the system of Spiegel, as modified by Singh and Patel, according to the gastrointestinal activity scoring taught by Masamori, such that gastrointestinal sound information is used as learning input information and a value indicative of gastrointestinal activity is used as corresponding output information for generating the trained model. Singh teaches using a trained CNN to process physiological acoustic information and generate classification scores and further teaches storing acoustic slices corresponding to classification scores for retraining the CNN model, while Spiegel teaches acquiring and processing gastrointestinal acoustic signals and Masamori teaches quantitatively representing gastrointestinal activity using predetermined activity scores. One of ordinary skill in the art would have been motivated to train Singh's acoustic model using Spiegel's gastrointestinal sound information and Masamori's gastrointestinal activity indicators as corresponding output information because doing this would establish a learned relationship between detected gastrointestinal acoustic characteristics and gastrointestinal activity, which predictably permits the trained model to quantitatively determine gastrointestinal activity from subsequently acquired gastrointestinal sounds for use in assessing the user's gut condition.
Regarding claim 14, Spiegel, Singh, Patel, and Masamori teach the invention in claim 13, as discussed above, and further teach wherein the output indicator is at least one of a bowel movement state and the number of peristalsis movements of the guts per unit time (Masamori, page 8, “Therefore, the calculation unit 12 may infer the position, the moving direction, or the like of the content based on the change over time in the activity score. For example, as shown in FIG. 7, the activity scores of "ascending colon, transverse colon, descending colon, and sigmoid colon" arranged in order from the anus are (1) (2) (3) (4). It is assumed that the order has changed. State (1) has the respective activity scores of “3, 1, 1, 1”, state (2) has the respective activity scores of “1, 3, 1, 1”, and the state (3) Assume that each has an activity score of "1, 1, 3, 1" and state (4) has each of an activity score of "1, 1, 1, 3". In FIG. 7, in the state (1), the activity score of the ascending colon far from the anus is 3 and is high, but the activity score of the sigmoid colon near the anus is 1 and is low. Since it is estimated that the content is present at a location with a high activity score, it can be inferred that the content is present at a position far from the anus. After that, as the state changes to (2), (3), and (4), the part with a high activity score approaches the anus. From this event it can be inferred that the contents are moving towards the anus. Further, the calculation unit 12 may predict the likelihood of excretion of the content based on the estimated movement distance of the content, the time required for the movement, and the length of the digestive tract.”, and Masamori, page 11, “Examples of the information regarding the arithmetic unit 12 stored in the storage unit 13 include information regarding peristaltic movement, information regarding contents, information regarding the digestive tract, and the like. The information about the peristaltic movement includes, for example, a threshold of the activity score, a history of the activity score, a time of the peristaltic movement, a weighting coefficient for each position to be measured, a pattern of a combination of one or more activity scores, and the like.”).
A person of ordinary skill in the art would have found it obvious to express the output indicator as the bowel movement condition or number of peristaltic movements because such values are quantitative representations of Masamori’s determined intestinal motility behavior. Selecting and reporting these particular parameters from the set of Masamori’s disclosed gastrointestinal activity metrics would have been a routine design choice to improve usability of the monitoring result, yielding predictable results. Therefore, the claimed output indicator would have been obvious.
Regarding claim 15, Spiegel, Singh, and Patel teach the invention in claim 1, as discussed above, and further teach wherein the gut score acquiring unit and acquires the gut score (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms.”,
Singh [0054] “In an aspect, the method can include steps of: computing, at the processors, any or a combination of a mean and standard deviation of the classification scores to remove any deviation, if present, in the classification scores; and storing, in the database, an audio slice corresponding to an obtained higher classification score.” and
Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”).
Spiegel, Singh, and Patel fail to teach includes an element score acquiring unit that acquires element scores respectively for two or more evaluation elements based on the input information, using the element scores acquired by the element score acquiring unit, and the score output unit further outputs a radar chart using the element scores acquired by the element score acquiring unit.
