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 .
DETAILED ACTION
This office action is in response to Applicant’s submission filed on 2/16/2024. Claims 1-20 are pending of which claims 1, 14 and 17 are independent. As such, claims 1-20 have been examined.
Claim Objections
Claim 7 is objected to because of the following informalities: in line 5, “text the summary” should read “text from the summary”.
Claim 15 is objected to because of the following informalities: in lines 3-4, “a suggested edit to replace the summarized phrase with based on” should read “a suggested edit with which to replace the summarized phrase, based on”.
Claim 20 is objected to because of the following informalities: in line 7, “candidate phrase by a user of the machine learning model” should read “candidate phrase by a user for the machine learning model”.
Appropriate correction is required.
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.
Claim 16, 18, and 20 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.
Regarding claim 16 and 20, it is not clear what “higher level” is being reference to.
Regarding claim 18, the phrase "substantially" renders the claim(s) indefinite because the claim(s) include(s) elements not actually disclosed (those encompassed by "substantially"), thereby rendering the scope of the claim(s) unascertainable. See MPEP § 2173.05(d).
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 an abstract idea without significantly more.
Claim 1 recites a method that, under the broadest reasonable interpretation, claims limitations that cover performance of the limitations in the human mind with the assistance of physical aids (e.g., pen and paper), but for the recitation of generic or well-known or conventional computer components. That is, other than reciting “graphical user interface, and a machine learning model” nothing in these claim limitations precludes the steps from practically being performed in the mind. As a whole, claim 1 pertains to content editing, which is a mental process that a human can do. Individually, each of the limitations also pertains to a mental process, for example:
providing a review graphical user interface (GUI) including an analysis output, generated by a machine learning model, of a natural language conversation, the analysis output including a transcript and a summary of the natural language conversation based on the transcript; (e.g., a human can input a transcript into a generative transformer model or large language model and receive an output that includes the transcript and a summary of the conversation.)
identifying a first candidate phrase and a second candidate phrase in the analysis output; (e.g., the human can identify candidate phrases from the analysis output.)
emphasizing the first candidate phrase in the review GUI; (e.g., the human can highlight, circle or bold or underline a first candidate phrase.)
in response to receiving a review action in relation to the first candidate phrase: deemphasizing the first candidate phrase; (e.g., the human removes the highlighting of the first candidate phrase after receiving a review action.)
and emphasizing the second candidate phrase in the review GUI. (e.g., the human can emphasize the second candidate phrase instead by circling, or bolding or underline it.)
The judicial exception is not integrated into a practical application. In particular, the claims only recites generic computing components. Such generic computing components are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of receiving, determining, or outputting information) such that they amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Claim 1 does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional limitations of using generic computer components amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. Claim 1 is not patent eligible.
The examiner further notes that the use of claimed generic computer components (“a user interface”) invokes such generic computer components “merely as a tool to perform an existing process”. MPEP 2106.05(f). MPEP 2106.05(f) further explains:
Use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Similarly, "claiming the improved speed or efficiency inherent with applying the abstract idea on a computer" does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015).
Claim 1 recites generic computer components (“graphical user interface, and a machine learning model”), with respect to performing tasks. MPEP 2106.05(d) and (f) further provides examples of court decisions where the courts found generic computing components to be mere instructions to apply a judicial exception, and further explains “increased speed” (e.g., using a computer to increase the speed of an otherwise mental process) does not provide an inventive concept. For example:
A commonplace business method or mathematical algorithm being applied on a general purpose computer, Alice Corp. Pty. Ltd. V. CLS Bank Int’l, 573 U.S. 208, 223, 110 USPQ2d 1976, 1983 (2014); Gottschalk v. Benson, 409 U.S. 63, 64, 175 USPQ 673, 674 (1972); Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
A process for monitoring audit log data that is executed on a general-purpose computer where the increased speed in the process comes solely from the capabilities of the general-purpose computer, FairWarning IP, LLC v. Iatric Sys., 839 F.3d 1089, 1095, 120 USPQ2d 1293, 1296 (Fed. Cir. 2016) (emphasis added).
Performing repetitive calculations. Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012) ("The computer required by some of Bancorp’s claims is employed only for its most basic function, the performance of repetitive calculations, and as such does not impose meaningful limits on the scope of those claims.")
