CTNF 18/375,960 CTNF 98706 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Information Disclosure Statement 06-52 The information disclosure statement (IDS) submitted on 10/03/2023 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Regarding claim 1, Step 1: Is the claim to a process, machine, manufacture or composition of matter? Claim 1 is directed to a machine. Step 1: yes. Step 2A, prong 1: Does the claim recite an abstract idea, law of nature, or natural phenomenon? for each of the one or more text segments in the text span, process the text segment to generate a set of text segment embeddings; (limitation is directed to a mental process, One can mentally determine the text segment embedding by use of pen and paper with respect to the respective text segments in the text span.) for each of the one or more text segments, process the respective set of text segment embeddings to determine whether the text segment is a section title or not; and (limitation is directed to a mental process, One can mentally determine if the text segment is a title or not by use of pen and paper with respect to the respective text segment.) for each of the one or more text segments, process the respective set of text segment embeddings to classify the text segment into a section type of a plurality of section types, wherein the section type characterizes a type of a clinical procedure that resulted in the clinical note being generated (limitation is directed to a mental process, One can mentally classify a text segment by use of pen and paper with respect to the section type.) Step 2A, prong 1: If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. According, the claim “recites” an abstract idea. Step 2A, prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application? A multi-task neural network system comprising one or more computers and one or more non-transitory computer storage media storing instructions that, when executed by the one or more computers, cause the one or more computers to implement: (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). a shared neural network configured to: (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). receive as input a text span from a clinical note, wherein the text span includes one or more text segments, and (is an insignificant extra solution activity of data gathering). a segmentation neural network configured to, (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). a section type classification neural network configured to, (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception? A multi-task neural network system comprising one or more computers and one or more non-transitory computer storage media storing instructions that, when executed by the one or more computers, cause the one or more computers to implement: (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). a shared neural network configured to: (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). receive as input a text span from a clinical note, wherein the text span includes one or more text segments, and (is an insignificant extra solution activity of data gathering. Under step 2B, this insignificant extra solution activity is well understood routine and conventional activity, see (Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362). a segmentation neural network configured to, (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). a section type classification neural network configured to, (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 2, Claim 2 incorporates the analysis of the machine of claim 1. Step 2A, prong 2/Step 2B: wherein the shared neural network includes a deep neural network. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 3, Claim 3 incorporates the analysis of the machine of claim 1. Step 2A, prong 2/Step 2B: wherein the deep neural network includes one or more fully-connected neural network layers with dropout. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 4, Claim 4 incorporates the analysis of the machine of claim 2. Step 2A, prong 2/Step 2B: wherein the deep neural network includes a Transformer neural network. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 5, Claim 5 incorporates the analysis of the machine of claim 4. Step 2A, prong 2/Step 2B: wherein the Transformer neural network is a bidirectional Transformer encoder neural network. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 6, Claim 6 incorporates the analysis of the machine of claim 1. Step 2A, prong 2/Step 2B: wherein the segmentation neural network includes an encoder neural network. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 7, Claim 7 incorporates the analysis of the machine of claim 1. Step 2A, prong 2/Step 2B: wherein the section type neural network includes one or more fully-connected neural network layers and a softmax neural network layer. