DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application is being examined under the pre-AIA first to invent provisions.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/26/2022 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
112f Claim interpretation Arguments
Applicant asserts:
Applicant argues, on page 12, claim 2, as amended, recites a controller with commensurate structure, the claim should not invoke 35 U.S.C. 112(f).
Examiner response:
Examiner respectfully disagrees. Examiner notes the 3-prong analysis in MPEP 2181 is considered when identifying and interpreting 112(f). Regarding prong a, the claim limitation includes “configured”, which is a substitute for “means.” Regarding prong b, the term “configured to” is modified by functional language, which performs the training, pre-processing, dividing, perform a MLA, and validating. Regarding prong c, the term “configured to” is not modified by sufficient structure, material, or acts for performing the claimed function. It is not clear what component in the controller is performing the instructions stored in memory. Therefore, Applicant’s arguments is not persuasive.
112b Rejection Arguments
Applicant asserts:
Applicant argues, on page 12-13, that applicant has amended controller to recite that it is configured by instructions in the memory. Further, the controller is recited in, for example, paragraphs [0077] and [0078] as discussed above, and further in paragraph [000129].
Examiner response:
Examiner respectfully disagrees. Examiner notes the 3-prong analysis in MPEP 2181 is considered when identifying and interpreting 112(f). Regarding prong a, the claim limitation includes “configured”, which is a substitute for “means.” Regarding prong b, the term “configured to” is modified by functional language, which performs the training, pre-processing, dividing, perform a MLA, and validating. Regarding prong c, the term “configured to” is not modified by sufficient structure, material, or acts for performing the claimed function. In light of the specification, It is not clear what component in the controller is performing the instructions stored in memory. Therefore, Applicant’s arguments is not persuasive.
103 Rejection Arguments
Applicant asserts:
Applicant argues, on page 15, that one of ordinary skill in the art would have no reason at the time of the application filing to modify Andrew in view of Posner.
Examiner response:
In response to applicant’s argument that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, One of ordinary skill would have motivation to combine Andrew and Posner to modify the use of Andrew’s system to provide recommended intervention based on risk of suicide “These suggested triage points and intervention guidelines per suggested risk level” (Posner Page 4 Paragraph 1).
Applicant asserts:
Applicant argues, on page 15-16, that Martin does not teach or suggest inputting the output of an intermediate trained model into a subsequent trained model as recited in claim 2.
Examiner response:
Examiner respectfully disagrees. Examiner examines the claim limitation under BRI. Examiner interprets that the NNM contains a plurality of intermediate models, where each output from one intermediate model is passed to the next intermediate model. Martin teaches this by “each one (model) being trained on a data set in which points misclassified (or, with regression, those poorly predicted) by the previous model are given more weight.” Where the output is the data set in which points have been misclassified by previous modes
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “Controller is further configured“ in claim 2.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112a
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 23 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 23 recites the limitations “An application specific integrated circuit (ASIC) for a neural network model (NNM), the ASIC comprising: a plurality of neurons organized in an array… an input layer including input neurons … a hidden layer including hidden neurons; an output layer including output neurons… a plurality of synaptic circuits, each synaptic circuit including a memory for storing a synaptic weight, where each of the hidden neurons and output neurons includes an activation function”
Examiner notes that paragraph 000172 of Applicant’s specification recites “The NNM 1400 includes an input layer 1401, a hidden layer 1404 and an output layer 1406. The input layer 1401 includes input neurons (11 and 12) which provide input signals to the network without any processing units (processing units, described further herein are comprised of summation and activation functions)… The output layer 1406 includes output neurons (01 and 02) containing processing units (summation and activation functions) which provide the means for obtaining the final output of the neural network.” Mentions an input, hidden, output layer, and how the hidden and output neurons include an activation function. In addition, paragraph 00064 states “The controller 208 can be a general purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).” Which mentions an application specific integrated circuit.
However, Applicant’s original disclosure does not support “An application specific integrated circuit (ASIC) for a neural network model (NNM), the ASIC comprising: a plurality of neurons organized in an array… an input layer including input neurons … a hidden layer including hidden neurons; an output layer including output neurons… a plurality of synaptic circuits, each synaptic circuit including a memory for storing a synaptic weight, where each of the hidden neurons and output neurons includes an activation function”. It is not supported that the ASIC must include the layers and neurons. For examination purposes, Examiner is interpreting that the ASIC is used to implement a physical NNM with an input layer including input neurons … a hidden layer including hidden neurons; an output layer including output neurons… a plurality of synaptic circuits, each synaptic circuit including a memory for storing a synaptic weight, where each of the hidden neurons and output neurons includes an activation function…”
Claim Rejections - 35 USC § 112b
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1 and 2 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim limitation “controller” in claims 1 and 2 invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. no association between the structure and the function can be found in the specification. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
For examination purposes, “controller” will be a generic processor.
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.
Claim(s) 1, 3, and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”).