Claim 14 recites a method that corresponds a variation that is similar to the method of claim 1 and is therefore rejected under the same grounds as claim 1 above. While claim 14 further recites “querying the machine learning model for a first summarized phrase in the summary corresponding to the first candidate phrase and a second summarized phrase in the summary corresponding to the second candidate phrase;”, this corresponds to the human querying the machine learning model for an output that includes also a first and second summarized phrase corresponding to the first and second candidate phrase respectively. The only other slight difference here the first summarized phrase is also initial emphasized and then subsequently deemphasized along with the first candidate phrase and the second summarized phase and the second candidate phase are emphasized instead. Again, these are steps that human can practically performed.
Therefore, none of these limitations (a) integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea or (b) amount to significantly more than the judicial exception, because in either case the additional limitations merely utilize generic computer components that amounts to no more than mere instructions to apply the exception using generic computer function. Claim 14 is not patent eligible.
Claim 17 recites a method that corresponds variation that is similar to the method of claim 1 and is therefore rejected under the same grounds as claim 1 above. While claim 17 further recites “querying the machine learning model for a first supporting phrase in the transcript on which the first candidate phrase is based and a second supporting phrase in the transcript on which the second candidate phrase is based;”, this corresponds to the human querying the machine learning model for an output that includes also a first and second support phrase corresponding to the first and second candidate phrase respectively. The only other slight difference here the first support phrase is also initial emphasized and then subsequently deemphasized along with the first candidate phrase and the second support phase and the second candidate phase are emphasized instead. Again, these are steps that human can practically performed.
Therefore, none of these limitations (a) integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea or (b) amount to significantly more than the judicial exception, because in either case the additional limitations merely utilize generic computer components that amounts to no more than mere instructions to apply the exception using generic computer function. Claim 17 is not patent eligible.
Claims 2-13, 15-16, and 18-20 depend from independent claims 1, 14 and 17, do not remedy any of the deficiencies of claims 1 and 11, and therefore are rejected on the same grounds as claim 1, 14 and 17 from above.
Claim 2 further recites: wherein the review action marks the first candidate phrase as correct without replacing the first candidate phrase with an alternative. (e.g., the human can review and determine the first candidate phrase as correct.)
Claim 3 further recite: wherein the review action marks the first candidate phrase as incorrect, the method further comprising: receiving a replacement phrase for the first candidate phrase; (e.g., the human can review and determine the first candidate phrase is wrong, the receive a replacement or substitute phrase for the first candidate phrase.)
and deemphasizing the first candidate phrase by replacing the first candidate phrase with the replacement phrase in an un-emphasized format. (e.g., the human can replace with first candidate phrase with the replacement phase and not place any emphasis on the phrase.)
Claim 4 further recites: identifying a third candidate phrase in response to replacing the first candidate phrase with the replacement phrase; (e.g., the human can identify a third candidate phrase in response to substitution replacement of the first candidate phrase.)
before emphasizing the second candidate phrase: emphasizing the third candidate phrase in the review GUI; (e.g., the human can emphasize the third candidate phrase prior to emphasize the second candidate phrase.)
in response to receiving a second review action in relation to the third candidate phrase: deemphasizing the third candidate phrase; and emphasizing the second candidate phrase. (e.g., the human can deemphasize the third candidate phrase in response to receiving a second review action, then emphasize the second candidate phrase.)
Claim 5, further recites: wherein the first candidate phrase is included in a first one of the transcript and the summary and the second candidate phrase is included in a second one of the transcript and the summary. (e.g., the human can determine that the first and second candidate phrases are included in the first and second transcripts and the summaries respectively.)
Claim 6, further recites: wherein the first candidate phrase is included in the summary and emphasizing the first candidate phrase in the review GUI further comprises: querying the machine learning model for supporting phrases in the transcript to support initial selection of the first candidate phrase for inclusion in the analysis output; (e.g., the human can query the machine learning model for supporting phrases in the transcript to support initial selection of the first candidate phrase for inclusion in the analysis output.)
and emphasizing the supporting phrases in the transcript in a different format than the first candidate phrase is emphasized with. (e.g., the human can use different type of emphasis, like using underline for the supporting phrase, and circle the candidate phrase.)