Masamori teaches includes an element score acquiring unit that acquires element scores respectively for two or more evaluation elements based on the input information, using the element scores acquired by the element score acquiring unit, and the score output unit further outputs a radar chart using the element scores acquired by the element score acquiring unit (Masamori, page 6, “The information on excretion includes, for example, the time of excretion, the time of feeling feces, the amount of excrement (for example, a metaphorical expression based on the number of bananas), the hardness of excrement (for example, the classification of feces on the Bristol scale).”,
Masamori, page 12, “The extraction step of the computing device 32 extracts information about the activity of the peristaltic movement from the measurement information about the bioactivity acquired by the acquisition device 31. Further, the calculation step of the calculation device 32 obtains an activity score indicating the degree of activity of the peristaltic movement, based on the information regarding the activity of the peristaltic movement. The detailed steps of the acquisition device 31 and the calculation device 32 are the same as the detailed steps of the acquisition unit 11 and the calculation unit 12 of the peristaltic movement automatic measurement device 1 described above. The arithmetic unit 32 can be realized as a physical server or a virtual server, for example. The peristaltic movement automatic measurement system 30 may include a plurality of acquisition devices 31 or a plurality of arithmetic devices 32.”)”,
Masamori, page 8, “Therefore, the calculation unit 12 may infer the position, the moving direction, or the like of the content based on the change over time in the activity score. For example, as shown in FIG. 7, the activity scores of “ascending colon, transverse colon, descending colon, and sigmoid colon” arranged in order from the anus are (1) (2) (3) (4). It is assumed that the order has changed. State (1) has the respective activity scores of “3, 1, 1, 1”, state (2) has the respective activity scores of “1, 3, 1, 1”, and the state (3) Assume that each has an activity score of “1, 1, 3, 1” and state (4) has each of an activity score of “1, 1, 1, 3”. In FIG. 7, in the state (1), the activity score of the ascending colon far from the anus is 3 and is high, but the activity score of the sigmoid colon near the anus is 1 and is low. Since it is estimated that the content is present at a location with a high activity score, it can be inferred that the content is present at a position far from the anus. After that, as the state changes to (2), (3), and (4), the part with a high activity score approaches the anus. From this event it can be inferred that the contents are moving towards the anus. Further, the calculation unit 12 may predict the likelihood of excretion of the content based on the estimated movement distance of the content, the time required for the movement, and the length of the digestive tract.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the system of Spiegel, as modified by Singh and Patel, to incorporate the multiple gastrointestinal element scores taught by Masamori. Masamori teaches calculating activity scores representing gastrointestinal activity and determining respective activity scores for multiple evaluation elements, including the ascending colon, transverse colon, descending colon, and sigmoid colon, while Singh teaches generating multiple classification scores from physiological information and performing further calculations using those scores. One of ordinary skill in the art would have been motivated to use Masamori's respective gastrointestinal activity scores as element scores and combine the element scores in determining the overall gut score of the Spiegel and Singh system because the individual scores provide quantitative information concerning different aspects or locations of gastrointestinal activity, which predictably provide a more comprehensive quantitative assessment of the user's overall gastrointestinal condition. Further, presenting the respective element scores together in a graphical format would have predictably facilitated comparison and interpretation of the multiple gastrointestinal evaluation elements by the user.
Claim 20 is analogous to claims 13-15, thus claim 20 is similarly analyzed and rejected in a manner consistent with the rejection of claims 13-15.
Claims 9-12 are rejected under 35 U.S.C. 103 as being unpatentable over Spiegel et al. (International Publication No. WO2016112127A1), referred to hereinafter as Spiegel, in view of Singh et al. (U.S. Patent Publication 2021/0090734A1), referred to hereinafter as Singh, and Patel et al. (U.S. Patent Publication 2019/0371311A1), referred to hereinafter as Patel, and further in view of Kinnunen et al. (U.S. Patent Publication 2018/0042540A1), referred to hereinafter as Kinnunen.