Regarding claim 1, Andrew teaches A server device comprising: a transceiver configured to receive one or more messages from a data collection engine (DCE); (Andrew Paragraph 0084; "the health care services performance analytics service provider 124 may include one or more servers including, e.g., but not limited to, web servers 136a-136c, application servers 138a-138c, coupled via, e.g., load balancer 134 and/or firewall 132, as well as a communications network 126, and one or more entity devices 106a, 106b, 106c, and 106d (collectively 106) may be client devices, which according to an exemplary embodiment, may also include, in an exemplary embodiment, a health care data capture device 116" Andrew Paragraph 0225; "These devices may include, e.g., but not limited to, a network interface card, and modems" Examiner notes that health care services performance analytics service provider/server comprises a transceiver/modem configured to receive the one or more messages/through communication network from the data collection engine/health care data capture device)
a controller operatively coupled to the transceiver; (Andrew Paragraph 0220; "The computer system 600 may include one or more processors, such as, e.g., but not limited to, processor(s) 604. The processor(s) 604 may be connected to a communication infrastructure 606" Examiner notes that computer system of health care services performance analytics service provider comprises a controller/processor coupled to transceiver)
and one or more memory sources operatively coupled to the controller, the one or more memory sources storing a trained neural network model (NNM) (Andrew Paragraph 0222; "The computer system 600 may also include, e.g., but may not be limited to, a main memory 608, random access memory (RAM), and a secondary memory 610, etc." Andrew Paragraph 0089; "the healthcare services performance analytics system 124 may include…a Bayesian inference engine 208f" Examiner notes that Bayesian inference engine/NNM is stored in one or more memory sources coupled to controller)
trained neural network model (NNM) for generating an output value corresponding to a present event based upon one or more of the identification information and position information in one or more messages, (Andrew Paragraph 0039; "method may include where the location based data may include at least one of: location based data in at least two dimensions; location based data in at least three dimensions; location based data in at least two dimensions plus time; a geosynchronous positioning satellite (GPS) data; a real time location system (RTLS) data; a radio frequency identification (RFID) data;" Andrew Paragraph 0040; "capturing the data wherein the data may include at least one of: at least one medical record…location data…temporal data…RFID" Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Examiner notes that output of NNM corresponds to/data input into a present event/real time based upon one or more of the identification information/RFID and position information/location based data in the one or more messages/data)
Andrew does not teach wherein the output value corresponds to (i) a risk of a non-fatal suicide attempt; (ii) a risk of a fatal suicide attempt; and (iii) recommended personnel to be deployed to reduce risk of a suicide outcome.
However, Posner does teach wherein the output value corresponds to (i) a risk of a non-fatal suicide attempt; (ii) a risk of a fatal suicide attempt; and (iii) recommended personnel to be deployed to reduce risk of a suicide outcome. (Posner Section "Recommended Intervention Guidelines" shows output value of assessment corresponds to a risk of a non-fatal suicide attempt/very low-low risk, a risk of a fatal suicide attempt/moderate-high risk, and recommended personnel to be deployed to reduce risk of a suicide outcome/schedule a check-in phone call to plan intervention)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew and Posner. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. One of ordinary skill would have motivation to combine Andrew and Posner to provide recommended intervention based on risk of suicide “These suggested triage points and intervention guidelines per suggested risk level” (Posner Page 4 Paragraph 1).
Regarding claim 3, Andrew teaches A method for predicting a suicide risk associated with a new event, the method comprising: storing a plurality of past events, each of the plurality of past events including a plurality of patient attributes and a quantifiable outcome; (Andrew Paragraph 0017; "capturing data associated with at least one health care services event, wherein the data may include at least one aspect of the at least one health care services event;" Andrew Paragraph 0119; "similar health care service events (such as events of similar description and/or of relatively similar completion time (e.g., operations of a particular type over the past month, etc.) may be reviewed and/or analyzed." Examiner notes that memory further store a plurality of past events/health care services event, each of the plurality of past events including a plurality of attributes/data of the event and a quantifiable outcome/completion time)
and training a neural network model (NNM) to generate a trained model, (Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Examiner notes that recommendation is output of NNM which indicates controller/processor trains NNM)
wherein the training of the NNM includes: performing pre-processing on the plurality of patient attributes for each of the plurality of past events to generate a plurality of input data sets; (Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events."
Andrew Paragraph 0190; "Normalized input data 810, which may be represented by numbers ranging from 0 to 1, may be supplied to input units of the neural network." Examiner notes that training includes preprocessing/normalizing on the plurality of attributes for each of the plurality of past events to generate a plurality of input data sets/input units)
dividing the plurality of past events into a first set of training data and a second set of validation data; (Andrew Paragraph 0191; "The neural network may be trained by a back-propagation algorithm using pairs of training input data and desired output data." Examiner notes that data/plurality of past events are divided into a first set of training data and a second set of validation data/desired output data)
iteratively performing a machine learning algorithm (MLA) to update synaptic weights of the NNM based upon the training data; (Andrew Paragraph 0190; "The weighting factors and offset values may be internal parameters of the neural network 902, which may be determined for a given set of input and output data." Andrew Paragraph 0191; "The neural network may be trained by a back-propagation algorithm… By iteration of this procedure in a random sequence for the same set of input and output data" Examiner notes that back propagation algorithm/machine learning algorithm is iteratively performed to update synaptic weights/weighting factors of the NNM based upon the training data/given set of input and output data)
and validating the NNM based upon the second set of validation data, (Andrew Paragraph 0191; "Two different basic processes may be involved in the neural network 902, namely, a training process and a testing process. The neural network may be trained by a back-propagation algorithm using pairs of training input data and desired output data." Examiner notes that testing process/validating the NNM based upon the second set of validation data/desired output data)
receiving a plurality of input attributes of the new event; (Andrew Paragraph 0189; "A first layer, input layer 804, may be assigned to accept a set of data representing an input" Examiner notes that input layer receives/accept a plurality/set of input attributes/data representing an input of the new event)
performing pre-processing on the plurality of input attributes to generate an input data set; (Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Andrew Paragraph 0190; "Normalized input data 810, which may be represented by numbers ranging from 0 to 1, may be supplied to input units of the neural network." Examiner notes that training includes preprocessing/normalizing on the plurality of attributes for each of the plurality of past events to generate a plurality of input data sets/input units)
generating an output value from a trained model based upon the input data set; (Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Examiner notes that output/classification is generated from a trained model/NNM based upon the input data set/known data)
Andrew does not teach and classifying the output value into a suicide risk category to predict an outcome.
However, Posner does teach and classifying the output value into a suicide risk category to predict an outcome. (Posner Section "Recommended Intervention Guidelines" shows a classifying the output value/triage points into a suicide risk category to predict an outcome/intervention)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew and Posner. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. One of ordinary skill would have motivation to combine Andrew and Posner to provide recommended intervention based on risk of suicide “These suggested triage points and intervention guidelines per suggested risk level” (Posner Page 4 Paragraph 1).