Claim 7, further recites: wherein the first candidate phrase is included in the transcript and emphasizing the first candidate phrase in the review GUI further comprises: querying the machine learning model for associated text in the summary based on the first candidate phrase; (e.g., the human can query the machine learning model for associated text in the summary based on the first candidate phrase.)
and emphasizing the associated text the summary in a different format than the first candidate phrase is emphasized with. (e.g., the human can emphasize the associated text in the summary with underline and circle the first candidate phrase.)
Claim 8, further recites: wherein the first candidate phrase is positioned later in the transcript than the second candidate phrase. (e.g., the human determines where the first candidate phrase is positioned in the transcript in relation to the second candidate phrase.)
Claim 9, further recites: wherein the first candidate phrase is positioned later in the summary than the second candidate phrase. (e.g., the human determines where the first candidate phrase is positioned in the summary in relation to the second candidate phrase.)
Claim 10, further recites: wherein the first candidate phrase is assigned a lower confidence level than the second candidate phrase by the machine learning model when generating the analysis output. (e.g., the human can assign lower confidence score for the first candidate phrase in relation with the second candidate phrase.)
Claim 11 further recites: wherein the first candidate phrase is assigned a higher certainty demand level than the second candidate phrase by a user of the machine learning model for generating the analysis output. (e.g., the human determine that a user has assigned a higher certain demand level to the first candidate phrase in relation to the second candidate phrase.)
Claim 12 further recites: wherein the first candidate phrase is determined by the machine learning model earlier in a sequential pipeline than the second candidate phrase when generating the analysis output. (e.g., the human determines a sequential process, that the first candidate phrase is determined before a second candidate is determined.)
Claim 13 further recites: identifying a third candidate phrase in the analysis output before identifying the first candidate phrase and the second candidate phrase; (e.g., the human identifies a third candidate phrase in the analysis output before identifying the first and second candidate phrase.)
determining an allotted review resource pool; (e.g., the human determines allotted review resource pool, how much time and effort and machine needed.)
and in response to determining that a combination of the first candidate phrase, the second candidate phrase, and the third candidate phrase exceeds the allotted review resource pool: selecting the first candidate phrase and the second candidate phrase for presentation in the review GUI; (e.g., the human determines that time and resource spent on finding the candidate phrase has exceed a threshold, to make a selection for the first and second candidate phrase.)
and discarding the third candidate phrase for review. (e.g., the human can discard the third candidate phrase for review, like skip it.)
Claim 15 further recites: in response to the review action replacing the first candidate phrase with a replacement phrase: requesting, from the machine learning model, a suggested edit to replace the summarized phrase with based on the replacement phrase; (e.g., the human request or query the machine learning model for a suggestion on how to replace the summarized phase.)
and replacing the first summarized phrase with the suggested edit phrase. (e.g., the human replaces the summarized phrase with the suggested edit phrase.)
Claim 16 further recites: wherein the second candidate phrase occurs at an earlier position in the analysis output than the first candidate phrase and is emphasized subsequently to the first candidate phrase based on at least one of: the first candidate phrase being assigned a lower confidence level than the second candidate phrase by the machine learning model when generating the analysis output; (e.g., the human can assigns a lower confidence level to the first candidate phrase relative to the second candidate phrase.)
the first candidate phrase being assigned a higher certainty demand level than the second candidate phrase by a user of the machine learning model for generating the analysis output; (e.g., the human determine that a user has assigned a higher certain demand level to the first candidate phrase in relation to the second candidate phrase.)
and the first candidate phrase being determined by the machine learning model at a higher level in a sequential pipeline than the second candidate phrase when generating the analysis output. (e.g., the human determine that the machine learning model has determine that the first candidate phrase at a higher confidence level in a sequential pipeline than the second candidate phrase.)
Claim 18 further recites: identifying a third candidate phrase in the transcript at substantially the same time as identifying the first candidate phrase and the second candidate phrase. (e.g., the human can determine a third candidate phrase in the transcript at substantially the same time as identifying the first and second candidate phrase.)