Regarding claim 9, Spiegel, Singh, and Patel teach the invention in claim 2, as discussed above.
Spiegel, Singh, and Patel fail to explicitly teach wherein the life information contains activity status information regarding an activity status of the user.
Kinnunen teaches wherein the life information contains activity status information regarding an activity status of the user (Kinnunen [0068] “The ring or other device is configured to measure at least one biosignal of the user, and optionally the user's movements, which may be referred to as ‘raw data’ associated with the user. Further, the measured data is associated with the activity period and the rest period, as may be relevant. The term ‘activity period’ used herein refers to those periods of a day when the user is subjected to any physical activity, such as when the user is exercising, walking, playing or attending to normal day to day tasks. Further, the term ‘rest period’ used herein primarily relates to a sleeping period of the user in a day. However, the rest period may also include time period when the user is sitting or lying down to relax. The movements of the user are measured or obtained from a separate device, and used to determine whether the user is active or resting, i.e. to select the nature of the period.”).
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the invention, to configure the life information of the base reference to include activity status information as taught by Kinnunen. Kinnunen discloses determining whether a user is in an activity period or a rest period based on measured biosignals and movement data, which provides information regarding the user’s activity status. A PHOSITA would have recognized that activity state is a commonly used contextual parameter associated with physiological or user data because the interpretation and usefulness of such data depends on whether the user is active or at rest. Incorporating activity status information into life information therefore represents the predictable use of known contextual data to improve interpretation of collected user data, and involves applying a known technique to a known system to obtain predictable results. Accordingly, modifying the base reference to include activity status information as taught by Kinnunen would have been obvious.
Regarding claim 10, Spiegel, Singh, Patel, and Kinnunen teach the invention in claim 9, as discussed above, and further teach wherein the activity status information contains at least one of sleep information regarding sleep and exercise information regarding exercise (Kinnunen [0068] “The ring or other device is configured to measure at least one biosignal of the user, and optionally the user's movements, which may be referred to as ‘raw data’ associated with the user. Further, the measured data is associated with the activity period and the rest period, as may be relevant. The term ‘activity period’ used herein refers to those periods of a day when the user is subjected to any physical activity, such as when the user is exercising, walking, playing or attending to normal day to day tasks. Further, the term ‘rest period’ used herein primarily relates to a sleeping period of the user in a day. However, the rest period may also include time period when the user is sitting or lying down to relax. The movements of the user are measured or obtained from a separate device, and used to determine whether the user is active or resting, i.e. to select the nature of the period.” and
Kinnunen [0084] “In another example, the deep data analysis includes determining a sleeping pattern of the user. Specifically, the data from the motion sensor may be processed by the mobile communication device to determine the sleeping pattern of the user. For example, based on the data from the motion sensor when the user went to bed and woke up can be identified. Also, based on the data from the motion sensor how long the user slept can be determined. Therefore, the data (i.e. when the user went to bed, when the user woke up and how long the user slept) enables in defining the sleeping pattern of the user.”.).
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the invention, to configure the activity status information to include sleep information and/or exercise information as taught by Kinnunen. Kinnunen discloses determining whether a user is in an activity period, including exercising or other physical activities, and a rest period corresponding to sleeping, and further determining a sleeping pattern including sleep duration and timing. A PHOSITA would have recognized that specific activity subclasses such as sleep and exercise is a routine refinement of general activity status because these states have distinct physiological and contextual significance and are commonly recorded separately to improve interpretation of user data. Incorporating such known activity subclasses therefore represents the predictable use of known techniques to improve data granularity and usability, and involves applying a known classification scheme to a known system to obtain predictable results. Accordingly, modifying the base reference to include sleep information and/or exercise information as taught by Kinnunen would have been obvious.
