Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Application
Claims 1-20 are currently pending in this case and have been examined and addressed below. This communication is a Final Rejection in response to the Amendments to the Claims and Remarks filed on 12/27/2025.
Claims 1-20 are currently amended.
Claim Rejections - 35 USC § 112
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.
Claims 1, 9, and 17 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.
The term “finer” in claims 1, 9, and 17 is a relative term which renders the claim indefinite. The term “finer” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. Therefore, the first, second, and third level of textual granularity in the claims have also been rendered as indefinite by the use of the term “finer”.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1 – 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Step 1: Claims 1-8 and 17-20 are drawn to a process. Claims 9-16 are drawn to a process. As such, claims 1-20 are drawn to one of the statutory categories of invention (Step 1: YES).
Step 2A - Prong One: In prong one of step 2A, the claim(s) is/are analyzed to evaluate whether it/they recite(s) a judicial exception.
Independent Claim 1: A system, comprising:
a memory configured to store computer-executable components;
and a processor that executes at least one of the computer-executable components that accesses a new medical order associated with a medical patient, wherein the new medical order was created by a medical professional attending to the medical patient, and the new medical order comprises information describing a medical action to be performed with respect to the medical patient;
generates, using a vectorizer, a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, wherein the vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model;
partitions the information in the new medical order into distinct textual sections, wherein each distinct textual section is less than the entirety of the new medical order;
generates, using the vectorizer, respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity, thereby yielding a group of local vector representations of the new medical order, wherein the combinations of the distinct textual sections are respectively less that the entirety of the new medical order, wherein the second level of textual granularity is finer than the first level of textual granularity, and the third level of textual granularity is finer than the second level of textual granularity;
assigns a new classification label to the new medical order, based on searching a historical order-label database comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion, wherein the historical order-label database further comprises, for each of the historical medical orders:
a historical global vector representation associated with the historical medical order, a group of historical local vector representations associated with the historical medical order, and a historical label associated with historical medical order;
and controls a medical device to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols associated with the medical device based on the new classification label.
Independent Claim 9: A computer-implemented method, comprising:
accessing, by a system comprising at least one processor, a new medical order associated with a medical patient, wherein the new medical order was created by a medical professional attending to the medical patient, and the new medical order comprises information describing a medical action to be performed with respect to the medical patient;
generating, by the system, using a vectorizer, a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, wherein the vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model;
partitioning, by the system, the information in the new medical order into distinct textual sections, wherein each distinct textual section is less than the entirety of the new medical order;
generating, by the system, respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity, thereby yielding a group of local vector representations of the new medical order, wherein the combinations of the distinct textual sections are respectively less that the entirety of the new medical order, wherein the second level of textual granularity is finer than the first level of textual granularity, and the third level of textual granularity is finer than the second level of textual granularity;
assigning, by the system, a new classification label to the new medical order, based on searching a historical order-label database comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion, wherein the historical order-label database further comprises, for each of the historical medical orders:
a historical global vector representation associated with the historical medical order, a group of historical local vector representations associated with the historical medical order, and a historical label associated with historical medical order;
and controlling, by the system, a medical device to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols associated with the medical device based on the new classification label.
Independent Claim 17: A computer program product for facilitating global and local search-based classification of text, the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by at least one processor of a system to cause the at least one processor to:
access a new medical order associated with a medical patient, wherein the new medical order was created by a medical professional attending to the medical patient, and the new medical order comprises information describing a medical action to be performed with respect to the medical patient;
generate, using a vectorizer, a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, wherein the vectorizer comprises at least one of anon-machine learning vectorizer or an encoder of a machine learning model;
partition the information in the new medical order into distinct textual sections, wherein each distinct textual section is less than the entirety of the new medical order;
generate, using the vectorizer, respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity, thereby yielding a group of local vector representations of the new medical order, wherein the combinations of the distinct textual sections are respectively less that the entirety of the new medical order, wherein the second level of textual granularity is finer than the first level of textual granularity, and the third level of textual granularity is finer than the second level of textual granularity;
assign a new classification label to the new medical order, based on searching a historical order-label database comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion, wherein the historical order-label database further comprises, for each of the historical medical orders:
a historical global vector representation associated with the historical medical order, a group of historical local vector representations associated with the historical medical order, and a historical label associated with historical medical order;
and control a medical device to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols associated with the medical device based on the new classification label.
(Examiner notes: The above claim terms underlined are additional elements that fall under Step 2A - Prong Two analysis section detailed below)
These steps amount to methods of organizing human activity which includes functions relating to interpersonal and intrapersonal activities, such as managing relationships or transactions between people, social activities, and human behavior; satisfying or avoiding a legal obligation; advertising, marketing, and sales activities or behaviors; and managing human mental activity (MPEP § 2106.04(a)(2)(II)(C) citing the abstract idea grouping for methods of organizing human activity for managing personal behavior or relationships or interactions between people). Therefore, accessing a new medical order associated with a medical patient, generating global and local vector representations, partitioning the information in the new medical order into distinct textual sections, and assigning a new classification label to the new medical order are directed to managing personal interactions or personal behavior.
The dependent claims 3, 11, and 18 are directed to comparing the global and local vector representations of the new medical order to the respective historical global vector representations of historical medical order, thereby yielding respective global similarity scores for the historical medical orders.
The dependent claims 4, 12, and 19 are directed to aggregating the global similarity scores and the group of local similarity scores historical medical order, thereby yielding an aggregate similarity score historical medical order and comparing the aggregate similarity score for the historical medical order to the matching criterion.
The dependent claims 5, 13, and 20 are directed to inserts the new medical order, the global vector representation of the new medical order, and the new classification label of the new medical order.
The dependent claims 6 and 14 are directed to the medical protocol includes imaging protocol to scan the medical patient according to the imaging protocol.
The dependent claims 7 and 15 are directed to the medical protocol includes a medication dispensing protocol to dispense the fluidic medication to the airway or blood vessel of the medical patient in accordance with the medication dispensing protocol.
The dependent claims 8 and 16 are directed to the medical protocol includes a surgical protocol to perform the surgical protocol of the medical patient.
Each of these steps of the preceding dependent claims 2-8, 10-16, and 18-20 only serve to further limit or specify the features of independent claims 1, 9, and 17 accordingly, and hence are nonetheless directed towards fundamentally the same abstract idea as the independent claim and utilize the additional elements analyzed below in the expected manner.
As such, the Examiner concludes that the preceding claims recite an abstract idea (Step 2A – Prong One: YES).
Step 2A - Prong Two: In prong two of step 2A, an evaluation is made whether a claim recites any additional element, or combination of additional elements, that integrate the exception into a practical application of that exception. An “additional element” is an element that is recited in the claim in addition to (beyond) the judicial exception (i.e., an element/limitation that sets forth an abstract idea is not an additional element). The phrase “integration into a practical application” is defined as requiring an additional element or a combination of additional elements in the claim to apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, such that it is more than a drafting effort designed to monopolize the exception.