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 8 and analogous claims 14 and 18, Claim 8 incorporates the analysis of the machine of claim 1. Step 2A, prong 1: a note type prediction neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine a note type of the text segment, wherein the note type characterizes a type of patient interaction that resulted in the clinical note being generated. (limitation is directed to a mental process, One can mentally determine a note type by use of pen and paper with respect to a patient interaction in the clinical note.) Step 2A, prong 1: If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. According, the claim “recites” an abstract idea. Regarding claim 9, Claim 9 incorporates the analysis of the machine of claim 8. Step 2A, prong 2/Step 2B: wherein the note type neural network includes one or more fully-connected neural network layers and a softmax neural network layer. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 10 and analogous claims 15 and 19, Claim 10 incorporates the analysis of the machine of claim 8. Step 2A, prong 2/Step 2B: wherein the shared neural network, the section type classification neural network, and the note type prediction neural network are jointly trained to optimize a combined loss function. (e.g., mere instructions to apply the judicial exception using generic computer components (MPEP 2106.05(f)). Step 2A, prong 2: Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea. Step 2B: Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible. Regarding claim 11 and analogous claims 16 and 20, Claim 11 incorporates the analysis of the machine of claim 10. Step 2A, prong 1: wherein the combined loss function is a combination of a section type loss that ensures an accuracy of classifying a text segment into a section type of the plurality of section types and a note type loss that ensures an accuracy of determining a note type for a text segment, wherein the note type is one of a plurality of note types. (limitation is directed to a mental process, One can mentally determine classifying accuracy by use of pen and paper with respect to the combined loss.) Step 2A, prong 1: If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. According, the claim “recites” an abstract idea. Regarding claim 12, Claim 12 incorporates the analysis of the machine of claim 10. Step 2A, prong 1: wherein the combined loss function is a weighted sum of a segmentation loss, a section type loss, and a note type loss. (limitation is directed to a mathematical concept.) Step 2A, prong 1: If claim limitations, under their broadest reasonable interpretation, covers performance of the limitations as a mental process but for the recitation of generic computer components, then it falls within the mental process grouping of abstract ideas. According, the claim “recites” an abstract idea. Regarding claim 13, Step 1: Is the claim to a process, machine, manufacture or composition of matter? Claim 13 is directed to a manufacture. Step 1: yes. The rest of the analysis for claim 13 is analogous to claim 1. Regarding claim 17, Step 1: Is the claim to a process, machine, manufacture or composition of matter? Claim 17 is directed to a process. Step 1: yes. The rest of the analysis for claim 17 is analogous to claim 1. Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-23-aia AIA 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. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. 07-21-aia AIA Claim s 1-3, 6-9, 13-14 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Shen (US Published Patent Application No. 20200218857), in view of Chang et al (US Published Patent Application No. 20180267956, "Chang") . In regard to claim 1, Shen teaches A multi-task neural network system comprising one or more computers and one or more non-transitory computer storage media storing instructions that, when executed by the one or more computers, cause the one or more computers to implement: ( Shen, paragraph 0010, “This disclosure also provides a system for processing numerical data within a natural language context. The system includes a non-transitory, computer-readable memory; one or more processors;”) a shared neural network configured to: ( Shen, paragraph 0010, “detect in a natural language text segment the presence of numerical data including one or more numbers; upon determining the presence of numerical data in the text segment, extract the numbers and words surrounding the numbers, the words being within a window of a predetermined length; create a word vector for each of the extracted words; determine the most correlated feature of the extract words by inputting the word vector for each of the extracted words into a first machine learning module; associate the most correlated feature of the extracted words with the numbers; and classify the natural language text segment by inputting the numbers and the associated most correlated feature into a second machine learning module.” Examiner would like to point out that the same input being put into a first and second machine learning module is being interpreted as the shared neural network. ) receive as input a text span from a clinical note, wherein the text span includes one or more text segments, and ( Shen, paragraph 0046, “To train and test the effectiveness of the model, the public Mimic III database was used. The database contains anonymized records from the Beth Israel Deaconess Medical Center of approximately 58,976 hospital admissions. To preprocess the data, all the sentences in the clinical notes that