Regarding claim 11, Spiegel, Singh, Patel, and Kinnunen teach the invention in claim 9, as discussed above, and further teach wherein the activity status information is information acquired by an activity tracker that acquires the level of activity of the user (Kinnunen [0068] “The ring or other device is configured to measure at least one biosignal of the user, and optionally the user's movements, which may be referred to as ‘raw data’ associated with the user. Further, the measured data is associated with the activity period and the rest period, as may be relevant. The term ‘activity period’ used herein refers to those periods of a day when the user is subjected to any physical activity, such as when the user is exercising, walking, playing or attending to normal day to day tasks. Further, the term ‘rest period’ used herein primarily relates to a sleeping period of the user in a day. However, the rest period may also include time period when the user is sitting or lying down to relax. The movements of the user are measured or obtained from a separate device, and used to determine whether the user is active or resting, i.e. to select the nature of the period.”).
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the invention, to obtain the activity status information using an activity tracker as taught by Kinnunen. Kinnunen discloses a wearable device (a ring) that measures user movement and biosignals to determine whether the user is in an activity period or rest period, which acquires a level of user activity. A PHOSITA would have recognized such a wearable movement monitoring device as an activity tracker because activity trackers conventionally measure motion and physiological signals to determine user activity level. Utilizing such a known device to acquire activity information represents the predictable use of known wearable sensing technology to gather contextual user data and would have been an obvious implementation choice for obtaining activity status information in the base system.
Regarding claim 12, Spiegel, Singh, Patel, and Kinnunen teach the invention in claim 9, as discussed above, and further teach wherein the gut score acquiring unit further includes an activity status score acquiring unit that acquires an activity status score based on the activity status information, and acquires the gut score using the activity status score acquired by the activity status score acquiring unit (Singh [0020] “An aspect of the present disclosure pertains to a system for early detection of valvular heart disorders in a patient. The system can include: a recording unit that can be configured to record a set of heart sounds of the patient and store the set of heart sounds in a database operatively coupled to the recording unit; and a control unit having processors and a memory that can be operatively coupled to the processors. The memory storing instructions can be executable by the processors to enable the control unit to: segment the set of heart sounds into a plurality of slices, each of a predetermined length, and each of the plurality of slices can include at least one audio slice; convert the at least one audio slice into corresponding spectrograms; obtain a feature vector corresponding to the spectrograms; compare the obtained feature vector with a predetermined set of feature vectors that can be stored in the database; and classify each of the spectrograms into any or a combination of a normal spectrogram and an abnormal spectrogram, based on the comparison of the obtained feature vector with the predetermined set of feature vectors, to obtain classification scores associated with the spectrograms., and Singh [0022] “In an aspect, the control unit can be configured to classify, using a deep convolutional neural network (CNN) trained model, each of the spectrograms into any or a combination of the normal spectrogram and the abnormal spectrogram.”, Singh [0054] “In an aspect, the method can include steps of: computing, at the processors, any or a combination of a mean and standard deviation of the classification scores to remove any deviation, if present, in the classification scores; and storing, in the database, an audio slice corresponding to an obtained higher classification score.” and
Spiegel [0022] “The abdominal statistics system of the present description includes multiple product configurations including a low profile rapidly deployable sensor element that can be conveniently attached to the abdomen of a patient by either a belt or adhesive attachment method. The system acquires acoustic signals as gastrointestinal (Gl) sounds, processes these signals, and provides actionable data to patients and their providers.”, and
Kinnunen [0068] “The ring or other device is configured to measure at least one biosignal of the user, and optionally the user's movements, which may be referred to as ‘raw data’ associated with the user. Further, the measured data is associated with the activity period and the rest period, as may be relevant. The term ‘activity period’ used herein refers to those periods of a day when the user is subjected to any physical activity, such as when the user is exercising, walking, playing or attending to normal day to day tasks. Further, the term ‘rest period’ used herein primarily relates to a sleeping period of the user in a day. However, the rest period may also include time period when the user is sitting or lying down to relax. The movements of the user are measured or obtained from a separate device, and used to determine whether the user is active or resting, i.e. to select the nature of the period.” and Kinnunen [0092] “In an embodiment, the mobile communication device is configured to calculate a readiness score for assessing readiness of the user. Specifically, based on long data, trends, cross-correlation analysis of the deep data analysis (i.e. heart rate variability, hypnogram, stress level and the like) the readiness score is calculated. Further, the long data, trends, cross-correlation analysis may be associated with a time period (for example a day, a week or a month) for which the deep data analysis is performed. Therefore, the measured user movements, and biosignals such as heart rate, sleep factor, heart rate variability and stress level for such time period are correlated to calculate the readiness score and thereby assessing readiness of the user.”).