Claim 19 further recites: identifying a third candidate phrase in the transcript at substantially the same time as identifying the first candidate phrase and the second candidate phrase. (e.g., the human can determine a third candidate phrase in the transcript at substantially the same time as identifying the first and second candidate phrase.)
Claim 20 further recites: wherein the second candidate phrase occurs at an earlier position in the analysis output than the first candidate phrase and is emphasized subsequently to the first candidate phrase based on at least one of: the first candidate phrase being assigned a lower confidence level than the second candidate phrase by the machine learning model when generating the analysis output; (e.g., the human can determine that the first candidate phrase being assigned a lower confidence score relative to the second candidate phrase by the machine learning model.)
the first candidate phrase being assigned a higher certainty demand level than the second candidate phrase by a user of the machine learning model for generating the analysis output; (e.g., the human determine that a user has assigned a higher certain demand level to the first candidate phrase in relation to the second candidate phrase.)
and the first candidate phrase being determined by the machine learning model at a higher level in a sequential pipeline than the second candidate phrase when generating the analysis output. (e.g., the human determine that the machine learning model has determine that the first candidate phrase at a higher confidence level in a sequential pipeline than the second candidate phrase.)
In sum, claims 2-13, 15-16 and 18-20 depend from claim 1, 14 and 17, and further recite mental processes as explained above. None of the additional limitations recited in claims 2-13, 15-16 and 18-20 amount to anything more than the same or a similar abstract idea as recited in claim 1, 14 and 17 respectively. Nor do any limitations in claims 2-13, 15-16 and 18-20: (a) integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea or (b) amount to significantly more than the judicial exception because the additional limitations of using generic computer components amounts to no more than mere instructions to apply the exception using generic computer components. Claims 2-13, 15-16 and 18-20 are not patent eligible.
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, 5, 10 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Stradder (US 20190121532), in view of Hilleli (US 20210099317).
Stradder discloses: A method, comprising: ([0005] The method includes a step of providing on a workstation a tool for rendering an audio recording of the conversation.)
providing a review graphical user interface (GUI) including an analysis output, ([0004] This disclosure relates to an interface (e.g., a display of a workstation used by a provider) for displaying a transcript of a patient-healthcare provider conversation and automated generation of a note or summary of the conversation using machine learning.)
generated by a machine learning model, of a natural language conversation, the analysis output including a transcript and a summary of the natural language conversation based on the transcript; ([0005] The method further includes a step of displaying on a display of the workstation (1) in first transcript region a transcript of the recording in substantial real time with the rendering of the audio recording and simultaneously (2) in a second note region a note summarizing the conversation, the note including automatically extracted words or phrases in the transcript related to medical topics relating to the patient, the extraction of the words or phrase performed with the aid of a trained machine learning model. The medical topics relating to the patient could be such things as symptoms and attributes thereof such as onset, tempo, severity, location, etc., medications, complaints, etc. The method further includes a step of providing links or a mapping between the extracted words or phrases in the note and the portions of the transcript from which the extracted words or phrases originated whereby the source and accuracy of the extracted words or phrases in the note can be verified by a user, for example by selecting one of the extracted words or phrases in the note or by inspection of the note side by side with the transcript with the extracted words or phrases highlighted in both the transcript and the note.)
identifying a first candidate phrase and a second candidate phrase in the analysis output; ([0035-0036] A named entity recognition model 112 is further included which processes the text generated by the speech to text conversion model 110 to recognize medically relevant words or phrases. The result of the application of the named entity recognition model 112 as applied to the text generated by the speech to text conversion model 110 is a highlighted transcript of the audio input 102 with relevant words or phrases highlighted (as recognized by the named entity recognition model) as well as extraction of such highlighted words or text as data for note generation and classification of highlighted words or phrases into different regions or fields of a note as indicated at 114. The application of these models to an audio file and generation of a transcript and note will be explained in detail in subsequent sections of this document.)