contained numbers were extracted. As the next step, all the numbers, as well as the words surrounding the numbers and within the word window, were used as the context.”) for each of the one or more text segments in the text span, process the text segment to generate a set of text segment embeddings; ( Shen, paragraph 0044, “The model includes a neural network for word embeddings. The word embedding are fed into a multi-layer convolutional neural network. The word embeddings are used as representations of the contexts of the numbers. Convolutional neural networks are commonly used for image recognition because they excel in identifying local features of data.”) a section type classification neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to classify the text segment into a section type of a plurality of section types, wherein the section type characterizes a type of a clinical procedure that resulted in the clinical note being generated. ( Shen, paragraph 0006, “In some embodiments, the method may also include providing a medical diagnosis based on the numerical data and the classification of the natural language text segment. In some embodiments, the method may include generating a treatment plan based on the medical diagnosis.”) However, Shen does not explicitly teach a segmentation neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine whether the text segment is a section title or not; and Chang teaches a segmentation neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine whether the text segment is a section title or not; and ( Chang, paragraph 0016, “The probabilistic language model measures whether splicing together a first text segment with another continuation text segment results in a phrase that is more likely than a phrase resulting from splicing together the first text segment with other continuation text segments. A plurality of sets of text segments are provided to the probabilistic model to generate a probability score for each set of text segments.” And paragraph 0017, “The language model allows the system to accurately suggest whether a constructed text segment made from a given text segment and a candidate continuation text segment is probable or not. Current solutions for ROTE from documents encoded in a portable document format do not exploit the power of language models. Additionally, current approaches to ROTE generally reflect a clear domain specificity. For instance, the classification of blocks as 'title' and 'body' is appropriate for magazine articles, but not for administrative documents.”) Shen and Chang are related to the same field of endeavor (i.e. machine learning). In view of the teachings of Chang, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Chang to Shen before the effective filing date of the claimed invention in order to improve the speed and accuracy of the processing. ( Chang, paragraph 0048, “FIG. 9 depicts a generalized example of a suitable general purpose computing system 900 in which the described innovations may be implemented in order to improve the processing speed and efficiency with which the computing system 900 provides probabilities for candidate text segment pairs for performing ROTE.”) In regard to claim 13, the claim recites similar limitations as corresponding claim 1, and is rejected for similar reasons as claim 1 using similar teachings and rationale. In regard to claim 17, the claim recites similar limitations as corresponding claim 1, and is rejected for similar reasons as claim 1 using similar teachings and rationale. In regard to claim 2, Shen and Chang teach the system of claim 1. Shen further teaches wherein the shared neural network includes a deep neural network. ( Shen, paragraph 0026, “In some embodiments, the first machine learning module may include a convolutional neural network (CNN). In machine learning, a convolutional neural network (CNN or ConvNet) is a group of deep, feed-forward artificial neural networks.”) In regard to claim 3, Shen and Chang teach the system of claim 1. Shen further teaches wherein the deep neural network includes one or more fully-connected neural network layers with dropout. ( Shen, paragraph 0026, “The hidden layers of a CNN further consist of convolutional layers, pooling layers, fully connected layers and normalization layers. Convolutional layers apply a convolution operation to the input, passing the result to the next layer.”) In regard to claim 6, Shen and Chang teach the system of claim 1. Shen further teaches wherein the segmentation neural network includes an encoder neural network. ( Shen, paragraph 0030, “feedforward neural network consists of a (possibly large) number of simple neuron-like processing units, organized in layers. Every unit in a layer is connected to all the units in the previous layer. Each connection may have a different strength or weight. The weights on these connections encode the knowledge of a network.”) In regard to claim 7, Shen and Chang teach the system of claim 1. Shen further teaches wherein the section type neural network includes one or more fully-connected neural network layers and a softmax neural network layer. ( Shen, paragraph 0026, “The hidden layers of a CNN further consist of convolutional