Regarding claim 9, Andrew teaches The method of claim 3, wherein one or more of the plurality of input attributes of the new event is geospatial data obtained from a location device proxy associated with a participant in the new event within an interval of date and time of the new event. (Andrew Paragraph 0021; "may include at least one of tracking the data, collecting the data; aggregating the data; storing the data; transmitting the data; capturing the data over time; capturing the data by location; and/or capturing the data by location and time." Andrew Paragraph 0219; "proxy servers" Examiner notes that geospatial data/capturing the data by location obtained from a location device proxy/proxy servers associated with a participant in the new event within an interval of date and time of the event/use of health care resources)
Regarding claim 22, Andrew does not teach The method of claim 3, wherein the output value includes one or more of: (a) armed forces status an individual associated with the new event, including whether the individual is a combat veteran; (b) a probability of transition of the individual from active duty status to veteran status in last predetermined interval of time; (c) a probability of lethal means access of the individual and use of strategies to reduce time to lethal means access; and (d) a probability of the individual adopting strategies to reduce time to lethal means access.
However, Posner does teach The method of claim 3, wherein the output value includes one or more of: (a) armed forces status an individual associated with the new event, including whether the individual is a combat veteran; (b) a probability of transition of the individual from active duty status to veteran status in last predetermined interval of time; (c) a probability of lethal means access of the individual and use of strategies to reduce time to lethal means access; and (d) a probability of the individual adopting strategies to reduce time to lethal means access. (Posner Page 3 Section "Potential Lethality" shows a probability of lethal means access of the individual; Posner Page 4 shows use of strategies to reduce time to lethal means access)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew and Posner. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. One of ordinary skill would have motivation to combine Andrew and Posner to provide recommended intervention based on risk of suicide “These suggested triage points and intervention guidelines per suggested risk level” (Posner Page 4 Paragraph 1).
Claim(s) 2 are rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Martin et al; “Ensemble Learning” (hereinafter Martin).
Regarding claim 2, Andrew teaches The server device of claim 1, wherein: the one or more memory sources further store a plurality of past events, each of the plurality of past events including a plurality of attributes and a quantifiable outcome; (Andrew Paragraph 0017; "capturing data associated with at least one health care services event, wherein the data may include at least one aspect of the at least one health care services event;" Andrew Paragraph 0119; "similar health care service events (such as events of similar description and/or of relatively similar completion time (e.g., operations of a particular type over the past month, etc.) may be reviewed and/or analyzed." Examiner notes that memory further store a plurality of past events/health care services event, each of the plurality of past events including a plurality of attributes/data of the event and a quantifiable outcome/completion time)
and the controller is further configured according to instructions in the one or more memory sources to: train a NNM to generate the trained NNM, (Andrew Paragraph 0046; "executed on a processor may perform a method for improving the delivery of healthcare services, where the method may include: … recommending at least one course of action based on the at least one aspect having the correlation and the cause and effect relationship to the at least one category." Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Andrew Paragraph 0223; “In alternative exemplary embodiments, secondary memory 610 may include other similar devices for allowing computer programs or other instructions to be loaded into computer system 600.” Examiner notes that recommendation is output of NNM which indicates controller/processor trains NNM)
wherein the training of the NNM includes: perform pre-processing on the plurality of attributes for each of the plurality of past events to generate a plurality of input data sets; (Andrew Paragraph 0190; "Normalized input data 810, which may be represented by numbers ranging from 0 to 1, may be supplied to input units of the neural network." Examiner notes that training includes preprocessing/normalizing on the plurality of attributes for each of the plurality of past events to generate a plurality of input data sets/input units)
divide the plurality of past events into a first set of training data and a second set of validation data; (Andrew Paragraph 0191; "The neural network may be trained by a back-propagation algorithm using pairs of training input data and desired output data." Examiner notes that data/plurality of past events are divided into a first set of training data and a second set of validation data/desired output data)
iteratively perform a machine learning algorithm (MLA) to update synaptic weights of the NNM based upon the training data; (Andrew Paragraph 0190; "The weighting factors and offset values may be internal parameters of the neural network 902, which may be determined for a given set of input and output data." Andrew Paragraph 0191; "The neural network may be trained by a back-propagation algorithm… By iteration of this procedure in a random sequence for the same set of input and output data" Examiner notes that back propagation algorithm/machine learning algorithm is iteratively performed to update synaptic weights/weighting factors of the NNM based upon the training data/given set of input and output data)
and validate the NNM based upon the second set of validation data, (Andrew Paragraph 0191; "Two different basic processes may be involved in the neural network 902, namely, a training process and a testing process. The neural network may be trained by a back-propagation algorithm using pairs of training input data and desired output data." Examiner notes that testing process/validating the NNM based upon the second set of validation data/desired output data)
Andrew does not teach wherein the trained NNM includes a plurality of intermediate trained models, wherein an intermediate output of each intermediate trained model is input into a subsequent intermediate trained model.
However, Martin does teach wherein the trained NNM includes a plurality of intermediate trained models, wherein an intermediate output of each intermediate trained model is input into a subsequent intermediate trained model. (Martin Page 9 Paragraph 2; "One first creates a ‘weak’ classifier, that is, it suffices that its accuracy on the training set is only slightly better than random guessing. A succession of models are built iteratively, each one being trained on a data set in which points misclassified (or, with regression, those poorly predicted) by the previous model are given more weight. Finally, all of the successive models are weighted according to their success and then the outputs are combined using voting (for classification) or averaging (for regression), thus creating a final model." Examiner notes that trained NNM/final model includes a plurality of intermediate trained models/succession of models, wherein an intermediate output of each intermediate trained model/data set in which points misclassified is input into a subsequent intermediate trained model/each model being trained from previous model)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Martin. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Martin teaches ensemble learning technique called Boosting. One of ordinary skill would have motivation to combine Andrew, Posner, and Martin to combine weak models to generate a stronger model “The original boosting algorithm combined three weak learners to generate a strong learner.” (Martin Page 2 Paragraph 2).