Claim 1 recites the use of a memory configured to store computer-executable components, only recites the memory configured to store computer-executable components as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 1 and 5 recite the use of a processor that executes at least one of the computer-executable components, in this case to accesses a new medical order associated with a medical patient, partitions the information in the new medical order into distinct textual sections, inserts the new medical order, the global vector representations of the new medical order, the group of local vector representations of the new medical order, and the new classification label of the new medical order, only recites the a processor that executes at least one of the computer-executable components as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 1, 9, and 17 recite the use of a vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model, in this case to generates a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, generates a respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity yielding a group of local vector representations of the new medical order, assigns a new classification label to the new medical order, only recites the vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model as a tool to apply data to an algorithm and report the results (MPEP § 2106.05(f)(2)) amounting to instruction to implement the abstract idea using a general purpose computer.
Claims 1, 3, 5, 9, 11-12, and 17-19 recite the use of a historical order-label database, in this case to comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion, a historical global vector representation, a group of historical local vector representations, a historical label, only recites the historical order-label database as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 1, 6-9, 14-16 recite the use of a controls a medical device, in this case to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols based on the new classification label, only recites the controls a medical device as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 2 and 10 recite the use of a the non-machine learning vector comprises at least one of a term-frequency-inverse-domain-frequency vectorizer, a one-hot encoding vectorizer, a count vectorizer, a bag-of-words vectorizer, or an n- grams vectorizer, in this case to , only recites the non-machine learning vector comprises at least one of a term-frequency-inverse-domain-frequency vectorizer, a one-hot encoding vectorizer, a count vectorizer, a bag-of-words vectorizer, or an n- grams vectorizer as a tool to apply data to an algorithm and report the results (MPEP § 2106.05(f)(2)) amounting to instruction to implement the abstract idea using a general purpose computer.
Claims 6 and 14 recite the use of a medical imaging scanner, only recites the medical imaging scanner as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 7 and 15 recite the use of a medication dispenser, only recites the medication dispenser as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 8 and 16 recite the use of a robotic surgery apparatus, only recites the robotic surgery apparatus as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claim 9 recites the use of a system comprising at least one processor, only recites the system comprising at least one processor, as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
Claims 17 and 20 recite the use of a computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by at least one processor of a system to cause the at least one processor, only recites the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by at least one processor of a system to cause the at least one processor as a tool to perform an existing process and only amounts to an instruction to implement the abstract idea using a computer (MPEP § 2106.05(f)(2)).
The Examiner has therefore determined that the additional elements, or combination of additional elements, do not integrate the abstract idea into a practical application. Accordingly, the claim(s) is/are directed to an abstract idea (Step 2A – Prong two: NO).
Step 2B: In step 2B, the claims are analyzed to determine whether any additional element, or combination of additional elements, is/are sufficient to ensure that the claims amount to significantly more than the judicial exception.
As discussed above in “Step 2A – Prong 2”, the identified additional elements, such as the memory configured to store computer-executable components, processor that executes at least one of the computer-executable components, the vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model, historical order-label database, controls a medical device, the non-machine learning vector comprises at least one of a term-frequency-inverse-domain-frequency vectorizer, a one-hot encoding vectorizer, a count vectorizer, a bag-of-words vectorizer, or an n- grams vectorizer, medical imaging scanner, medication dispenser, robotic surgery apparatus, system comprising at least one processor, computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by at least one processor of a system to cause the at least one processor in independent claims 1, 9, and 17 and dependent claims 2-8, 10-16, and 18-20 are equivalent to adding the words “apply it” on a generic computer. Each of these elements is only recited as a tool for performing steps of the abstract idea, such as the use of the computer and data processing devices to apply the algorithm. These additional elements therefore only amount to mere instructions to perform the abstract idea using a computer and are not sufficient to amount to significantly more than the abstract idea (MPEP 2016.05(f) see for additional guidance on the “mere instructions to apply an exception”). Each additional element under Step 2A, Prong 2 is analyzed in light of the specification’s explanation of the additional element’s structure. The claimed invention’s additional elements are directed to generic computer component and functions being used to perform the abstract idea.
Applicant’s own disclosure in paragraph [0068] acknowledges that the “processor 110 (e.g., computer processing unit, microprocessor) and a non-transitory computer-readable memory 112 that is operably or operatively or communicatively connected or coupled to the processor 110. The non-transitory computer-readable memory 112 can store computer-executable instructions which, upon execution by the processor 110, can cause the processor 110 or other components of the classification system 102 (e.g., access component 114, vector component 116, search component 118, execution component 120) to perform one or more acts. In various embodiments, the non-transitory computer-readable memory 112 can store computer-executable components (e.g., access component 114, vector component 116, search component 118, execution component 120), and the processor 110 can execute the computer-executable components”. Paragraph [0069] discloses “an access component 114. In various aspects, the access component 114 can electronically access or otherwise electronically communicate in any suitable fashion with the medical device 104”. Additionally, paragraphs [0039-0041] acknowledges “the vector component of the computerized tool can electronically generate a global vector and a set of local vectors, by applying any suitable vectorizer to the new medical order. More specifically, the vectorizer can be any suitable text-to-vector transformation technique (e.g., any suitable algorithm that can convert any given piece of text into a numerical representation). In some cases, the vectorizer can be any suitable non-machine-learning vectorizer, such as a term-frequency-inverse-domain-frequency (TF-IDF) vectorization technique. In other cases, the vectorizer can instead be any suitable machine learning vectorizer, such as an encoder from any suitable pre-trained text-analysis machine learning model (e.g., the encoder from an already-trained variational autoencoder; the encoder from an already-trained text classifier; the encoder from an already-trained LLM)… the global vector can be considered as an embedding, encoded representation, or latent representation of the new medical order as a whole. In various instances, the vector component can generate the global vector, by applying or executing the vectorizer on the new medical order… a local vector can be considered as an embedding, encoded representation, or latent representation of some portion or part of the new medical order. In various instances, the new medical order can be considered as being made up of a plurality of textual sections (e.g., each discrete text field of the new medical order can be considered as a respective textual section). In various cases, for any given textual section of the new medical order, the vector component can generate a respective local vector, by applying or executing the vectorizer on that given textual section”. Paragraph [0044] discloses “the search component of the computerized tool can electronically store, maintain, control, or otherwise access an historical order-label database”. The disclosure further acknowledges in paragraph [0028] that “an order-label database that stores: past medical orders; the classification labels that were known or selected for those past medical orders; and the global and local vector representations that were computed for those past medical orders”. Furthermore paragraph [0035] discloses “the medical device can be any suitable type of medical image-capture equipment or modality (e.g., a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, an X-ray scanner, an ultrasound scanner, a positron emission tomography (PET) scanner, a nuclear medicine (NM) scanner). In various instances, the medical device can instead be any suitable type of automated medication dispenser (e.g., an intravenous infusion pump, a respirator, a hemodialysis machine, an aerosol tent or mask, a nebulizer). In various aspects, the medical device can instead be any suitable type of automated surgical equipment or modality (e.g., robotically-assisted surgery machine for laparoscopic procedures)”.
The Examiner has therefore determined that no additional element, or combination of additional claims elements is/are sufficient to ensure the claim(s) amount to significantly more than the abstract idea identified above (Step 2B: NO).