layers, pooling layers, fully connected layers and normalization layers. Convolutional layers apply a convolution operation to the input, passing the result to the next layer.” And paragraph 0029, “The second machine learning module may include a feedforward neural network. In some embodiments, the feedforward neural network may include softmax as the final output layer.”) In regard to claim 8 and analogous claims 14 and 18, Shen and Chang teach the system of claim 1. Shen further teaches a note type prediction neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine a note type of the text segment, wherein the note type characterizes a type of patient interaction that resulted in the clinical note being generated. ( Shen, paragraph 0033, “Additionally and/or optionally, the method may include providing a medical diagnosis based on the classification of the natural language text segment. For example, based on the classification of a temperature number and feature, i.e., 104.2 degrees, the method may include determining that the patient may have a (high) fever. Further, the method may also include providing a medical diagnosis related to the cause of a fever, for example, bacterial infection or viral infection. As the disclosed machine learning model can be trained by providing medical data including diagnosis and prescribed treatment plans as inputs, it is capable of determining a treatment plan for a patient based on the diagnosis.’) In regard to claim 9, Shen and Chang teach the system of claim 8. Shen further teaches wherein the note type neural network includes one or more fully-connected neural network layers and a softmax neural network layer. ( Shen, paragraph 0026, “The hidden layers of a CNN further consist of convolutional layers, pooling layers, fully connected layers and normalization layers. Convolutional layers apply a convolution operation to the input, passing the result to the next layer.” And paragraph 0029, “The second machine learning module may include a feedforward neural network. In some embodiments, the feedforward neural network may include softmax as the final output layer.”) 07-21-aia AIA Claim s 4 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over Shen, in view of CHang and in further view of Li et al (Model-based clinical note entity recognition for rheumatoid arthritis using bidirectional encoder representation from transformers, "Li") . In regard to claim 4, Shen and Chang teach the system of claim 2. However, Shen and Chang do not explicitly teach wherein the deep neural network includes a Transformer neural network. Li teaches wherein the deep neural network includes a Transformer neural network. ( Li, pg. 185, Col. 2, paragraph 1, “which is superior to the traditional memory network in terms of learning effect and can realize the integrated bi-directional prediction with the help of the masked language model. The transformer uses the self-attention mechanism to solve the challenge of parallel processing and long-term dependency of a large amount of data in the corpus. BERT first builds masked-language modeling (MLM) on the general domain data during the pre-training period and performs the next sentence prediction (NSP) tasks.”). Shen, Chang and Li are related to the same field of endeavor (i.e. machine learning). In view of the teachings of Li, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Li to Shen and Chang before the effective filing date of the claimed invention in order to improve the accuracy of the model. ( Li, pg. 185, Col. 1, paragraph 2, “For example, in the medical field, real world data will greatly improve the accuracy of the model, and the results will be better used in interpreting medical data (3).”) In regard to claim 5, Shen, Chang and Li teach the system of claim 4. Li further teaches wherein the Transformer neural network is a bidirectional Transformer encoder neural network. ( Li, pg. 185, Col. 2, paragraph 1, “which is superior to the traditional memory network in terms of learning effect and can realize the integrated bi-directional prediction with the help of the masked language model. The transformer uses the self-attention mechanism to solve the challenge of parallel processing and long-term dependency of a large amount of data in the corpus. BERT first builds masked-language modeling (MLM) on the general domain data during the pre-training period and performs the next sentence prediction (NSP) tasks.”) Shen, Chang and Li are combinable for the same rationale as set forth above with respect to claim 4 . 