Claim(s) 4 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Rubendran et al; US 10593426 B2 (hereinafter “Rubendran”).
Regarding claim 4, Andrew does not teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is social determinants of health (SDoH) related data.
However, Rubendran does teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is social determinants of health (SDoH) related data. (Rubendran Column 3 Paragraph 3; "The EMR non-clinical data may include, but is not limited to, social, behavioral, lifestyle, and economic data; …" Examiner notes that input attributes is social determinants of health related data/non-clinical data)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Rubendran. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Rubendran teaches a holistic hospital patient care and management system. One of ordinary skill would have motivation to combine Andrew, Posner, and Rubendran to reduce hospital readmission rates “The system 10 is most suited for identifying particular patients who require intensive inpatient and/or outpatient care to avert serious detrimental effects of certain diseases and to reduce hospital readmission rates.” (Rubendran Column 3 Paragraph 1).
Regarding claim 5, Andrew does not teach The method of claim 4, wherein the SDoH data includes one or more of zip code related data, employment data, financial data, education level data, housing status, food and access status.
However, Rubendran does teach The method of claim 4, wherein the SDoH data includes one or more of zip code related data, employment data, financial data, education level data, housing status, food and access status. (Rubendran Column 3 Paragraph 3; "The EMR non-clinical data may include, but is not limited to, social, behavioral, lifestyle, and economic data; …, type and nature of employment; … location of residences and frequency of residence changes over a specific time period; … diet; … education; proximity and number of family or care-giving assistants; address; housing status; social media data; and educational level.")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Rubendran. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Rubendran teaches a holistic hospital patient care and management system. One of ordinary skill would have motivation to combine Andrew, Posner, and Rubendran to reduce hospital readmission rates “The system 10 is most suited for identifying particular patients who require intensive inpatient and/or outpatient care to avert serious detrimental effects of certain diseases and to reduce hospital readmission rates.” (Rubendran Column 3 Paragraph 1).
Claim(s) 6 is rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of David et al; US 20110046920 A1 (hereinafter “David”).
Regarding claim 6, Andrew does not teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is data from court or law enforcement databases.
However, David does teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is data from court or law enforcement databases. (David Paragraph 0146; “The Algorithm 601 would search federal and state databases for criminal history, any incidents reported to online dating sites regarding the person's profile, local law enforcement databases for reports of domestic abuse or outstanding warrants, etc.”)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and David. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. David teaches a system for anticipating a potentially threatening or dangerous incident and providing varying levels of response to a user. One of ordinary skill would have motivation to combine Andrew, Posner, and David to reduce the likelihood of an incident, mitigate the effects, and bring peace “An intelligent system which can assess risk, provide a measurable rating, and recommendations to reduce that risk, would reduce the likelihood of an incident, mitigate the effect if one does occur, and bring peace and well-being to the user.” (David Paragraph 0005).
Claim(s) 7 is rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Konstantinos et al; “Relationship of suicide rates with climate and economic variables in Europe during 2000– 2012” (hereinafter “Konstantinos”).
Regarding claim 7, Andrew does not teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event includes economics and meteorological data within an interval of date and time of the new event.
However, Konstantinos does teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event includes economics and meteorological data within an interval of date and time of the new event. (Konstantinos Page 2 Paragraph 5; "The statistical analysis included cluster analysis of variables (separately for economic and climate variables) and principal component analysis to identify prominent variables to be used afterwards in a categorical regression to test for the relationship of suicidal rates (dependent variables—DV) with economic and climate components (independent variables—IV)." Examiner notes that input attributes includes economics and meteorological data/economic and climate components within an inter of date and time of new event/2000-2012)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Konstantinos. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Konstantinos teaches correlation between suicide rates with economic and climate variables. One of ordinary skill would have motivation to combine Andrew, Posner, and Konstantinos to utilize potentially different underlying mechanisms for males and females pertaining to interaction with different stimuli “The current study is the first successful attempt to explain the large differences between European countries in terms of suicidal rates. It also suggests the presence of different underlying mechanisms for males and females pertaining to the interaction with different qualities of environmental stimuli.” (Konstantinos Page 4 Paragraph 3).
Claim(s) 8 is rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Robert et al; “Genetic and Environmental Contributions Self-Reported Thoughts of Self-Harm and Suicide” (hereinafter “Robert”).
Regarding claim 8, Andrew does not teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is genomics data obtained from a specimen from a participant in the new event within an interval of date and time of the new event.
However, Robert does teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is genomics data obtained from a specimen from a participant in the new event within an interval of date and time of the new event. (Robert Page 4 Paragraph 2; "For this study, we assessed a sample of Dutch twin pairs (mean age = 27.5, SD = 12.21) who reported on their SHSB every 2–3 years for six sampling periods between 1991 and 2009." Examiner notes that input attributes is genomic data obtained from a specimen from a participant/Dutch twin pairs in the new event within an interval of date and time of the new event/data collection)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Robert. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Robert teaches correlation between suicide rates with gene expression. One of ordinary skill would have motivation to combine Andrew, Posner, and Robert to utilize genetic data in determining likelihood of suicidal ideation and attempts “Our findings that the architecture of SHSB in males is equal part genes and unique environment are consistent with what has been reported about suicidal ideation and attempts in males.. Suicidal behavior has been reported to be familial in males and males who engage in suicidal behavior are commonly also affected by a unique environmental moderator like loss of a job, loss of a spouse, or injury.” (Robert Page 7 Paragraph 2).