emphasizing the first candidate phrase in the review GUI; ([0036] relevant words or phrases highlighted (as recognized by the named entity recognition model)
in response to receiving a review action in relation to the first candidate phrase: deemphasizing the first candidate phrase; ([0079] The user interface shown in the Figures includes the ability to edit the transcript and the note, including the ability accept or reject suggestions for the transcript and note, e.g., when the words are misspoken, the speech is muffled or partially inaudible, or other situations arise when the speech recognition engine is not confident as to the words spoken. In the example of FIG. 19 the patient was asked about the medication and state the name “Lipodrene”, a term not in the vocabulary of the NER model, and the user is presented with two alternatives 1904 and 1906 which may the name of the medication the patient intended to say. The user can select either one or reject them by activating the X icon 1908. Furthermore, the user can change classifications for the suggestions, through moving items to different groupings, changing drop downs, deleting suggestions or adding more context. An example of this was shown in FIG. 4 with the moving of the moving of the extracted phrase “leg hurts” from the symptoms region in the note to the chief complaint region of the note.)
and emphasizing the second candidate phrase in the review GUI. ([0015] FIG. 4 is an illustration of the ability to edit groupings of highlighted medical events or terms in the note.)
Although Stradder disclose emphasizing -highlighting, however it does not explicitly disclose deemphasizing.
Hilleli (in the related field of highlighting actions items in notes from meeting) discloses: deemphasize ([0029] extraneous content not related to the action items or not helpful for user understanding is deemphasized)
Stradder and Hilleli are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder to combine the teaching of Hilleli, because emphasize of phrase or terms can help reader better understand the importance of the content while extraneous content not related to action item or not helpful for user understanding is deemphasized (Hilleli, [0029]).
Regarding Claim 2, Stradder in view of Hilleli discloses all of claim 1,
Stradder further discloses: wherein the review action marks the first candidate phrase as correct without replacing the first candidate phrase with an alternative. ([0045] Furthermore, the audio recording tools on the workstation display include pause, rewind, play, fast forward, etc., so that the user can start and stop the recording to listen to sensitive or important patient information and confirm that the transcript, highlighted words or phrases, and insertion of words or phrases into the note are correct.) Also see para 0011 and 0067.
Regarding Claim 3, Stradder in view of Hilleli discloses all of claim 1,
Stradder further discloses: wherein the review action marks the first candidate phrase as incorrect, the method further comprising: receiving a replacement phrase for the first candidate phrase; ([0016] FIG. 5 is an illustration of features for editing the transcript with smart suggestions of words to replace text in the transcript, as well as editing of the note. [0087] In applicable cases the terminology in the note is adapted to professionally preferred terms. For example, in FIG. 21 the note has replaced “rash” with “dermatitis” and “feeling feverish” with “pyrexia.”)
Hilleli further discloses: and deemphasizing the first candidate phrase by replacing the first candidate phrase with the replacement phrase in an un-emphasized format. ([0029] In this example, for instance, the text that is not the action item is not bolded text, while the text that is the action item is bolded text.)
The rationale for the combination would be similar to the one already provided.
Regarding Claim 5, Stradder in view of Hilleli discloses all of claim 1,
Stradder further discloses: wherein the first candidate phrase is included in a first one of the transcript and the summary and the second candidate phrase is included in a second one of the transcript and the summary. ([0005] The method further includes a step of providing links or a mapping between the extracted words or phrases in the note and the portions of the transcript from which the extracted words or phrases originated whereby the source and accuracy of the extracted words or phrases in the note can be verified by a user, for example by selecting one of the extracted words or phrases in the note or by inspection of the note side by side with the transcript with the extracted words or phrases highlighted in both the transcript and the note.)
Regarding Claim 10, Stradder in view of Hilleli discloses all of claim 1,
Stradder further discloses: wherein the first candidate phrase is assigned a lower confidence level than the second candidate phrase by the machine learning model when generating the analysis output. ([0058] The method and system may also provide for displaying a confidence level for generated suggestions of alternative words or phrases, e.g., as shown in FIG. 5.)