A person of ordinary skill in the art would have found it obvious to modify Spiegel’s gastrointestinal monitoring system, which processes abdominal acoustic signals to provide actionable physiological data, by incorporating a score derived from user activity status as taught by Kinnunen and by applying a classification and score framework from Singh’s. Singh teaches generating quantitative classification scores from physiological signal features using machine learning analysis, while Kinnunen teaches calculating a physiological readiness score by correlating biosignals with activity period versus rest period information and user movement data. Because gastrointestinal motility and acoustic activity are well known to vary with physical activity state (rest versus active periods), a PHOSITA would have been motivated to incorporate an activity status score into Spiegel’s gut condition evaluation and use it as an input to the overall gut score in order to improve accuracy and contextual relevance of the physiological assessment. This represents the predictable use of known scoring techniques to enhance interpretation of physiological sensor data. Therefore, acquiring an activity status score and using it to determine a gut score would have been obvious.
Response to Arguments
Applicant’s arguments and amendments, see Remarks/Amendments submitted on 05/19/2026 with respect to the rejection of the claims have been carefully considered and is addressed below.
Claim Rejections - 35 USC § 101
Applicant's arguments have been fully considered but are not persuasive. Applicant states that amended claim 1 recites specific technological limitations, including consideration of device differences and analysis of abdominal sounds within a predetermined frequency band and predetermined time window, and therefore integrates the judicial exception into a practical application. The Examiner acknowledges that these amendments narrow the scope of the claim. However, the claim continues to recite the abstract idea of evaluating physiological information by selecting appropriate evaluation criteria based on device identifying information and determining a gut score. The additional limitations define the type of information that is collected and analyzed, and the criteria used to perform the evaluation, rather than reciting a specific improvement to computer functionality, audio signal processing technology, or another technological field.
Applicant further states that the claimed arrangement of elements is a specific technological implementation. However, claim 1 does not recite a particular signal processing algorithm, machine learning architecture, or other technological mechanism that improves the processing of abdominal sound data. Instead, the claim functionally recites analyzing recorded audio within a predetermined frequency band and predetermined time window and selecting corresponding learning information based on device identifying information to evaluate the information and determine a gut score. These limitations implement the abstract idea using generic computer components operating in their ordinary capacities. Accordingly, when considered individually and as an ordered combination, the additional elements do not integrate the judicial exception into a practical application and do not amount to significantly more than the abstract idea itself.
Claim Rejections - 35 USC § 103
Applicant's arguments have been fully considered but are not persuasive. Applicant states that Singh and Patel constitute nonanalogous art because Singh concerns heart sounds rather than abdominal sounds and Patel is not directed to acoustic medical technology. Singh is reasonably pertinent because Singh concerns the processing and evaluation of physiological acoustic signals and teaches applying a trained machine learning model to recorded physiological sounds to generate classification scores. Singh further teaches signal processing techniques including analysis over a preselected frequency range and predetermined temporal windows. Thus, although Singh analyzes heart sounds rather than gastrointestinal sounds, its teachings concerning machine learning analysis, scoring, frequency processing, and time window processing of physiological acoustic signals would reasonably have commended themselves to one of ordinary skill seeking to analyze and evaluate the gastrointestinal acoustic signals acquired by Spiegel. Patel is also reasonably pertinent to the claimed problem because Patel is relied upon for its teachings concerning acoustic model selection based on device and recording-condition metadata, rather than for generic device identification. Specifically, Patel teaches selecting an appropriate acoustic model based on metadata including device type or condition, environmental conditions, surrounding acoustics, interfering noise, and hardware and software involved in receiving audio, and further teaches selecting an acoustic model created or tuned for the corresponding device or condition. Accordingly, Singh and Patel are reasonably pertinent to the acoustic processing and device dependent model selection problems addressed by the claimed system and are properly considered in combination with Spiegel.