Claim(s) 10 is rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Benjamin et al; “Novel Use of Natural Language Processing (NLP) to Predict Suicidal Ideation and Psychiatric Symptoms in a Text-Based Mental Health Intervention in Madrid” (hereinafter “Benjamin”).
Regarding claim 10, Andrew teaches data from [text based narratives] stored on a computer readable medium. (Andrew Paragraph 0222; "The computer system 600 may also include, e.g., but may not be limited to, a main memory 608, random access memory (RAM), and a secondary memory 610, etc." Examiner notes that data is stored on a computer readable medium/main memory)
Andrew does not teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is natural language processing (NLP) data from text based narratives
However, Benjamin does teach The method of claim 3, wherein one or more of the plurality of input attributes of the new event is natural language processing (NLP) data from text based narratives (Benjamin Page 2 Paragraph 6; "2.2. Description of Texting Intervention. The intervention was comprised of therapeutic reminders delivered by SMS messages that were sent out two days, seven days, 15 days, and monthly after hospital discharge. Each text message also provided a link to a mobile application that contained a questionnaire eliciting responses related to the patients’ sources of help, evidence-based self-help strategies, and structured interview questions related to suicidal ideation, psychiatric symptoms, and satisfaction with care. Participants were also asked one unstructured, open-ended question related to their current mental state, “how are you feeling today?, ”and were encouraged to report on their progress since the hospitalization. Participants were able to enter responses to questionnaires up to once per day and were instructed to answer as often as they wished." Examiner notes that input attributes is NLP data from text based narratives/SMS messages)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Benjamin. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Benjamin teaches using NPL and machine learning to predict suicidal ideation. One of ordinary skill would have motivation to combine Andrew, Posner, and Benjamin to utilize NLP and machine learning to effectively predict suicidal ideation “Our analysis found that a NLP-based machine learning model using only open-ended texts from patients had a reasonably high predictive value for suicidal ideation and heightened psychiatric symptoms. The structured data per-formed better, with higher PPV and better sensitivity and specificity, but with the tradeoff that these structured data require significantly more time from the respondent. These findings suggest that even data obtained from free-text responses to general questions about patients’ mental state could be used to effectively predict suicidal ideation using computational analytics such as NLP.” (Benjamin Page 5 Paragraph 4)
Claim(s) 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Perry et al; US 20190027240 A1 (hereinafter “Perry”) in further view of Valery et al; US 7627475 B2 (hereinafter “Valery”).
Regarding claim 12, Andrew does not teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis, where the text analysis includes one or more of statistical methods, natural language processing (NLP), data science / machine learning based techniques, word databases, and taxonomies to determining meaning of the text.
However, Perry does teach [The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis], where the text analysis includes one or more of statistical methods, natural language processing (NLP), data science / machine learning based techniques, word databases, and taxonomies to determining meaning of the text. (Perry Paragraph 0265; "the system converts the statement into a selection criterion, based on available natural language processing tools 822, optionally augmented by machine learning 826." Perry Paragraph 0266; "and extraction of meaning from the words." Examiner notes that text analysis includes machine learning based techniques/augmented by machine learning to determine meaning of the text/meaning from the words)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Perry. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Perry teaches a system for analyzing and/or using information from a plurality of users with the use of delivery devices for active agents. One of ordinary skill would have motivation to combine Andrew, Posner, and Perry to allow users to provide input to the model through speech “the field of natural language user interfaces has achieved several widely-deployed implementations capable of speech to text conversion, together with assignment of sufficient meaning to the extracted text to allow machine-supplied responses.” (Perry Paragraph 0266)
Andrew in view of Posner in further view of Perry does not teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis
However, Valery does teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis (Valery Column Paragraph 1; "The method also includes extracting acoustic features from the speech signals" Examiner notes that pre-processing includes extracting acoustic properties/features from an audio signal/speech signal)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Perry, and Valery. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Perry teaches a system for analyzing and/or using information from a plurality of users with the use of delivery devices for active agents. Valery teaches a detecting emotional states using statistics. One of ordinary skill would have motivation to combine Andrew, Posner, Perry, and Valery to allow users to recognize the emotional states of patients and act accordingly “Recognizing emotions may help call-center personnel deal with angry or emotional callers. Knowing a customer or caller's emotional state may help operators deal with callers who are angry or excited. Conversely, detecting little emotion in a caller in whom excitement or happiness is expected may also prove useful. Detecting other emotions, such as nervousness or fear, may alert businesses to persons who may be attempting to cheat or defraud them. There are many business uses for a system or a method that detects emotions in persons.” (Valery Column 4 Paragraph 3)
Regarding claim 13, Andrew does not teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis where the extracting text from audio signals to extract text analysis includes one or more of sentence detection, tokenization, lemmatization, cleaning, categorization, classification, sentiment analysis, named entity recognition, clustering, matrix factorization, latent semantic indexing, part of speech tagging, parse labeling indicating how a token is used in a sentence, phrase or utterance, dependency analysis showing how tokens are interrelated, feature extraction from raw linguistic analysis, grouping similar topics, classifying topic of text, and determining the frequency or occurrence of topics.