Therefore, claims 1-20 are not eligible subject matter under 35 USC 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3-6, 9, 11-14, and 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Boloor et al. (US-9690861-B2)[hereinafter Boloor], in view of Difeng Wang et al. (“Global-to-Local Neural Networks for Document-Level Relation Extraction”)[hereinafter Difeng], in view of Cohen-Solal (US-20130311472-A1)[hereinafter Cohen-Solal].
As per Claim 1, Boloor discloses a system in column 12 lines 13-18 (a system), comprising: a memory configured to store computer-executable components in column 12 lines 13-18 (a processor that carries outs the computer readable program instructions); and a processor that executes at least one of the computer-executable components in column 4 line 60-column 5 line 15 and column 6 lines 9-41 (access a query medication order (synonymous to a new medical order) created by a medical professional attending to the patient, and the query medication order includes prescription medications (Examiner notes that prescription medications indicates medical action to be performed to the patient)) that accesses a new medical order associated with a medical patient, wherein the new medical order was created by a medical professional attending to the medical patient, and the new medical order comprises information describing a medical action to be performed with respect to the medical patient in column 4 line 60-column 5 line 15 and column 6 lines 9-41 (access a query medication order (synonymous to a new medical order) created by a medical professional attending to the patient, and the query medication order includes prescription medications (Examiner notes that prescription medications indicates medical action to be performed to the patient)); assigns a new classification label to the new medical order, based on searching historical order-label database comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion in column 4 line 60-column 5 line 15, column 6 lines 9-41, column 7 lines 12-42, column 9 lines 44-62, and column 11 line 50-column 12 line 12 (identifies semantically relevant information, referred to as tags, (synonymous to a new classification label) for the query medication order (synonymous to the new medical order), based on a deep semantic searching the EMR (synonymous to a historical order-label database) for the semantically analyzed medication order that corresponds to the query medication order according to the semantically analyzed medication order having an aggregate score above a threshold (synonymous to a matching criterion) (Examiner notes that according to "Global and Local Information Adjustment for Semantic Similarity Evaluation", performing a deep sematic search of the medication orders indicates using the global vector representations and the set of local vector representation to perform the search)), wherein the historical order-label database further comprises, for each of the historical medical orders in column 4 lines 25-53 and column 5 lines 16-34 and column 11 lines 22-49 (the EMR includes semantically analyzed medication orders): a historical global vector representation associated with the historical medical order in column 5 lines 16-column 6 lines 8, column 9 lines 55-62, column 10 lines 1-21, column 11 lines 22-49 (the terms in the semantically analyzed medication orders mapped using latent semantic analysis (synonymous to a historical global vector representations of each respective one of the plurality of past medical orders) (Examiner notes that latent semantic analysis compares topics as the occur in the corpus of the EMR, which indicates a comparison of global vector representations)), a group of historical local vector representations associated with the historical medical order in column 5 lines 16-column 6 lines 8, column 9 lines 55-67, column 11 lines 22-49 (the terms in the semantically analyzed medication orders mapped using a string matching technique (synonymous to a group of historical local vector representations of each respective one of the plurality of past medical orders)), and a historical label associated with historical medical order in column 7 lines 12-42, (a plurality of tagged annotations (synonymous to a historical classification labels) corresponding to the semantically analyzed medication orders).
Boloor discloses global and local vector representations, but Boloor does not disclose generating the global and local vector representations according to levels of granularity using a vectorizer. However, Difeng discloses generates, using a vectorizer, a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, wherein the vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model in the 2nd-4th paragraphs under the "Our approach and contributions" on page 3712 and Figure 2 and 2nd paragraph under "3 Proposed Model" on page 3713 (generates, using a GLRE (synonymous to a vectorizer), global representations or coarse-grained semantic features (synonymous to a global vector representation based on an entirety of the new medical order according to a first level of textual granularity), wherein the GLRE is pre-trained language model BERT (Examiner notes that the BERT model is an encoder of a machine learning model)); partitions the information in the new medical order into distinct textual sections, wherein each distinct textual section is less than the entirety of the new medical order in the 2nd paragraph under "3 Proposed Model" and "3.1 Encoding Layer" on page 3713 (encoding a long document sequentially in form of short paragraphs (synonymous to partitions the information in the new medical order into distinct textual sections) (Examiner notes that short paragraphs are distinct textual sections that are less than the entirety of the new medical order)); generates, using the vectorizer, respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity, thereby yielding a group of local vector representations of the new medical order, wherein the combinations of the distinct textual sections are respectively less that the entirety of the new medical order, wherein the second level of textual granularity is finer than the first level of textual granularity, and the third level of textual granularity is finer than the second level of textual granularity in the 2nd-4th paragraphs under the "Our approach and contributions" on page 3712 and Figure 2 and "3.1 Encoding Layer" on page 3713 (generates, using the GLRE, respective local representations or fine-grained semantic features for one of the short paragraphs (synonymous to local vector representations according to a finer level of textual granularity)).
It would have been obvious to one of ordinary still in the art to include in the a system that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label of Boloor with the generating global and local vector representations according to levels of granularity using a vectorizer as taught by Difeng since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately. One of ordinary skill in the art would have recognized that the results of the combination were predictably a system that accesses a new medical order associated with a medical patient, generate global and local vector representations according to levels of granularity using a vectorizer, label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label.
Boloor and Difeng do not disclose the following limitations. However, Cohen-Solal discloses controls a medical device to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols associated with the medical device based on the new classification label in paragraphs [0003-0004] and [0031] and [0043] and [0047] (controlling an imaging modality (synonymous to a medical imaging scanner) to perform the imaging protocol for the imaging modality based on the classifier (synonymous to the new classification label)).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a system that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined the controlling a medical device to perform the medical action on the patient using a protocol based on the new classification label, as disclosed by Cohen-Solal, for the purpose of minimizing errors in patient handling, protocol choice and adaption [0002-0009].
As per Claim 3, Boloor, Difeng, and Cohen-Solal discloses the system of claim 1, wherein searching the historical order- label database comprises: Boloor also discloses comparing the global vector representation of the new medical order to the respective historical global vector representations of historical medical orders, thereby yielding respective global similarity scores for the historical medical orders in column 1 lines 25-45, column 5 lines 16-column 6 lines 8, column 9 lines 55-62, column 10 lines 1-21, column 11 lines 22-49 (compares, using latent semantic analysis, the terms of the query medication orders (synonymous to the one or more global vector representations of the new medical order) to the terms in the semantically analyzed medication orders (synonymous to the one or more past global vector representations of each respective one of the plurality of past medical orders), yielding textual match scores or a LSA similarity score (synonymous to global similarity scores) for each of the semantically analyzed medication orders (Examiner notes that latent semantic analysis compares topics as the occur in the corpus of the EMR, which indicates a comparison of global vector representations)); and comparing the group of local vector representations of the new medical order to the respective groups of historical local vector representations of the historical medical orders, thereby yielding a respective group of local similarity scores for the historical medical orders in column 1 lines 25-45, column 5 lines 16-column 6 lines 8, column 9 lines 55-67, column 11 lines 22-49 (compares, using string matching technique, the terms of the query medication orders (synonymous to the set of local vector representations of the new medical order) to the terms in the semantically analyzed medication orders (synonymous to the set of past local vector representations of each respective one of the plurality of past medical orders), yielding medical relationship strength of the passages scores (synonymous to a set of local similarity scores) for each of the semantically analyzed medication orders (Examiner notes that string matching terms in the medication records indicates comparing local vector representations)).