07-21-aia AIA Claim s 10-12, 15-16 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Shen, in view of Chang and in further view of Vatathanuvaro et al (Improved Identification of Imbalanced Multiple Annotation Intent Labels with a Hybrid BLSTM and CNN Model and Hybrid Loss Function, "Vatathanavaro") . In regard to claim 10 and analogous claims 15 and 19, Shen and Chang teach the system of claim 8. However, Shen and Chang do not explicitly teach wherein the shared neural network, the section type classification neural network, and the note type prediction neural network are jointly trained to optimize a combined loss function. Vatathanovaro teaches wherein the shared neural network, the section type classification neural network, and the note type prediction neural network are jointly trained to optimize a combined loss function. ( Vatathanovaro, pg. 360, paragraph 2, “We aimed to minimise the distance function in (4). Furthermore, we combined a cross-entropy loss function with distance, D , as a new hybrid loss function with a weight, w . Therefore, the model can consider not only the distance but also the cross-entropy loss between the predicted and the actual labels. The hybrid loss function increases as the predicted probability diverges from the actual label. Additionally, to get the best-fit hybrid loss function for this task, the weight w is applied to give an important to each loss differently.” Examiner would like to point out that the hybrid loss combines the training of neural networks. ) Shen, Chang and Vatathanovaro are related to the same field of endeavor (i.e. machine learning). In view of the teachings of Vatathanovaro, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Vatathanovaro to Shen and Chang before the effective filing date of the claimed invention in order to build an accurate model for classification. ( Vatathanovaro, pg. 356, paragraph 2, “Hence, building an accurate model, for text classification to obtain the right information from text data, is important to launch a marketing campaign at the right time to the right group.”) In regard to claim 11 and analogous claims 16 and 20, Shen, Chang and Vatathanovaro teach the system of claim 10. Shen further teaches wherein the combined loss function is a combination of a section type loss that ensures an accuracy of classifying a text segment into a section type of the plurality of section types and a note type loss that ensures an accuracy of determining a note type for a text segment, wherein the note type is one of a plurality of note types. ( Shen, paragraph 0035, “At 204, the method may include using a gradient descent algorithm to minimize the cost function and improve the classification accuracy. Gradient descent is an optimization algorithm used to minimize some function by iteratively moving in the direction of steepest descent as defined by the negative of the gradient. In machine learning, gradient descent is used to update the parameters of the model. Parameters refer to coefficients in linear regression and weights in neural networks. A cost function shows the level of accuracy of a model at making predictions for a given set of parameters.”) Shen, Chang and Vatathanovaro are combinable for the same rationale as set forth above with respect to claim 10. In regard to claim 12, Shen, Chang and Vatathanovaro teach the system of claim 10. Vatathanovaro further teaches wherein the combined loss function is a weighted sum of a segmentation loss, a section type loss, and a note type loss. ( Vatathanovaro, pg. 360, paragraph 2, “We aimed to minimise the distance function in (4). Furthermore, we combined a cross-entropy loss function with distance, D , as a new hybrid loss function with a weight, w . Therefore, the model can consider not only the distance but also the cross-entropy loss between the predicted and the actual labels. The hybrid loss function increases as the predicted probability diverges from the actual label. Additionally, to get the best-fit hybrid loss function for this task, the weight w is applied to give an important to each loss differently [a weighted sum of a segmentation loss, a section type loss, and a note type loss] .”) Shen, Chang and Vatathanovaro are combinable for the same rationale as set forth above with respect to claim 10. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to SKYLAR K VANWORMER whose telephone number is (703)756-1571. The examiner can normally be reached M-F 6:00am to 3:00 pm. 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, Usmaan Saeed can be reached at (571) 272-4046. 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. /S.K.V./ Examiner, Art Unit 2146 /USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146 Application/Control Number: 18/375,960 Page 2 Art Unit: 2146 Application/Control Number: 18/375,960 Page 3 Art Unit: 2146 Application/Control Number: 18/375,960 Page 4 Art Unit: 2146 Application/Control Number: 18/375,960 Page 5 Art Unit: 2146 Application/Control Number: 18/375,960 Page 6 Art Unit: 2146 Application/Control Number: 18/375,960 Page 7 Art Unit: 2146 Application/Control Number: 18/375,960 Page 8 Art Unit: 2146 Application/Control Number: 18/375,960 Page 9 Art Unit: 2146 Application/Control Number: 18/375,960 Page 10 Art Unit: 2146 Application/Control Number: 18/375,960 Page 11 Art Unit: 2146 Application/Control Number: 18/375,960 Page 12 Art Unit: 2146 Application/Control Number: 18/375,960 Page 13 Art Unit: 2146 Application/Control Number: 18/375,960 Page 14 Art Unit: 2146 Application/Control Number: 18/375,960 Page 15 Art Unit: 2146 Application/Control Number: 18/375,960 Page 16 Art Unit: 2146 Application/Control Number: 18/375,960 Page 17 Art Unit: 2146 Application/Control Number: 18/375,960 Page 18 Art Unit: 2146 Application/Control Number: 18/375,960 Page 19 Art Unit: 2146 Application/Control Number: 18/375,960 Page 20 Art Unit: 2146
Prosecution Insights