However, Perry does teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis, where the extracting text from audio signals to extract text analysis includes one or more of sentence detection, tokenization, lemmatization, cleaning, categorization, classification, sentiment analysis, named entity recognition, clustering, matrix factorization, latent semantic indexing, part of speech tagging, parse labeling indicating how a token is used in a sentence, phrase or utterance, dependency analysis showing how tokens are interrelated, feature extraction from raw linguistic analysis, grouping similar topics, classifying topic of text, and determining the frequency or occurrence of topics. (Perry Paragraph 0120; "tokens expressed in the inputs (such as words, phrases, tags such as hashtags, emojis, emoticons, and the like) are provided as inputs to a machine learning implementation" Examiner notes that tokens expressed in the inputs is tokenization)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Perry. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Perry teaches a system for analyzing and/or using information from a plurality of users with the use of delivery devices for active agents. One of ordinary skill would have motivation to combine Andrew, Posner, and Perry to allow users to provide input to the model through speech “the field of natural language user interfaces has achieved several widely-deployed implementations capable of speech to text conversion, together with assignment of sufficient meaning to the extracted text to allow machine-supplied responses.” (Perry Paragraph 0266)
Andrew in view of Posner in further view of Perry does not teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis
However, Valery does teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting text from audio signals to extract text analysis (Valery Column Paragraph 1; "The method also includes extracting acoustic features from the speech signals" Examiner notes that pre-processing includes extracting acoustic properties/features from an audio signal/speech signal)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Perry, and Valery. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Perry teaches a system for analyzing and/or using information from a plurality of users with the use of delivery devices for active agents. Valery teaches a detecting emotional states using statistics. One of ordinary skill would have motivation to combine Andrew, Posner, Perry, and Valery to allow users to recognize the emotional states of patients and act accordingly “Recognizing emotions may help call-center personnel deal with angry or emotional callers. Knowing a customer or caller's emotional state may help operators deal with callers who are angry or excited. Conversely, detecting little emotion in a caller in whom excitement or happiness is expected may also prove useful. Detecting other emotions, such as nervousness or fear, may alert businesses to persons who may be attempting to cheat or defraud them. There are many business uses for a system or a method that detects emotions in persons.” (Valery Column 4 Paragraph 3)
Claim(s) 14 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Valery et al; US 7627475 B2 (hereinafter “Valery”).
Regarding claim 14, Andrew does not teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting acoustic properties from an audio signal.
However, Valery does teach The method of claim 3, wherein the performing of the pre-processing on the plurality of patient attributes further includes extracting acoustic properties from an audio signal. (Valery Column Paragraph 1; "The method also includes extracting acoustic features from the speech signals" Examiner notes that pre-processing includes extracting acoustic properties/features from an audio signal/speech signal)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Valery. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. One of ordinary skill would have motivation to combine Andrew, Posner, and Valery to allow users to recognize the emotional states of patients and act accordingly “Recognizing emotions may help call-center personnel deal with angry or emotional callers. Knowing a customer or caller's emotional state may help operators deal with callers who are angry or excited. Conversely, detecting little emotion in a caller in whom excitement or happiness is expected may also prove useful. Detecting other emotions, such as nervousness or fear, may alert businesses to persons who may be attempting to cheat or defraud them. There are many business uses for a system or a method that detects emotions in persons.” (Valery Column 4 Paragraph 3)
Regarding claim 15, Andrew does not teach The method of claim 14, wherein the acoustic properties include one or more of intonation, pitch, perturbation, loudness, format frequencies and subharmonics.
However, Valery does teach The method of claim 14, wherein the acoustic properties include one or more of intonation, pitch, perturbation, loudness, format frequencies and subharmonics. (Valery Column 6 Paragraph 4; "acoustic parameters, such as fundamental frequency (pitch), energy, formants, speaking rate, and the like, are extracted" Examiner notes that acoustic properties/parameters includes pitch)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Valery. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. One of ordinary skill would have motivation to combine Andrew, Posner, and Valery to allow users to recognize the emotional states of patients and act accordingly “Recognizing emotions may help call-center personnel deal with angry or emotional callers. Knowing a customer or caller's emotional state may help operators deal with callers who are angry or excited. Conversely, detecting little emotion in a caller in whom excitement or happiness is expected may also prove useful. Detecting other emotions, such as nervousness or fear, may alert businesses to persons who may be attempting to cheat or defraud them. There are many business uses for a system or a method that detects emotions in persons.” (Valery Column 4 Paragraph 3)
Claim(s) 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Valery et al; US 7627475 B2 (hereinafter “Valery”) in further view of Terrance et al; US 20160351074 A1 (hereinafter “Terrance”).
Regarding claim 16, Andrew does not teach The method of claim 14, wherein the acoustic properties include non-speech sounds associated with emotional states.
However, Terrance does teach The method of claim 14, wherein the acoustic properties include non-speech sounds associated with emotional states. (Terrance Paragraph 0227; "non-vocal sounds related to respiration and digestion, such as coughing, sneezing, and burping. Fixed-signal sounds are related to voluntary reactions to the environment and include laughing, moaning, sighing, and lip smacking." Examiner notes that acoustic properties include non-speech sounds/non-vocal sounds associated with emotional states/voluntary reactions)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Valery, and Terrance. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. Terrance teaches a method to analyze a sound signal to determine at least one characteristic of the sound signal. One of ordinary skill would have motivation to combine Andrew, Posner, Valery, and Terrance to reduce the need for human classification of child speech “This methodology may reduce the need for human classification of child speech.” (Terrance Paragraph 0321)
Regarding claim 17, Andrew does not teach The method of claim 16, wherein the emotional states include crying, laughing, and sighing.
However, Terrance does teach The method of claim 16, wherein the emotional states include crying, laughing, and sighing. (Terrance Paragraph 0227; "voluntary reactions to the environment and include laughing, moaning, sighing, and lip smacking." Terrance Paragraph 0229; " Although not performed in this specific method, the analysis of cries according to the described techniques may be used to detect disorders or diseases, since crying is also another means of communication in a baby's life." Examiner notes that emotional states include crying, laughing, and sighing)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Valery, and Terrance. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. Terrance teaches a method to analyze a sound signal to determine at least one characteristic of the sound signal. One of ordinary skill would have motivation to combine Andrew, Posner, Valery, and Terrance to reduce the need for human classification of child speech “This methodology may reduce the need for human classification of child speech.” (Terrance Paragraph 0321)
Regarding claim 18, Andrew does not teach The method of claim 14, wherein the acoustic properties include non-speech sounds associated with gender.