As per Claim 4, Boloor, Difeng, and Cohen-Solal discloses the system of claim 3, wherein searching the historical order-label database further comprises: Boloor also discloses for each of the historical medical orders: aggregating the global similarity score and the group of local similarity scores for the historical medical order, thereby yielding an aggregate similarity score for the historical medical order in column 6 lines 9-31 and column 11 line 50-column 12 line 12 (aggregates the textual match scores and the medical relationship strength of passages scores for each of the semantically analyzed medication orders, generating an aggregate score (synonymous to an aggregate similarity score) for each one of the semantically analyzed medication orders); and comparing the aggregate similarity score for the historical medical order to the matching criterion in column 6 lines 9-31 and column 11 line 50-column 12 line 12 (comparing the aggregate score for the semantically analyzed medication order to the threshold).
As per Claim 5, Boloor, Difeng, and Cohen-Solal discloses the system of claim 1, wherein the at least one of the computer-executable components further: Boloor also discloses inserts the new medical order, the global vector representation of the new medical order, the group of local vector representations of the new medical order, and the new classification label of the new medical order into the historical order-label database in column 4 line 60-column 5 line 15 and column 8 line 67-column 9 line 3 (stores the query medication order and the tag as a new entry in the EMR for subsequent searching (Examiner notes that the query medication order includes the global vector representations and the set of local vector representations in order perform another deep semantic search)).
As per Claim 6, Boloor, Difeng, and Cohen-Solal discloses the system of claim 1.
Boloor and Difeng do not disclose the following limitations. However, Cohen-Solal discloses wherein the medical device comprises a medical imaging scanner, and wherein the medical protocol comprises an imaging protocol for the medical imaging scanner in paragraphs [0003-0004] and [0031] and [0043] and [0047] (an imaging modality (synonymous to a medical imaging scanner), wherein the protocol includes an imaging protocol for the imaging modality), and wherein controlling the medical device to perform the medical action comprises controlling the medical imaging scanner to scan the medical patient according to the imaging protocol in paragraphs [0005-0007] and [0080-0081] (controlling the imaging modality to scan the patient according to the imaging protocol).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a system that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined with controlling a medical device, wherein the medical device is a medical imaging scanner to perform the medical action on the patient using a protocol, wherein the protocol is an imaging protocol for the medical imaging scanner based on the new classification label, as disclosed by Cohen-Solal, for the purpose of minimizing errors in patient handling, protocol choice and adaption [0002-0009].
As per Claim 9, Boloor discloses a computer-implemented method in column 12 lines 13-18 (a method), comprising: accessing, by a system comprising at least one processor, a new medical order associated with a medical patient, wherein the new medical order was created by a medical professional attending to the medical patient, and the new medical order comprises information describing a medical action to be performed with respect to the medical patient in column 4 line 60-column 5 line 15 and column 6 lines 9-41 (access a query medication order (synonymous to a new medical order) created by a medical professional attending to the patient, and the query medication order includes prescription medications (Examiner notes that prescription medications indicates medical action to be performed to the patient)); assigning, by the system, a new classification label to the new medical order, based on searching a historical order-label database comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion in column 4 line 60-column 5 line 15, column 6 lines 9-41, column 7 lines 12-42, column 9 lines 44-62, and column 11 line 50-column 12 line 12 (identifies semantically relevant information, referred to as tags, (synonymous to a new classification label) for the query medication order (synonymous to the new medical order), based on a deep semantic searching the EMR (synonymous to a historical order-label database) for the semantically analyzed medication order that corresponds to the query medication order according to the semantically analyzed medication order having an aggregate score above a threshold (synonymous to a matching criterion) (Examiner notes that according to "Global and Local Information Adjustment for Semantic Similarity Evaluation", performing a deep sematic search of the medication orders indicates using the global vector representations and the set of local vector representation to perform the search)), wherein the historical order-label database further comprises, for each of the historical medical orders in column 4 lines 25-53 and column 5 lines 16-34 and column 11 lines 22-49 (the EMR includes semantically analyzed medication orders): a historical global vector representation associated with the historical medical order in column 5 lines 16-column 6 lines 8, column 9 lines 55-62, column 10 lines 1-21, column 11 lines 22-49 (the terms in the semantically analyzed medication orders mapped using latent semantic analysis (synonymous to a historical global vector representations of each respective one of the plurality of past medical orders) (Examiner notes that latent semantic analysis compares topics as the occur in the corpus of the EMR, which indicates a comparison of global vector representations)), a group of historical local vector representations associated with the historical medical order in column 5 lines 16-column 6 lines 8, column 9 lines 55-67, column 11 lines 22-49 (the terms in the semantically analyzed medication orders mapped using a string matching technique (synonymous to a group of historical local vector representations of each respective one of the plurality of past medical orders)), and a historical label associated with historical medical order in column 7 lines 12-42, (a plurality of tagged annotations (synonymous to a historical classification labels) corresponding to the semantically analyzed medication orders).
Boloor discloses global and local vector representations, but Boloor does not disclose generating the global and local vector representations according to levels of granularity using a vectorizer. However, Difeng discloses generating, by the system, using a vectorizer, a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, wherein the vectorizer comprises at least one of anon-machine learning vectorizer or an encoder of a machine learning model in the 2nd-4th paragraphs under the "Our approach and contributions" on page 3712 and Figure 2 and 2nd paragraph under "3 Proposed Model" on page 3713 (generates, using a GLRE (synonymous to a vectorizer), global representations or coarse-grained semantic features (synonymous to a global vector representation based on an entirety of the new medical order according to a first level of textual granularity), wherein the GLRE is pre-trained language model BERT (Examiner notes that the BERT model is an encoder of a machine learning model)); partitioning, by the system, the information in the new medical order into distinct textual sections, wherein each distinct textual section is less than the entirety of the new medical order in the 2nd paragraph under "3 Proposed Model" and "3.1 Encoding Layer" on page 3713 (encoding a long document sequentially in form of short paragraphs (synonymous to partitions the information in the new medical order into distinct textual sections) (Examiner notes that short paragraphs are distinct textual sections that are less than the entirety of the new medical order)); generating, by the system, respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity, thereby yielding a group of local vector representations of the new medical order, wherein the combinations of the distinct textual sections are respectively less that the entirety of the new medical order, wherein the second level of textual granularity is finer than the first level of textual granularity, and the third level of textual granularity is finer than the second level of textual granularity in the 2nd-4th paragraphs under the "Our approach and contributions" on page 3712 and Figure 2 and "3.1 Encoding Layer" on page 3713 (generates, using the GLRE, respective local representations or fine-grained semantic features for one of the short paragraphs (synonymous to local vector representations according to a finer level of textual granularity)).