Regarding Claim 12, Stradder in view of Hilleli discloses all of claim 1,
Hilleli further discloses: wherein the first candidate phrase is determined by the machine learning model earlier in a sequential pipeline than the second candidate phrase when generating the analysis output. ([0087] a component may extract or copy the next or succeeding five (or other predetermined number) words after the beginning word or other character sequences and feed them through a DNN to determine if the third (or other predetermined number) word or other character sequences is the action item's end location.) [The reference describes a series of steps: extracting a sequence of words, feeding them into a Deep Neural Network (DNN), and using the DNN to determine a specific word's role within that sequence. This reflects the pipeline structure of a sequential process, where one step occurs after another. The overall process is one of sequential analysis. It builds on previous information (the beginning word) to analyze and label subsequent information (the third word)]
Stradder and Hilleli are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder to combine the teaching of Hilleli, because this would create ability to learn complex patterns and contextual dependencies (Hilleli, [0087]).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Stradder, in view of Hilleli, further in view of Baldwin (US 20190206524), and furthermore in view of Shirani (US 20210133279).
Regarding Claim 6, Stradder in view of Hilleli discloses all of claim 5,
Stradder in view of Hilleli does not explicitly disclose the feature recited below.
Baldwin (in the related field of classifying medically relevant phrase from patient’s EMR) discloses: wherein the first candidate phrase is included in the summary and emphasizing the first candidate phrase in the review GUI further comprises: querying the machine learning model for supporting phrases in the transcript to support initial selection of the first candidate phrase for inclusion in the analysis output; ([0103] natural language request processing engine 340 automatically finds medically relevant phrases utilizing a process that is not dependent on rules but, rather, is linked to anchor medical concepts.)
Stradder/Hilleli/Baldwin are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder and Hilleli to combine the teaching of Baldwin, because the technique disclosed would improve data processing and more specifically to mechanisms for classifying medically relevant phrases from a patient's electronic medical records into relevant categories (Baldwin, [background]).
Stradder/Hilleli/Baldwin does not explicitly disclose the following features.
Shirani (in the related field of text emphasis system) discloses: and emphasizing the supporting phrases in the transcript in a different format than the first candidate phrase is emphasized with. ([0024] the text emphasis system applies different modifications to different words of a text segment based on the label distributions corresponding to those words (e.g., modifies a given word with a relatively high probability for emphasis so that the word is emphasized more than other emphasized words).)
Stradder/Hilleli/Baldwin/Shirani are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder/Hilleli/Baldwin to combine the teaching of Shirani, because the technique disclosed would help guide reader’s attention effectively to identify most relevant information quickly (Shirani, [0024]).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Stradder, in view of Hilleli, further in view of Ahlstrom (US 20220179904), and furthermore in view of Shirani (already of record).
Regarding Claim 7, Stradder in view of Hilleli discloses all of claim 5,
Stradder in view of Hilleli does not explicitly disclose the feature recited below.
Ahlstrom (in the related field of analyzing database content items for improved viewing ability) discloses: wherein the first candidate phrase is included in the transcript and emphasizing the first candidate phrase in the review GUI further comprises: querying the machine learning model for associated text in the summary based on the first candidate phrase; ([0032] the summary model may be trained to identify salient or key terms to include in the summary, based on frequency or importance.)
Stradder/ Hilleli/Alhstrom are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder and Hilleli to combine the teaching of Alhstrom, because the technique disclosed leverage a pretrained model to find text related to a candidate phrase, ensure the summary contains the most relevant information (Alhstrom, [0032]).
Shirani (in the related field of text emphasis system) discloses: and emphasizing the associated text the summary in a different format than the first candidate phrase is emphasized with. ([0024] the text emphasis system applies different modifications to different words of a text segment based on the label distributions corresponding to those words (e.g., modifies a given word with a relatively high probability for emphasis so that the word is emphasized more than other emphasized words).)
Stradder/Hilleli/Ahlstrom/Shirani are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder/Hilleli/Alhstrom to combine the teaching of Shirani, because the technique disclosed would help guide reader’s attention effectively to identify most relevant information quickly (Shirani, [0024]).
Claims 8-9 are rejected under 35 U.S.C. 103 as being unpatentable over Stradder), in view of Hilleli, and further in view of Wang (US 20030229487).
Regarding Claim 8, Stradder in view of Hilleli discloses all of claim 1,
Stradder and Hilleli does not explicitly disclosed the following feature.
Wang (in the related field of language processing) discloses: wherein the first candidate phrase is positioned later in the transcript than the second candidate phrase. ([0017] in the foregoing comparing, one of the predefined conditions is that the identified term corresponding to the another group must appear in the text after an identified term corresponding to the one group.) [This directly states that the another group (first candidate phrase) comes after the one group (second candidate phrase), which what the claim recites.]