Applicant further states that the references fail to disclose or suggest selecting learning information corresponding to device identifying information and obtaining a gut score using abdominal sound information and the corresponding learning information. This argument is not persuasive because it does not consider the combined teachings of the references. Spiegel teaches acquiring and processing gastrointestinal acoustic signals to provide actionable information concerning a patient. Singh teaches applying previously prepared learning information, including a trained CNN model, to physiological acoustic information to generate classification scores. Patel teaches receiving device and acoustic condition metadata and selecting an acoustic model created or tuned for the corresponding device or condition. Thus, the combined teachings suggest acquiring Spiegel's gastrointestinal acoustic information, selecting corresponding learning information according to the device or recording condition information as taught by Patel, and applying trained model acoustic analysis and scoring as taught by Singh to obtain a score relating to the gastrointestinal condition. The rejection does not rely on Singh alone to teach abdominal sounds or on Patel alone to teach a gut score, instead the features result from the proposed combination of the respective teachings of Spiegel, Singh, and Patel.
Applicant's statement that the rejection is based on impermissible hindsight is also not persuasive. Spiegel provides a system for acquiring and processing gastrointestinal acoustic signals, Singh teaches a known technique for using trained machine learning models and frequency and time-window signal processing to quantitatively evaluate physiological acoustic signals, and Patel teaches a known technique for selecting an acoustic model based on device and acoustic recording conditions to account for differences affecting acoustic analysis. One of ordinary skill would have had reason to apply Singh's trained model acoustic analysis to Spiegel's gastrointestinal acoustic signals to provide automated quantitative assessment and would further have had reason to employ Patel's device dependent model selection to account for variations attributable to the acoustic acquisition device and recording conditions, which improve the reliability of the resulting acoustic analysis. Accordingly, Applicant's arguments do not overcome the prima facie case of obviousness.
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure.
Momeni et al. (U.S. Patent Publication 2019/0298295) teaches a system sense and processes a person’s gut sounds, applies the resulting digital acoustic data to a model to determine an aspect of the person’s physiological state, and presents information regarding the determined state to a user.
Tsai et al. (U.S. Patent Publication 2016/0354053 A1) teaches a physiological sound recognition system that receives a body sound, extract features, classifies them in to categories, and compares the results to normal or abnormal reference sounds to assess disease risk while filtering noise.
Inoue et al. (International Publication WO 2020/202738 A1) teaches an intestinal flora analysis system that collects fecal sample from a user for testing, uses the results to generate user specific questions, evaluates the correlation between the test results and the user’s answers, and provides personalized feedback via the user’s smartphone to help improve intestinal health.
Muir et al. (International Publication 2020/118372 A1) teaches a method of monitoring a subject’s gastrointestinal region by obtaining an abdominal signal of bowel sounds, identifying the individual bowel sounds, determining parameter values for each sound, and indicating the presence or absence of at least one GI symptom.
Spiegelet al. (CN Publication 104736043 A) teaches a multisensory wireless abdominal monitoring system that continuously monitors gastrointestinal and abdominal wall function, and generates clinically interpretable information for immediate clinical action in various inpatient and outpatient settings.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYRA R LAGOY whose telephone number is (703)756-1773. The examiner can normally be reached Monday - Friday, 8:00 am - 5:00 pm EST.
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, Kambiz Abdi can be reached at (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 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.
/K.R.L./Examiner, Art Unit 3685
/MARK HOLCOMB/Primary Examiner, Art Unit 3685
Prosecution Insights