It would have been obvious to one of ordinary still in the art to include in the a method that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label of Boloor with the generating global and local vector representations according to levels of granularity using a vectorizer as taught by Difeng since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately. One of ordinary skill in the art would have recognized that the results of the combination were predictably a method that accesses a new medical order associated with a medical patient, generate global and local vector representations according to levels of granularity using a vectorizer, label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label.
Boloor and Difeng do not disclose the following limitations. However, Cohen-Solal discloses and controlling, by the system, a medical device to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols associated with the medical device based on the new classification label in paragraphs [0003-0004] and [0031] and [0043] and [0047] (controlling an imaging modality (synonymous to a medical imaging scanner) to perform the imaging protocol for the imaging modality based on the classifier (synonymous to the new classification label)).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a method that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined the controlling a medical device to perform the medical action on the patient using a protocol based on the new classification label, as disclosed by Cohen-Solal, for the purpose of minimizing errors in patient handling, protocol choice and adaption [0002-0009].
As per Claim 11, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 9, wherein searching the historical order-label database comprises: Boloor also discloses comparing, by the system, the global vector representation of the new medical order to the respective historical global vector representations of historical medical orders, thereby yielding respective global similarity scores for historical medical orders in column 1 lines 25-45, column 5 lines 16-column 6 lines 8, column 9 lines 55-62, column 10 lines 1-21, column 11 lines 22-49 (compares, using latent semantic analysis, the terms of the query medication orders (synonymous to the one or more global vector representations of the new medical order) to the terms in the semantically analyzed medication orders (synonymous to the one or more past global vector representations of each respective one of the plurality of past medical orders), yielding textual match scores or a LSA similarity score (synonymous to global similarity scores) for each of the semantically analyzed medication orders (Examiner notes that latent semantic analysis compares topics as the occur in the corpus of the EMR, which indicates a comparison of global vector representations)); and comparing, by the system, the group of local vector representations of the new medical order to the respective groups of historical local vector representations of the historical medical orders, thereby yielding a respective group of local similarity scores for the historical medical orders in column 1 lines 25-45, column 5 lines 16-column 6 lines 8, column 9 lines 55-67, column 11 lines 22-49 (compares, using string matching technique, the terms of the query medication orders (synonymous to the set of local vector representations of the new medical order) to the terms in the semantically analyzed medication orders (synonymous to the set of past local vector representations of each respective one of the plurality of past medical orders), yielding medical relationship strength of the passages scores (synonymous to a set of local similarity scores) for each of the semantically analyzed medication orders (Examiner notes that string matching terms in the medication records indicates comparing local vector representations)).
As per Claim 12, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 11, wherein searching the historical order-label database further comprises: Boloor also discloses for each of the historical medical orders: aggregating, by the system, the global similarity scores and the group of local similarity scores for historical medical order, thereby yielding an aggregate similarity score for the historical medical order in column 6 lines 9-31 and column 11 line 50-column 12 line 12 (aggregates the textual match scores and the medical relationship strength of passages scores for each of the semantically analyzed medication orders, generating an aggregate score (synonymous to an aggregate similarity score) for each one of the semantically analyzed medication orders); and comparing, by the system, the aggregate similarity score for the historical medical order to the matching criterion in column 6 lines 9-31 and column 11 line 50-column 12 line 12 (comparing the aggregate score for the semantically analyzed medication order to the threshold).
As per Claim 13, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 12, further comprising: Boloor also discloses inserting, by the system, the new medical order, the global vector representation of the new medical order, the group of local vector representations of the new medical order, and the new classification label of the new medical order into the historical order-label database in column 4 line 60-column 5 line 15 and column 8 line 67-column 9 line 3 (stores the query medication order and the tag as a new entry in the EMR for subsequent searching (Examiner notes that the query medication order includes the global vector representations and the set of local vector representations in order perform another deep semantic search)).
As per Claim 14, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 9.
Boloor and Difeng do not disclose the following limitations. However, Cohen-Solal discloses wherein the medical device comprises a medical imaging scanner, and wherein the medical protocol comprises an imaging protocol for the medical imaging scanner in paragraphs [0003-0004] and [0031] and [0043] and [0047] (an imaging modality (synonymous to a medical imaging scanner), wherein the protocol includes an imaging protocol for the imaging modality), and wherein controlling the medical device to perform the medical action comprises controlling the medical imaging scanner to scan the medical patient according to the imaging protocol in paragraphs [0005-0007] and [0080-0081] (controlling the imaging modality to scan the patient according to the imaging protocol).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a method that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined the controlling a medical device, wherein the medical device is a medical imaging scanner to perform the medical action on the patient using a protocol, wherein the protocol is an imaging protocol for the medical imaging scanner based on the new classification label, as disclosed by Cohen-Solal, for the purpose of minimizing errors in patient handling, protocol choice and adaption [0002-0009].
As per Claim 17, Boloor discloses a computer program product for facilitating global and local search-based classification of text, the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by at least one processor of a system to cause the at least one processor in column 12 lines 13-18 (a computer program product including a computer readable storage medium having computer readable program instructions, executable by a processor of a system) to: access a new medical order associated with a medical patient, wherein the new medical order was created by a medical professional attending to the medical patient, and the new medical order comprises information describing a medical action to be performed with respect to the medical patient in column 4 line 60-column 5 line 15 and column 6 lines 9-41 (access a query medication order (synonymous to a new medical order) created by a medical professional attending to the patient, and the query medication order includes prescription medications (Examiner notes that prescription medications indicates medical action to be performed to the patient)); assign a new classification label to the new medical order, based on searching a historical order-label database comprising historical medical orders using both the global vector representation and the group of local vector representations for at least one historical medical order that matches the new medical order according to a matching criterion in column 4 line 60-column 5 line 15, column 6 lines 9-41, column 7 lines 12-42, column 9 lines 44-62, and column 11 line 50-column 12 line 12 (identifies semantically relevant information, referred to as tags, (synonymous to a new classification label) for the query medication order (synonymous to the new medical order), based on a deep semantic searching the EMR (synonymous to a historical order-label database) for the semantically analyzed medication order that corresponds to the query medication order according to the semantically analyzed medication order having an aggregate score above a threshold (synonymous to a matching criterion) (Examiner notes that according to "Global and Local Information Adjustment for Semantic Similarity Evaluation", performing a deep sematic search of the medication orders indicates using the global vector representations and the set of local vector representation to perform the search)), wherein the historical order-label database further comprises, for each of the historical medical orders in column 4 lines 25-53 and column 5 lines 16-34 and column 11 lines 22-49 (the EMR includes semantically analyzed medication orders): a historical global vector representation associated with the historical medical order in column 5 lines 16-column 6 lines 8, column 9 lines 55-62, column 10 lines 1-21, column 11 lines 22-49 (the terms in the semantically analyzed medication orders mapped using latent semantic analysis (synonymous to a historical global vector representations of each respective one of the plurality of past medical orders) (Examiner notes that latent semantic analysis compares topics as the occur in the corpus of the EMR, which indicates a comparison of global vector representations)), a group of historical local vector representations associated with the historical medical order in column 5 lines 16-column 6 lines 8, column 9 lines 55-67, column 11 lines 22-49 (the terms in the semantically analyzed medication orders mapped using a string matching technique (synonymous to a group of historical local vector representations of each respective one of the plurality of past medical orders)), and a historical label associated with historical medical order in column 7 lines 12-42, (a plurality of tagged annotations (synonymous to a historical classification labels) corresponding to the semantically analyzed medication orders).