Stradder/ Hilleli /Wang are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder/Hilleli to combine the teaching of Wang, because predicting positional relationships between terms can significantly improves the accuracy and relevance of analysis (Wang, [0017]).
Regarding Claim 9, Stradder in view of Hillei discloses all of claim 1,
Stradder and Hilleli does not explicitly disclosed the following feature.
Wang (in the related field of language processing) discloses: wherein the first candidate phrase is positioned later in the summary than the second candidate phrase. ([0017] in the foregoing comparing, one of the predefined conditions is that the identified term corresponding to the another group must appear in the text after an identified term corresponding to the one group.) [This directly states that the another group (first candidate phrase) comes after the one group (second candidate phrase), which what the claim recites.]
Stradder/ Hilleli /Wang are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder/Hilleli to combine the teaching of Wang, because predicting positional relationships between terms can significantly improves the accuracy and relevance of analysis (Wang, [0017]).
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Stradder, in view of Hilleli, and further in view of Rings (US 20210042343).
Regarding Claim 11, Stradder in view of Hilleli discloses all of claim 1,
Stradder further discloses: wherein the first candidate phrase is ([0058] The method and system may also provide for displaying a confidence level for generated suggestions of alternative words or phrases, e.g., as shown in FIG. 5.)
Stradder and Hilleli does not explicitly disclose a user setting certainty demand level.
Rings (in the related field of natural language processing in response document template) discloses: a user certainty demand level ([0030] the degree or level of certainty and actions performed may be configurable by a user and/or one or more components of the document processing system)
Stradder/Hilleli/Rings are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder/Hilleli to combine the teaching of Rings, because configurability allows a user to strike a balance between speed and accuracy based on specific needs and priorities (Rings, [0030]).
Claims 14-16 are rejected under 35 U.S.C. 103 as being unpatentable over Stradder (US 20190121532), in view of Hilleli (US 20210099317), and further in view of Asi (US 20230360640).
Stradder discloses: A method, comprising: ([0005] The method includes a step of providing on a workstation a tool for rendering an audio recording of the conversation.)
providing a review graphical user interface (GUI) including an analysis output, ([0004] This disclosure relates to an interface (e.g., a display of a workstation used by a provider) for displaying a transcript of a patient-healthcare provider conversation and automated generation of a note or summary of the conversation using machine learning.)
generated by a machine learning model, of a natural language conversation, the analysis output including a transcript and a summary of the natural language conversation based on the transcript; ([0005] The method further includes a step of displaying on a display of the workstation (1) in first transcript region a transcript of the recording in substantial real time with the rendering of the audio recording and simultaneously (2) in a second note region a note summarizing the conversation, the note including automatically extracted words or phrases in the transcript related to medical topics relating to the patient, the extraction of the words or phrase performed with the aid of a trained machine learning model. The medical topics relating to the patient could be such things as symptoms and attributes thereof such as onset, tempo, severity, location, etc., medications, complaints, etc. The method further includes a step of providing links or a mapping between the extracted words or phrases in the note and the portions of the transcript from which the extracted words or phrases originated whereby the source and accuracy of the extracted words or phrases in the note can be verified by a user, for example by selecting one of the extracted words or phrases in the note or by inspection of the note side by side with the transcript with the extracted words or phrases highlighted in both the transcript and the note.)
identifying a first candidate phrase and a second candidate phrase in the transcript; ([0035-0036] A named entity recognition model 112 is further included which processes the text generated by the speech to text conversion model 110 to recognize medically relevant words or phrases. The result of the application of the named entity recognition model 112 as applied to the text generated by the speech to text conversion model 110 is a highlighted transcript of the audio input 102 with relevant words or phrases highlighted (as recognized by the named entity recognition model) as well as extraction of such highlighted words or text as data for note generation and classification of highlighted words or phrases into different regions or fields of a note as indicated at 114. The application of these models to an audio file and generation of a transcript and note will be explained in detail in subsequent sections of this document.)