However, Terrance does teach The method of claim 14, wherein the acoustic properties include non-speech sounds associated with gender. (Terrance Paragraph 0107; "includes characteristics of sounds of an adult male and an adult female model that includes characteristics of sounds of an adult female." Examiner notes that acoustic properties include non-speech sounds associated with gender/male or female)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Valery, and Terrance. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. Terrance teaches a method to analyze a sound signal to determine at least one characteristic of the sound signal. One of ordinary skill would have motivation to combine Andrew, Posner, Valery, and Terrance to reduce the need for human classification of child speech “This methodology may reduce the need for human classification of child speech.” (Terrance Paragraph 0321)
Regarding claim 19, Andrew does not teach The method of claim 14, wherein the acoustic properties include non-speech sounds associated with cognitive and physical performance.
However, Terrance does teach The method of claim 14, wherein the acoustic properties include non-speech sounds associated with cognitive and physical performance. (Terrance Paragraph 0149; "Vegetative-sound includes non-vocal sounds related to respiration and digestion, such as coughing, sneezing, and burping." Examiner notes that acoustic properties include non-speech sounds associated with cognitive and physical performance/vegetative sound)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Valery, and Terrance. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. Terrance teaches a method to analyze a sound signal to determine at least one characteristic of the sound signal. One of ordinary skill would have motivation to combine Andrew, Posner, Valery, and Terrance to reduce the need for human classification of child speech “This methodology may reduce the need for human classification of child speech.” (Terrance Paragraph 0321)
Claim(s) 20 is rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Valery et al; US 7627475 B2 (hereinafter “Valery”) in further view of Ruhi et al; US 20180061421 A1 (hereinafter “Ruhi”).
Regarding claim 20, Andrew does not teach The method of claim 14, wherein the acoustic properties include identification of discriminating accents within a language.
However, Ruhi does teach The method of claim 14, wherein the acoustic properties include identification of discriminating accents within a language. (Ruhi Paragraph 0023; "an accent for a specific user (e.g., southern, immigrant, Indian, Chinese, German, French, etc.).")
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, Valery, and Ruhi. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Valery teaches a detecting emotional states using statistics. Ruhi teaches using an accent detection model. One of ordinary skill would have motivation to combine Andrew, Posner, Valery, and Ruhi to utilize user background characteristic models to identify additional traits and characteristics to help build a profile “Other user background characteristic models may also be used to identify additional background traits and characteristics of a user as more fully described below. This information may be compiled into a voice-based profile for each specific user of a group of users.” (Ruhi Paragraph 0023)
Claim(s) 21 is rejected under 35 U.S.C. 103 as being unpatentable over Andrew et al; US 20090099862 A1 (hereinafter “Andrew”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Newton et al; US 20170258389 A1 (hereinafter “Newton”)
Regarding claim 21, Andrew does not teach The method of claim 3, wherein the plurality of input attributes include whether an individual associated with the new event is an active service member or a veteran.
However, Newton does teach The method of claim 3, wherein the plurality of input attributes include whether an individual associated with the new event is an active service member or a veteran. (Newton Paragraph 0025; "prototypes of BCP 100 may be used to help diagnose, track, and manage PTSD in active and veteran troops. BCP 100 may also be used to construct systems for suicide prevention and the early detection of depression." Examiner notes that input attributes include whether an individual associated with the new event is an active service member or a veteran/active and veteran troops)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Andrew, Posner, and Newton. Andrew teaches a method for improving the delivery of healthcare services. Posner teaches how to determine risk level of suicide and appropriate intervention. Newton teaches method for detecting neurological disorders. One of ordinary skill would have motivation to combine Andrew, Posner, and Newton to diagnose, trach and manage PTSD in active and veteran officers “BCP 100 may be used to help diagnose, track, and manage PTSD in active and veteran troops.” (Newton Paragraph 0025)
Claim(s) 23 is rejected under 35 U.S.C. 103 as being unpatentable over F. Merrikh Bayat; “Implementation of Multilayer Perceptron Network with Highly Uniform Passive Memristive Crossbar Circuits” (hereinafter “Bayat”) in view of Posner et al; “COLUMBIA-SUICIDE SEVERITY RATING SCALE” (hereinafter “Posner”) in further view of Newton et al; US 20170258389 A1 (hereinafter “Newton”) in further view of Andrew et al; US 20090099862 A1 (hereinafter “Andrew”)
Regarding claim 23, Bayat teaches An application specific integrated circuit (ASIC) for a neural network model (NNM), the ASIC comprising: a plurality of neurons organized in an array, wherein the plurality of neurons includes (Bayat Page 4 Paragraph 4; “Two 20×20 crossbar circuits were packaged and integrated with discrete CMOS components on two printed circuit boards (Fig. S2b) to implement the multilayer perceptron (MLP) (Fig. 4).”)