Boloor discloses global and local vector representations, but Boloor does not disclose generating the global and local vector representations according to levels of granularity using a vectorizer. However, Difeng discloses generate, using a vectorizer, a global vector representation based on an entirety of the new medical order according to a first level of textual granularity, wherein the vectorizer comprises at least one of anon-machine learning vectorizer or an encoder of a machine learning model in the 2nd-4th paragraphs under the "Our approach and contributions" on page 3712 and Figure 2 and 2nd paragraph under "3 Proposed Model" on page 3713 (generates, using a GLRE (synonymous to a vectorizer), global representations or coarse-grained semantic features (synonymous to a global vector representation based on an entirety of the new medical order according to a first level of textual granularity), wherein the GLRE is pre-trained language model BERT (Examiner notes that the BERT model is an encoder of a machine learning model)); partition the information in the new medical order into distinct textual sections, wherein each distinct textual section is less than the entirety of the new medical order in the 2nd paragraph under "3 Proposed Model" and "3.1 Encoding Layer" on page 3713 (encoding a long document sequentially in form of short paragraphs (synonymous to partitions the information in the new medical order into distinct textual sections) (Examiner notes that short paragraphs are distinct textual sections that are less than the entirety of the new medical order)); generate, using the vectorizer, respective local vector representations for at least one of ones of the distinct textual sections according to a third level of textual granularity or combinations of the distinct textual sections according to a second level of textual granularity, thereby yielding a group of local vector representations of the new medical order, wherein the combinations of the distinct textual sections are respectively less that the entirety of the new medical order, wherein the second level of textual granularity is finer than the first level of textual granularity, and the third level of textual granularity is finer than the second level of textual granularity in the 2nd-4th paragraphs under the "Our approach and contributions" on page 3712 and Figure 2 and "3.1 Encoding Layer" on page 3713 (generates, using the GLRE, respective local representations or fine-grained semantic features for one of the short paragraphs (synonymous to local vector representations according to a finer level of textual granularity)).
It would have been obvious to one of ordinary still in the art to include in the computer program product for facilitating global and local search-based classification of text of Boloor with the generating global and local vector representations according to levels of granularity using a vectorizer as taught by Difeng since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately. One of ordinary skill in the art would have recognized that the results of the combination were predictably a method that accesses a new medical order associated with a medical patient, generate global and local vector representations according to levels of granularity using a vectorizer, label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label.
Boloor and Difeng do not disclose the following limitations. However, Cohen-Solal discloses and control a medical device to perform the medical action on the medical patient using a medical protocol selected from a group of medical protocols associated with the medical device based on the new classification label in paragraphs [0003-0004] and [0031] and [0043] and [0047] (controlling an imaging modality (synonymous to a medical imaging scanner) to perform the imaging protocol for the imaging modality based on the classifier (synonymous to the new classification label)).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of computer program product for facilitating global and local search-based classification of text, as disclosed by Boloor and Difeng, to be combined with controlling a medical device to perform the medical action on the patient using a protocol based on the new classification label, as disclosed by Cohen-Solal, for the purpose of minimizing errors in patient handling, protocol choice and adaption [0002-0009].
As per Claim 18, Boloor, Difeng, and Cohen-Solal discloses the computer program product of claim 17, wherein searching the historical document-label database comprises: Boloor also discloses comparing the global vector representation of the new medical order to the respective historical global vector representations of the historical medical orders, thereby yielding respective global similarity scores for the historical medical orders in column 1 lines 25-45, column 5 lines 16-column 6 lines 8, column 9 lines 55-62, column 10 lines 1-21, column 11 lines 22-49 (compares, using latent semantic analysis, the terms of the query medication orders (synonymous to the one or more global vector representations of the new medical order) to the terms in the semantically analyzed medication orders (synonymous to the one or more past global vector representations of each respective one of the plurality of past medical orders), yielding textual match scores or a LSA similarity score (synonymous to global similarity scores) for each of the semantically analyzed medication orders (Examiner notes that latent semantic analysis compares topics as the occur in the corpus of the EMR, which indicates a comparison of global vector representations)); and comparing the group of local vector representations of the new medical order to the respective groups of historical local vector representations of the historical medical orders, thereby yielding a respective group of local similarity scores for the historical medical orders in column 1 lines 25-45, column 5 lines 16-column 6 lines 8, column 9 lines 55-67, column 11 lines 22-49 (compares, using string matching technique, the terms of the query medication orders (synonymous to the set of local vector representations of the new medical order) to the terms in the semantically analyzed medication orders (synonymous to the set of past local vector representations of each respective one of the plurality of past medical orders), yielding medical relationship strength of the passages scores (synonymous to a set of local similarity scores) for each of the semantically analyzed medication orders (Examiner notes that string matching terms in the medication records indicates comparing local vector representations)).
As per Claim 19, Boloor, Difeng, and Cohen-Solal discloses the computer program product of claim 18, wherein searching the historical order-label database further comprises: Boloor also discloses aggregating the global similarity scores and the group of local similarity scores for historical medical orders, thereby yielding an aggregate similarity score for the historical medical order in column 6 lines 9-31 and column 11 line 50-column 12 line 12 (aggregates the textual match scores and the medical relationship strength of passages scores for each of the semantically analyzed medication orders, generating an aggregate score (synonymous to an aggregate similarity score) for each one of the semantically analyzed medication orders); and comparing the aggregate similarity score for the historical medical order to the matching criterion in column 6 lines 9-31 and column 11 line 50-column 12 line 12 (comparing the aggregate score for the semantically analyzed medication order to the threshold).
As per Claim 20, Boloor, Difeng, and Cohen-Solal discloses the computer program product of claim 17, wherein the program instructions are further executable to cause the at least one processor to: Boloor also discloses insert the new medical order, the global vector representation of the new medical order, the group of local vector representations of the new medical order, and the new classification label of the new medical order into the historical order-label database in column 4 line 60-column 5 line 15 and column 8 line 67-column 9 line 3 (stores the query medication order and the tag as a new entry in the EMR for subsequent searching (Examiner notes that the query medication order includes the global vector representations and the set of local vector representations in order perform another deep semantic search)).
Claims 2 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Boloor et al. (US-9690861-B2)[hereinafter Boloor], in view of Difeng et al. (“Global-to-Local Neural Networks for Document-Level Relation Extraction”)[hereinafter Difeng], in view of Cohen-Solal (US-20130311472-A1)[hereinafter Cohen-Solal], in view of Kalogeratos (“Text document clustering using global term context vectors”)[hereinafter Kalogeratos].
As per Claim 2, Boloor, Difeng, and Cohen-Solal discloses the system of claim 1.