emphasizing the first candidate phrase and the first summarized phrase in the review GUI; ([0036] relevant words or phrases highlighted (as recognized by the named entity recognition model)
in response to receiving a review action in relation to the first candidate phrase: deemphasizing the first candidate phrase and the first summarized phrase; ([0079] The user interface shown in the Figures includes the ability to edit the transcript and the note, including the ability accept or reject suggestions for the transcript and note, e.g., when the words are misspoken, the speech is muffled or partially inaudible, or other situations arise when the speech recognition engine is not confident as to the words spoken. In the example of FIG. 19 the patient was asked about the medication and state the name “Lipodrene”, a term not in the vocabulary of the NER model, and the user is presented with two alternatives 1904 and 1906 which may the name of the medication the patient intended to say. The user can select either one or reject them by activating the X icon 1908. Furthermore, the user can change classifications for the suggestions, through moving items to different groupings, changing drop downs, deleting suggestions or adding more context. An example of this was shown in FIG. 4 with the moving of the moving of the extracted phrase “leg hurts” from the symptoms region in the note to the chief complaint region of the note.)
and emphasizing the second candidate phrase and the second summarized phrase in the review GUI. ([0015] FIG. 4 is an illustration of the ability to edit groupings of highlighted medical events or terms in the note.)
Although Stradder disclose emphasizing -highlighting, however it does not explicitly disclose deemphasizing.
Hilleli (in the related field of highlighting actions items in notes from meeting) discloses: deemphasize ([0029] extraneous content not related to the action items or not helpful for user understanding is deemphasized)
Stradder and Hilleli are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder to combine the teaching of Hilleli, because emphasize of phrase or terms can help reader better understand the importance of the content while extraneous content not related to action item or not helpful for user understanding is deemphasized (Hilleli, [0029]).
Stradder and Hilleli does not explicitly discloses querying the machine learning model for a first summarized phrase in the summary corresponding to the first candidate phrase and a second summarized phrase in the summary corresponding to the second candidate phrase;
Asi (in the related field of creating summary from transcripts) discloses: querying the machine learning model for a first summarized phrase in the summary corresponding to the first candidate phrase and a second summarized phrase in the summary corresponding to the second candidate phrase; ([0061] An example method of generating keyword-based dialogue summaries is provided, the method includes inputting a portion of a transcript of an audio conversation and a predefined keyword into a machine learning model trained based on a first encoding representing the predefined keyword and a second encoding representing text of a portion of a different transcript, generating, by the trained machine learning model, computer-generated text different from and semantically descriptive of at least the portion of the transcript, the computer-generated text semantically associated with the predefined keyword, based on the predefined keyword and the portion of the transcript, and outputting the computer-generated text in association with a selectable item selectable for inclusion of the computer-generated text in displayed text representing the transcript, the selectable item associated with the predefined keyword.) [This explicitly describes the model generating a summary phrase based on the input. Because the output is different from the original text, this represents an abstractive summary, rather than an extractive one. The output summary is based on a keyword and a portion of the transcript, which serves as a candidate phrase or segment of text that the summary is created to cover. The phrase/term “candidate phrase” is not used in the passage, but the concept is the same: the model uses a segment of the transcript to generate its summary.]
Stradder/Hilleli/Asi are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Stradder/Hilleli to combine the teaching of Asi, because the method would generate summaries highly relevant to the specific keyword (Asi, [0061]).
Regarding Claim 15, Stradder in view of Hilleli and Asi discloses all of claim 14,
Stradder further discloses: in response to the review action replacing the first candidate phrase with a replacement phrase: requesting, from the machine learning model, a suggested edit to replace the summarized phrase with based on the replacement phrase; ([0016] FIG. 5 is an illustration of features for editing the transcript with smart suggestions of words to replace text in the transcript, as well as editing of the note. [0087] In applicable cases the terminology in the note is adapted to professionally preferred terms. For example, in FIG. 21 the note has replaced “rash” with “dermatitis” and “feeling feverish” with “pyrexia.”) [same concept could be applied to summary portion instead of the transcript]
and replacing the first summarized phrase with the suggested edit phrase. ([0016] FIG. 5 is an illustration of features for editing the transcript with smart suggestions of words to replace text in the transcript, as well as editing of the note. [0087] In ap