an input layer including input neurons which provide input data set signals [associated with an event to the NNM, wherein the event is a quantifiable outcome associated with a suicide risk, and the plurality of input data set signals include a plurality of plurality of patient attributes associated with the quantifiable outcome]; (Bayat Page 4 Paragraph 4; “The MLP network features 16 inputs, 10 hidden-layer neurons, and 4-outputs, which is sufficient to perform classification of 4×4-pixel black-and-white patterns (Fig. 4d) into 4 classes.” Examiner notes that 16 inputs is the input layers including 16 input neurons which provide input data signals)
PNG
media_image1.png
652
644
media_image1.png
Greyscale
a hidden layer including hidden neurons; (Bayat Page 4 Paragraph 4; “The MLP network features 16 inputs, 10 hidden-layer neurons, and 4-outputs, which is sufficient to perform classification of 4×4-pixel black-and-white patterns (Fig. 4d) into 4 classes.” Examiner notes that 10 hidden layers is hidden layers)
an output layer including output neurons which provide output data set signals; and (Bayat Page 4 Paragraph 4; “The MLP network features 16 inputs, 10 hidden-layer neurons, and 4-outputs, which is sufficient to perform classification of 4×4-pixel black-and-white patterns (Fig. 4d) into 4 classes.” Examiner notes that 4 outputs is an output layer with 4 output neurons which provide output data set signals)
a plurality of synaptic circuits, each synaptic circuit including a memory for storing a synaptic weight, (Bayat Page 5 Paragraph 1; “The integrated memristors implement synaptic weights, while discrete CMOS circuitry implements switching matrix and neurons. Each synaptic weight is implemented with a pair of memristors, so that 17×20 and 11×8 contiguous subarrays” Examiner notes that integrated memristors is a plurality of synaptic circuits where each circuit includes a memory for storing synaptic weight)
where each of the hidden neurons and output neurons includes an activation function, the activation function is one of: (1) the sigmoid function f(x)=1/(1+e-x); (2) the hyperbolic tangent function f(x)= (e2x-1)/(e2x+1); and (3) a linear function f(x)=x, wherein x is a summation of input neurons biased by the synoptic weights, (Bayat Page 5 Paragraph 2; “The neuron circuitry is comprised of three distinct stages … The operational amplifier’s output in this stage is allowed to saturate for large input currents, thus effectively implementing tanh-like activation function.” Examiner notes that each of the hidden neurons and output neurons (neurons included in neuron circuitry) includes an activation function (implements tanh-like activation function), wherein the activation function is a hyperbolic tangent function)
Bayat does not teach input data [set signals] associated with an event to the NNM, wherein the event is a quantifiable outcome associated with a suicide risk, and the plurality of input data set signals include a plurality of plurality of patient attributes associated with the quantifiable outcome
However, Posner does teach input data [set signals] associated with an event to the NNM, wherein the event is a quantifiable outcome associated with a suicide risk, and the plurality of input data set signals include a plurality of plurality of patient attributes associated with the quantifiable outcome (Posner Section "Recommended Intervention Guidelines" shows inputs of the assessment to obtain output value of assessment corresponds to a risk of a non-fatal suicide attempt/very low-low risk, a risk of a fatal suicide attempt/moderate-high risk, and recommended personnel to be deployed to reduce risk of a suicide outcome/schedule a check-in phone call to plan intervention)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Bayat and Posner. Bayat teaches an implementation of Multilayer Perceptron Network with Highly Uniform Passive Memristive Crossbar Circuits. Posner teaches how to determine risk level of suicide and appropriate intervention. One of ordinary skill would have motivation to combine Bayat and Posner to provide recommended intervention based on risk of suicide “These suggested triage points and intervention guidelines per suggested risk level” (Posner Page 4 Paragraph 1).
Bayat in view of Posner does not teach wherein values of the synaptic weights are obtained by training the NNM, the training of the NNM includes:
performing pre-processing on the plurality of input attributes for each of a plurality of past events to generate a plurality of input data sets;
dividing the plurality of past events into a first set of training data and a second set of validation data;
iteratively performing a machine learning algorithm (MLA) to update values of the synaptic weights of the NNM based upon the training data;
and validating the NNM based upon the second set of validation data.
However, Andrew does teach wherein values of the synaptic weights are obtained by training the NNM, the training of the NNM includes: (Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Examiner notes that recommendation is output of NNM which indicates controller/processor trains NNM; training the model means obtaining synaptic weights for the NNM)
performing pre-processing on the plurality of input attributes for each of a plurality of past events to generate a plurality of input data sets; (Andrew Paragraph 0189; "The networks may be first trained by presentation of known data about objects or classes of events, and then may be applied to distinguish between unknown objects or classes of events." Andrew Paragraph 0190; "Normalized input data 810, which may be represented by numbers ranging from 0 to 1, may be supplied to input units of the neural network." Examiner notes that training includes preprocessing/normalizing on the plurality of attributes for each of the plurality of past events to generate a plurality of input data sets/input units)
dividing the plurality of past events into a first set of training data and a second set of validation data; (Andrew Paragraph 0191; "The neural network may be trained by a back-propagation algorithm using pairs of training input data and desired output data." Examiner notes that data/plurality of past events are divided into a first set of training data and a second set of validation data/desired output data)
iteratively performing a machine learning algorithm (MLA) to update values of the synaptic weights of the NNM based upon the training data; (Andrew Paragraph 0190; "The weighting factors and offset values may be internal parameters of the neural network 902, which may be determined for a given set of input and output data." Andrew Paragraph 0191; "The neural network may be trained by a back-propagation algorithm… By iteration of this procedure in a random sequence for the same set of input and output data" Examiner notes that back propagation algorithm/machine learning algorithm is iteratively performed to update synaptic weights/weighting factors of the NNM based upon the training data/given set of input and output data)
and validating the NNM based upon the second set of validation data. (Andrew Paragraph 0191; "Two different basic processes may be involved in the neural network 902, namely, a training process and a testing process. The neural network may be trained by a back-propagation algorithm using pairs of training input data and desired output data." Examiner notes that testing process/validating the NNM based upon the second set of validation data/desired output data)
It would have obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Bayat, Posner, and Andrew. Bayat teaches an implementation of Multilayer Perceptron Network with Highly Uniform Passive Memristive Crossbar Circuits. Posner teaches how to determine risk level of suicide and appropriate intervention. Andrew teaches a method for improving the delivery of healthcare services. One of ordinary skill would have motivation to combine Bayat, Posner, and Andrew to improve in cost and quality of patient care “However, technology also promises real improvements in both costs and quality that can be achieved by leveraging data and information and making the delivery of care more effective and efficient.” (Andrew Paragraph 0012).
Conclusion
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 DANIEL DUC TRAN whose telephone number is (571)272-6870. The examiner can normally be reached Mon-Fri 8:00-5:00 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, Viker Lamardo can be reached at (571) 270-5871. 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.
/D.D.T./Examiner, Art Unit 2147
/ERIC NILSSON/Primary Examiner, Art Unit 2151
Prosecution Insights