Boloor, Difeng, and Cohen-Solal do not disclose the following limitations. However, Kalogeratos discloses wherein the non-machine learning vectorizer comprises at least one of a term-frequency-inverse-domain-frequency vectorizer, a one-hot encoding vectorizer, a count vectorizer, a bag-of-words vectorizer, or an n- grams vectorizer in the 3rd paragraph of the Introduction on page 456 (the vector space model includes a bag of words model (synonymous to a bag of words vectorizer) (Examiner notes that the bag of words model meets the "at least one of" limitations)).
Since each individual element and its function are shown in the prior art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself- that is in the substitution of the vectorizer including non-machine learning vectorizer of the Kalogeratos for the vectorizer including an encoder of a machine learning model of the combination of Boloor, Difeng, and Cohen-Solal. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious.
As per Claim 10, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 9.
Boloor, Difeng, and Cohen-Solal do not disclose the following limitations. However, Kalogeratos discloses wherein the non-machine learning vectorizer comprises at least one of a term-frequency-inverse-domain- frequency vectorizer, a one-hot encoding vectorizer, a count vectorizer, a bag-of-words vectorizer, or an n-grams vectorizer in the 3rd paragraph of the Introduction on page 456 (the vector space model includes a bag of words model (synonymous to a bag of words vectorizer) (Examiner notes that the bag of words model meets the "at least one of" limitations)).
Since each individual element and its function are shown in the prior art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself- that is in the substitution of the vectorizer including non-machine learning vectorizer of the Kalogeratos for the vectorizer including an encoder of a machine learning model of the combination of Boloor, Difeng, and Cohen-Solal. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious.
Claims 7 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Boloor et al. (US-9690861-B2)[hereinafter Boloor], in view of Difeng et al. (“Global-to-Local Neural Networks for Document-Level Relation Extraction”)[hereinafter Difeng], in view of Cohen-Solal (US-20130311472-A1)[hereinafter Cohen-Solal], in view of Neumann (US-20230360795-A1)[hereinafter Neumann].
As per Claim 7, Boloor, Difeng, and Cohen-Solal discloses the system of claim 1.
Boloor, Difeng, and Cohen-Solal do not disclose the following limitations. However, Neumann discloses wherein the medical device comprises a medication dispenser, and wherein an airway or blood vessel of the medical patient is coupled to a tank of the medication dispenser containing a fluidic medication, wherein the medical protocol comprises a medication dispensing protocol in paragraphs [0015] and [0088-0089] (a blood vessel of the patient is coupled to an analgesia pump (synonymous to a tank of a medication dispenser containing a fluidic medication), wherein the instruction set of the antidotal therapeutic provision includes the dosage (synonymous to a medication dispensing protocol)), and wherein controlling the medical device to perform the medical action comprises controlling the medication dispenser to cause a pump of the tank to dispense the fluidic medication to the airway or blood vessel of the medical patient in accordance with the medication dispensing protocol in paragraphs [0089] and [0118-0120] (controlling the analgesia pump to dispense the fluidic medication to the blood vessel of the patient in accordance to the dosage).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a system that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined with controlling a medical device, wherein the medical device is a medical dispenser wherein the airway or blood vessel of the patient is coupled to the tank of the medication dispenser to perform the medical action on the patient using a protocol, wherein the protocol is a medication dispensing protocol for the medication dispenser based on the new classification label, as disclosed by Neumann, for the purpose of providing therapeutic provisions that are better tolerated and provide superior results [0003].
As per Claim 15, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 9.
Boloor, Difeng, and Cohen-Solal do not disclose the following limitations. However, Neumann discloses wherein the medical device comprises a medication dispenser, and wherein an airway or blood vessel of the medical patient is coupled to a tank of the medication dispenser containing a fluidic medication, wherein the medical protocol comprises a medication dispensing protocol in paragraphs [0015] and [0088-0089] (a blood vessel of the patient is coupled to an analgesia pump (synonymous to a tank of a medication dispenser containing a fluidic medication), wherein the instruction set of the antidotal therapeutic provision includes the dosage (synonymous to a medication dispensing protocol)), and wherein controlling the medical device to perform the medical action comprises controlling a pump of the tank to dispense the fluidic medication to the airway or blood vessel of the medical patient in accordance with the medication dispensing protocol in paragraphs [0089] and [0118-0120] (controlling the analgesia pump to dispense the fluidic medication to the blood vessel of the patient in accordance to the dosage).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a method that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined with controlling a medical device, wherein the medical device is a medical dispenser wherein the airway or blood vessel of the patient is coupled to the tank of the medication dispenser to perform the medical action on the patient using a protocol, wherein the protocol is a medication dispensing protocol for the medication dispenser based on the new classification label, as disclosed by Neumann, for the purpose of providing therapeutic provisions that are better tolerated and provide superior results [0003].
Claims 8 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Boloor et al. (US-9690861-B2)[hereinafter Boloor], in view of Difeng et al. (“Global-to-Local Neural Networks for Document-Level Relation Extraction”)[hereinafter Difeng], in view of Cohen-Solal (US-20130311472-A1)[hereinafter Cohen-Solal], in view of Liu et al. (US-20230316545-A1)[hereinafter Liu].
As per Claim 8, Boloor, Difeng, and Cohen-Solal discloses the system of claim 1.
Boloor, Difeng, and Cohen-Solal do not disclose the following limitations. However, Liu discloses wherein the medical device comprises a robotic surgery apparatus in paragraphs [0082] and [0087] and [0123-0124] and [0158-0163] (robotic surgical system), wherein the medical protocol comprises a surgical protocol in paragraphs [0123-0124] (a surgical operation), and wherein controlling the medical device to perform the medical action comprises controlling the robotic surgery apparatus to perform the surgical protocol on the medical patient in paragraphs [0123-0124] and [0158-0163] and [0254] (controlling the robotic surgical system to perform the surgical operation on the patient).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a system that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined with controlling a medical device, wherein the medical device is a robotic surgery apparatus, wherein the protocol is a surgical protocol based on the new classification label, as disclosed by Liu, for the purpose of facilitating an analysis when available data is limited or incomplete [0004-0005].
As per Claim 16, Boloor, Difeng, and Cohen-Solal discloses the computer-implemented method of claim 9.
Boloor, Difeng, and Cohen-Solal do not disclose the following limitations. However, Liu discloses wherein the medical device comprises a robotic surgery apparatus in paragraphs [0082] and [0087] and [0123-0124] and [0158-0163] (robotic surgical system), wherein the medical protocol comprises a surgical protocol in paragraphs [0123-0124] (a surgical operation), and wherein controlling the medical device to perform the medical action comprises controlling the robotic surgery apparatus to perform the surgical protocol on the medical patient in paragraphs [0123-0124] and [0158-0163] and [0254] (controlling the robotic surgical system to perform the surgical operation on the patient).
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention of a method that accesses a new medical order associated with a medical patient, assigns a new classification label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, as disclosed by Boloor and Difeng, to be combined with controlling a medical device, wherein the medical device is a robotic surgery apparatus, wherein the protocol is a surgical protocol based on the new classification label, as disclosed by Liu, for the purpose of facilitating an analysis when available data is limited or incomplete [0004-0005].
Response to Arguments
Applicant's arguments, see Pages 12-22, “Rejection of Claims 1-20 under 35 U.S.C. § 101” filed 12/17/2025 with respect to claims 1, 9, and 17 have been fully considered but they are not persuasive.
Regarding remarks directed to Ex parte Desjardins, Appeal 2024-000567 (Review Panel of the PTAB, Sept. 26, 2025), Examiner submits that PTAB Decisions of other applications are not legally binding on the instant claims. PTAB decisions are particular to the facts of each individual case, and each case is evaluated individually on its own merits. These remarks are not persuasive.
Applicant argues that the amended claim limitations do not recite a judicial exception. Examiner respectfully disagrees. The amended claim limitations are directed to document classification. The limitations merely recite accessing a new medical order associated with a medical patient, generating global and local vector representations, partitioning the information in the new medical order into distinct textual sections, and assigning a new classification label to the new medical order, which are activities performed by medical staff, which falls into the abstract grouping of certain methods of organizing human activity because it is the business relations of medical staff and patients. Additionally, the claim limitations involve managing personal behaviors or interactions between people.
Applicant argues that the amended claim limitations integrates the judicial exception into a practical application by providing a technical improvement to semantic representation and search to reduce protocol-selection errors at the machine level. Examiner respectfully disagrees. The claims do not recite an improvement to semantic representation and search technology. The claims merely recite accessing a new medical order associated with a medical patient, generating global and local vector representations, partitioning the information in the new medical order into distinct textual sections, and assigning a new classification label to the new medical order, which are a part of the abstract idea. An improvement to the abstract ideas of accessing a new medical order associated with a medical patient, generating global and local vector representations, partitioning the information in the new medical order into distinct textual sections, and assigning a new classification label to the new medical order does not amount to an improvement to technology or a technical field (see MPEP § 2106.05(a)(II) stating “it is important to keep in mind that an improvement in the abstract idea itself (e.g. a recited fundamental economic concept) is not an improvement in technology."). The courts indicated in TLI Communications, 823 F.3d at 612-13, 118 USPQ2d at 1747-48, that gathering and analyzing information using conventional techniques and providing the output is not sufficient to show an improvement to technology. The claim language and instant application fails to provide details regarding how a computer aids the method, the extent to which the computer aids the method, or the significance of a computer to the performance of the method. Here, the improvement is to accessing a new medical order associated with a medical patient, generating global and local vector representations, partitioning the information in the new medical order into distinct textual sections, and assigning a new classification label to the new medical order . There is no indication in the disclosure that the involvement of a computer assists in improving the technology for the outlined problem statement. Merely adding generic computer components to perform the method is not sufficient.
Applicant argues that the amended claim limitations recites an inventive concept that amounts to significantly more than any alleged abstract idea. Examiner respectfully disagrees. The amended claim limitations are directed to accessing a new medical order associated with a medical patient, generating global and local vector representations, partitioning the information in the new medical order into distinct textual sections, and assigning a new classification label to the new medical order. The use of the memory configured to store computer-executable components, processor that executes at least one of the computer-executable components, the vectorizer comprises at least one of a non-machine learning vectorizer or an encoder of a machine learning model, historical order-label database, controls a medical device, the non-machine learning vector comprises at least one of a term-frequency-inverse-domain-frequency vectorizer, a one-hot encoding vectorizer, a count vectorizer, a bag-of-words vectorizer, or an n- grams vectorizer, medical imaging scanner, medication dispenser, robotic surgery apparatus, system comprising at least one processor, computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by at least one processor of a system to cause the at least one processor to carry out the steps of the abstract idea is merely applying the abstract idea to general purpose computer components which amounts to mere instructions to apply the exceptions, see MPEP 2106.05(f)(2). The courts indicated in Alice Corp., 573 U.S. at 225-26, 110 USPQ2d at 1984, that “a limitation indicating that a particular function such as creating and maintaining electronic records is performed by a computer” is not enough to qualify as significantly more.
Applicant’s arguments, see Pages 22-36, “Rejection of Claims 1-5 and 9-13 under 35 U.S.C. § 103”, filed 12/17/2025 with respect to claims 1-20 have been fully considered.
With regards to Claims 1-5 and 9-13, Applicant argues that Xia and Boloor alone or in combination do not disclose, teach, or suggest the amended limitations in the claims. Examiner finds this persuasive. Therefore, the rejection of 10/02/2025 has been withdrawn. However, upon further consideration a new grounds of rejection is made over Boloor in view Difeng, in view of Cohen-Solal. In response to the argument that Boloor does not teach the amended limitations of the claims, Examiner respectfully disagrees. Examiner notes that Boloor discloses in column 7 lines 12-42 and column 11 line 50-column 12 line 12 that the query medication order is identified by a tag (synonymous to a new classification label) based on a deep semantic search in the EMR (synonymous to a historical order-label database) for the semantically analyzed medication order (synonymous to a historical medical order) with an aggregate score above a threshold, which indicates the semantically analyzed medication order that matches the query medication order according to a matching criterion. In response to the argument that a prima facie case of obviousness was failed to be established, Examiner respectfully disagrees. It would have been obvious to one of ordinary still in the art to include in the computer program product for facilitating global and local search-based classification of text of Boloor with the generating global and local vector representations according to levels of granularity using a vectorizer as taught by Difeng, with the controlling a medical device to perform the medical action on the patient using a protocol based on the new classification label as taught by Cohen-Solal since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately. One of ordinary skill in the art would have recognized that the results of the combination were predictably a system and method that accesses a new medical order associated with a medical patient, generate global and local vector representations according to levels of granularity using a vectorizer, label to the new medical order based on searching a historical order-label database which includes historical medical orders, historical global and local vector representations, and a historical label, and controls a medical device to perform the medical action on the patient using a protocol based on the new classification label. With regards to Claims 17-20, Applicant argues that Subraveti and Sacaleanu, alone or in combination, do not disclose, teach or suggest the amended claim limitations. Examiner finds this persuasive. Therefore, the rejection of 10/02/2025 has been withdrawn. However, upon further consideration a new grounds of rejection is made over Boloor in view Difeng, in view of Cohen-Solal.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Dani Yogatama et al., “Embedding Methods for Fine Grained Entity Type Classification” (2015) teaches type classifications based on label embeddings.
Li, Q.-Y., Tang, B.-H., Wu, Y.-E., Yao, B.-F., Zhang, W., Zheng, Y., Zhou, Y., van den Anker, J., Hao, G.-X. and Zhao, W. (2023), Machine Learning: A New Approach for Dose Individualization teaches classifiers that label dosages.
THIS ACTION IS MADE FINAL. 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 KRYSTEN N WRIGHT whose telephone number is (571)272-5116. The examiner can normally be reached Monday thru Friday 8 - 5 pm, ET.
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, Fonya Long can be reached on (571)270-5096. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/K.N.W./Examiner, Art Unit 3682
/FONYA M LONG/Supervisory Patent Examiner, Art Unit 3682